diff options
author | David S. Miller <davem@davemloft.net> | 2018-02-04 16:46:58 -0500 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2018-02-04 16:46:58 -0500 |
commit | a6b88814ab541d386d793f6df260a3e4d5cccb11 (patch) | |
tree | a7c633be819bb450edab3beebd1a9a0cfba8bb72 | |
parent | 35277995e17919ab838beae765f440674e8576eb (diff) | |
parent | 09c0656dfabd0b15e410eca67dc45cb14ec9c13a (diff) | |
download | linux-a6b88814ab541d386d793f6df260a3e4d5cccb11.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf
Alexei Starovoitov says:
====================
pull-request: bpf 2018-02-02
The following pull-request contains BPF updates for your *net* tree.
The main changes are:
1) support XDP attach in libbpf, from Eric.
2) minor fixes, from Daniel, Jakub, Yonghong, Alexei.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
28 files changed, 1716 insertions, 141 deletions
diff --git a/Documentation/bpf/bpf_devel_QA.txt b/Documentation/bpf/bpf_devel_QA.txt index cefef855dea4..84cbb302f2b5 100644 --- a/Documentation/bpf/bpf_devel_QA.txt +++ b/Documentation/bpf/bpf_devel_QA.txt @@ -516,4 +516,35 @@ A: LLVM has a -mcpu selector for the BPF back end in order to allow the By the way, the BPF kernel selftests run with -mcpu=probe for better test coverage. +Q: In some cases clang flag "-target bpf" is used but in other cases the + default clang target, which matches the underlying architecture, is used. + What is the difference and when I should use which? + +A: Although LLVM IR generation and optimization try to stay architecture + independent, "-target <arch>" still has some impact on generated code: + + - BPF program may recursively include header file(s) with file scope + inline assembly codes. The default target can handle this well, + while bpf target may fail if bpf backend assembler does not + understand these assembly codes, which is true in most cases. + + - When compiled without -g, additional elf sections, e.g., + .eh_frame and .rela.eh_frame, may be present in the object file + with default target, but not with bpf target. + + - The default target may turn a C switch statement into a switch table + lookup and jump operation. Since the switch table is placed + in the global readonly section, the bpf program will fail to load. + The bpf target does not support switch table optimization. + The clang option "-fno-jump-tables" can be used to disable + switch table generation. + + You should use default target when: + + - Your program includes a header file, e.g., ptrace.h, which eventually + pulls in some header files containing file scope host assembly codes. + - You can add "-fno-jump-tables" to work around the switch table issue. + + Otherwise, you can use bpf target. + Happy BPF hacking! diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index de73c1ff0939..75c25306d234 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -480,8 +480,7 @@ static int nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) { struct nsim_bpf_bound_map *nmap; - unsigned int i; - int err; + int i, err; if (WARN_ON(offmap->map.map_type != BPF_MAP_TYPE_ARRAY && offmap->map.map_type != BPF_MAP_TYPE_HASH)) @@ -518,7 +517,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) return 0; err_free: - while (--i) { + while (--i >= 0) { kfree(nmap->entry[i].key); kfree(nmap->entry[i].value); } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4c77f39ebd65..5eef6c8e2741 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3228,6 +3228,12 @@ static inline int netif_set_real_num_rx_queues(struct net_device *dev, } #endif +static inline struct netdev_rx_queue * +__netif_get_rx_queue(struct net_device *dev, unsigned int rxq) +{ + return dev->_rx + rxq; +} + #ifdef CONFIG_SYSFS static inline unsigned int get_netdev_rx_queue_index( struct netdev_rx_queue *queue) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 5f35f93dcab2..29ca9208dcfa 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1576,25 +1576,41 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, __u32 __user *prog_ids, u32 cnt) { struct bpf_prog **prog; - u32 i = 0, id; - + unsigned long err = 0; + u32 i = 0, *ids; + bool nospc; + + /* users of this function are doing: + * cnt = bpf_prog_array_length(); + * if (cnt > 0) + * bpf_prog_array_copy_to_user(..., cnt); + * so below kcalloc doesn't need extra cnt > 0 check, but + * bpf_prog_array_length() releases rcu lock and + * prog array could have been swapped with empty or larger array, + * so always copy 'cnt' prog_ids to the user. + * In a rare race the user will see zero prog_ids + */ + ids = kcalloc(cnt, sizeof(u32), GFP_USER); + if (!ids) + return -ENOMEM; rcu_read_lock(); prog = rcu_dereference(progs)->progs; for (; *prog; prog++) { if (*prog == &dummy_bpf_prog.prog) continue; - id = (*prog)->aux->id; - if (copy_to_user(prog_ids + i, &id, sizeof(id))) { - rcu_read_unlock(); - return -EFAULT; - } + ids[i] = (*prog)->aux->id; if (++i == cnt) { prog++; break; } } + nospc = !!(*prog); rcu_read_unlock(); - if (*prog) + err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); + kfree(ids); + if (err) + return -EFAULT; + if (nospc) return -ENOSPC; return 0; } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index a86e6687026e..2ced48662c1f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -151,6 +151,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, { u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; + struct netdev_rx_queue *rxqueue; struct xdp_buff xdp = {}; u32 retval, duration; void *data; @@ -165,6 +166,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, xdp.data_meta = xdp.data; xdp.data_end = xdp.data + size; + rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); + xdp.rxq = &rxqueue->xdp_rxq; + retval = bpf_test_run(prog, &xdp, repeat, &duration); if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN) size = xdp.data_end - xdp.data; diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 64335bb94f9f..ec3fc8d88e87 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -45,7 +45,7 @@ hostprogs-y += xdp_rxq_info hostprogs-y += syscall_tp # Libbpf dependencies -LIBBPF := ../../tools/lib/bpf/bpf.o +LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o test_lru_dist-objs := test_lru_dist.o $(LIBBPF) diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 242631aa4ea2..69806d74fa53 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -695,105 +695,3 @@ struct ksym *ksym_search(long key) return &syms[0]; } -int set_link_xdp_fd(int ifindex, int fd, __u32 flags) -{ - struct sockaddr_nl sa; - int sock, seq = 0, len, ret = -1; - char buf[4096]; - struct nlattr *nla, *nla_xdp; - struct { - struct nlmsghdr nh; - struct ifinfomsg ifinfo; - char attrbuf[64]; - } req; - struct nlmsghdr *nh; - struct nlmsgerr *err; - - memset(&sa, 0, sizeof(sa)); - sa.nl_family = AF_NETLINK; - - sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); - if (sock < 0) { - printf("open netlink socket: %s\n", strerror(errno)); - return -1; - } - - if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { - printf("bind to netlink: %s\n", strerror(errno)); - goto cleanup; - } - - memset(&req, 0, sizeof(req)); - req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); - req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; - req.nh.nlmsg_type = RTM_SETLINK; - req.nh.nlmsg_pid = 0; - req.nh.nlmsg_seq = ++seq; - req.ifinfo.ifi_family = AF_UNSPEC; - req.ifinfo.ifi_index = ifindex; - - /* started nested attribute for XDP */ - nla = (struct nlattr *)(((char *)&req) - + NLMSG_ALIGN(req.nh.nlmsg_len)); - nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/; - nla->nla_len = NLA_HDRLEN; - - /* add XDP fd */ - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = 1/*IFLA_XDP_FD*/; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); - memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); - nla->nla_len += nla_xdp->nla_len; - - /* if user passed in any flags, add those too */ - if (flags) { - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = 3/*IFLA_XDP_FLAGS*/; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags); - memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags)); - nla->nla_len += nla_xdp->nla_len; - } - - req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); - - if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { - printf("send to netlink: %s\n", strerror(errno)); - goto cleanup; - } - - len = recv(sock, buf, sizeof(buf), 0); - if (len < 0) { - printf("recv from netlink: %s\n", strerror(errno)); - goto cleanup; - } - - for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); - nh = NLMSG_NEXT(nh, len)) { - if (nh->nlmsg_pid != getpid()) { - printf("Wrong pid %d, expected %d\n", - nh->nlmsg_pid, getpid()); - goto cleanup; - } - if (nh->nlmsg_seq != seq) { - printf("Wrong seq %d, expected %d\n", - nh->nlmsg_seq, seq); - goto cleanup; - } - switch (nh->nlmsg_type) { - case NLMSG_ERROR: - err = (struct nlmsgerr *)NLMSG_DATA(nh); - if (!err->error) - continue; - printf("nlmsg error %s\n", strerror(-err->error)); - goto cleanup; - case NLMSG_DONE: - break; - } - } - - ret = 0; - -cleanup: - close(sock); - return ret; -} diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h index 7d57a4248893..453c200b389b 100644 --- a/samples/bpf/bpf_load.h +++ b/samples/bpf/bpf_load.h @@ -61,5 +61,5 @@ struct ksym { int load_kallsyms(void); struct ksym *ksym_search(long key); -int set_link_xdp_fd(int ifindex, int fd, __u32 flags); +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); #endif diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index fdaefe91801d..b901ee2b3336 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -25,7 +25,7 @@ static __u32 xdp_flags; static void int_exit(int sig) { - set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); exit(0); } @@ -116,7 +116,7 @@ int main(int argc, char **argv) signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { printf("link set xdp fd failed\n"); return 1; } diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 35fec9fecb57..23744a8aaf21 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -26,7 +26,7 @@ static const char *__doc__ = /* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead * use bpf/libbpf.h), but cannot as (currently) needed for XDP - * attaching to a device via set_link_xdp_fd() + * attaching to a device via bpf_set_link_xdp_fd() */ #include "libbpf.h" #include "bpf_load.h" @@ -67,7 +67,7 @@ static void int_exit(int sig) "Interrupted: Removing XDP program on ifindex:%d device:%s\n", ifindex, ifname); if (ifindex > -1) - set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); exit(EXIT_OK); } @@ -682,7 +682,7 @@ int main(int argc, char **argv) /* Remove XDP program when program is interrupted */ signal(SIGINT, int_exit); - if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) { fprintf(stderr, "link set xdp fd failed\n"); return EXIT_FAIL_XDP; } diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c index 978a532f0748..7eae07d7293e 100644 --- a/samples/bpf/xdp_redirect_map_user.c +++ b/samples/bpf/xdp_redirect_map_user.c @@ -34,9 +34,9 @@ static __u32 xdp_flags; static void int_exit(int sig) { - set_link_xdp_fd(ifindex_in, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags); if (ifindex_out_xdp_dummy_attached) - set_link_xdp_fd(ifindex_out, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); exit(0); } @@ -120,13 +120,13 @@ int main(int argc, char **argv) return 1; } - if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) { printf("ERROR: link set xdp fd failed on %d\n", ifindex_in); return 1; } /* Loading dummy XDP prog on out-device */ - if (set_link_xdp_fd(ifindex_out, prog_fd[1], + if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1], (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) { printf("WARN: link set xdp fd failed on %d\n", ifindex_out); ifindex_out_xdp_dummy_attached = false; diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index 4475d837bf2c..d54e91eb6cbf 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -33,9 +33,9 @@ static __u32 xdp_flags; static void int_exit(int sig) { - set_link_xdp_fd(ifindex_in, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags); if (ifindex_out_xdp_dummy_attached) - set_link_xdp_fd(ifindex_out, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); exit(0); } @@ -114,13 +114,13 @@ int main(int argc, char **argv) return 1; } - if (set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) { printf("ERROR: link set xdp fd failed on %d\n", ifindex_in); return 1; } /* Loading dummy XDP prog on out-device */ - if (set_link_xdp_fd(ifindex_out, prog_fd[1], + if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1], (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) { printf("WARN: link set xdp fd failed on %d\n", ifindex_out); ifindex_out_xdp_dummy_attached = false; diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index 916462112d55..6296741c1fbd 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -37,7 +37,7 @@ static void int_exit(int sig) int i = 0; for (i = 0; i < total_ifindex; i++) - set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); exit(0); } @@ -49,7 +49,7 @@ static void close_and_exit(int sig) close(sock_arp); for (i = 0; i < total_ifindex; i++) - set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); exit(0); } @@ -183,7 +183,7 @@ static void read_route(struct nlmsghdr *nh, int nll) int i = 0; for (i = 0; i < total_ifindex; i++) - set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); exit(0); } assert(bpf_map_update_elem(map_fd[4], &route.iface, &route.iface, 0) == 0); @@ -633,12 +633,12 @@ int main(int ac, char **argv) } } for (i = 0; i < total_ifindex; i++) { - if (set_link_xdp_fd(ifindex_list[i], prog_fd[0], flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd[0], flags) < 0) { printf("link set xdp fd failed\n"); int recovery_index = i; for (i = 0; i < recovery_index; i++) - set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); return 1; } diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index 32430e8b3a6a..478d95412de4 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -56,7 +56,7 @@ static void int_exit(int sig) "Interrupted: Removing XDP program on ifindex:%d device:%s\n", ifindex, ifname); if (ifindex > -1) - set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); exit(EXIT_OK); } @@ -521,7 +521,7 @@ int main(int argc, char **argv) /* Remove XDP program when program is interrupted */ signal(SIGINT, int_exit); - if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { fprintf(stderr, "link set xdp fd failed\n"); return EXIT_FAIL_XDP; } diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index 715cd12eaca5..f0a787268a87 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -30,7 +30,7 @@ static __u32 xdp_flags = 0; static void int_exit(int sig) { if (ifindex > -1) - set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); exit(0); } @@ -254,14 +254,14 @@ int main(int argc, char **argv) } } - if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { printf("link set xdp fd failed\n"); return 1; } poll_stats(kill_after_s); - set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); return 0; } diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h new file mode 100644 index 000000000000..8616131e2c61 --- /dev/null +++ b/tools/include/uapi/linux/if_link.h @@ -0,0 +1,943 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_IF_LINK_H +#define _UAPI_LINUX_IF_LINK_H + +#include <linux/types.h> +#include <linux/netlink.h> + +/* This struct should be in sync with struct rtnl_link_stats64 */ +struct rtnl_link_stats { + __u32 rx_packets; /* total packets received */ + __u32 tx_packets; /* total packets transmitted */ + __u32 rx_bytes; /* total bytes received */ + __u32 tx_bytes; /* total bytes transmitted */ + __u32 rx_errors; /* bad packets received */ + __u32 tx_errors; /* packet transmit problems */ + __u32 rx_dropped; /* no space in linux buffers */ + __u32 tx_dropped; /* no space available in linux */ + __u32 multicast; /* multicast packets received */ + __u32 collisions; + + /* detailed rx_errors: */ + __u32 rx_length_errors; + __u32 rx_over_errors; /* receiver ring buff overflow */ + __u32 rx_crc_errors; /* recved pkt with crc error */ + __u32 rx_frame_errors; /* recv'd frame alignment error */ + __u32 rx_fifo_errors; /* recv'r fifo overrun */ + __u32 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u32 tx_aborted_errors; + __u32 tx_carrier_errors; + __u32 tx_fifo_errors; + __u32 tx_heartbeat_errors; + __u32 tx_window_errors; + + /* for cslip etc */ + __u32 rx_compressed; + __u32 tx_compressed; + + __u32 rx_nohandler; /* dropped, no handler found */ +}; + +/* The main device statistics structure */ +struct rtnl_link_stats64 { + __u64 rx_packets; /* total packets received */ + __u64 tx_packets; /* total packets transmitted */ + __u64 rx_bytes; /* total bytes received */ + __u64 tx_bytes; /* total bytes transmitted */ + __u64 rx_errors; /* bad packets received */ + __u64 tx_errors; /* packet transmit problems */ + __u64 rx_dropped; /* no space in linux buffers */ + __u64 tx_dropped; /* no space available in linux */ + __u64 multicast; /* multicast packets received */ + __u64 collisions; + + /* detailed rx_errors: */ + __u64 rx_length_errors; + __u64 rx_over_errors; /* receiver ring buff overflow */ + __u64 rx_crc_errors; /* recved pkt with crc error */ + __u64 rx_frame_errors; /* recv'd frame alignment error */ + __u64 rx_fifo_errors; /* recv'r fifo overrun */ + __u64 rx_missed_errors; /* receiver missed packet */ + + /* detailed tx_errors */ + __u64 tx_aborted_errors; + __u64 tx_carrier_errors; + __u64 tx_fifo_errors; + __u64 tx_heartbeat_errors; + __u64 tx_window_errors; + + /* for cslip etc */ + __u64 rx_compressed; + __u64 tx_compressed; + + __u64 rx_nohandler; /* dropped, no handler found */ +}; + +/* The struct should be in sync with struct ifmap */ +struct rtnl_link_ifmap { + __u64 mem_start; + __u64 mem_end; + __u64 base_addr; + __u16 irq; + __u8 dma; + __u8 port; +}; + +/* + * IFLA_AF_SPEC + * Contains nested attributes for address family specific attributes. + * Each address family may create a attribute with the address family + * number as type and create its own attribute structure in it. + * + * Example: + * [IFLA_AF_SPEC] = { + * [AF_INET] = { + * [IFLA_INET_CONF] = ..., + * }, + * [AF_INET6] = { + * [IFLA_INET6_FLAGS] = ..., + * [IFLA_INET6_CONF] = ..., + * } + * } + */ + +enum { + IFLA_UNSPEC, + IFLA_ADDRESS, + IFLA_BROADCAST, + IFLA_IFNAME, + IFLA_MTU, + IFLA_LINK, + IFLA_QDISC, + IFLA_STATS, + IFLA_COST, +#define IFLA_COST IFLA_COST + IFLA_PRIORITY, +#define IFLA_PRIORITY IFLA_PRIORITY + IFLA_MASTER, +#define IFLA_MASTER IFLA_MASTER + IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */ +#define IFLA_WIRELESS IFLA_WIRELESS + IFLA_PROTINFO, /* Protocol specific information for a link */ +#define IFLA_PROTINFO IFLA_PROTINFO + IFLA_TXQLEN, +#define IFLA_TXQLEN IFLA_TXQLEN + IFLA_MAP, +#define IFLA_MAP IFLA_MAP + IFLA_WEIGHT, +#define IFLA_WEIGHT IFLA_WEIGHT + IFLA_OPERSTATE, + IFLA_LINKMODE, + IFLA_LINKINFO, +#define IFLA_LINKINFO IFLA_LINKINFO + IFLA_NET_NS_PID, + IFLA_IFALIAS, + IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */ + IFLA_VFINFO_LIST, + IFLA_STATS64, + IFLA_VF_PORTS, + IFLA_PORT_SELF, + IFLA_AF_SPEC, + IFLA_GROUP, /* Group the device belongs to */ + IFLA_NET_NS_FD, + IFLA_EXT_MASK, /* Extended info mask, VFs, etc */ + IFLA_PROMISCUITY, /* Promiscuity count: > 0 means acts PROMISC */ +#define IFLA_PROMISCUITY IFLA_PROMISCUITY + IFLA_NUM_TX_QUEUES, + IFLA_NUM_RX_QUEUES, + IFLA_CARRIER, + IFLA_PHYS_PORT_ID, + IFLA_CARRIER_CHANGES, + IFLA_PHYS_SWITCH_ID, + IFLA_LINK_NETNSID, + IFLA_PHYS_PORT_NAME, + IFLA_PROTO_DOWN, + IFLA_GSO_MAX_SEGS, + IFLA_GSO_MAX_SIZE, + IFLA_PAD, + IFLA_XDP, + IFLA_EVENT, + IFLA_NEW_NETNSID, + IFLA_IF_NETNSID, + IFLA_CARRIER_UP_COUNT, + IFLA_CARRIER_DOWN_COUNT, + __IFLA_MAX +}; + + +#define IFLA_MAX (__IFLA_MAX - 1) + +/* backwards compatibility for userspace */ +#ifndef __KERNEL__ +#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) +#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) +#endif + +enum { + IFLA_INET_UNSPEC, + IFLA_INET_CONF, + __IFLA_INET_MAX, +}; + +#define IFLA_INET_MAX (__IFLA_INET_MAX - 1) + +/* ifi_flags. + + IFF_* flags. + + The only change is: + IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are + more not changeable by user. They describe link media + characteristics and set by device driver. + + Comments: + - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid + - If neither of these three flags are set; + the interface is NBMA. + + - IFF_MULTICAST does not mean anything special: + multicasts can be used on all not-NBMA links. + IFF_MULTICAST means that this media uses special encapsulation + for multicast frames. Apparently, all IFF_POINTOPOINT and + IFF_BROADCAST devices are able to use multicasts too. + */ + +/* IFLA_LINK. + For usual devices it is equal ifi_index. + If it is a "virtual interface" (f.e. tunnel), ifi_link + can point to real physical interface (f.e. for bandwidth calculations), + or maybe 0, what means, that real media is unknown (usual + for IPIP tunnels, when route to endpoint is allowed to change) + */ + +/* Subtype attributes for IFLA_PROTINFO */ +enum { + IFLA_INET6_UNSPEC, + IFLA_INET6_FLAGS, /* link flags */ + IFLA_INET6_CONF, /* sysctl parameters */ + IFLA_INET6_STATS, /* statistics */ + IFLA_INET6_MCAST, /* MC things. What of them? */ + IFLA_INET6_CACHEINFO, /* time values and max reasm size */ + IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */ + IFLA_INET6_TOKEN, /* device token */ + IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */ + __IFLA_INET6_MAX +}; + +#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) + +enum in6_addr_gen_mode { + IN6_ADDR_GEN_MODE_EUI64, + IN6_ADDR_GEN_MODE_NONE, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY, + IN6_ADDR_GEN_MODE_RANDOM, +}; + +/* Bridge section */ + +enum { + IFLA_BR_UNSPEC, + IFLA_BR_FORWARD_DELAY, + IFLA_BR_HELLO_TIME, + IFLA_BR_MAX_AGE, + IFLA_BR_AGEING_TIME, + IFLA_BR_STP_STATE, + IFLA_BR_PRIORITY, + IFLA_BR_VLAN_FILTERING, + IFLA_BR_VLAN_PROTOCOL, + IFLA_BR_GROUP_FWD_MASK, + IFLA_BR_ROOT_ID, + IFLA_BR_BRIDGE_ID, + IFLA_BR_ROOT_PORT, + IFLA_BR_ROOT_PATH_COST, + IFLA_BR_TOPOLOGY_CHANGE, + IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + IFLA_BR_HELLO_TIMER, + IFLA_BR_TCN_TIMER, + IFLA_BR_TOPOLOGY_CHANGE_TIMER, + IFLA_BR_GC_TIMER, + IFLA_BR_GROUP_ADDR, + IFLA_BR_FDB_FLUSH, + IFLA_BR_MCAST_ROUTER, + IFLA_BR_MCAST_SNOOPING, + IFLA_BR_MCAST_QUERY_USE_IFADDR, + IFLA_BR_MCAST_QUERIER, + IFLA_BR_MCAST_HASH_ELASTICITY, + IFLA_BR_MCAST_HASH_MAX, + IFLA_BR_MCAST_LAST_MEMBER_CNT, + IFLA_BR_MCAST_STARTUP_QUERY_CNT, + IFLA_BR_MCAST_LAST_MEMBER_INTVL, + IFLA_BR_MCAST_MEMBERSHIP_INTVL, + IFLA_BR_MCAST_QUERIER_INTVL, + IFLA_BR_MCAST_QUERY_INTVL, + IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, + IFLA_BR_MCAST_STARTUP_QUERY_INTVL, + IFLA_BR_NF_CALL_IPTABLES, + IFLA_BR_NF_CALL_IP6TABLES, + IFLA_BR_NF_CALL_ARPTABLES, + IFLA_BR_VLAN_DEFAULT_PVID, + IFLA_BR_PAD, + IFLA_BR_VLAN_STATS_ENABLED, + IFLA_BR_MCAST_STATS_ENABLED, + IFLA_BR_MCAST_IGMP_VERSION, + IFLA_BR_MCAST_MLD_VERSION, + __IFLA_BR_MAX, +}; + +#define IFLA_BR_MAX (__IFLA_BR_MAX - 1) + +struct ifla_bridge_id { + __u8 prio[2]; + __u8 addr[6]; /* ETH_ALEN */ +}; + +enum { + BRIDGE_MODE_UNSPEC, + BRIDGE_MODE_HAIRPIN, +}; + +enum { + IFLA_BRPORT_UNSPEC, + IFLA_BRPORT_STATE, /* Spanning tree state */ + IFLA_BRPORT_PRIORITY, /* " priority */ + IFLA_BRPORT_COST, /* " cost */ + IFLA_BRPORT_MODE, /* mode (hairpin) */ + IFLA_BRPORT_GUARD, /* bpdu guard */ + IFLA_BRPORT_PROTECT, /* root port protection */ + IFLA_BRPORT_FAST_LEAVE, /* multicast fast leave */ + IFLA_BRPORT_LEARNING, /* mac learning */ + IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */ + IFLA_BRPORT_PROXYARP, /* proxy ARP */ + IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ + IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ + IFLA_BRPORT_ROOT_ID, /* designated root */ + IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ + IFLA_BRPORT_DESIGNATED_PORT, + IFLA_BRPORT_DESIGNATED_COST, + IFLA_BRPORT_ID, + IFLA_BRPORT_NO, + IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + IFLA_BRPORT_CONFIG_PENDING, + IFLA_BRPORT_MESSAGE_AGE_TIMER, + IFLA_BRPORT_FORWARD_DELAY_TIMER, + IFLA_BRPORT_HOLD_TIMER, + IFLA_BRPORT_FLUSH, + IFLA_BRPORT_MULTICAST_ROUTER, + IFLA_BRPORT_PAD, + IFLA_BRPORT_MCAST_FLOOD, + IFLA_BRPORT_MCAST_TO_UCAST, + IFLA_BRPORT_VLAN_TUNNEL, + IFLA_BRPORT_BCAST_FLOOD, + IFLA_BRPORT_GROUP_FWD_MASK, + IFLA_BRPORT_NEIGH_SUPPRESS, + __IFLA_BRPORT_MAX +}; +#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) + +struct ifla_cacheinfo { + __u32 max_reasm_len; + __u32 tstamp; /* ipv6InterfaceTable updated timestamp */ + __u32 reachable_time; + __u32 retrans_time; +}; + +enum { + IFLA_INFO_UNSPEC, + IFLA_INFO_KIND, + IFLA_INFO_DATA, + IFLA_INFO_XSTATS, + IFLA_INFO_SLAVE_KIND, + IFLA_INFO_SLAVE_DATA, + __IFLA_INFO_MAX, +}; + +#define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1) + +/* VLAN section */ + +enum { + IFLA_VLAN_UNSPEC, + IFLA_VLAN_ID, + IFLA_VLAN_FLAGS, + IFLA_VLAN_EGRESS_QOS, + IFLA_VLAN_INGRESS_QOS, + IFLA_VLAN_PROTOCOL, + __IFLA_VLAN_MAX, +}; + +#define IFLA_VLAN_MAX (__IFLA_VLAN_MAX - 1) + +struct ifla_vlan_flags { + __u32 flags; + __u32 mask; +}; + +enum { + IFLA_VLAN_QOS_UNSPEC, + IFLA_VLAN_QOS_MAPPING, + __IFLA_VLAN_QOS_MAX +}; + +#define IFLA_VLAN_QOS_MAX (__IFLA_VLAN_QOS_MAX - 1) + +struct ifla_vlan_qos_mapping { + __u32 from; + __u32 to; +}; + +/* MACVLAN section */ +enum { + IFLA_MACVLAN_UNSPEC, + IFLA_MACVLAN_MODE, + IFLA_MACVLAN_FLAGS, + IFLA_MACVLAN_MACADDR_MODE, + IFLA_MACVLAN_MACADDR, + IFLA_MACVLAN_MACADDR_DATA, + IFLA_MACVLAN_MACADDR_COUNT, + __IFLA_MACVLAN_MAX, +}; + +#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1) + +enum macvlan_mode { + MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */ + MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */ + MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ + MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */ + MACVLAN_MODE_SOURCE = 16,/* use source MAC address list to assign */ +}; + +enum macvlan_macaddr_mode { + MACVLAN_MACADDR_ADD, + MACVLAN_MACADDR_DEL, + MACVLAN_MACADDR_FLUSH, + MACVLAN_MACADDR_SET, +}; + +#define MACVLAN_FLAG_NOPROMISC 1 + +/* VRF section */ +enum { + IFLA_VRF_UNSPEC, + IFLA_VRF_TABLE, + __IFLA_VRF_MAX +}; + +#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1) + +enum { + IFLA_VRF_PORT_UNSPEC, + IFLA_VRF_PORT_TABLE, + __IFLA_VRF_PORT_MAX +}; + +#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1) + +/* MACSEC section */ +enum { + IFLA_MACSEC_UNSPEC, + IFLA_MACSEC_SCI, + IFLA_MACSEC_PORT, + IFLA_MACSEC_ICV_LEN, + IFLA_MACSEC_CIPHER_SUITE, + IFLA_MACSEC_WINDOW, + IFLA_MACSEC_ENCODING_SA, + IFLA_MACSEC_ENCRYPT, + IFLA_MACSEC_PROTECT, + IFLA_MACSEC_INC_SCI, + IFLA_MACSEC_ES, + IFLA_MACSEC_SCB, + IFLA_MACSEC_REPLAY_PROTECT, + IFLA_MACSEC_VALIDATION, + IFLA_MACSEC_PAD, + __IFLA_MACSEC_MAX, +}; + +#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) + +enum macsec_validation_type { + MACSEC_VALIDATE_DISABLED = 0, + MACSEC_VALIDATE_CHECK = 1, + MACSEC_VALIDATE_STRICT = 2, + __MACSEC_VALIDATE_END, + MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1, +}; + +/* IPVLAN section */ +enum { + IFLA_IPVLAN_UNSPEC, + IFLA_IPVLAN_MODE, + IFLA_IPVLAN_FLAGS, + __IFLA_IPVLAN_MAX +}; + +#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1) + +enum ipvlan_mode { + IPVLAN_MODE_L2 = 0, + IPVLAN_MODE_L3, + IPVLAN_MODE_L3S, + IPVLAN_MODE_MAX +}; + +#define IPVLAN_F_PRIVATE 0x01 +#define IPVLAN_F_VEPA 0x02 + +/* VXLAN section */ +enum { + IFLA_VXLAN_UNSPEC, + IFLA_VXLAN_ID, + IFLA_VXLAN_GROUP, /* group or remote address */ + IFLA_VXLAN_LINK, + IFLA_VXLAN_LOCAL, + IFLA_VXLAN_TTL, + IFLA_VXLAN_TOS, + IFLA_VXLAN_LEARNING, + IFLA_VXLAN_AGEING, + IFLA_VXLAN_LIMIT, + IFLA_VXLAN_PORT_RANGE, /* source port */ + IFLA_VXLAN_PROXY, + IFLA_VXLAN_RSC, + IFLA_VXLAN_L2MISS, + IFLA_VXLAN_L3MISS, + IFLA_VXLAN_PORT, /* destination port */ + IFLA_VXLAN_GROUP6, + IFLA_VXLAN_LOCAL6, + IFLA_VXLAN_UDP_CSUM, + IFLA_VXLAN_UDP_ZERO_CSUM6_TX, + IFLA_VXLAN_UDP_ZERO_CSUM6_RX, + IFLA_VXLAN_REMCSUM_TX, + IFLA_VXLAN_REMCSUM_RX, + IFLA_VXLAN_GBP, + IFLA_VXLAN_REMCSUM_NOPARTIAL, + IFLA_VXLAN_COLLECT_METADATA, + IFLA_VXLAN_LABEL, + IFLA_VXLAN_GPE, + __IFLA_VXLAN_MAX +}; +#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) + +struct ifla_vxlan_port_range { + __be16 low; + __be16 high; +}; + +/* GENEVE section */ +enum { + IFLA_GENEVE_UNSPEC, + IFLA_GENEVE_ID, + IFLA_GENEVE_REMOTE, + IFLA_GENEVE_TTL, + IFLA_GENEVE_TOS, + IFLA_GENEVE_PORT, /* destination port */ + IFLA_GENEVE_COLLECT_METADATA, + IFLA_GENEVE_REMOTE6, + IFLA_GENEVE_UDP_CSUM, + IFLA_GENEVE_UDP_ZERO_CSUM6_TX, + IFLA_GENEVE_UDP_ZERO_CSUM6_RX, + IFLA_GENEVE_LABEL, + __IFLA_GENEVE_MAX +}; +#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) + +/* PPP section */ +enum { + IFLA_PPP_UNSPEC, + IFLA_PPP_DEV_FD, + __IFLA_PPP_MAX +}; +#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1) + +/* GTP section */ + +enum ifla_gtp_role { + GTP_ROLE_GGSN = 0, + GTP_ROLE_SGSN, +}; + +enum { + IFLA_GTP_UNSPEC, + IFLA_GTP_FD0, + IFLA_GTP_FD1, + IFLA_GTP_PDP_HASHSIZE, + IFLA_GTP_ROLE, + __IFLA_GTP_MAX, +}; +#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) + +/* Bonding section */ + +enum { + IFLA_BOND_UNSPEC, + IFLA_BOND_MODE, + IFLA_BOND_ACTIVE_SLAVE, + IFLA_BOND_MIIMON, + IFLA_BOND_UPDELAY, + IFLA_BOND_DOWNDELAY, + IFLA_BOND_USE_CARRIER, + IFLA_BOND_ARP_INTERVAL, + IFLA_BOND_ARP_IP_TARGET, + IFLA_BOND_ARP_VALIDATE, + IFLA_BOND_ARP_ALL_TARGETS, + IFLA_BOND_PRIMARY, + IFLA_BOND_PRIMARY_RESELECT, + IFLA_BOND_FAIL_OVER_MAC, + IFLA_BOND_XMIT_HASH_POLICY, + IFLA_BOND_RESEND_IGMP, + IFLA_BOND_NUM_PEER_NOTIF, + IFLA_BOND_ALL_SLAVES_ACTIVE, + IFLA_BOND_MIN_LINKS, + IFLA_BOND_LP_INTERVAL, + IFLA_BOND_PACKETS_PER_SLAVE, + IFLA_BOND_AD_LACP_RATE, + IFLA_BOND_AD_SELECT, + IFLA_BOND_AD_INFO, + IFLA_BOND_AD_ACTOR_SYS_PRIO, + IFLA_BOND_AD_USER_PORT_KEY, + IFLA_BOND_AD_ACTOR_SYSTEM, + IFLA_BOND_TLB_DYNAMIC_LB, + __IFLA_BOND_MAX, +}; + +#define IFLA_BOND_MAX (__IFLA_BOND_MAX - 1) + +enum { + IFLA_BOND_AD_INFO_UNSPEC, + IFLA_BOND_AD_INFO_AGGREGATOR, + IFLA_BOND_AD_INFO_NUM_PORTS, + IFLA_BOND_AD_INFO_ACTOR_KEY, + IFLA_BOND_AD_INFO_PARTNER_KEY, + IFLA_BOND_AD_INFO_PARTNER_MAC, + __IFLA_BOND_AD_INFO_MAX, +}; + +#define IFLA_BOND_AD_INFO_MAX (__IFLA_BOND_AD_INFO_MAX - 1) + +enum { + IFLA_BOND_SLAVE_UNSPEC, + IFLA_BOND_SLAVE_STATE, + IFLA_BOND_SLAVE_MII_STATUS, + IFLA_BOND_SLAVE_LINK_FAILURE_COUNT, + IFLA_BOND_SLAVE_PERM_HWADDR, + IFLA_BOND_SLAVE_QUEUE_ID, + IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, + IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, + IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, + __IFLA_BOND_SLAVE_MAX, +}; + +#define IFLA_BOND_SLAVE_MAX (__IFLA_BOND_SLAVE_MAX - 1) + +/* SR-IOV virtual function management section */ + +enum { + IFLA_VF_INFO_UNSPEC, + IFLA_VF_INFO, + __IFLA_VF_INFO_MAX, +}; + +#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1) + +enum { + IFLA_VF_UNSPEC, + IFLA_VF_MAC, /* Hardware queue specific attributes */ + IFLA_VF_VLAN, /* VLAN ID and QoS */ + IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */ + IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */ + IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */ + IFLA_VF_RATE, /* Min and Max TX Bandwidth Allocation */ + IFLA_VF_RSS_QUERY_EN, /* RSS Redirection Table and Hash Key query + * on/off switch + */ + IFLA_VF_STATS, /* network device statistics */ + IFLA_VF_TRUST, /* Trust VF */ + IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ + IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ + IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ + __IFLA_VF_MAX, +}; + +#define IFLA_VF_MAX (__IFLA_VF_MAX - 1) + +struct ifla_vf_mac { + __u32 vf; + __u8 mac[32]; /* MAX_ADDR_LEN */ +}; + +struct ifla_vf_vlan { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; +}; + +enum { + IFLA_VF_VLAN_INFO_UNSPEC, + IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */ + __IFLA_VF_VLAN_INFO_MAX, +}; + +#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1) +#define MAX_VLAN_LIST_LEN 1 + +struct ifla_vf_vlan_info { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; + __be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */ +}; + +struct ifla_vf_tx_rate { + __u32 vf; + __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */ +}; + +struct ifla_vf_rate { + __u32 vf; + __u32 min_tx_rate; /* Min Bandwidth in Mbps */ + __u32 max_tx_rate; /* Max Bandwidth in Mbps */ +}; + +struct ifla_vf_spoofchk { + __u32 vf; + __u32 setting; +}; + +struct ifla_vf_guid { + __u32 vf; + __u64 guid; +}; + +enum { + IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */ + IFLA_VF_LINK_STATE_ENABLE, /* link always up */ + IFLA_VF_LINK_STATE_DISABLE, /* link always down */ + __IFLA_VF_LINK_STATE_MAX, +}; + +struct ifla_vf_link_state { + __u32 vf; + __u32 link_state; +}; + +struct ifla_vf_rss_query_en { + __u32 vf; + __u32 setting; +}; + +enum { + IFLA_VF_STATS_RX_PACKETS, + IFLA_VF_STATS_TX_PACKETS, + IFLA_VF_STATS_RX_BYTES, + IFLA_VF_STATS_TX_BYTES, + IFLA_VF_STATS_BROADCAST, + IFLA_VF_STATS_MULTICAST, + IFLA_VF_STATS_PAD, + IFLA_VF_STATS_RX_DROPPED, + IFLA_VF_STATS_TX_DROPPED, + __IFLA_VF_STATS_MAX, +}; + +#define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1) + +struct ifla_vf_trust { + __u32 vf; + __u32 setting; +}; + +/* VF ports management section + * + * Nested layout of set/get msg is: + * + * [IFLA_NUM_VF] + * [IFLA_VF_PORTS] + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * ... + * [IFLA_PORT_SELF] + * [IFLA_PORT_*], ... + */ + +enum { + IFLA_VF_PORT_UNSPEC, + IFLA_VF_PORT, /* nest */ + __IFLA_VF_PORT_MAX, +}; + +#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1) + +enum { + IFLA_PORT_UNSPEC, + IFLA_PORT_VF, /* __u32 */ + IFLA_PORT_PROFILE, /* string */ + IFLA_PORT_VSI_TYPE, /* 802.1Qbg (pre-)standard VDP */ + IFLA_PORT_INSTANCE_UUID, /* binary UUID */ + IFLA_PORT_HOST_UUID, /* binary UUID */ + IFLA_PORT_REQUEST, /* __u8 */ + IFLA_PORT_RESPONSE, /* __u16, output only */ + __IFLA_PORT_MAX, +}; + +#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1) + +#define PORT_PROFILE_MAX 40 +#define PORT_UUID_MAX 16 +#define PORT_SELF_VF -1 + +enum { + PORT_REQUEST_PREASSOCIATE = 0, + PORT_REQUEST_PREASSOCIATE_RR, + PORT_REQUEST_ASSOCIATE, + PORT_REQUEST_DISASSOCIATE, +}; + +enum { + PORT_VDP_RESPONSE_SUCCESS = 0, + PORT_VDP_RESPONSE_INVALID_FORMAT, + PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_VDP_RESPONSE_UNUSED_VTID, + PORT_VDP_RESPONSE_VTID_VIOLATION, + PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION, + PORT_VDP_RESPONSE_OUT_OF_SYNC, + /* 0x08-0xFF reserved for future VDP use */ + PORT_PROFILE_RESPONSE_SUCCESS = 0x100, + PORT_PROFILE_RESPONSE_INPROGRESS, + PORT_PROFILE_RESPONSE_INVALID, + PORT_PROFILE_RESPONSE_BADSTATE, + PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_PROFILE_RESPONSE_ERROR, +}; + +struct ifla_port_vsi { + __u8 vsi_mgr_id; + __u8 vsi_type_id[3]; + __u8 vsi_type_version; + __u8 pad[3]; +}; + + +/* IPoIB section */ + +enum { + IFLA_IPOIB_UNSPEC, + IFLA_IPOIB_PKEY, + IFLA_IPOIB_MODE, + IFLA_IPOIB_UMCAST, + __IFLA_IPOIB_MAX +}; + +enum { + IPOIB_MODE_DATAGRAM = 0, /* using unreliable datagram QPs */ + IPOIB_MODE_CONNECTED = 1, /* using connected QPs */ +}; + +#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) + + +/* HSR section */ + +enum { + IFLA_HSR_UNSPEC, + IFLA_HSR_SLAVE1, + IFLA_HSR_SLAVE2, + IFLA_HSR_MULTICAST_SPEC, /* Last byte of supervision addr */ + IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ + IFLA_HSR_SEQ_NR, + IFLA_HSR_VERSION, /* HSR version */ + __IFLA_HSR_MAX, +}; + +#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1) + +/* STATS section */ + +struct if_stats_msg { + __u8 family; + __u8 pad1; + __u16 pad2; + __u32 ifindex; + __u32 filter_mask; +}; + +/* A stats attribute can be netdev specific or a global stat. + * For netdev stats, lets use the prefix IFLA_STATS_LINK_* + */ +enum { + IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */ + IFLA_STATS_LINK_64, + IFLA_STATS_LINK_XSTATS, + IFLA_STATS_LINK_XSTATS_SLAVE, + IFLA_STATS_LINK_OFFLOAD_XSTATS, + IFLA_STATS_AF_SPEC, + __IFLA_STATS_MAX, +}; + +#define IFLA_STATS_MAX (__IFLA_STATS_MAX - 1) + +#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1)) + +/* These are embedded into IFLA_STATS_LINK_XSTATS: + * [IFLA_STATS_LINK_XSTATS] + * -> [LINK_XSTATS_TYPE_xxx] + * -> [rtnl link type specific attributes] + */ +enum { + LINK_XSTATS_TYPE_UNSPEC, + LINK_XSTATS_TYPE_BRIDGE, + __LINK_XSTATS_TYPE_MAX +}; +#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) + +/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */ +enum { + IFLA_OFFLOAD_XSTATS_UNSPEC, + IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */ + __IFLA_OFFLOAD_XSTATS_MAX +}; +#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1) + +/* XDP section */ + +#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) +#define XDP_FLAGS_SKB_MODE (1U << 1) +#define XDP_FLAGS_DRV_MODE (1U << 2) +#define XDP_FLAGS_HW_MODE (1U << 3) +#define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \ + XDP_FLAGS_DRV_MODE | \ + XDP_FLAGS_HW_MODE) +#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ + XDP_FLAGS_MODES) + +/* These are stored into IFLA_XDP_ATTACHED on dump. */ +enum { + XDP_ATTACHED_NONE = 0, + XDP_ATTACHED_DRV, + XDP_ATTACHED_SKB, + XDP_ATTACHED_HW, +}; + +enum { + IFLA_XDP_UNSPEC, + IFLA_XDP_FD, + IFLA_XDP_ATTACHED, + IFLA_XDP_FLAGS, + IFLA_XDP_PROG_ID, + __IFLA_XDP_MAX, +}; + +#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1) + +enum { + IFLA_EVENT_NONE, + IFLA_EVENT_REBOOT, /* internal reset / reboot */ + IFLA_EVENT_FEATURES, /* change in offload features */ + IFLA_EVENT_BONDING_FAILOVER, /* change in active slave */ + IFLA_EVENT_NOTIFY_PEERS, /* re-sent grat. arp/ndisc */ + IFLA_EVENT_IGMP_RESEND, /* re-sent IGMP JOIN */ + IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */ +}; + +#endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h new file mode 100644 index 000000000000..776bc92e9118 --- /dev/null +++ b/tools/include/uapi/linux/netlink.h @@ -0,0 +1,251 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_NETLINK_H +#define _UAPI__LINUX_NETLINK_H + +#include <linux/kernel.h> +#include <linux/socket.h> /* for __kernel_sa_family_t */ +#include <linux/types.h> + +#define NETLINK_ROUTE 0 /* Routing/device hook */ +#define NETLINK_UNUSED 1 /* Unused number */ +#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */ +#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */ +#define NETLINK_SOCK_DIAG 4 /* socket monitoring */ +#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */ +#define NETLINK_XFRM 6 /* ipsec */ +#define NETLINK_SELINUX 7 /* SELinux event notifications */ +#define NETLINK_ISCSI 8 /* Open-iSCSI */ +#define NETLINK_AUDIT 9 /* auditing */ +#define NETLINK_FIB_LOOKUP 10 +#define NETLINK_CONNECTOR 11 +#define NETLINK_NETFILTER 12 /* netfilter subsystem */ +#define NETLINK_IP6_FW 13 +#define NETLINK_DNRTMSG 14 /* DECnet routing messages */ +#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */ +#define NETLINK_GENERIC 16 +/* leave room for NETLINK_DM (DM Events) */ +#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */ +#define NETLINK_ECRYPTFS 19 +#define NETLINK_RDMA 20 +#define NETLINK_CRYPTO 21 /* Crypto layer */ +#define NETLINK_SMC 22 /* SMC monitoring */ + +#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG + +#define MAX_LINKS 32 + +struct sockaddr_nl { + __kernel_sa_family_t nl_family; /* AF_NETLINK */ + unsigned short nl_pad; /* zero */ + __u32 nl_pid; /* port ID */ + __u32 nl_groups; /* multicast groups mask */ +}; + +struct nlmsghdr { + __u32 nlmsg_len; /* Length of message including header */ + __u16 nlmsg_type; /* Message content */ + __u16 nlmsg_flags; /* Additional flags */ + __u32 nlmsg_seq; /* Sequence number */ + __u32 nlmsg_pid; /* Sending process port ID */ +}; + +/* Flags values */ + +#define NLM_F_REQUEST 0x01 /* It is request message. */ +#define NLM_F_MULTI 0x02 /* Multipart message, terminated by NLMSG_DONE */ +#define NLM_F_ACK 0x04 /* Reply with ack, with zero or error code */ +#define NLM_F_ECHO 0x08 /* Echo this request */ +#define NLM_F_DUMP_INTR 0x10 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 0x20 /* Dump was filtered as requested */ + +/* Modifiers to GET request */ +#define NLM_F_ROOT 0x100 /* specify tree root */ +#define NLM_F_MATCH 0x200 /* return all matching */ +#define NLM_F_ATOMIC 0x400 /* atomic GET */ +#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH) + +/* Modifiers to NEW request */ +#define NLM_F_REPLACE 0x100 /* Override existing */ +#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */ +#define NLM_F_CREATE 0x400 /* Create, if it does not exist */ +#define NLM_F_APPEND 0x800 /* Add to end of list */ + +/* Modifiers to DELETE request */ +#define NLM_F_NONREC 0x100 /* Do not delete recursively */ + +/* Flags for ACK message */ +#define NLM_F_CAPPED 0x100 /* request was capped */ +#define NLM_F_ACK_TLVS 0x200 /* extended ACK TVLs were included */ + +/* + 4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL + 4.4BSD CHANGE NLM_F_REPLACE + + True CHANGE NLM_F_CREATE|NLM_F_REPLACE + Append NLM_F_CREATE + Check NLM_F_EXCL + */ + +#define NLMSG_ALIGNTO 4U +#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) ) +#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) +#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN) +#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len)) +#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0))) +#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \ + (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len))) +#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len <= (len)) +#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len))) + +#define NLMSG_NOOP 0x1 /* Nothing. */ +#define NLMSG_ERROR 0x2 /* Error */ +#define NLMSG_DONE 0x3 /* End of a dump */ +#define NLMSG_OVERRUN 0x4 /* Data lost */ + +#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */ + +struct nlmsgerr { + int error; + struct nlmsghdr msg; + /* + * followed by the message contents unless NETLINK_CAP_ACK was set + * or the ACK indicates success (error == 0) + * message length is aligned with NLMSG_ALIGN() + */ + /* + * followed by TLVs defined in enum nlmsgerr_attrs + * if NETLINK_EXT_ACK was set + */ +}; + +/** + * enum nlmsgerr_attrs - nlmsgerr attributes + * @NLMSGERR_ATTR_UNUSED: unused + * @NLMSGERR_ATTR_MSG: error message string (string) + * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original + * message, counting from the beginning of the header (u32) + * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to + * be used - in the success case - to identify a created + * object or operation or similar (binary) + * @__NLMSGERR_ATTR_MAX: number of attributes + * @NLMSGERR_ATTR_MAX: highest attribute number + */ +enum nlmsgerr_attrs { + NLMSGERR_ATTR_UNUSED, + NLMSGERR_ATTR_MSG, + NLMSGERR_ATTR_OFFS, + NLMSGERR_ATTR_COOKIE, + + __NLMSGERR_ATTR_MAX, + NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1 +}; + +#define NETLINK_ADD_MEMBERSHIP 1 +#define NETLINK_DROP_MEMBERSHIP 2 +#define NETLINK_PKTINFO 3 +#define NETLINK_BROADCAST_ERROR 4 +#define NETLINK_NO_ENOBUFS 5 +#ifndef __KERNEL__ +#define NETLINK_RX_RING 6 +#define NETLINK_TX_RING 7 +#endif +#define NETLINK_LISTEN_ALL_NSID 8 +#define NETLINK_LIST_MEMBERSHIPS 9 +#define NETLINK_CAP_ACK 10 +#define NETLINK_EXT_ACK 11 + +struct nl_pktinfo { + __u32 group; +}; + +struct nl_mmap_req { + unsigned int nm_block_size; + unsigned int nm_block_nr; + unsigned int nm_frame_size; + unsigned int nm_frame_nr; +}; + +struct nl_mmap_hdr { + unsigned int nm_status; + unsigned int nm_len; + __u32 nm_group; + /* credentials */ + __u32 nm_pid; + __u32 nm_uid; + __u32 nm_gid; +}; + +#ifndef __KERNEL__ +enum nl_mmap_status { + NL_MMAP_STATUS_UNUSED, + NL_MMAP_STATUS_RESERVED, + NL_MMAP_STATUS_VALID, + NL_MMAP_STATUS_COPY, + NL_MMAP_STATUS_SKIP, +}; + +#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO +#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT) +#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr)) +#endif + +#define NET_MAJOR 36 /* Major 36 is reserved for networking */ + +enum { + NETLINK_UNCONNECTED = 0, + NETLINK_CONNECTED, +}; + +/* + * <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)--> + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * | Header | Pad | Payload | Pad | + * | (struct nlattr) | ing | | ing | + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * <-------------- nlattr->nla_len --------------> + */ + +struct nlattr { + __u16 nla_len; + __u16 nla_type; +}; + +/* + * nla_type (16 bits) + * +---+---+-------------------------------+ + * | N | O | Attribute Type | + * +---+---+-------------------------------+ + * N := Carries nested attributes + * O := Payload stored in network byte order + * + * Note: The N and O flag are mutually exclusive. + */ +#define NLA_F_NESTED (1 << 15) +#define NLA_F_NET_BYTEORDER (1 << 14) +#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER) + +#define NLA_ALIGNTO 4 +#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1)) +#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr))) + +/* Generic 32 bitflags attribute content sent to the kernel. + * + * The value is a bitmap that defines the values being set + * The selector is a bitmask that defines which value is legit + * + * Examples: + * value = 0x0, and selector = 0x1 + * implies we are selecting bit 1 and we want to set its value to 0. + * + * value = 0x2, and selector = 0x2 + * implies we are selecting bit 2 and we want to set its value to 1. + * + */ +struct nla_bitfield32 { + __u32 value; + __u32 selector; +}; + +#endif /* _UAPI__LINUX_NETLINK_H */ diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index d8749756352d..64c679d67109 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1 +1 @@ -libbpf-y := libbpf.o bpf.o +libbpf-y := libbpf.o bpf.o nlattr.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 83714ca1f22b..e6d5f8d1477f 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -160,6 +160,12 @@ $(BPF_IN): force elfdep bpfdep @(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \ (diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true + @(test -f ../../include/uapi/linux/netlink.h -a -f ../../../include/uapi/linux/netlink.h && ( \ + (diff -B ../../include/uapi/linux/netlink.h ../../../include/uapi/linux/netlink.h >/dev/null) || \ + echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'" >&2 )) || true + @(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \ + (diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \ + echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf $(OUTPUT)libbpf.so: $(BPF_IN) diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 5128677e4117..592a58a2b681 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: LGPL-2.1 + /* * common eBPF ELF operations. * @@ -25,6 +27,16 @@ #include <asm/unistd.h> #include <linux/bpf.h> #include "bpf.h" +#include "libbpf.h" +#include "nlattr.h" +#include <linux/rtnetlink.h> +#include <linux/if_link.h> +#include <sys/socket.h> +#include <errno.h> + +#ifndef SOL_NETLINK +#define SOL_NETLINK 270 +#endif /* * When building perf, unistd.h is overridden. __NR_bpf is @@ -46,7 +58,9 @@ # endif #endif +#ifndef min #define min(x, y) ((x) < (y) ? (x) : (y)) +#endif static inline __u64 ptr_to_u64(const void *ptr) { @@ -413,3 +427,124 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len) return err; } + +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) +{ + struct sockaddr_nl sa; + int sock, seq = 0, len, ret = -1; + char buf[4096]; + struct nlattr *nla, *nla_xdp; + struct { + struct nlmsghdr nh; + struct ifinfomsg ifinfo; + char attrbuf[64]; + } req; + struct nlmsghdr *nh; + struct nlmsgerr *err; + socklen_t addrlen; + int one = 1; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) { + return -errno; + } + + if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)) < 0) { + fprintf(stderr, "Netlink error reporting not supported\n"); + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + ret = -errno; + goto cleanup; + } + + addrlen = sizeof(sa); + if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { + ret = -errno; + goto cleanup; + } + + if (addrlen != sizeof(sa)) { + ret = -LIBBPF_ERRNO__INTERNAL; + goto cleanup; + } + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_SETLINK; + req.nh.nlmsg_pid = 0; + req.nh.nlmsg_seq = ++seq; + req.ifinfo.ifi_family = AF_UNSPEC; + req.ifinfo.ifi_index = ifindex; + + /* started nested attribute for XDP */ + nla = (struct nlattr *)(((char *)&req) + + NLMSG_ALIGN(req.nh.nlmsg_len)); + nla->nla_type = NLA_F_NESTED | IFLA_XDP; + nla->nla_len = NLA_HDRLEN; + + /* add XDP fd */ + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_FD; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); + memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); + nla->nla_len += nla_xdp->nla_len; + + /* if user passed in any flags, add those too */ + if (flags) { + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_FLAGS; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags); + memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags)); + nla->nla_len += nla_xdp->nla_len; + } + + req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); + + if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { + ret = -errno; + goto cleanup; + } + + len = recv(sock, buf, sizeof(buf), 0); + if (len < 0) { + ret = -errno; + goto cleanup; + } + + for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_pid != sa.nl_pid) { + ret = -LIBBPF_ERRNO__WRNGPID; + goto cleanup; + } + if (nh->nlmsg_seq != seq) { + ret = -LIBBPF_ERRNO__INVSEQ; + goto cleanup; + } + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + ret = err->error; + nla_dump_errormsg(nh); + goto cleanup; + case NLMSG_DONE: + break; + default: + break; + } + } + + ret = 0; + +cleanup: + close(sock); + return ret; +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 9f44c196931e..8d18fb73d7fb 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ + /* * common eBPF ELF operations. * diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 30c776375118..71ddc481f349 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1,3 +1,5 @@ +// SPDX-License-Identifier: LGPL-2.1 + /* * Common eBPF ELF object loading operations. * @@ -106,6 +108,8 @@ static const char *libbpf_strerror_table[NR_ERRNO] = { [ERRCODE_OFFSET(PROG2BIG)] = "Program too big", [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version", [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type", + [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message", + [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence", }; int libbpf_strerror(int err, char *buf, size_t size) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 6e20003109e0..f85906533cdd 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ + /* * Common eBPF ELF object loading operations. * @@ -42,6 +44,8 @@ enum libbpf_errno { LIBBPF_ERRNO__PROG2BIG, /* Program too big */ LIBBPF_ERRNO__KVER, /* Incorrect kernel version */ LIBBPF_ERRNO__PROGTYPE, /* Kernel doesn't support this program type */ + LIBBPF_ERRNO__WRNGPID, /* Wrong pid in netlink message */ + LIBBPF_ERRNO__INVSEQ, /* Invalid netlink sequence */ __LIBBPF_ERRNO__END, }; @@ -246,4 +250,6 @@ long libbpf_get_error(const void *ptr); int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd); + +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); #endif diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c new file mode 100644 index 000000000000..4719434278b2 --- /dev/null +++ b/tools/lib/bpf/nlattr.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: LGPL-2.1 + +/* + * NETLINK Netlink attributes + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation version 2.1 + * of the License. + * + * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch> + */ + +#include <errno.h> +#include "nlattr.h" +#include <linux/rtnetlink.h> +#include <string.h> +#include <stdio.h> + +static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = { + [NLA_U8] = sizeof(uint8_t), + [NLA_U16] = sizeof(uint16_t), + [NLA_U32] = sizeof(uint32_t), + [NLA_U64] = sizeof(uint64_t), + [NLA_STRING] = 1, + [NLA_FLAG] = 0, +}; + +static int nla_len(const struct nlattr *nla) +{ + return nla->nla_len - NLA_HDRLEN; +} + +static struct nlattr *nla_next(const struct nlattr *nla, int *remaining) +{ + int totlen = NLA_ALIGN(nla->nla_len); + + *remaining -= totlen; + return (struct nlattr *) ((char *) nla + totlen); +} + +static int nla_ok(const struct nlattr *nla, int remaining) +{ + return remaining >= sizeof(*nla) && + nla->nla_len >= sizeof(*nla) && + nla->nla_len <= remaining; +} + +static void *nla_data(const struct nlattr *nla) +{ + return (char *) nla + NLA_HDRLEN; +} + +static int nla_type(const struct nlattr *nla) +{ + return nla->nla_type & NLA_TYPE_MASK; +} + +static int validate_nla(struct nlattr *nla, int maxtype, + struct nla_policy *policy) +{ + struct nla_policy *pt; + unsigned int minlen = 0; + int type = nla_type(nla); + + if (type < 0 || type > maxtype) + return 0; + + pt = &policy[type]; + + if (pt->type > NLA_TYPE_MAX) + return 0; + + if (pt->minlen) + minlen = pt->minlen; + else if (pt->type != NLA_UNSPEC) + minlen = nla_attr_minlen[pt->type]; + + if (nla_len(nla) < minlen) + return -1; + + if (pt->maxlen && nla_len(nla) > pt->maxlen) + return -1; + + if (pt->type == NLA_STRING) { + char *data = nla_data(nla); + if (data[nla_len(nla) - 1] != '\0') + return -1; + } + + return 0; +} + +static inline int nlmsg_len(const struct nlmsghdr *nlh) +{ + return nlh->nlmsg_len - NLMSG_HDRLEN; +} + +/** + * Create attribute index based on a stream of attributes. + * @arg tb Index array to be filled (maxtype+1 elements). + * @arg maxtype Maximum attribute type expected and accepted. + * @arg head Head of attribute stream. + * @arg len Length of attribute stream. + * @arg policy Attribute validation policy. + * + * Iterates over the stream of attributes and stores a pointer to each + * attribute in the index array using the attribute type as index to + * the array. Attribute with a type greater than the maximum type + * specified will be silently ignored in order to maintain backwards + * compatibility. If \a policy is not NULL, the attribute will be + * validated using the specified policy. + * + * @see nla_validate + * @return 0 on success or a negative error code. + */ +static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len, + struct nla_policy *policy) +{ + struct nlattr *nla; + int rem, err; + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + + nla_for_each_attr(nla, head, len, rem) { + int type = nla_type(nla); + + if (type > maxtype) + continue; + + if (policy) { + err = validate_nla(nla, maxtype, policy); + if (err < 0) + goto errout; + } + + if (tb[type]) + fprintf(stderr, "Attribute of type %#x found multiple times in message, " + "previous attribute is being ignored.\n", type); + + tb[type] = nla; + } + + err = 0; +errout: + return err; +} + +/* dump netlink extended ack error message */ +int nla_dump_errormsg(struct nlmsghdr *nlh) +{ + struct nla_policy extack_policy[NLMSGERR_ATTR_MAX + 1] = { + [NLMSGERR_ATTR_MSG] = { .type = NLA_STRING }, + [NLMSGERR_ATTR_OFFS] = { .type = NLA_U32 }, + }; + struct nlattr *tb[NLMSGERR_ATTR_MAX + 1], *attr; + struct nlmsgerr *err; + char *errmsg = NULL; + int hlen, alen; + + /* no TLVs, nothing to do here */ + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return 0; + + err = (struct nlmsgerr *)NLMSG_DATA(nlh); + hlen = sizeof(*err); + + /* if NLM_F_CAPPED is set then the inner err msg was capped */ + if (!(nlh->nlmsg_flags & NLM_F_CAPPED)) + hlen += nlmsg_len(&err->msg); + + attr = (struct nlattr *) ((void *) err + hlen); + alen = nlh->nlmsg_len - hlen; + + if (nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) { + fprintf(stderr, + "Failed to parse extended error attributes\n"); + return 0; + } + + if (tb[NLMSGERR_ATTR_MSG]) + errmsg = (char *) nla_data(tb[NLMSGERR_ATTR_MSG]); + + fprintf(stderr, "Kernel error message: %s\n", errmsg); + + return 0; +} diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h new file mode 100644 index 000000000000..931a71f68f93 --- /dev/null +++ b/tools/lib/bpf/nlattr.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ + +/* + * NETLINK Netlink attributes + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation version 2.1 + * of the License. + * + * Copyright (c) 2003-2013 Thomas Graf <tgraf@suug.ch> + */ + +#ifndef __NLATTR_H +#define __NLATTR_H + +#include <stdint.h> +#include <linux/netlink.h> +/* avoid multiple definition of netlink features */ +#define __LINUX_NETLINK_H + +/** + * Standard attribute types to specify validation policy + */ +enum { + NLA_UNSPEC, /**< Unspecified type, binary data chunk */ + NLA_U8, /**< 8 bit integer */ + NLA_U16, /**< 16 bit integer */ + NLA_U32, /**< 32 bit integer */ + NLA_U64, /**< 64 bit integer */ + NLA_STRING, /**< NUL terminated character string */ + NLA_FLAG, /**< Flag */ + NLA_MSECS, /**< Micro seconds (64bit) */ + NLA_NESTED, /**< Nested attributes */ + __NLA_TYPE_MAX, +}; + +#define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1) + +/** + * @ingroup attr + * Attribute validation policy. + * + * See section @core_doc{core_attr_parse,Attribute Parsing} for more details. + */ +struct nla_policy { + /** Type of attribute or NLA_UNSPEC */ + uint16_t type; + + /** Minimal length of payload required */ + uint16_t minlen; + + /** Maximal length of payload allowed */ + uint16_t maxlen; +}; + +/** + * @ingroup attr + * Iterate over a stream of attributes + * @arg pos loop counter, set to current attribute + * @arg head head of attribute stream + * @arg len length of attribute stream + * @arg rem initialized to len, holds bytes currently remaining in stream + */ +#define nla_for_each_attr(pos, head, len, rem) \ + for (pos = head, rem = len; \ + nla_ok(pos, rem); \ + pos = nla_next(pos, &(rem))) + +int nla_dump_errormsg(struct nlmsghdr *nlh); + +#endif /* __NLATTR_H */ diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 1e09d77f1948..cc15af2e54fe 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -8,5 +8,6 @@ fixdep test_align test_dev_cgroup test_progs +test_tcpbpf_user test_verifier_log feature diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index bf05bc5e36e5..566d6adc172a 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -27,7 +27,7 @@ TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \ include ../lib.mk -BPFOBJ := $(OUTPUT)/libbpf.a $(OUTPUT)/cgroup_helpers.c +BPFOBJ := $(OUTPUT)/libbpf.a cgroup_helpers.c $(TEST_GEN_PROGS): $(BPFOBJ) @@ -58,7 +58,7 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline -%.o: %.c +$(OUTPUT)/%.o: %.c $(CLANG) $(CLANG_FLAGS) \ -O2 -target bpf -emit-llvm -c $< -o - | \ $(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@ diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 697bd83de295..c0f16e93f9bd 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -7780,6 +7780,20 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "XDP, using ifindex from netdev", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, ingress_ifindex)), + BPF_JMP_IMM(BPF_JLT, BPF_REG_2, 1, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .retval = 1, + }, + { "meta access, test1", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, |