From: Kumar Kartikeya Dwivedi memxor@gmail.com
mainline inclusion from mainline-5.14-rc1 commit 715c5ce454a6a9b94a1a4a3360de6a87eaf0d833 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I5EUVD CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
-------------------------------------------------
This adds functions that wrap the netlink API used for adding, manipulating, and removing traffic control filters.
The API summary:
A bpf_tc_hook represents a location where a TC-BPF filter can be attached. This means that creating a hook leads to creation of the backing qdisc, while destruction either removes all filters attached to a hook, or destroys qdisc if requested explicitly (as discussed below).
The TC-BPF API functions operate on this bpf_tc_hook to attach, replace, query, and detach tc filters. All functions return 0 on success, and a negative error code on failure.
bpf_tc_hook_create - Create a hook Parameters: @hook - Cannot be NULL, ifindex > 0, attach_point must be set to proper enum constant. Note that parent must be unset when attach_point is one of BPF_TC_INGRESS or BPF_TC_EGRESS. Note that as an exception BPF_TC_INGRESS|BPF_TC_EGRESS is also a valid value for attach_point.
Returns -EOPNOTSUPP when hook has attach_point as BPF_TC_CUSTOM.
bpf_tc_hook_destroy - Destroy a hook Parameters: @hook - Cannot be NULL. The behaviour depends on value of attach_point. If BPF_TC_INGRESS, all filters attached to the ingress hook will be detached. If BPF_TC_EGRESS, all filters attached to the egress hook will be detached. If BPF_TC_INGRESS|BPF_TC_EGRESS, the clsact qdisc will be deleted, also detaching all filters. As before, parent must be unset for these attach_points, and set for BPF_TC_CUSTOM.
It is advised that if the qdisc is operated on by many programs, then the program at least check that there are no other existing filters before deleting the clsact qdisc. An example is shown below:
DECLARE_LIBBPF_OPTS(bpf_tc_hook, .ifindex = if_nametoindex("lo"), .attach_point = BPF_TC_INGRESS); /* set opts as NULL, as we're not really interested in * getting any info for a particular filter, but just * detecting its presence. */ r = bpf_tc_query(&hook, NULL); if (r == -ENOENT) { /* no filters */ hook.attach_point = BPF_TC_INGRESS|BPF_TC_EGREESS; return bpf_tc_hook_destroy(&hook); } else { /* failed or r == 0, the latter means filters do exist */ return r; }
Note that there is a small race between checking for no filters and deleting the qdisc. This is currently unavoidable.
Returns -EOPNOTSUPP when hook has attach_point as BPF_TC_CUSTOM.
bpf_tc_attach - Attach a filter to a hook Parameters: @hook - Cannot be NULL. Represents the hook the filter will be attached to. Requirements for ifindex and attach_point are same as described in bpf_tc_hook_create, but BPF_TC_CUSTOM is also supported. In that case, parent must be set to the handle where the filter will be attached (using BPF_TC_PARENT). E.g. to set parent to 1:16 like in tc command line, the equivalent would be BPF_TC_PARENT(1, 16).
@opts - Cannot be NULL. The following opts are optional: * handle - The handle of the filter * priority - The priority of the filter Must be >= 0 and <= UINT16_MAX Note that when left unset, they will be auto-allocated by the kernel. The following opts must be set: * prog_fd - The fd of the loaded SCHED_CLS prog The following opts must be unset: * prog_id - The ID of the BPF prog The following opts are optional: * flags - Currently only BPF_TC_F_REPLACE is allowed. It allows replacing an existing filter instead of failing with -EEXIST. The following opts will be filled by bpf_tc_attach on a successful attach operation if they are unset: * handle - The handle of the attached filter * priority - The priority of the attached filter * prog_id - The ID of the attached SCHED_CLS prog This way, the user can know what the auto allocated values for optional opts like handle and priority are for the newly attached filter, if they were unset.
Note that some other attributes are set to fixed default values listed below (this holds for all bpf_tc_* APIs): protocol as ETH_P_ALL, direct action mode, chain index of 0, and class ID of 0 (this can be set by writing to the skb->tc_classid field from the BPF program).
bpf_tc_detach Parameters: @hook - Cannot be NULL. Represents the hook the filter will be detached from. Requirements are same as described above in bpf_tc_attach.
@opts - Cannot be NULL. The following opts must be set: * handle, priority The following opts must be unset: * prog_fd, prog_id, flags
bpf_tc_query Parameters: @hook - Cannot be NULL. Represents the hook where the filter lookup will be performed. Requirements are same as described above in bpf_tc_attach().
@opts - Cannot be NULL. The following opts must be set: * handle, priority The following opts must be unset: * prog_fd, prog_id, flags The following fields will be filled by bpf_tc_query upon a successful lookup: * prog_id
Some usage examples (using BPF skeleton infrastructure):
BPF program (test_tc_bpf.c):
#include <linux/bpf.h> #include <bpf/bpf_helpers.h>
SEC("classifier") int cls(struct __sk_buff *skb) { return 0; }
Userspace loader:
struct test_tc_bpf *skel = NULL; int fd, r;
skel = test_tc_bpf__open_and_load(); if (!skel) return -ENOMEM;
fd = bpf_program__fd(skel->progs.cls);
DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = if_nametoindex("lo"), .attach_point = BPF_TC_INGRESS); /* Create clsact qdisc */ r = bpf_tc_hook_create(&hook); if (r < 0) goto end;
DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .prog_fd = fd); r = bpf_tc_attach(&hook, &opts); if (r < 0) goto end; /* Print the auto allocated handle and priority */ printf("Handle=%u", opts.handle); printf("Priority=%u", opts.priority);
opts.prog_fd = opts.prog_id = 0; bpf_tc_detach(&hook, &opts); end: test_tc_bpf__destroy(skel);
This is equivalent to doing the following using tc command line: # tc qdisc add dev lo clsact # tc filter add dev lo ingress bpf obj foo.o sec classifier da # tc filter del dev lo ingress handle <h> prio <p> bpf ... where the handle and priority can be found using: # tc filter show dev lo ingress
Another example replacing a filter (extending prior example):
/* We can also choose both (or one), let's try replacing an * existing filter. */ DECLARE_LIBBPF_OPTS(bpf_tc_opts, replace_opts, .handle = opts.handle, .priority = opts.priority, .prog_fd = fd); r = bpf_tc_attach(&hook, &replace_opts); if (r == -EEXIST) { /* Expected, now use BPF_TC_F_REPLACE to replace it */ replace_opts.flags = BPF_TC_F_REPLACE; return bpf_tc_attach(&hook, &replace_opts); } else if (r < 0) { return r; } /* There must be no existing filter with these * attributes, so cleanup and return an error. */ replace_opts.prog_fd = replace_opts.prog_id = 0; bpf_tc_detach(&hook, &replace_opts); return -1;
To obtain info of a particular filter:
/* Find info for filter with handle 1 and priority 50 */ DECLARE_LIBBPF_OPTS(bpf_tc_opts, info_opts, .handle = 1, .priority = 50); r = bpf_tc_query(&hook, &info_opts); if (r == -ENOENT) printf("Filter not found"); else if (r < 0) return r; printf("Prog ID: %u", info_opts.prog_id); return 0;
Signed-off-by: Kumar Kartikeya Dwivedi memxor@gmail.com Co-developed-by: Daniel Borkmann daniel@iogearbox.net # libbpf API design [ Daniel: also did major patch cleanup ] Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Toke Høiland-Jørgensen toke@redhat.com Link: https://lore.kernel.org/bpf/20210512103451.989420-3-memxor@gmail.com
(cherry picked from commit 715c5ce454a6a9b94a1a4a3360de6a87eaf0d833) Signed-off-by: Wang Yufen wangyufen@huawei.com --- tools/lib/bpf/libbpf.h | 44 ++++ tools/lib/bpf/libbpf.map | 5 + tools/lib/bpf/netlink.c | 421 ++++++++++++++++++++++++++++++++++++++- 3 files changed, 469 insertions(+), 1 deletion(-)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 9f2c588faf3d..e2c0aaf20416 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -502,6 +502,7 @@ LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd);
+/* XDP related API */ struct xdp_link_info { __u32 prog_id; __u32 drv_prog_id; @@ -524,6 +525,49 @@ LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags);
+/* TC related API */ +enum bpf_tc_attach_point { + BPF_TC_INGRESS = 1 << 0, + BPF_TC_EGRESS = 1 << 1, + BPF_TC_CUSTOM = 1 << 2, +}; + +#define BPF_TC_PARENT(a, b) \ + ((((a) << 16) & 0xFFFF0000U) | ((b) & 0x0000FFFFU)) + +enum bpf_tc_flags { + BPF_TC_F_REPLACE = 1 << 0, +}; + +struct bpf_tc_hook { + size_t sz; + int ifindex; + enum bpf_tc_attach_point attach_point; + __u32 parent; + size_t :0; +}; +#define bpf_tc_hook__last_field parent + +struct bpf_tc_opts { + size_t sz; + int prog_fd; + __u32 flags; + __u32 prog_id; + __u32 handle; + __u32 priority; + size_t :0; +}; +#define bpf_tc_opts__last_field priority + +LIBBPF_API int bpf_tc_hook_create(struct bpf_tc_hook *hook); +LIBBPF_API int bpf_tc_hook_destroy(struct bpf_tc_hook *hook); +LIBBPF_API int bpf_tc_attach(const struct bpf_tc_hook *hook, + struct bpf_tc_opts *opts); +LIBBPF_API int bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts); +LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook, + struct bpf_tc_opts *opts); + /* Ring buffer APIs */ struct ring_buffer;
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 238830f75522..cd09c984ccdc 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -361,4 +361,9 @@ LIBBPF_0.4.0 { bpf_linker__new; bpf_map__inner_map; bpf_object__set_kversion; + bpf_tc_attach; + bpf_tc_detach; + bpf_tc_hook_create; + bpf_tc_hook_destroy; + bpf_tc_query; } LIBBPF_0.3.0; diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 8bbdc6c38f06..47444588e0d2 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -4,7 +4,10 @@ #include <stdlib.h> #include <memory.h> #include <unistd.h> +#include <arpa/inet.h> #include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/pkt_cls.h> #include <linux/rtnetlink.h> #include <sys/socket.h> #include <errno.h> @@ -78,6 +81,12 @@ static void libbpf_netlink_close(int sock) close(sock); }
+enum { + NL_CONT, + NL_NEXT, + NL_DONE, +}; + static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq, __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn, void *cookie) @@ -89,6 +98,7 @@ static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq, int len, ret;
while (multipart) { +start: multipart = false; len = recv(sock, buf, sizeof(buf), 0); if (len < 0) { @@ -126,8 +136,16 @@ static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq, } if (_fn) { ret = _fn(nh, fn, cookie); - if (ret) + switch (ret) { + case NL_CONT: + break; + case NL_NEXT: + goto start; + case NL_DONE: + return 0; + default: return ret; + } } } } @@ -353,3 +371,404 @@ int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
return ret; } + +typedef int (*qdisc_config_t)(struct nlmsghdr *nh, struct tcmsg *t, + size_t maxsz); + +static int clsact_config(struct nlmsghdr *nh, struct tcmsg *t, size_t maxsz) +{ + t->tcm_parent = TC_H_CLSACT; + t->tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0); + + return nlattr_add(nh, maxsz, TCA_KIND, "clsact", sizeof("clsact")); +} + +static int attach_point_to_config(struct bpf_tc_hook *hook, + qdisc_config_t *config) +{ + switch (OPTS_GET(hook, attach_point, 0)) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + case BPF_TC_INGRESS | BPF_TC_EGRESS: + if (OPTS_GET(hook, parent, 0)) + return -EINVAL; + *config = &clsact_config; + return 0; + case BPF_TC_CUSTOM: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +static int tc_get_tcm_parent(enum bpf_tc_attach_point attach_point, + __u32 *parent) +{ + switch (attach_point) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + if (*parent) + return -EINVAL; + *parent = TC_H_MAKE(TC_H_CLSACT, + attach_point == BPF_TC_INGRESS ? + TC_H_MIN_INGRESS : TC_H_MIN_EGRESS); + break; + case BPF_TC_CUSTOM: + if (!*parent) + return -EINVAL; + break; + default: + return -EINVAL; + } + return 0; +} + +static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags) +{ + qdisc_config_t config; + int ret; + struct { + struct nlmsghdr nh; + struct tcmsg tc; + char buf[256]; + } req; + + ret = attach_point_to_config(hook, &config); + if (ret < 0) + return ret; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags; + req.nh.nlmsg_type = cmd; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0); + + ret = config(&req.nh, &req.tc, sizeof(req)); + if (ret < 0) + return ret; + + return libbpf_netlink_send_recv(&req.nh, NULL, NULL, NULL); +} + +static int tc_qdisc_create_excl(struct bpf_tc_hook *hook) +{ + return tc_qdisc_modify(hook, RTM_NEWQDISC, NLM_F_CREATE); +} + +static int tc_qdisc_delete(struct bpf_tc_hook *hook) +{ + return tc_qdisc_modify(hook, RTM_DELQDISC, 0); +} + +int bpf_tc_hook_create(struct bpf_tc_hook *hook) +{ + if (!hook || !OPTS_VALID(hook, bpf_tc_hook) || + OPTS_GET(hook, ifindex, 0) <= 0) + return -EINVAL; + + return tc_qdisc_create_excl(hook); +} + +static int __bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts, + const bool flush); + +int bpf_tc_hook_destroy(struct bpf_tc_hook *hook) +{ + if (!hook || !OPTS_VALID(hook, bpf_tc_hook) || + OPTS_GET(hook, ifindex, 0) <= 0) + return -EINVAL; + + switch (OPTS_GET(hook, attach_point, 0)) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + return __bpf_tc_detach(hook, NULL, true); + case BPF_TC_INGRESS | BPF_TC_EGRESS: + return tc_qdisc_delete(hook); + case BPF_TC_CUSTOM: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +struct bpf_cb_ctx { + struct bpf_tc_opts *opts; + bool processed; +}; + +static int __get_tc_info(void *cookie, struct tcmsg *tc, struct nlattr **tb, + bool unicast) +{ + struct nlattr *tbb[TCA_BPF_MAX + 1]; + struct bpf_cb_ctx *info = cookie; + + if (!info || !info->opts) + return -EINVAL; + if (unicast && info->processed) + return -EINVAL; + if (!tb[TCA_OPTIONS]) + return NL_CONT; + + libbpf_nla_parse_nested(tbb, TCA_BPF_MAX, tb[TCA_OPTIONS], NULL); + if (!tbb[TCA_BPF_ID]) + return -EINVAL; + + OPTS_SET(info->opts, prog_id, libbpf_nla_getattr_u32(tbb[TCA_BPF_ID])); + OPTS_SET(info->opts, handle, tc->tcm_handle); + OPTS_SET(info->opts, priority, TC_H_MAJ(tc->tcm_info) >> 16); + + info->processed = true; + return unicast ? NL_NEXT : NL_DONE; +} + +static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct tcmsg *tc = NLMSG_DATA(nh); + struct nlattr *tb[TCA_MAX + 1]; + + libbpf_nla_parse(tb, TCA_MAX, + (struct nlattr *)((char *)tc + NLMSG_ALIGN(sizeof(*tc))), + NLMSG_PAYLOAD(nh, sizeof(*tc)), NULL); + if (!tb[TCA_KIND]) + return NL_CONT; + return __get_tc_info(cookie, tc, tb, nh->nlmsg_flags & NLM_F_ECHO); +} + +static int tc_add_fd_and_name(struct nlmsghdr *nh, size_t maxsz, int fd) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + char name[256]; + int len, ret; + + ret = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (ret < 0) + return ret; + + ret = nlattr_add(nh, maxsz, TCA_BPF_FD, &fd, sizeof(fd)); + if (ret < 0) + return ret; + len = snprintf(name, sizeof(name), "%s:[%u]", info.name, info.id); + if (len < 0) + return -errno; + if (len >= sizeof(name)) + return -ENAMETOOLONG; + return nlattr_add(nh, maxsz, TCA_BPF_NAME, name, len + 1); +} + +int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) +{ + __u32 protocol, bpf_flags, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct bpf_cb_ctx info = {}; + struct nlattr *nla; + struct { + struct nlmsghdr nh; + struct tcmsg tc; + char buf[256]; + } req; + + if (!hook || !opts || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return -EINVAL; + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || !prog_fd || prog_id) + return -EINVAL; + if (priority > UINT16_MAX) + return -EINVAL; + if (flags & ~BPF_TC_F_REPLACE) + return -EINVAL; + + flags = (flags & BPF_TC_F_REPLACE) ? NLM_F_REPLACE : NLM_F_EXCL; + protocol = ETH_P_ALL; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_CREATE | + NLM_F_ECHO | flags; + req.nh.nlmsg_type = RTM_NEWTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return ret; + req.tc.tcm_parent = parent; + + ret = nlattr_add(&req.nh, sizeof(req), TCA_KIND, "bpf", sizeof("bpf")); + if (ret < 0) + return ret; + nla = nlattr_begin_nested(&req.nh, sizeof(req), TCA_OPTIONS); + if (!nla) + return -EMSGSIZE; + ret = tc_add_fd_and_name(&req.nh, sizeof(req), prog_fd); + if (ret < 0) + return ret; + bpf_flags = TCA_BPF_FLAG_ACT_DIRECT; + ret = nlattr_add(&req.nh, sizeof(req), TCA_BPF_FLAGS, &bpf_flags, + sizeof(bpf_flags)); + if (ret < 0) + return ret; + nlattr_end_nested(&req.nh, nla); + + info.opts = opts; + + ret = libbpf_netlink_send_recv(&req.nh, get_tc_info, NULL, &info); + if (ret < 0) + return ret; + if (!info.processed) + return -ENOENT; + return ret; +} + +static int __bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts, + const bool flush) +{ + __u32 protocol = 0, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct { + struct nlmsghdr nh; + struct tcmsg tc; + char buf[256]; + } req; + + if (!hook || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return -EINVAL; + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || flags || prog_fd || prog_id) + return -EINVAL; + if (priority > UINT16_MAX) + return -EINVAL; + if (flags & ~BPF_TC_F_REPLACE) + return -EINVAL; + if (!flush) { + if (!handle || !priority) + return -EINVAL; + protocol = ETH_P_ALL; + } else { + if (handle || priority) + return -EINVAL; + } + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_DELTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + if (!flush) { + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + } + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return ret; + req.tc.tcm_parent = parent; + + if (!flush) { + ret = nlattr_add(&req.nh, sizeof(req), TCA_KIND, + "bpf", sizeof("bpf")); + if (ret < 0) + return ret; + } + + return libbpf_netlink_send_recv(&req.nh, NULL, NULL, NULL); +} + +int bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts) +{ + return !opts ? -EINVAL : __bpf_tc_detach(hook, opts, false); +} + +int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) +{ + __u32 protocol, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct bpf_cb_ctx info = {}; + struct { + struct nlmsghdr nh; + struct tcmsg tc; + char buf[256]; + } req; + + if (!hook || !opts || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return -EINVAL; + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || flags || prog_fd || prog_id || + !handle || !priority) + return -EINVAL; + if (priority > UINT16_MAX) + return -EINVAL; + + protocol = ETH_P_ALL; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST; + req.nh.nlmsg_type = RTM_GETTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return ret; + req.tc.tcm_parent = parent; + + ret = nlattr_add(&req.nh, sizeof(req), TCA_KIND, "bpf", sizeof("bpf")); + if (ret < 0) + return ret; + + info.opts = opts; + + ret = libbpf_netlink_send_recv(&req.nh, get_tc_info, NULL, &info); + if (ret < 0) + return ret; + if (!info.processed) + return -ENOENT; + return ret; +}