diff options
Diffstat (limited to 'tools')
| -rw-r--r-- | tools/bpf/bpftool/Documentation/bpftool-prog.rst | 3 | ||||
| -rw-r--r-- | tools/bpf/bpftool/prog.c | 3 | ||||
| -rw-r--r-- | tools/include/uapi/linux/bpf.h | 1784 | ||||
| -rw-r--r-- | tools/include/uapi/linux/btf.h | 8 | ||||
| -rw-r--r-- | tools/lib/bpf/btf.c | 2 | ||||
| -rw-r--r-- | tools/lib/bpf/libbpf.c | 4 | ||||
| -rw-r--r-- | tools/lib/bpf/libbpf.h | 2 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/.gitignore | 1 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/Makefile | 10 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/bpf_helpers.h | 4 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/test_sockmap.c | 1464 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/test_sockmap_kern.c | 340 | ||||
| -rwxr-xr-x | tools/testing/selftests/bpf/test_tunnel.sh | 729 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/test_tunnel_kern.c | 713 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/test_verifier.c | 266 |
15 files changed, 4931 insertions, 402 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 67ca6c69376c..43d34a5c3ec5 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -95,7 +95,7 @@ EXAMPLES **# bpftool prog show** :: - 10: xdp name some_prog tag 005a3d2123620c8b + 10: xdp name some_prog tag 005a3d2123620c8b gpl loaded_at Sep 29/20:11 uid 0 xlated 528B jited 370B memlock 4096B map_ids 10 @@ -108,6 +108,7 @@ EXAMPLES "id": 10, "type": "xdp", "tag": "005a3d2123620c8b", + "gpl_compatible": true, "loaded_at": "Sep 29/20:11", "uid": 0, "bytes_xlated": 528, diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 548adb9b7317..e71a0a11afde 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -235,6 +235,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) info->tag[0], info->tag[1], info->tag[2], info->tag[3], info->tag[4], info->tag[5], info->tag[6], info->tag[7]); + jsonw_bool_field(json_wtr, "gpl_compatible", info->gpl_compatible); + print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -295,6 +297,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) printf("tag "); fprint_hex(stdout, info->tag, BPF_TAG_SIZE, ""); print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); + printf("%s", info->gpl_compatible ? " gpl" : ""); printf("\n"); if (info->load_time) { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c8383a289f7b..da77a9388947 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -377,403 +377,1396 @@ union bpf_attr { }; } __attribute__((aligned(8))); -/* BPF helper function descriptions: - * - * void *bpf_map_lookup_elem(&map, &key) - * Return: Map value or NULL - * - * int bpf_map_update_elem(&map, &key, &value, flags) - * Return: 0 on success or negative error - * - * int bpf_map_delete_elem(&map, &key) - * Return: 0 on success or negative error - * - * int bpf_probe_read(void *dst, int size, void *src) - * Return: 0 on success or negative error +/* The description below is an attempt at providing documentation to eBPF + * developers about the multiple available eBPF helper functions. It can be + * parsed and used to produce a manual page. The workflow is the following, + * and requires the rst2man utility: + * + * $ ./scripts/bpf_helpers_doc.py \ + * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst + * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 + * $ man /tmp/bpf-helpers.7 + * + * Note that in order to produce this external documentation, some RST + * formatting is used in the descriptions to get "bold" and "italics" in + * manual pages. Also note that the few trailing white spaces are + * intentional, removing them would break paragraphs for rst2man. + * + * Start of BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key) + * Description + * Perform a lookup in *map* for an entry associated to *key*. + * Return + * Map value associated to *key*, or **NULL** if no entry was + * found. + * + * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + * Description + * Add or update the value of the entry associated to *key* in + * *map* with *value*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_delete_elem(struct bpf_map *map, const void *key) + * Description + * Delete entry with *key* from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read(void *dst, u32 size, const void *src) + * Description + * For tracing programs, safely attempt to read *size* bytes from + * address *src* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_ktime_get_ns(void) - * Return: current ktime - * - * int bpf_trace_printk(const char *fmt, int fmt_size, ...) - * Return: length of buffer written or negative error - * - * u32 bpf_prandom_u32(void) - * Return: random value - * - * u32 bpf_raw_smp_processor_id(void) - * Return: SMP processor ID - * - * int bpf_skb_store_bytes(skb, offset, from, len, flags) - * store bytes into packet - * @skb: pointer to skb - * @offset: offset within packet from skb->mac_header - * @from: pointer where to copy bytes from - * @len: number of bytes to store into packet - * @flags: bit 0 - if true, recompute skb->csum - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l3_csum_replace(skb, offset, from, to, flags) - * recompute IP checksum - * @skb: pointer to skb - * @offset: offset within packet where IP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l4_csum_replace(skb, offset, from, to, flags) - * recompute TCP/UDP checksum - * @skb: pointer to skb - * @offset: offset within packet where TCP/UDP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * bit 4 - is pseudo header - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_tail_call(ctx, prog_array_map, index) - * jump into another BPF program - * @ctx: context pointer passed to next program - * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: 32-bit index inside array that selects specific program to run - * Return: 0 on success or negative error - * - * int bpf_clone_redirect(skb, ifindex, flags) - * redirect to another netdev - * @skb: pointer to skb - * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: 0 on success or negative error + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Return + * Current *ktime*. + * + * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...) + * Description + * This helper is a "printk()-like" facility for debugging. It + * prints a message defined by format *fmt* (of size *fmt_size*) + * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * available. It can take up to three additional **u64** + * arguments (as an eBPF helpers, the total number of arguments is + * limited to five). + * + * Each time the helper is called, it appends a line to the trace. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *README* file under the same directory). However, it usually + * defaults to something like: + * + * :: + * + * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg> + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ``<formatted msg>`` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * bloc (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * u32 bpf_get_prandom_u32(void) + * Description + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * Return + * A random 32-bit unsigned value. + * + * u32 bpf_get_smp_processor_id(void) + * Description + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with preemption disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * Return + * The SMP id of the processor running the program. + * + * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. *flags* are a combination of + * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the + * checksum for the packet after storing the bytes) and + * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ + * **->swhash** and *skb*\ **->l4hash** to 0). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * Description + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * Description + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * the checksum is to be computed against a pseudo-header. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * Description + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 32. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * Description + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) - * Return: current->tgid << 32 | current->pid + * Return + * A 64-bit integer containing the current tgid and pid, and + * created as such: + * *current_task*\ **->tgid << 32 \|** + * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) - * Return: current_gid << 32 | current_uid - * - * int bpf_get_current_comm(char *buf, int size_of_buf) - * stores current->comm into buf - * Return: 0 on success or negative error - * - * u32 bpf_get_cgroup_classid(skb) - * retrieve a proc's classid - * @skb: pointer to skb - * Return: classid if != 0 - * - * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) - * Return: 0 on success or negative error - * - * int bpf_skb_vlan_pop(skb) - * Return: 0 on success or negative error - * - * int bpf_skb_get_tunnel_key(skb, key, size, flags) - * int bpf_skb_set_tunnel_key(skb, key, size, flags) - * retrieve or populate tunnel metadata - * @skb: pointer to skb - * @key: pointer to 'struct bpf_tunnel_key' - * @size: size of 'struct bpf_tunnel_key' - * @flags: room for future extensions - * Return: 0 on success or negative error - * - * u64 bpf_perf_event_read(map, flags) - * read perf event counter value - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * Return: value of perf event counter read or error code - * - * int bpf_redirect(ifindex, flags) - * redirect to another netdev - * @ifindex: ifindex of the net device - * @flags: - * cls_bpf: - * bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * xdp_bpf: - * all bits - reserved - * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error - * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error - * int bpf_redirect_map(map, key, flags) - * redirect to endpoint in map - * @map: pointer to dev map - * @key: index in map to lookup - * @flags: -- - * Return: XDP_REDIRECT on success or XDP_ABORT on error - * - * u32 bpf_get_route_realm(skb) - * retrieve a dst's tclassid - * @skb: pointer to skb - * Return: realm if != 0 - * - * int bpf_perf_event_output(ctx, map, flags, data, size) - * output perf raw sample - * @ctx: struct pt_regs* - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @data: data on stack to be output as raw data - * @size: size of data - * Return: 0 on success or negative error - * - * int bpf_get_stackid(ctx, map, flags) - * walk user or kernel stack and return id - * @ctx: struct pt_regs* - * @map: pointer to stack_trace map - * @flags: bits 0-7 - numer of stack frames to skip - * bit 8 - collect user stack instead of kernel - * bit 9 - compare stacks by hash only - * bit 10 - if two different stacks hash into the same stackid - * discard old - * other bits - reserved - * Return: >= 0 stackid on success or negative error - * - * s64 bpf_csum_diff(from, from_size, to, to_size, seed) - * calculate csum diff - * @from: raw from buffer - * @from_size: length of from buffer - * @to: raw to buffer - * @to_size: length of to buffer - * @seed: optional seed - * Return: csum result or negative error code - * - * int bpf_skb_get_tunnel_opt(skb, opt, size) - * retrieve tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: option size - * - * int bpf_skb_set_tunnel_opt(skb, opt, size) - * populate tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: 0 on success or negative error - * - * int bpf_skb_change_proto(skb, proto, flags) - * Change protocol of the skb. Currently supported is v4 -> v6, - * v6 -> v4 transitions. The helper will also resize the skb. eBPF - * program is expected to fill the new headers via skb_store_bytes - * and lX_csum_replace. - * @skb: pointer to skb - * @proto: new skb->protocol type - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_change_type(skb, type) - * Change packet type of skb. - * @skb: pointer to skb - * @type: new skb->pkt_type type - * Return: 0 on success or negative error - * - * int bpf_skb_under_cgroup(skb, map, index) - * Check cgroup2 membership of skb - * @skb: pointer to skb - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 skb failed the cgroup2 descendant test - * == 1 skb succeeded the cgroup2 descendant test - * < 0 error - * - * u32 bpf_get_hash_recalc(skb) - * Retrieve and possibly recalculate skb->hash. - * @skb: pointer to skb - * Return: hash + * Return + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + * + * int bpf_get_current_comm(char *buf, u32 size_of_buf) + * Description + * Copy the **comm** attribute of the current task into *buf* of + * *size_of_buf*. The **comm** attribute contains the name of + * the executable (excluding the path) for the current task. The + * *size_of_buf* must be strictly positive. On success, the + * helper makes sure that the *buf* is NUL-terminated. On failure, + * it is filled with zeroes. + * Return + * 0 on success, or a negative error in case of failure. + * + * u32 bpf_get_cgroup_classid(struct sk_buff *skb) + * Description + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/cgroup-v1/net_cls.txt*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * Return + * The classid, or 0 for the default unconfigured classid. + * + * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * Description + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_vlan_pop(struct sk_buff *skb) + * Description + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags) + * Description + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read*\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with bpf_perf_event_read_value(), which at the same time + * provides more features over the **bpf_perf_event_read**\ () + * interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * Return + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + * + * int bpf_redirect(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can be attained with the more generic + * **bpf_redirect_map**\ (), which requires specific maps to be + * used but offers better performance. + * Return + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + * + * u32 bpf_get_route_realm(struct sk_buff *skb) + * Description + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * indentifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * Return + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + * + * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output_kern.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) + * Description + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags) + * Description + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * + * Return + * The positive or null stack id on success, or a negative error + * in case of failure. + * + * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed) + * Description + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * Return + * The checksum result, or a negative error code in case of + * failure. + * + * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * Return + * The size of the option data retrieved. + * + * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * Description + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_type(struct sk_buff *skb, u32 type) + * Description + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * Description + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + * + * u32 bpf_get_hash_recalc(struct sk_buff *skb) + * Description + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * Return + * The 32-bit hash. * * u64 bpf_get_current_task(void) - * Returns current task_struct - * Return: current - * - * int bpf_probe_write_user(void *dst, void *src, int len) - * safely attempt to write to a location - * @dst: destination address in userspace - * @src: source address on stack - * @len: number of bytes to copy - * Return: 0 on success or negative error - * - * int bpf_current_task_under_cgroup(map, index) - * Check cgroup2 membership of current task - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 current failed the cgroup2 descendant test - * == 1 current succeeded the cgroup2 descendant test - * < 0 error - * - * int bpf_skb_change_tail(skb, len, flags) - * The helper will resize the skb to the given new size, to be used f.e. - * with control messages. - * @skb: pointer to skb - * @len: new skb length - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_pull_data(skb, len) - * The helper will pull in non-linear data in case the skb is non-linear - * and not all of len are part of the linear section. Only needed for - * read/write with direct packet access. - * @skb: pointer to skb - * @len: len to make read/writeable - * Return: 0 on success or negative error - * - * s64 bpf_csum_update(skb, csum) - * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. - * @skb: pointer to skb - * @csum: csum to add - * Return: csum on success or negative error - * - * void bpf_set_hash_invalid(skb) - * Invalidate current skb->hash. - * @skb: pointer to skb - * - * int bpf_get_numa_node_id() - * Return: Id of current NUMA node. - * - * int bpf_skb_change_head() - * Grows headroom of skb and adjusts MAC header offset accordingly. - * Will extends/reallocae as required automatically. - * May change skb data pointer and will thus invalidate any check - * performed for direct packet access. - * @skb: pointer to skb - * @len: length of header to be pushed in front - * @flags: Flags (unused for now) - * Return: 0 on success or negative error - * - * int bpf_xdp_adjust_head(xdp_md, delta) - * Adjust the xdp_md.data by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data - * Return: 0 on success or negative on error + * Return + * A pointer to the current task struct. + * + * int bpf_probe_write_user(void *dst, const void *src, u32 len) + * Description + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * Description + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* task belongs to the cgroup2. + * * 1, if the *skb* task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + * + * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * Description + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then the whole length of the *skb* is pulled. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum) + * Description + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * Return + * The checksum on success, or a negative error code in case of + * failure. + * + * void bpf_set_hash_invalid(struct sk_buff *skb) + * Description + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * + * int bpf_get_numa_node_id(void) + * Description + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * Return + * The id of current NUMA node. + * + * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. * * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) - * Copy a NUL terminated string from unsafe address. In case the string - * length is smaller than size, the target is not padded with further NUL - * bytes. In case the string length is larger than size, just count-1 - * bytes are copied and the last byte is set to NUL. - * @dst: destination address - * @size: maximum number of bytes to copy, including the trailing NUL - * @unsafe_ptr: unsafe address - * Return: - * > 0 length of the string including the trailing NUL on success - * < 0 error - * - * u64 bpf_get_socket_cookie(skb) - * Get the cookie for the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: 8 Bytes non-decreasing number on success or 0 if the socket - * field is missing inside sk_buff - * - * u32 bpf_get_socket_uid(skb) - * Get the owner uid of the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: uid of the socket owner on success or overflowuid if failed. - * - * u32 bpf_set_hash(skb, hash) - * Set full skb->hash. - * @skb: pointer to skb - * @hash: hash to set - * - * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen) - * Calls setsockopt. Not all opts are available, only those with - * integer optvals plus TCP_CONGESTION. - * Supported levels: SOL_SOCKET and IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: SOL_SOCKET or IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen) - * Calls getsockopt. Not all opts are available. - * Supported levels: IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags) - * Set callback flags for sock_ops - * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct - * @flags: flags value - * Return: 0 for no error - * -EINVAL if there is no full tcp socket - * bits in flags that are not supported by current kernel - * - * int bpf_skb_adjust_room(skb, len_diff, mode, flags) - * Grow or shrink room in sk_buff. - * @skb: pointer to skb - * @len_diff: (signed) amount of room to grow/shrink - * @mode: operation mode (enum bpf_adj_room_mode) - * @flags: reserved for future use - * Return: 0 on success or negative error code - * - * int bpf_sk_redirect_map(map, key, flags) - * Redirect skb to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_PASS - * - * int bpf_sock_map_update(skops, map, key, flags) - * @skops: pointer to bpf_sock_ops - * @map: pointer to sockmap to update - * @key: key to insert/update sock in map - * @flags: same flags as map update elem - * - * int bpf_xdp_adjust_meta(xdp_md, delta) - * Adjust the xdp_md.data_meta by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data_meta - * Return: 0 on success or negative on error - * - * int bpf_perf_event_read_value(map, flags, buf, buf_size) - * read perf event counter value and perf event enabled/running time - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @buf: buf to fill - * @buf_size: size of the buf - * Return: 0 on success or negative error code - * - * int bpf_perf_prog_read_value(ctx, buf, buf_size) - * read perf prog attached perf event counter and enabled/running time - * @ctx: pointer to ctx - * @buf: buf to fill - * @buf_size: size of the buf - * Return : 0 on success or negative error code - * - * int bpf_override_return(pt_regs, rc) - * @pt_regs: pointer to struct pt_regs - * @rc: the return value to set - * - * int bpf_msg_redirect_map(map, key, flags) - * Redirect msg to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_PASS - * - * int bpf_bind(ctx, addr, addr_len) - * Bind socket to address. Only binding to IP is supported, no port can be - * set in addr. - * @ctx: pointer to context of type bpf_sock_addr - * @addr: pointer to struct sockaddr to bind socket to - * @addr_len: length of sockaddr structure - * Return: 0 on success or negative error code - * - * int bpf_xdp_adjust_tail(xdp_md, delta) - * Adjust the xdp_md.data_end by delta. Only shrinking of packet's - * size is supported. - * @xdp_md: pointer to xdp_md - * @delta: A negative integer to be added to xdp_md.data_end - * Return: 0 on success or negative on error + * Description + * Copy a NUL terminated string from an unsafe address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read()** helper here instead + * to read the string would require to estimate the length at + * compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * u64 bpf_get_socket_cookie(struct sk_buff *skb) + * Description + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a unique socket + * identifier per namespace. + * Return + * A 8-byte long non-decreasing number on success, or 0 if the + * socket field is missing inside *skb*. + * + * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Return + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + * + * u32 bpf_set_hash(struct sk_buff *skb, u32 hash) + * Description + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * Return + * 0 + * + * int bpf_setsockopt(struct bpf_sock_ops_kern *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **setsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * Description + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * There is a single supported mode at this time: + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed below the layer 3 header). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * When used to redirect packets to net devices, this helper + * provides a high performance increase over **bpf_redirect**\ (). + * This is due to various implementation details of the underlying + * mechanisms, one of which is the fact that **bpf_redirect_map**\ + * () tries to send packet as a "bulk" to the device. + * Return + * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * + * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sock_map_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * the time running for event since last normalization. The + * enabled and running times are accumulated since the perf event + * open. To achieve scaling factor between two invocations of an + * eBPF program, users can can use CPU id as the key (which is + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_prog_read_value(struct bpf_perf_event_data_kern *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * For en eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_getsockopt(struct bpf_sock_ops_kern *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **getsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the following *level*\ s: + * + * * **IPPROTO_TCP**, which supports *optname* + * **TCP_CONGESTION**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_override_return(struct pt_reg *regs, u64 rc) + * Description + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting setting the PC (program counter) + * to an override function which is run in place of the original + * probed function. This means the probed function is not run at + * all. The replacement function just returns with the required + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * + * Also, the helper is only available for the architectures having + * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, + * x86 architecture is the only one to support this feature. + * Return + * 0 + * + * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops_kern *bpf_sock, int argval) + * Description + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * The supported callback values that *argval* can combine are: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * Return + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + * + * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * Return + * 0 + * + * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * Return + * 0 + * + * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * Description + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_bind(struct bpf_sock_addr_kern *ctx, struct sockaddr *addr, int addr_len) + * Description + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * This helper works for IPv4 and IPv6, TCP and UDP sockets. The + * domain (*addr*\ **->sa_family**) must be **AF_INET** (or + * **AF_INET6**). Looking for a free port to bind to can be + * expensive, therefore binding to port is not permitted by the + * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) + * must be set to zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * only possible to shrink the packet as of this writing, + * therefore *delta* must be a negative integer. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * Description + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -841,7 +1834,8 @@ union bpf_attr { FN(msg_cork_bytes), \ FN(msg_pull_data), \ FN(bind), \ - FN(xdp_adjust_tail), + FN(xdp_adjust_tail), \ + FN(skb_get_xfrm_state), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -947,6 +1941,19 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* user accessible mirror of in-kernel xfrm_state. + * new fields can only be added to the end of this structure + */ +struct bpf_xfrm_state { + __u32 reqid; + __u32 spi; /* Stored in network byte order */ + __u16 family; + union { + __u32 remote_ipv4; /* Stored in network byte order */ + __u32 remote_ipv6[4]; /* Stored in network byte order */ + }; +}; + /* Generic BPF return codes which all BPF program types may support. * The values are binary compatible with their TC_ACT_* counter-part to * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT @@ -1037,6 +2044,7 @@ struct bpf_prog_info { __aligned_u64 map_ids; char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; + __u32 gpl_compatible:1; __u64 netns_dev; __u64 netns_ino; } __attribute__((aligned(8))); diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 74a30b1090df..bcb56ee47014 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -6,9 +6,7 @@ #include <linux/types.h> #define BTF_MAGIC 0xeB9F -#define BTF_MAGIC_SWAP 0x9FeB #define BTF_VERSION 1 -#define BTF_FLAGS_COMPR 0x01 struct btf_header { __u16 magic; @@ -43,7 +41,7 @@ struct btf_header { #define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET) struct btf_type { - __u32 name; + __u32 name_off; /* "info" bits arrangement * bits 0-15: vlen (e.g. # of struct's members) * bits 16-23: unused @@ -105,7 +103,7 @@ struct btf_type { * info in "struct btf_type"). */ struct btf_enum { - __u32 name; + __u32 name_off; __s32 val; }; @@ -122,7 +120,7 @@ struct btf_array { * "struct btf_type"). */ struct btf_member { - __u32 name; + __u32 name_off; __u32 type; __u32 offset; /* offset in bits */ }; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 58b6255abc7a..2bac710e3194 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -281,7 +281,7 @@ int32_t btf__find_by_name(const struct btf *btf, const char *type_name) for (i = 1; i <= btf->nr_types; i++) { const struct btf_type *t = btf->types[i]; - const char *name = btf_name_by_offset(btf, t->name); + const char *name = btf_name_by_offset(btf, t->name_off); if (name && !strcmp(type_name, name)) return i; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 6513e0b08795..7bcdca13083a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1961,8 +1961,8 @@ BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); -static void bpf_program__set_expected_attach_type(struct bpf_program *prog, - enum bpf_attach_type type) +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type) { prog->expected_attach_type = type; } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index d6ac4fa6f472..197f9ce2248c 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -193,6 +193,8 @@ int bpf_program__set_sched_act(struct bpf_program *prog); int bpf_program__set_xdp(struct bpf_program *prog); int bpf_program__set_perf_event(struct bpf_program *prog); void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type); bool bpf_program__is_socket_filter(struct bpf_program *prog); bool bpf_program__is_tracepoint(struct bpf_program *prog); diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 5e1ab2f0eb79..3e3b3ced3f7c 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -15,3 +15,4 @@ test_libbpf_open test_sock test_sock_addr urandom_read +test_btf diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 0b72cc7596f1..b64a7a39cbc8 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -24,7 +24,7 @@ urandom_read: urandom_read.c # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ - test_sock test_sock_addr test_btf + test_sock test_btf test_sockmap TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ @@ -32,7 +32,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \ sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \ sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \ - test_btf_haskv.o test_btf_nokv.o + test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ @@ -40,10 +40,11 @@ TEST_PROGS := test_kmod.sh \ test_xdp_redirect.sh \ test_xdp_meta.sh \ test_offload.py \ - test_sock_addr.sh + test_sock_addr.sh \ + test_tunnel.sh # Compile but not part of 'make run_tests' -TEST_GEN_PROGS_EXTENDED = test_libbpf_open +TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr include ../lib.mk @@ -56,6 +57,7 @@ $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c $(OUTPUT)/test_sock: cgroup_helpers.c $(OUTPUT)/test_sock_addr: cgroup_helpers.c +$(OUTPUT)/test_sockmap: cgroup_helpers.c .PHONY: force diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 9271576bdc8f..69d7b918e66a 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -98,7 +98,9 @@ static int (*bpf_bind)(void *ctx, void *addr, int addr_len) = (void *) BPF_FUNC_bind; static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) = (void *) BPF_FUNC_xdp_adjust_tail; - +static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state, + int size, int flags) = + (void *) BPF_FUNC_skb_get_xfrm_state; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c new file mode 100644 index 000000000000..29c022d23f4e --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -0,0 +1,1464 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <sys/ioctl.h> +#include <sys/select.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <sys/ioctl.h> +#include <stdbool.h> +#include <signal.h> +#include <fcntl.h> +#include <sys/wait.h> +#include <time.h> +#include <sched.h> + +#include <sys/time.h> +#include <sys/resource.h> +#include <sys/types.h> +#include <sys/sendfile.h> + +#include <linux/netlink.h> +#include <linux/socket.h> +#include <linux/sock_diag.h> +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <assert.h> +#include <libgen.h> + +#include <getopt.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_util.h" +#include "bpf_rlimit.h" +#include "cgroup_helpers.h" + +int running; +static void running_handler(int a); + +/* randomly selected ports for testing on lo */ +#define S1_PORT 10000 +#define S2_PORT 10001 + +#define BPF_FILENAME "test_sockmap_kern.o" +#define CG_PATH "/sockmap" + +/* global sockets */ +int s1, s2, c1, c2, p1, p2; +int test_cnt; +int passed; +int failed; +int map_fd[8]; +struct bpf_map *maps[8]; +int prog_fd[11]; + +int txmsg_pass; +int txmsg_noisy; +int txmsg_redir; +int txmsg_redir_noisy; +int txmsg_drop; +int txmsg_apply; +int txmsg_cork; +int txmsg_start; +int txmsg_end; +int txmsg_ingress; +int txmsg_skb; + +static const struct option long_options[] = { + {"help", no_argument, NULL, 'h' }, + {"cgroup", required_argument, NULL, 'c' }, + {"rate", required_argument, NULL, 'r' }, + {"verbose", no_argument, NULL, 'v' }, + {"iov_count", required_argument, NULL, 'i' }, + {"length", required_argument, NULL, 'l' }, + {"test", required_argument, NULL, 't' }, + {"data_test", no_argument, NULL, 'd' }, + {"txmsg", no_argument, &txmsg_pass, 1 }, + {"txmsg_noisy", no_argument, &txmsg_noisy, 1 }, + {"txmsg_redir", no_argument, &txmsg_redir, 1 }, + {"txmsg_redir_noisy", no_argument, &txmsg_redir_noisy, 1}, + {"txmsg_drop", no_argument, &txmsg_drop, 1 }, + {"txmsg_apply", required_argument, NULL, 'a'}, + {"txmsg_cork", required_argument, NULL, 'k'}, + {"txmsg_start", required_argument, NULL, 's'}, + {"txmsg_end", required_argument, NULL, 'e'}, + {"txmsg_ingress", no_argument, &txmsg_ingress, 1 }, + {"txmsg_skb", no_argument, &txmsg_skb, 1 }, + {0, 0, NULL, 0 } +}; + +static void usage(char *argv[]) +{ + int i; + + printf(" Usage: %s --cgroup <cgroup_path>\n", argv[0]); + printf(" options:\n"); + for (i = 0; long_options[i].name != 0; i++) { + printf(" --%-12s", long_options[i].name); + if (long_options[i].flag != NULL) + printf(" flag (internal value:%d)\n", + *long_options[i].flag); + else + printf(" -%c\n", long_options[i].val); + } + printf("\n"); +} + +static int sockmap_init_sockets(int verbose) +{ + int i, err, one = 1; + struct sockaddr_in addr; + int *fds[4] = {&s1, &s2, &c1, &c2}; + + s1 = s2 = p1 = p2 = c1 = c2 = 0; + + /* Init sockets */ + for (i = 0; i < 4; i++) { + *fds[i] = socket(AF_INET, SOCK_STREAM, 0); + if (*fds[i] < 0) { + perror("socket s1 failed()"); + return errno; + } + } + + /* Allow reuse */ + for (i = 0; i < 2; i++) { + err = setsockopt(*fds[i], SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)); + if (err) { + perror("setsockopt failed()"); + return errno; + } + } + + /* Non-blocking sockets */ + for (i = 0; i < 2; i++) { + err = ioctl(*fds[i], FIONBIO, (char *)&one); + if (err < 0) { + perror("ioctl s1 failed()"); + return errno; + } + } + + /* Bind server sockets */ + memset(&addr, 0, sizeof(struct sockaddr_in)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = inet_addr("127.0.0.1"); + + addr.sin_port = htons(S1_PORT); + err = bind(s1, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + perror("bind s1 failed()\n"); + return errno; + } + + addr.sin_port = htons(S2_PORT); + err = bind(s2, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + perror("bind s2 failed()\n"); + return errno; + } + + /* Listen server sockets */ + addr.sin_port = htons(S1_PORT); + err = listen(s1, 32); + if (err < 0) { + perror("listen s1 failed()\n"); + return errno; + } + + addr.sin_port = htons(S2_PORT); + err = listen(s2, 32); + if (err < 0) { + perror("listen s1 failed()\n"); + return errno; + } + + /* Initiate Connect */ + addr.sin_port = htons(S1_PORT); + err = connect(c1, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0 && errno != EINPROGRESS) { + perror("connect c1 failed()\n"); + return errno; + } + + addr.sin_port = htons(S2_PORT); + err = connect(c2, (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0 && errno != EINPROGRESS) { + perror("connect c2 failed()\n"); + return errno; + } else if (err < 0) { + err = 0; + } + + /* Accept Connecrtions */ + p1 = accept(s1, NULL, NULL); + if (p1 < 0) { + perror("accept s1 failed()\n"); + return errno; + } + + p2 = accept(s2, NULL, NULL); + if (p2 < 0) { + perror("accept s1 failed()\n"); + return errno; + } + + if (verbose) { + printf("connected sockets: c1 <-> p1, c2 <-> p2\n"); + printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n", + c1, s1, c2, s2); + } + return 0; +} + +struct msg_stats { + size_t bytes_sent; + size_t bytes_recvd; + struct timespec start; + struct timespec end; +}; + +struct sockmap_options { + int verbose; + bool base; + bool sendpage; + bool data_test; + bool drop_expected; + int iov_count; + int iov_length; + int rate; +}; + +static int msg_loop_sendpage(int fd, int iov_length, int cnt, + struct msg_stats *s, + struct sockmap_options *opt) +{ + bool drop = opt->drop_expected; + unsigned char k = 0; + FILE *file; + int i, fp; + + file = fopen(".sendpage_tst.tmp", "w+"); + for (i = 0; i < iov_length * cnt; i++, k++) + fwrite(&k, sizeof(char), 1, file); + fflush(file); + fseek(file, 0, SEEK_SET); + fclose(file); + + fp = open(".sendpage_tst.tmp", O_RDONLY); + clock_gettime(CLOCK_MONOTONIC, &s->start); + for (i = 0; i < cnt; i++) { + int sent = sendfile(fd, fp, NULL, iov_length); + + if (!drop && sent < 0) { + perror("send loop error:"); + close(fp); + return sent; + } else if (drop && sent >= 0) { + printf("sendpage loop error expected: %i\n", sent); + close(fp); + return -EIO; + } + + if (sent > 0) + s->bytes_sent += sent; + } + clock_gettime(CLOCK_MONOTONIC, &s->end); + close(fp); + return 0; +} + +static int msg_loop(int fd, int iov_count, int iov_length, int cnt, + struct msg_stats *s, bool tx, + struct sockmap_options *opt) +{ + struct msghdr msg = {0}; + int err, i, flags = MSG_NOSIGNAL; + struct iovec *iov; + unsigned char k; + bool data_test = opt->data_test; + bool drop = opt->drop_expected; + + iov = calloc(iov_count, sizeof(struct iovec)); + if (!iov) + return errno; + + k = 0; + for (i = 0; i < iov_count; i++) { + unsigned char *d = calloc(iov_length, sizeof(char)); + + if (!d) { + fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count); + goto out_errno; + } + iov[i].iov_base = d; + iov[i].iov_len = iov_length; + + if (data_test && tx) { + int j; + + for (j = 0; j < iov_length; j++) + d[j] = k++; + } + } + + msg.msg_iov = iov; + msg.msg_iovlen = iov_count; + k = 0; + + if (tx) { + clock_gettime(CLOCK_MONOTONIC, &s->start); + for (i = 0; i < cnt; i++) { + int sent = sendmsg(fd, &msg, flags); + + if (!drop && sent < 0) { + perror("send loop error:"); + goto out_errno; + } else if (drop && sent >= 0) { + printf("send loop error expected: %i\n", sent); + errno = -EIO; + goto out_errno; + } + if (sent > 0) + s->bytes_sent += sent; + } + clock_gettime(CLOCK_MONOTONIC, &s->end); + } else { + int slct, recv, max_fd = fd; + int fd_flags = O_NONBLOCK; + struct timeval timeout; + float total_bytes; + fd_set w; + + fcntl(fd, fd_flags); + total_bytes = (float)iov_count * (float)iov_length * (float)cnt; + err = clock_gettime(CLOCK_MONOTONIC, &s->start); + if (err < 0) + perror("recv start time: "); + while (s->bytes_recvd < total_bytes) { + timeout.tv_sec = 0; + timeout.tv_usec = 10; + + /* FD sets */ + FD_ZERO(&w); + FD_SET(fd, &w); + + slct = select(max_fd + 1, &w, NULL, NULL, &timeout); + if (slct == -1) { + perror("select()"); + clock_gettime(CLOCK_MONOTONIC, &s->end); + goto out_errno; + } else if (!slct) { + if (opt->verbose) + fprintf(stderr, "unexpected timeout\n"); + errno = -EIO; + clock_gettime(CLOCK_MONOTONIC, &s->end); + goto out_errno; + } + + recv = recvmsg(fd, &msg, flags); + if (recv < 0) { + if (errno != EWOULDBLOCK) { + clock_gettime(CLOCK_MONOTONIC, &s->end); + perror("recv failed()\n"); + goto out_errno; + } + } + + s->bytes_recvd += recv; + + if (data_test) { + int j; + + for (i = 0; i < msg.msg_iovlen; i++) { + unsigned char *d = iov[i].iov_base; + + for (j = 0; + j < iov[i].iov_len && recv; j++) { + if (d[j] != k++) { + errno = -EIO; + fprintf(stderr, + "detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n", + i, j, d[j], k - 1, d[j+1], k + 1); + goto out_errno; + } + recv--; + } + } + } + } + clock_gettime(CLOCK_MONOTONIC, &s->end); + } + + for (i = 0; i < iov_count; i++) + free(iov[i].iov_base); + free(iov); + return 0; +out_errno: + for (i = 0; i < iov_count; i++) + free(iov[i].iov_base); + free(iov); + return errno; +} + +static float giga = 1000000000; + +static inline float sentBps(struct msg_stats s) +{ + return s.bytes_sent / (s.end.tv_sec - s.start.tv_sec); +} + +static inline float recvdBps(struct msg_stats s) +{ + return s.bytes_recvd / (s.end.tv_sec - s.start.tv_sec); +} + +static int sendmsg_test(struct sockmap_options *opt) +{ + float sent_Bps = 0, recvd_Bps = 0; + int rx_fd, txpid, rxpid, err = 0; + struct msg_stats s = {0}; + int iov_count = opt->iov_count; + int iov_buf = opt->iov_length; + int cnt = opt->rate; + int status; + + errno = 0; + + if (opt->base) + rx_fd = p1; + else + rx_fd = p2; + + rxpid = fork(); + if (rxpid == 0) { + if (opt->drop_expected) + exit(1); + + if (opt->sendpage) + iov_count = 1; + err = msg_loop(rx_fd, iov_count, iov_buf, + cnt, &s, false, opt); + if (err && opt->verbose) + fprintf(stderr, + "msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n", + iov_count, iov_buf, cnt, err); + shutdown(p2, SHUT_RDWR); + shutdown(p1, SHUT_RDWR); + if (s.end.tv_sec - s.start.tv_sec) { + sent_Bps = sentBps(s); + recvd_Bps = recvdBps(s); + } + if (opt->verbose) + fprintf(stdout, + "rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n", + s.bytes_sent, sent_Bps, sent_Bps/giga, + s.bytes_recvd, recvd_Bps, recvd_Bps/giga); + exit(1); + } else if (rxpid == -1) { + perror("msg_loop_rx: "); + return errno; + } + + txpid = fork(); + if (txpid == 0) { + if (opt->sendpage) + err = msg_loop_sendpage(c1, iov_buf, cnt, &s, opt); + else + err = msg_loop(c1, iov_count, iov_buf, + cnt, &s, true, opt); + + if (err) + fprintf(stderr, + "msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n", + iov_count, iov_buf, cnt, err); + shutdown(c1, SHUT_RDWR); + if (s.end.tv_sec - s.start.tv_sec) { + sent_Bps = sentBps(s); + recvd_Bps = recvdBps(s); + } + if (opt->verbose) + fprintf(stdout, + "tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n", + s.bytes_sent, sent_Bps, sent_Bps/giga, + s.bytes_recvd, recvd_Bps, recvd_Bps/giga); + exit(1); + } else if (txpid == -1) { + perror("msg_loop_tx: "); + return errno; + } + + assert(waitpid(rxpid, &status, 0) == rxpid); + assert(waitpid(txpid, &status, 0) == txpid); + return err; +} + +static int forever_ping_pong(int rate, struct sockmap_options *opt) +{ + struct timeval timeout; + char buf[1024] = {0}; + int sc; + + timeout.tv_sec = 10; + timeout.tv_usec = 0; + + /* Ping/Pong data from client to server */ + sc = send(c1, buf, sizeof(buf), 0); + if (sc < 0) { + perror("send failed()\n"); + return sc; + } + + do { + int s, rc, i, max_fd = p2; + fd_set w; + + /* FD sets */ + FD_ZERO(&w); + FD_SET(c1, &w); + FD_SET(c2, &w); + FD_SET(p1, &w); + FD_SET(p2, &w); + + s = select(max_fd + 1, &w, NULL, NULL, &timeout); + if (s == -1) { + perror("select()"); + break; + } else if (!s) { + fprintf(stderr, "unexpected timeout\n"); + break; + } + + for (i = 0; i <= max_fd && s > 0; ++i) { + if (!FD_ISSET(i, &w)) + continue; + + s--; + + rc = recv(i, buf, sizeof(buf), 0); + if (rc < 0) { + if (errno != EWOULDBLOCK) { + perror("recv failed()\n"); + return rc; + } + } + + if (rc == 0) { + close(i); + break; + } + + sc = send(i, buf, rc, 0); + if (sc < 0) { + perror("send failed()\n"); + return sc; + } + } + + if (rate) + sleep(rate); + + if (opt->verbose) { + printf("."); + fflush(stdout); + + } + } while (running); + + return 0; +} + +enum { + PING_PONG, + SENDMSG, + BASE, + BASE_SENDPAGE, + SENDPAGE, +}; + +static int run_options(struct sockmap_options *options, int cg_fd, int test) +{ + int i, key, next_key, err, tx_prog_fd = -1, zero = 0; + + /* If base test skip BPF setup */ + if (test == BASE || test == BASE_SENDPAGE) + goto run; + + /* Attach programs to sockmap */ + err = bpf_prog_attach(prog_fd[0], map_fd[0], + BPF_SK_SKB_STREAM_PARSER, 0); + if (err) { + fprintf(stderr, + "ERROR: bpf_prog_attach (sockmap %i->%i): %d (%s)\n", + prog_fd[0], map_fd[0], err, strerror(errno)); + return err; + } + + err = bpf_prog_attach(prog_fd[1], map_fd[0], + BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) { + fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n", + err, strerror(errno)); + return err; + } + + /* Attach to cgroups */ + err = bpf_prog_attach(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS, 0); + if (err) { + fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n", + err, strerror(errno)); + return err; + } + +run: + err = sockmap_init_sockets(options->verbose); + if (err) { + fprintf(stderr, "ERROR: test socket failed: %d\n", err); + goto out; + } + + /* Attach txmsg program to sockmap */ + if (txmsg_pass) + tx_prog_fd = prog_fd[3]; + else if (txmsg_noisy) + tx_prog_fd = prog_fd[4]; + else if (txmsg_redir) + tx_prog_fd = prog_fd[5]; + else if (txmsg_redir_noisy) + tx_prog_fd = prog_fd[6]; + else if (txmsg_drop) + tx_prog_fd = prog_fd[9]; + /* apply and cork must be last */ + else if (txmsg_apply) + tx_prog_fd = prog_fd[7]; + else if (txmsg_cork) + tx_prog_fd = prog_fd[8]; + else + tx_prog_fd = 0; + + if (tx_prog_fd) { + int redir_fd, i = 0; + + err = bpf_prog_attach(tx_prog_fd, + map_fd[1], BPF_SK_MSG_VERDICT, 0); + if (err) { + fprintf(stderr, + "ERROR: bpf_prog_attach (txmsg): %d (%s)\n", + err, strerror(errno)); + goto out; + } + + err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg): %d (%s\n", + err, strerror(errno)); + goto out; + } + + if (txmsg_redir || txmsg_redir_noisy) + redir_fd = c2; + else + redir_fd = c1; + + err = bpf_map_update_elem(map_fd[2], &i, &redir_fd, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg): %d (%s\n", + err, strerror(errno)); + goto out; + } + + if (txmsg_apply) { + err = bpf_map_update_elem(map_fd[3], + &i, &txmsg_apply, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (apply_bytes): %d (%s\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_cork) { + err = bpf_map_update_elem(map_fd[4], + &i, &txmsg_cork, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (cork_bytes): %d (%s\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_start) { + err = bpf_map_update_elem(map_fd[5], + &i, &txmsg_start, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_start): %d (%s)\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_end) { + i = 1; + err = bpf_map_update_elem(map_fd[5], + &i, &txmsg_end, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_end): %d (%s)\n", + err, strerror(errno)); + goto out; + } + } + + if (txmsg_ingress) { + int in = BPF_F_INGRESS; + + i = 0; + err = bpf_map_update_elem(map_fd[6], &i, &in, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n", + err, strerror(errno)); + } + i = 1; + err = bpf_map_update_elem(map_fd[1], &i, &p1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p1 txmsg): %d (%s)\n", + err, strerror(errno)); + } + err = bpf_map_update_elem(map_fd[2], &i, &p1, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p1 redir): %d (%s)\n", + err, strerror(errno)); + } + + i = 2; + err = bpf_map_update_elem(map_fd[2], &i, &p2, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (p2 txmsg): %d (%s)\n", + err, strerror(errno)); + } + } + + if (txmsg_skb) { + int skb_fd = (test == SENDMSG || test == SENDPAGE) ? + p2 : p1; + int ingress = BPF_F_INGRESS; + + i = 0; + err = bpf_map_update_elem(map_fd[7], + &i, &ingress, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n", + err, strerror(errno)); + } + + i = 3; + err = bpf_map_update_elem(map_fd[0], + &i, &skb_fd, BPF_ANY); + if (err) { + fprintf(stderr, + "ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n", + err, strerror(errno)); + } + } + } + + if (txmsg_drop) + options->drop_expected = true; + + if (test == PING_PONG) + err = forever_ping_pong(options->rate, options); + else if (test == SENDMSG) { + options->base = false; + options->sendpage = false; + err = sendmsg_test(options); + } else if (test == SENDPAGE) { + options->base = false; + options->sendpage = true; + err = sendmsg_test(options); + } else if (test == BASE) { + options->base = true; + options->sendpage = false; + err = sendmsg_test(options); + } else if (test == BASE_SENDPAGE) { + options->base = true; + options->sendpage = true; + err = sendmsg_test(options); + } else + fprintf(stderr, "unknown test\n"); +out: + /* Detatch and zero all the maps */ + bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS); + bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER); + bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT); + if (tx_prog_fd >= 0) + bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT); + + for (i = 0; i < 8; i++) { + key = next_key = 0; + bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY); + while (bpf_map_get_next_key(map_fd[i], &key, &next_key) == 0) { + bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY); + key = next_key; + } + } + + close(s1); + close(s2); + close(p1); + close(p2); + close(c1); + close(c2); + return err; +} + +static char *test_to_str(int test) +{ + switch (test) { + case SENDMSG: + return "sendmsg"; + case SENDPAGE: + return "sendpage"; + } + return "unknown"; +} + +#define OPTSTRING 60 +static void test_options(char *options) +{ + memset(options, 0, OPTSTRING); + + if (txmsg_pass) + strncat(options, "pass,", OPTSTRING); + if (txmsg_noisy) + strncat(options, "pass_noisy,", OPTSTRING); + if (txmsg_redir) + strncat(options, "redir,", OPTSTRING); + if (txmsg_redir_noisy) + strncat(options, "redir_noisy,", OPTSTRING); + if (txmsg_drop) + strncat(options, "drop,", OPTSTRING); + if (txmsg_apply) + strncat(options, "apply,", OPTSTRING); + if (txmsg_cork) + strncat(options, "cork,", OPTSTRING); + if (txmsg_start) + strncat(options, "start,", OPTSTRING); + if (txmsg_end) + strncat(options, "end,", OPTSTRING); + if (txmsg_ingress) + strncat(options, "ingress,", OPTSTRING); + if (txmsg_skb) + strncat(options, "skb,", OPTSTRING); +} + +static int __test_exec(int cgrp, int test, struct sockmap_options *opt) +{ + char *options = calloc(60, sizeof(char)); + int err; + + if (test == SENDPAGE) + opt->sendpage = true; + else + opt->sendpage = false; + + if (txmsg_drop) + opt->drop_expected = true; + else + opt->drop_expected = false; + + test_options(options); + + fprintf(stdout, + "[TEST %i]: (%i, %i, %i, %s, %s): ", + test_cnt, opt->rate, opt->iov_count, opt->iov_length, + test_to_str(test), options); + fflush(stdout); + err = run_options(opt, cgrp, test); + fprintf(stdout, "%s\n", !err ? "PASS" : "FAILED"); + test_cnt++; + !err ? passed++ : failed++; + free(options); + return err; +} + +static int test_exec(int cgrp, struct sockmap_options *opt) +{ + int err = __test_exec(cgrp, SENDMSG, opt); + + if (err) + goto out; + + err = __test_exec(cgrp, SENDPAGE, opt); +out: + return err; +} + +static int test_loop(int cgrp) +{ + struct sockmap_options opt; + + int err, i, l, r; + + opt.verbose = 0; + opt.base = false; + opt.sendpage = false; + opt.data_test = false; + opt.drop_expected = false; + opt.iov_count = 0; + opt.iov_length = 0; + opt.rate = 0; + + r = 1; + for (i = 1; i < 100; i += 33) { + for (l = 1; l < 100; l += 33) { + opt.rate = r; + opt.iov_count = i; + opt.iov_length = l; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + } + sched_yield(); +out: + return err; +} + +static int test_txmsg(int cgrp) +{ + int err; + + txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0; + txmsg_apply = txmsg_cork = 0; + txmsg_ingress = txmsg_skb = 0; + + txmsg_pass = 1; + err = test_loop(cgrp); + txmsg_pass = 0; + if (err) + goto out; + + txmsg_redir = 1; + err = test_loop(cgrp); + txmsg_redir = 0; + if (err) + goto out; + + txmsg_drop = 1; + err = test_loop(cgrp); + txmsg_drop = 0; + if (err) + goto out; + + txmsg_redir = 1; + txmsg_ingress = 1; + err = test_loop(cgrp); + txmsg_redir = 0; + txmsg_ingress = 0; + if (err) + goto out; +out: + txmsg_pass = 0; + txmsg_redir = 0; + txmsg_drop = 0; + return err; +} + +static int test_send(struct sockmap_options *opt, int cgrp) +{ + int err; + + opt->iov_length = 1; + opt->iov_count = 1; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1; + opt->iov_count = 1024; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1024; + opt->iov_count = 1; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1; + opt->iov_count = 1; + opt->rate = 1024; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 256; + opt->iov_count = 1024; + opt->rate = 10; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->rate = 100; + opt->iov_count = 1; + opt->iov_length = 5; + err = test_exec(cgrp, opt); + if (err) + goto out; +out: + sched_yield(); + return err; +} + +static int test_mixed(int cgrp) +{ + struct sockmap_options opt = {0}; + int err; + + txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0; + txmsg_apply = txmsg_cork = 0; + txmsg_start = txmsg_end = 0; + /* Test small and large iov_count values with pass/redir/apply/cork */ + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 0; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1024; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 0; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1024; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_cork = 4096; + txmsg_apply = 4096; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 0; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1024; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 0; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1024; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_cork = 4096; + txmsg_apply = 4096; + err = test_send(&opt, cgrp); + if (err) + goto out; +out: + return err; +} + +static int test_start_end(int cgrp) +{ + struct sockmap_options opt = {0}; + int err, i; + + /* Test basic start/end with lots of iov_count and iov_lengths */ + txmsg_start = 1; + txmsg_end = 2; + err = test_txmsg(cgrp); + if (err) + goto out; + + /* Test start/end with cork */ + opt.rate = 16; + opt.iov_count = 1; + opt.iov_length = 100; + txmsg_cork = 1600; + + for (i = 99; i <= 1600; i += 500) { + txmsg_start = 0; + txmsg_end = i; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + + /* Test start/end with cork but pull data in middle */ + for (i = 199; i <= 1600; i += 500) { + txmsg_start = 100; + txmsg_end = i; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + + /* Test start/end with cork pulling last sg entry */ + txmsg_start = 1500; + txmsg_end = 1600; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end pull of single byte in last page */ + txmsg_start = 1111; + txmsg_end = 1112; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with end < start */ + txmsg_start = 1111; + txmsg_end = 0; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with end > data */ + txmsg_start = 0; + txmsg_end = 1601; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with start > data */ + txmsg_start = 1601; + txmsg_end = 1600; + err = test_exec(cgrp, &opt); + +out: + txmsg_start = 0; + txmsg_end = 0; + sched_yield(); + return err; +} + +char *map_names[] = { + "sock_map", + "sock_map_txmsg", + "sock_map_redir", + "sock_apply_bytes", + "sock_cork_bytes", + "sock_pull_bytes", + "sock_redir_flags", + "sock_skb_opts", +}; + +int prog_attach_type[] = { + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_SOCK_OPS, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, +}; + +int prog_type[] = { + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, +}; + +static int populate_progs(void) +{ + char *bpf_file = BPF_FILENAME; + struct bpf_program *prog; + struct bpf_object *obj; + int i = 0; + long err; + + obj = bpf_object__open(bpf_file); + err = libbpf_get_error(obj); + if (err) { + char err_buf[256]; + + libbpf_strerror(err, err_buf, sizeof(err_buf)); + printf("Unable to load eBPF objects in file '%s' : %s\n", + bpf_file, err_buf); + return -1; + } + + bpf_object__for_each_program(prog, obj) { + bpf_program__set_type(prog, prog_type[i]); + bpf_program__set_expected_attach_type(prog, + prog_attach_type[i]); + i++; + } + + i = bpf_object__load(obj); + i = 0; + bpf_object__for_each_program(prog, obj) { + prog_fd[i] = bpf_program__fd(prog); + i++; + } + + for (i = 0; i < sizeof(map_fd)/sizeof(int); i++) { + maps[i] = bpf_object__find_map_by_name(obj, map_names[i]); + map_fd[i] = bpf_map__fd(maps[i]); + if (map_fd[i] < 0) { + fprintf(stderr, "load_bpf_file: (%i) %s\n", + map_fd[i], strerror(errno)); + return -1; + } + } + + return 0; +} + +static int test_suite(void) +{ + int cg_fd, err; + + err = populate_progs(); + if (err < 0) { + fprintf(stderr, "ERROR: (%i) load bpf failed\n", err); + return err; + } + + if (setup_cgroup_environment()) { + fprintf(stderr, "ERROR: cgroup env failed\n"); + return -EINVAL; + } + + cg_fd = create_and_get_cgroup(CG_PATH); + if (cg_fd < 0) { + fprintf(stderr, + "ERROR: (%i) open cg path failed: %s\n", + cg_fd, optarg); + return cg_fd; + } + + /* Tests basic commands and APIs with range of iov values */ + txmsg_start = txmsg_end = 0; + err = test_txmsg(cg_fd); + if (err) + goto out; + + /* Tests interesting combinations of APIs used together */ + err = test_mixed(cg_fd); + if (err) + goto out; + + /* Tests pull_data API using start/end API */ + err = test_start_end(cg_fd); + if (err) + goto out; + +out: + printf("Summary: %i PASSED %i FAILED\n", passed, failed); + close(cg_fd); + return err; +} + +int main(int argc, char **argv) +{ + struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + int iov_count = 1, length = 1024, rate = 1; + struct sockmap_options options = {0}; + int opt, longindex, err, cg_fd = 0; + char *bpf_file = BPF_FILENAME; + int test = PING_PONG; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (argc < 2) + return test_suite(); + + while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:", + long_options, &longindex)) != -1) { + switch (opt) { + case 's': + txmsg_start = atoi(optarg); + break; + case 'e': + txmsg_end = atoi(optarg); + break; + case 'a': + txmsg_apply = atoi(optarg); + break; + case 'k': + txmsg_cork = atoi(optarg); + break; + case 'c': + cg_fd = open(optarg, O_DIRECTORY, O_RDONLY); + if (cg_fd < 0) { + fprintf(stderr, + "ERROR: (%i) open cg path failed: %s\n", + cg_fd, optarg); + return cg_fd; + } + break; + case 'r': + rate = atoi(optarg); + break; + case 'v': + options.verbose = 1; + break; + case 'i': + iov_count = atoi(optarg); + break; + case 'l': + length = atoi(optarg); + break; + case 'd': + options.data_test = true; + break; + case 't': + if (strcmp(optarg, "ping") == 0) { + test = PING_PONG; + } else if (strcmp(optarg, "sendmsg") == 0) { + test = SENDMSG; + } else if (strcmp(optarg, "base") == 0) { + test = BASE; + } else if (strcmp(optarg, "base_sendpage") == 0) { + test = BASE_SENDPAGE; + } else if (strcmp(optarg, "sendpage") == 0) { + test = SENDPAGE; + } else { + usage(argv); + return -1; + } + break; + case 0: + break; + case 'h': + default: + usage(argv); + return -1; + } + } + + if (!cg_fd) { + fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n", + argv[0]); + return -1; + } + + err = populate_progs(); + if (err) { + fprintf(stderr, "populate program: (%s) %s\n", + bpf_file, strerror(errno)); + return 1; + } + running = 1; + + /* catch SIGINT */ + signal(SIGINT, running_handler); + + options.iov_count = iov_count; + options.iov_length = length; + options.rate = rate; + + err = run_options(&options, cg_fd, test); + close(cg_fd); + return err; +} + +void running_handler(int a) +{ + running = 0; +} diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.c b/tools/testing/selftests/bpf/test_sockmap_kern.c new file mode 100644 index 000000000000..33de97e2b6b6 --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockmap_kern.c @@ -0,0 +1,340 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +/* Sockmap sample program connects a client and a backend together + * using cgroups. + * + * client:X <---> frontend:80 client:X <---> backend:80 + * + * For simplicity we hard code values here and bind 1:1. The hard + * coded values are part of the setup in sockmap.sh script that + * is associated with this BPF program. + * + * The bpf_printk is verbose and prints information as connections + * are established and verdicts are decided. + */ + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +struct bpf_map_def SEC("maps") sock_map = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_txmsg = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_redir = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_apply_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_cork_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_pull_bytes = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 2 +}; + +struct bpf_map_def SEC("maps") sock_redir_flags = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +struct bpf_map_def SEC("maps") sock_skb_opts = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1 +}; + +SEC("sk_skb1") +int bpf_prog1(struct __sk_buff *skb) +{ + return skb->len; +} + +SEC("sk_skb2") +int bpf_prog2(struct __sk_buff *skb) +{ + __u32 lport = skb->local_port; + __u32 rport = skb->remote_port; + int len, *f, ret, zero = 0; + __u64 flags = 0; + + if (lport == 10000) + ret = 10; + else + ret = 1; + + len = (__u32)skb->data_end - (__u32)skb->data; + f = bpf_map_lookup_elem(&sock_skb_opts, &zero); + if (f && *f) { + ret = 3; + flags = *f; + } + + bpf_printk("sk_skb2: redirect(%iB) flags=%i\n", + len, flags); + return bpf_sk_redirect_map(skb, &sock_map, ret, flags); +} + +SEC("sockops") +int bpf_sockmap(struct bpf_sock_ops *skops) +{ + __u32 lport, rport; + int op, err = 0, index, key, ret; + + + op = (int) skops->op; + + switch (op) { + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + lport = skops->local_port; + rport = skops->remote_port; + + if (lport == 10000) { + ret = 1; + err = bpf_sock_map_update(skops, &sock_map, &ret, + BPF_NOEXIST); + bpf_printk("passive(%i -> %i) map ctx update err: %d\n", + lport, bpf_ntohl(rport), err); + } + break; + case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: + lport = skops->local_port; + rport = skops->remote_port; + + if (bpf_ntohl(rport) == 10001) { + ret = 10; + err = bpf_sock_map_update(skops, &sock_map, &ret, + BPF_NOEXIST); + bpf_printk("active(%i -> %i) map ctx update err: %d\n", + lport, bpf_ntohl(rport), err); + } + break; + default: + break; + } + + return 0; +} + +SEC("sk_msg1") +int bpf_prog4(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1; + int *start, *end; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + return SK_PASS; +} + +SEC("sk_msg2") +int bpf_prog5(struct sk_msg_md *msg) +{ + int err1 = -1, err2 = -1, zero = 0, one = 1; + int *bytes, *start, *end, len1, len2; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + err1 = bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + err2 = bpf_msg_cork_bytes(msg, *bytes); + len1 = (__u64)msg->data_end - (__u64)msg->data; + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) { + int err; + + bpf_printk("sk_msg2: pull(%i:%i)\n", + start ? *start : 0, end ? *end : 0); + err = bpf_msg_pull_data(msg, *start, *end, 0); + if (err) + bpf_printk("sk_msg2: pull_data err %i\n", + err); + len2 = (__u64)msg->data_end - (__u64)msg->data; + bpf_printk("sk_msg2: length update %i->%i\n", + len1, len2); + } + bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n", + len1, err1, err2); + return SK_PASS; +} + +SEC("sk_msg3") +int bpf_prog6(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1, key = 0; + int *start, *end, *f; + __u64 flags = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + f = bpf_map_lookup_elem(&sock_redir_flags, &zero); + if (f && *f) { + key = 2; + flags = *f; + } + return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags); +} + +SEC("sk_msg4") +int bpf_prog7(struct sk_msg_md *msg) +{ + int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0; + int *f, *bytes, *start, *end, len1, len2; + __u64 flags = 0; + + int err; + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + err1 = bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + err2 = bpf_msg_cork_bytes(msg, *bytes); + len1 = (__u64)msg->data_end - (__u64)msg->data; + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) { + + bpf_printk("sk_msg2: pull(%i:%i)\n", + start ? *start : 0, end ? *end : 0); + err = bpf_msg_pull_data(msg, *start, *end, 0); + if (err) + bpf_printk("sk_msg2: pull_data err %i\n", + err); + len2 = (__u64)msg->data_end - (__u64)msg->data; + bpf_printk("sk_msg2: length update %i->%i\n", + len1, len2); + } + f = bpf_map_lookup_elem(&sock_redir_flags, &zero); + if (f && *f) { + key = 2; + flags = *f; + } + bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n", + len1, flags, err1 ? err1 : err2); + err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags); + bpf_printk("sk_msg3: err %i\n", err); + return err; +} + +SEC("sk_msg5") +int bpf_prog8(struct sk_msg_md *msg) +{ + void *data_end = (void *)(long) msg->data_end; + void *data = (void *)(long) msg->data; + int ret = 0, *bytes, zero = 0; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) { + ret = bpf_msg_apply_bytes(msg, *bytes); + if (ret) + return SK_DROP; + } else { + return SK_DROP; + } + return SK_PASS; +} +SEC("sk_msg6") +int bpf_prog9(struct sk_msg_md *msg) +{ + void *data_end = (void *)(long) msg->data_end; + void *data = (void *)(long) msg->data; + int ret = 0, *bytes, zero = 0; + + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) { + if (((__u64)data_end - (__u64)data) >= *bytes) + return SK_PASS; + ret = bpf_msg_cork_bytes(msg, *bytes); + if (ret) + return SK_DROP; + } + return SK_PASS; +} + +SEC("sk_msg7") +int bpf_prog10(struct sk_msg_md *msg) +{ + int *bytes, zero = 0, one = 1; + int *start, *end; + + bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); + if (bytes) + bpf_msg_apply_bytes(msg, *bytes); + bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero); + if (bytes) + bpf_msg_cork_bytes(msg, *bytes); + start = bpf_map_lookup_elem(&sock_pull_bytes, &zero); + end = bpf_map_lookup_elem(&sock_pull_bytes, &one); + if (start && end) + bpf_msg_pull_data(msg, *start, *end, 0); + + return SK_DROP; +} + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh new file mode 100755 index 000000000000..aeb2901f21f4 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -0,0 +1,729 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# End-to-end eBPF tunnel test suite +# The script tests BPF network tunnel implementation. +# +# Topology: +# --------- +# root namespace | at_ns0 namespace +# | +# ----------- | ----------- +# | tnl dev | | | tnl dev | (overlay network) +# ----------- | ----------- +# metadata-mode | native-mode +# with bpf | +# | +# ---------- | ---------- +# | veth1 | --------- | veth0 | (underlay network) +# ---------- peer ---------- +# +# +# Device Configuration +# -------------------- +# Root namespace with metadata-mode tunnel + BPF +# Device names and addresses: +# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay) +# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay) +# +# Namespace at_ns0 with native tunnel +# Device names and addresses: +# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay) +# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay) +# +# +# End-to-end ping packet flow +# --------------------------- +# Most of the tests start by namespace creation, device configuration, +# then ping the underlay and overlay network. When doing 'ping 10.1.1.100' +# from root namespace, the following operations happen: +# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev. +# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata, +# with remote_ip=172.16.1.200 and others. +# 3) Outer tunnel header is prepended and route the packet to veth1's egress +# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0 +# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet +# 6) Forward the packet to the overlay tnl dev + +PING_ARG="-c 3 -w 10 -q" +ret=0 +GREEN='\033[0;92m' +RED='\033[0;31m' +NC='\033[0m' # No Color + +config_device() +{ + ip netns add at_ns0 + ip link add veth0 type veth peer name veth1 + ip link set veth0 netns at_ns0 + ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip link set dev veth1 up mtu 1500 + ip addr add dev veth1 172.16.1.200/24 +} + +add_gre_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE key 2 external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6gretap_tunnel() +{ + + # assign ipv6 address + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \ + local ::11 remote ::22 + + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip addr add dev $DEV fc80::200/24 + ip link set dev $DEV up +} + +add_erspan_tunnel() +{ + # at_ns0 namespace + if [ "$1" == "v1" ]; then + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 \ + erspan_ver 1 erspan 123 + else + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 \ + erspan_ver 2 erspan_dir egress erspan_hwid 3 + fi + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6erspan_tunnel() +{ + + # assign ipv6 address + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + if [ "$1" == "v1" ]; then + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local ::11 remote ::22 \ + erspan_ver 1 erspan 123 + else + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local ::11 remote ::22 \ + erspan_ver 2 erspan_dir egress erspan_hwid 7 + fi + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_vxlan_tunnel() +{ + # Set static ARP entry here because iptables set-mark works + # on L3 packet, as a result not applying to ARP packets, + # causing errors at get_tunnel_{key/opt}. + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + id 2 dstport 4789 gbp remote 172.16.1.200 + ip netns exec at_ns0 \ + ip link set dev $DEV_NS address 52:54:00:d9:01:00 up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00 + ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF + + # root namespace + ip link add dev $DEV type $TYPE external gbp dstport 4789 + ip link set dev $DEV address 52:54:00:d9:02:00 up + ip addr add dev $DEV 10.1.1.200/24 + arp -s 10.1.1.100 52:54:00:d9:01:00 +} + +add_ip6vxlan_tunnel() +{ + #ip netns exec at_ns0 ip -4 addr del 172.16.1.100 dev veth0 + ip netns exec at_ns0 ip -6 addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + #ip -4 addr del 172.16.1.200 dev veth1 + ip -6 addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE id 22 dstport 4789 \ + local ::11 remote ::22 + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external dstport 4789 + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_geneve_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + id 2 dstport 6081 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE dstport 6081 external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6geneve_tunnel() +{ + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE id 22 \ + remote ::22 # geneve has no local option + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_ipip_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + local 172.16.1.100 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ipip6tnl_tunnel() +{ + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + local ::11 remote ::22 + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +test_gre() +{ + TYPE=gretap + DEV_NS=gretap00 + DEV=gretap11 + ret=0 + + check $TYPE + config_device + add_gre_tunnel + attach_bpf $DEV gre_set_tunnel gre_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6gre() +{ + TYPE=ip6gre + DEV_NS=ip6gre00 + DEV=ip6gre11 + ret=0 + + check $TYPE + config_device + # reuse the ip6gretap function + add_ip6gretap_tunnel + attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # overlay: ipv4 over ipv6 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + ping $PING_ARG 10.1.1.100 + check_err $? + # overlay: ipv6 over ipv6 + ip netns exec at_ns0 ping6 $PING_ARG fc80::200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6gretap() +{ + TYPE=ip6gretap + DEV_NS=ip6gretap00 + DEV=ip6gretap11 + ret=0 + + check $TYPE + config_device + add_ip6gretap_tunnel + attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # overlay: ipv4 over ipv6 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + ping $PING_ARG 10.1.1.100 + check_err $? + # overlay: ipv6 over ipv6 + ip netns exec at_ns0 ping6 $PING_ARG fc80::200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_erspan() +{ + TYPE=erspan + DEV_NS=erspan00 + DEV=erspan11 + ret=0 + + check $TYPE + config_device + add_erspan_tunnel $1 + attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6erspan() +{ + TYPE=ip6erspan + DEV_NS=ip6erspan00 + DEV=ip6erspan11 + ret=0 + + check $TYPE + config_device + add_ip6erspan_tunnel $1 + attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel + ping6 $PING_ARG ::11 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_vxlan() +{ + TYPE=vxlan + DEV_NS=vxlan00 + DEV=vxlan11 + ret=0 + + check $TYPE + config_device + add_vxlan_tunnel + attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6vxlan() +{ + TYPE=vxlan + DEV_NS=ip6vxlan00 + DEV=ip6vxlan11 + ret=0 + + check $TYPE + config_device + add_ip6vxlan_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ip6vxlan_set_tunnel ip6vxlan_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # ip4 over ip6 + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: ip6$TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: ip6$TYPE"${NC} +} + +test_geneve() +{ + TYPE=geneve + DEV_NS=geneve00 + DEV=geneve11 + ret=0 + + check $TYPE + config_device + add_geneve_tunnel + attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6geneve() +{ + TYPE=geneve + DEV_NS=ip6geneve00 + DEV=ip6geneve11 + ret=0 + + check $TYPE + config_device + add_ip6geneve_tunnel + attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: ip6$TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: ip6$TYPE"${NC} +} + +test_ipip() +{ + TYPE=ipip + DEV_NS=ipip00 + DEV=ipip11 + ret=0 + + check $TYPE + config_device + add_ipip_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ipip6() +{ + TYPE=ip6tnl + DEV_NS=ipip6tnl00 + DEV=ipip6tnl11 + ret=0 + + check $TYPE + config_device + add_ipip6tnl_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # ip4 over ip6 + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +setup_xfrm_tunnel() +{ + auth=0x$(printf '1%.0s' {1..40}) + enc=0x$(printf '2%.0s' {1..32}) + spi_in_to_out=0x1 + spi_out_to_in=0x2 + # at_ns0 namespace + # at_ns0 -> root + ip netns exec at_ns0 \ + ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ + spi $spi_in_to_out reqid 1 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip netns exec at_ns0 \ + ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \ + tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ + mode tunnel + # root -> at_ns0 + ip netns exec at_ns0 \ + ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ + spi $spi_out_to_in reqid 2 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip netns exec at_ns0 \ + ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \ + tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ + mode tunnel + # address & route + ip netns exec at_ns0 \ + ip addr add dev veth0 10.1.1.100/32 + ip netns exec at_ns0 \ + ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \ + src 10.1.1.100 + + # root namespace + # at_ns0 -> root + ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ + spi $spi_in_to_out reqid 1 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \ + tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ + mode tunnel + # root -> at_ns0 + ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ + spi $spi_out_to_in reqid 2 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \ + tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ + mode tunnel + # address & route + ip addr add dev veth1 10.1.1.200/32 + ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200 +} + +test_xfrm_tunnel() +{ + config_device + #tcpdump -nei veth1 ip & + output=$(mktemp) + cat /sys/kernel/debug/tracing/trace_pipe | tee $output & + setup_xfrm_tunnel + tc qdisc add dev veth1 clsact + tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \ + sec xfrm_get_state + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + sleep 1 + grep "reqid 1" $output + check_err $? + grep "spi 0x1" $output + check_err $? + grep "remote ip 0xac100164" $output + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: xfrm tunnel"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: xfrm tunnel"${NC} +} + +attach_bpf() +{ + DEV=$1 + SET=$2 + GET=$3 + tc qdisc add dev $DEV clsact + tc filter add dev $DEV egress bpf da obj test_tunnel_kern.o sec $SET + tc filter add dev $DEV ingress bpf da obj test_tunnel_kern.o sec $GET +} + +cleanup() +{ + ip netns delete at_ns0 2> /dev/null + ip link del veth1 2> /dev/null + ip link del ipip11 2> /dev/null + ip link del ipip6tnl11 2> /dev/null + ip link del gretap11 2> /dev/null + ip link del ip6gre11 2> /dev/null + ip link del ip6gretap11 2> /dev/null + ip link del vxlan11 2> /dev/null + ip link del ip6vxlan11 2> /dev/null + ip link del geneve11 2> /dev/null + ip link del ip6geneve11 2> /dev/null + ip link del erspan11 2> /dev/null + ip link del ip6erspan11 2> /dev/null +} + +cleanup_exit() +{ + echo "CATCH SIGKILL or SIGINT, cleanup and exit" + cleanup + exit 0 +} + +check() +{ + ip link help $1 2>&1 | grep -q "^Usage:" + if [ $? -ne 0 ];then + echo "SKIP $1: iproute2 not support" + cleanup + return 1 + fi +} + +enable_debug() +{ + echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file vxlan.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control +} + +check_err() +{ + if [ $ret -eq 0 ]; then + ret=$1 + fi +} + +bpf_tunnel_test() +{ + echo "Testing GRE tunnel..." + test_gre + echo "Testing IP6GRE tunnel..." + test_ip6gre + echo "Testing IP6GRETAP tunnel..." + test_ip6gretap + echo "Testing ERSPAN tunnel..." + test_erspan v2 + echo "Testing IP6ERSPAN tunnel..." + test_ip6erspan v2 + echo "Testing VXLAN tunnel..." + test_vxlan + echo "Testing IP6VXLAN tunnel..." + test_ip6vxlan + echo "Testing GENEVE tunnel..." + test_geneve + echo "Testing IP6GENEVE tunnel..." + test_ip6geneve + echo "Testing IPIP tunnel..." + test_ipip + echo "Testing IPIP6 tunnel..." + test_ipip6 + echo "Testing IPSec tunnel..." + test_xfrm_tunnel +} + +trap cleanup 0 3 6 +trap cleanup_exit 2 9 + +cleanup +bpf_tunnel_test + +exit 0 diff --git a/tools/testing/selftests/bpf/test_tunnel_kern.c b/tools/testing/selftests/bpf/test_tunnel_kern.c new file mode 100644 index 000000000000..504df69c83df --- /dev/null +++ b/tools/testing/selftests/bpf/test_tunnel_kern.c @@ -0,0 +1,713 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2016 VMware + * Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <stddef.h> +#include <string.h> +#include <arpa/inet.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <linux/tcp.h> +#include <linux/socket.h> +#include <linux/pkt_cls.h> +#include <linux/erspan.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define ERROR(ret) do {\ + char fmt[] = "ERROR line:%d ret:%d\n";\ + bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \ + } while (0) + +int _version SEC("version") = 1; + +struct geneve_opt { + __be16 opt_class; + __u8 type; + __u8 length:5; + __u8 r3:1; + __u8 r2:1; + __u8 r1:1; + __u8 opt_data[8]; /* hard-coded to 8 byte */ +}; + +struct vxlan_metadata { + __u32 gbp; +}; + +SEC("gre_set_tunnel") +int _gre_set_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("gre_get_tunnel") +int _gre_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "key %d remote ip 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), key.tunnel_id, key.remote_ipv4); + return TC_ACT_OK; +} + +SEC("ip6gretap_set_tunnel") +int _ip6gretap_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + key.tunnel_label = 0xabcde; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | + BPF_F_SEQ_NUMBER); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6gretap_get_tunnel") +int _ip6gretap_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip6 ::%x label %x\n"; + struct bpf_tunnel_key key; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv6[3], key.tunnel_label); + + return TC_ACT_OK; +} + +SEC("erspan_set_tunnel") +int _erspan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct erspan_metadata md; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&md, 0, sizeof(md)); +#ifdef ERSPAN_V1 + md.version = 1; + md.u.index = bpf_htonl(123); +#else + __u8 direction = 1; + __u8 hwid = 7; + + md.version = 2; + md.u.md2.dir = direction; + md.u.md2.hwid = hwid & 0xf; + md.u.md2.hwid_upper = (hwid >> 4) & 0x3; +#endif + + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("erspan_get_tunnel") +int _erspan_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip 0x%x erspan version %d\n"; + struct bpf_tunnel_key key; + struct erspan_metadata md; + __u32 index; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, md.version); + +#ifdef ERSPAN_V1 + char fmt2[] = "\tindex %x\n"; + + index = bpf_ntohl(md.u.index); + bpf_trace_printk(fmt2, sizeof(fmt2), index); +#else + char fmt2[] = "\tdirection %d hwid %x timestamp %u\n"; + + bpf_trace_printk(fmt2, sizeof(fmt2), + md.u.md2.dir, + (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + bpf_ntohl(md.u.md2.timestamp)); +#endif + + return TC_ACT_OK; +} + +SEC("ip4ip6erspan_set_tunnel") +int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct erspan_metadata md; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&md, 0, sizeof(md)); + +#ifdef ERSPAN_V1 + md.u.index = bpf_htonl(123); + md.version = 1; +#else + __u8 direction = 0; + __u8 hwid = 17; + + md.version = 2; + md.u.md2.dir = direction; + md.u.md2.hwid = hwid & 0xf; + md.u.md2.hwid_upper = (hwid >> 4) & 0x3; +#endif + + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip4ip6erspan_get_tunnel") +int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "ip6erspan get key %d remote ip6 ::%x erspan version %d\n"; + struct bpf_tunnel_key key; + struct erspan_metadata md; + __u32 index; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, md.version); + +#ifdef ERSPAN_V1 + char fmt2[] = "\tindex %x\n"; + + index = bpf_ntohl(md.u.index); + bpf_trace_printk(fmt2, sizeof(fmt2), index); +#else + char fmt2[] = "\tdirection %d hwid %x timestamp %u\n"; + + bpf_trace_printk(fmt2, sizeof(fmt2), + md.u.md2.dir, + (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + bpf_ntohl(md.u.md2.timestamp)); +#endif + + return TC_ACT_OK; +} + +SEC("vxlan_set_tunnel") +int _vxlan_set_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct vxlan_metadata md; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + md.gbp = 0x800FF; /* Set VXLAN Group Policy extension */ + ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("vxlan_get_tunnel") +int _vxlan_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct vxlan_metadata md; + char fmt[] = "key %d remote ip 0x%x vxlan gbp 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, md.gbp); + + return TC_ACT_OK; +} + +SEC("ip6vxlan_set_tunnel") +int _ip6vxlan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6vxlan_get_tunnel") +int _ip6vxlan_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip6 ::%x label %x\n"; + struct bpf_tunnel_key key; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv6[3], key.tunnel_label); + + return TC_ACT_OK; +} + +SEC("geneve_set_tunnel") +int _geneve_set_tunnel(struct __sk_buff *skb) +{ + int ret, ret2; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + key.tunnel_id = 2; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + __builtin_memset(&gopt, 0x0, sizeof(gopt)); + gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt.type = 0x08; + gopt.r1 = 0; + gopt.r2 = 0; + gopt.r3 = 0; + gopt.length = 2; /* 4-byte multiple */ + *(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef); + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("geneve_get_tunnel") +int _geneve_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, gopt.opt_class); + return TC_ACT_OK; +} + +SEC("ip6geneve_set_tunnel") +int _ip6geneve_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct geneve_opt gopt; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&gopt, 0x0, sizeof(gopt)); + gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt.type = 0x08; + gopt.r1 = 0; + gopt.r2 = 0; + gopt.r3 = 0; + gopt.length = 2; /* 4-byte multiple */ + *(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef); + + ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6geneve_get_tunnel") +int _ip6geneve_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n"; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, gopt.opt_class); + + return TC_ACT_OK; +} + +SEC("ipip_set_tunnel") +int _ipip_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct iphdr *iph = data; + struct tcphdr *tcp = data + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) + sizeof(*tcp) > data_end) { + ERROR(1); + return TC_ACT_SHOT; + } + + key.tunnel_ttl = 64; + if (iph->protocol == IPPROTO_ICMP) { + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + } else { + if (iph->protocol != IPPROTO_TCP || iph->ihl != 5) + return TC_ACT_SHOT; + + if (tcp->dest == bpf_htons(5200)) + key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ + else if (tcp->dest == bpf_htons(5201)) + key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */ + else + return TC_ACT_SHOT; + } + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ipip_get_tunnel") +int _ipip_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "remote ip 0x%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), key.remote_ipv4); + return TC_ACT_OK; +} + +SEC("ipip6_set_tunnel") +int _ipip6_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct iphdr *iph = data; + struct tcphdr *tcp = data + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) + sizeof(*tcp) > data_end) { + ERROR(1); + return TC_ACT_SHOT; + } + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ipip6_get_tunnel") +int _ipip6_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "remote ip6 %x::%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]), + bpf_htonl(key.remote_ipv6[3])); + return TC_ACT_OK; +} + +SEC("ip6ip6_set_tunnel") +int _ip6ip6_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key = {}; + void *data = (void *)(long)skb->data; + struct ipv6hdr *iph = data; + struct tcphdr *tcp = data + sizeof(*iph); + void *data_end = (void *)(long)skb->data_end; + int ret; + + /* single length check */ + if (data + sizeof(*iph) + sizeof(*tcp) > data_end) { + ERROR(1); + return TC_ACT_SHOT; + } + + key.remote_ipv6[0] = bpf_htonl(0x2401db00); + key.tunnel_ttl = 64; + + if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) { + key.remote_ipv6[3] = bpf_htonl(1); + } else { + if (iph->nexthdr != 6 /* NEXTHDR_TCP */) { + ERROR(iph->nexthdr); + return TC_ACT_SHOT; + } + + if (tcp->dest == bpf_htons(5200)) { + key.remote_ipv6[3] = bpf_htonl(1); + } else if (tcp->dest == bpf_htons(5201)) { + key.remote_ipv6[3] = bpf_htonl(2); + } else { + ERROR(tcp->dest); + return TC_ACT_SHOT; + } + } + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6ip6_get_tunnel") +int _ip6ip6_get_tunnel(struct __sk_buff *skb) +{ + int ret; + struct bpf_tunnel_key key; + char fmt[] = "remote ip6 %x::%x\n"; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]), + bpf_htonl(key.remote_ipv6[3])); + return TC_ACT_OK; +} + +SEC("xfrm_get_state") +int _xfrm_get_state(struct __sk_buff *skb) +{ + struct bpf_xfrm_state x; + char fmt[] = "reqid %d spi 0x%x remote ip 0x%x\n"; + int ret; + + ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0); + if (ret < 0) + return TC_ACT_OK; + + bpf_trace_printk(fmt, sizeof(fmt), x.reqid, bpf_ntohl(x.spi), + bpf_ntohl(x.remote_ipv4)); + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 3e7718b1a9ae..165e9ddfa446 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -64,6 +64,7 @@ struct bpf_test { struct bpf_insn insns[MAX_INSNS]; int fixup_map1[MAX_FIXUPS]; int fixup_map2[MAX_FIXUPS]; + int fixup_map3[MAX_FIXUPS]; int fixup_prog[MAX_FIXUPS]; int fixup_map_in_map[MAX_FIXUPS]; const char *errstr; @@ -88,6 +89,11 @@ struct test_val { int foo[MAX_ENTRIES]; }; +struct other_val { + long long foo; + long long bar; +}; + static struct bpf_test tests[] = { { "add+sub+mul", @@ -5594,6 +5600,257 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "map lookup helper access to map", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 8 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map update helper access to map", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_update_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map update helper access to map: wrong size", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_update_elem), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .fixup_map3 = { 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=8 off=0 size=16", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, + offsetof(struct other_val, bar)), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm): out-of-bound 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, + sizeof(struct other_val) - 4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=12 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm): out-of-bound 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=-4 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + offsetof(struct other_val, bar)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg): out-of-bound 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + sizeof(struct other_val) - 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=12 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg): out-of-bound 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, -4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=-4 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct other_val, bar), 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 11 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable): no max check", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable): wrong max check", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct other_val, bar) + 1, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 11 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=9 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { "map element value is preserved across register spilling", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -11533,6 +11790,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, { int *fixup_map1 = test->fixup_map1; int *fixup_map2 = test->fixup_map2; + int *fixup_map3 = test->fixup_map3; int *fixup_prog = test->fixup_prog; int *fixup_map_in_map = test->fixup_map_in_map; @@ -11556,6 +11814,14 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, } while (*fixup_map2); } + if (*fixup_map3) { + map_fds[1] = create_map(sizeof(struct other_val), 1); + do { + prog[*fixup_map3].imm = map_fds[1]; + fixup_map3++; + } while (*fixup_map3); + } + if (*fixup_prog) { map_fds[2] = create_prog_array(); do { |