diff options
author | David S. Miller <davem@davemloft.net> | 2019-04-22 21:35:55 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2019-04-22 21:35:55 -0700 |
commit | 2843ba2ec75948e274d2c4f0a9390980e68a6461 (patch) | |
tree | b2fde70246956609ac43ad62026a4fdb48e33fbc /tools | |
parent | be659b8d3c79afc54e087ebf8d849685d7b0d395 (diff) | |
parent | f79b464fd6b56b6256de43bc4c7d5968c0e52968 (diff) | |
download | linux-2843ba2ec75948e274d2c4f0a9390980e68a6461.tar.gz linux-2843ba2ec75948e274d2c4f0a9390980e68a6461.tar.bz2 linux-2843ba2ec75948e274d2c4f0a9390980e68a6461.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2019-04-22
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) allow stack/queue helpers from more bpf program types, from Alban.
2) allow parallel verification of root bpf programs, from Alexei.
3) introduce bpf sysctl hook for trusted root cases, from Andrey.
4) recognize var/datasec in btf deduplication, from Andrii.
5) cpumap performance optimizations, from Jesper.
6) verifier prep for alu32 optimization, from Jiong.
7) libbpf xsk cleanup, from Magnus.
8) other various fixes and cleanups.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'tools')
33 files changed, 2454 insertions, 187 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 9bb9ace54ba8..89b6b10e2183 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -29,7 +29,7 @@ CGROUP COMMANDS | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } | *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | | **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | -| **sendmsg4** | **sendmsg6** } +| **sendmsg4** | **sendmsg6** | **sysctl** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -85,7 +85,8 @@ DESCRIPTION **sendmsg4** call to sendto(2), sendmsg(2), sendmmsg(2) for an unconnected udp4 socket (since 4.18); **sendmsg6** call to sendto(2), sendmsg(2), sendmmsg(2) for an - unconnected udp6 socket (since 4.18). + unconnected udp6 socket (since 4.18); + **sysctl** sysctl access (since 5.2). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type @@ -99,7 +100,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index 82de03dd8f52..10177343b7ce 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -63,7 +63,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 5c984ffc9f01..55ecf80ca03e 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -135,7 +135,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index 779dab3650ee..6b692b428373 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -55,7 +55,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst index bca5590a80d0..86154740fabb 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -43,7 +43,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 9386bd6e0396..2f183ffd8351 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -25,7 +25,7 @@ PROG COMMANDS | **bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual** | **linum**}] | **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes** | **linum**}] | **bpftool** **prog pin** *PROG* *FILE* -| **bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] +| **bpftool** **prog { load | loadall }** *OBJ* *PATH* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] [**pinmaps** *MAP_DIR*] | **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** @@ -39,7 +39,8 @@ PROG COMMANDS | **cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** | | **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** | | **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** | -| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** +| **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | +| **cgroup/sysctl** | } | *ATTACH_TYPE* := { | **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector** @@ -56,6 +57,14 @@ DESCRIPTION Output will start with program ID followed by program type and zero or more named attributes (depending on kernel version). + Since Linux 5.1 the kernel can collect statistics on BPF + programs (such as the total time spent running the program, + and the number of times it was run). If available, bpftool + shows such statistics. However, the kernel does not collect + them by defaults, as it slightly impacts performance on each + program run. Activation or deactivation of the feature is + performed via the **kernel.bpf_stats_enabled** sysctl knob. + **bpftool prog dump xlated** *PROG* [{ **file** *FILE* | **opcodes** | **visual** | **linum** }] Dump eBPF instructions of the program from the kernel. By default, eBPF will be disassembled and printed to standard @@ -144,7 +153,7 @@ OPTIONS -h, --help Print short generic help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 4f2188845dd8..deb2ca911ddf 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -49,7 +49,7 @@ OPTIONS -h, --help Print short help message (similar to **bpftool help**). - -v, --version + -V, --version Print version number (similar to **bpftool version**). -j, --json diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index b803827d01e8..9f3ffe1e26ab 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -370,7 +370,8 @@ _bpftool() lirc_mode2 cgroup/bind4 cgroup/bind6 \ cgroup/connect4 cgroup/connect6 \ cgroup/sendmsg4 cgroup/sendmsg6 \ - cgroup/post_bind4 cgroup/post_bind6" -- \ + cgroup/post_bind4 cgroup/post_bind6 \ + cgroup/sysctl" -- \ "$cur" ) ) return 0 ;; @@ -619,7 +620,7 @@ _bpftool() attach|detach) local ATTACH_TYPES='ingress egress sock_create sock_ops \ device bind4 bind6 post_bind4 post_bind6 connect4 \ - connect6 sendmsg4 sendmsg6' + connect6 sendmsg4 sendmsg6 sysctl' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag' case $prev in @@ -629,7 +630,7 @@ _bpftool() ;; ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ post_bind4|post_bind6|connect4|connect6|sendmsg4|\ - sendmsg6) + sendmsg6|sysctl) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 4b5c8da2a7c0..7e22f115c8c1 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -25,7 +25,7 @@ " ATTACH_TYPE := { ingress | egress | sock_create |\n" \ " sock_ops | device | bind4 | bind6 |\n" \ " post_bind4 | post_bind6 | connect4 |\n" \ - " connect6 | sendmsg4 | sendmsg6 }" + " connect6 | sendmsg4 | sendmsg6 | sysctl }" static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", @@ -41,6 +41,7 @@ static const char * const attach_type_strings[] = { [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", [BPF_CGROUP_UDP4_SENDMSG] = "sendmsg4", [BPF_CGROUP_UDP6_SENDMSG] = "sendmsg6", + [BPF_CGROUP_SYSCTL] = "sysctl", [__MAX_BPF_ATTACH_TYPE] = NULL, }; @@ -248,6 +249,13 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) show_attached_bpf_progs(cgroup_fd, type, ftw->level); + if (errno == EINVAL) + /* Last attach type does not support query. + * Do not report an error for this, especially because batch + * mode would stop processing commands. + */ + errno = 0; + if (json_output) { jsonw_end_array(json_wtr); jsonw_end_object(json_wtr); diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index d7dd84d3c660..1ccc46169a19 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -73,6 +73,7 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", + [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", }; extern const char * const map_type_name[]; diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index e96903078991..10b6c9d3e525 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -261,20 +261,20 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, } static void print_entry_error(struct bpf_map_info *info, unsigned char *key, - const char *value) + const char *error_msg) { - int value_size = strlen(value); + int msg_size = strlen(error_msg); bool single_line, break_names; - break_names = info->key_size > 16 || value_size > 16; - single_line = info->key_size + value_size <= 24 && !break_names; + break_names = info->key_size > 16 || msg_size > 16; + single_line = info->key_size + msg_size <= 24 && !break_names; printf("key:%c", break_names ? '\n' : ' '); fprint_hex(stdout, key, info->key_size, " "); printf(single_line ? " " : "\n"); - printf("value:%c%s", break_names ? '\n' : ' ', value); + printf("value:%c%s", break_names ? '\n' : ' ', error_msg); printf("\n"); } @@ -298,11 +298,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, if (info->value_size) { printf("value:%c", break_names ? '\n' : ' '); - if (value) - fprint_hex(stdout, value, info->value_size, - " "); - else - printf("<no entry>"); + fprint_hex(stdout, value, info->value_size, " "); } printf("\n"); @@ -321,11 +317,8 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, for (i = 0; i < n; i++) { printf("value (CPU %02d):%c", i, info->value_size > 16 ? '\n' : ' '); - if (value) - fprint_hex(stdout, value + i * step, - info->value_size, " "); - else - printf("<no entry>"); + fprint_hex(stdout, value + i * step, + info->value_size, " "); printf("\n"); } } @@ -538,6 +531,9 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) } close(fd); + if (info->btf_id) + jsonw_int_field(json_wtr, "btf_id", info->btf_id); + if (!hash_empty(map_table.table)) { struct pinned_obj *obj; @@ -604,15 +600,19 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) } close(fd); - printf("\n"); if (!hash_empty(map_table.table)) { struct pinned_obj *obj; hash_for_each_possible(map_table.table, obj, hash, info->id) { if (obj->id == info->id) - printf("\tpinned %s\n", obj->path); + printf("\n\tpinned %s", obj->path); } } + + if (info->btf_id) + printf("\n\tbtf_id %d", info->btf_id); + + printf("\n"); return 0; } @@ -722,11 +722,16 @@ static int dump_map_elem(int fd, void *key, void *value, jsonw_string_field(json_wtr, "error", strerror(lookup_errno)); jsonw_end_object(json_wtr); } else { + const char *msg = NULL; + if (errno == ENOENT) - print_entry_plain(map_info, key, NULL); - else - print_entry_error(map_info, key, - strerror(lookup_errno)); + msg = "<no entry>"; + else if (lookup_errno == ENOSPC && + map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) + msg = "<cannot read>"; + + print_entry_error(map_info, key, + msg ? : strerror(lookup_errno)); } return 0; @@ -780,6 +785,10 @@ static int do_dump(int argc, char **argv) } } + if (info.type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && + info.value_size != 8) + p_info("Warning: cannot read values from %s map with value_size != 8", + map_type_name[info.type]); while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 81067803189e..fc495b27f0fc 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -323,7 +323,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) } if (info->btf_id) - printf("\n\tbtf_id %d\n", info->btf_id); + printf("\n\tbtf_id %d", info->btf_id); printf("\n"); } @@ -1060,7 +1060,7 @@ static int do_help(int argc, char **argv) " tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n" " cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n" " lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n" - " sk_reuseport | flow_dissector |\n" + " sk_reuseport | flow_dissector | cgroup/sysctl |\n" " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n" " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n" " cgroup/sendmsg4 | cgroup/sendmsg6 }\n" diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 2e96d0b4bf65..704bb69514a2 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -167,6 +167,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LIRC_MODE2, BPF_PROG_TYPE_SK_REUSEPORT, BPF_PROG_TYPE_FLOW_DISSECTOR, + BPF_PROG_TYPE_CGROUP_SYSCTL, }; enum bpf_attach_type { @@ -188,6 +189,7 @@ enum bpf_attach_type { BPF_CGROUP_UDP6_SENDMSG, BPF_LIRC_MODE2, BPF_FLOW_DISSECTOR, + BPF_CGROUP_SYSCTL, __MAX_BPF_ATTACH_TYPE }; @@ -2504,6 +2506,122 @@ union bpf_attr { * Return * 0 if iph and th are a valid SYN cookie ACK, or a negative error * otherwise. + * + * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) + * Description + * Get name of sysctl in /proc/sys/ and copy it into provided by + * program buffer *buf* of size *buf_len*. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is + * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name + * only (e.g. "tcp_mem"). + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get current value of sysctl as it is presented in /proc/sys + * (incl. newline, etc), and copy it as a string into provided + * by program buffer *buf* of size *buf_len*. + * + * The whole value is copied, no matter what file position user + * space issued e.g. sys_read at. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if current value was unavailable, e.g. because + * sysctl is uninitialized and read returns -EIO for it. + * + * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get new value being written by user space to sysctl (before + * the actual write happens) and copy it as a string into + * provided by program buffer *buf* of size *buf_len*. + * + * User space may write new value at file position > 0. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) + * Description + * Override new value being written by user space to sysctl with + * value provided by program in buffer *buf* of size *buf_len*. + * + * *buf* should contain a string in same form as provided by user + * space on sysctl write. + * + * User space may write new value at file position > 0. To override + * the whole sysctl value file position should be set to zero. + * Return + * 0 on success. + * + * **-E2BIG** if the *buf_len* is too big. + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to a long integer according to the given base + * and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by isspace(3)) followed by a single optional '-' + * sign. + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space strtol(3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than buf_len. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to an unsigned long integer according to the + * given base and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by isspace(3)). + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space strtoul(3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than buf_len. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2606,7 +2724,13 @@ union bpf_attr { FN(skb_ecn_set_ce), \ FN(get_listener_sock), \ FN(skc_lookup_tcp), \ - FN(tcp_check_syncookie), + FN(tcp_check_syncookie), \ + FN(sysctl_get_name), \ + FN(sysctl_get_current_value), \ + FN(sysctl_get_new_value), \ + FN(sysctl_set_new_value), \ + FN(strtol), \ + FN(strtoul), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2668,17 +2792,20 @@ enum bpf_func_id { /* BPF_FUNC_skb_adjust_room flags. */ #define BPF_F_ADJ_ROOM_FIXED_GSO (1ULL << 0) -#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff -#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56 +#define BPF_ADJ_ROOM_ENCAP_L2_MASK 0xff +#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT 56 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 (1ULL << 1) #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 (1ULL << 2) #define BPF_F_ADJ_ROOM_ENCAP_L4_GRE (1ULL << 3) #define BPF_F_ADJ_ROOM_ENCAP_L4_UDP (1ULL << 4) -#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \ +#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \ BPF_ADJ_ROOM_ENCAP_L2_MASK) \ << BPF_ADJ_ROOM_ENCAP_L2_SHIFT) +/* BPF_FUNC_sysctl_get_name flags. */ +#define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, @@ -3308,4 +3435,14 @@ struct bpf_line_info { struct bpf_spin_lock { __u32 val; }; + +struct bpf_sysctl { + __u32 write; /* Sysctl is being read (= 0) or written (= 1). + * Allows 1,2,4-byte read, but no write. + */ + __u32 file_pos; /* Sysctl file position to read from, write to. + * Allows 1,2,4-byte read an 4-byte write. + */ +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index bc30783d1403..ff2506fe6bd2 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -92,7 +92,7 @@ struct bpf_load_program_attr { #define MAPS_RELAX_COMPAT 0x01 /* Recommend log buffer size */ -#define BPF_LOG_BUF_SIZE (16 * 1024 * 1024) /* verifier maximum in kernels <= 5.1 */ +#define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */ LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, char *log_buf, size_t log_buf_sz); diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 701e7e28ada3..75eaf10b9e1a 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1354,8 +1354,16 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, } /* special BTF "void" type is made canonical immediately */ d->map[0] = 0; - for (i = 1; i <= btf->nr_types; i++) - d->map[i] = BTF_UNPROCESSED_ID; + for (i = 1; i <= btf->nr_types; i++) { + struct btf_type *t = d->btf->types[i]; + __u16 kind = BTF_INFO_KIND(t->info); + + /* VAR and DATASEC are never deduped and are self-canonical */ + if (kind == BTF_KIND_VAR || kind == BTF_KIND_DATASEC) + d->map[i] = i; + else + d->map[i] = BTF_UNPROCESSED_ID; + } d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types)); if (!d->hypot_map) { @@ -1946,6 +1954,8 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_UNION: case BTF_KIND_FUNC: case BTF_KIND_FUNC_PROTO: + case BTF_KIND_VAR: + case BTF_KIND_DATASEC: return 0; case BTF_KIND_INT: @@ -2699,6 +2709,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + case BTF_KIND_VAR: r = btf_dedup_remap_type_id(d, t->type); if (r < 0) return r; @@ -2753,6 +2764,20 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) break; } + case BTF_KIND_DATASEC: { + struct btf_var_secinfo *var = (struct btf_var_secinfo *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + + for (i = 0; i < vlen; i++) { + r = btf_dedup_remap_type_id(d, var->type); + if (r < 0) + return r; + var->type = r; + var++; + } + break; + } + default: return -EINVAL; } diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 67484cf32b2e..d817bf20f3d6 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -817,7 +817,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map, memcpy(*data_buff, data->d_buf, data->d_size); } - pr_debug("map %ld is \"%s\"\n", map - obj->maps, map->name); + pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name); return 0; } @@ -2064,6 +2064,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_CGROUP_SYSCTL: return false; case BPF_PROG_TYPE_KPROBE: default: @@ -3004,6 +3005,8 @@ static const struct { BPF_CGROUP_UDP4_SENDMSG), BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG), + BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_CGROUP_SYSCTL), }; #undef BPF_PROG_SEC_IMPL diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 8c3a1c04dcb2..0f25541632e3 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -97,6 +97,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_LIRC_MODE2: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_CGROUP_SYSCTL: default: break; } diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h index 81ecda0cb9c9..da94c4cb2e4d 100644 --- a/tools/lib/bpf/libbpf_util.h +++ b/tools/lib/bpf/libbpf_util.h @@ -23,6 +23,36 @@ do { \ #define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) #define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) +/* Use these barrier functions instead of smp_[rw]mb() when they are + * used in a libbpf header file. That way they can be built into the + * application that uses libbpf. + */ +#if defined(__i386__) || defined(__x86_64__) +# define libbpf_smp_rmb() asm volatile("" : : : "memory") +# define libbpf_smp_wmb() asm volatile("" : : : "memory") +# define libbpf_smp_mb() \ + asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc") +/* Hinders stores to be observed before older loads. */ +# define libbpf_smp_rwmb() asm volatile("" : : : "memory") +#elif defined(__aarch64__) +# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory") +# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory") +# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_rwmb() libbpf_smp_mb() +#elif defined(__arm__) +/* These are only valid for armv7 and above */ +# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory") +# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_rwmb() libbpf_smp_mb() +#else +/* Architecture missing native barrier functions. */ +# define libbpf_smp_rmb() __sync_synchronize() +# define libbpf_smp_wmb() __sync_synchronize() +# define libbpf_smp_mb() __sync_synchronize() +# define libbpf_smp_rwmb() __sync_synchronize() +#endif + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h index a497f00e2962..82ea71a0f3ec 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/lib/bpf/xsk.h @@ -16,6 +16,7 @@ #include <linux/if_xdp.h> #include "libbpf.h" +#include "libbpf_util.h" #ifdef __cplusplus extern "C" { @@ -36,6 +37,10 @@ struct name { \ DEFINE_XSK_RING(xsk_ring_prod); DEFINE_XSK_RING(xsk_ring_cons); +/* For a detailed explanation on the memory barriers associated with the + * ring, please take a look at net/xdp/xsk_queue.h. + */ + struct xsk_umem; struct xsk_socket; @@ -105,7 +110,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb) static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod, size_t nb, __u32 *idx) { - if (unlikely(xsk_prod_nb_free(prod, nb) < nb)) + if (xsk_prod_nb_free(prod, nb) < nb) return 0; *idx = prod->cached_prod; @@ -116,10 +121,10 @@ static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod, static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb) { - /* Make sure everything has been written to the ring before signalling - * this to the kernel. + /* Make sure everything has been written to the ring before indicating + * this to the kernel by writing the producer pointer. */ - smp_wmb(); + libbpf_smp_wmb(); *prod->producer += nb; } @@ -129,11 +134,11 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons, { size_t entries = xsk_cons_nb_avail(cons, nb); - if (likely(entries > 0)) { + if (entries > 0) { /* Make sure we do not speculatively read the data before * we have received the packet buffers from the ring. */ - smp_rmb(); + libbpf_smp_rmb(); *idx = cons->cached_cons; cons->cached_cons += entries; @@ -144,6 +149,11 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons, static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb) { + /* Make sure data has been read before indicating we are done + * with the entries by updating the consumer pointer. + */ + libbpf_smp_rwmb(); + *cons->consumer += nb; } diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 078283d073b0..f9d83ba7843e 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -23,7 +23,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \ test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \ - test_netcnt test_tcpnotify_user test_sock_fields + test_netcnt test_tcpnotify_user test_sock_fields test_sysctl BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c))) TEST_GEN_FILES = $(BPF_OBJ_FILES) @@ -93,6 +93,7 @@ $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c $(OUTPUT)/test_netcnt: cgroup_helpers.c $(OUTPUT)/test_sock_fields: cgroup_helpers.c +$(OUTPUT)/test_sysctl: cgroup_helpers.c .PHONY: force diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index e85d62cb53d0..59e221586cf7 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -192,6 +192,25 @@ static int (*bpf_skb_ecn_set_ce)(void *ctx) = static int (*bpf_tcp_check_syncookie)(struct bpf_sock *sk, void *ip, int ip_len, void *tcp, int tcp_len) = (void *) BPF_FUNC_tcp_check_syncookie; +static int (*bpf_sysctl_get_name)(void *ctx, char *buf, + unsigned long long buf_len, + unsigned long long flags) = + (void *) BPF_FUNC_sysctl_get_name; +static int (*bpf_sysctl_get_current_value)(void *ctx, char *buf, + unsigned long long buf_len) = + (void *) BPF_FUNC_sysctl_get_current_value; +static int (*bpf_sysctl_get_new_value)(void *ctx, char *buf, + unsigned long long buf_len) = + (void *) BPF_FUNC_sysctl_get_new_value; +static int (*bpf_sysctl_set_new_value)(void *ctx, const char *buf, + unsigned long long buf_len) = + (void *) BPF_FUNC_sysctl_set_new_value; +static int (*bpf_strtol)(const char *buf, unsigned long long buf_len, + unsigned long long flags, long *res) = + (void *) BPF_FUNC_strtol; +static int (*bpf_strtoul)(const char *buf, unsigned long long buf_len, + unsigned long long flags, unsigned long *res) = + (void *) BPF_FUNC_strtoul; /* 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/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index fc818bc1d729..126319f9a97c 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -2,7 +2,7 @@ #include <test_progs.h> #define CHECK_FLOW_KEYS(desc, got, expected) \ - CHECK(memcmp(&got, &expected, sizeof(got)) != 0, \ + CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0, \ desc, \ "nhoff=%u/%u " \ "thoff=%u/%u " \ @@ -10,6 +10,7 @@ "is_frag=%u/%u " \ "is_first_frag=%u/%u " \ "is_encap=%u/%u " \ + "ip_proto=0x%x/0x%x " \ "n_proto=0x%x/0x%x " \ "sport=%u/%u " \ "dport=%u/%u\n", \ @@ -19,53 +20,32 @@ got.is_frag, expected.is_frag, \ got.is_first_frag, expected.is_first_frag, \ got.is_encap, expected.is_encap, \ + got.ip_proto, expected.ip_proto, \ got.n_proto, expected.n_proto, \ got.sport, expected.sport, \ got.dport, expected.dport) -static struct bpf_flow_keys pkt_v4_flow_keys = { - .nhoff = 0, - .thoff = sizeof(struct iphdr), - .addr_proto = ETH_P_IP, - .ip_proto = IPPROTO_TCP, - .n_proto = __bpf_constant_htons(ETH_P_IP), -}; - -static struct bpf_flow_keys pkt_v6_flow_keys = { - .nhoff = 0, - .thoff = sizeof(struct ipv6hdr), - .addr_proto = ETH_P_IPV6, - .ip_proto = IPPROTO_TCP, - .n_proto = __bpf_constant_htons(ETH_P_IPV6), -}; - -#define VLAN_HLEN 4 +struct ipv4_pkt { + struct ethhdr eth; + struct iphdr iph; + struct tcphdr tcp; +} __packed; -static struct { +struct svlan_ipv4_pkt { struct ethhdr eth; __u16 vlan_tci; __u16 vlan_proto; struct iphdr iph; struct tcphdr tcp; -} __packed pkt_vlan_v4 = { - .eth.h_proto = __bpf_constant_htons(ETH_P_8021Q), - .vlan_proto = __bpf_constant_htons(ETH_P_IP), - .iph.ihl = 5, - .iph.protocol = IPPROTO_TCP, - .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), - .tcp.urg_ptr = 123, - .tcp.doff = 5, -}; +} __packed; -static struct bpf_flow_keys pkt_vlan_v4_flow_keys = { - .nhoff = VLAN_HLEN, - .thoff = VLAN_HLEN + sizeof(struct iphdr), - .addr_proto = ETH_P_IP, - .ip_proto = IPPROTO_TCP, - .n_proto = __bpf_constant_htons(ETH_P_IP), -}; +struct ipv6_pkt { + struct ethhdr eth; + struct ipv6hdr iph; + struct tcphdr tcp; +} __packed; -static struct { +struct dvlan_ipv6_pkt { struct ethhdr eth; __u16 vlan_tci; __u16 vlan_proto; @@ -73,31 +53,97 @@ static struct { __u16 vlan_proto2; struct ipv6hdr iph; struct tcphdr tcp; -} __packed pkt_vlan_v6 = { - .eth.h_proto = __bpf_constant_htons(ETH_P_8021AD), - .vlan_proto = __bpf_constant_htons(ETH_P_8021Q), - .vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6), - .iph.nexthdr = IPPROTO_TCP, - .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), - .tcp.urg_ptr = 123, - .tcp.doff = 5, +} __packed; + +struct test { + const char *name; + union { + struct ipv4_pkt ipv4; + struct svlan_ipv4_pkt svlan_ipv4; + struct ipv6_pkt ipv6; + struct dvlan_ipv6_pkt dvlan_ipv6; + } pkt; + struct bpf_flow_keys keys; }; -static struct bpf_flow_keys pkt_vlan_v6_flow_keys = { - .nhoff = VLAN_HLEN * 2, - .thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr), - .addr_proto = ETH_P_IPV6, - .ip_proto = IPPROTO_TCP, - .n_proto = __bpf_constant_htons(ETH_P_IPV6), +#define VLAN_HLEN 4 + +struct test tests[] = { + { + .name = "ipv4", + .pkt.ipv4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.doff = 5, + }, + .keys = { + .nhoff = 0, + .thoff = sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + }, + }, + { + .name = "ipv6", + .pkt.ipv6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.doff = 5, + }, + .keys = { + .nhoff = 0, + .thoff = sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + }, + }, + { + .name = "802.1q-ipv4", + .pkt.svlan_ipv4 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_8021Q), + .vlan_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_TCP, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.doff = 5, + }, + .keys = { + .nhoff = VLAN_HLEN, + .thoff = VLAN_HLEN + sizeof(struct iphdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + }, + }, + { + .name = "802.1ad-ipv6", + .pkt.dvlan_ipv6 = { + .eth.h_proto = __bpf_constant_htons(ETH_P_8021AD), + .vlan_proto = __bpf_constant_htons(ETH_P_8021Q), + .vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6), + .iph.nexthdr = IPPROTO_TCP, + .iph.payload_len = __bpf_constant_htons(MAGIC_BYTES), + .tcp.doff = 5, + }, + .keys = { + .nhoff = VLAN_HLEN * 2, + .thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr), + .addr_proto = ETH_P_IPV6, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IPV6), + }, + }, }; void test_flow_dissector(void) { - struct bpf_flow_keys flow_keys; struct bpf_object *obj; - __u32 duration, retval; - int err, prog_fd; - __u32 size; + int i, err, prog_fd; err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector", "jmp_table", &prog_fd); @@ -106,35 +152,24 @@ void test_flow_dissector(void) return; } - err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4), - &flow_keys, &size, &retval, &duration); - CHECK(size != sizeof(flow_keys) || err || retval != 1, "ipv4", - "err %d errno %d retval %d duration %d size %u/%lu\n", - err, errno, retval, duration, size, sizeof(flow_keys)); - CHECK_FLOW_KEYS("ipv4_flow_keys", flow_keys, pkt_v4_flow_keys); - - err = bpf_prog_test_run(prog_fd, 10, &pkt_v6, sizeof(pkt_v6), - &flow_keys, &size, &retval, &duration); - CHECK(size != sizeof(flow_keys) || err || retval != 1, "ipv6", - "err %d errno %d retval %d duration %d size %u/%lu\n", - err, errno, retval, duration, size, sizeof(flow_keys)); - CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys); + for (i = 0; i < ARRAY_SIZE(tests); i++) { + struct bpf_flow_keys flow_keys; + struct bpf_prog_test_run_attr tattr = { + .prog_fd = prog_fd, + .data_in = &tests[i].pkt, + .data_size_in = sizeof(tests[i].pkt), + .data_out = &flow_keys, + }; - err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4), - &flow_keys, &size, &retval, &duration); - CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4", - "err %d errno %d retval %d duration %d size %u/%lu\n", - err, errno, retval, duration, size, sizeof(flow_keys)); - CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys, - pkt_vlan_v4_flow_keys); - - err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6), - &flow_keys, &size, &retval, &duration); - CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6", - "err %d errno %d retval %d duration %d size %u/%lu\n", - err, errno, retval, duration, size, sizeof(flow_keys)); - CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys, - pkt_vlan_v6_flow_keys); + err = bpf_prog_test_run_xattr(&tattr); + CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) || + err || tattr.retval != 1, + tests[i].name, + "err %d errno %d retval %d duration %d size %u/%lu\n", + err, errno, tattr.retval, tattr.duration, + tattr.data_size_out, sizeof(flow_keys)); + CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + } bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c new file mode 100644 index 000000000000..a295cad805d7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stdint.h> +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include "bpf_helpers.h" +#include "bpf_util.h" + +/* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */ +#define MAX_ULONG_STR_LEN 0xF + +/* Max supported length of sysctl value string (pow2). */ +#define MAX_VALUE_STR_LEN 0x40 + +static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx) +{ + char tcp_mem_name[] = "net/ipv4/tcp_mem"; + unsigned char i; + char name[64]; + int ret; + + memset(name, 0, sizeof(name)); + ret = bpf_sysctl_get_name(ctx, name, sizeof(name), 0); + if (ret < 0 || ret != sizeof(tcp_mem_name) - 1) + return 0; + +#pragma clang loop unroll(full) + for (i = 0; i < sizeof(tcp_mem_name); ++i) + if (name[i] != tcp_mem_name[i]) + return 0; + + return 1; +} + +SEC("cgroup/sysctl") +int sysctl_tcp_mem(struct bpf_sysctl *ctx) +{ + unsigned long tcp_mem[3] = {0, 0, 0}; + char value[MAX_VALUE_STR_LEN]; + unsigned char i, off = 0; + int ret; + + if (ctx->write) + return 0; + + if (!is_tcp_mem(ctx)) + return 0; + + ret = bpf_sysctl_get_current_value(ctx, value, MAX_VALUE_STR_LEN); + if (ret < 0 || ret >= MAX_VALUE_STR_LEN) + return 0; + +#pragma clang loop unroll(full) + for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) { + ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0, + tcp_mem + i); + if (ret <= 0 || ret > MAX_ULONG_STR_LEN) + return 0; + off += ret & MAX_ULONG_STR_LEN; + } + + + return tcp_mem[0] < tcp_mem[1] && tcp_mem[1] < tcp_mem[2]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c index bcb00d737e95..ab56a6a72b7a 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -157,7 +157,7 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, bpf_ntohs(h_outer.ip.tot_len)); h_outer.ip.protocol = encap_proto; - set_ipv4_csum(&h_outer.ip); + set_ipv4_csum((void *)&h_outer.ip); /* store new outer network header */ if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen, diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index 74f73b33a7b0..c7c3240e0dd4 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <stddef.h> #include <string.h> +#include <netinet/in.h> #include <linux/bpf.h> #include <linux/if_ether.h> #include <linux/if_packet.h> @@ -9,7 +10,6 @@ #include <linux/types.h> #include <linux/socket.h> #include <linux/tcp.h> -#include <netinet/in.h> #include "bpf_helpers.h" #include "bpf_endian.h" #include "test_tcpbpf.h" diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index edbca203ce2d..ec6db6e64c41 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <stddef.h> #include <string.h> +#include <netinet/in.h> #include <linux/bpf.h> #include <linux/if_ether.h> #include <linux/if_packet.h> @@ -9,7 +10,6 @@ #include <linux/types.h> #include <linux/socket.h> #include <linux/tcp.h> -#include <netinet/in.h> #include "bpf_helpers.h" #include "bpf_endian.h" #include "test_tcpnotify.h" diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 44cd3378d216..f8eb7987b794 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -6642,6 +6642,51 @@ const struct btf_dedup_test dedup_tests[] = { .dont_resolve_fwds = false, }, }, +{ + .descr = "dedup: datasec and vars pass-through", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* static int t */ + BTF_VAR_ENC(NAME_NTH(2), 1, 0), /* [2] */ + /* .bss section */ /* [3] */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + /* int, referenced from [5] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [4] */ + /* another static int t */ + BTF_VAR_ENC(NAME_NTH(2), 4, 0), /* [5] */ + /* another .bss section */ /* [6] */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(5, 0, 4), + BTF_END_RAW, + }, + BTF_STR_SEC("\0.bss\0t"), + }, + .expect = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* static int t */ + BTF_VAR_ENC(NAME_NTH(2), 1, 0), /* [2] */ + /* .bss section */ /* [3] */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + /* another static int t */ + BTF_VAR_ENC(NAME_NTH(2), 1, 0), /* [4] */ + /* another .bss section */ /* [5] */ + BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(4, 0, 4), + BTF_END_RAW, + }, + BTF_STR_SEC("\0.bss\0t"), + }, + .opts = { + .dont_resolve_fwds = false, + .dedup_table_size = 1 + }, +}, }; @@ -6671,6 +6716,10 @@ static int btf_type_size(const struct btf_type *t) return base_size + vlen * sizeof(struct btf_member); case BTF_KIND_FUNC_PROTO: return base_size + vlen * sizeof(struct btf_param); + case BTF_KIND_VAR: + return base_size + sizeof(struct btf_var); + case BTF_KIND_DATASEC: + return base_size + vlen * sizeof(struct btf_var_secinfo); default: fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind); return -EINVAL; diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index d4d3391cc13a..acf7a74f97cd 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -129,6 +129,24 @@ setup() ip link set veth7 netns ${NS2} ip link set veth8 netns ${NS3} + if [ ! -z "${VRF}" ] ; then + ip -netns ${NS1} link add red type vrf table 1001 + ip -netns ${NS1} link set red up + ip -netns ${NS1} route add table 1001 unreachable default metric 8192 + ip -netns ${NS1} -6 route add table 1001 unreachable default metric 8192 + ip -netns ${NS1} link set veth1 vrf red + ip -netns ${NS1} link set veth5 vrf red + + ip -netns ${NS2} link add red type vrf table 1001 + ip -netns ${NS2} link set red up + ip -netns ${NS2} route add table 1001 unreachable default metric 8192 + ip -netns ${NS2} -6 route add table 1001 unreachable default metric 8192 + ip -netns ${NS2} link set veth2 vrf red + ip -netns ${NS2} link set veth3 vrf red + ip -netns ${NS2} link set veth6 vrf red + ip -netns ${NS2} link set veth7 vrf red + fi + # configure addesses: the top route (1-2-3-4) ip -netns ${NS1} addr add ${IPv4_1}/24 dev veth1 ip -netns ${NS2} addr add ${IPv4_2}/24 dev veth2 @@ -163,29 +181,29 @@ setup() # NS1 # top route - ip -netns ${NS1} route add ${IPv4_2}/32 dev veth1 - ip -netns ${NS1} route add default dev veth1 via ${IPv4_2} # go top by default - ip -netns ${NS1} -6 route add ${IPv6_2}/128 dev veth1 - ip -netns ${NS1} -6 route add default dev veth1 via ${IPv6_2} # go top by default + ip -netns ${NS1} route add ${IPv4_2}/32 dev veth1 ${VRF} + ip -netns ${NS1} route add default dev veth1 via ${IPv4_2} ${VRF} # go top by default + ip -netns ${NS1} -6 route add ${IPv6_2}/128 dev veth1 ${VRF} + ip -netns ${NS1} -6 route add default dev veth1 via ${IPv6_2} ${VRF} # go top by default # bottom route - ip -netns ${NS1} route add ${IPv4_6}/32 dev veth5 - ip -netns ${NS1} route add ${IPv4_7}/32 dev veth5 via ${IPv4_6} - ip -netns ${NS1} route add ${IPv4_8}/32 dev veth5 via ${IPv4_6} - ip -netns ${NS1} -6 route add ${IPv6_6}/128 dev veth5 - ip -netns ${NS1} -6 route add ${IPv6_7}/128 dev veth5 via ${IPv6_6} - ip -netns ${NS1} -6 route add ${IPv6_8}/128 dev veth5 via ${IPv6_6} + ip -netns ${NS1} route add ${IPv4_6}/32 dev veth5 ${VRF} + ip -netns ${NS1} route add ${IPv4_7}/32 dev veth5 via ${IPv4_6} ${VRF} + ip -netns ${NS1} route add ${IPv4_8}/32 dev veth5 via ${IPv4_6} ${VRF} + ip -netns ${NS1} -6 route add ${IPv6_6}/128 dev veth5 ${VRF} + ip -netns ${NS1} -6 route add ${IPv6_7}/128 dev veth5 via ${IPv6_6} ${VRF} + ip -netns ${NS1} -6 route add ${IPv6_8}/128 dev veth5 via ${IPv6_6} ${VRF} # NS2 # top route - ip -netns ${NS2} route add ${IPv4_1}/32 dev veth2 - ip -netns ${NS2} route add ${IPv4_4}/32 dev veth3 - ip -netns ${NS2} -6 route add ${IPv6_1}/128 dev veth2 - ip -netns ${NS2} -6 route add ${IPv6_4}/128 dev veth3 + ip -netns ${NS2} route add ${IPv4_1}/32 dev veth2 ${VRF} + ip -netns ${NS2} route add ${IPv4_4}/32 dev veth3 ${VRF} + ip -netns ${NS2} -6 route add ${IPv6_1}/128 dev veth2 ${VRF} + ip -netns ${NS2} -6 route add ${IPv6_4}/128 dev veth3 ${VRF} # bottom route - ip -netns ${NS2} route add ${IPv4_5}/32 dev veth6 - ip -netns ${NS2} route add ${IPv4_8}/32 dev veth7 - ip -netns ${NS2} -6 route add ${IPv6_5}/128 dev veth6 - ip -netns ${NS2} -6 route add ${IPv6_8}/128 dev veth7 + ip -netns ${NS2} route add ${IPv4_5}/32 dev veth6 ${VRF} + ip -netns ${NS2} route add ${IPv4_8}/32 dev veth7 ${VRF} + ip -netns ${NS2} -6 route add ${IPv6_5}/128 dev veth6 ${VRF} + ip -netns ${NS2} -6 route add ${IPv6_8}/128 dev veth7 ${VRF} # NS3 # top route @@ -207,16 +225,16 @@ setup() ip -netns ${NS3} tunnel add gre_dev mode gre remote ${IPv4_1} local ${IPv4_GRE} ttl 255 ip -netns ${NS3} link set gre_dev up ip -netns ${NS3} addr add ${IPv4_GRE} dev gre_dev - ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6} - ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8} + ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6} ${VRF} + ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8} ${VRF} # configure IPv6 GRE device in NS3, and a route to it via the "bottom" route ip -netns ${NS3} -6 tunnel add name gre6_dev mode ip6gre remote ${IPv6_1} local ${IPv6_GRE} ttl 255 ip -netns ${NS3} link set gre6_dev up ip -netns ${NS3} -6 addr add ${IPv6_GRE} nodad dev gre6_dev - ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} - ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} + ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF} + ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF} # rp_filter gets confused by what these tests are doing, so disable it ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 @@ -244,18 +262,18 @@ trap cleanup EXIT remove_routes_to_gredev() { - ip -netns ${NS1} route del ${IPv4_GRE} dev veth5 - ip -netns ${NS2} route del ${IPv4_GRE} dev veth7 - ip -netns ${NS1} -6 route del ${IPv6_GRE}/128 dev veth5 - ip -netns ${NS2} -6 route del ${IPv6_GRE}/128 dev veth7 + ip -netns ${NS1} route del ${IPv4_GRE} dev veth5 ${VRF} + ip -netns ${NS2} route del ${IPv4_GRE} dev veth7 ${VRF} + ip -netns ${NS1} -6 route del ${IPv6_GRE}/128 dev veth5 ${VRF} + ip -netns ${NS2} -6 route del ${IPv6_GRE}/128 dev veth7 ${VRF} } add_unreachable_routes_to_gredev() { - ip -netns ${NS1} route add unreachable ${IPv4_GRE}/32 - ip -netns ${NS2} route add unreachable ${IPv4_GRE}/32 - ip -netns ${NS1} -6 route add unreachable ${IPv6_GRE}/128 - ip -netns ${NS2} -6 route add unreachable ${IPv6_GRE}/128 + ip -netns ${NS1} route add unreachable ${IPv4_GRE}/32 ${VRF} + ip -netns ${NS2} route add unreachable ${IPv4_GRE}/32 ${VRF} + ip -netns ${NS1} -6 route add unreachable ${IPv6_GRE}/128 ${VRF} + ip -netns ${NS2} -6 route add unreachable ${IPv6_GRE}/128 ${VRF} } test_ping() @@ -265,10 +283,10 @@ test_ping() local RET=0 if [ "${PROTO}" == "IPv4" ] ; then - ip netns exec ${NS1} ping -c 1 -W 1 -I ${IPv4_SRC} ${IPv4_DST} 2>&1 > /dev/null + ip netns exec ${NS1} ping -c 1 -W 1 -I veth1 ${IPv4_DST} 2>&1 > /dev/null RET=$? elif [ "${PROTO}" == "IPv6" ] ; then - ip netns exec ${NS1} ping6 -c 1 -W 6 -I ${IPv6_SRC} ${IPv6_DST} 2>&1 > /dev/null + ip netns exec ${NS1} ping6 -c 1 -W 6 -I veth1 ${IPv6_DST} 2>&1 > /dev/null RET=$? else echo " test_ping: unknown PROTO: ${PROTO}" @@ -328,7 +346,7 @@ test_gso() test_egress() { local readonly ENCAP=$1 - echo "starting egress ${ENCAP} encap test" + echo "starting egress ${ENCAP} encap test ${VRF}" setup # by default, pings work @@ -336,26 +354,35 @@ test_egress() test_ping IPv6 0 # remove NS2->DST routes, ping fails - ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 - ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 + ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 ${VRF} + ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 ${VRF} test_ping IPv4 1 test_ping IPv6 1 # install replacement routes (LWT/eBPF), pings succeed if [ "${ENCAP}" == "IPv4" ] ; then - ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre dev veth1 - ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre dev veth1 + ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj \ + test_lwt_ip_encap.o sec encap_gre dev veth1 ${VRF} + ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj \ + test_lwt_ip_encap.o sec encap_gre dev veth1 ${VRF} elif [ "${ENCAP}" == "IPv6" ] ; then - ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre6 dev veth1 - ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre6 dev veth1 + ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj \ + test_lwt_ip_encap.o sec encap_gre6 dev veth1 ${VRF} + ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj \ + test_lwt_ip_encap.o sec encap_gre6 dev veth1 ${VRF} else echo " unknown encap ${ENCAP}" TEST_STATUS=1 fi test_ping IPv4 0 test_ping IPv6 0 - test_gso IPv4 - test_gso IPv6 + + # skip GSO tests with VRF: VRF routing needs properly assigned + # source IP/device, which is easy to do with ping and hard with dd/nc. + if [ -z "${VRF}" ] ; then + test_gso IPv4 + test_gso IPv6 + fi # a negative test: remove routes to GRE devices: ping fails remove_routes_to_gredev @@ -374,7 +401,7 @@ test_egress() test_ingress() { local readonly ENCAP=$1 - echo "starting ingress ${ENCAP} encap test" + echo "starting ingress ${ENCAP} encap test ${VRF}" setup # need to wait a bit for IPv6 to autoconf, otherwise @@ -385,18 +412,22 @@ test_ingress() test_ping IPv6 0 # remove NS2->DST routes, pings fail - ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 - ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 + ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 ${VRF} + ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 ${VRF} test_ping IPv4 1 test_ping IPv6 1 # install replacement routes (LWT/eBPF), pings succeed if [ "${ENCAP}" == "IPv4" ] ; then - ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre dev veth2 - ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre dev veth2 + ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj \ + test_lwt_ip_encap.o sec encap_gre dev veth2 ${VRF} + ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj \ + test_lwt_ip_encap.o sec encap_gre dev veth2 ${VRF} elif [ "${ENCAP}" == "IPv6" ] ; then - ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre6 dev veth2 - ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre6 dev veth2 + ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj \ + test_lwt_ip_encap.o sec encap_gre6 dev veth2 ${VRF} + ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj \ + test_lwt_ip_encap.o sec encap_gre6 dev veth2 ${VRF} else echo "FAIL: unknown encap ${ENCAP}" TEST_STATUS=1 @@ -418,6 +449,13 @@ test_ingress() process_test_results } +VRF="" +test_egress IPv4 +test_egress IPv6 +test_ingress IPv4 +test_ingress IPv6 + +VRF="vrf red" test_egress IPv4 test_egress IPv6 test_ingress IPv4 diff --git a/tools/testing/selftests/bpf/test_section_names.c b/tools/testing/selftests/bpf/test_section_names.c index 7c4f41572b1c..bebd4fbca1f4 100644 --- a/tools/testing/selftests/bpf/test_section_names.c +++ b/tools/testing/selftests/bpf/test_section_names.c @@ -119,6 +119,11 @@ static struct sec_name_test tests[] = { {0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG}, {0, BPF_CGROUP_UDP6_SENDMSG}, }, + { + "cgroup/sysctl", + {0, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL}, + {0, BPF_CGROUP_SYSCTL}, + }, }; static int test_prog_type_by_name(const struct sec_name_test *test) diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c new file mode 100644 index 000000000000..a3bebd7c68dd --- /dev/null +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -0,0 +1,1567 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <fcntl.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include <linux/filter.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_rlimit.h" +#include "bpf_util.h" +#include "cgroup_helpers.h" + +#define CG_PATH "/foo" +#define MAX_INSNS 512 +#define FIXUP_SYSCTL_VALUE 0 + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +struct sysctl_test { + const char *descr; + size_t fixup_value_insn; + struct bpf_insn insns[MAX_INSNS]; + const char *prog_file; + enum bpf_attach_type attach_type; + const char *sysctl; + int open_flags; + const char *newval; + const char *oldval; + enum { + LOAD_REJECT, + ATTACH_REJECT, + OP_EPERM, + SUCCESS, + } result; +}; + +static struct sysctl_test tests[] = { + { + .descr = "sysctl wrong attach_type", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = 0, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .result = ATTACH_REJECT, + }, + { + .descr = "sysctl:read allow all", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl:read deny all", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .result = OP_EPERM, + }, + { + .descr = "ctx:write sysctl:read read ok", + .insns = { + /* If (write) */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sysctl, write)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 1, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "ctx:write sysctl:write read ok", + .insns = { + /* If (write) */ + BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sysctl, write)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 1, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/domainname", + .open_flags = O_WRONLY, + .newval = "(none)", /* same as default, should fail anyway */ + .result = OP_EPERM, + }, + { + .descr = "ctx:write sysctl:read write reject", + .insns = { + /* write = X */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sysctl, write)), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .result = LOAD_REJECT, + }, + { + .descr = "ctx:file_pos sysctl:read read ok", + .insns = { + /* If (file_pos == X) */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sysctl, file_pos)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "ctx:file_pos sysctl:read read ok narrow", + .insns = { + /* If (file_pos == X) */ + BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sysctl, file_pos)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "ctx:file_pos sysctl:read write ok", + .insns = { + /* file_pos = X */ + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sysctl, file_pos)), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .oldval = "nux\n", + .result = SUCCESS, + }, + { + .descr = "sysctl_get_name sysctl_value:base ok", + .insns = { + /* sysctl_get_name arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_name arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 8), + + /* sysctl_get_name arg4 (flags) */ + BPF_MOV64_IMM(BPF_REG_4, BPF_F_SYSCTL_BASE_NAME), + + /* sysctl_get_name(ctx, buf, buf_len, flags) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_name), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, sizeof("tcp_mem") - 1, 6), + /* buf == "tcp_mem\0") */ + BPF_LD_IMM64(BPF_REG_8, 0x006d656d5f706374ULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/tcp_mem", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl_get_name sysctl_value:base E2BIG truncated", + .insns = { + /* sysctl_get_name arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_name arg3 (buf_len) too small */ + BPF_MOV64_IMM(BPF_REG_3, 7), + + /* sysctl_get_name arg4 (flags) */ + BPF_MOV64_IMM(BPF_REG_4, BPF_F_SYSCTL_BASE_NAME), + + /* sysctl_get_name(ctx, buf, buf_len, flags) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_name), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6), + + /* buf[0:7] == "tcp_me\0") */ + BPF_LD_IMM64(BPF_REG_8, 0x00656d5f706374ULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/tcp_mem", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl_get_name sysctl:full ok", + .insns = { + /* sysctl_get_name arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 16), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_name arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 17), + + /* sysctl_get_name arg4 (flags) */ + BPF_MOV64_IMM(BPF_REG_4, 0), + + /* sysctl_get_name(ctx, buf, buf_len, flags) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_name), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 16, 14), + + /* buf[0:8] == "net/ipv4" && */ + BPF_LD_IMM64(BPF_REG_8, 0x347670692f74656eULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 10), + + /* buf[8:16] == "/tcp_mem" && */ + BPF_LD_IMM64(BPF_REG_8, 0x6d656d5f7063742fULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6), + + /* buf[16:24] == "\0") */ + BPF_LD_IMM64(BPF_REG_8, 0x0ULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 16), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/tcp_mem", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl_get_name sysctl:full E2BIG truncated", + .insns = { + /* sysctl_get_name arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -16), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_name arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 16), + + /* sysctl_get_name arg4 (flags) */ + BPF_MOV64_IMM(BPF_REG_4, 0), + + /* sysctl_get_name(ctx, buf, buf_len, flags) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_name), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 10), + + /* buf[0:8] == "net/ipv4" && */ + BPF_LD_IMM64(BPF_REG_8, 0x347670692f74656eULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6), + + /* buf[8:16] == "/tcp_me\0") */ + BPF_LD_IMM64(BPF_REG_8, 0x00656d5f7063742fULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/tcp_mem", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl_get_name sysctl:full E2BIG truncated small", + .insns = { + /* sysctl_get_name arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_name arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 7), + + /* sysctl_get_name arg4 (flags) */ + BPF_MOV64_IMM(BPF_REG_4, 0), + + /* sysctl_get_name(ctx, buf, buf_len, flags) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_name), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6), + + /* buf[0:8] == "net/ip\0") */ + BPF_LD_IMM64(BPF_REG_8, 0x000070692f74656eULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/tcp_mem", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl_get_current_value sysctl:read ok, gt", + .insns = { + /* sysctl_get_current_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_current_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 8), + + /* sysctl_get_current_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_current_value), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 6, 6), + + /* buf[0:6] == "Linux\n\0") */ + BPF_LD_IMM64(BPF_REG_8, 0x000a78756e694cULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl_get_current_value sysctl:read ok, eq", + .insns = { + /* sysctl_get_current_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_7, BPF_REG_0, 7), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_current_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 7), + + /* sysctl_get_current_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_current_value), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 6, 6), + + /* buf[0:6] == "Linux\n\0") */ + BPF_LD_IMM64(BPF_REG_8, 0x000a78756e694cULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl_get_current_value sysctl:read E2BIG truncated", + .insns = { + /* sysctl_get_current_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_H, BPF_REG_7, BPF_REG_0, 6), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_current_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 6), + + /* sysctl_get_current_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_current_value), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 6), + + /* buf[0:6] == "Linux\0") */ + BPF_LD_IMM64(BPF_REG_8, 0x000078756e694cULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "kernel/ostype", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl_get_current_value sysctl:read EINVAL", + .insns = { + /* sysctl_get_current_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_current_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 8), + + /* sysctl_get_current_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_current_value), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 4), + + /* buf[0:8] is NUL-filled) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv6/conf/lo/stable_secret", /* -EIO */ + .open_flags = O_RDONLY, + .result = OP_EPERM, + }, + { + .descr = "sysctl_get_current_value sysctl:write ok", + .fixup_value_insn = 6, + .insns = { + /* sysctl_get_current_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_current_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 8), + + /* sysctl_get_current_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_current_value), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 4, 6), + + /* buf[0:4] == expected) */ + BPF_LD_IMM64(BPF_REG_8, FIXUP_SYSCTL_VALUE), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_WRONLY, + .newval = "600", /* same as default, should fail anyway */ + .result = OP_EPERM, + }, + { + .descr = "sysctl_get_new_value sysctl:read EINVAL", + .insns = { + /* sysctl_get_new_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_new_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 8), + + /* sysctl_get_new_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_new_value), + + /* if (ret == expected) */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/tcp_mem", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl_get_new_value sysctl:write ok", + .insns = { + /* sysctl_get_new_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_new_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 4), + + /* sysctl_get_new_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_new_value), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 3, 4), + + /* buf[0:4] == "606\0") */ + BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0x00363036, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_WRONLY, + .newval = "606", + .result = OP_EPERM, + }, + { + .descr = "sysctl_get_new_value sysctl:write ok long", + .insns = { + /* sysctl_get_new_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_new_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 24), + + /* sysctl_get_new_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_new_value), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 23, 14), + + /* buf[0:8] == "3000000 " && */ + BPF_LD_IMM64(BPF_REG_8, 0x2030303030303033ULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 10), + + /* buf[8:16] == "4000000 " && */ + BPF_LD_IMM64(BPF_REG_8, 0x2030303030303034ULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 8), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 6), + + /* buf[16:24] == "6000000\0") */ + BPF_LD_IMM64(BPF_REG_8, 0x0030303030303036ULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 16), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/tcp_mem", + .open_flags = O_WRONLY, + .newval = "3000000 4000000 6000000", + .result = OP_EPERM, + }, + { + .descr = "sysctl_get_new_value sysctl:write E2BIG", + .insns = { + /* sysctl_get_new_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_7, BPF_REG_0, 3), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_get_new_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 3), + + /* sysctl_get_new_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_get_new_value), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -E2BIG, 4), + + /* buf[0:3] == "60\0") */ + BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0x003036, 2), + + /* return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_A(1), + + /* else return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_WRONLY, + .newval = "606", + .result = OP_EPERM, + }, + { + .descr = "sysctl_set_new_value sysctl:read EINVAL", + .insns = { + /* sysctl_set_new_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_set_new_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 3), + + /* sysctl_set_new_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_set_new_value), + + /* if (ret == expected) */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + .descr = "sysctl_set_new_value sysctl:write ok", + .fixup_value_insn = 2, + .insns = { + /* sysctl_set_new_value arg2 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, FIXUP_SYSCTL_VALUE), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + + /* sysctl_set_new_value arg3 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_3, 3), + + /* sysctl_set_new_value(ctx, buf, buf_len) */ + BPF_EMIT_CALL(BPF_FUNC_sysctl_set_new_value), + + /* if (ret == expected) */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_WRONLY, + .newval = "606", + .result = SUCCESS, + }, + { + "bpf_strtoul one number string", + .insns = { + /* arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 3, 4), + /* res == expected) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 600, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + "bpf_strtoul multi number string", + .insns = { + /* arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + /* "600 602\0" */ + BPF_LD_IMM64(BPF_REG_0, 0x0032303620303036ULL), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 8), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 3, 18), + /* res == expected) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 600, 16), + + /* arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_0), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* arg4 (res) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -16), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 4, 4), + /* res == expected) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 602, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/tcp_mem", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + "bpf_strtoul buf_len = 0, reject", + .insns = { + /* arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 0), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = LOAD_REJECT, + }, + { + "bpf_strtoul supported base, ok", + .insns = { + /* arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00373730), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 8), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 3, 4), + /* res == expected) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 63, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + "bpf_strtoul unsupported base, EINVAL", + .insns = { + /* arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 3), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + /* if (ret == expected) */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + "bpf_strtoul buf with spaces only, EINVAL", + .insns = { + /* arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x090a0c0d), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + /* if (ret == expected) */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + "bpf_strtoul negative number, EINVAL", + .insns = { + /* arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00362d0a), /* " -6\0" */ + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + /* if (ret == expected) */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -EINVAL, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + "bpf_strtol negative number, ok", + .insns = { + /* arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00362d0a), /* " -6\0" */ + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 10), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtol), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 3, 4), + /* res == expected) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, -6, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + "bpf_strtol hex number, ok", + .insns = { + /* arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x65667830), /* "0xfe" */ + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtol), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 4, 4), + /* res == expected) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 254, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + "bpf_strtol max long", + .insns = { + /* arg1 (buf) 9223372036854775807 */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24), + BPF_LD_IMM64(BPF_REG_0, 0x3032373333323239ULL), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_LD_IMM64(BPF_REG_0, 0x3537373435383633ULL), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8), + BPF_LD_IMM64(BPF_REG_0, 0x0000000000373038ULL), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 16), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 19), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtol), + + /* if (ret == expected && */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 19, 6), + /* res == expected) */ + BPF_LD_IMM64(BPF_REG_8, 0x7fffffffffffffffULL), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0), + BPF_JMP_REG(BPF_JNE, BPF_REG_8, BPF_REG_9, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + "bpf_strtol overflow, ERANGE", + .insns = { + /* arg1 (buf) 9223372036854775808 */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -24), + BPF_LD_IMM64(BPF_REG_0, 0x3032373333323239ULL), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_LD_IMM64(BPF_REG_0, 0x3537373435383633ULL), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 8), + BPF_LD_IMM64(BPF_REG_0, 0x0000000000383038ULL), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 16), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 19), + + /* arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + BPF_EMIT_CALL(BPF_FUNC_strtol), + + /* if (ret == expected) */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, -ERANGE, 2), + + /* return ALLOW; */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + + /* else return DENY; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, + { + "C prog: deny all writes", + .prog_file = "./test_sysctl_prog.o", + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/tcp_mem", + .open_flags = O_WRONLY, + .newval = "123 456 789", + .result = OP_EPERM, + }, + { + "C prog: deny access by name", + .prog_file = "./test_sysctl_prog.o", + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/route/mtu_expires", + .open_flags = O_RDONLY, + .result = OP_EPERM, + }, + { + "C prog: read tcp_mem", + .prog_file = "./test_sysctl_prog.o", + .attach_type = BPF_CGROUP_SYSCTL, + .sysctl = "net/ipv4/tcp_mem", + .open_flags = O_RDONLY, + .result = SUCCESS, + }, +}; + +static size_t probe_prog_length(const struct bpf_insn *fp) +{ + size_t len; + + for (len = MAX_INSNS - 1; len > 0; --len) + if (fp[len].code != 0 || fp[len].imm != 0) + break; + return len + 1; +} + +static int fixup_sysctl_value(const char *buf, size_t buf_len, + struct bpf_insn *prog, size_t insn_num) +{ + uint32_t value_num = 0; + uint8_t c, i; + + if (buf_len > sizeof(value_num)) { + log_err("Value is too big (%zd) to use in fixup", buf_len); + return -1; + } + + for (i = 0; i < buf_len; ++i) { + c = buf[i]; + value_num |= (c << i * 8); + } + + prog[insn_num].imm = value_num; + + return 0; +} + +static int load_sysctl_prog_insns(struct sysctl_test *test, + const char *sysctl_path) +{ + struct bpf_insn *prog = test->insns; + struct bpf_load_program_attr attr; + int ret; + + memset(&attr, 0, sizeof(struct bpf_load_program_attr)); + attr.prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL; + attr.insns = prog; + attr.insns_cnt = probe_prog_length(attr.insns); + attr.license = "GPL"; + + if (test->fixup_value_insn) { + char buf[128]; + ssize_t len; + int fd; + + fd = open(sysctl_path, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + log_err("open(%s) failed", sysctl_path); + return -1; + } + len = read(fd, buf, sizeof(buf)); + if (len == -1) { + log_err("read(%s) failed", sysctl_path); + close(fd); + return -1; + } + close(fd); + if (fixup_sysctl_value(buf, len, prog, test->fixup_value_insn)) + return -1; + } + + ret = bpf_load_program_xattr(&attr, bpf_log_buf, BPF_LOG_BUF_SIZE); + if (ret < 0 && test->result != LOAD_REJECT) { + log_err(">>> Loading program error.\n" + ">>> Verifier output:\n%s\n-------\n", bpf_log_buf); + } + + return ret; +} + +static int load_sysctl_prog_file(struct sysctl_test *test) +{ + struct bpf_prog_load_attr attr; + struct bpf_object *obj; + int prog_fd; + + memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); + attr.file = test->prog_file; + attr.prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL; + + if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) { + if (test->result != LOAD_REJECT) + log_err(">>> Loading program (%s) error.\n", + test->prog_file); + return -1; + } + + return prog_fd; +} + +static int load_sysctl_prog(struct sysctl_test *test, const char *sysctl_path) +{ + return test->prog_file + ? load_sysctl_prog_file(test) + : load_sysctl_prog_insns(test, sysctl_path); +} + +static int access_sysctl(const char *sysctl_path, + const struct sysctl_test *test) +{ + int err = 0; + int fd; + + fd = open(sysctl_path, test->open_flags | O_CLOEXEC); + if (fd < 0) + return fd; + + if (test->open_flags == O_RDONLY) { + char buf[128]; + + if (read(fd, buf, sizeof(buf)) == -1) + goto err; + if (test->oldval && + strncmp(buf, test->oldval, strlen(test->oldval))) { + log_err("Read value %s != %s", buf, test->oldval); + goto err; + } + } else if (test->open_flags == O_WRONLY) { + if (!test->newval) { + log_err("New value for sysctl is not set"); + goto err; + } + if (write(fd, test->newval, strlen(test->newval)) == -1) + goto err; + } else { + log_err("Unexpected sysctl access: neither read nor write"); + goto err; + } + + goto out; +err: + err = -1; +out: + close(fd); + return err; +} + +static int run_test_case(int cgfd, struct sysctl_test *test) +{ + enum bpf_attach_type atype = test->attach_type; + char sysctl_path[128]; + int progfd = -1; + int err = 0; + + printf("Test case: %s .. ", test->descr); + + snprintf(sysctl_path, sizeof(sysctl_path), "/proc/sys/%s", + test->sysctl); + + progfd = load_sysctl_prog(test, sysctl_path); + if (progfd < 0) { + if (test->result == LOAD_REJECT) + goto out; + else + goto err; + } + + if (bpf_prog_attach(progfd, cgfd, atype, BPF_F_ALLOW_OVERRIDE) == -1) { + if (test->result == ATTACH_REJECT) + goto out; + else + goto err; + } + + if (access_sysctl(sysctl_path, test) == -1) { + if (test->result == OP_EPERM && errno == EPERM) + goto out; + else + goto err; + } + + if (test->result != SUCCESS) { + log_err("Unexpected failure"); + goto err; + } + + goto out; +err: + err = -1; +out: + /* Detaching w/o checking return code: best effort attempt. */ + if (progfd != -1) + bpf_prog_detach(cgfd, atype); + close(progfd); + printf("[%s]\n", err ? "FAIL" : "PASS"); + return err; +} + +static int run_tests(int cgfd) +{ + int passes = 0; + int fails = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(tests); ++i) { + if (run_test_case(cgfd, &tests[i])) + ++fails; + else + ++passes; + } + printf("Summary: %d PASSED, %d FAILED\n", passes, fails); + return fails ? -1 : 0; +} + +int main(int argc, char **argv) +{ + int cgfd = -1; + int err = 0; + + if (setup_cgroup_environment()) + goto err; + + cgfd = create_and_get_cgroup(CG_PATH); + if (cgfd < 0) + goto err; + + if (join_cgroup(CG_PATH)) + goto err; + + if (run_tests(cgfd)) + goto err; + + goto out; +err: + err = -1; +out: + close(cgfd); + cleanup_cgroup_environment(); + return err; +} diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index e2ebcaddbe78..ed9e894afef3 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -52,7 +52,7 @@ #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 16 +#define MAX_NR_MAPS 17 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -208,6 +208,76 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self) self->retval = (uint32_t)res; } +/* test the sequence of 1k jumps */ +static void bpf_fill_scale1(struct bpf_test *self) +{ + struct bpf_insn *insn = self->fill_insns; + int i = 0, k = 0; + + insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); + /* test to check that the sequence of 1024 jumps is acceptable */ + while (k++ < 1024) { + insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_prandom_u32); + insn[i++] = BPF_JMP_IMM(BPF_JGT, BPF_REG_0, bpf_semi_rand_get(), 2); + insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_10); + insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, + -8 * (k % 64 + 1)); + } + /* every jump adds 1024 steps to insn_processed, so to stay exactly + * within 1m limit add MAX_TEST_INSNS - 1025 MOVs and 1 EXIT + */ + while (i < MAX_TEST_INSNS - 1025) + insn[i++] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 42); + insn[i] = BPF_EXIT_INSN(); + self->prog_len = i + 1; + self->retval = 42; +} + +/* test the sequence of 1k jumps in inner most function (function depth 8)*/ +static void bpf_fill_scale2(struct bpf_test *self) +{ + struct bpf_insn *insn = self->fill_insns; + int i = 0, k = 0; + +#define FUNC_NEST 7 + for (k = 0; k < FUNC_NEST; k++) { + insn[i++] = BPF_CALL_REL(1); + insn[i++] = BPF_EXIT_INSN(); + } + insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); + /* test to check that the sequence of 1024 jumps is acceptable */ + while (k++ < 1024) { + insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_prandom_u32); + insn[i++] = BPF_JMP_IMM(BPF_JGT, BPF_REG_0, bpf_semi_rand_get(), 2); + insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_10); + insn[i++] = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, + -8 * (k % (64 - 4 * FUNC_NEST) + 1)); + } + /* every jump adds 1024 steps to insn_processed, so to stay exactly + * within 1m limit add MAX_TEST_INSNS - 1025 MOVs and 1 EXIT + */ + while (i < MAX_TEST_INSNS - 1025) + insn[i++] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 42); + insn[i] = BPF_EXIT_INSN(); + self->prog_len = i + 1; + self->retval = 42; +} + +static void bpf_fill_scale(struct bpf_test *self) +{ + switch (self->retval) { + case 1: + return bpf_fill_scale1(self); + case 2: + return bpf_fill_scale2(self); + default: + self->prog_len = 0; + break; + } +} + /* BPF_SK_LOOKUP contains 13 instructions, if you need to fix up maps */ #define BPF_SK_LOOKUP(func) \ /* struct bpf_sock_tuple tuple = {} */ \ diff --git a/tools/testing/selftests/bpf/verifier/int_ptr.c b/tools/testing/selftests/bpf/verifier/int_ptr.c new file mode 100644 index 000000000000..ca3b4729df66 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/int_ptr.c @@ -0,0 +1,160 @@ +{ + "ARG_PTR_TO_LONG uninitialized", + .insns = { + /* bpf_strtoul arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* bpf_strtoul arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* bpf_strtoul arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* bpf_strtoul arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + /* bpf_strtoul() */ + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL, + .errstr = "invalid indirect read from stack off -16+0 size 8", +}, +{ + "ARG_PTR_TO_LONG half-uninitialized", + .insns = { + /* bpf_strtoul arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* bpf_strtoul arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* bpf_strtoul arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* bpf_strtoul arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + /* bpf_strtoul() */ + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL, + .errstr = "invalid indirect read from stack off -16+4 size 8", +}, +{ + "ARG_PTR_TO_LONG misaligned", + .insns = { + /* bpf_strtoul arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* bpf_strtoul arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* bpf_strtoul arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* bpf_strtoul arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -12), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + /* bpf_strtoul() */ + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL, + .errstr = "misaligned stack access off (0x0; 0x0)+-20+0 size 8", +}, +{ + "ARG_PTR_TO_LONG size < sizeof(long)", + .insns = { + /* bpf_strtoul arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -16), + BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* bpf_strtoul arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* bpf_strtoul arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* bpf_strtoul arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 12), + BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + /* bpf_strtoul() */ + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL, + .errstr = "invalid stack type R4 off=-4 access_size=8", +}, +{ + "ARG_PTR_TO_LONG initialized", + .insns = { + /* bpf_strtoul arg1 (buf) */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_MOV64_IMM(BPF_REG_0, 0x00303036), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + + /* bpf_strtoul arg2 (buf_len) */ + BPF_MOV64_IMM(BPF_REG_2, 4), + + /* bpf_strtoul arg3 (flags) */ + BPF_MOV64_IMM(BPF_REG_3, 0), + + /* bpf_strtoul arg4 (res) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_7), + + /* bpf_strtoul() */ + BPF_EMIT_CALL(BPF_FUNC_strtoul), + + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL, +}, diff --git a/tools/testing/selftests/bpf/verifier/scale.c b/tools/testing/selftests/bpf/verifier/scale.c new file mode 100644 index 000000000000..7f868d4802e0 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/scale.c @@ -0,0 +1,18 @@ +{ + "scale: scale test 1", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_scale, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 1, +}, +{ + "scale: scale test 2", + .insns = { }, + .data = { }, + .fill_helper = bpf_fill_scale, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 2, +}, |