diff options
Diffstat (limited to 'tools')
112 files changed, 12240 insertions, 2077 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst new file mode 100644 index 000000000000..86a87da97d0b --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -0,0 +1,305 @@ +================ +bpftool-gen +================ +------------------------------------------------------------------------------- +tool for BPF code-generation +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **gen** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + + *COMMAND* := { **skeleton | **help** } + +GEN COMMANDS +============= + +| **bpftool** **gen skeleton** *FILE* +| **bpftool** **gen help** + +DESCRIPTION +=========== + **bpftool gen skeleton** *FILE* + Generate BPF skeleton C header file for a given *FILE*. + + BPF skeleton is an alternative interface to existing libbpf + APIs for working with BPF objects. Skeleton code is intended + to significantly shorten and simplify code to load and work + with BPF programs from userspace side. Generated code is + tailored to specific input BPF object *FILE*, reflecting its + structure by listing out available maps, program, variables, + etc. Skeleton eliminates the need to lookup mentioned + components by name. Instead, if skeleton instantiation + succeeds, they are populated in skeleton structure as valid + libbpf types (e.g., struct bpf_map pointer) and can be + passed to existing generic libbpf APIs. + + In addition to simple and reliable access to maps and + programs, skeleton provides a storage for BPF links (struct + bpf_link) for each BPF program within BPF object. When + requested, supported BPF programs will be automatically + attached and resulting BPF links stored for further use by + user in pre-allocated fields in skeleton struct. For BPF + programs that can't be automatically attached by libbpf, + user can attach them manually, but store resulting BPF link + in per-program link field. All such set up links will be + automatically destroyed on BPF skeleton destruction. This + eliminates the need for users to manage links manually and + rely on libbpf support to detach programs and free up + resources. + + Another facility provided by BPF skeleton is an interface to + global variables of all supported kinds: mutable, read-only, + as well as extern ones. This interface allows to pre-setup + initial values of variables before BPF object is loaded and + verified by kernel. For non-read-only variables, the same + interface can be used to fetch values of global variables on + userspace side, even if they are modified by BPF code. + + During skeleton generation, contents of source BPF object + *FILE* is embedded within generated code and is thus not + necessary to keep around. This ensures skeleton and BPF + object file are matching 1-to-1 and always stay in sync. + Generated code is dual-licensed under LGPL-2.1 and + BSD-2-Clause licenses. + + It is a design goal and guarantee that skeleton interfaces + are interoperable with generic libbpf APIs. User should + always be able to use skeleton API to create and load BPF + object, and later use libbpf APIs to keep working with + specific maps, programs, etc. + + As part of skeleton, few custom functions are generated. + Each of them is prefixed with object name, derived from + object file name. I.e., if BPF object file name is + **example.o**, BPF object name will be **example**. The + following custom functions are provided in such case: + + - **example__open** and **example__open_opts**. + These functions are used to instantiate skeleton. It + corresponds to libbpf's **bpf_object__open()** API. + **_opts** variants accepts extra **bpf_object_open_opts** + options. + + - **example__load**. + This function creates maps, loads and verifies BPF + programs, initializes global data maps. It corresponds to + libppf's **bpf_object__load** API. + + - **example__open_and_load** combines **example__open** and + **example__load** invocations in one commonly used + operation. + + - **example__attach** and **example__detach** + This pair of functions allow to attach and detach, + correspondingly, already loaded BPF object. Only BPF + programs of types supported by libbpf for auto-attachment + will be auto-attached and their corresponding BPF links + instantiated. For other BPF programs, user can manually + create a BPF link and assign it to corresponding fields in + skeleton struct. **example__detach** will detach both + links created automatically, as well as those populated by + user manually. + + - **example__destroy** + Detach and unload BPF programs, free up all the resources + used by skeleton and BPF object. + + If BPF object has global variables, corresponding structs + with memory layout corresponding to global data data section + layout will be created. Currently supported ones are: *.data*, + *.bss*, *.rodata*, and *.kconfig* structs/data sections. + These data sections/structs can be used to set up initial + values of variables, if set before **example__load**. + Afterwards, if target kernel supports memory-mapped BPF + arrays, same structs can be used to fetch and update + (non-read-only) data from userspace, with same simplicity + as for BPF side. + + **bpftool gen help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -V, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, + this option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + + -d, --debug + Print all logs available from libbpf, including debug-level + information. + +EXAMPLES +======== +**$ cat example.c** +:: + + #include <stdbool.h> + #include <linux/ptrace.h> + #include <linux/bpf.h> + #include "bpf_helpers.h" + + const volatile int param1 = 42; + bool global_flag = true; + struct { int x; } data = {}; + + struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 128); + __type(key, int); + __type(value, long); + } my_map SEC(".maps"); + + SEC("raw_tp/sys_enter") + int handle_sys_enter(struct pt_regs *ctx) + { + static long my_static_var; + if (global_flag) + my_static_var++; + else + data.x += param1; + return 0; + } + + SEC("raw_tp/sys_exit") + int handle_sys_exit(struct pt_regs *ctx) + { + int zero = 0; + bpf_map_lookup_elem(&my_map, &zero); + return 0; + } + +This is example BPF application with two BPF programs and a mix of BPF maps +and global variables. + +**$ bpftool gen skeleton example.o** +:: + + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + + /* THIS FILE IS AUTOGENERATED! */ + #ifndef __EXAMPLE_SKEL_H__ + #define __EXAMPLE_SKEL_H__ + + #include <stdlib.h> + #include <libbpf.h> + + struct example { + struct bpf_object_skeleton *skeleton; + struct bpf_object *obj; + struct { + struct bpf_map *rodata; + struct bpf_map *data; + struct bpf_map *bss; + struct bpf_map *my_map; + } maps; + struct { + struct bpf_program *handle_sys_enter; + struct bpf_program *handle_sys_exit; + } progs; + struct { + struct bpf_link *handle_sys_enter; + struct bpf_link *handle_sys_exit; + } links; + struct example__bss { + struct { + int x; + } data; + } *bss; + struct example__data { + _Bool global_flag; + long int handle_sys_enter_my_static_var; + } *data; + struct example__rodata { + int param1; + } *rodata; + }; + + static void example__destroy(struct example *obj); + static inline struct example *example__open_opts( + const struct bpf_object_open_opts *opts); + static inline struct example *example__open(); + static inline int example__load(struct example *obj); + static inline struct example *example__open_and_load(); + static inline int example__attach(struct example *obj); + static inline void example__detach(struct example *obj); + + #endif /* __EXAMPLE_SKEL_H__ */ + +**$ cat example_user.c** +:: + + #include "example.skel.h" + + int main() + { + struct example *skel; + int err = 0; + + skel = example__open(); + if (!skel) + goto cleanup; + + skel->rodata->param1 = 128; + + err = example__load(skel); + if (err) + goto cleanup; + + err = example__attach(skel); + if (err) + goto cleanup; + + /* all libbpf APIs are usable */ + printf("my_map name: %s\n", bpf_map__name(skel->maps.my_map)); + printf("sys_enter prog FD: %d\n", + bpf_program__fd(skel->progs.handle_sys_enter)); + + /* detach and re-attach sys_exit program */ + bpf_link__destroy(skel->links.handle_sys_exit); + skel->links.handle_sys_exit = + bpf_program__attach(skel->progs.handle_sys_exit); + + printf("my_static_var: %ld\n", + skel->bss->handle_sys_enter_my_static_var); + + cleanup: + example__destroy(skel); + return err; + } + +**# ./example_user** +:: + + my_map name: my_map + sys_enter prog FD: 8 + my_static_var: 7 + +This is a stripped-out version of skeleton generated for above example code. + +SEE ALSO +======== + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-map**\ (8), + **bpftool-prog**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-feature**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 1c0f7146aab0..cdeae8ae90ba 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -39,9 +39,9 @@ MAP COMMANDS | **bpftool** **map freeze** *MAP* | **bpftool** **map help** | -| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* | **name** *MAP_NAME* } | *DATA* := { [**hex**] *BYTES* } -| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } | *VALUE* := { *DATA* | *MAP* | *PROG* } | *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } | *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash** @@ -55,8 +55,9 @@ DESCRIPTION =========== **bpftool map { show | list }** [*MAP*] Show information about loaded maps. If *MAP* is specified - show information only about given map, otherwise list all - maps currently loaded on the system. + show information only about given maps, otherwise list all + maps currently loaded on the system. In case of **name**, + *MAP* may match several maps which will all be shown. Output will start with map ID followed by map type and zero or more named attributes (depending on kernel version). @@ -66,7 +67,8 @@ DESCRIPTION as *FILE*. **bpftool map dump** *MAP* - Dump all entries in a given *MAP*. + Dump all entries in a given *MAP*. In case of **name**, + *MAP* may match several maps which will all be dumped. **bpftool map update** *MAP* [**key** *DATA*] [**value** *VALUE*] [*UPDATE_FLAGS*] Update map entry for a given *KEY*. diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 7a374b3c851d..64ddf8a4c518 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -33,7 +33,7 @@ PROG COMMANDS | **bpftool** **prog help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } -| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* | **name** *PROG_NAME* } | *TYPE* := { | **socket** | **kprobe** | **kretprobe** | **classifier** | **action** | | **tracepoint** | **raw_tracepoint** | **xdp** | **perf_event** | **cgroup/skb** | @@ -53,8 +53,10 @@ DESCRIPTION =========== **bpftool prog { show | list }** [*PROG*] Show information about loaded programs. If *PROG* is - specified show information only about given program, otherwise - list all programs currently loaded on the system. + specified show information only about given programs, + otherwise list all programs currently loaded on the system. + In case of **tag** or **name**, *PROG* may match several + programs which will all be shown. Output will start with program ID followed by program type and zero or more named attributes (depending on kernel version). @@ -68,11 +70,15 @@ DESCRIPTION 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 + Dump eBPF instructions of the programs from the kernel. By default, eBPF will be disassembled and printed to standard output in human-readable format. In this case, **opcodes** controls if raw opcodes should be printed as well. + In case of **tag** or **name**, *PROG* may match several + programs which will all be dumped. However, if **file** or + **visual** is specified, *PROG* must match a single program. + If **file** is specified, the binary image will instead be written to *FILE*. @@ -80,15 +86,17 @@ DESCRIPTION built instead, and eBPF instructions will be presented with CFG in DOT format, on standard output. - If the prog has line_info available, the source line will + If the programs have line_info available, the source line will be displayed by default. If **linum** is specified, the filename, line number and line column will also be displayed on top of the source line. **bpftool prog dump jited** *PROG* [{ **file** *FILE* | **opcodes** | **linum** }] Dump jited image (host machine code) of the program. + If *FILE* is specified image will be written to a file, otherwise it will be disassembled and printed to stdout. + *PROG* must match a single program when **file** is specified. **opcodes** controls if raw opcodes will be printed. diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 6a9c52ef84a9..34239fda69ed 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -81,4 +81,5 @@ SEE ALSO **bpftool-feature**\ (8), **bpftool-net**\ (8), **bpftool-perf**\ (8), - **bpftool-btf**\ (8) + **bpftool-btf**\ (8), + **bpftool-gen**\ (8), diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 70493a6da206..754d8395e451 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -59,6 +59,21 @@ _bpftool_get_map_ids_for_type() command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_map_names() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + +# Takes map type and adds matching map names to the list of suggestions. +_bpftool_get_map_names_for_type() +{ + local type="$1" + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 "$type" | \ + command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + _bpftool_get_prog_ids() { COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ @@ -71,6 +86,12 @@ _bpftool_get_prog_tags() command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_prog_names() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ + command sed -n 's/.*"name": "\(.*\)",$/\1/p' )" -- "$cur" ) ) +} + _bpftool_get_btf_ids() { COMPREPLY+=( $( compgen -W "$( bpftool -jp btf 2>&1 | \ @@ -180,6 +201,52 @@ _bpftool_map_update_get_id() esac } +_bpftool_map_update_get_name() +{ + local command="$1" + + # Is it the map to update, or a map to insert into the map to update? + # Search for "value" keyword. + local idx value + for (( idx=7; idx < ${#words[@]}-1; idx++ )); do + if [[ ${words[idx]} == "value" ]]; then + value=1 + break + fi + done + if [[ $value -eq 0 ]]; then + case "$command" in + push) + _bpftool_get_map_names_for_type stack + ;; + enqueue) + _bpftool_get_map_names_for_type queue + ;; + *) + _bpftool_get_map_names + ;; + esac + return 0 + fi + + # Name to complete is for a value. It can be either prog name or map name. This + # depends on the type of the map to update. + local type=$(_bpftool_map_guess_map_type) + case $type in + array_of_maps|hash_of_maps) + _bpftool_get_map_names + return 0 + ;; + prog_array) + _bpftool_get_prog_names + return 0 + ;; + *) + return 0 + ;; + esac +} + _bpftool() { local cur prev words objword @@ -251,7 +318,8 @@ _bpftool() # Completion depends on object and command in use case $object in prog) - # Complete id, only for subcommands that use prog (but no map) ids + # Complete id and name, only for subcommands that use prog (but no + # map) ids/names. case $command in show|list|dump|pin) case $prev in @@ -259,12 +327,16 @@ _bpftool() _bpftool_get_prog_ids return 0 ;; + name) + _bpftool_get_prog_names + return 0 + ;; esac ;; esac - local PROG_TYPE='id pinned tag' - local MAP_TYPE='id pinned' + local PROG_TYPE='id pinned tag name' + local MAP_TYPE='id pinned name' case $command in show|list) [[ $prev != "$command" ]] && return 0 @@ -315,6 +387,9 @@ _bpftool() id) _bpftool_get_prog_ids ;; + name) + _bpftool_get_map_names + ;; pinned) _filedir ;; @@ -335,6 +410,9 @@ _bpftool() id) _bpftool_get_map_ids ;; + name) + _bpftool_get_map_names + ;; pinned) _filedir ;; @@ -399,6 +477,10 @@ _bpftool() _bpftool_get_map_ids return 0 ;; + name) + _bpftool_get_map_names + return 0 + ;; pinned|pinmaps) _filedir return 0 @@ -447,7 +529,7 @@ _bpftool() esac ;; map) - local MAP_TYPE='id pinned' + local MAP_TYPE='id pinned name' case $command in show|list|dump|peek|pop|dequeue|freeze) case $prev in @@ -473,6 +555,24 @@ _bpftool() esac return 0 ;; + name) + case "$command" in + peek) + _bpftool_get_map_names_for_type stack + _bpftool_get_map_names_for_type queue + ;; + pop) + _bpftool_get_map_names_for_type stack + ;; + dequeue) + _bpftool_get_map_names_for_type queue + ;; + *) + _bpftool_get_map_names + ;; + esac + return 0 + ;; *) return 0 ;; @@ -520,6 +620,10 @@ _bpftool() _bpftool_get_map_ids return 0 ;; + name) + _bpftool_get_map_names + return 0 + ;; key) COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; @@ -545,6 +649,10 @@ _bpftool() _bpftool_map_update_get_id $command return 0 ;; + name) + _bpftool_map_update_get_name $command + return 0 + ;; key) COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; @@ -553,13 +661,13 @@ _bpftool() # map, depending on the type of the map to update. case "$(_bpftool_map_guess_map_type)" in array_of_maps|hash_of_maps) - local MAP_TYPE='id pinned' + local MAP_TYPE='id pinned name' COMPREPLY+=( $( compgen -W "$MAP_TYPE" \ -- "$cur" ) ) return 0 ;; prog_array) - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' COMPREPLY+=( $( compgen -W "$PROG_TYPE" \ -- "$cur" ) ) return 0 @@ -621,6 +729,10 @@ _bpftool() _bpftool_get_map_ids_for_type perf_event_array return 0 ;; + name) + _bpftool_get_map_names_for_type perf_event_array + return 0 + ;; cpu) return 0 ;; @@ -644,8 +756,8 @@ _bpftool() esac ;; btf) - local PROG_TYPE='id pinned tag' - local MAP_TYPE='id pinned' + local PROG_TYPE='id pinned tag name' + local MAP_TYPE='id pinned name' case $command in dump) case $prev in @@ -676,6 +788,17 @@ _bpftool() esac return 0 ;; + name) + case $pprev in + prog) + _bpftool_get_prog_names + ;; + map) + _bpftool_get_map_names + ;; + esac + return 0 + ;; format) COMPREPLY=( $( compgen -W "c raw" -- "$cur" ) ) ;; @@ -716,6 +839,17 @@ _bpftool() ;; esac ;; + gen) + case $command in + skeleton) + _filedir + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'skeleton help' -- "$cur" ) ) + ;; + esac + ;; cgroup) case $command in show|list|tree) @@ -735,7 +869,7 @@ _bpftool() connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl \ getsockopt setsockopt' local ATTACH_FLAGS='multi override' - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' case $prev in $command) _filedir @@ -760,7 +894,7 @@ _bpftool() elif [[ "$command" == "attach" ]]; then # We have an attach type on the command line, # but it is not the previous word, or - # "id|pinned|tag" (we already checked for + # "id|pinned|tag|name" (we already checked for # that). This should only leave the case when # we need attach flags for "attach" commamnd. _bpftool_one_of_list "$ATTACH_FLAGS" @@ -786,7 +920,7 @@ _bpftool() esac ;; net) - local PROG_TYPE='id pinned tag' + local PROG_TYPE='id pinned tag name' local ATTACH_TYPES='xdp xdpgeneric xdpdrv xdpoffload' case $command in show|list) diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 1ef45e55039e..2f017caa678d 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -117,6 +117,25 @@ static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type) return prog_cnt; } +static int cgroup_has_attached_progs(int cgroup_fd) +{ + enum bpf_attach_type type; + bool no_prog = true; + + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + int count = count_attached_bpf_progs(cgroup_fd, type); + + if (count < 0 && errno != EINVAL) + return -1; + + if (count > 0) { + no_prog = false; + break; + } + } + + return no_prog ? 0 : 1; +} static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, int level) { @@ -161,6 +180,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type, static int do_show(int argc, char **argv) { enum bpf_attach_type type; + int has_attached_progs; const char *path; int cgroup_fd; int ret = -1; @@ -192,6 +212,16 @@ static int do_show(int argc, char **argv) goto exit; } + has_attached_progs = cgroup_has_attached_progs(cgroup_fd); + if (has_attached_progs < 0) { + p_err("can't query bpf programs attached to %s: %s", + path, strerror(errno)); + goto exit_cgroup; + } else if (!has_attached_progs) { + ret = 0; + goto exit_cgroup; + } + if (json_output) jsonw_start_array(json_wtr); else @@ -212,6 +242,7 @@ static int do_show(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); +exit_cgroup: close(cgroup_fd); exit: return ret; @@ -228,7 +259,7 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, int typeflag, struct FTW *ftw) { enum bpf_attach_type type; - bool skip = true; + int has_attached_progs; int cgroup_fd; if (typeflag != FTW_D) @@ -240,22 +271,13 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb, return SHOW_TREE_FN_ERR; } - for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { - int count = count_attached_bpf_progs(cgroup_fd, type); - - if (count < 0 && errno != EINVAL) { - p_err("can't query bpf programs attached to %s: %s", - fpath, strerror(errno)); - close(cgroup_fd); - return SHOW_TREE_FN_ERR; - } - if (count > 0) { - skip = false; - break; - } - } - - if (skip) { + has_attached_progs = cgroup_has_attached_progs(cgroup_fd); + if (has_attached_progs < 0) { + p_err("can't query bpf programs attached to %s: %s", + fpath, strerror(errno)); + close(cgroup_fd); + return SHOW_TREE_FN_ERR; + } else if (!has_attached_progs) { close(cgroup_fd); return 0; } diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c new file mode 100644 index 000000000000..7ce09a9a6999 --- /dev/null +++ b/tools/bpf/bpftool/gen.c @@ -0,0 +1,609 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Facebook */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <bpf.h> +#include <libbpf.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <unistd.h> + +#include "btf.h" +#include "libbpf_internal.h" +#include "json_writer.h" +#include "main.h" + + +#define MAX_OBJ_NAME_LEN 64 + +static void sanitize_identifier(char *name) +{ + int i; + + for (i = 0; name[i]; i++) + if (!isalnum(name[i]) && name[i] != '_') + name[i] = '_'; +} + +static bool str_has_suffix(const char *str, const char *suffix) +{ + size_t i, n1 = strlen(str), n2 = strlen(suffix); + + if (n1 < n2) + return false; + + for (i = 0; i < n2; i++) { + if (str[n1 - i - 1] != suffix[n2 - i - 1]) + return false; + } + + return true; +} + +static void get_obj_name(char *name, const char *file) +{ + /* Using basename() GNU version which doesn't modify arg. */ + strncpy(name, basename(file), MAX_OBJ_NAME_LEN - 1); + name[MAX_OBJ_NAME_LEN - 1] = '\0'; + if (str_has_suffix(name, ".o")) + name[strlen(name) - 2] = '\0'; + sanitize_identifier(name); +} + +static void get_header_guard(char *guard, const char *obj_name) +{ + int i; + + sprintf(guard, "__%s_SKEL_H__", obj_name); + for (i = 0; guard[i]; i++) + guard[i] = toupper(guard[i]); +} + +static const char *get_map_ident(const struct bpf_map *map) +{ + const char *name = bpf_map__name(map); + + if (!bpf_map__is_internal(map)) + return name; + + if (str_has_suffix(name, ".data")) + return "data"; + else if (str_has_suffix(name, ".rodata")) + return "rodata"; + else if (str_has_suffix(name, ".bss")) + return "bss"; + else if (str_has_suffix(name, ".kconfig")) + return "kconfig"; + else + return NULL; +} + +static void codegen_btf_dump_printf(void *ct, const char *fmt, va_list args) +{ + vprintf(fmt, args); +} + +static int codegen_datasec_def(struct bpf_object *obj, + struct btf *btf, + struct btf_dump *d, + const struct btf_type *sec, + const char *obj_name) +{ + const char *sec_name = btf__name_by_offset(btf, sec->name_off); + const struct btf_var_secinfo *sec_var = btf_var_secinfos(sec); + int i, err, off = 0, pad_cnt = 0, vlen = btf_vlen(sec); + const char *sec_ident; + char var_ident[256]; + + if (strcmp(sec_name, ".data") == 0) + sec_ident = "data"; + else if (strcmp(sec_name, ".bss") == 0) + sec_ident = "bss"; + else if (strcmp(sec_name, ".rodata") == 0) + sec_ident = "rodata"; + else if (strcmp(sec_name, ".kconfig") == 0) + sec_ident = "kconfig"; + else + return 0; + + printf(" struct %s__%s {\n", obj_name, sec_ident); + for (i = 0; i < vlen; i++, sec_var++) { + const struct btf_type *var = btf__type_by_id(btf, sec_var->type); + const char *var_name = btf__name_by_offset(btf, var->name_off); + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .field_name = var_ident, + .indent_level = 2, + ); + int need_off = sec_var->offset, align_off, align; + __u32 var_type_id = var->type; + const struct btf_type *t; + + t = btf__type_by_id(btf, var_type_id); + while (btf_is_mod(t)) { + var_type_id = t->type; + t = btf__type_by_id(btf, var_type_id); + } + + if (off > need_off) { + p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n", + sec_name, i, need_off, off); + return -EINVAL; + } + + align = btf__align_of(btf, var->type); + if (align <= 0) { + p_err("Failed to determine alignment of variable '%s': %d", + var_name, align); + return -EINVAL; + } + + align_off = (off + align - 1) / align * align; + if (align_off != need_off) { + printf("\t\tchar __pad%d[%d];\n", + pad_cnt, need_off - off); + pad_cnt++; + } + + /* sanitize variable name, e.g., for static vars inside + * a function, it's name is '<function name>.<variable name>', + * which we'll turn into a '<function name>_<variable name>' + */ + var_ident[0] = '\0'; + strncat(var_ident, var_name, sizeof(var_ident) - 1); + sanitize_identifier(var_ident); + + printf("\t\t"); + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + return err; + printf(";\n"); + + off = sec_var->offset + sec_var->size; + } + printf(" } *%s;\n", sec_ident); + return 0; +} + +static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + int n = btf__get_nr_types(btf); + struct btf_dump *d; + int i, err = 0; + + d = btf_dump__new(btf, NULL, NULL, codegen_btf_dump_printf); + if (IS_ERR(d)) + return PTR_ERR(d); + + for (i = 1; i <= n; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + + if (!btf_is_datasec(t)) + continue; + + err = codegen_datasec_def(obj, btf, d, t, obj_name); + if (err) + goto out; + } +out: + btf_dump__free(d); + return err; +} + +static int codegen(const char *template, ...) +{ + const char *src, *end; + int skip_tabs = 0, n; + char *s, *dst; + va_list args; + char c; + + n = strlen(template); + s = malloc(n + 1); + if (!s) + return -ENOMEM; + src = template; + dst = s; + + /* find out "baseline" indentation to skip */ + while ((c = *src++)) { + if (c == '\t') { + skip_tabs++; + } else if (c == '\n') { + break; + } else { + p_err("unrecognized character at pos %td in template '%s'", + src - template - 1, template); + return -EINVAL; + } + } + + while (*src) { + /* skip baseline indentation tabs */ + for (n = skip_tabs; n > 0; n--, src++) { + if (*src != '\t') { + p_err("not enough tabs at pos %td in template '%s'", + src - template - 1, template); + return -EINVAL; + } + } + /* trim trailing whitespace */ + end = strchrnul(src, '\n'); + for (n = end - src; n > 0 && isspace(src[n - 1]); n--) + ; + memcpy(dst, src, n); + dst += n; + if (*end) + *dst++ = '\n'; + src = *end ? end + 1 : end; + } + *dst++ = '\0'; + + /* print out using adjusted template */ + va_start(args, template); + n = vprintf(s, args); + va_end(args); + + free(s); + return n; +} + +static int do_skeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; + size_t i, map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN], *obj_data; + struct bpf_object *obj = NULL; + const char *file, *ident; + struct bpf_program *prog; + int fd, len, err = -1; + struct bpf_map *map; + struct btf *btf; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + get_obj_name(obj_name, file); + opts.object_name = obj_name; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + if (IS_ERR(obj)) { + obj = NULL; + p_err("failed to open BPF object file: %ld", PTR_ERR(obj)); + goto out; + } + + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + if (!ident) { + p_err("ignoring unrecognized internal map '%s'...", + bpf_map__name(map)); + continue; + } + map_cnt++; + } + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + get_header_guard(header_guard, obj_name); + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <stdlib.h> \n\ + #include <libbpf.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_object_skeleton *skeleton; \n\ + struct bpf_object *obj; \n\ + ", + obj_name, header_guard + ); + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + if (!ident) + continue; + printf("\t\tstruct bpf_map *%s;\n", ident); + } + printf("\t} maps;\n"); + } + + if (prog_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); + } + printf("\t} progs;\n"); + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_link *%s;\n", + bpf_program__name(prog)); + } + printf("\t} links;\n"); + } + + btf = bpf_object__btf(obj); + if (btf) { + err = codegen_datasecs(obj, obj_name); + if (err) + goto out; + } + + codegen("\ + \n\ + }; \n\ + \n\ + static void \n\ + %1$s__destroy(struct %1$s *obj) \n\ + { \n\ + if (!obj) \n\ + return; \n\ + if (obj->skeleton) \n\ + bpf_object__destroy_skeleton(obj->skeleton);\n\ + free(obj); \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj); \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_opts(const struct bpf_object_open_opts *opts) \n\ + { \n\ + struct %1$s *obj; \n\ + \n\ + obj = (typeof(obj))calloc(1, sizeof(*obj)); \n\ + if (!obj) \n\ + return NULL; \n\ + if (%1$s__create_skeleton(obj)) \n\ + goto err; \n\ + if (bpf_object__open_skeleton(obj->skeleton, opts)) \n\ + goto err; \n\ + \n\ + return obj; \n\ + err: \n\ + %1$s__destroy(obj); \n\ + return NULL; \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(void) \n\ + { \n\ + return %1$s__open_opts(NULL); \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__load(struct %1$s *obj) \n\ + { \n\ + return bpf_object__load_skeleton(obj->skeleton); \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_and_load(void) \n\ + { \n\ + struct %1$s *obj; \n\ + \n\ + obj = %1$s__open(); \n\ + if (!obj) \n\ + return NULL; \n\ + if (%1$s__load(obj)) { \n\ + %1$s__destroy(obj); \n\ + return NULL; \n\ + } \n\ + return obj; \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__attach(struct %1$s *obj) \n\ + { \n\ + return bpf_object__attach_skeleton(obj->skeleton); \n\ + } \n\ + \n\ + static inline void \n\ + %1$s__detach(struct %1$s *obj) \n\ + { \n\ + return bpf_object__detach_skeleton(obj->skeleton); \n\ + } \n\ + ", + obj_name + ); + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__create_skeleton(struct %1$s *obj) \n\ + { \n\ + struct bpf_object_skeleton *s; \n\ + \n\ + s = (typeof(s))calloc(1, sizeof(*s)); \n\ + if (!s) \n\ + return -1; \n\ + obj->skeleton = s; \n\ + \n\ + s->sz = sizeof(*s); \n\ + s->name = \"%1$s\"; \n\ + s->obj = &obj->obj; \n\ + ", + obj_name + ); + if (map_cnt) { + codegen("\ + \n\ + \n\ + /* maps */ \n\ + s->map_cnt = %zu; \n\ + s->map_skel_sz = sizeof(*s->maps); \n\ + s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);\n\ + if (!s->maps) \n\ + goto err; \n\ + ", + map_cnt + ); + i = 0; + bpf_object__for_each_map(map, obj) { + ident = get_map_ident(map); + + if (!ident) + continue; + + codegen("\ + \n\ + \n\ + s->maps[%zu].name = \"%s\"; \n\ + s->maps[%zu].map = &obj->maps.%s; \n\ + ", + i, bpf_map__name(map), i, ident); + /* memory-mapped internal maps */ + if (bpf_map__is_internal(map) && + (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) { + printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", + i, ident); + } + i++; + } + } + if (prog_cnt) { + codegen("\ + \n\ + \n\ + /* programs */ \n\ + s->prog_cnt = %zu; \n\ + s->prog_skel_sz = sizeof(*s->progs); \n\ + s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);\n\ + if (!s->progs) \n\ + goto err; \n\ + ", + prog_cnt + ); + i = 0; + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + \n\ + s->progs[%1$zu].name = \"%2$s\"; \n\ + s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ + s->progs[%1$zu].link = &obj->links.%2$s;\n\ + ", + i, bpf_program__name(prog)); + i++; + } + } + codegen("\ + \n\ + \n\ + s->data_sz = %d; \n\ + s->data = (void *)\"\\ \n\ + ", + file_sz); + + /* embed contents of BPF object file */ + for (i = 0, len = 0; i < file_sz; i++) { + int w = obj_data[i] ? 4 : 2; + + len += w; + if (len > 78) { + printf("\\\n"); + len = w; + } + if (!obj_data[i]) + printf("\\0"); + else + printf("\\x%02x", (unsigned char)obj_data[i]); + } + + codegen("\ + \n\ + \"; \n\ + \n\ + return 0; \n\ + err: \n\ + bpf_object__destroy_skeleton(s); \n\ + return -1; \n\ + } \n\ + \n\ + #endif /* %s */ \n\ + ", + header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %1$s gen skeleton FILE\n" + " %1$s gen help\n" + "\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name); + + return 0; +} + +static const struct cmd cmds[] = { + { "skeleton", do_skeleton }, + { "help", do_help }, + { 0 } +}; + +int do_gen(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 4764581ff9ea..1fe91c558508 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -58,7 +58,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf | net | feature | btf }\n" + " OBJECT := { prog | map | cgroup | perf | net | feature | btf | gen }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -227,6 +227,7 @@ static const struct cmd cmds[] = { { "net", do_net }, { "feature", do_feature }, { "btf", do_btf }, + { "gen", do_gen }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 2899095f8254..4e75b58d3989 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -42,12 +42,12 @@ #define BPF_TAG_FMT "%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx" #define HELP_SPEC_PROGRAM \ - "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }" + "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG | name PROG_NAME }" #define HELP_SPEC_OPTIONS \ "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} |\n" \ "\t {-m|--mapcompat} | {-n|--nomount} }" #define HELP_SPEC_MAP \ - "MAP := { id MAP_ID | pinned FILE }" + "MAP := { id MAP_ID | pinned FILE | name MAP_NAME }" static const char * const prog_type_name[] = { [BPF_PROG_TYPE_UNSPEC] = "unspec", @@ -155,6 +155,7 @@ int do_net(int argc, char **arg); int do_tracelog(int argc, char **arg); int do_feature(int argc, char **argv); int do_btf(int argc, char **argv); +int do_gen(int argc, char **argv); int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index de61d73b9030..c01f76fa6876 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -91,10 +91,66 @@ static void *alloc_value(struct bpf_map_info *info) return malloc(info->value_size); } -int map_parse_fd(int *argc, char ***argv) +static int map_fd_by_name(char *name, int **fds) { - int fd; + unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; + int err; + + while (true) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + err = bpf_map_get_next_id(id, &id); + if (err) { + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; + } + + fd = bpf_map_get_fd_by_id(id); + if (fd < 0) { + p_err("can't get map by id (%u): %s", + id, strerror(errno)); + goto err_close_fds; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get map info (%u): %s", + id, strerror(errno)); + goto err_close_fd; + } + + if (strncmp(name, info.name, BPF_OBJ_NAME_LEN)) { + close(fd); + continue; + } + + if (nb_fds > 0) { + tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); + if (!tmp) { + p_err("failed to realloc"); + goto err_close_fd; + } + *fds = tmp; + } + (*fds)[nb_fds++] = fd; + } + +err_close_fd: + close(fd); +err_close_fds: + while (--nb_fds >= 0) + close((*fds)[nb_fds]); + return -1; +} +static int map_parse_fds(int *argc, char ***argv, int **fds) +{ if (is_prefix(**argv, "id")) { unsigned int id; char *endptr; @@ -108,10 +164,25 @@ int map_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - fd = bpf_map_get_fd_by_id(id); - if (fd < 0) + (*fds)[0] = bpf_map_get_fd_by_id(id); + if ((*fds)[0] < 0) { p_err("get map by id (%u): %s", id, strerror(errno)); - return fd; + return -1; + } + return 1; + } else if (is_prefix(**argv, "name")) { + char *name; + + NEXT_ARGP(); + + name = **argv; + if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { + p_err("can't parse name"); + return -1; + } + NEXT_ARGP(); + + return map_fd_by_name(name, fds); } else if (is_prefix(**argv, "pinned")) { char *path; @@ -120,13 +191,43 @@ int map_parse_fd(int *argc, char ***argv) path = **argv; NEXT_ARGP(); - return open_obj_pinned_any(path, BPF_OBJ_MAP); + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP); + if ((*fds)[0] < 0) + return -1; + return 1; } - p_err("expected 'id' or 'pinned', got: '%s'?", **argv); + p_err("expected 'id', 'name' or 'pinned', got: '%s'?", **argv); return -1; } +int map_parse_fd(int *argc, char ***argv) +{ + int *fds = NULL; + int nb_fds, fd; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(argc, argv, &fds); + if (nb_fds != 1) { + if (nb_fds > 1) { + p_err("several maps match this handle"); + while (nb_fds--) + close(fds[nb_fds]); + } + fd = -1; + goto exit_free; + } + + fd = fds[0]; +exit_free: + free(fds); + return fd; +} + int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) { int err; @@ -479,6 +580,21 @@ static int parse_elem(char **argv, struct bpf_map_info *info, return -1; } +static void show_map_header_json(struct bpf_map_info *info, json_writer_t *wtr) +{ + jsonw_uint_field(wtr, "id", info->id); + if (info->type < ARRAY_SIZE(map_type_name)) + jsonw_string_field(wtr, "type", map_type_name[info->type]); + else + jsonw_uint_field(wtr, "type", info->type); + + if (*info->name) + jsonw_string_field(wtr, "name", info->name); + + jsonw_name(wtr, "flags"); + jsonw_printf(wtr, "%d", info->map_flags); +} + static int show_map_close_json(int fd, struct bpf_map_info *info) { char *memlock, *frozen_str; @@ -489,18 +605,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_start_object(json_wtr); - jsonw_uint_field(json_wtr, "id", info->id); - if (info->type < ARRAY_SIZE(map_type_name)) - jsonw_string_field(json_wtr, "type", - map_type_name[info->type]); - else - jsonw_uint_field(json_wtr, "type", info->type); - - if (*info->name) - jsonw_string_field(json_wtr, "name", info->name); - - jsonw_name(json_wtr, "flags"); - jsonw_printf(json_wtr, "%d", info->map_flags); + show_map_header_json(info, json_wtr); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); @@ -561,14 +666,8 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) return 0; } -static int show_map_close_plain(int fd, struct bpf_map_info *info) +static void show_map_header_plain(struct bpf_map_info *info) { - char *memlock, *frozen_str; - int frozen = 0; - - memlock = get_fdinfo(fd, "memlock"); - frozen_str = get_fdinfo(fd, "frozen"); - printf("%u: ", info->id); if (info->type < ARRAY_SIZE(map_type_name)) printf("%s ", map_type_name[info->type]); @@ -581,6 +680,17 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) printf("flags 0x%x", info->map_flags); print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); printf("\n"); +} + +static int show_map_close_plain(int fd, struct bpf_map_info *info) +{ + char *memlock, *frozen_str; + int frozen = 0; + + memlock = get_fdinfo(fd, "memlock"); + frozen_str = get_fdinfo(fd, "frozen"); + + show_map_header_plain(info); printf("\tkey %uB value %uB max_entries %u", info->key_size, info->value_size, info->max_entries); @@ -642,6 +752,50 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) return 0; } +static int do_show_subset(int argc, char **argv) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int *fds = NULL; + int nb_fds, i; + int err = -1; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + if (err) { + p_err("can't get map info: %s", + strerror(errno)); + for (; i < nb_fds; i++) + close(fds[i]); + break; + } + + if (json_output) + show_map_close_json(fds[i], &info); + else + show_map_close_plain(fds[i], &info); + + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + free(fds); + return err; +} + static int do_show(int argc, char **argv) { struct bpf_map_info info = {}; @@ -653,16 +807,8 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&map_table, BPF_OBJ_MAP); - if (argc == 2) { - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); - if (fd < 0) - return -1; - - if (json_output) - return show_map_close_json(fd, &info); - else - return show_map_close_plain(fd, &info); - } + if (argc == 2) + return do_show_subset(argc, argv); if (argc) return BAD_ARG(); @@ -765,26 +911,49 @@ static int dump_map_elem(int fd, void *key, void *value, return 0; } -static int do_dump(int argc, char **argv) +static int maps_have_btf(int *fds, int nb_fds) { struct bpf_map_info info = {}; - void *key, *value, *prev_key; - unsigned int num_elems = 0; __u32 len = sizeof(info); - json_writer_t *btf_wtr; struct btf *btf = NULL; - int err; - int fd; + int err, i; - if (argc != 2) - usage(); + for (i = 0; i < nb_fds; i++) { + err = bpf_obj_get_info_by_fd(fds[i], &info, &len); + if (err) { + p_err("can't get map info: %s", strerror(errno)); + goto err_close; + } - fd = map_parse_fd_and_info(&argc, &argv, &info, &len); - if (fd < 0) - return -1; + err = btf__get_from_id(info.btf_id, &btf); + if (err) { + p_err("failed to get btf"); + goto err_close; + } - key = malloc(info.key_size); - value = alloc_value(&info); + if (!btf) + return 0; + } + + return 1; + +err_close: + for (; i < nb_fds; i++) + close(fds[i]); + return -1; +} + +static int +map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, + bool enable_btf, bool show_header) +{ + void *key, *value, *prev_key; + unsigned int num_elems = 0; + struct btf *btf = NULL; + int err; + + key = malloc(info->key_size); + value = alloc_value(info); if (!key || !value) { p_err("mem alloc failed"); err = -1; @@ -793,30 +962,32 @@ static int do_dump(int argc, char **argv) prev_key = NULL; - err = btf__get_from_id(info.btf_id, &btf); - if (err) { - p_err("failed to get btf"); - goto exit_free; + if (enable_btf) { + err = btf__get_from_id(info->btf_id, &btf); + if (err || !btf) { + /* enable_btf is true only if we've already checked + * that all maps have BTF information. + */ + p_err("failed to get btf"); + goto exit_free; + } } - if (json_output) - jsonw_start_array(json_wtr); - else - if (btf) { - btf_wtr = get_btf_writer(); - if (!btf_wtr) { - p_info("failed to create json writer for btf. falling back to plain output"); - btf__free(btf); - btf = NULL; - } else { - jsonw_start_array(btf_wtr); - } + if (wtr) { + if (show_header) { + jsonw_start_object(wtr); /* map object */ + show_map_header_json(info, wtr); + jsonw_name(wtr, "elements"); } + jsonw_start_array(wtr); /* elements */ + } else if (show_header) { + show_map_header_plain(info); + } - if (info.type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && - info.value_size != 8) + 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]); + map_type_name[info->type]); while (true) { err = bpf_map_get_next_key(fd, prev_key, key); if (err) { @@ -824,15 +995,14 @@ static int do_dump(int argc, char **argv) err = 0; break; } - num_elems += dump_map_elem(fd, key, value, &info, btf, btf_wtr); + num_elems += dump_map_elem(fd, key, value, info, btf, wtr); prev_key = key; } - if (json_output) - jsonw_end_array(json_wtr); - else if (btf) { - jsonw_end_array(btf_wtr); - jsonw_destroy(&btf_wtr); + if (wtr) { + jsonw_end_array(wtr); /* elements */ + if (show_header) + jsonw_end_object(wtr); /* map object */ } else { printf("Found %u element%s\n", num_elems, num_elems != 1 ? "s" : ""); @@ -847,6 +1017,72 @@ exit_free: return err; } +static int do_dump(int argc, char **argv) +{ + json_writer_t *wtr = NULL, *btf_wtr = NULL; + struct bpf_map_info info = {}; + int nb_fds, i = 0, btf = 0; + __u32 len = sizeof(info); + int *fds = NULL; + int err = -1; + + if (argc != 2) + usage(); + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = map_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (json_output) { + wtr = json_wtr; + } else { + btf = maps_have_btf(fds, nb_fds); + if (btf < 0) + goto exit_close; + if (btf) { + btf_wtr = get_btf_writer(); + if (btf_wtr) { + wtr = btf_wtr; + } else { + p_info("failed to create json writer for btf. falling back to plain output"); + btf = 0; + } + } + } + + if (wtr && nb_fds > 1) + jsonw_start_array(wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + if (bpf_obj_get_info_by_fd(fds[i], &info, &len)) { + p_err("can't get map info: %s", strerror(errno)); + break; + } + err = map_dump(fds[i], &info, wtr, btf, nb_fds > 1); + if (!wtr && i != nb_fds - 1) + printf("\n"); + + if (err) + break; + close(fds[i]); + } + if (wtr && nb_fds > 1) + jsonw_end_array(wtr); /* root array */ + + if (btf) + jsonw_destroy(&btf_wtr); +exit_close: + for (; i < nb_fds; i++) + close(fds[i]); +exit_free: + free(fds); + return err; +} + static int alloc_key_value(struct bpf_map_info *info, void **key, void **value) { *key = NULL; diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 4f52d3151616..d93bee298e54 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -18,6 +18,7 @@ #include <bpf.h> #include <nlattr.h> +#include "libbpf_internal.h" #include "main.h" #include "netlink_dumper.h" diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 2ce9c5ba1934..47a61ac42dc0 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -25,6 +25,11 @@ #include "main.h" #include "xlated_dumper.h" +enum dump_mode { + DUMP_JITED, + DUMP_XLATED, +}; + static const char * const attach_type_strings[] = { [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", @@ -77,11 +82,12 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) strftime(buf, size, "%FT%T%z", &load_tm); } -static int prog_fd_by_tag(unsigned char *tag) +static int prog_fd_by_nametag(void *nametag, int **fds, bool tag) { unsigned int id = 0; + int fd, nb_fds = 0; + void *tmp; int err; - int fd; while (true) { struct bpf_prog_info info = {}; @@ -89,36 +95,54 @@ static int prog_fd_by_tag(unsigned char *tag) err = bpf_prog_get_next_id(id, &id); if (err) { - p_err("%s", strerror(errno)); - return -1; + if (errno != ENOENT) { + p_err("%s", strerror(errno)); + goto err_close_fds; + } + return nb_fds; } fd = bpf_prog_get_fd_by_id(id); if (fd < 0) { p_err("can't get prog by id (%u): %s", id, strerror(errno)); - return -1; + goto err_close_fds; } err = bpf_obj_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get prog info (%u): %s", id, strerror(errno)); - close(fd); - return -1; + goto err_close_fd; } - if (!memcmp(tag, info.tag, BPF_TAG_SIZE)) - return fd; + if ((tag && memcmp(nametag, info.tag, BPF_TAG_SIZE)) || + (!tag && strncmp(nametag, info.name, BPF_OBJ_NAME_LEN))) { + close(fd); + continue; + } - close(fd); + if (nb_fds > 0) { + tmp = realloc(*fds, (nb_fds + 1) * sizeof(int)); + if (!tmp) { + p_err("failed to realloc"); + goto err_close_fd; + } + *fds = tmp; + } + (*fds)[nb_fds++] = fd; } + +err_close_fd: + close(fd); +err_close_fds: + while (--nb_fds >= 0) + close((*fds)[nb_fds]); + return -1; } -int prog_parse_fd(int *argc, char ***argv) +static int prog_parse_fds(int *argc, char ***argv, int **fds) { - int fd; - if (is_prefix(**argv, "id")) { unsigned int id; char *endptr; @@ -132,10 +156,12 @@ int prog_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - fd = bpf_prog_get_fd_by_id(id); - if (fd < 0) + (*fds)[0] = bpf_prog_get_fd_by_id(id); + if ((*fds)[0] < 0) { p_err("get by id (%u): %s", id, strerror(errno)); - return fd; + return -1; + } + return 1; } else if (is_prefix(**argv, "tag")) { unsigned char tag[BPF_TAG_SIZE]; @@ -149,7 +175,20 @@ int prog_parse_fd(int *argc, char ***argv) } NEXT_ARGP(); - return prog_fd_by_tag(tag); + return prog_fd_by_nametag(tag, fds, true); + } else if (is_prefix(**argv, "name")) { + char *name; + + NEXT_ARGP(); + + name = **argv; + if (strlen(name) > BPF_OBJ_NAME_LEN - 1) { + p_err("can't parse name"); + return -1; + } + NEXT_ARGP(); + + return prog_fd_by_nametag(name, fds, false); } else if (is_prefix(**argv, "pinned")) { char *path; @@ -158,13 +197,43 @@ int prog_parse_fd(int *argc, char ***argv) path = **argv; NEXT_ARGP(); - return open_obj_pinned_any(path, BPF_OBJ_PROG); + (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG); + if ((*fds)[0] < 0) + return -1; + return 1; } - p_err("expected 'id', 'tag' or 'pinned', got: '%s'?", **argv); + p_err("expected 'id', 'tag', 'name' or 'pinned', got: '%s'?", **argv); return -1; } +int prog_parse_fd(int *argc, char ***argv) +{ + int *fds = NULL; + int nb_fds, fd; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(argc, argv, &fds); + if (nb_fds != 1) { + if (nb_fds > 1) { + p_err("several programs match this handle"); + while (nb_fds--) + close(fds[nb_fds]); + } + fd = -1; + goto exit_free; + } + + fd = fds[0]; +exit_free: + free(fds); + return fd; +} + static void show_prog_maps(int fd, u32 num_maps) { struct bpf_prog_info info = {}; @@ -194,11 +263,8 @@ static void show_prog_maps(int fd, u32 num_maps) } } -static void print_prog_json(struct bpf_prog_info *info, int fd) +static void print_prog_header_json(struct bpf_prog_info *info) { - char *memlock; - - jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) jsonw_string_field(json_wtr, "type", @@ -219,7 +285,14 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_uint_field(json_wtr, "run_time_ns", info->run_time_ns); jsonw_uint_field(json_wtr, "run_cnt", info->run_cnt); } +} +static void print_prog_json(struct bpf_prog_info *info, int fd) +{ + char *memlock; + + jsonw_start_object(json_wtr); + print_prog_header_json(info); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -268,10 +341,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_end_object(json_wtr); } -static void print_prog_plain(struct bpf_prog_info *info, int fd) +static void print_prog_header_plain(struct bpf_prog_info *info) { - char *memlock; - printf("%u: ", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) printf("%s ", prog_type_name[info->type]); @@ -289,6 +360,13 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) printf(" run_time_ns %lld run_cnt %lld", info->run_time_ns, info->run_cnt); printf("\n"); +} + +static void print_prog_plain(struct bpf_prog_info *info, int fd) +{ + char *memlock; + + print_prog_header_plain(info); if (info->load_time) { char buf[32]; @@ -349,6 +427,40 @@ static int show_prog(int fd) return 0; } +static int do_show_subset(int argc, char **argv) +{ + int *fds = NULL; + int nb_fds, i; + int err = -1; + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + err = show_prog(fds[i]); + if (err) { + for (; i < nb_fds; i++) + close(fds[i]); + break; + } + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_free: + free(fds); + return err; +} + static int do_show(int argc, char **argv) { __u32 id = 0; @@ -358,15 +470,8 @@ static int do_show(int argc, char **argv) if (show_pinned) build_pinned_obj_table(&prog_table, BPF_OBJ_PROG); - if (argc == 2) { - fd = prog_parse_fd(&argc, &argv); - if (fd < 0) - return -1; - - err = show_prog(fd); - close(fd); - return err; - } + if (argc == 2) + return do_show_subset(argc, argv); if (argc) return BAD_ARG(); @@ -408,101 +513,32 @@ static int do_show(int argc, char **argv) return err; } -static int do_dump(int argc, char **argv) +static int +prog_dump(struct bpf_prog_info *info, enum dump_mode mode, + char *filepath, bool opcodes, bool visual, bool linum) { - struct bpf_prog_info_linear *info_linear; struct bpf_prog_linfo *prog_linfo = NULL; - enum {DUMP_JITED, DUMP_XLATED} mode; const char *disasm_opt = NULL; - struct bpf_prog_info *info; struct dump_data dd = {}; void *func_info = NULL; struct btf *btf = NULL; - char *filepath = NULL; - bool opcodes = false; - bool visual = false; char func_sig[1024]; unsigned char *buf; - bool linum = false; __u32 member_len; - __u64 arrays; ssize_t n; int fd; - if (is_prefix(*argv, "jited")) { - if (disasm_init()) - return -1; - mode = DUMP_JITED; - } else if (is_prefix(*argv, "xlated")) { - mode = DUMP_XLATED; - } else { - p_err("expected 'xlated' or 'jited', got: %s", *argv); - return -1; - } - NEXT_ARG(); - - if (argc < 2) - usage(); - - fd = prog_parse_fd(&argc, &argv); - if (fd < 0) - return -1; - - if (is_prefix(*argv, "file")) { - NEXT_ARG(); - if (!argc) { - p_err("expected file path"); - return -1; - } - - filepath = *argv; - NEXT_ARG(); - } else if (is_prefix(*argv, "opcodes")) { - opcodes = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "visual")) { - visual = true; - NEXT_ARG(); - } else if (is_prefix(*argv, "linum")) { - linum = true; - NEXT_ARG(); - } - - if (argc) { - usage(); - return -1; - } - - if (mode == DUMP_JITED) - arrays = 1UL << BPF_PROG_INFO_JITED_INSNS; - else - arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS; - - arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS; - arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; - arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; - arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; - arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; - - info_linear = bpf_program__get_prog_info_linear(fd, arrays); - close(fd); - if (IS_ERR_OR_NULL(info_linear)) { - p_err("can't get prog info: %s", strerror(errno)); - return -1; - } - - info = &info_linear->info; if (mode == DUMP_JITED) { if (info->jited_prog_len == 0 || !info->jited_prog_insns) { p_info("no instructions returned"); - goto err_free; + return -1; } buf = (unsigned char *)(info->jited_prog_insns); member_len = info->jited_prog_len; } else { /* DUMP_XLATED */ if (info->xlated_prog_len == 0) { p_err("error retrieving insn dump: kernel.kptr_restrict set?"); - goto err_free; + return -1; } buf = (unsigned char *)info->xlated_prog_insns; member_len = info->xlated_prog_len; @@ -510,7 +546,7 @@ static int do_dump(int argc, char **argv) if (info->btf_id && btf__get_from_id(info->btf_id, &btf)) { p_err("failed to get btf"); - goto err_free; + return -1; } func_info = (void *)info->func_info; @@ -526,7 +562,7 @@ static int do_dump(int argc, char **argv) if (fd < 0) { p_err("can't open file %s: %s", filepath, strerror(errno)); - goto err_free; + return -1; } n = write(fd, buf, member_len); @@ -534,7 +570,7 @@ static int do_dump(int argc, char **argv) if (n != member_len) { p_err("error writing output file: %s", n < 0 ? strerror(errno) : "short write"); - goto err_free; + return -1; } if (json_output) @@ -548,7 +584,7 @@ static int do_dump(int argc, char **argv) info->netns_ino, &disasm_opt); if (!name) - goto err_free; + return -1; } if (info->nr_jited_func_lens && info->jited_func_lens) { @@ -643,12 +679,130 @@ static int do_dump(int argc, char **argv) kernel_syms_destroy(&dd); } - free(info_linear); return 0; +} -err_free: - free(info_linear); - return -1; +static int do_dump(int argc, char **argv) +{ + struct bpf_prog_info_linear *info_linear; + char *filepath = NULL; + bool opcodes = false; + bool visual = false; + enum dump_mode mode; + bool linum = false; + int *fds = NULL; + int nb_fds, i = 0; + int err = -1; + __u64 arrays; + + if (is_prefix(*argv, "jited")) { + if (disasm_init()) + return -1; + mode = DUMP_JITED; + } else if (is_prefix(*argv, "xlated")) { + mode = DUMP_XLATED; + } else { + p_err("expected 'xlated' or 'jited', got: %s", *argv); + return -1; + } + NEXT_ARG(); + + if (argc < 2) + usage(); + + fds = malloc(sizeof(int)); + if (!fds) { + p_err("mem alloc failed"); + return -1; + } + nb_fds = prog_parse_fds(&argc, &argv, &fds); + if (nb_fds < 1) + goto exit_free; + + if (is_prefix(*argv, "file")) { + NEXT_ARG(); + if (!argc) { + p_err("expected file path"); + goto exit_close; + } + if (nb_fds > 1) { + p_err("several programs matched"); + goto exit_close; + } + + filepath = *argv; + NEXT_ARG(); + } else if (is_prefix(*argv, "opcodes")) { + opcodes = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "visual")) { + if (nb_fds > 1) { + p_err("several programs matched"); + goto exit_close; + } + + visual = true; + NEXT_ARG(); + } else if (is_prefix(*argv, "linum")) { + linum = true; + NEXT_ARG(); + } + + if (argc) { + usage(); + goto exit_close; + } + + if (mode == DUMP_JITED) + arrays = 1UL << BPF_PROG_INFO_JITED_INSNS; + else + arrays = 1UL << BPF_PROG_INFO_XLATED_INSNS; + + arrays |= 1UL << BPF_PROG_INFO_JITED_KSYMS; + arrays |= 1UL << BPF_PROG_INFO_JITED_FUNC_LENS; + arrays |= 1UL << BPF_PROG_INFO_FUNC_INFO; + arrays |= 1UL << BPF_PROG_INFO_LINE_INFO; + arrays |= 1UL << BPF_PROG_INFO_JITED_LINE_INFO; + + if (json_output && nb_fds > 1) + jsonw_start_array(json_wtr); /* root array */ + for (i = 0; i < nb_fds; i++) { + info_linear = bpf_program__get_prog_info_linear(fds[i], arrays); + if (IS_ERR_OR_NULL(info_linear)) { + p_err("can't get prog info: %s", strerror(errno)); + break; + } + + if (json_output && nb_fds > 1) { + jsonw_start_object(json_wtr); /* prog object */ + print_prog_header_json(&info_linear->info); + jsonw_name(json_wtr, "insns"); + } else if (nb_fds > 1) { + print_prog_header_plain(&info_linear->info); + } + + err = prog_dump(&info_linear->info, mode, filepath, opcodes, + visual, linum); + + if (json_output && nb_fds > 1) + jsonw_end_object(json_wtr); /* prog object */ + else if (i != nb_fds - 1 && nb_fds > 1) + printf("\n"); + + free(info_linear); + if (err) + break; + close(fds[i]); + } + if (json_output && nb_fds > 1) + jsonw_end_array(json_wtr); /* root array */ + +exit_close: + for (; i < nb_fds; i++) + close(fds[i]); +exit_free: + free(fds); + return err; } static int do_pin(int argc, char **argv) diff --git a/tools/include/uapi/asm/bpf_perf_event.h b/tools/include/uapi/asm/bpf_perf_event.h index 13a58531e6fa..39acc149d843 100644 --- a/tools/include/uapi/asm/bpf_perf_event.h +++ b/tools/include/uapi/asm/bpf_perf_event.h @@ -2,6 +2,8 @@ #include "../../arch/arm64/include/uapi/asm/bpf_perf_event.h" #elif defined(__s390__) #include "../../arch/s390/include/uapi/asm/bpf_perf_event.h" +#elif defined(__riscv) +#include "../../arch/riscv/include/uapi/asm/bpf_perf_event.h" #else #include <uapi/asm-generic/bpf_perf_event.h> #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index dbbcf0b02970..7df436da542d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -231,6 +231,11 @@ enum bpf_attach_type { * When children program makes decision (like picking TCP CA or sock bind) * parent program has a chance to override it. * + * With BPF_F_ALLOW_MULTI a new program is added to the end of the list of + * programs for a cgroup. Though it's possible to replace an old program at + * any position by also specifying BPF_F_REPLACE flag and position itself in + * replace_bpf_fd attribute. Old program at this position will be released. + * * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. * A cgroup with NONE doesn't allow any programs in sub-cgroups. * Ex1: @@ -249,6 +254,7 @@ enum bpf_attach_type { */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) #define BPF_F_ALLOW_MULTI (1U << 1) +#define BPF_F_REPLACE (1U << 2) /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel @@ -442,6 +448,10 @@ union bpf_attr { __u32 attach_bpf_fd; /* eBPF program to attach */ __u32 attach_type; __u32 attach_flags; + __u32 replace_bpf_fd; /* previously attached eBPF + * program to replace if + * BPF_F_REPLACE is used + */ }; struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 63ae4a39e58b..1a2898c482ee 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -22,9 +22,9 @@ struct btf_header { }; /* Max # of type identifier */ -#define BTF_MAX_TYPE 0x0000ffff +#define BTF_MAX_TYPE 0x000fffff /* Max offset into the string section */ -#define BTF_MAX_NAME_OFFSET 0x0000ffff +#define BTF_MAX_NAME_OFFSET 0x00ffffff /* Max # of struct/union/enum members or func args */ #define BTF_MAX_VLEN 0xffff @@ -142,7 +142,8 @@ struct btf_param { enum { BTF_VAR_STATIC = 0, - BTF_VAR_GLOBAL_ALLOCATED, + BTF_VAR_GLOBAL_ALLOCATED = 1, + BTF_VAR_GLOBAL_EXTERN = 2, }; /* BTF_KIND_VAR is followed by a single "struct btf_var" to describe diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 8aec8769d944..42efdb84d189 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -485,6 +485,13 @@ enum macsec_validation_type { MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1, }; +enum macsec_offload { + MACSEC_OFFLOAD_OFF = 0, + MACSEC_OFFLOAD_PHY = 1, + __MACSEC_OFFLOAD_END, + MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_END - 1, +}; + /* IPVLAN section */ enum { IFLA_IPVLAN_UNSPEC, diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index e7ad9d350a28..1521073b6348 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -76,6 +76,8 @@ enum { #define IPPROTO_MPLS IPPROTO_MPLS IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_MPTCP = 262, /* Multipath TCP connection */ +#define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX }; #endif diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 97830e46d1a0..d87830e7ea63 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -56,8 +56,8 @@ ifndef VERBOSE endif FEATURE_USER = .libbpf -FEATURE_TESTS = libelf libelf-mmap bpf reallocarray -FEATURE_DISPLAY = libelf bpf +FEATURE_TESTS = libelf libelf-mmap zlib bpf reallocarray +FEATURE_DISPLAY = libelf zlib bpf INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES) @@ -148,6 +148,7 @@ TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags) GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ @@ -160,7 +161,7 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force elfdep bpfdep $(BPF_HELPER_DEFS) +$(BPF_IN_SHARED): force elfdep zdep bpfdep $(BPF_HELPER_DEFS) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -178,7 +179,7 @@ $(BPF_IN_SHARED): force elfdep bpfdep $(BPF_HELPER_DEFS) echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force elfdep bpfdep $(BPF_HELPER_DEFS) +$(BPF_IN_STATIC): force elfdep zdep bpfdep $(BPF_HELPER_DEFS) $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h @@ -190,7 +191,7 @@ $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(QUIET_LINK)$(CC) $(LDFLAGS) \ --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ - -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -lz -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION) @@ -214,6 +215,7 @@ check_abi: $(OUTPUT)libbpf.so "versioned in $(VERSION_SCRIPT)." >&2; \ readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + sed 's/\[.*\]//' | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf -s --wide $(OUTPUT)libbpf.so | \ @@ -250,6 +252,7 @@ install_headers: $(BPF_HELPER_DEFS) $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ $(call do_install,btf.h,$(prefix)/include/bpf,644); \ $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \ + $(call do_install,libbpf_common.h,$(prefix)/include/bpf,644); \ $(call do_install,xsk.h,$(prefix)/include/bpf,644); \ $(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \ $(call do_install,$(BPF_HELPER_DEFS),$(prefix)/include/bpf,644); \ @@ -278,12 +281,15 @@ clean: -PHONY += force elfdep bpfdep cscope tags +PHONY += force elfdep zdep bpfdep cscope tags force: elfdep: @if [ "$(feature-libelf)" != "1" ]; then echo "No libelf found"; exit 1 ; fi +zdep: + @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi + bpfdep: @if [ "$(feature-bpf)" != "1" ]; then echo "BPF API too old"; exit 1 ; fi diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 98596e15390f..a787d53699c8 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -467,13 +467,28 @@ int bpf_obj_get(const char *pathname) int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, unsigned int flags) { + DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, opts, + .flags = flags, + ); + + return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts); +} + +int bpf_prog_attach_xattr(int prog_fd, int target_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts) +{ union bpf_attr attr; + if (!OPTS_VALID(opts, bpf_prog_attach_opts)) + return -EINVAL; + memset(&attr, 0, sizeof(attr)); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; - attr.attach_flags = flags; + attr.attach_flags = OPTS_GET(opts, flags, 0); + attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0); return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 3c791fa8e68e..f0ab8519986e 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -28,14 +28,12 @@ #include <stddef.h> #include <stdint.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - struct bpf_create_map_attr { const char *name; enum bpf_map_type map_type; @@ -128,8 +126,19 @@ LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); LIBBPF_API int bpf_map_freeze(int fd); LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); LIBBPF_API int bpf_obj_get(const char *pathname); + +struct bpf_prog_attach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + unsigned int flags; + int replace_prog_fd; +}; +#define bpf_prog_attach_opts__last_field replace_prog_fd + LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); +LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 0c7d28292898..f69cc208778a 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -25,6 +25,9 @@ #ifndef __always_inline #define __always_inline __attribute__((always_inline)) #endif +#ifndef __weak +#define __weak __attribute__((weak)) +#endif /* * Helper structure used by eBPF C program @@ -44,4 +47,12 @@ enum libbpf_pin_type { LIBBPF_PIN_BY_NAME, }; +enum libbpf_tristate { + TRI_NO = 0, + TRI_YES = 1, + TRI_MODULE = 2, +}; + +#define __kconfig __attribute__((section(".kconfig"))) + #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 88efa2bb7137..5f04f56e1eb6 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -278,6 +278,45 @@ done: return nelems * size; } +int btf__align_of(const struct btf *btf, __u32 id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + __u16 kind = btf_kind(t); + + switch (kind) { + case BTF_KIND_INT: + case BTF_KIND_ENUM: + return min(sizeof(void *), t->size); + case BTF_KIND_PTR: + return sizeof(void *); + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return btf__align_of(btf, t->type); + case BTF_KIND_ARRAY: + return btf__align_of(btf, btf_array(t)->type); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); + int i, max_align = 1, align; + + for (i = 0; i < vlen; i++, m++) { + align = btf__align_of(btf, m->type); + if (align <= 0) + return align; + max_align = max(max_align, align); + } + + return max_align; + } + default: + pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); + return 0; + } +} + int btf__resolve_type(const struct btf *btf, __u32 type_id) { const struct btf_type *t; @@ -539,6 +578,12 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, return -ENOENT; } + /* .extern datasec size and var offsets were set correctly during + * extern collection step, so just skip straight to sorting variables + */ + if (t->size) + goto sort_vars; + ret = bpf_object__section_size(obj, name, &size); if (ret || !size || (t->size && t->size != size)) { pr_debug("Invalid size for section %s: %u bytes\n", name, size); @@ -575,7 +620,8 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, vsi->offset = off; } - qsort(t + 1, vars, sizeof(*vsi), compare_vsi_off); +sort_vars: + qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off); return 0; } diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index d9ac73a02cde..8d73f7f5551f 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -8,14 +8,12 @@ #include <linux/btf.h> #include <linux/types.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - #define BTF_ELF_SEC ".BTF" #define BTF_EXT_ELF_SEC ".BTF.ext" #define MAPS_ELF_SEC ".maps" @@ -79,6 +77,7 @@ LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); +LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); LIBBPF_API int btf__fd(const struct btf *btf); LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); @@ -127,6 +126,28 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); +struct btf_dump_emit_type_decl_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* optional field name for type declaration, e.g.: + * - struct my_struct <FNAME> + * - void (*<FNAME>)(int) + * - char (*<FNAME>)[123] + */ + const char *field_name; + /* extra indentation level (in number of tabs) to emit for multi-line + * type declarations (e.g., anonymous struct); applies for lines + * starting from the second one (first line is assumed to have + * necessary indentation already + */ + int indent_level; +}; +#define btf_dump_emit_type_decl_opts__last_field indent_level + +LIBBPF_API int +btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, + const struct btf_dump_emit_type_decl_opts *opts); + /* * A set of helpers for easier BTF types handling */ diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index cb126d8fcf75..e95f7710f210 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -116,6 +116,8 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...) va_end(args); } +static int btf_dump_mark_referenced(struct btf_dump *d); + struct btf_dump *btf_dump__new(const struct btf *btf, const struct btf_ext *btf_ext, const struct btf_dump_opts *opts, @@ -137,18 +139,39 @@ struct btf_dump *btf_dump__new(const struct btf *btf, if (IS_ERR(d->type_names)) { err = PTR_ERR(d->type_names); d->type_names = NULL; - btf_dump__free(d); - return ERR_PTR(err); } d->ident_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); if (IS_ERR(d->ident_names)) { err = PTR_ERR(d->ident_names); d->ident_names = NULL; - btf_dump__free(d); - return ERR_PTR(err); + goto err; + } + d->type_states = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->type_states[0])); + if (!d->type_states) { + err = -ENOMEM; + goto err; + } + d->cached_names = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->cached_names[0])); + if (!d->cached_names) { + err = -ENOMEM; + goto err; } + /* VOID is special */ + d->type_states[0].order_state = ORDERED; + d->type_states[0].emit_state = EMITTED; + + /* eagerly determine referenced types for anon enums */ + err = btf_dump_mark_referenced(d); + if (err) + goto err; + return d; +err: + btf_dump__free(d); + return ERR_PTR(err); } void btf_dump__free(struct btf_dump *d) @@ -175,7 +198,6 @@ void btf_dump__free(struct btf_dump *d) free(d); } -static int btf_dump_mark_referenced(struct btf_dump *d); static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr); static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id); @@ -202,27 +224,6 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id) if (id > btf__get_nr_types(d->btf)) return -EINVAL; - /* type states are lazily allocated, as they might not be needed */ - if (!d->type_states) { - d->type_states = calloc(1 + btf__get_nr_types(d->btf), - sizeof(d->type_states[0])); - if (!d->type_states) - return -ENOMEM; - d->cached_names = calloc(1 + btf__get_nr_types(d->btf), - sizeof(d->cached_names[0])); - if (!d->cached_names) - return -ENOMEM; - - /* VOID is special */ - d->type_states[0].order_state = ORDERED; - d->type_states[0].emit_state = EMITTED; - - /* eagerly determine referenced types for anon enums */ - err = btf_dump_mark_referenced(d); - if (err) - return err; - } - d->emit_queue_cnt = 0; err = btf_dump_order_type(d, id, false); if (err < 0) @@ -752,41 +753,6 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) } } -static int btf_align_of(const struct btf *btf, __u32 id) -{ - const struct btf_type *t = btf__type_by_id(btf, id); - __u16 kind = btf_kind(t); - - switch (kind) { - case BTF_KIND_INT: - case BTF_KIND_ENUM: - return min(sizeof(void *), t->size); - case BTF_KIND_PTR: - return sizeof(void *); - case BTF_KIND_TYPEDEF: - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - return btf_align_of(btf, t->type); - case BTF_KIND_ARRAY: - return btf_align_of(btf, btf_array(t)->type); - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: { - const struct btf_member *m = btf_members(t); - __u16 vlen = btf_vlen(t); - int i, align = 1; - - for (i = 0; i < vlen; i++, m++) - align = max(align, btf_align_of(btf, m->type)); - - return align; - } - default: - pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); - return 1; - } -} - static bool btf_is_struct_packed(const struct btf *btf, __u32 id, const struct btf_type *t) { @@ -794,18 +760,18 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, int align, i, bit_sz; __u16 vlen; - align = btf_align_of(btf, id); + align = btf__align_of(btf, id); /* size of a non-packed struct has to be a multiple of its alignment*/ - if (t->size % align) + if (align && t->size % align) return true; m = btf_members(t); vlen = btf_vlen(t); /* all non-bitfield fields have to be naturally aligned */ for (i = 0; i < vlen; i++, m++) { - align = btf_align_of(btf, m->type); + align = btf__align_of(btf, m->type); bit_sz = btf_member_bitfield_size(t, i); - if (bit_sz == 0 && m->offset % (8 * align) != 0) + if (align && bit_sz == 0 && m->offset % (8 * align) != 0) return true; } @@ -889,7 +855,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, fname = btf_name_of(d, m->name_off); m_sz = btf_member_bitfield_size(t, i); m_off = btf_member_bit_offset(t, i); - align = packed ? 1 : btf_align_of(d->btf, m->type); + align = packed ? 1 : btf__align_of(d->btf, m->type); btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1); btf_dump_printf(d, "\n%s", pfx(lvl + 1)); @@ -907,7 +873,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, /* pad at the end, if necessary */ if (is_struct) { - align = packed ? 1 : btf_align_of(d->btf, id); + align = packed ? 1 : btf__align_of(d->btf, id); btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align, lvl + 1); } @@ -1051,6 +1017,21 @@ static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id) * of a stack frame. Some care is required to "pop" stack frames after * processing type declaration chain. */ +int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, + const struct btf_dump_emit_type_decl_opts *opts) +{ + const char *fname; + int lvl; + + if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts)) + return -EINVAL; + + fname = OPTS_GET(opts, field_name, NULL); + lvl = OPTS_GET(opts, indent_level, 0); + btf_dump_emit_type_decl(d, id, fname, lvl); + return 0; +} + static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, const char *fname, int lvl) { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 3f09772192f1..7513165b104f 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -18,6 +18,7 @@ #include <stdarg.h> #include <libgen.h> #include <inttypes.h> +#include <limits.h> #include <string.h> #include <unistd.h> #include <endian.h> @@ -41,9 +42,11 @@ #include <sys/types.h> #include <sys/vfs.h> #include <sys/utsname.h> +#include <sys/resource.h> #include <tools/libc_compat.h> #include <libelf.h> #include <gelf.h> +#include <zlib.h> #include "libbpf.h" #include "bpf.h" @@ -99,14 +102,33 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...) va_end(args); } -#define STRERR_BUFSIZE 128 +static void pr_perm_msg(int err) +{ + struct rlimit limit; + char buf[100]; + + if (err != -EPERM || geteuid() != 0) + return; + + err = getrlimit(RLIMIT_MEMLOCK, &limit); + if (err) + return; + + if (limit.rlim_cur == RLIM_INFINITY) + return; + + if (limit.rlim_cur < 1024) + snprintf(buf, sizeof(buf), "%zu bytes", (size_t)limit.rlim_cur); + else if (limit.rlim_cur < 1024*1024) + snprintf(buf, sizeof(buf), "%.1f KiB", (double)limit.rlim_cur / 1024); + else + snprintf(buf, sizeof(buf), "%.1f MiB", (double)limit.rlim_cur / (1024*1024)); -#define CHECK_ERR(action, err, out) do { \ - err = action; \ - if (err) \ - goto out; \ -} while (0) + pr_warn("permission error while running as root; try raising 'ulimit -l'? current value: %s\n", + buf); +} +#define STRERR_BUFSIZE 128 /* Copied from tools/perf/util/util.h */ #ifndef zfree @@ -146,6 +168,20 @@ struct bpf_capabilities { __u32 array_mmap:1; }; +enum reloc_type { + RELO_LD64, + RELO_CALL, + RELO_DATA, + RELO_EXTERN, +}; + +struct reloc_desc { + enum reloc_type type; + int insn_idx; + int map_idx; + int sym_off; +}; + /* * bpf_prog should be a better name but it has been used in * linux/filter.h. @@ -164,16 +200,7 @@ struct bpf_program { size_t insns_cnt, main_prog_cnt; enum bpf_prog_type type; - struct reloc_desc { - enum { - RELO_LD64, - RELO_CALL, - RELO_DATA, - } type; - int insn_idx; - int map_idx; - int sym_off; - } *reloc_desc; + struct reloc_desc *reloc_desc; int nr_reloc; int log_level; @@ -202,22 +229,29 @@ struct bpf_program { __u32 prog_flags; }; +#define DATA_SEC ".data" +#define BSS_SEC ".bss" +#define RODATA_SEC ".rodata" +#define KCONFIG_SEC ".kconfig" + enum libbpf_map_type { LIBBPF_MAP_UNSPEC, LIBBPF_MAP_DATA, LIBBPF_MAP_BSS, LIBBPF_MAP_RODATA, + LIBBPF_MAP_KCONFIG, }; static const char * const libbpf_type_to_btf_name[] = { - [LIBBPF_MAP_DATA] = ".data", - [LIBBPF_MAP_BSS] = ".bss", - [LIBBPF_MAP_RODATA] = ".rodata", + [LIBBPF_MAP_DATA] = DATA_SEC, + [LIBBPF_MAP_BSS] = BSS_SEC, + [LIBBPF_MAP_RODATA] = RODATA_SEC, + [LIBBPF_MAP_KCONFIG] = KCONFIG_SEC, }; struct bpf_map { - int fd; char *name; + int fd; int sec_idx; size_t sec_offset; int map_ifindex; @@ -228,14 +262,32 @@ struct bpf_map { void *priv; bpf_map_clear_priv_t clear_priv; enum libbpf_map_type libbpf_type; + void *mmaped; char *pin_path; bool pinned; bool reused; }; -struct bpf_secdata { - void *rodata; - void *data; +enum extern_type { + EXT_UNKNOWN, + EXT_CHAR, + EXT_BOOL, + EXT_INT, + EXT_TRISTATE, + EXT_CHAR_ARR, +}; + +struct extern_desc { + const char *name; + int sym_idx; + int btf_id; + enum extern_type type; + int sz; + int align; + int data_off; + bool is_signed; + bool is_weak; + bool is_set; }; static LIST_HEAD(bpf_objects_list); @@ -250,7 +302,11 @@ struct bpf_object { struct bpf_map *maps; size_t nr_maps; size_t maps_cap; - struct bpf_secdata sections; + + char *kconfig; + struct extern_desc *externs; + int nr_extern; + int kconfig_map_idx; bool loaded; bool has_pseudo_calls; @@ -279,6 +335,7 @@ struct bpf_object { int maps_shndx; int btf_maps_shndx; int text_shndx; + int symbols_shndx; int data_shndx; int rodata_shndx; int bss_shndx; @@ -550,6 +607,7 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.data_shndx = -1; obj->efile.rodata_shndx = -1; obj->efile.bss_shndx = -1; + obj->kconfig_map_idx = -1; obj->kern_version = get_kernel_version(); obj->loaded = false; @@ -748,13 +806,13 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name, *size = 0; if (!name) { return -EINVAL; - } else if (!strcmp(name, ".data")) { + } else if (!strcmp(name, DATA_SEC)) { if (obj->efile.data) *size = obj->efile.data->d_size; - } else if (!strcmp(name, ".bss")) { + } else if (!strcmp(name, BSS_SEC)) { if (obj->efile.bss) *size = obj->efile.bss->d_size; - } else if (!strcmp(name, ".rodata")) { + } else if (!strcmp(name, RODATA_SEC)) { if (obj->efile.rodata) *size = obj->efile.rodata->d_size; } else { @@ -835,13 +893,38 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) return &obj->maps[obj->nr_maps++]; } +static size_t bpf_map_mmap_sz(const struct bpf_map *map) +{ + long page_sz = sysconf(_SC_PAGE_SIZE); + size_t map_sz; + + map_sz = roundup(map->def.value_size, 8) * map->def.max_entries; + map_sz = roundup(map_sz, page_sz); + return map_sz; +} + +static char *internal_map_name(struct bpf_object *obj, + enum libbpf_map_type type) +{ + char map_name[BPF_OBJ_NAME_LEN]; + const char *sfx = libbpf_type_to_btf_name[type]; + int sfx_len = max((size_t)7, strlen(sfx)); + int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, + strlen(obj->name)); + + snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name, + sfx_len, libbpf_type_to_btf_name[type]); + + return strdup(map_name); +} + static int bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, - int sec_idx, Elf_Data *data, void **data_buff) + int sec_idx, void *data, size_t data_sz) { - char map_name[BPF_OBJ_NAME_LEN]; struct bpf_map_def *def; struct bpf_map *map; + int err; map = bpf_object__add_map(obj); if (IS_ERR(map)) @@ -850,9 +933,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, map->libbpf_type = type; map->sec_idx = sec_idx; map->sec_offset = 0; - snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, - libbpf_type_to_btf_name[type]); - map->name = strdup(map_name); + map->name = internal_map_name(obj, type); if (!map->name) { pr_warn("failed to alloc map name\n"); return -ENOMEM; @@ -861,25 +942,29 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, def = &map->def; def->type = BPF_MAP_TYPE_ARRAY; def->key_size = sizeof(int); - def->value_size = data->d_size; + def->value_size = data_sz; def->max_entries = 1; - def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0; - if (obj->caps.array_mmap) - def->map_flags |= BPF_F_MMAPABLE; + def->map_flags = type == LIBBPF_MAP_RODATA || type == LIBBPF_MAP_KCONFIG + ? BPF_F_RDONLY_PROG : 0; + def->map_flags |= BPF_F_MMAPABLE; pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n", - map_name, map->sec_idx, map->sec_offset, def->map_flags); + map->name, map->sec_idx, map->sec_offset, def->map_flags); - if (data_buff) { - *data_buff = malloc(data->d_size); - if (!*data_buff) { - zfree(&map->name); - pr_warn("failed to alloc map content buffer\n"); - return -ENOMEM; - } - memcpy(*data_buff, data->d_buf, data->d_size); + map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (map->mmaped == MAP_FAILED) { + err = -errno; + map->mmaped = NULL; + pr_warn("failed to alloc map '%s' content buffer: %d\n", + map->name, err); + zfree(&map->name); + return err; } + if (data) + memcpy(map->mmaped, data, data_sz); + pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name); return 0; } @@ -888,37 +973,332 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj) { int err; - if (!obj->caps.global_data) - return 0; /* * Populate obj->maps with libbpf internal maps. */ if (obj->efile.data_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, obj->efile.data_shndx, - obj->efile.data, - &obj->sections.data); + obj->efile.data->d_buf, + obj->efile.data->d_size); if (err) return err; } if (obj->efile.rodata_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, obj->efile.rodata_shndx, - obj->efile.rodata, - &obj->sections.rodata); + obj->efile.rodata->d_buf, + obj->efile.rodata->d_size); if (err) return err; } if (obj->efile.bss_shndx >= 0) { err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, obj->efile.bss_shndx, - obj->efile.bss, NULL); + NULL, + obj->efile.bss->d_size); if (err) return err; } return 0; } + +static struct extern_desc *find_extern_by_name(const struct bpf_object *obj, + const void *name) +{ + int i; + + for (i = 0; i < obj->nr_extern; i++) { + if (strcmp(obj->externs[i].name, name) == 0) + return &obj->externs[i]; + } + return NULL; +} + +static int set_ext_value_tri(struct extern_desc *ext, void *ext_val, + char value) +{ + switch (ext->type) { + case EXT_BOOL: + if (value == 'm') { + pr_warn("extern %s=%c should be tristate or char\n", + ext->name, value); + return -EINVAL; + } + *(bool *)ext_val = value == 'y' ? true : false; + break; + case EXT_TRISTATE: + if (value == 'y') + *(enum libbpf_tristate *)ext_val = TRI_YES; + else if (value == 'm') + *(enum libbpf_tristate *)ext_val = TRI_MODULE; + else /* value == 'n' */ + *(enum libbpf_tristate *)ext_val = TRI_NO; + break; + case EXT_CHAR: + *(char *)ext_val = value; + break; + case EXT_UNKNOWN: + case EXT_INT: + case EXT_CHAR_ARR: + default: + pr_warn("extern %s=%c should be bool, tristate, or char\n", + ext->name, value); + return -EINVAL; + } + ext->is_set = true; + return 0; +} + +static int set_ext_value_str(struct extern_desc *ext, char *ext_val, + const char *value) +{ + size_t len; + + if (ext->type != EXT_CHAR_ARR) { + pr_warn("extern %s=%s should char array\n", ext->name, value); + return -EINVAL; + } + + len = strlen(value); + if (value[len - 1] != '"') { + pr_warn("extern '%s': invalid string config '%s'\n", + ext->name, value); + return -EINVAL; + } + + /* strip quotes */ + len -= 2; + if (len >= ext->sz) { + pr_warn("extern '%s': long string config %s of (%zu bytes) truncated to %d bytes\n", + ext->name, value, len, ext->sz - 1); + len = ext->sz - 1; + } + memcpy(ext_val, value + 1, len); + ext_val[len] = '\0'; + ext->is_set = true; + return 0; +} + +static int parse_u64(const char *value, __u64 *res) +{ + char *value_end; + int err; + + errno = 0; + *res = strtoull(value, &value_end, 0); + if (errno) { + err = -errno; + pr_warn("failed to parse '%s' as integer: %d\n", value, err); + return err; + } + if (*value_end) { + pr_warn("failed to parse '%s' as integer completely\n", value); + return -EINVAL; + } + return 0; +} + +static bool is_ext_value_in_range(const struct extern_desc *ext, __u64 v) +{ + int bit_sz = ext->sz * 8; + + if (ext->sz == 8) + return true; + + /* Validate that value stored in u64 fits in integer of `ext->sz` + * bytes size without any loss of information. If the target integer + * is signed, we rely on the following limits of integer type of + * Y bits and subsequent transformation: + * + * -2^(Y-1) <= X <= 2^(Y-1) - 1 + * 0 <= X + 2^(Y-1) <= 2^Y - 1 + * 0 <= X + 2^(Y-1) < 2^Y + * + * For unsigned target integer, check that all the (64 - Y) bits are + * zero. + */ + if (ext->is_signed) + return v + (1ULL << (bit_sz - 1)) < (1ULL << bit_sz); + else + return (v >> bit_sz) == 0; +} + +static int set_ext_value_num(struct extern_desc *ext, void *ext_val, + __u64 value) +{ + if (ext->type != EXT_INT && ext->type != EXT_CHAR) { + pr_warn("extern %s=%llu should be integer\n", + ext->name, (unsigned long long)value); + return -EINVAL; + } + if (!is_ext_value_in_range(ext, value)) { + pr_warn("extern %s=%llu value doesn't fit in %d bytes\n", + ext->name, (unsigned long long)value, ext->sz); + return -ERANGE; + } + switch (ext->sz) { + case 1: *(__u8 *)ext_val = value; break; + case 2: *(__u16 *)ext_val = value; break; + case 4: *(__u32 *)ext_val = value; break; + case 8: *(__u64 *)ext_val = value; break; + default: + return -EINVAL; + } + ext->is_set = true; + return 0; +} + +static int bpf_object__process_kconfig_line(struct bpf_object *obj, + char *buf, void *data) +{ + struct extern_desc *ext; + char *sep, *value; + int len, err = 0; + void *ext_val; + __u64 num; + + if (strncmp(buf, "CONFIG_", 7)) + return 0; + + sep = strchr(buf, '='); + if (!sep) { + pr_warn("failed to parse '%s': no separator\n", buf); + return -EINVAL; + } + + /* Trim ending '\n' */ + len = strlen(buf); + if (buf[len - 1] == '\n') + buf[len - 1] = '\0'; + /* Split on '=' and ensure that a value is present. */ + *sep = '\0'; + if (!sep[1]) { + *sep = '='; + pr_warn("failed to parse '%s': no value\n", buf); + return -EINVAL; + } + + ext = find_extern_by_name(obj, buf); + if (!ext || ext->is_set) + return 0; + + ext_val = data + ext->data_off; + value = sep + 1; + + switch (*value) { + case 'y': case 'n': case 'm': + err = set_ext_value_tri(ext, ext_val, *value); + break; + case '"': + err = set_ext_value_str(ext, ext_val, value); + break; + default: + /* assume integer */ + err = parse_u64(value, &num); + if (err) { + pr_warn("extern %s=%s should be integer\n", + ext->name, value); + return err; + } + err = set_ext_value_num(ext, ext_val, num); + break; + } + if (err) + return err; + pr_debug("extern %s=%s\n", ext->name, value); + return 0; +} + +static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data) +{ + char buf[PATH_MAX]; + struct utsname uts; + int len, err = 0; + gzFile file; + + uname(&uts); + len = snprintf(buf, PATH_MAX, "/boot/config-%s", uts.release); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + /* gzopen also accepts uncompressed files. */ + file = gzopen(buf, "r"); + if (!file) + file = gzopen("/proc/config.gz", "r"); + + if (!file) { + pr_warn("failed to open system Kconfig\n"); + return -ENOENT; + } + + while (gzgets(file, buf, sizeof(buf))) { + err = bpf_object__process_kconfig_line(obj, buf, data); + if (err) { + pr_warn("error parsing system Kconfig line '%s': %d\n", + buf, err); + goto out; + } + } + +out: + gzclose(file); + return err; +} + +static int bpf_object__read_kconfig_mem(struct bpf_object *obj, + const char *config, void *data) +{ + char buf[PATH_MAX]; + int err = 0; + FILE *file; + + file = fmemopen((void *)config, strlen(config), "r"); + if (!file) { + err = -errno; + pr_warn("failed to open in-memory Kconfig: %d\n", err); + return err; + } + + while (fgets(buf, sizeof(buf), file)) { + err = bpf_object__process_kconfig_line(obj, buf, data); + if (err) { + pr_warn("error parsing in-memory Kconfig line '%s': %d\n", + buf, err); + break; + } + } + + fclose(file); + return err; +} + +static int bpf_object__init_kconfig_map(struct bpf_object *obj) +{ + struct extern_desc *last_ext; + size_t map_sz; + int err; + + if (obj->nr_extern == 0) + return 0; + + last_ext = &obj->externs[obj->nr_extern - 1]; + map_sz = last_ext->data_off + last_ext->sz; + + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_KCONFIG, + obj->efile.symbols_shndx, + NULL, map_sz); + if (err) + return err; + + obj->kconfig_map_idx = obj->nr_maps - 1; + + return 0; +} + static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) { Elf_Data *symbols = obj->efile.symbols; @@ -1242,15 +1622,15 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } sz = btf__resolve_size(obj->btf, t->type); if (sz < 0) { - pr_warn("map '%s': can't determine key size for type [%u]: %lld.\n", - map_name, t->type, sz); + pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n", + map_name, t->type, (ssize_t)sz); return sz; } - pr_debug("map '%s': found key [%u], sz = %lld.\n", - map_name, t->type, sz); + pr_debug("map '%s': found key [%u], sz = %zd.\n", + map_name, t->type, (ssize_t)sz); if (map->def.key_size && map->def.key_size != sz) { - pr_warn("map '%s': conflicting key size %u != %lld.\n", - map_name, map->def.key_size, sz); + pr_warn("map '%s': conflicting key size %u != %zd.\n", + map_name, map->def.key_size, (ssize_t)sz); return -EINVAL; } map->def.key_size = sz; @@ -1285,15 +1665,15 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } sz = btf__resolve_size(obj->btf, t->type); if (sz < 0) { - pr_warn("map '%s': can't determine value size for type [%u]: %lld.\n", - map_name, t->type, sz); + pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n", + map_name, t->type, (ssize_t)sz); return sz; } - pr_debug("map '%s': found value [%u], sz = %lld.\n", - map_name, t->type, sz); + pr_debug("map '%s': found value [%u], sz = %zd.\n", + map_name, t->type, (ssize_t)sz); if (map->def.value_size && map->def.value_size != sz) { - pr_warn("map '%s': conflicting value size %u != %lld.\n", - map_name, map->def.value_size, sz); + pr_warn("map '%s': conflicting value size %u != %zd.\n", + map_name, map->def.value_size, (ssize_t)sz); return -EINVAL; } map->def.value_size = sz; @@ -1393,21 +1773,20 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, return 0; } -static int bpf_object__init_maps(struct bpf_object *obj, bool relaxed_maps, - const char *pin_root_path) +static int bpf_object__init_maps(struct bpf_object *obj, + const struct bpf_object_open_opts *opts) { - bool strict = !relaxed_maps; + const char *pin_root_path; + bool strict; int err; - err = bpf_object__init_user_maps(obj, strict); - if (err) - return err; - - err = bpf_object__init_user_btf_maps(obj, strict, pin_root_path); - if (err) - return err; + strict = !OPTS_GET(opts, relaxed_maps, false); + pin_root_path = OPTS_GET(opts, pin_root_path, NULL); - err = bpf_object__init_global_data_maps(obj); + err = bpf_object__init_user_maps(obj, strict); + err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path); + err = err ?: bpf_object__init_global_data_maps(obj); + err = err ?: bpf_object__init_kconfig_map(obj); if (err) return err; @@ -1509,7 +1888,8 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) { - return obj->efile.btf_maps_shndx >= 0; + return obj->efile.btf_maps_shndx >= 0 || + obj->nr_extern > 0; } static int bpf_object__init_btf(struct bpf_object *obj, @@ -1526,11 +1906,6 @@ static int bpf_object__init_btf(struct bpf_object *obj, BTF_ELF_SEC, err); goto out; } - err = btf__finalize_data(obj, obj->btf); - if (err) { - pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); - goto out; - } } if (btf_ext_data) { if (!obj->btf) { @@ -1564,6 +1939,30 @@ out: return 0; } +static int bpf_object__finalize_btf(struct bpf_object *obj) +{ + int err; + + if (!obj->btf) + return 0; + + err = btf__finalize_data(obj, obj->btf); + if (!err) + return 0; + + pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + + if (bpf_object__is_btf_mandatory(obj)) { + pr_warn("BTF is required, but is missing or corrupted.\n"); + return -ENOENT; + } + return 0; +} + static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) { int err = 0; @@ -1592,8 +1991,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) return 0; } -static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, - const char *pin_root_path) +static int bpf_object__elf_collect(struct bpf_object *obj) { Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; @@ -1665,6 +2063,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, return -LIBBPF_ERRNO__FORMAT; } obj->efile.symbols = data; + obj->efile.symbols_shndx = idx; obj->efile.strtabidx = sh.sh_link; } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { if (sh.sh_flags & SHF_EXECINSTR) { @@ -1683,10 +2082,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, name, obj->path, cp); return err; } - } else if (strcmp(name, ".data") == 0) { + } else if (strcmp(name, DATA_SEC) == 0) { obj->efile.data = data; obj->efile.data_shndx = idx; - } else if (strcmp(name, ".rodata") == 0) { + } else if (strcmp(name, RODATA_SEC) == 0) { obj->efile.rodata = data; obj->efile.rodata_shndx = idx; } else { @@ -1716,7 +2115,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, obj->efile.reloc_sects[nr_sects].shdr = sh; obj->efile.reloc_sects[nr_sects].data = data; - } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { + } else if (sh.sh_type == SHT_NOBITS && + strcmp(name, BSS_SEC) == 0) { obj->efile.bss = data; obj->efile.bss_shndx = idx; } else { @@ -1728,14 +2128,217 @@ static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, pr_warn("Corrupted ELF file: index of strtab invalid\n"); return -LIBBPF_ERRNO__FORMAT; } - err = bpf_object__init_btf(obj, btf_data, btf_ext_data); - if (!err) - err = bpf_object__init_maps(obj, relaxed_maps, pin_root_path); - if (!err) - err = bpf_object__sanitize_and_load_btf(obj); - if (!err) - err = bpf_object__init_prog_names(obj); - return err; + return bpf_object__init_btf(obj, btf_data, btf_ext_data); +} + +static bool sym_is_extern(const GElf_Sym *sym) +{ + int bind = GELF_ST_BIND(sym->st_info); + /* externs are symbols w/ type=NOTYPE, bind=GLOBAL|WEAK, section=UND */ + return sym->st_shndx == SHN_UNDEF && + (bind == STB_GLOBAL || bind == STB_WEAK) && + GELF_ST_TYPE(sym->st_info) == STT_NOTYPE; +} + +static int find_extern_btf_id(const struct btf *btf, const char *ext_name) +{ + const struct btf_type *t; + const char *var_name; + int i, n; + + if (!btf) + return -ESRCH; + + n = btf__get_nr_types(btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(btf, i); + + if (!btf_is_var(t)) + continue; + + var_name = btf__name_by_offset(btf, t->name_off); + if (strcmp(var_name, ext_name)) + continue; + + if (btf_var(t)->linkage != BTF_VAR_GLOBAL_EXTERN) + return -EINVAL; + + return i; + } + + return -ENOENT; +} + +static enum extern_type find_extern_type(const struct btf *btf, int id, + bool *is_signed) +{ + const struct btf_type *t; + const char *name; + + t = skip_mods_and_typedefs(btf, id, NULL); + name = btf__name_by_offset(btf, t->name_off); + + if (is_signed) + *is_signed = false; + switch (btf_kind(t)) { + case BTF_KIND_INT: { + int enc = btf_int_encoding(t); + + if (enc & BTF_INT_BOOL) + return t->size == 1 ? EXT_BOOL : EXT_UNKNOWN; + if (is_signed) + *is_signed = enc & BTF_INT_SIGNED; + if (t->size == 1) + return EXT_CHAR; + if (t->size < 1 || t->size > 8 || (t->size & (t->size - 1))) + return EXT_UNKNOWN; + return EXT_INT; + } + case BTF_KIND_ENUM: + if (t->size != 4) + return EXT_UNKNOWN; + if (strcmp(name, "libbpf_tristate")) + return EXT_UNKNOWN; + return EXT_TRISTATE; + case BTF_KIND_ARRAY: + if (btf_array(t)->nelems == 0) + return EXT_UNKNOWN; + if (find_extern_type(btf, btf_array(t)->type, NULL) != EXT_CHAR) + return EXT_UNKNOWN; + return EXT_CHAR_ARR; + default: + return EXT_UNKNOWN; + } +} + +static int cmp_externs(const void *_a, const void *_b) +{ + const struct extern_desc *a = _a; + const struct extern_desc *b = _b; + + /* descending order by alignment requirements */ + if (a->align != b->align) + return a->align > b->align ? -1 : 1; + /* ascending order by size, within same alignment class */ + if (a->sz != b->sz) + return a->sz < b->sz ? -1 : 1; + /* resolve ties by name */ + return strcmp(a->name, b->name); +} + +static int bpf_object__collect_externs(struct bpf_object *obj) +{ + const struct btf_type *t; + struct extern_desc *ext; + int i, n, off, btf_id; + struct btf_type *sec; + const char *ext_name; + Elf_Scn *scn; + GElf_Shdr sh; + + if (!obj->efile.symbols) + return 0; + + scn = elf_getscn(obj->efile.elf, obj->efile.symbols_shndx); + if (!scn) + return -LIBBPF_ERRNO__FORMAT; + if (gelf_getshdr(scn, &sh) != &sh) + return -LIBBPF_ERRNO__FORMAT; + n = sh.sh_size / sh.sh_entsize; + + pr_debug("looking for externs among %d symbols...\n", n); + for (i = 0; i < n; i++) { + GElf_Sym sym; + + if (!gelf_getsym(obj->efile.symbols, i, &sym)) + return -LIBBPF_ERRNO__FORMAT; + if (!sym_is_extern(&sym)) + continue; + ext_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + if (!ext_name || !ext_name[0]) + continue; + + ext = obj->externs; + ext = reallocarray(ext, obj->nr_extern + 1, sizeof(*ext)); + if (!ext) + return -ENOMEM; + obj->externs = ext; + ext = &ext[obj->nr_extern]; + memset(ext, 0, sizeof(*ext)); + obj->nr_extern++; + + ext->btf_id = find_extern_btf_id(obj->btf, ext_name); + if (ext->btf_id <= 0) { + pr_warn("failed to find BTF for extern '%s': %d\n", + ext_name, ext->btf_id); + return ext->btf_id; + } + t = btf__type_by_id(obj->btf, ext->btf_id); + ext->name = btf__name_by_offset(obj->btf, t->name_off); + ext->sym_idx = i; + ext->is_weak = GELF_ST_BIND(sym.st_info) == STB_WEAK; + ext->sz = btf__resolve_size(obj->btf, t->type); + if (ext->sz <= 0) { + pr_warn("failed to resolve size of extern '%s': %d\n", + ext_name, ext->sz); + return ext->sz; + } + ext->align = btf__align_of(obj->btf, t->type); + if (ext->align <= 0) { + pr_warn("failed to determine alignment of extern '%s': %d\n", + ext_name, ext->align); + return -EINVAL; + } + ext->type = find_extern_type(obj->btf, t->type, + &ext->is_signed); + if (ext->type == EXT_UNKNOWN) { + pr_warn("extern '%s' type is unsupported\n", ext_name); + return -ENOTSUP; + } + } + pr_debug("collected %d externs total\n", obj->nr_extern); + + if (!obj->nr_extern) + return 0; + + /* sort externs by (alignment, size, name) and calculate their offsets + * within a map */ + qsort(obj->externs, obj->nr_extern, sizeof(*ext), cmp_externs); + off = 0; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + ext->data_off = roundup(off, ext->align); + off = ext->data_off + ext->sz; + pr_debug("extern #%d: symbol %d, off %u, name %s\n", + i, ext->sym_idx, ext->data_off, ext->name); + } + + btf_id = btf__find_by_name(obj->btf, KCONFIG_SEC); + if (btf_id <= 0) { + pr_warn("no BTF info found for '%s' datasec\n", KCONFIG_SEC); + return -ESRCH; + } + + sec = (struct btf_type *)btf__type_by_id(obj->btf, btf_id); + sec->size = off; + n = btf_vlen(sec); + for (i = 0; i < n; i++) { + struct btf_var_secinfo *vs = btf_var_secinfos(sec) + i; + + t = btf__type_by_id(obj->btf, vs->type); + ext_name = btf__name_by_offset(obj->btf, t->name_off); + ext = find_extern_by_name(obj, ext_name); + if (!ext) { + pr_warn("failed to find extern definition for BTF var '%s'\n", + ext_name); + return -ESRCH; + } + vs->offset = ext->data_off; + btf_var(t)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + } + + return 0; } static struct bpf_program * @@ -1765,6 +2368,19 @@ bpf_object__find_program_by_title(const struct bpf_object *obj, return NULL; } +struct bpf_program * +bpf_object__find_program_by_name(const struct bpf_object *obj, + const char *name) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + if (!strcmp(prog->name, name)) + return prog; + } + return NULL; +} + static bool bpf_object__shndx_is_data(const struct bpf_object *obj, int shndx) { @@ -1789,6 +2405,8 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) return LIBBPF_MAP_BSS; else if (shndx == obj->efile.rodata_shndx) return LIBBPF_MAP_RODATA; + else if (shndx == obj->efile.symbols_shndx) + return LIBBPF_MAP_KCONFIG; else return LIBBPF_MAP_UNSPEC; } @@ -1817,7 +2435,8 @@ static int bpf_program__record_reloc(struct bpf_program *prog, return -LIBBPF_ERRNO__RELOC; } if (sym->st_value % 8) { - pr_warn("bad call relo offset: %llu\n", (__u64)sym->st_value); + pr_warn("bad call relo offset: %zu\n", + (size_t)sym->st_value); return -LIBBPF_ERRNO__RELOC; } reloc_desc->type = RELO_CALL; @@ -1832,6 +2451,30 @@ static int bpf_program__record_reloc(struct bpf_program *prog, insn_idx, insn->code); return -LIBBPF_ERRNO__RELOC; } + + if (sym_is_extern(sym)) { + int sym_idx = GELF_R_SYM(rel->r_info); + int i, n = obj->nr_extern; + struct extern_desc *ext; + + for (i = 0; i < n; i++) { + ext = &obj->externs[i]; + if (ext->sym_idx == sym_idx) + break; + } + if (i >= n) { + pr_warn("extern relo failed to find extern for sym %d\n", + sym_idx); + return -LIBBPF_ERRNO__RELOC; + } + pr_debug("found extern #%d '%s' (sym %d, off %u) for insn %u\n", + i, ext->name, ext->sym_idx, ext->data_off, insn_idx); + reloc_desc->type = RELO_EXTERN; + reloc_desc->insn_idx = insn_idx; + reloc_desc->sym_off = ext->data_off; + return 0; + } + if (!shdr_idx || shdr_idx >= SHN_LORESERVE) { pr_warn("invalid relo for \'%s\' in special section 0x%x; forgot to initialize global var?..\n", name, shdr_idx); @@ -1859,8 +2502,8 @@ static int bpf_program__record_reloc(struct bpf_program *prog, break; } if (map_idx >= nr_maps) { - pr_warn("map relo failed to find map for sec %u, off %llu\n", - shdr_idx, (__u64)sym->st_value); + pr_warn("map relo failed to find map for sec %u, off %zu\n", + shdr_idx, (size_t)sym->st_value); return -LIBBPF_ERRNO__RELOC; } reloc_desc->type = RELO_LD64; @@ -1875,11 +2518,6 @@ static int bpf_program__record_reloc(struct bpf_program *prog, pr_warn("bad data relo against section %u\n", shdr_idx); return -LIBBPF_ERRNO__RELOC; } - if (!obj->caps.global_data) { - pr_warn("relocation: kernel does not support global \'%s\' variable access in insns[%d]\n", - name, insn_idx); - return -LIBBPF_ERRNO__RELOC; - } for (map_idx = 0; map_idx < nr_maps; map_idx++) { map = &obj->maps[map_idx]; if (map->libbpf_type != type) @@ -1941,9 +2579,9 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name) ? : "<?>"; - pr_debug("relo for shdr %u, symb %llu, value %llu, type %d, bind %d, name %d (\'%s\'), insn %u\n", - (__u32)sym.st_shndx, (__u64)GELF_R_SYM(rel.r_info), - (__u64)sym.st_value, GELF_ST_TYPE(sym.st_info), + pr_debug("relo for shdr %u, symb %zu, value %zu, type %d, bind %d, name %d (\'%s\'), insn %u\n", + (__u32)sym.st_shndx, (size_t)GELF_R_SYM(rel.r_info), + (size_t)sym.st_value, GELF_ST_TYPE(sym.st_info), GELF_ST_BIND(sym.st_info), sym.st_name, name, insn_idx); @@ -2298,29 +2936,35 @@ bpf_object__reuse_map(struct bpf_map *map) static int bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) { + enum libbpf_map_type map_type = map->libbpf_type; char *cp, errmsg[STRERR_BUFSIZE]; int err, zero = 0; - __u8 *data; - /* Nothing to do here since kernel already zero-initializes .bss map. */ - if (map->libbpf_type == LIBBPF_MAP_BSS) + /* kernel already zero-initializes .bss map. */ + if (map_type == LIBBPF_MAP_BSS) return 0; - data = map->libbpf_type == LIBBPF_MAP_DATA ? - obj->sections.data : obj->sections.rodata; + err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0); + if (err) { + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error setting initial map(%s) contents: %s\n", + map->name, cp); + return err; + } - err = bpf_map_update_elem(map->fd, &zero, data, 0); - /* Freeze .rodata map as read-only from syscall side. */ - if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) { + /* Freeze .rodata and .kconfig map as read-only from syscall side. */ + if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG) { err = bpf_map_freeze(map->fd); if (err) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("Error freezing map(%s) as read-only: %s\n", map->name, cp); - err = 0; + return err; } } - return err; + return 0; } static int @@ -2411,6 +3055,7 @@ err_out: cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("failed to create map (name: '%s'): %s(%d)\n", map->name, cp, err); + pr_perm_msg(err); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; @@ -2536,6 +3181,21 @@ static bool str_is_empty(const char *s) return !s || !s[0]; } +static bool is_flex_arr(const struct btf *btf, + const struct bpf_core_accessor *acc, + const struct btf_array *arr) +{ + const struct btf_type *t; + + /* not a flexible array, if not inside a struct or has non-zero size */ + if (!acc->name || arr->nelems > 0) + return false; + + /* has to be the last member of enclosing struct */ + t = btf__type_by_id(btf, acc->type_id); + return acc->idx == btf_vlen(t) - 1; +} + /* * Turn bpf_field_reloc into a low- and high-level spec representation, * validating correctness along the way, as well as calculating resulting @@ -2573,6 +3233,7 @@ static int bpf_core_spec_parse(const struct btf *btf, struct bpf_core_spec *spec) { int access_idx, parsed_len, i; + struct bpf_core_accessor *acc; const struct btf_type *t; const char *name; __u32 id; @@ -2620,6 +3281,7 @@ static int bpf_core_spec_parse(const struct btf *btf, return -EINVAL; access_idx = spec->raw_spec[i]; + acc = &spec->spec[spec->len]; if (btf_is_composite(t)) { const struct btf_member *m; @@ -2637,18 +3299,23 @@ static int bpf_core_spec_parse(const struct btf *btf, if (str_is_empty(name)) return -EINVAL; - spec->spec[spec->len].type_id = id; - spec->spec[spec->len].idx = access_idx; - spec->spec[spec->len].name = name; + acc->type_id = id; + acc->idx = access_idx; + acc->name = name; spec->len++; } id = m->type; } else if (btf_is_array(t)) { const struct btf_array *a = btf_array(t); + bool flex; t = skip_mods_and_typedefs(btf, a->type, &id); - if (!t || access_idx >= a->nelems) + if (!t) + return -EINVAL; + + flex = is_flex_arr(btf, acc - 1, a); + if (!flex && access_idx >= a->nelems) return -EINVAL; spec->spec[spec->len].type_id = id; @@ -2953,12 +3620,14 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, */ if (i > 0) { const struct btf_array *a; + bool flex; if (!btf_is_array(targ_type)) return 0; a = btf_array(targ_type); - if (local_acc->idx >= a->nelems) + flex = is_flex_arr(targ_btf, targ_acc - 1, a); + if (!flex && local_acc->idx >= a->nelems) return 0; if (!skip_mods_and_typedefs(targ_btf, a->type, &targ_id)) @@ -3142,11 +3811,13 @@ static int bpf_core_reloc_insn(struct bpf_program *prog, insn = &prog->insns[insn_idx]; class = BPF_CLASS(insn->code); - if (class == BPF_ALU || class == BPF_ALU64) { + switch (class) { + case BPF_ALU: + case BPF_ALU64: if (BPF_SRC(insn->code) != BPF_K) return -EINVAL; if (!failed && validate && insn->imm != orig_val) { - pr_warn("prog '%s': unexpected insn #%d value: got %u, exp %u -> %u\n", + pr_warn("prog '%s': unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n", bpf_program__title(prog, false), insn_idx, insn->imm, orig_val, new_val); return -EINVAL; @@ -3156,7 +3827,29 @@ static int bpf_core_reloc_insn(struct bpf_program *prog, pr_debug("prog '%s': patched insn #%d (ALU/ALU64)%s imm %u -> %u\n", bpf_program__title(prog, false), insn_idx, failed ? " w/ failed reloc" : "", orig_val, new_val); - } else { + break; + case BPF_LDX: + case BPF_ST: + case BPF_STX: + if (!failed && validate && insn->off != orig_val) { + pr_warn("prog '%s': unexpected insn #%d (LD/LDX/ST/STX) value: got %u, exp %u -> %u\n", + bpf_program__title(prog, false), insn_idx, + insn->off, orig_val, new_val); + return -EINVAL; + } + if (new_val > SHRT_MAX) { + pr_warn("prog '%s': insn #%d (LD/LDX/ST/STX) value too big: %u\n", + bpf_program__title(prog, false), insn_idx, + new_val); + return -ERANGE; + } + orig_val = insn->off; + insn->off = new_val; + pr_debug("prog '%s': patched insn #%d (LD/LDX/ST/STX)%s off %u -> %u\n", + bpf_program__title(prog, false), insn_idx, + failed ? " w/ failed reloc" : "", orig_val, new_val); + break; + default: pr_warn("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", bpf_program__title(prog, false), insn_idx, insn->code, insn->src_reg, insn->dst_reg, @@ -3559,9 +4252,6 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, size_t new_cnt; int err; - if (relo->type != RELO_CALL) - return -LIBBPF_ERRNO__RELOC; - if (prog->idx == obj->efile.text_shndx) { pr_warn("relo in .text insn %d into off %d (insn #%d)\n", relo->insn_idx, relo->sym_off, relo->sym_off / 8); @@ -3623,27 +4313,37 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) for (i = 0; i < prog->nr_reloc; i++) { struct reloc_desc *relo = &prog->reloc_desc[i]; + struct bpf_insn *insn = &prog->insns[relo->insn_idx]; - if (relo->type == RELO_LD64 || relo->type == RELO_DATA) { - struct bpf_insn *insn = &prog->insns[relo->insn_idx]; - - if (relo->insn_idx + 1 >= (int)prog->insns_cnt) { - pr_warn("relocation out of range: '%s'\n", - prog->section_name); - return -LIBBPF_ERRNO__RELOC; - } + if (relo->insn_idx + 1 >= (int)prog->insns_cnt) { + pr_warn("relocation out of range: '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__RELOC; + } - if (relo->type != RELO_DATA) { - insn[0].src_reg = BPF_PSEUDO_MAP_FD; - } else { - insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; - insn[1].imm = insn[0].imm + relo->sym_off; - } + switch (relo->type) { + case RELO_LD64: + insn[0].src_reg = BPF_PSEUDO_MAP_FD; + insn[0].imm = obj->maps[relo->map_idx].fd; + break; + case RELO_DATA: + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[1].imm = insn[0].imm + relo->sym_off; insn[0].imm = obj->maps[relo->map_idx].fd; - } else if (relo->type == RELO_CALL) { + break; + case RELO_EXTERN: + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[0].imm = obj->maps[obj->kconfig_map_idx].fd; + insn[1].imm = relo->sym_off; + break; + case RELO_CALL: err = bpf_program__reloc_text(prog, obj, relo); if (err) return err; + break; + default: + pr_warn("relo #%d: bad relo type %d\n", i, relo->type); + return -EINVAL; } } @@ -3778,6 +4478,7 @@ retry_load: ret = -errno; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warn("load bpf program failed: %s\n", cp); + pr_perm_msg(ret); if (log_buf && log_buf[0] != '\0') { ret = -LIBBPF_ERRNO__VERIFY; @@ -3807,11 +4508,22 @@ out: return ret; } -int -bpf_program__load(struct bpf_program *prog, - char *license, __u32 kern_version) +static int libbpf_find_attach_btf_id(const char *name, + enum bpf_attach_type attach_type, + __u32 attach_prog_fd); + +int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) { - int err = 0, fd, i; + int err = 0, fd, i, btf_id; + + if (prog->type == BPF_PROG_TYPE_TRACING) { + btf_id = libbpf_find_attach_btf_id(prog->section_name, + prog->expected_attach_type, + prog->attach_prog_fd); + if (btf_id <= 0) + return btf_id; + prog->attach_btf_id = btf_id; + } if (prog->instances.nr < 0 || !prog->instances.fds) { if (prog->preprocessor) { @@ -3835,7 +4547,7 @@ bpf_program__load(struct bpf_program *prog, prog->section_name, prog->instances.nr); } err = load_program(prog, prog->insns, prog->insns_cnt, - license, kern_version, &fd); + license, kern_ver, &fd); if (!err) prog->instances.fds[0] = fd; goto out; @@ -3864,9 +4576,7 @@ bpf_program__load(struct bpf_program *prog, } err = load_program(prog, result.new_insn_ptr, - result.new_insn_cnt, - license, kern_version, &fd); - + result.new_insn_cnt, license, kern_ver, &fd); if (err) { pr_warn("Loading the %dth instance of program '%s' failed\n", i, prog->section_name); @@ -3910,20 +4620,14 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) return 0; } -static int libbpf_find_attach_btf_id(const char *name, - enum bpf_attach_type attach_type, - __u32 attach_prog_fd); static struct bpf_object * __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, - struct bpf_object_open_opts *opts) + const struct bpf_object_open_opts *opts) { - const char *pin_root_path; + const char *obj_name, *kconfig; struct bpf_program *prog; struct bpf_object *obj; - const char *obj_name; char tmp_name[64]; - bool relaxed_maps; - __u32 attach_prog_fd; int err; if (elf_version(EV_CURRENT) == EV_NONE) { @@ -3952,16 +4656,23 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, return obj; obj->relaxed_core_relocs = OPTS_GET(opts, relaxed_core_relocs, false); - relaxed_maps = OPTS_GET(opts, relaxed_maps, false); - pin_root_path = OPTS_GET(opts, pin_root_path, NULL); - attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); - - CHECK_ERR(bpf_object__elf_init(obj), err, out); - CHECK_ERR(bpf_object__check_endianness(obj), err, out); - CHECK_ERR(bpf_object__probe_caps(obj), err, out); - CHECK_ERR(bpf_object__elf_collect(obj, relaxed_maps, pin_root_path), - err, out); - CHECK_ERR(bpf_object__collect_reloc(obj), err, out); + kconfig = OPTS_GET(opts, kconfig, NULL); + if (kconfig) { + obj->kconfig = strdup(kconfig); + if (!obj->kconfig) + return ERR_PTR(-ENOMEM); + } + + err = bpf_object__elf_init(obj); + err = err ? : bpf_object__check_endianness(obj); + err = err ? : bpf_object__elf_collect(obj); + err = err ? : bpf_object__collect_externs(obj); + err = err ? : bpf_object__finalize_btf(obj); + err = err ? : bpf_object__init_maps(obj, opts); + err = err ? : bpf_object__init_prog_names(obj); + err = err ? : bpf_object__collect_reloc(obj); + if (err) + goto out; bpf_object__elf_finish(obj); bpf_object__for_each_program(prog, obj) { @@ -3978,15 +4689,8 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, bpf_program__set_type(prog, prog_type); bpf_program__set_expected_attach_type(prog, attach_type); - if (prog_type == BPF_PROG_TYPE_TRACING) { - err = libbpf_find_attach_btf_id(prog->section_name, - attach_type, - attach_prog_fd); - if (err <= 0) - goto out; - prog->attach_btf_id = err; - prog->attach_prog_fd = attach_prog_fd; - } + if (prog_type == BPF_PROG_TYPE_TRACING) + prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); } return obj; @@ -4026,7 +4730,7 @@ struct bpf_object *bpf_object__open(const char *path) } struct bpf_object * -bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts) +bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) { if (!path) return ERR_PTR(-EINVAL); @@ -4038,7 +4742,7 @@ bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts) struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, - struct bpf_object_open_opts *opts) + const struct bpf_object_open_opts *opts) { if (!obj_buf || obj_buf_sz == 0) return ERR_PTR(-EINVAL); @@ -4079,6 +4783,92 @@ int bpf_object__unload(struct bpf_object *obj) return 0; } +static int bpf_object__sanitize_maps(struct bpf_object *obj) +{ + struct bpf_map *m; + + bpf_object__for_each_map(m, obj) { + if (!bpf_map__is_internal(m)) + continue; + if (!obj->caps.global_data) { + pr_warn("kernel doesn't support global data\n"); + return -ENOTSUP; + } + if (!obj->caps.array_mmap) + m->def.map_flags ^= BPF_F_MMAPABLE; + } + + return 0; +} + +static int bpf_object__resolve_externs(struct bpf_object *obj, + const char *extra_kconfig) +{ + bool need_config = false; + struct extern_desc *ext; + int err, i; + void *data; + + if (obj->nr_extern == 0) + return 0; + + data = obj->maps[obj->kconfig_map_idx].mmaped; + + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + + if (strcmp(ext->name, "LINUX_KERNEL_VERSION") == 0) { + void *ext_val = data + ext->data_off; + __u32 kver = get_kernel_version(); + + if (!kver) { + pr_warn("failed to get kernel version\n"); + return -EINVAL; + } + err = set_ext_value_num(ext, ext_val, kver); + if (err) + return err; + pr_debug("extern %s=0x%x\n", ext->name, kver); + } else if (strncmp(ext->name, "CONFIG_", 7) == 0) { + need_config = true; + } else { + pr_warn("unrecognized extern '%s'\n", ext->name); + return -EINVAL; + } + } + if (need_config && extra_kconfig) { + err = bpf_object__read_kconfig_mem(obj, extra_kconfig, data); + if (err) + return -EINVAL; + need_config = false; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (!ext->is_set) { + need_config = true; + break; + } + } + } + if (need_config) { + err = bpf_object__read_kconfig_file(obj, data); + if (err) + return -EINVAL; + } + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + + if (!ext->is_set && !ext->is_weak) { + pr_warn("extern %s (strong) not resolved\n", ext->name); + return -ESRCH; + } else if (!ext->is_set) { + pr_debug("extern %s (weak) not resolved, defaulting to zero\n", + ext->name); + } + } + + return 0; +} + int bpf_object__load_xattr(struct bpf_object_load_attr *attr) { struct bpf_object *obj; @@ -4097,9 +4887,15 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) obj->loaded = true; - CHECK_ERR(bpf_object__create_maps(obj), err, out); - CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out); - CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); + err = bpf_object__probe_caps(obj); + err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); + err = err ? : bpf_object__sanitize_and_load_btf(obj); + err = err ? : bpf_object__sanitize_maps(obj); + err = err ? : bpf_object__create_maps(obj); + err = err ? : bpf_object__relocate(obj, attr->target_btf_path); + err = err ? : bpf_object__load_progs(obj, attr->log_level); + if (err) + goto out; return 0; out: @@ -4670,17 +5466,26 @@ void bpf_object__close(struct bpf_object *obj) btf_ext__free(obj->btf_ext); for (i = 0; i < obj->nr_maps; i++) { - zfree(&obj->maps[i].name); - zfree(&obj->maps[i].pin_path); - if (obj->maps[i].clear_priv) - obj->maps[i].clear_priv(&obj->maps[i], - obj->maps[i].priv); - obj->maps[i].priv = NULL; - obj->maps[i].clear_priv = NULL; + struct bpf_map *map = &obj->maps[i]; + + if (map->clear_priv) + map->clear_priv(map, map->priv); + map->priv = NULL; + map->clear_priv = NULL; + + if (map->mmaped) { + munmap(map->mmaped, bpf_map_mmap_sz(map)); + map->mmaped = NULL; + } + + zfree(&map->name); + zfree(&map->pin_path); } - zfree(&obj->sections.rodata); - zfree(&obj->sections.data); + zfree(&obj->kconfig); + zfree(&obj->externs); + obj->nr_extern = 0; + zfree(&obj->maps); obj->nr_maps = 0; @@ -4820,6 +5625,11 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) prog->prog_ifindex = ifindex; } +const char *bpf_program__name(const struct bpf_program *prog) +{ + return prog->name; +} + const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) { const char *title; @@ -4972,7 +5782,28 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, */ #define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype) -static const struct { +#define SEC_DEF(sec_pfx, ptype, ...) { \ + .sec = sec_pfx, \ + .len = sizeof(sec_pfx) - 1, \ + .prog_type = BPF_PROG_TYPE_##ptype, \ + __VA_ARGS__ \ +} + +struct bpf_sec_def; + +typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec, + struct bpf_program *prog); + +static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, + struct bpf_program *prog); +static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog); +static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog); +static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, + struct bpf_program *prog); + +struct bpf_sec_def { const char *sec; size_t len; enum bpf_prog_type prog_type; @@ -4980,24 +5811,40 @@ static const struct { bool is_attachable; bool is_attach_btf; enum bpf_attach_type attach_type; -} section_names[] = { + attach_fn_t attach_fn; +}; + +static const struct bpf_sec_def section_defs[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), - BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT), + SEC_DEF("kprobe/", KPROBE, + .attach_fn = attach_kprobe), BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), - BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE), + SEC_DEF("kretprobe/", KPROBE, + .attach_fn = attach_kprobe), BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), - BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), - BPF_PROG_SEC("tp/", BPF_PROG_TYPE_TRACEPOINT), - BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), - BPF_PROG_SEC("raw_tp/", BPF_PROG_TYPE_RAW_TRACEPOINT), - BPF_PROG_BTF("tp_btf/", BPF_PROG_TYPE_TRACING, - BPF_TRACE_RAW_TP), - BPF_PROG_BTF("fentry/", BPF_PROG_TYPE_TRACING, - BPF_TRACE_FENTRY), - BPF_PROG_BTF("fexit/", BPF_PROG_TYPE_TRACING, - BPF_TRACE_FEXIT), + SEC_DEF("tracepoint/", TRACEPOINT, + .attach_fn = attach_tp), + SEC_DEF("tp/", TRACEPOINT, + .attach_fn = attach_tp), + SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, + .attach_fn = attach_raw_tp), + SEC_DEF("raw_tp/", RAW_TRACEPOINT, + .attach_fn = attach_raw_tp), + SEC_DEF("tp_btf/", TRACING, + .expected_attach_type = BPF_TRACE_RAW_TP, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("fentry/", TRACING, + .expected_attach_type = BPF_TRACE_FENTRY, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("fexit/", TRACING, + .expected_attach_type = BPF_TRACE_FEXIT, + .is_attach_btf = true, + .attach_fn = attach_trace), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), @@ -5059,12 +5906,26 @@ static const struct { #undef BPF_APROG_SEC #undef BPF_EAPROG_SEC #undef BPF_APROG_COMPAT +#undef SEC_DEF #define MAX_TYPE_NAME_SIZE 32 +static const struct bpf_sec_def *find_sec_def(const char *sec_name) +{ + int i, n = ARRAY_SIZE(section_defs); + + for (i = 0; i < n; i++) { + if (strncmp(sec_name, + section_defs[i].sec, section_defs[i].len)) + continue; + return §ion_defs[i]; + } + return NULL; +} + static char *libbpf_get_type_names(bool attach_type) { - int i, len = ARRAY_SIZE(section_names) * MAX_TYPE_NAME_SIZE; + int i, len = ARRAY_SIZE(section_defs) * MAX_TYPE_NAME_SIZE; char *buf; buf = malloc(len); @@ -5073,16 +5934,16 @@ static char *libbpf_get_type_names(bool attach_type) buf[0] = '\0'; /* Forge string buf with all available names */ - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (attach_type && !section_names[i].is_attachable) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (attach_type && !section_defs[i].is_attachable) continue; - if (strlen(buf) + strlen(section_names[i].sec) + 2 > len) { + if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) { free(buf); return NULL; } strcat(buf, " "); - strcat(buf, section_names[i].sec); + strcat(buf, section_defs[i].sec); } return buf; @@ -5091,23 +5952,23 @@ static char *libbpf_get_type_names(bool attach_type) int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, enum bpf_attach_type *expected_attach_type) { + const struct bpf_sec_def *sec_def; char *type_names; - int i; if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (strncmp(name, section_names[i].sec, section_names[i].len)) - continue; - *prog_type = section_names[i].prog_type; - *expected_attach_type = section_names[i].expected_attach_type; + sec_def = find_sec_def(name); + if (sec_def) { + *prog_type = sec_def->prog_type; + *expected_attach_type = sec_def->expected_attach_type; return 0; } - pr_warn("failed to guess program type from ELF section '%s'\n", name); + + pr_debug("failed to guess program type from ELF section '%s'\n", name); type_names = libbpf_get_type_names(false); if (type_names != NULL) { - pr_info("supported section(type) names are:%s\n", type_names); + pr_debug("supported section(type) names are:%s\n", type_names); free(type_names); } @@ -5186,16 +6047,16 @@ static int libbpf_find_attach_btf_id(const char *name, if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (!section_names[i].is_attach_btf) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (!section_defs[i].is_attach_btf) continue; - if (strncmp(name, section_names[i].sec, section_names[i].len)) + if (strncmp(name, section_defs[i].sec, section_defs[i].len)) continue; if (attach_prog_fd) - err = libbpf_find_prog_btf_id(name + section_names[i].len, + err = libbpf_find_prog_btf_id(name + section_defs[i].len, attach_prog_fd); else - err = libbpf_find_vmlinux_btf_id(name + section_names[i].len, + err = libbpf_find_vmlinux_btf_id(name + section_defs[i].len, attach_type); if (err <= 0) pr_warn("%s is not found in vmlinux BTF\n", name); @@ -5214,18 +6075,18 @@ int libbpf_attach_type_by_name(const char *name, if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (strncmp(name, section_names[i].sec, section_names[i].len)) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (strncmp(name, section_defs[i].sec, section_defs[i].len)) continue; - if (!section_names[i].is_attachable) + if (!section_defs[i].is_attachable) return -EINVAL; - *attach_type = section_names[i].attach_type; + *attach_type = section_defs[i].attach_type; return 0; } - pr_warn("failed to guess attach type based on ELF section name '%s'\n", name); + pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); type_names = libbpf_get_type_names(true); if (type_names != NULL) { - pr_info("attachable section(type) names are:%s\n", type_names); + pr_debug("attachable section(type) names are:%s\n", type_names); free(type_names); } @@ -5466,17 +6327,37 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, } struct bpf_link { + int (*detach)(struct bpf_link *link); int (*destroy)(struct bpf_link *link); + bool disconnected; }; +/* Release "ownership" of underlying BPF resource (typically, BPF program + * attached to some BPF hook, e.g., tracepoint, kprobe, etc). Disconnected + * link, when destructed through bpf_link__destroy() call won't attempt to + * detach/unregisted that BPF resource. This is useful in situations where, + * say, attached BPF program has to outlive userspace program that attached it + * in the system. Depending on type of BPF program, though, there might be + * additional steps (like pinning BPF program in BPF FS) necessary to ensure + * exit of userspace program doesn't trigger automatic detachment and clean up + * inside the kernel. + */ +void bpf_link__disconnect(struct bpf_link *link) +{ + link->disconnected = true; +} + int bpf_link__destroy(struct bpf_link *link) { - int err; + int err = 0; if (!link) return 0; - err = link->destroy(link); + if (!link->disconnected && link->detach) + err = link->detach(link); + if (link->destroy) + link->destroy(link); free(link); return err; @@ -5487,7 +6368,7 @@ struct bpf_link_fd { int fd; /* hook FD */ }; -static int bpf_link__destroy_perf_event(struct bpf_link *link) +static int bpf_link__detach_perf_event(struct bpf_link *link) { struct bpf_link_fd *l = (void *)link; int err; @@ -5519,10 +6400,10 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, return ERR_PTR(-EINVAL); } - link = malloc(sizeof(*link)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_perf_event; + link->link.detach = &bpf_link__detach_perf_event; link->fd = pfd; if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { @@ -5679,6 +6560,18 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, return link; } +static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + const char *func_name; + bool retprobe; + + func_name = bpf_program__title(prog, false) + sec->len; + retprobe = strcmp(sec->sec, "kretprobe/") == 0; + + return bpf_program__attach_kprobe(prog, retprobe, func_name); +} + struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, @@ -5791,7 +6684,33 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, return link; } -static int bpf_link__destroy_fd(struct bpf_link *link) +static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + char *sec_name, *tp_cat, *tp_name; + struct bpf_link *link; + + sec_name = strdup(bpf_program__title(prog, false)); + if (!sec_name) + return ERR_PTR(-ENOMEM); + + /* extract "tp/<category>/<name>" */ + tp_cat = sec_name + sec->len; + tp_name = strchr(tp_cat, '/'); + if (!tp_name) { + link = ERR_PTR(-EINVAL); + goto out; + } + *tp_name = '\0'; + tp_name++; + + link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); +out: + free(sec_name); + return link; +} + +static int bpf_link__detach_fd(struct bpf_link *link) { struct bpf_link_fd *l = (void *)link; @@ -5812,10 +6731,10 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, return ERR_PTR(-EINVAL); } - link = malloc(sizeof(*link)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_fd; + link->link.detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); if (pfd < 0) { @@ -5830,6 +6749,14 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, return (struct bpf_link *)link; } +static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + const char *tp_name = bpf_program__title(prog, false) + sec->len; + + return bpf_program__attach_raw_tracepoint(prog, tp_name); +} + struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) { char errmsg[STRERR_BUFSIZE]; @@ -5843,10 +6770,10 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) return ERR_PTR(-EINVAL); } - link = malloc(sizeof(*link)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_fd; + link->link.detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(NULL, prog_fd); if (pfd < 0) { @@ -5861,6 +6788,23 @@ struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) return (struct bpf_link *)link; } +static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + return bpf_program__attach_trace(prog); +} + +struct bpf_link *bpf_program__attach(struct bpf_program *prog) +{ + const struct bpf_sec_def *sec_def; + + sec_def = find_sec_def(bpf_program__title(prog, false)); + if (!sec_def || !sec_def->attach_fn) + return ERR_PTR(-ESRCH); + + return sec_def->attach_fn(sec_def, prog); +} + enum bpf_perf_event_ret bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, @@ -5944,7 +6888,7 @@ struct perf_buffer { size_t mmap_size; struct perf_cpu_buf **cpu_bufs; struct epoll_event *events; - int cpu_cnt; + int cpu_cnt; /* number of allocated CPU buffers */ int epoll_fd; /* perf event FD */ int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */ }; @@ -6078,11 +7022,13 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt, static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, struct perf_buffer_params *p) { + const char *online_cpus_file = "/sys/devices/system/cpu/online"; struct bpf_map_info map = {}; char msg[STRERR_BUFSIZE]; struct perf_buffer *pb; + bool *online = NULL; __u32 map_info_len; - int err, i; + int err, i, j, n; if (page_cnt & (page_cnt - 1)) { pr_warn("page count should be power of two, but is %zu\n", @@ -6151,20 +7097,32 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, goto error; } - for (i = 0; i < pb->cpu_cnt; i++) { + err = parse_cpu_mask_file(online_cpus_file, &online, &n); + if (err) { + pr_warn("failed to get online CPU mask: %d\n", err); + goto error; + } + + for (i = 0, j = 0; i < pb->cpu_cnt; i++) { struct perf_cpu_buf *cpu_buf; int cpu, map_key; cpu = p->cpu_cnt > 0 ? p->cpus[i] : i; map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i; + /* in case user didn't explicitly requested particular CPUs to + * be attached to, skip offline/not present CPUs + */ + if (p->cpu_cnt <= 0 && (cpu >= n || !online[cpu])) + continue; + cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key); if (IS_ERR(cpu_buf)) { err = PTR_ERR(cpu_buf); goto error; } - pb->cpu_bufs[i] = cpu_buf; + pb->cpu_bufs[j] = cpu_buf; err = bpf_map_update_elem(pb->map_fd, &map_key, &cpu_buf->fd, 0); @@ -6176,21 +7134,25 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, goto error; } - pb->events[i].events = EPOLLIN; - pb->events[i].data.ptr = cpu_buf; + pb->events[j].events = EPOLLIN; + pb->events[j].data.ptr = cpu_buf; if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd, - &pb->events[i]) < 0) { + &pb->events[j]) < 0) { err = -errno; pr_warn("failed to epoll_ctl cpu #%d perf FD %d: %s\n", cpu, cpu_buf->fd, libbpf_strerror_r(err, msg, sizeof(msg))); goto error; } + j++; } + pb->cpu_cnt = j; + free(online); return pb; error: + free(online); if (pb) perf_buffer__free(pb); return ERR_PTR(err); @@ -6521,62 +7483,267 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) } } -int libbpf_num_possible_cpus(void) +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz) { - static const char *fcpu = "/sys/devices/system/cpu/possible"; - int len = 0, n = 0, il = 0, ir = 0; - unsigned int start = 0, end = 0; - int tmp_cpus = 0; - static int cpus; - char buf[128]; - int error = 0; - int fd = -1; + int err = 0, n, len, start, end = -1; + bool *tmp; - tmp_cpus = READ_ONCE(cpus); - if (tmp_cpus > 0) - return tmp_cpus; + *mask = NULL; + *mask_sz = 0; + + /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ + while (*s) { + if (*s == ',' || *s == '\n') { + s++; + continue; + } + n = sscanf(s, "%d%n-%d%n", &start, &len, &end, &len); + if (n <= 0 || n > 2) { + pr_warn("Failed to get CPU range %s: %d\n", s, n); + err = -EINVAL; + goto cleanup; + } else if (n == 1) { + end = start; + } + if (start < 0 || start > end) { + pr_warn("Invalid CPU range [%d,%d] in %s\n", + start, end, s); + err = -EINVAL; + goto cleanup; + } + tmp = realloc(*mask, end + 1); + if (!tmp) { + err = -ENOMEM; + goto cleanup; + } + *mask = tmp; + memset(tmp + *mask_sz, 0, start - *mask_sz); + memset(tmp + start, 1, end - start + 1); + *mask_sz = end + 1; + s += len; + } + if (!*mask_sz) { + pr_warn("Empty CPU range\n"); + return -EINVAL; + } + return 0; +cleanup: + free(*mask); + *mask = NULL; + return err; +} + +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz) +{ + int fd, err = 0, len; + char buf[128]; fd = open(fcpu, O_RDONLY); if (fd < 0) { - error = errno; - pr_warn("Failed to open file %s: %s\n", fcpu, strerror(error)); - return -error; + err = -errno; + pr_warn("Failed to open cpu mask file %s: %d\n", fcpu, err); + return err; } len = read(fd, buf, sizeof(buf)); close(fd); if (len <= 0) { - error = len ? errno : EINVAL; - pr_warn("Failed to read # of possible cpus from %s: %s\n", - fcpu, strerror(error)); - return -error; + err = len ? -errno : -EINVAL; + pr_warn("Failed to read cpu mask from %s: %d\n", fcpu, err); + return err; } - if (len == sizeof(buf)) { - pr_warn("File %s size overflow\n", fcpu); - return -EOVERFLOW; + if (len >= sizeof(buf)) { + pr_warn("CPU mask is too big in file %s\n", fcpu); + return -E2BIG; } buf[len] = '\0'; - for (ir = 0, tmp_cpus = 0; ir <= len; ir++) { - /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ - if (buf[ir] == ',' || buf[ir] == '\0') { - buf[ir] = '\0'; - n = sscanf(&buf[il], "%u-%u", &start, &end); - if (n <= 0) { - pr_warn("Failed to get # CPUs from %s\n", - &buf[il]); - return -EINVAL; - } else if (n == 1) { - end = start; - } - tmp_cpus += end - start + 1; - il = ir + 1; - } - } - if (tmp_cpus <= 0) { - pr_warn("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu); - return -EINVAL; + return parse_cpu_mask_str(buf, mask, mask_sz); +} + +int libbpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + static int cpus; + int err, n, i, tmp_cpus; + bool *mask; + + tmp_cpus = READ_ONCE(cpus); + if (tmp_cpus > 0) + return tmp_cpus; + + err = parse_cpu_mask_file(fcpu, &mask, &n); + if (err) + return err; + + tmp_cpus = 0; + for (i = 0; i < n; i++) { + if (mask[i]) + tmp_cpus++; } + free(mask); WRITE_ONCE(cpus, tmp_cpus); return tmp_cpus; } + +int bpf_object__open_skeleton(struct bpf_object_skeleton *s, + const struct bpf_object_open_opts *opts) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts, + .object_name = s->name, + ); + struct bpf_object *obj; + int i; + + /* Attempt to preserve opts->object_name, unless overriden by user + * explicitly. Overwriting object name for skeletons is discouraged, + * as it breaks global data maps, because they contain object name + * prefix as their own map name prefix. When skeleton is generated, + * bpftool is making an assumption that this name will stay the same. + */ + if (opts) { + memcpy(&skel_opts, opts, sizeof(*opts)); + if (!opts->object_name) + skel_opts.object_name = s->name; + } + + obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts); + if (IS_ERR(obj)) { + pr_warn("failed to initialize skeleton BPF object '%s': %ld\n", + s->name, PTR_ERR(obj)); + return PTR_ERR(obj); + } + + *s->obj = obj; + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map **map = s->maps[i].map; + const char *name = s->maps[i].name; + void **mmaped = s->maps[i].mmaped; + + *map = bpf_object__find_map_by_name(obj, name); + if (!*map) { + pr_warn("failed to find skeleton map '%s'\n", name); + return -ESRCH; + } + + /* externs shouldn't be pre-setup from user code */ + if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) + *mmaped = (*map)->mmaped; + } + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_program **prog = s->progs[i].prog; + const char *name = s->progs[i].name; + + *prog = bpf_object__find_program_by_name(obj, name); + if (!*prog) { + pr_warn("failed to find skeleton program '%s'\n", name); + return -ESRCH; + } + } + + return 0; +} + +int bpf_object__load_skeleton(struct bpf_object_skeleton *s) +{ + int i, err; + + err = bpf_object__load(*s->obj); + if (err) { + pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err); + return err; + } + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map *map = *s->maps[i].map; + size_t mmap_sz = bpf_map_mmap_sz(map); + int prot, map_fd = bpf_map__fd(map); + void **mmaped = s->maps[i].mmaped; + + if (!mmaped) + continue; + + if (!(map->def.map_flags & BPF_F_MMAPABLE)) { + *mmaped = NULL; + continue; + } + + if (map->def.map_flags & BPF_F_RDONLY_PROG) + prot = PROT_READ; + else + prot = PROT_READ | PROT_WRITE; + + /* Remap anonymous mmap()-ed "map initialization image" as + * a BPF map-backed mmap()-ed memory, but preserving the same + * memory address. This will cause kernel to change process' + * page table to point to a different piece of kernel memory, + * but from userspace point of view memory address (and its + * contents, being identical at this point) will stay the + * same. This mapping will be released by bpf_object__close() + * as per normal clean up procedure, so we don't need to worry + * about it from skeleton's clean up perspective. + */ + *mmaped = mmap(map->mmaped, mmap_sz, prot, + MAP_SHARED | MAP_FIXED, map_fd, 0); + if (*mmaped == MAP_FAILED) { + err = -errno; + *mmaped = NULL; + pr_warn("failed to re-mmap() map '%s': %d\n", + bpf_map__name(map), err); + return err; + } + } + + return 0; +} + +int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) +{ + int i; + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_program *prog = *s->progs[i].prog; + struct bpf_link **link = s->progs[i].link; + const struct bpf_sec_def *sec_def; + const char *sec_name = bpf_program__title(prog, false); + + sec_def = find_sec_def(sec_name); + if (!sec_def || !sec_def->attach_fn) + continue; + + *link = sec_def->attach_fn(sec_def, prog); + if (IS_ERR(*link)) { + pr_warn("failed to auto-attach program '%s': %ld\n", + bpf_program__name(prog), PTR_ERR(*link)); + return PTR_ERR(*link); + } + } + + return 0; +} + +void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) +{ + int i; + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_link **link = s->progs[i].link; + + if (!IS_ERR_OR_NULL(*link)) + bpf_link__destroy(*link); + *link = NULL; + } +} + +void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) +{ + if (s->progs) + bpf_object__detach_skeleton(s); + if (s->obj) + bpf_object__close(*s->obj); + free(s->maps); + free(s->progs); + free(s); +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 0dbf4bfba0c4..fe592ef48f1b 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -17,14 +17,12 @@ #include <sys/types.h> // for size_t #include <linux/bpf.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - enum libbpf_errno { __LIBBPF_ERRNO__START = 4000, @@ -67,28 +65,6 @@ struct bpf_object_open_attr { enum bpf_prog_type prog_type; }; -/* Helper macro to declare and initialize libbpf options struct - * - * This dance with uninitialized declaration, followed by memset to zero, - * followed by assignment using compound literal syntax is done to preserve - * ability to use a nice struct field initialization syntax and **hopefully** - * have all the padding bytes initialized to zero. It's not guaranteed though, - * when copying literal, that compiler won't copy garbage in literal's padding - * bytes, but that's the best way I've found and it seems to work in practice. - * - * Macro declares opts struct of given type and name, zero-initializes, - * including any extra padding, it with memset() and then assigns initial - * values provided by users in struct initializer-syntax as varargs. - */ -#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...) \ - struct TYPE NAME = ({ \ - memset(&NAME, 0, sizeof(struct TYPE)); \ - (struct TYPE) { \ - .sz = sizeof(struct TYPE), \ - __VA_ARGS__ \ - }; \ - }) - struct bpf_object_open_opts { /* size of this struct, for forward/backward compatiblity */ size_t sz; @@ -109,15 +85,19 @@ struct bpf_object_open_opts { */ const char *pin_root_path; __u32 attach_prog_fd; + /* Additional kernel config content that augments and overrides + * system Kconfig for CONFIG_xxx externs. + */ + const char *kconfig; }; -#define bpf_object_open_opts__last_field attach_prog_fd +#define bpf_object_open_opts__last_field kconfig LIBBPF_API struct bpf_object *bpf_object__open(const char *path); LIBBPF_API struct bpf_object * -bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts); +bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts); LIBBPF_API struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, - struct bpf_object_open_opts *opts); + const struct bpf_object_open_opts *opts); /* deprecated bpf_object__open variants */ LIBBPF_API struct bpf_object * @@ -126,11 +106,6 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, LIBBPF_API struct bpf_object * bpf_object__open_xattr(struct bpf_object_open_attr *attr); -int bpf_object__section_size(const struct bpf_object *obj, const char *name, - __u32 *size); -int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, - __u32 *off); - enum libbpf_pin_type { LIBBPF_PIN_NONE, /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ @@ -161,6 +136,7 @@ struct bpf_object_load_attr { LIBBPF_API int bpf_object__load(struct bpf_object *obj); LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); LIBBPF_API int bpf_object__unload(struct bpf_object *obj); + LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); @@ -171,6 +147,9 @@ LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); LIBBPF_API struct bpf_program * bpf_object__find_program_by_title(const struct bpf_object *obj, const char *title); +LIBBPF_API struct bpf_program * +bpf_object__find_program_by_name(const struct bpf_object *obj, + const char *name); LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ @@ -214,6 +193,7 @@ LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); +LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog); LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy); @@ -235,9 +215,12 @@ LIBBPF_API void bpf_program__unload(struct bpf_program *prog); struct bpf_link; +LIBBPF_API void bpf_link__disconnect(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); LIBBPF_API struct bpf_link * +bpf_program__attach(struct bpf_program *prog); +LIBBPF_API struct bpf_link * bpf_program__attach_perf_event(struct bpf_program *prog, int pfd); LIBBPF_API struct bpf_link * bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe, @@ -512,18 +495,6 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, bpf_perf_event_print_t fn, void *private_data); -struct nlattr; -typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); -int libbpf_netlink_open(unsigned int *nl_pid); -int libbpf_nl_get_link(int sock, unsigned int nl_pid, - libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); -int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); -int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); -int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, - libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); - struct bpf_prog_linfo; struct bpf_prog_info; @@ -630,6 +601,50 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); */ LIBBPF_API int libbpf_num_possible_cpus(void); +struct bpf_map_skeleton { + const char *name; + struct bpf_map **map; + void **mmaped; +}; + +struct bpf_prog_skeleton { + const char *name; + struct bpf_program **prog; + struct bpf_link **link; +}; + +struct bpf_object_skeleton { + size_t sz; /* size of this struct, for forward/backward compatibility */ + + const char *name; + void *data; + size_t data_sz; + + struct bpf_object **obj; + + int map_cnt; + int map_skel_sz; /* sizeof(struct bpf_skeleton_map) */ + struct bpf_map_skeleton *maps; + + int prog_cnt; + int prog_skel_sz; /* sizeof(struct bpf_skeleton_prog) */ + struct bpf_prog_skeleton *progs; +}; + +LIBBPF_API int +bpf_object__open_skeleton(struct bpf_object_skeleton *s, + const struct bpf_object_open_opts *opts); +LIBBPF_API int bpf_object__load_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s); + +enum libbpf_tristate { + TRI_NO = 0, + TRI_YES = 1, + TRI_MODULE = 2, +}; + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 8ddc2c40e482..e9713a574243 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -208,3 +208,19 @@ LIBBPF_0.0.6 { btf__find_by_name_kind; libbpf_find_vmlinux_btf_id; } LIBBPF_0.0.5; + +LIBBPF_0.0.7 { + global: + btf_dump__emit_type_decl; + bpf_link__disconnect; + bpf_object__find_program_by_name; + bpf_object__attach_skeleton; + bpf_object__destroy_skeleton; + bpf_object__detach_skeleton; + bpf_object__load_skeleton; + bpf_object__open_skeleton; + bpf_prog_attach_xattr; + bpf_program__attach; + bpf_program__name; + btf__align_of; +} LIBBPF_0.0.6; diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template index ac17fcef2108..b45ed534bdfb 100644 --- a/tools/lib/bpf/libbpf.pc.template +++ b/tools/lib/bpf/libbpf.pc.template @@ -8,5 +8,5 @@ Name: libbpf Description: BPF library Version: @VERSION@ Libs: -L${libdir} -lbpf -Requires.private: libelf +Requires.private: libelf zlib Cflags: -I${includedir} diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h new file mode 100644 index 000000000000..a23ae1ac27eb --- /dev/null +++ b/tools/lib/bpf/libbpf_common.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Common user-facing libbpf helpers. + * + * Copyright (c) 2019 Facebook + */ + +#ifndef __LIBBPF_LIBBPF_COMMON_H +#define __LIBBPF_LIBBPF_COMMON_H + +#include <string.h> + +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + +/* Helper macro to declare and initialize libbpf options struct + * + * This dance with uninitialized declaration, followed by memset to zero, + * followed by assignment using compound literal syntax is done to preserve + * ability to use a nice struct field initialization syntax and **hopefully** + * have all the padding bytes initialized to zero. It's not guaranteed though, + * when copying literal, that compiler won't copy garbage in literal's padding + * bytes, but that's the best way I've found and it seems to work in practice. + * + * Macro declares opts struct of given type and name, zero-initializes, + * including any extra padding, it with memset() and then assigns initial + * values provided by users in struct initializer-syntax as varargs. + */ +#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...) \ + struct TYPE NAME = ({ \ + memset(&NAME, 0, sizeof(struct TYPE)); \ + (struct TYPE) { \ + .sz = sizeof(struct TYPE), \ + __VA_ARGS__ \ + }; \ + }) + +#endif /* __LIBBPF_LIBBPF_COMMON_H */ diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 97ac17a64a58..8c3afbd97747 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -76,7 +76,7 @@ static inline bool libbpf_validate_opts(const char *opts, for (i = opts_sz; i < user_sz; i++) { if (opts[i]) { - pr_warn("%s has non-zero extra bytes", + pr_warn("%s has non-zero extra bytes\n", type_name); return false; } @@ -95,9 +95,28 @@ static inline bool libbpf_validate_opts(const char *opts, #define OPTS_GET(opts, field, fallback_value) \ (OPTS_HAS(opts, field) ? (opts)->field : fallback_value) +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size); +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off); + +struct nlattr; +typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); +int libbpf_netlink_open(unsigned int *nl_pid); +int libbpf_nl_get_link(int sock, unsigned int nl_pid, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); +int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); +int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); +int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); + struct btf_ext_info { /* * info points to the individual info section (e.g. func_info and diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 1ff0a9f49c01..301ac12d5d69 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -21,7 +21,6 @@ test_lirc_mode2_user get_cgroup_id_user test_skb_cgroup_id_user test_socket_cookie -test_cgroup_attach test_cgroup_storage test_select_reuseport test_flow_dissector @@ -38,6 +37,8 @@ test_hashmap test_btf_dump xdping test_cpp +*.skel.h /no_alu32 /bpf_gcc +/tools bpf_helper_defs.h diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index e2fd6f8d579c..f1f949cd8ed9 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -3,10 +3,12 @@ include ../../../../scripts/Kbuild.include include ../../../scripts/Makefile.arch CURDIR := $(abspath .) -LIBDIR := $(abspath ../../../lib) +TOOLSDIR := $(abspath ../../..) +LIBDIR := $(TOOLSDIR)/lib BPFDIR := $(LIBDIR)/bpf -TOOLSDIR := $(abspath ../../../include) -APIDIR := $(TOOLSDIR)/uapi +TOOLSINCDIR := $(TOOLSDIR)/include +BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool +APIDIR := $(TOOLSINCDIR)/uapi GENDIR := $(abspath ../../../../include/generated) GENHDR := $(GENDIR)/autoconf.h @@ -19,18 +21,18 @@ LLC ?= llc LLVM_OBJCOPY ?= llvm-objcopy BPF_GCC ?= $(shell command -v bpf-gcc;) CFLAGS += -g -Wall -O2 $(GENFLAGS) -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) \ - -I$(GENDIR) -I$(TOOLSDIR) -I$(CURDIR) \ + -I$(GENDIR) -I$(TOOLSINCDIR) -I$(CURDIR) \ -Dbpf_prog_load=bpf_prog_test_load \ -Dbpf_load_program=bpf_test_load_program -LDLIBS += -lcap -lelf -lrt -lpthread +LDLIBS += -lcap -lelf -lz -lrt -lpthread # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \ - test_cgroup_storage test_select_reuseport \ + test_cgroup_storage \ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \ - test_cgroup_attach test_progs-no_alu32 + test_progs-no_alu32 # Also test bpf-gcc, if present ifneq ($(BPF_GCC),) @@ -75,6 +77,24 @@ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ TEST_CUSTOM_PROGS = urandom_read +# Emit succinct information message describing current building step +# $1 - generic step name (e.g., CC, LINK, etc); +# $2 - optional "flavor" specifier; if provided, will be emitted as [flavor]; +# $3 - target (assumed to be file); only file name will be emitted; +# $4 - optional extra arg, emitted as-is, if provided. +ifeq ($(V),1) +msg = +else +msg = @$(info $(1)$(if $(2), [$(2)]) $(notdir $(3)))$(if $(4), $(4)) +endif + +# override lib.mk's default rules +OVERRIDE_TARGETS := 1 +override define CLEAN + $(call msg, CLEAN) + $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) +endef + include ../lib.mk # Define simple and short `make test_progs`, `make test_sysctl`, etc targets @@ -87,10 +107,16 @@ $(notdir $(TEST_GEN_PROGS) \ $(TEST_GEN_PROGS_EXTENDED) \ $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ; +$(OUTPUT)/%:%.c + $(call msg, BINARY,,$@) + $(LINK.c) $^ $(LDLIBS) -o $@ + $(OUTPUT)/urandom_read: urandom_read.c + $(call msg, BINARY,,$@) $(CC) -o $@ $< -Wl,--build-id $(OUTPUT)/test_stub.o: test_stub.c + $(call msg, CC,,$@) $(CC) -c $(CFLAGS) -o $@ $< BPFOBJ := $(OUTPUT)/libbpf.a @@ -110,13 +136,18 @@ $(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 -$(OUTPUT)/test_cgroup_attach: cgroup_helpers.c .PHONY: force # force a rebuild of BPFOBJ when its dependencies are updated force: +DEFAULT_BPFTOOL := $(OUTPUT)/tools/usr/local/sbin/bpftool +BPFTOOL ?= $(DEFAULT_BPFTOOL) + +$(DEFAULT_BPFTOOL): force + $(MAKE) -C $(BPFTOOLDIR) DESTDIR=$(OUTPUT)/tools install + $(BPFOBJ): force $(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/ @@ -159,27 +190,33 @@ $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h # $3 - CFLAGS # $4 - LDFLAGS define CLANG_BPF_BUILD_RULE + $(call msg, CLANG-LLC,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -target bpf -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -mattr=dwarfris -march=bpf -mcpu=probe $4 -filetype=obj -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32 define CLANG_NOALU32_BPF_BUILD_RULE + $(call msg, CLANG-LLC,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -target bpf -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC define CLANG_NATIVE_BPF_BUILD_RULE + $(call msg, CLANG-BPF,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ $(LLC) -march=bpf -mcpu=probe $4 -filetype=obj -o $2 endef # Build BPF object using GCC define GCC_BPF_BUILD_RULE + $(call msg, GCC-BPF,$(TRUNNER_BINARY),$2) $(BPF_GCC) $3 $4 -O2 -c $1 -o $2 endef +SKEL_BLACKLIST := btf__% test_pinning_invalid.c + # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES. # Parameters: @@ -195,8 +232,11 @@ TRUNNER_EXTRA_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, \ $$(filter %.c,$(TRUNNER_EXTRA_SOURCES))) TRUNNER_EXTRA_HDRS := $$(filter %.h,$(TRUNNER_EXTRA_SOURCES)) TRUNNER_TESTS_HDR := $(TRUNNER_TESTS_DIR)/tests.h -TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, \ - $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c))) +TRUNNER_BPF_SRCS := $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c)) +TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS)) +TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \ + $$(filter-out $(SKEL_BLACKLIST), \ + $$(TRUNNER_BPF_SRCS))) # Evaluate rules now with extra TRUNNER_XXX variables above already defined $$(eval $$(call DEFINE_TEST_RUNNER_RULES,$1,$2)) @@ -226,12 +266,19 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \ $(TRUNNER_BPF_CFLAGS), \ $(TRUNNER_BPF_LDFLAGS)) + +$(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h: \ + $(TRUNNER_OUTPUT)/%.o \ + | $(BPFTOOL) $(TRUNNER_OUTPUT) + $$(call msg, GEN-SKEL,$(TRUNNER_BINARY),$$@) + $$(BPFTOOL) gen skeleton $$< > $$@ endif # ensure we set up tests.h header generation rule just once ifeq ($($(TRUNNER_TESTS_DIR)-tests-hdr),) $(TRUNNER_TESTS_DIR)-tests-hdr := y $(TRUNNER_TESTS_HDR): $(TRUNNER_TESTS_DIR)/*.c + $$(call msg, TEST-HDR,$(TRUNNER_BINARY),$$@) $$(shell ( cd $(TRUNNER_TESTS_DIR); \ echo '/* Generated header, do not edit */'; \ ls *.c 2> /dev/null | \ @@ -245,7 +292,9 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o: \ $(TRUNNER_TESTS_DIR)/%.c \ $(TRUNNER_EXTRA_HDRS) \ $(TRUNNER_BPF_OBJS) \ + $(TRUNNER_BPF_SKELS) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) + $$(call msg, TEST-OBJ,$(TRUNNER_BINARY),$$@) cd $$(@D) && $$(CC) $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F) $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ @@ -253,17 +302,20 @@ $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $(TRUNNER_EXTRA_HDRS) \ $(TRUNNER_TESTS_HDR) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) + $$(call msg, EXTRA-OBJ,$(TRUNNER_BINARY),$$@) $$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@ +# only copy extra resources if in flavored build $(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT) ifneq ($2,) - # only copy extra resources if in flavored build + $$(call msg, EXTRAS-CP,$(TRUNNER_BINARY),$(TRUNNER_EXTRA_FILES)) cp -a $$^ $(TRUNNER_OUTPUT)/ endif $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \ | $(TRUNNER_BINARY)-extras + $$(call msg, BINARY,,$$@) $$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ endef @@ -315,12 +367,15 @@ verifier/tests.h: verifier/*.c echo '#endif' \ ) > verifier/tests.h) $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT) + $(call msg, BINARY,,$@) $(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ # Make sure we are able to include and link libbpf against c++. -$(OUTPUT)/test_cpp: test_cpp.cpp $(BPFOBJ) +$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) + $(call msg, CXX,,$@) $(CXX) $(CFLAGS) $^ $(LDLIBS) -o $@ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ - feature $(OUTPUT)/*.o $(OUTPUT)/no_alu32 $(OUTPUT)/bpf_gcc + feature $(OUTPUT)/*.o $(OUTPUT)/no_alu32 $(OUTPUT)/bpf_gcc \ + tools *.skel.h diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index a83111a32d4a..a0ee87c8e1ea 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -1,26 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> - -#define EMBED_FILE(NAME, PATH) \ -asm ( \ -" .pushsection \".rodata\", \"a\", @progbits \n" \ -" .global "#NAME"_data \n" \ -#NAME"_data: \n" \ -" .incbin \"" PATH "\" \n" \ -#NAME"_data_end: \n" \ -" .global "#NAME"_size \n" \ -" .type "#NAME"_size, @object \n" \ -" .size "#NAME"_size, 4 \n" \ -" .align 4, \n" \ -#NAME"_size: \n" \ -" .int "#NAME"_data_end - "#NAME"_data \n" \ -" .popsection \n" \ -); \ -extern char NAME##_data[]; \ -extern int NAME##_size; +#include "test_attach_probe.skel.h" ssize_t get_base_addr() { - size_t start; + size_t start, offset; char buf[256]; FILE *f; @@ -28,10 +11,11 @@ ssize_t get_base_addr() { if (!f) return -errno; - while (fscanf(f, "%zx-%*x %s %*s\n", &start, buf) == 2) { + while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n", + &start, buf, &offset) == 3) { if (strcmp(buf, "r-xp") == 0) { fclose(f); - return start; + return start - offset; } } @@ -39,30 +23,12 @@ ssize_t get_base_addr() { return -EINVAL; } -EMBED_FILE(probe, "test_attach_probe.o"); - void test_attach_probe(void) { - const char *kprobe_name = "kprobe/sys_nanosleep"; - const char *kretprobe_name = "kretprobe/sys_nanosleep"; - const char *uprobe_name = "uprobe/trigger_func"; - const char *uretprobe_name = "uretprobe/trigger_func"; - const int kprobe_idx = 0, kretprobe_idx = 1; - const int uprobe_idx = 2, uretprobe_idx = 3; - const char *obj_name = "attach_probe"; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts, - .object_name = obj_name, - .relaxed_maps = true, - ); - struct bpf_program *kprobe_prog, *kretprobe_prog; - struct bpf_program *uprobe_prog, *uretprobe_prog; - struct bpf_object *obj; - int err, duration = 0, res; - struct bpf_link *kprobe_link = NULL; - struct bpf_link *kretprobe_link = NULL; - struct bpf_link *uprobe_link = NULL; - struct bpf_link *uretprobe_link = NULL; - int results_map_fd; + int duration = 0; + struct bpf_link *kprobe_link, *kretprobe_link; + struct bpf_link *uprobe_link, *uretprobe_link; + struct test_attach_probe* skel; size_t uprobe_offset; ssize_t base_addr; @@ -72,123 +38,68 @@ void test_attach_probe(void) return; uprobe_offset = (size_t)&get_base_addr - base_addr; - /* open object */ - obj = bpf_object__open_mem(probe_data, probe_size, &open_opts); - if (CHECK(IS_ERR(obj), "obj_open_mem", "err %ld\n", PTR_ERR(obj))) + skel = test_attach_probe__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) return; - - if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name", - "wrong obj name '%s', expected '%s'\n", - bpf_object__name(obj), obj_name)) + if (CHECK(!skel->bss, "check_bss", ".bss wasn't mmap()-ed\n")) goto cleanup; - kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name); - if (CHECK(!kprobe_prog, "find_probe", - "prog '%s' not found\n", kprobe_name)) - goto cleanup; - kretprobe_prog = bpf_object__find_program_by_title(obj, kretprobe_name); - if (CHECK(!kretprobe_prog, "find_probe", - "prog '%s' not found\n", kretprobe_name)) - goto cleanup; - uprobe_prog = bpf_object__find_program_by_title(obj, uprobe_name); - if (CHECK(!uprobe_prog, "find_probe", - "prog '%s' not found\n", uprobe_name)) - goto cleanup; - uretprobe_prog = bpf_object__find_program_by_title(obj, uretprobe_name); - if (CHECK(!uretprobe_prog, "find_probe", - "prog '%s' not found\n", uretprobe_name)) - goto cleanup; - - /* create maps && load programs */ - err = bpf_object__load(obj); - if (CHECK(err, "obj_load", "err %d\n", err)) - goto cleanup; - - /* load maps */ - results_map_fd = bpf_find_map(__func__, obj, "results_map"); - if (CHECK(results_map_fd < 0, "find_results_map", - "err %d\n", results_map_fd)) - goto cleanup; - - kprobe_link = bpf_program__attach_kprobe(kprobe_prog, + kprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kprobe, false /* retprobe */, SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(kprobe_link), "attach_kprobe", - "err %ld\n", PTR_ERR(kprobe_link))) { - kprobe_link = NULL; + "err %ld\n", PTR_ERR(kprobe_link))) goto cleanup; - } - kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog, + skel->links.handle_kprobe = kprobe_link; + + kretprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kretprobe, true /* retprobe */, SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe", - "err %ld\n", PTR_ERR(kretprobe_link))) { - kretprobe_link = NULL; + "err %ld\n", PTR_ERR(kretprobe_link))) goto cleanup; - } - uprobe_link = bpf_program__attach_uprobe(uprobe_prog, + skel->links.handle_kretprobe = kretprobe_link; + + uprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uprobe, false /* retprobe */, 0 /* self pid */, "/proc/self/exe", uprobe_offset); if (CHECK(IS_ERR(uprobe_link), "attach_uprobe", - "err %ld\n", PTR_ERR(uprobe_link))) { - uprobe_link = NULL; + "err %ld\n", PTR_ERR(uprobe_link))) goto cleanup; - } - uretprobe_link = bpf_program__attach_uprobe(uretprobe_prog, + skel->links.handle_uprobe = uprobe_link; + + uretprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uretprobe, true /* retprobe */, -1 /* any pid */, "/proc/self/exe", uprobe_offset); if (CHECK(IS_ERR(uretprobe_link), "attach_uretprobe", - "err %ld\n", PTR_ERR(uretprobe_link))) { - uretprobe_link = NULL; + "err %ld\n", PTR_ERR(uretprobe_link))) goto cleanup; - } + skel->links.handle_uretprobe = uretprobe_link; /* trigger & validate kprobe && kretprobe */ usleep(1); - err = bpf_map_lookup_elem(results_map_fd, &kprobe_idx, &res); - if (CHECK(err, "get_kprobe_res", - "failed to get kprobe res: %d\n", err)) + if (CHECK(skel->bss->kprobe_res != 1, "check_kprobe_res", + "wrong kprobe res: %d\n", skel->bss->kprobe_res)) goto cleanup; - if (CHECK(res != kprobe_idx + 1, "check_kprobe_res", - "wrong kprobe res: %d\n", res)) - goto cleanup; - - err = bpf_map_lookup_elem(results_map_fd, &kretprobe_idx, &res); - if (CHECK(err, "get_kretprobe_res", - "failed to get kretprobe res: %d\n", err)) - goto cleanup; - if (CHECK(res != kretprobe_idx + 1, "check_kretprobe_res", - "wrong kretprobe res: %d\n", res)) + if (CHECK(skel->bss->kretprobe_res != 2, "check_kretprobe_res", + "wrong kretprobe res: %d\n", skel->bss->kretprobe_res)) goto cleanup; /* trigger & validate uprobe & uretprobe */ get_base_addr(); - err = bpf_map_lookup_elem(results_map_fd, &uprobe_idx, &res); - if (CHECK(err, "get_uprobe_res", - "failed to get uprobe res: %d\n", err)) - goto cleanup; - if (CHECK(res != uprobe_idx + 1, "check_uprobe_res", - "wrong uprobe res: %d\n", res)) - goto cleanup; - - err = bpf_map_lookup_elem(results_map_fd, &uretprobe_idx, &res); - if (CHECK(err, "get_uretprobe_res", - "failed to get uretprobe res: %d\n", err)) + if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res", + "wrong uprobe res: %d\n", skel->bss->uprobe_res)) goto cleanup; - if (CHECK(res != uretprobe_idx + 1, "check_uretprobe_res", - "wrong uretprobe res: %d\n", res)) + if (CHECK(skel->bss->uretprobe_res != 4, "check_uretprobe_res", + "wrong uretprobe res: %d\n", skel->bss->uretprobe_res)) goto cleanup; cleanup: - bpf_link__destroy(kprobe_link); - bpf_link__destroy(kretprobe_link); - bpf_link__destroy(uprobe_link); - bpf_link__destroy(uretprobe_link); - bpf_object__close(obj); + test_attach_probe__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c new file mode 100644 index 000000000000..5b13f2c6c402 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "cgroup_helpers.h" + +#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int prog_load(void) +{ + struct bpf_insn prog[] = { + BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = 1 */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + + return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); +} + +void test_cgroup_attach_autodetach(void) +{ + __u32 duration = 0, prog_cnt = 4, attach_flags; + int allow_prog[2] = {-1}; + __u32 prog_ids[2] = {0}; + void *ptr = NULL; + int cg = 0, i; + int attempts; + + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { + allow_prog[i] = prog_load(); + if (CHECK(allow_prog[i] < 0, "prog_load", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + } + + if (CHECK_FAIL(setup_cgroup_environment())) + goto err; + + /* create a cgroup, attach two programs and remember their ids */ + cg = create_and_get_cgroup("/cg_autodetach"); + if (CHECK_FAIL(cg < 0)) + goto err; + + if (CHECK_FAIL(join_cgroup("/cg_autodetach"))) + goto err; + + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) + if (CHECK(bpf_prog_attach(allow_prog[i], cg, + BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog_attach", "prog[%d], errno=%d\n", i, errno)) + goto err; + + /* make sure that programs are attached and run some traffic */ + if (CHECK(bpf_prog_query(cg, BPF_CGROUP_INET_EGRESS, 0, &attach_flags, + prog_ids, &prog_cnt), + "prog_query", "errno=%d\n", errno)) + goto err; + if (CHECK_FAIL(system(PING_CMD))) + goto err; + + /* allocate some memory (4Mb) to pin the original cgroup */ + ptr = malloc(4 * (1 << 20)); + if (CHECK_FAIL(!ptr)) + goto err; + + /* close programs and cgroup fd */ + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { + close(allow_prog[i]); + allow_prog[i] = -1; + } + + close(cg); + cg = 0; + + /* leave the cgroup and remove it. don't detach programs */ + cleanup_cgroup_environment(); + + /* wait for the asynchronous auto-detachment. + * wait for no more than 5 sec and give up. + */ + for (i = 0; i < ARRAY_SIZE(prog_ids); i++) { + for (attempts = 5; attempts >= 0; attempts--) { + int fd = bpf_prog_get_fd_by_id(prog_ids[i]); + + if (fd < 0) + break; + + /* don't leave the fd open */ + close(fd); + + if (CHECK_FAIL(!attempts)) + goto err; + + sleep(1); + } + } + +err: + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) + if (allow_prog[i] >= 0) + close(allow_prog[i]); + if (cg) + close(cg); + free(ptr); + cleanup_cgroup_environment(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c new file mode 100644 index 000000000000..2ff21dbce179 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "cgroup_helpers.h" + +#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int map_fd = -1; + +static int prog_load_cnt(int verdict, int val) +{ + int cgroup_storage_fd, percpu_cgroup_storage_fd; + + if (map_fd < 0) + map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); + if (map_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + + cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, + sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + if (cgroup_storage_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + + percpu_cgroup_storage_fd = bpf_create_map( + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + if (percpu_cgroup_storage_fd < 0) { + printf("failed to create map '%s'\n", strerror(errno)); + return -1; + } + + struct bpf_insn prog[] = { + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */ + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ + + BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), + BPF_MOV64_IMM(BPF_REG_1, val), + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0), + + BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1), + BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0), + + BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + int ret; + + ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); + + close(cgroup_storage_fd); + return ret; +} + +void test_cgroup_attach_multi(void) +{ + __u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id; + int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0; + DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, attach_opts); + int allow_prog[7] = {-1}; + unsigned long long value; + __u32 duration = 0; + int i = 0; + + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { + allow_prog[i] = prog_load_cnt(1, 1 << i); + if (CHECK(allow_prog[i] < 0, "prog_load", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + } + + if (CHECK_FAIL(setup_cgroup_environment())) + goto err; + + cg1 = create_and_get_cgroup("/cg1"); + if (CHECK_FAIL(cg1 < 0)) + goto err; + cg2 = create_and_get_cgroup("/cg1/cg2"); + if (CHECK_FAIL(cg2 < 0)) + goto err; + cg3 = create_and_get_cgroup("/cg1/cg2/cg3"); + if (CHECK_FAIL(cg3 < 0)) + goto err; + cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4"); + if (CHECK_FAIL(cg4 < 0)) + goto err; + cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5"); + if (CHECK_FAIL(cg5 < 0)) + goto err; + + if (CHECK_FAIL(join_cgroup("/cg1/cg2/cg3/cg4/cg5"))) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog0_attach_to_cg1_multi", "errno=%d\n", errno)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "fail_same_prog_attach_to_cg1", "unexpected success\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog1_attach_to_cg1_multi", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog2_attach_to_cg2_override", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_MULTI), + "prog3_attach_to_cg3_multi", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog4_attach_to_cg4_override", "errno=%d\n", errno)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0), + "prog5_attach_to_cg5_none", "errno=%d\n", errno)) + goto err; + + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 1 + 2 + 8 + 32); + + /* query the number of effective progs in cg5 */ + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, NULL, NULL, &prog_cnt)); + CHECK_FAIL(prog_cnt != 4); + /* retrieve prog_ids of effective progs in cg5 */ + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 4); + CHECK_FAIL(attach_flags != 0); + saved_prog_id = prog_ids[0]; + /* check enospc handling */ + prog_ids[0] = 0; + prog_cnt = 2; + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, + prog_ids, &prog_cnt) != -1); + CHECK_FAIL(errno != ENOSPC); + CHECK_FAIL(prog_cnt != 4); + /* check that prog_ids are returned even when buffer is too small */ + CHECK_FAIL(prog_ids[0] != saved_prog_id); + /* retrieve prog_id of single attached prog in cg5 */ + prog_ids[0] = 0; + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, NULL, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 1); + CHECK_FAIL(prog_ids[0] != saved_prog_id); + + /* detach bottom program and ping again */ + if (CHECK(bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS), + "prog_detach_from_cg5", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 1 + 2 + 8 + 16); + + /* test replace */ + + attach_opts.flags = BPF_F_ALLOW_OVERRIDE | BPF_F_REPLACE; + attach_opts.replace_prog_fd = allow_prog[0]; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_override", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != EINVAL); + + attach_opts.flags = BPF_F_REPLACE; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_no_multi", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != EINVAL); + + attach_opts.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE; + attach_opts.replace_prog_fd = -1; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_bad_fd", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != EBADF); + + /* replacing a program that is not attached to cgroup should fail */ + attach_opts.replace_prog_fd = allow_prog[3]; + if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "fail_prog_replace_no_ent", "unexpected success\n")) + goto err; + CHECK_FAIL(errno != ENOENT); + + /* replace 1st from the top program */ + attach_opts.replace_prog_fd = allow_prog[0]; + if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + BPF_CGROUP_INET_EGRESS, &attach_opts), + "prog_replace", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 64 + 2 + 8 + 16); + + /* detach 3rd from bottom program and ping again */ + if (CHECK(!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS), + "fail_prog_detach_from_cg3", "unexpected success\n")) + goto err; + + if (CHECK(bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS), + "prog3_detach_from_cg3", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 64 + 2 + 16); + + /* detach 2nd from bottom program and ping again */ + if (CHECK(bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS), + "prog_detach_from_cg4", "errno=%d\n", errno)) + goto err; + + value = 0; + CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0)); + CHECK_FAIL(system(PING_CMD)); + CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value)); + CHECK_FAIL(value != 64 + 2 + 4); + + prog_cnt = 4; + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, + BPF_F_QUERY_EFFECTIVE, &attach_flags, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 3); + CHECK_FAIL(attach_flags != 0); + CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, NULL, + prog_ids, &prog_cnt)); + CHECK_FAIL(prog_cnt != 0); + +err: + for (i = 0; i < ARRAY_SIZE(allow_prog); i++) + if (allow_prog[i] >= 0) + close(allow_prog[i]); + close(cg1); + close(cg2); + close(cg3); + close(cg4); + close(cg5); + cleanup_cgroup_environment(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c new file mode 100644 index 000000000000..9d8cb48b99de --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c @@ -0,0 +1,148 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "cgroup_helpers.h" + +#define FOO "/foo" +#define BAR "/foo/bar/" +#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" + +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +static int prog_load(int verdict) +{ + struct bpf_insn prog[] = { + BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ + BPF_EXIT_INSN(), + }; + size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + + return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, + prog, insns_cnt, "GPL", 0, + bpf_log_buf, BPF_LOG_BUF_SIZE); +} + +void test_cgroup_attach_override(void) +{ + int drop_prog = -1, allow_prog = -1, foo = -1, bar = -1; + __u32 duration = 0; + + allow_prog = prog_load(1); + if (CHECK(allow_prog < 0, "prog_load_allow", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + + drop_prog = prog_load(0); + if (CHECK(drop_prog < 0, "prog_load_drop", + "verifier output:\n%s\n-------\n", bpf_log_buf)) + goto err; + + foo = test__join_cgroup(FOO); + if (CHECK(foo < 0, "cgroup_join_foo", "cgroup setup failed\n")) + goto err; + + if (CHECK(bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_drop_foo_override", + "attach prog to %s failed, errno=%d\n", FOO, errno)) + goto err; + + if (CHECK(!system(PING_CMD), "ping_fail", + "ping unexpectedly succeeded\n")) + goto err; + + bar = test__join_cgroup(BAR); + if (CHECK(bar < 0, "cgroup_join_bar", "cgroup setup failed\n")) + goto err; + + if (CHECK(!system(PING_CMD), "ping_fail", + "ping unexpectedly succeeded\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_allow_bar_override", + "attach prog to %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(system(PING_CMD), "ping_ok", "ping failed\n")) + goto err; + + if (CHECK(bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS), + "prog_detach_bar", + "detach prog from %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(!system(PING_CMD), "ping_fail", + "ping unexpectedly succeeded\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_allow_bar_override", + "attach prog to %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS), + "prog_detach_foo", + "detach prog from %s failed, errno=%d\n", FOO, errno)) + goto err; + + if (CHECK(system(PING_CMD), "ping_ok", "ping failed\n")) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "prog_attach_allow_bar_override", + "attach prog to %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0), + "fail_prog_attach_allow_bar_none", + "attach prog to %s unexpectedly succeeded\n", BAR)) + goto err; + + if (CHECK(bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS), + "prog_detach_bar", + "detach prog from %s failed, errno=%d\n", BAR, errno)) + goto err; + + if (CHECK(!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS), + "fail_prog_detach_foo", + "double detach from %s unexpectedly succeeded\n", FOO)) + goto err; + + if (CHECK(bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0), + "prog_attach_allow_foo_none", + "attach prog to %s failed, errno=%d\n", FOO, errno)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0), + "fail_prog_attach_allow_bar_none", + "attach prog to %s unexpectedly succeeded\n", BAR)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "fail_prog_attach_allow_bar_override", + "attach prog to %s unexpectedly succeeded\n", BAR)) + goto err; + + if (CHECK(!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, + BPF_F_ALLOW_OVERRIDE), + "fail_prog_attach_allow_foo_override", + "attach prog to %s unexpectedly succeeded\n", FOO)) + goto err; + + if (CHECK(bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0), + "prog_attach_drop_foo_none", + "attach prog to %s failed, errno=%d\n", FOO, errno)) + goto err; + +err: + close(foo); + close(bar); + close(allow_prog); + close(drop_prog); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_extern.c b/tools/testing/selftests/bpf/prog_tests/core_extern.c new file mode 100644 index 000000000000..b093787e9448 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_extern.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <test_progs.h> +#include <sys/mman.h> +#include <sys/utsname.h> +#include <linux/version.h> +#include "test_core_extern.skel.h" + +static uint32_t get_kernel_version(void) +{ + uint32_t major, minor, patch; + struct utsname info; + + uname(&info); + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + return KERNEL_VERSION(major, minor, patch); +} + +#define CFG "CONFIG_BPF_SYSCALL=n\n" + +static struct test_case { + const char *name; + const char *cfg; + bool fails; + struct test_core_extern__data data; +} test_cases[] = { + { .name = "default search path", .data = { .bpf_syscall = true } }, + { + .name = "custom values", + .cfg = "CONFIG_BPF_SYSCALL=n\n" + "CONFIG_TRISTATE=m\n" + "CONFIG_BOOL=y\n" + "CONFIG_CHAR=100\n" + "CONFIG_USHORT=30000\n" + "CONFIG_INT=123456\n" + "CONFIG_ULONG=0xDEADBEEFC0DE\n" + "CONFIG_STR=\"abracad\"\n" + "CONFIG_MISSING=0", + .data = { + .bpf_syscall = false, + .tristate_val = TRI_MODULE, + .bool_val = true, + .char_val = 100, + .ushort_val = 30000, + .int_val = 123456, + .ulong_val = 0xDEADBEEFC0DE, + .str_val = "abracad", + }, + }, + /* TRISTATE */ + { .name = "tristate (y)", .cfg = CFG"CONFIG_TRISTATE=y\n", + .data = { .tristate_val = TRI_YES } }, + { .name = "tristate (n)", .cfg = CFG"CONFIG_TRISTATE=n\n", + .data = { .tristate_val = TRI_NO } }, + { .name = "tristate (m)", .cfg = CFG"CONFIG_TRISTATE=m\n", + .data = { .tristate_val = TRI_MODULE } }, + { .name = "tristate (int)", .fails = 1, .cfg = CFG"CONFIG_TRISTATE=1" }, + { .name = "tristate (bad)", .fails = 1, .cfg = CFG"CONFIG_TRISTATE=M" }, + /* BOOL */ + { .name = "bool (y)", .cfg = CFG"CONFIG_BOOL=y\n", + .data = { .bool_val = true } }, + { .name = "bool (n)", .cfg = CFG"CONFIG_BOOL=n\n", + .data = { .bool_val = false } }, + { .name = "bool (tristate)", .fails = 1, .cfg = CFG"CONFIG_BOOL=m" }, + { .name = "bool (int)", .fails = 1, .cfg = CFG"CONFIG_BOOL=1" }, + /* CHAR */ + { .name = "char (tristate)", .cfg = CFG"CONFIG_CHAR=m\n", + .data = { .char_val = 'm' } }, + { .name = "char (bad)", .fails = 1, .cfg = CFG"CONFIG_CHAR=q\n" }, + { .name = "char (empty)", .fails = 1, .cfg = CFG"CONFIG_CHAR=\n" }, + { .name = "char (str)", .fails = 1, .cfg = CFG"CONFIG_CHAR=\"y\"\n" }, + /* STRING */ + { .name = "str (empty)", .cfg = CFG"CONFIG_STR=\"\"\n", + .data = { .str_val = "\0\0\0\0\0\0\0" } }, + { .name = "str (padded)", .cfg = CFG"CONFIG_STR=\"abra\"\n", + .data = { .str_val = "abra\0\0\0" } }, + { .name = "str (too long)", .cfg = CFG"CONFIG_STR=\"abracada\"\n", + .data = { .str_val = "abracad" } }, + { .name = "str (no value)", .fails = 1, .cfg = CFG"CONFIG_STR=\n" }, + { .name = "str (bad value)", .fails = 1, .cfg = CFG"CONFIG_STR=bla\n" }, + /* INTEGERS */ + { + .name = "integer forms", + .cfg = CFG + "CONFIG_CHAR=0xA\n" + "CONFIG_USHORT=0462\n" + "CONFIG_INT=-100\n" + "CONFIG_ULONG=+1000000000000", + .data = { + .char_val = 0xA, + .ushort_val = 0462, + .int_val = -100, + .ulong_val = 1000000000000, + }, + }, + { .name = "int (bad)", .fails = 1, .cfg = CFG"CONFIG_INT=abc" }, + { .name = "int (str)", .fails = 1, .cfg = CFG"CONFIG_INT=\"abc\"" }, + { .name = "int (empty)", .fails = 1, .cfg = CFG"CONFIG_INT=" }, + { .name = "int (mixed)", .fails = 1, .cfg = CFG"CONFIG_INT=123abc" }, + { .name = "int (max)", .cfg = CFG"CONFIG_INT=2147483647", + .data = { .int_val = 2147483647 } }, + { .name = "int (min)", .cfg = CFG"CONFIG_INT=-2147483648", + .data = { .int_val = -2147483648 } }, + { .name = "int (max+1)", .fails = 1, .cfg = CFG"CONFIG_INT=2147483648" }, + { .name = "int (min-1)", .fails = 1, .cfg = CFG"CONFIG_INT=-2147483649" }, + { .name = "ushort (max)", .cfg = CFG"CONFIG_USHORT=65535", + .data = { .ushort_val = 65535 } }, + { .name = "ushort (min)", .cfg = CFG"CONFIG_USHORT=0", + .data = { .ushort_val = 0 } }, + { .name = "ushort (max+1)", .fails = 1, .cfg = CFG"CONFIG_USHORT=65536" }, + { .name = "ushort (min-1)", .fails = 1, .cfg = CFG"CONFIG_USHORT=-1" }, + { .name = "u64 (max)", .cfg = CFG"CONFIG_ULONG=0xffffffffffffffff", + .data = { .ulong_val = 0xffffffffffffffff } }, + { .name = "u64 (min)", .cfg = CFG"CONFIG_ULONG=0", + .data = { .ulong_val = 0 } }, + { .name = "u64 (max+1)", .fails = 1, .cfg = CFG"CONFIG_ULONG=0x10000000000000000" }, +}; + +void test_core_extern(void) +{ + const uint32_t kern_ver = get_kernel_version(); + int err, duration = 0, i, j; + struct test_core_extern *skel = NULL; + uint64_t *got, *exp; + int n = sizeof(*skel->data) / sizeof(uint64_t); + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + struct test_case *t = &test_cases[i]; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, + .kconfig = t->cfg, + ); + + if (!test__start_subtest(t->name)) + continue; + + skel = test_core_extern__open_opts(&opts); + if (CHECK(!skel, "skel_open", "skeleton open failed\n")) + goto cleanup; + err = test_core_extern__load(skel); + if (t->fails) { + CHECK(!err, "skel_load", + "shouldn't succeed open/load of skeleton\n"); + goto cleanup; + } else if (CHECK(err, "skel_load", + "failed to open/load skeleton\n")) { + goto cleanup; + } + err = test_core_extern__attach(skel); + if (CHECK(err, "attach_raw_tp", "failed attach: %d\n", err)) + goto cleanup; + + usleep(1); + + t->data.kern_ver = kern_ver; + t->data.missing_val = 0xDEADC0DE; + got = (uint64_t *)skel->data; + exp = (uint64_t *)&t->data; + for (j = 0; j < n; j++) { + CHECK(got[j] != exp[j], "check_res", + "result #%d: expected %lx, but got %lx\n", + j, exp[j], got[j]); + } +cleanup: + test_core_extern__destroy(skel); + skel = NULL; + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 05fe85281ff7..31e177adbdf1 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -74,6 +74,7 @@ .b123 = 2, \ .c1c = 3, \ .d00d = 4, \ + .f10c = 0, \ }, \ .output_len = sizeof(struct core_reloc_arrays_output) \ } @@ -308,12 +309,15 @@ static struct core_reloc_test_case test_cases[] = { ARRAYS_CASE(arrays), ARRAYS_CASE(arrays___diff_arr_dim), ARRAYS_CASE(arrays___diff_arr_val_sz), + ARRAYS_CASE(arrays___equiv_zero_sz_arr), + ARRAYS_CASE(arrays___fixed_arr), ARRAYS_ERR_CASE(arrays___err_too_small), ARRAYS_ERR_CASE(arrays___err_too_shallow), ARRAYS_ERR_CASE(arrays___err_non_array), ARRAYS_ERR_CASE(arrays___err_wrong_val_type1), ARRAYS_ERR_CASE(arrays___err_wrong_val_type2), + ARRAYS_ERR_CASE(arrays___err_bad_zero_sz_arr), /* enum/ptr/int handling scenarios */ PRIMITIVES_CASE(primitives), diff --git a/tools/testing/selftests/bpf/prog_tests/cpu_mask.c b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c new file mode 100644 index 000000000000..1fa1bdbaffa9 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <bpf/btf.h> +#include "libbpf_internal.h" + +static int duration = 0; + +static void validate_mask(int case_nr, const char *exp, bool *mask, int n) +{ + int i; + + for (i = 0; exp[i]; i++) { + if (exp[i] == '1') { + if (CHECK(i + 1 > n, "mask_short", + "case #%d: mask too short, got n=%d, need at least %d\n", + case_nr, n, i + 1)) + return; + CHECK(!mask[i], "cpu_not_set", + "case #%d: mask differs, expected cpu#%d SET\n", + case_nr, i); + } else { + CHECK(i < n && mask[i], "cpu_set", + "case #%d: mask differs, expected cpu#%d UNSET\n", + case_nr, i); + } + } + CHECK(i < n, "mask_long", + "case #%d: mask too long, got n=%d, expected at most %d\n", + case_nr, n, i); +} + +static struct { + const char *cpu_mask; + const char *expect; + bool fails; +} test_cases[] = { + { "0\n", "1", false }, + { "0,2\n", "101", false }, + { "0-2\n", "111", false }, + { "0-2,3-4\n", "11111", false }, + { "0", "1", false }, + { "0-2", "111", false }, + { "0,2", "101", false }, + { "0,1-3", "1111", false }, + { "0,1,2,3", "1111", false }, + { "0,2-3,5", "101101", false }, + { "3-3", "0001", false }, + { "2-4,6,9-10", "00111010011", false }, + /* failure cases */ + { "", "", true }, + { "0-", "", true }, + { "0 ", "", true }, + { "0_1", "", true }, + { "1-0", "", true }, + { "-1", "", true }, +}; + +void test_cpu_mask() +{ + int i, err, n; + bool *mask; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + mask = NULL; + err = parse_cpu_mask_str(test_cases[i].cpu_mask, &mask, &n); + if (test_cases[i].fails) { + CHECK(!err, "should_fail", + "case #%d: parsing should fail!\n", i + 1); + } else { + if (CHECK(err, "parse_err", + "case #%d: cpu mask parsing failed: %d\n", + i + 1, err)) + continue; + validate_mask(i + 1, test_cases[i].expect, mask, n); + } + free(mask); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 40bcff2cc274..235ac4f67f5b 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -1,90 +1,55 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> +#include "test_pkt_access.skel.h" +#include "fentry_test.skel.h" +#include "fexit_test.skel.h" void test_fentry_fexit(void) { - struct bpf_prog_load_attr attr_fentry = { - .file = "./fentry_test.o", - }; - struct bpf_prog_load_attr attr_fexit = { - .file = "./fexit_test.o", - }; - - struct bpf_object *obj_fentry = NULL, *obj_fexit = NULL, *pkt_obj; - struct bpf_map *data_map_fentry, *data_map_fexit; - char fentry_name[] = "fentry/bpf_fentry_testX"; - char fexit_name[] = "fexit/bpf_fentry_testX"; - int err, pkt_fd, kfree_skb_fd, i; - struct bpf_link *link[12] = {}; - struct bpf_program *prog[12]; - __u32 duration, retval; - const int zero = 0; - u64 result[12]; - - err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, - &pkt_obj, &pkt_fd); - if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) + struct test_pkt_access *pkt_skel = NULL; + struct fentry_test *fentry_skel = NULL; + struct fexit_test *fexit_skel = NULL; + __u64 *fentry_res, *fexit_res; + __u32 duration = 0, retval; + int err, pkt_fd, i; + + pkt_skel = test_pkt_access__open_and_load(); + if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n")) return; - err = bpf_prog_load_xattr(&attr_fentry, &obj_fentry, &kfree_skb_fd); - if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno)) + fentry_skel = fentry_test__open_and_load(); + if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) goto close_prog; - err = bpf_prog_load_xattr(&attr_fexit, &obj_fexit, &kfree_skb_fd); - if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno)) + fexit_skel = fexit_test__open_and_load(); + if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n")) goto close_prog; - for (i = 0; i < 6; i++) { - fentry_name[sizeof(fentry_name) - 2] = '1' + i; - prog[i] = bpf_object__find_program_by_title(obj_fentry, fentry_name); - if (CHECK(!prog[i], "find_prog", "prog %s not found\n", fentry_name)) - goto close_prog; - link[i] = bpf_program__attach_trace(prog[i]); - if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) - goto close_prog; - } - data_map_fentry = bpf_object__find_map_by_name(obj_fentry, "fentry_t.bss"); - if (CHECK(!data_map_fentry, "find_data_map", "data map not found\n")) + err = fentry_test__attach(fentry_skel); + if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) goto close_prog; - - for (i = 6; i < 12; i++) { - fexit_name[sizeof(fexit_name) - 2] = '1' + i - 6; - prog[i] = bpf_object__find_program_by_title(obj_fexit, fexit_name); - if (CHECK(!prog[i], "find_prog", "prog %s not found\n", fexit_name)) - goto close_prog; - link[i] = bpf_program__attach_trace(prog[i]); - if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) - goto close_prog; - } - data_map_fexit = bpf_object__find_map_by_name(obj_fexit, "fexit_te.bss"); - if (CHECK(!data_map_fexit, "find_data_map", "data map not found\n")) + err = fexit_test__attach(fexit_skel); + if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) goto close_prog; + pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access); err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6), NULL, NULL, &retval, &duration); CHECK(err || retval, "ipv6", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration); - err = bpf_map_lookup_elem(bpf_map__fd(data_map_fentry), &zero, &result); - if (CHECK(err, "get_result", - "failed to get output data: %d\n", err)) - goto close_prog; - - err = bpf_map_lookup_elem(bpf_map__fd(data_map_fexit), &zero, result + 6); - if (CHECK(err, "get_result", - "failed to get output data: %d\n", err)) - goto close_prog; - - for (i = 0; i < 12; i++) - if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n", - i % 6 + 1, result[i])) - goto close_prog; + fentry_res = (__u64 *)fentry_skel->bss; + fexit_res = (__u64 *)fexit_skel->bss; + printf("%lld\n", fentry_skel->bss->test1_result); + for (i = 0; i < 6; i++) { + CHECK(fentry_res[i] != 1, "result", + "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]); + CHECK(fexit_res[i] != 1, "result", + "fexit_test%d failed err %lld\n", i + 1, fexit_res[i]); + } close_prog: - for (i = 0; i < 12; i++) - if (!IS_ERR_OR_NULL(link[i])) - bpf_link__destroy(link[i]); - bpf_object__close(obj_fentry); - bpf_object__close(obj_fexit); - bpf_object__close(pkt_obj); + test_pkt_access__destroy(pkt_skel); + fentry_test__destroy(fentry_skel); + fexit_test__destroy(fexit_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index 9fb103193878..e1a379f5f7d2 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -1,64 +1,43 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> +#include "test_pkt_access.skel.h" +#include "fentry_test.skel.h" void test_fentry_test(void) { - struct bpf_prog_load_attr attr = { - .file = "./fentry_test.o", - }; - - char prog_name[] = "fentry/bpf_fentry_testX"; - struct bpf_object *obj = NULL, *pkt_obj; - int err, pkt_fd, kfree_skb_fd, i; - struct bpf_link *link[6] = {}; - struct bpf_program *prog[6]; + struct test_pkt_access *pkt_skel = NULL; + struct fentry_test *fentry_skel = NULL; + int err, pkt_fd, i; __u32 duration, retval; - struct bpf_map *data_map; - const int zero = 0; - u64 result[6]; + __u64 *result; - err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, - &pkt_obj, &pkt_fd); - if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) + pkt_skel = test_pkt_access__open_and_load(); + if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n")) return; - err = bpf_prog_load_xattr(&attr, &obj, &kfree_skb_fd); - if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno)) - goto close_prog; + fentry_skel = fentry_test__open_and_load(); + if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) + goto cleanup; - for (i = 0; i < 6; i++) { - prog_name[sizeof(prog_name) - 2] = '1' + i; - prog[i] = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name)) - goto close_prog; - link[i] = bpf_program__attach_trace(prog[i]); - if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n")) - goto close_prog; - } - data_map = bpf_object__find_map_by_name(obj, "fentry_t.bss"); - if (CHECK(!data_map, "find_data_map", "data map not found\n")) - goto close_prog; + err = fentry_test__attach(fentry_skel); + if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) + goto cleanup; + pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access); err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6), NULL, NULL, &retval, &duration); CHECK(err || retval, "ipv6", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration); - err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result); - if (CHECK(err, "get_result", - "failed to get output data: %d\n", err)) - goto close_prog; - - for (i = 0; i < 6; i++) - if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n", - i + 1, result[i])) - goto close_prog; + result = (__u64 *)fentry_skel->bss; + for (i = 0; i < 6; i++) { + if (CHECK(result[i] != 1, "result", + "fentry_test%d failed err %lld\n", i + 1, result[i])) + goto cleanup; + } -close_prog: - for (i = 0; i < 6; i++) - if (!IS_ERR_OR_NULL(link[i])) - bpf_link__destroy(link[i]); - bpf_object__close(obj); - bpf_object__close(pkt_obj); +cleanup: + fentry_test__destroy(fentry_skel); + test_pkt_access__destroy(pkt_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 051a6d48762c..16a814eb4d64 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -1,16 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> #include <sys/mman.h> +#include "test_mmap.skel.h" struct map_data { __u64 val[512 * 4]; }; -struct bss_data { - __u64 in_val; - __u64 out_val; -}; - static size_t roundup_page(size_t sz) { long page_size = sysconf(_SC_PAGE_SIZE); @@ -19,41 +15,25 @@ static size_t roundup_page(size_t sz) void test_mmap(void) { - const char *file = "test_mmap.o"; - const char *probe_name = "raw_tracepoint/sys_enter"; - const char *tp_name = "sys_enter"; - const size_t bss_sz = roundup_page(sizeof(struct bss_data)); + const size_t bss_sz = roundup_page(sizeof(struct test_mmap__bss)); const size_t map_sz = roundup_page(sizeof(struct map_data)); const int zero = 0, one = 1, two = 2, far = 1500; const long page_size = sysconf(_SC_PAGE_SIZE); int err, duration = 0, i, data_map_fd; - struct bpf_program *prog; - struct bpf_object *obj; - struct bpf_link *link = NULL; struct bpf_map *data_map, *bss_map; void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2; - volatile struct bss_data *bss_data; - volatile struct map_data *map_data; + struct test_mmap__bss *bss_data; + struct map_data *map_data; + struct test_mmap *skel; __u64 val = 0; - obj = bpf_object__open_file("test_mmap.o", NULL); - if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n", - file, PTR_ERR(obj))) + + skel = test_mmap__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) return; - prog = bpf_object__find_program_by_title(obj, probe_name); - if (CHECK(!prog, "find_probe", "prog '%s' not found\n", probe_name)) - goto cleanup; - err = bpf_object__load(obj); - if (CHECK(err, "obj_load", "failed to load prog '%s': %d\n", - probe_name, err)) - goto cleanup; - bss_map = bpf_object__find_map_by_name(obj, "test_mma.bss"); - if (CHECK(!bss_map, "find_bss_map", ".bss map not found\n")) - goto cleanup; - data_map = bpf_object__find_map_by_name(obj, "data_map"); - if (CHECK(!data_map, "find_data_map", "data_map map not found\n")) - goto cleanup; + bss_map = skel->maps.bss; + data_map = skel->maps.data_map; data_map_fd = bpf_map__fd(data_map); bss_mmaped = mmap(NULL, bss_sz, PROT_READ | PROT_WRITE, MAP_SHARED, @@ -77,13 +57,15 @@ void test_mmap(void) CHECK_FAIL(bss_data->in_val); CHECK_FAIL(bss_data->out_val); + CHECK_FAIL(skel->bss->in_val); + CHECK_FAIL(skel->bss->out_val); CHECK_FAIL(map_data->val[0]); CHECK_FAIL(map_data->val[1]); CHECK_FAIL(map_data->val[2]); CHECK_FAIL(map_data->val[far]); - link = bpf_program__attach_raw_tracepoint(prog, tp_name); - if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link))) + err = test_mmap__attach(skel); + if (CHECK(err, "attach_raw_tp", "err %d\n", err)) goto cleanup; bss_data->in_val = 123; @@ -94,6 +76,8 @@ void test_mmap(void) CHECK_FAIL(bss_data->in_val != 123); CHECK_FAIL(bss_data->out_val != 123); + CHECK_FAIL(skel->bss->in_val != 123); + CHECK_FAIL(skel->bss->out_val != 123); CHECK_FAIL(map_data->val[0] != 111); CHECK_FAIL(map_data->val[1] != 222); CHECK_FAIL(map_data->val[2] != 123); @@ -160,6 +144,8 @@ void test_mmap(void) usleep(1); CHECK_FAIL(bss_data->in_val != 321); CHECK_FAIL(bss_data->out_val != 321); + CHECK_FAIL(skel->bss->in_val != 321); + CHECK_FAIL(skel->bss->out_val != 321); CHECK_FAIL(map_data->val[0] != 111); CHECK_FAIL(map_data->val[1] != 222); CHECK_FAIL(map_data->val[2] != 321); @@ -203,6 +189,8 @@ void test_mmap(void) map_data = tmp2; CHECK_FAIL(bss_data->in_val != 321); CHECK_FAIL(bss_data->out_val != 321); + CHECK_FAIL(skel->bss->in_val != 321); + CHECK_FAIL(skel->bss->out_val != 321); CHECK_FAIL(map_data->val[0] != 111); CHECK_FAIL(map_data->val[1] != 222); CHECK_FAIL(map_data->val[2] != 321); @@ -214,7 +202,5 @@ cleanup: CHECK_FAIL(munmap(bss_mmaped, bss_sz)); if (map_mmaped) CHECK_FAIL(munmap(map_mmaped, map_sz)); - if (!IS_ERR_OR_NULL(link)) - bpf_link__destroy(link); - bpf_object__close(obj); + test_mmap__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index 3003fddc0613..cf6c87936c69 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -4,6 +4,7 @@ #include <sched.h> #include <sys/socket.h> #include <test_progs.h> +#include "libbpf_internal.h" static void on_sample(void *ctx, int cpu, void *data, __u32 size) { @@ -19,7 +20,7 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) void test_perf_buffer(void) { - int err, prog_fd, nr_cpus, i, duration = 0; + int err, prog_fd, on_len, nr_on_cpus = 0, nr_cpus, i, duration = 0; const char *prog_name = "kprobe/sys_nanosleep"; const char *file = "./test_perf_buffer.o"; struct perf_buffer_opts pb_opts = {}; @@ -29,15 +30,27 @@ void test_perf_buffer(void) struct bpf_object *obj; struct perf_buffer *pb; struct bpf_link *link; + bool *online; nr_cpus = libbpf_num_possible_cpus(); if (CHECK(nr_cpus < 0, "nr_cpus", "err %d\n", nr_cpus)) return; + err = parse_cpu_mask_file("/sys/devices/system/cpu/online", + &online, &on_len); + if (CHECK(err, "nr_on_cpus", "err %d\n", err)) + return; + + for (i = 0; i < on_len; i++) + if (online[i]) + nr_on_cpus++; + /* load program */ err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd); - if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) - return; + if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) { + obj = NULL; + goto out_close; + } prog = bpf_object__find_program_by_title(obj, prog_name); if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name)) @@ -64,6 +77,11 @@ void test_perf_buffer(void) /* trigger kprobe on every CPU */ CPU_ZERO(&cpu_seen); for (i = 0; i < nr_cpus; i++) { + if (i >= on_len || !online[i]) { + printf("skipping offline CPU #%d\n", i); + continue; + } + CPU_ZERO(&cpu_set); CPU_SET(i, &cpu_set); @@ -81,8 +99,8 @@ void test_perf_buffer(void) if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err)) goto out_free_pb; - if (CHECK(CPU_COUNT(&cpu_seen) != nr_cpus, "seen_cpu_cnt", - "expect %d, seen %d\n", nr_cpus, CPU_COUNT(&cpu_seen))) + if (CHECK(CPU_COUNT(&cpu_seen) != nr_on_cpus, "seen_cpu_cnt", + "expect %d, seen %d\n", nr_on_cpus, CPU_COUNT(&cpu_seen))) goto out_free_pb; out_free_pb: @@ -91,4 +109,5 @@ out_detach: bpf_link__destroy(link); out_close: bpf_object__close(obj); + free(online); } diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c index 8a3187dec048..7aecfd9e87d1 100644 --- a/tools/testing/selftests/bpf/prog_tests/probe_user.c +++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c @@ -3,8 +3,7 @@ void test_probe_user(void) { -#define kprobe_name "__sys_connect" - const char *prog_name = "kprobe/" kprobe_name; + const char *prog_name = "kprobe/__sys_connect"; const char *obj_file = "./test_probe_user.o"; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, ); int err, results_map_fd, sock_fd, duration = 0; @@ -33,8 +32,7 @@ void test_probe_user(void) "err %d\n", results_map_fd)) goto cleanup; - kprobe_link = bpf_program__attach_kprobe(kprobe_prog, false, - kprobe_name); + kprobe_link = bpf_program__attach(kprobe_prog); if (CHECK(IS_ERR(kprobe_link), "attach_kprobe", "err %ld\n", PTR_ERR(kprobe_link))) { kprobe_link = NULL; diff --git a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c index d90acc13d1ec..563e12120e77 100644 --- a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c +++ b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c @@ -16,14 +16,11 @@ struct rdonly_map_subtest { void test_rdonly_maps(void) { - const char *prog_name_skip_loop = "raw_tracepoint/sys_enter:skip_loop"; - const char *prog_name_part_loop = "raw_tracepoint/sys_enter:part_loop"; - const char *prog_name_full_loop = "raw_tracepoint/sys_enter:full_loop"; const char *file = "test_rdonly_maps.o"; struct rdonly_map_subtest subtests[] = { - { "skip loop", prog_name_skip_loop, 0, 0 }, - { "part loop", prog_name_part_loop, 3, 2 + 3 + 4 }, - { "full loop", prog_name_full_loop, 4, 2 + 3 + 4 + 5 }, + { "skip loop", "skip_loop", 0, 0 }, + { "part loop", "part_loop", 3, 2 + 3 + 4 }, + { "full loop", "full_loop", 4, 2 + 3 + 4 + 5 }, }; int i, err, zero = 0, duration = 0; struct bpf_link *link = NULL; @@ -50,7 +47,7 @@ void test_rdonly_maps(void) if (!test__start_subtest(t->subtest_name)) continue; - prog = bpf_object__find_program_by_title(obj, t->prog_name); + prog = bpf_object__find_program_by_name(obj, t->prog_name); if (CHECK(!prog, "find_prog", "prog '%s' not found\n", t->prog_name)) goto cleanup; diff --git a/tools/testing/selftests/bpf/test_select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 7566c13eb51a..2c37ae7dc214 100644 --- a/tools/testing/selftests/bpf/test_select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -20,8 +20,11 @@ #include <bpf/libbpf.h> #include "bpf_rlimit.h" #include "bpf_util.h" + +#include "test_progs.h" #include "test_select_reuseport_common.h" +#define MAX_TEST_NAME 80 #define MIN_TCPHDR_LEN 20 #define UDPHDR_LEN 8 @@ -32,11 +35,11 @@ static int result_map, tmp_index_ovr_map, linum_map, data_check_map; static enum result expected_results[NR_RESULTS]; static int sk_fds[REUSEPORT_ARRAY_SIZE]; -static int reuseport_array, outer_map; +static int reuseport_array = -1, outer_map = -1; static int select_by_skb_data_prog; -static int saved_tcp_syncookie; +static int saved_tcp_syncookie = -1; static struct bpf_object *obj; -static int saved_tcp_fo; +static int saved_tcp_fo = -1; static __u32 index_zero; static int epfd; @@ -46,16 +49,21 @@ static union sa46 { sa_family_t family; } srv_sa; -#define CHECK(condition, tag, format...) ({ \ - int __ret = !!(condition); \ - if (__ret) { \ - printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag); \ - printf(format); \ - exit(-1); \ +#define RET_IF(condition, tag, format...) ({ \ + if (CHECK_FAIL(condition)) { \ + printf(tag " " format); \ + return; \ + } \ +}) + +#define RET_ERR(condition, tag, format...) ({ \ + if (CHECK_FAIL(condition)) { \ + printf(tag " " format); \ + return -1; \ } \ }) -static void create_maps(void) +static int create_maps(void) { struct bpf_create_map_attr attr = {}; @@ -67,8 +75,8 @@ static void create_maps(void) attr.max_entries = REUSEPORT_ARRAY_SIZE; reuseport_array = bpf_create_map_xattr(&attr); - CHECK(reuseport_array == -1, "creating reuseport_array", - "reuseport_array:%d errno:%d\n", reuseport_array, errno); + RET_ERR(reuseport_array == -1, "creating reuseport_array", + "reuseport_array:%d errno:%d\n", reuseport_array, errno); /* Creating outer_map */ attr.name = "outer_map"; @@ -78,63 +86,61 @@ static void create_maps(void) attr.max_entries = 1; attr.inner_map_fd = reuseport_array; outer_map = bpf_create_map_xattr(&attr); - CHECK(outer_map == -1, "creating outer_map", - "outer_map:%d errno:%d\n", outer_map, errno); + RET_ERR(outer_map == -1, "creating outer_map", + "outer_map:%d errno:%d\n", outer_map, errno); + + return 0; } -static void prepare_bpf_obj(void) +static int prepare_bpf_obj(void) { struct bpf_program *prog; struct bpf_map *map; int err; - struct bpf_object_open_attr attr = { - .file = "test_select_reuseport_kern.o", - .prog_type = BPF_PROG_TYPE_SK_REUSEPORT, - }; - obj = bpf_object__open_xattr(&attr); - CHECK(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o", - "obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj)); - - prog = bpf_program__next(NULL, obj); - CHECK(!prog, "get first bpf_program", "!prog\n"); - bpf_program__set_type(prog, attr.prog_type); + obj = bpf_object__open("test_select_reuseport_kern.o"); + RET_ERR(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o", + "obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj)); map = bpf_object__find_map_by_name(obj, "outer_map"); - CHECK(!map, "find outer_map", "!map\n"); + RET_ERR(!map, "find outer_map", "!map\n"); err = bpf_map__reuse_fd(map, outer_map); - CHECK(err, "reuse outer_map", "err:%d\n", err); + RET_ERR(err, "reuse outer_map", "err:%d\n", err); err = bpf_object__load(obj); - CHECK(err, "load bpf_object", "err:%d\n", err); + RET_ERR(err, "load bpf_object", "err:%d\n", err); + prog = bpf_program__next(NULL, obj); + RET_ERR(!prog, "get first bpf_program", "!prog\n"); select_by_skb_data_prog = bpf_program__fd(prog); - CHECK(select_by_skb_data_prog == -1, "get prog fd", - "select_by_skb_data_prog:%d\n", select_by_skb_data_prog); + RET_ERR(select_by_skb_data_prog == -1, "get prog fd", + "select_by_skb_data_prog:%d\n", select_by_skb_data_prog); map = bpf_object__find_map_by_name(obj, "result_map"); - CHECK(!map, "find result_map", "!map\n"); + RET_ERR(!map, "find result_map", "!map\n"); result_map = bpf_map__fd(map); - CHECK(result_map == -1, "get result_map fd", - "result_map:%d\n", result_map); + RET_ERR(result_map == -1, "get result_map fd", + "result_map:%d\n", result_map); map = bpf_object__find_map_by_name(obj, "tmp_index_ovr_map"); - CHECK(!map, "find tmp_index_ovr_map", "!map\n"); + RET_ERR(!map, "find tmp_index_ovr_map\n", "!map"); tmp_index_ovr_map = bpf_map__fd(map); - CHECK(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd", - "tmp_index_ovr_map:%d\n", tmp_index_ovr_map); + RET_ERR(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd", + "tmp_index_ovr_map:%d\n", tmp_index_ovr_map); map = bpf_object__find_map_by_name(obj, "linum_map"); - CHECK(!map, "find linum_map", "!map\n"); + RET_ERR(!map, "find linum_map", "!map\n"); linum_map = bpf_map__fd(map); - CHECK(linum_map == -1, "get linum_map fd", - "linum_map:%d\n", linum_map); + RET_ERR(linum_map == -1, "get linum_map fd", + "linum_map:%d\n", linum_map); map = bpf_object__find_map_by_name(obj, "data_check_map"); - CHECK(!map, "find data_check_map", "!map\n"); + RET_ERR(!map, "find data_check_map", "!map\n"); data_check_map = bpf_map__fd(map); - CHECK(data_check_map == -1, "get data_check_map fd", - "data_check_map:%d\n", data_check_map); + RET_ERR(data_check_map == -1, "get data_check_map fd", + "data_check_map:%d\n", data_check_map); + + return 0; } static void sa46_init_loopback(union sa46 *sa, sa_family_t family) @@ -163,65 +169,73 @@ static int read_int_sysctl(const char *sysctl) int fd, ret; fd = open(sysctl, 0); - CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n", - sysctl, fd, errno); + RET_ERR(fd == -1, "open(sysctl)", + "sysctl:%s fd:%d errno:%d\n", sysctl, fd, errno); ret = read(fd, buf, sizeof(buf)); - CHECK(ret <= 0, "read(sysctl)", "sysctl:%s ret:%d errno:%d\n", - sysctl, ret, errno); - close(fd); + RET_ERR(ret <= 0, "read(sysctl)", + "sysctl:%s ret:%d errno:%d\n", sysctl, ret, errno); + close(fd); return atoi(buf); } -static void write_int_sysctl(const char *sysctl, int v) +static int write_int_sysctl(const char *sysctl, int v) { int fd, ret, size; char buf[16]; fd = open(sysctl, O_RDWR); - CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n", - sysctl, fd, errno); + RET_ERR(fd == -1, "open(sysctl)", + "sysctl:%s fd:%d errno:%d\n", sysctl, fd, errno); size = snprintf(buf, sizeof(buf), "%d", v); ret = write(fd, buf, size); - CHECK(ret != size, "write(sysctl)", - "sysctl:%s ret:%d size:%d errno:%d\n", sysctl, ret, size, errno); + RET_ERR(ret != size, "write(sysctl)", + "sysctl:%s ret:%d size:%d errno:%d\n", + sysctl, ret, size, errno); + close(fd); + return 0; } static void restore_sysctls(void) { - write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo); - write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie); + if (saved_tcp_fo != -1) + write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo); + if (saved_tcp_syncookie != -1) + write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie); } -static void enable_fastopen(void) +static int enable_fastopen(void) { int fo; fo = read_int_sysctl(TCP_FO_SYSCTL); - write_int_sysctl(TCP_FO_SYSCTL, fo | 7); + if (fo < 0) + return -1; + + return write_int_sysctl(TCP_FO_SYSCTL, fo | 7); } -static void enable_syncookie(void) +static int enable_syncookie(void) { - write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 2); + return write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 2); } -static void disable_syncookie(void) +static int disable_syncookie(void) { - write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 0); + return write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 0); } -static __u32 get_linum(void) +static long get_linum(void) { __u32 linum; int err; err = bpf_map_lookup_elem(linum_map, &index_zero, &linum); - CHECK(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n", - err, errno); + RET_ERR(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n", + err, errno); return linum; } @@ -237,12 +251,12 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, addrlen = sizeof(cli_sa); err = getsockname(cli_fd, (struct sockaddr *)&cli_sa, &addrlen); - CHECK(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n", - err, errno); + RET_IF(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n", + err, errno); err = bpf_map_lookup_elem(data_check_map, &index_zero, &result); - CHECK(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n", - err, errno); + RET_IF(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n", + err, errno); if (type == SOCK_STREAM) { expected.len = MIN_TCPHDR_LEN; @@ -284,22 +298,22 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, printf("expected: (0x%x, %u, %u)\n", expected.eth_protocol, expected.ip_protocol, expected.bind_inany); - CHECK(1, "data_check result != expected", - "bpf_prog_linum:%u\n", get_linum()); + RET_IF(1, "data_check result != expected", + "bpf_prog_linum:%ld\n", get_linum()); } - CHECK(!result.hash, "data_check result.hash empty", - "result.hash:%u", result.hash); + RET_IF(!result.hash, "data_check result.hash empty", + "result.hash:%u", result.hash); expected.len += cmd ? sizeof(*cmd) : 0; if (type == SOCK_STREAM) - CHECK(expected.len > result.len, "expected.len > result.len", - "expected.len:%u result.len:%u bpf_prog_linum:%u\n", - expected.len, result.len, get_linum()); + RET_IF(expected.len > result.len, "expected.len > result.len", + "expected.len:%u result.len:%u bpf_prog_linum:%ld\n", + expected.len, result.len, get_linum()); else - CHECK(expected.len != result.len, "expected.len != result.len", - "expected.len:%u result.len:%u bpf_prog_linum:%u\n", - expected.len, result.len, get_linum()); + RET_IF(expected.len != result.len, "expected.len != result.len", + "expected.len:%u result.len:%u bpf_prog_linum:%ld\n", + expected.len, result.len, get_linum()); } static void check_results(void) @@ -310,8 +324,8 @@ static void check_results(void) for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &results[i]); - CHECK(err == -1, "lookup_elem(result_map)", - "i:%u err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); } for (i = 0; i < NR_RESULTS; i++) { @@ -337,10 +351,10 @@ static void check_results(void) printf(", %u", expected_results[i]); printf("]\n"); - CHECK(expected_results[broken] != results[broken], - "unexpected result", - "expected_results[%u] != results[%u] bpf_prog_linum:%u\n", - broken, broken, get_linum()); + RET_IF(expected_results[broken] != results[broken], + "unexpected result", + "expected_results[%u] != results[%u] bpf_prog_linum:%ld\n", + broken, broken, get_linum()); } static int send_data(int type, sa_family_t family, void *data, size_t len, @@ -350,17 +364,17 @@ static int send_data(int type, sa_family_t family, void *data, size_t len, int fd, err; fd = socket(family, type, 0); - CHECK(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno); + RET_ERR(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno); sa46_init_loopback(&cli_sa, family); err = bind(fd, (struct sockaddr *)&cli_sa, sizeof(cli_sa)); - CHECK(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno); + RET_ERR(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno); err = sendto(fd, data, len, MSG_FASTOPEN, (struct sockaddr *)&srv_sa, sizeof(srv_sa)); - CHECK(err != len && expected >= PASS, - "sendto()", "family:%u err:%d errno:%d expected:%d\n", - family, err, errno, expected); + RET_ERR(err != len && expected >= PASS, + "sendto()", "family:%u err:%d errno:%d expected:%d\n", + family, err, errno, expected); return fd; } @@ -375,47 +389,49 @@ static void do_test(int type, sa_family_t family, struct cmd *cmd, cli_fd = send_data(type, family, cmd, cmd ? sizeof(*cmd) : 0, expected); + if (cli_fd < 0) + return; nev = epoll_wait(epfd, &ev, 1, expected >= PASS ? 5 : 0); - CHECK((nev <= 0 && expected >= PASS) || - (nev > 0 && expected < PASS), - "nev <> expected", - "nev:%d expected:%d type:%d family:%d data:(%d, %d)\n", - nev, expected, type, family, - cmd ? cmd->reuseport_index : -1, - cmd ? cmd->pass_on_failure : -1); + RET_IF((nev <= 0 && expected >= PASS) || + (nev > 0 && expected < PASS), + "nev <> expected", + "nev:%d expected:%d type:%d family:%d data:(%d, %d)\n", + nev, expected, type, family, + cmd ? cmd->reuseport_index : -1, + cmd ? cmd->pass_on_failure : -1); check_results(); check_data(type, family, cmd, cli_fd); if (expected < PASS) return; - CHECK(expected != PASS_ERR_SK_SELECT_REUSEPORT && - cmd->reuseport_index != ev.data.u32, - "check cmd->reuseport_index", - "cmd:(%u, %u) ev.data.u32:%u\n", - cmd->pass_on_failure, cmd->reuseport_index, ev.data.u32); + RET_IF(expected != PASS_ERR_SK_SELECT_REUSEPORT && + cmd->reuseport_index != ev.data.u32, + "check cmd->reuseport_index", + "cmd:(%u, %u) ev.data.u32:%u\n", + cmd->pass_on_failure, cmd->reuseport_index, ev.data.u32); srv_fd = sk_fds[ev.data.u32]; if (type == SOCK_STREAM) { int new_fd = accept(srv_fd, NULL, 0); - CHECK(new_fd == -1, "accept(srv_fd)", - "ev.data.u32:%u new_fd:%d errno:%d\n", - ev.data.u32, new_fd, errno); + RET_IF(new_fd == -1, "accept(srv_fd)", + "ev.data.u32:%u new_fd:%d errno:%d\n", + ev.data.u32, new_fd, errno); nread = recv(new_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT); - CHECK(nread != sizeof(rcv_cmd), - "recv(new_fd)", - "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", - ev.data.u32, nread, sizeof(rcv_cmd), errno); + RET_IF(nread != sizeof(rcv_cmd), + "recv(new_fd)", + "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", + ev.data.u32, nread, sizeof(rcv_cmd), errno); close(new_fd); } else { nread = recv(srv_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT); - CHECK(nread != sizeof(rcv_cmd), - "recv(sk_fds)", - "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", - ev.data.u32, nread, sizeof(rcv_cmd), errno); + RET_IF(nread != sizeof(rcv_cmd), + "recv(sk_fds)", + "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n", + ev.data.u32, nread, sizeof(rcv_cmd), errno); } close(cli_fd); @@ -428,18 +444,14 @@ static void test_err_inner_map(int type, sa_family_t family) .pass_on_failure = 0, }; - printf("%s: ", __func__); expected_results[DROP_ERR_INNER_MAP]++; do_test(type, family, &cmd, DROP_ERR_INNER_MAP); - printf("OK\n"); } static void test_err_skb_data(int type, sa_family_t family) { - printf("%s: ", __func__); expected_results[DROP_ERR_SKB_DATA]++; do_test(type, family, NULL, DROP_ERR_SKB_DATA); - printf("OK\n"); } static void test_err_sk_select_port(int type, sa_family_t family) @@ -449,10 +461,8 @@ static void test_err_sk_select_port(int type, sa_family_t family) .pass_on_failure = 0, }; - printf("%s: ", __func__); expected_results[DROP_ERR_SK_SELECT_REUSEPORT]++; do_test(type, family, &cmd, DROP_ERR_SK_SELECT_REUSEPORT); - printf("OK\n"); } static void test_pass(int type, sa_family_t family) @@ -460,14 +470,12 @@ static void test_pass(int type, sa_family_t family) struct cmd cmd; int i; - printf("%s: ", __func__); cmd.pass_on_failure = 0; for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) { expected_results[PASS]++; cmd.reuseport_index = i; do_test(type, family, &cmd, PASS); } - printf("OK\n"); } static void test_syncookie(int type, sa_family_t family) @@ -481,7 +489,6 @@ static void test_syncookie(int type, sa_family_t family) if (type != SOCK_STREAM) return; - printf("%s: ", __func__); /* * +1 for TCP-SYN and * +1 for the TCP-ACK (ack the syncookie) @@ -497,17 +504,16 @@ static void test_syncookie(int type, sa_family_t family) */ err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &tmp_index, BPF_ANY); - CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)", + "err:%d errno:%d\n", err, errno); do_test(type, family, &cmd, PASS); err = bpf_map_lookup_elem(tmp_index_ovr_map, &index_zero, &tmp_index); - CHECK(err == -1 || tmp_index != -1, - "lookup_elem(tmp_index_ovr_map)", - "err:%d errno:%d tmp_index:%d\n", - err, errno, tmp_index); + RET_IF(err == -1 || tmp_index != -1, + "lookup_elem(tmp_index_ovr_map)", + "err:%d errno:%d tmp_index:%d\n", + err, errno, tmp_index); disable_syncookie(); - printf("OK\n"); } static void test_pass_on_err(int type, sa_family_t family) @@ -517,10 +523,8 @@ static void test_pass_on_err(int type, sa_family_t family) .pass_on_failure = 1, }; - printf("%s: ", __func__); expected_results[PASS_ERR_SK_SELECT_REUSEPORT] += 1; do_test(type, family, &cmd, PASS_ERR_SK_SELECT_REUSEPORT); - printf("OK\n"); } static void test_detach_bpf(int type, sa_family_t family) @@ -532,46 +536,47 @@ static void test_detach_bpf(int type, sa_family_t family) struct cmd cmd = {}; int optvalue = 0; - printf("%s: ", __func__); err = setsockopt(sk_fds[0], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF, &optvalue, sizeof(optvalue)); - CHECK(err == -1, "setsockopt(SO_DETACH_REUSEPORT_BPF)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "setsockopt(SO_DETACH_REUSEPORT_BPF)", + "err:%d errno:%d\n", err, errno); err = setsockopt(sk_fds[1], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF, &optvalue, sizeof(optvalue)); - CHECK(err == 0 || errno != ENOENT, "setsockopt(SO_DETACH_REUSEPORT_BPF)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == 0 || errno != ENOENT, + "setsockopt(SO_DETACH_REUSEPORT_BPF)", + "err:%d errno:%d\n", err, errno); for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &tmp); - CHECK(err == -1, "lookup_elem(result_map)", - "i:%u err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); nr_run_before += tmp; } cli_fd = send_data(type, family, &cmd, sizeof(cmd), PASS); + if (cli_fd < 0) + return; nev = epoll_wait(epfd, &ev, 1, 5); - CHECK(nev <= 0, "nev <= 0", - "nev:%d expected:1 type:%d family:%d data:(0, 0)\n", - nev, type, family); + RET_IF(nev <= 0, "nev <= 0", + "nev:%d expected:1 type:%d family:%d data:(0, 0)\n", + nev, type, family); for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &tmp); - CHECK(err == -1, "lookup_elem(result_map)", - "i:%u err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "lookup_elem(result_map)", + "i:%u err:%d errno:%d\n", i, err, errno); nr_run_after += tmp; } - CHECK(nr_run_before != nr_run_after, - "nr_run_before != nr_run_after", - "nr_run_before:%u nr_run_after:%u\n", - nr_run_before, nr_run_after); + RET_IF(nr_run_before != nr_run_after, + "nr_run_before != nr_run_after", + "nr_run_before:%u nr_run_after:%u\n", + nr_run_before, nr_run_after); - printf("OK\n"); close(cli_fd); #else - printf("%s: SKIP\n", __func__); + test__skip(); #endif } @@ -594,73 +599,83 @@ static void prepare_sk_fds(int type, sa_family_t family, bool inany) */ for (i = first; i >= 0; i--) { sk_fds[i] = socket(family, type, 0); - CHECK(sk_fds[i] == -1, "socket()", "sk_fds[%d]:%d errno:%d\n", - i, sk_fds[i], errno); + RET_IF(sk_fds[i] == -1, "socket()", "sk_fds[%d]:%d errno:%d\n", + i, sk_fds[i], errno); err = setsockopt(sk_fds[i], SOL_SOCKET, SO_REUSEPORT, &optval, sizeof(optval)); - CHECK(err == -1, "setsockopt(SO_REUSEPORT)", - "sk_fds[%d] err:%d errno:%d\n", - i, err, errno); + RET_IF(err == -1, "setsockopt(SO_REUSEPORT)", + "sk_fds[%d] err:%d errno:%d\n", + i, err, errno); if (i == first) { err = setsockopt(sk_fds[i], SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &select_by_skb_data_prog, sizeof(select_by_skb_data_prog)); - CHECK(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)", + "err:%d errno:%d\n", err, errno); } err = bind(sk_fds[i], (struct sockaddr *)&srv_sa, addrlen); - CHECK(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n", - i, err, errno); + RET_IF(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n", + i, err, errno); if (type == SOCK_STREAM) { err = listen(sk_fds[i], 10); - CHECK(err == -1, "listen()", - "sk_fds[%d] err:%d errno:%d\n", - i, err, errno); + RET_IF(err == -1, "listen()", + "sk_fds[%d] err:%d errno:%d\n", + i, err, errno); } err = bpf_map_update_elem(reuseport_array, &i, &sk_fds[i], BPF_NOEXIST); - CHECK(err == -1, "update_elem(reuseport_array)", - "sk_fds[%d] err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "update_elem(reuseport_array)", + "sk_fds[%d] err:%d errno:%d\n", i, err, errno); if (i == first) { socklen_t addrlen = sizeof(srv_sa); err = getsockname(sk_fds[i], (struct sockaddr *)&srv_sa, &addrlen); - CHECK(err == -1, "getsockname()", - "sk_fds[%d] err:%d errno:%d\n", i, err, errno); + RET_IF(err == -1, "getsockname()", + "sk_fds[%d] err:%d errno:%d\n", i, err, errno); } } epfd = epoll_create(1); - CHECK(epfd == -1, "epoll_create(1)", - "epfd:%d errno:%d\n", epfd, errno); + RET_IF(epfd == -1, "epoll_create(1)", + "epfd:%d errno:%d\n", epfd, errno); ev.events = EPOLLIN; for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) { ev.data.u32 = i; err = epoll_ctl(epfd, EPOLL_CTL_ADD, sk_fds[i], &ev); - CHECK(err, "epoll_ctl(EPOLL_CTL_ADD)", "sk_fds[%d]\n", i); + RET_IF(err, "epoll_ctl(EPOLL_CTL_ADD)", "sk_fds[%d]\n", i); } } -static void setup_per_test(int type, unsigned short family, bool inany) +static void setup_per_test(int type, sa_family_t family, bool inany, + bool no_inner_map) { int ovr = -1, err; prepare_sk_fds(type, family, inany); err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &ovr, BPF_ANY); - CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)", + "err:%d errno:%d\n", err, errno); + + /* Install reuseport_array to outer_map? */ + if (no_inner_map) + return; + + err = bpf_map_update_elem(outer_map, &index_zero, &reuseport_array, + BPF_ANY); + RET_IF(err == -1, "update_elem(outer_map, 0, reuseport_array)", + "err:%d errno:%d\n", err, errno); } -static void cleanup_per_test(void) +static void cleanup_per_test(bool no_inner_map) { int i, err; @@ -668,75 +683,124 @@ static void cleanup_per_test(void) close(sk_fds[i]); close(epfd); + /* Delete reuseport_array from outer_map? */ + if (no_inner_map) + return; + err = bpf_map_delete_elem(outer_map, &index_zero); - CHECK(err == -1, "delete_elem(outer_map)", - "err:%d errno:%d\n", err, errno); + RET_IF(err == -1, "delete_elem(outer_map)", + "err:%d errno:%d\n", err, errno); } static void cleanup(void) { - close(outer_map); - close(reuseport_array); - bpf_object__close(obj); + if (outer_map != -1) + close(outer_map); + if (reuseport_array != -1) + close(reuseport_array); + if (obj) + bpf_object__close(obj); } -static void test_all(void) +static const char *family_str(sa_family_t family) { - /* Extra SOCK_STREAM to test bind_inany==true */ - const int types[] = { SOCK_STREAM, SOCK_DGRAM, SOCK_STREAM }; - const char * const type_strings[] = { "TCP", "UDP", "TCP" }; - const char * const family_strings[] = { "IPv6", "IPv4" }; - const unsigned short families[] = { AF_INET6, AF_INET }; - const bool bind_inany[] = { false, false, true }; - int t, f, err; - - for (f = 0; f < ARRAY_SIZE(families); f++) { - unsigned short family = families[f]; - - for (t = 0; t < ARRAY_SIZE(types); t++) { - bool inany = bind_inany[t]; - int type = types[t]; - - printf("######## %s/%s %s ########\n", - family_strings[f], type_strings[t], - inany ? " INANY " : "LOOPBACK"); - - setup_per_test(type, family, inany); - - test_err_inner_map(type, family); - - /* Install reuseport_array to the outer_map */ - err = bpf_map_update_elem(outer_map, &index_zero, - &reuseport_array, BPF_ANY); - CHECK(err == -1, "update_elem(outer_map)", - "err:%d errno:%d\n", err, errno); - - test_err_skb_data(type, family); - test_err_sk_select_port(type, family); - test_pass(type, family); - test_syncookie(type, family); - test_pass_on_err(type, family); - /* Must be the last test */ - test_detach_bpf(type, family); - - cleanup_per_test(); - printf("\n"); - } + switch (family) { + case AF_INET: + return "IPv4"; + case AF_INET6: + return "IPv6"; + default: + return "unknown"; + } +} + +static const char *sotype_str(int sotype) +{ + switch (sotype) { + case SOCK_STREAM: + return "TCP"; + case SOCK_DGRAM: + return "UDP"; + default: + return "unknown"; + } +} + +#define TEST_INIT(fn, ...) { fn, #fn, __VA_ARGS__ } + +static void test_config(int sotype, sa_family_t family, bool inany) +{ + const struct test { + void (*fn)(int sotype, sa_family_t family); + const char *name; + bool no_inner_map; + } tests[] = { + TEST_INIT(test_err_inner_map, true /* no_inner_map */), + TEST_INIT(test_err_skb_data), + TEST_INIT(test_err_sk_select_port), + TEST_INIT(test_pass), + TEST_INIT(test_syncookie), + TEST_INIT(test_pass_on_err), + TEST_INIT(test_detach_bpf), + }; + char s[MAX_TEST_NAME]; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + snprintf(s, sizeof(s), "%s/%s %s %s", + family_str(family), sotype_str(sotype), + inany ? "INANY" : "LOOPBACK", t->name); + + if (!test__start_subtest(s)) + continue; + + setup_per_test(sotype, family, inany, t->no_inner_map); + t->fn(sotype, family); + cleanup_per_test(t->no_inner_map); } } -int main(int argc, const char **argv) +#define BIND_INANY true + +static void test_all(void) { - create_maps(); - prepare_bpf_obj(); + const struct config { + int sotype; + sa_family_t family; + bool inany; + } configs[] = { + { SOCK_STREAM, AF_INET }, + { SOCK_STREAM, AF_INET, BIND_INANY }, + { SOCK_STREAM, AF_INET6 }, + { SOCK_STREAM, AF_INET6, BIND_INANY }, + { SOCK_DGRAM, AF_INET }, + { SOCK_DGRAM, AF_INET6 }, + }; + const struct config *c; + + for (c = configs; c < configs + ARRAY_SIZE(configs); c++) + test_config(c->sotype, c->family, c->inany); +} + +void test_select_reuseport(void) +{ + if (create_maps()) + goto out; + if (prepare_bpf_obj()) + goto out; + saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL); - enable_fastopen(); - disable_syncookie(); - atexit(restore_sysctls); + if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0) + goto out; - test_all(); + if (enable_fastopen()) + goto out; + if (disable_syncookie()) + goto out; + test_all(); +out: cleanup(); - return 0; + restore_sysctls(); } diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index a2eb8db8dafb..c6d6b685a946 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -11,6 +11,9 @@ void test_skb_ctx(void) .cb[4] = 5, .priority = 6, .tstamp = 7, + .wire_len = 100, + .gso_segs = 8, + .mark = 9, }; struct bpf_prog_test_run_attr tattr = { .data_in = &pkt_v4, @@ -91,4 +94,8 @@ void test_skb_ctx(void) "ctx_out_tstamp", "skb->tstamp == %lld, expected %d\n", skb.tstamp, 8); + CHECK_ATTR(skb.mark != 10, + "ctx_out_mark", + "skb->mark == %u, expected %d\n", + skb.mark, 10); } diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c new file mode 100644 index 000000000000..9264a2736018 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <test_progs.h> + +struct s { + int a; + long long b; +} __attribute__((packed)); + +#include "test_skeleton.skel.h" + +void test_skeleton(void) +{ + int duration = 0, err; + struct test_skeleton* skel; + struct test_skeleton__bss *bss; + struct test_skeleton__kconfig *kcfg; + + skel = test_skeleton__open(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + + if (CHECK(skel->kconfig, "skel_kconfig", "kconfig is mmaped()!\n")) + goto cleanup; + + err = test_skeleton__load(skel); + if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + goto cleanup; + + bss = skel->bss; + bss->in1 = 1; + bss->in2 = 2; + bss->in3 = 3; + bss->in4 = 4; + bss->in5.a = 5; + bss->in5.b = 6; + kcfg = skel->kconfig; + + err = test_skeleton__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + /* trigger tracepoint */ + usleep(1); + + CHECK(bss->out1 != 1, "res1", "got %d != exp %d\n", bss->out1, 1); + CHECK(bss->out2 != 2, "res2", "got %lld != exp %d\n", bss->out2, 2); + CHECK(bss->out3 != 3, "res3", "got %d != exp %d\n", (int)bss->out3, 3); + CHECK(bss->out4 != 4, "res4", "got %lld != exp %d\n", bss->out4, 4); + CHECK(bss->handler_out5.a != 5, "res5", "got %d != exp %d\n", + bss->handler_out5.a, 5); + CHECK(bss->handler_out5.b != 6, "res6", "got %lld != exp %d\n", + bss->handler_out5.b, 6); + + CHECK(bss->bpf_syscall != kcfg->CONFIG_BPF_SYSCALL, "ext1", + "got %d != exp %d\n", bss->bpf_syscall, kcfg->CONFIG_BPF_SYSCALL); + CHECK(bss->kern_ver != kcfg->LINUX_KERNEL_VERSION, "ext2", + "got %d != exp %d\n", bss->kern_ver, kcfg->LINUX_KERNEL_VERSION); + +cleanup: + test_skeleton__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c index d841dced971f..e8399ae50e77 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c @@ -1,16 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include "test_stacktrace_build_id.skel.h" void test_stacktrace_build_id(void) { + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; - const char *prog_name = "tracepoint/random/urandom_read"; - const char *file = "./test_stacktrace_build_id.o"; - int err, prog_fd, stack_trace_len; + struct test_stacktrace_build_id *skel; + int err, stack_trace_len; __u32 key, previous_key, val, duration = 0; - struct bpf_program *prog; - struct bpf_object *obj; - struct bpf_link *link = NULL; char buf[256]; int i, j; struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH]; @@ -18,43 +16,24 @@ void test_stacktrace_build_id(void) int retry = 1; retry: - err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); - if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) + skel = test_stacktrace_build_id__open_and_load(); + if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n")) return; - prog = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name)) - goto close_prog; - - link = bpf_program__attach_tracepoint(prog, "random", "urandom_read"); - if (CHECK(IS_ERR(link), "attach_tp", "err %ld\n", PTR_ERR(link))) - goto close_prog; + err = test_stacktrace_build_id__attach(skel); + if (CHECK(err, "attach_tp", "err %d\n", err)) + goto cleanup; /* find map fds */ - control_map_fd = bpf_find_map(__func__, obj, "control_map"); - if (CHECK(control_map_fd < 0, "bpf_find_map control_map", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); - if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); - if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n", - err, errno)) - goto disable_pmu; - - stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); - if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; + control_map_fd = bpf_map__fd(skel->maps.control_map); + stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap); + stackmap_fd = bpf_map__fd(skel->maps.stackmap); + stack_amap_fd = bpf_map__fd(skel->maps.stack_amap); if (CHECK_FAIL(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null"))) - goto disable_pmu; + goto cleanup; if (CHECK_FAIL(system("./urandom_read"))) - goto disable_pmu; + goto cleanup; /* disable stack trace collection */ key = 0; val = 1; @@ -66,23 +45,23 @@ retry: err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = compare_map_keys(stackmap_fd, stackid_hmap_fd); if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = extract_build_id(buf, 256); if (CHECK(err, "get build_id with readelf", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = bpf_map_get_next_key(stackmap_fd, NULL, &key); if (CHECK(err, "get_next_key from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; do { char build_id[64]; @@ -90,7 +69,7 @@ retry: err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs); if (CHECK(err, "lookup_elem from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i) if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID && id_offs[i].offset != 0) { @@ -108,8 +87,7 @@ retry: * try it one more time. */ if (build_id_matches < 1 && retry--) { - bpf_link__destroy(link); - bpf_object__close(obj); + test_stacktrace_build_id__destroy(skel); printf("%s:WARN:Didn't find expected build ID from the map, retrying\n", __func__); goto retry; @@ -117,17 +95,14 @@ retry: if (CHECK(build_id_matches < 1, "build id match", "Didn't find expected build ID from the map\n")) - goto disable_pmu; + goto cleanup; - stack_trace_len = PERF_MAX_STACK_DEPTH - * sizeof(struct bpf_stack_build_id); + stack_trace_len = PERF_MAX_STACK_DEPTH * + sizeof(struct bpf_stack_build_id); err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); CHECK(err, "compare_stack_ips stackmap vs. stack_amap", "err %d errno %d\n", err, errno); -disable_pmu: - bpf_link__destroy(link); - -close_prog: - bpf_object__close(obj); +cleanup: + test_stacktrace_build_id__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c index f62aa0eb959b..8974450a4bdb 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include "test_stacktrace_build_id.skel.h" static __u64 read_perf_max_sample_freq(void) { @@ -16,19 +17,15 @@ static __u64 read_perf_max_sample_freq(void) void test_stacktrace_build_id_nmi(void) { - int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; - const char *prog_name = "tracepoint/random/urandom_read"; - const char *file = "./test_stacktrace_build_id.o"; - int err, pmu_fd, prog_fd; + int control_map_fd, stackid_hmap_fd, stackmap_fd; + struct test_stacktrace_build_id *skel; + int err, pmu_fd; struct perf_event_attr attr = { .freq = 1, .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, }; __u32 key, previous_key, val, duration = 0; - struct bpf_program *prog; - struct bpf_object *obj; - struct bpf_link *link; char buf[256]; int i, j; struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH]; @@ -38,13 +35,16 @@ void test_stacktrace_build_id_nmi(void) attr.sample_freq = read_perf_max_sample_freq(); retry: - err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd); - if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) + skel = test_stacktrace_build_id__open(); + if (CHECK(!skel, "skel_open", "skeleton open failed\n")) return; - prog = bpf_object__find_program_by_title(obj, prog_name); - if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name)) - goto close_prog; + /* override program type */ + bpf_program__set_perf_event(skel->progs.oncpu); + + err = test_stacktrace_build_id__load(skel); + if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) + goto cleanup; pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu 0 */, -1 /* group id */, @@ -52,40 +52,25 @@ retry: if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n", pmu_fd, errno)) - goto close_prog; + goto cleanup; - link = bpf_program__attach_perf_event(prog, pmu_fd); - if (CHECK(IS_ERR(link), "attach_perf_event", - "err %ld\n", PTR_ERR(link))) { + skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, + pmu_fd); + if (CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event", + "err %ld\n", PTR_ERR(skel->links.oncpu))) { close(pmu_fd); - goto close_prog; + goto cleanup; } /* find map fds */ - control_map_fd = bpf_find_map(__func__, obj, "control_map"); - if (CHECK(control_map_fd < 0, "bpf_find_map control_map", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); - if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; - - stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); - if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n", - err, errno)) - goto disable_pmu; - - stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); - if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", - "err %d errno %d\n", err, errno)) - goto disable_pmu; + control_map_fd = bpf_map__fd(skel->maps.control_map); + stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap); + stackmap_fd = bpf_map__fd(skel->maps.stackmap); if (CHECK_FAIL(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null"))) - goto disable_pmu; + goto cleanup; if (CHECK_FAIL(system("taskset 0x1 ./urandom_read 100000"))) - goto disable_pmu; + goto cleanup; /* disable stack trace collection */ key = 0; val = 1; @@ -97,23 +82,23 @@ retry: err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = compare_map_keys(stackmap_fd, stackid_hmap_fd); if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = extract_build_id(buf, 256); if (CHECK(err, "get build_id with readelf", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; err = bpf_map_get_next_key(stackmap_fd, NULL, &key); if (CHECK(err, "get_next_key from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; do { char build_id[64]; @@ -121,7 +106,7 @@ retry: err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs); if (CHECK(err, "lookup_elem from stackmap", "err %d, errno %d\n", err, errno)) - goto disable_pmu; + goto cleanup; for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i) if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID && id_offs[i].offset != 0) { @@ -139,8 +124,7 @@ retry: * try it one more time. */ if (build_id_matches < 1 && retry--) { - bpf_link__destroy(link); - bpf_object__close(obj); + test_stacktrace_build_id__destroy(skel); printf("%s:WARN:Didn't find expected build ID from the map, retrying\n", __func__); goto retry; @@ -148,7 +132,7 @@ retry: if (CHECK(build_id_matches < 1, "build id match", "Didn't find expected build ID from the map\n")) - goto disable_pmu; + goto cleanup; /* * We intentionally skip compare_stack_ips(). This is because we @@ -157,8 +141,6 @@ retry: * BPF_STACK_BUILD_ID_IP; */ -disable_pmu: - bpf_link__destroy(link); -close_prog: - bpf_object__close(obj); +cleanup: + test_stacktrace_build_id__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c new file mode 100644 index 000000000000..7185bee16fe4 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +void test_xdp_perf(void) +{ + const char *file = "./xdp_dummy.o"; + __u32 duration, retval, size; + struct bpf_object *obj; + char in[128], out[128]; + int err, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (CHECK_FAIL(err)) + return; + + err = bpf_prog_test_run(prog_fd, 1000000, &in[0], 128, + out, &size, &retval, &duration); + + CHECK(err || retval != XDP_PASS || size != 128, + "xdp-perf", + "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + + bpf_object__close(obj); +} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c new file mode 100644 index 000000000000..65eac371b061 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___equiv_zero_sz_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___equiv_zero_sz_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c new file mode 100644 index 000000000000..ecda2b545ac2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_zero_sz_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___err_bad_zero_sz_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c new file mode 100644 index 000000000000..fe1d01232c22 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___fixed_arr.c @@ -0,0 +1,3 @@ +#include "core_reloc_types.h" + +void f(struct core_reloc_arrays___fixed_arr x) {} diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h index 9311489e14b2..6d598cfbdb3e 100644 --- a/tools/testing/selftests/bpf/progs/core_reloc_types.h +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -327,6 +327,7 @@ struct core_reloc_arrays_output { char b123; int c1c; int d00d; + int f10c; }; struct core_reloc_arrays_substruct { @@ -339,6 +340,7 @@ struct core_reloc_arrays { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; /* bigger array dimensions */ @@ -347,6 +349,7 @@ struct core_reloc_arrays___diff_arr_dim { char b[3][4][5]; struct core_reloc_arrays_substruct c[4]; struct core_reloc_arrays_substruct d[2][3]; + struct core_reloc_arrays_substruct f[1][3]; }; /* different size of array's value (struct) */ @@ -363,6 +366,29 @@ struct core_reloc_arrays___diff_arr_val_sz { int d; int __padding2; } d[1][2]; + struct { + int __padding1; + int c; + int __padding2; + } f[][2]; +}; + +struct core_reloc_arrays___equiv_zero_sz_arr { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + /* equivalent to flexible array */ + struct core_reloc_arrays_substruct f[0][2]; +}; + +struct core_reloc_arrays___fixed_arr { + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; + /* not a flexible array anymore, but within access bounds */ + struct core_reloc_arrays_substruct f[1][2]; }; struct core_reloc_arrays___err_too_small { @@ -370,6 +396,7 @@ struct core_reloc_arrays___err_too_small { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; struct core_reloc_arrays___err_too_shallow { @@ -377,6 +404,7 @@ struct core_reloc_arrays___err_too_shallow { char b[2][3]; /* this one lacks one dimension */ struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; struct core_reloc_arrays___err_non_array { @@ -384,6 +412,7 @@ struct core_reloc_arrays___err_non_array { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; struct core_reloc_arrays___err_wrong_val_type { @@ -391,6 +420,16 @@ struct core_reloc_arrays___err_wrong_val_type { char b[2][3][4]; int c[3]; /* value is not a struct */ struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; +}; + +struct core_reloc_arrays___err_bad_zero_sz_arr { + /* zero-sized array, but not at the end */ + struct core_reloc_arrays_substruct f[0][2]; + int a[5]; + char b[2][3][4]; + struct core_reloc_arrays_substruct c[3]; + struct core_reloc_arrays_substruct d[1][2]; }; /* diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c index 534621e38906..221b69700625 100644 --- a/tools/testing/selftests/bpf/progs/test_attach_probe.c +++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c @@ -5,46 +5,36 @@ #include <linux/bpf.h> #include "bpf_helpers.h" -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 4); - __type(key, int); - __type(value, int); -} results_map SEC(".maps"); +int kprobe_res = 0; +int kretprobe_res = 0; +int uprobe_res = 0; +int uretprobe_res = 0; SEC("kprobe/sys_nanosleep") -int handle_sys_nanosleep_entry(struct pt_regs *ctx) +int handle_kprobe(struct pt_regs *ctx) { - const int key = 0, value = 1; - - bpf_map_update_elem(&results_map, &key, &value, 0); + kprobe_res = 1; return 0; } SEC("kretprobe/sys_nanosleep") -int handle_sys_getpid_return(struct pt_regs *ctx) +int handle_kretprobe(struct pt_regs *ctx) { - const int key = 1, value = 2; - - bpf_map_update_elem(&results_map, &key, &value, 0); + kretprobe_res = 2; return 0; } SEC("uprobe/trigger_func") -int handle_uprobe_entry(struct pt_regs *ctx) +int handle_uprobe(struct pt_regs *ctx) { - const int key = 2, value = 3; - - bpf_map_update_elem(&results_map, &key, &value, 0); + uprobe_res = 3; return 0; } SEC("uretprobe/trigger_func") -int handle_uprobe_return(struct pt_regs *ctx) +int handle_uretprobe(struct pt_regs *ctx) { - const int key = 3, value = 4; - - bpf_map_update_elem(&results_map, &key, &value, 0); + uretprobe_res = 4; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_core_extern.c b/tools/testing/selftests/bpf/progs/test_core_extern.c new file mode 100644 index 000000000000..9bfc91d9d004 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_extern.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <stdint.h> +#include <stdbool.h> +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +/* non-existing BPF helper, to test dead code elimination */ +static int (*bpf_missing_helper)(const void *arg1, int arg2) = (void *) 999; + +extern int LINUX_KERNEL_VERSION __kconfig; +extern bool CONFIG_BPF_SYSCALL __kconfig; /* strong */ +extern enum libbpf_tristate CONFIG_TRISTATE __kconfig __weak; +extern bool CONFIG_BOOL __kconfig __weak; +extern char CONFIG_CHAR __kconfig __weak; +extern uint16_t CONFIG_USHORT __kconfig __weak; +extern int CONFIG_INT __kconfig __weak; +extern uint64_t CONFIG_ULONG __kconfig __weak; +extern const char CONFIG_STR[8] __kconfig __weak; +extern uint64_t CONFIG_MISSING __kconfig __weak; + +uint64_t kern_ver = -1; +uint64_t bpf_syscall = -1; +uint64_t tristate_val = -1; +uint64_t bool_val = -1; +uint64_t char_val = -1; +uint64_t ushort_val = -1; +uint64_t int_val = -1; +uint64_t ulong_val = -1; +char str_val[8] = {-1, -1, -1, -1, -1, -1, -1, -1}; +uint64_t missing_val = -1; + +SEC("raw_tp/sys_enter") +int handle_sys_enter(struct pt_regs *ctx) +{ + int i; + + kern_ver = LINUX_KERNEL_VERSION; + bpf_syscall = CONFIG_BPF_SYSCALL; + tristate_val = CONFIG_TRISTATE; + bool_val = CONFIG_BOOL; + char_val = CONFIG_CHAR; + ushort_val = CONFIG_USHORT; + int_val = CONFIG_INT; + ulong_val = CONFIG_ULONG; + + for (i = 0; i < sizeof(CONFIG_STR); i++) { + str_val[i] = CONFIG_STR[i]; + } + + if (CONFIG_MISSING) + /* invalid, but dead code - never executed */ + missing_val = bpf_missing_helper(ctx, 123); + else + missing_val = 0xDEADC0DE; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c index 89951b684282..053b86f6b53f 100644 --- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c @@ -18,6 +18,7 @@ struct core_reloc_arrays_output { char b123; int c1c; int d00d; + int f01c; }; struct core_reloc_arrays_substruct { @@ -30,6 +31,7 @@ struct core_reloc_arrays { char b[2][3][4]; struct core_reloc_arrays_substruct c[3]; struct core_reloc_arrays_substruct d[1][2]; + struct core_reloc_arrays_substruct f[][2]; }; #define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src) @@ -40,18 +42,16 @@ int test_core_arrays(void *ctx) struct core_reloc_arrays *in = (void *)&data.in; struct core_reloc_arrays_output *out = (void *)&data.out; - /* in->a[2] */ if (CORE_READ(&out->a2, &in->a[2])) return 1; - /* in->b[1][2][3] */ if (CORE_READ(&out->b123, &in->b[1][2][3])) return 1; - /* in->c[1].c */ if (CORE_READ(&out->c1c, &in->c[1].c)) return 1; - /* in->d[0][0].d */ if (CORE_READ(&out->d00d, &in->d[0][0].d)) return 1; + if (CORE_READ(&out->f01c, &in->f[0][1].c)) + return 1; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index ea7d84f01235..b1f09f5bb1cf 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -62,7 +62,7 @@ struct { goto done; \ }) -SEC("select_by_skb_data") +SEC("sk_reuseport") int _select_by_skb_data(struct sk_reuseport_md *reuse_md) { __u32 linum, index = 0, flags = 0, index_zero = 0; diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c index 2a9f4c736ebc..e18da87fe84f 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c +++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c @@ -17,6 +17,12 @@ int process(struct __sk_buff *skb) } skb->priority++; skb->tstamp++; + skb->mark++; + + if (skb->wire_len != 100) + return 1; + if (skb->gso_segs != 8) + return 1; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c new file mode 100644 index 000000000000..4f69aac5635f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_skeleton.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +struct s { + int a; + long long b; +} __attribute__((packed)); + +int in1 = 0; +long long in2 = 0; +char in3 = '\0'; +long long in4 __attribute__((aligned(64))) = 0; +struct s in5 = {}; + +long long out2 = 0; +char out3 = 0; +long long out4 = 0; +int out1 = 0; + +extern bool CONFIG_BPF_SYSCALL __kconfig; +extern int LINUX_KERNEL_VERSION __kconfig; +bool bpf_syscall = 0; +int kern_ver = 0; + +SEC("raw_tp/sys_enter") +int handler(const void *ctx) +{ + static volatile struct s out5; + + out1 = in1; + out2 = in2; + out3 = in3; + out4 = in4; + out5 = in5; + + bpf_syscall = CONFIG_BPF_SYSCALL; + kern_ver = LINUX_KERNEL_VERSION; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_cgroup_attach.c b/tools/testing/selftests/bpf/test_cgroup_attach.c deleted file mode 100644 index 7671909ee1cb..000000000000 --- a/tools/testing/selftests/bpf/test_cgroup_attach.c +++ /dev/null @@ -1,571 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -/* eBPF example program: - * - * - Creates arraymap in kernel with 4 bytes keys and 8 byte values - * - * - Loads eBPF program - * - * The eBPF program accesses the map passed in to store two pieces of - * information. The number of invocations of the program, which maps - * to the number of packets received, is stored to key 0. Key 1 is - * incremented on each iteration by the number of bytes stored in - * the skb. The program also stores the number of received bytes - * in the cgroup storage. - * - * - Attaches the new program to a cgroup using BPF_PROG_ATTACH - * - * - Every second, reads map[0] and map[1] to see how many bytes and - * packets were seen on any socket of tasks in the given cgroup. - */ - -#define _GNU_SOURCE - -#include <stdio.h> -#include <stdlib.h> -#include <assert.h> -#include <sys/resource.h> -#include <sys/time.h> -#include <unistd.h> -#include <linux/filter.h> - -#include <linux/bpf.h> -#include <bpf/bpf.h> - -#include "bpf_util.h" -#include "bpf_rlimit.h" -#include "cgroup_helpers.h" - -#define FOO "/foo" -#define BAR "/foo/bar/" -#define PING_CMD "ping -q -c1 -w1 127.0.0.1 > /dev/null" - -char bpf_log_buf[BPF_LOG_BUF_SIZE]; - -#ifdef DEBUG -#define debug(args...) printf(args) -#else -#define debug(args...) -#endif - -static int prog_load(int verdict) -{ - int ret; - struct bpf_insn prog[] = { - BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ - BPF_EXIT_INSN(), - }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); - - ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, - prog, insns_cnt, "GPL", 0, - bpf_log_buf, BPF_LOG_BUF_SIZE); - - if (ret < 0) { - log_err("Loading program"); - printf("Output from verifier:\n%s\n-------\n", bpf_log_buf); - return 0; - } - return ret; -} - -static int test_foo_bar(void) -{ - int drop_prog, allow_prog, foo = 0, bar = 0, rc = 0; - - allow_prog = prog_load(1); - if (!allow_prog) - goto err; - - drop_prog = prog_load(0); - if (!drop_prog) - goto err; - - if (setup_cgroup_environment()) - goto err; - - /* Create cgroup /foo, get fd, and join it */ - foo = create_and_get_cgroup(FOO); - if (foo < 0) - goto err; - - if (join_cgroup(FOO)) - goto err; - - if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo"); - goto err; - } - - debug("Attached DROP prog. This ping in cgroup /foo should fail...\n"); - assert(system(PING_CMD) != 0); - - /* Create cgroup /foo/bar, get fd, and join it */ - bar = create_and_get_cgroup(BAR); - if (bar < 0) - goto err; - - if (join_cgroup(BAR)) - goto err; - - debug("Attached DROP prog. This ping in cgroup /foo/bar should fail...\n"); - assert(system(PING_CMD) != 0); - - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo/bar"); - goto err; - } - - debug("Attached PASS prog. This ping in cgroup /foo/bar should pass...\n"); - assert(system(PING_CMD) == 0); - - if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching program from /foo/bar"); - goto err; - } - - debug("Detached PASS from /foo/bar while DROP is attached to /foo.\n" - "This ping in cgroup /foo/bar should fail...\n"); - assert(system(PING_CMD) != 0); - - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo/bar"); - goto err; - } - - if (bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching program from /foo"); - goto err; - } - - debug("Attached PASS from /foo/bar and detached DROP from /foo.\n" - "This ping in cgroup /foo/bar should pass...\n"); - assert(system(PING_CMD) == 0); - - if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to /foo/bar"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) { - errno = 0; - log_err("Unexpected success attaching prog to /foo/bar"); - goto err; - } - - if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching program from /foo/bar"); - goto err; - } - - if (!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) { - errno = 0; - log_err("Unexpected success in double detach from /foo"); - goto err; - } - - if (bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) { - log_err("Attaching non-overridable prog to /foo"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) { - errno = 0; - log_err("Unexpected success attaching non-overridable prog to /foo/bar"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - errno = 0; - log_err("Unexpected success attaching overridable prog to /foo/bar"); - goto err; - } - - if (!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - errno = 0; - log_err("Unexpected success attaching overridable prog to /foo"); - goto err; - } - - if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) { - log_err("Attaching different non-overridable prog to /foo"); - goto err; - } - - goto out; - -err: - rc = 1; - -out: - close(foo); - close(bar); - cleanup_cgroup_environment(); - if (!rc) - printf("#override:PASS\n"); - else - printf("#override:FAIL\n"); - return rc; -} - -static int map_fd = -1; - -static int prog_load_cnt(int verdict, int val) -{ - int cgroup_storage_fd, percpu_cgroup_storage_fd; - - if (map_fd < 0) - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); - if (map_fd < 0) { - printf("failed to create map '%s'\n", strerror(errno)); - return -1; - } - - cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, - sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); - if (cgroup_storage_fd < 0) { - printf("failed to create map '%s'\n", strerror(errno)); - return -1; - } - - percpu_cgroup_storage_fd = bpf_create_map( - BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, - sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); - if (percpu_cgroup_storage_fd < 0) { - printf("failed to create map '%s'\n", strerror(errno)); - return -1; - } - - struct bpf_insn prog[] = { - BPF_MOV32_IMM(BPF_REG_0, 0), - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */ - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */ - BPF_LD_MAP_FD(BPF_REG_1, map_fd), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), - BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */ - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */ - - BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd), - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), - BPF_MOV64_IMM(BPF_REG_1, val), - BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0), - - BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd), - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), - BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1), - BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0), - - BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ - BPF_EXIT_INSN(), - }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); - int ret; - - ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, - prog, insns_cnt, "GPL", 0, - bpf_log_buf, BPF_LOG_BUF_SIZE); - - if (ret < 0) { - log_err("Loading program"); - printf("Output from verifier:\n%s\n-------\n", bpf_log_buf); - return 0; - } - close(cgroup_storage_fd); - return ret; -} - - -static int test_multiprog(void) -{ - __u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id; - int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0; - int drop_prog, allow_prog[6] = {}, rc = 0; - unsigned long long value; - int i = 0; - - for (i = 0; i < 6; i++) { - allow_prog[i] = prog_load_cnt(1, 1 << i); - if (!allow_prog[i]) - goto err; - } - drop_prog = prog_load_cnt(0, 1); - if (!drop_prog) - goto err; - - if (setup_cgroup_environment()) - goto err; - - cg1 = create_and_get_cgroup("/cg1"); - if (cg1 < 0) - goto err; - cg2 = create_and_get_cgroup("/cg1/cg2"); - if (cg2 < 0) - goto err; - cg3 = create_and_get_cgroup("/cg1/cg2/cg3"); - if (cg3 < 0) - goto err; - cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4"); - if (cg4 < 0) - goto err; - cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5"); - if (cg5 < 0) - goto err; - - if (join_cgroup("/cg1/cg2/cg3/cg4/cg5")) - goto err; - - if (bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog to cg1"); - goto err; - } - if (!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Unexpected success attaching the same prog to cg1"); - goto err; - } - if (bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog2 to cg1"); - goto err; - } - if (bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to cg2"); - goto err; - } - if (bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog to cg3"); - goto err; - } - if (bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_OVERRIDE)) { - log_err("Attaching prog to cg4"); - goto err; - } - if (bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0)) { - log_err("Attaching prog to cg5"); - goto err; - } - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 8 + 32); - - /* query the number of effective progs in cg5 */ - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - NULL, NULL, &prog_cnt) == 0); - assert(prog_cnt == 4); - /* retrieve prog_ids of effective progs in cg5 */ - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - &attach_flags, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 4); - assert(attach_flags == 0); - saved_prog_id = prog_ids[0]; - /* check enospc handling */ - prog_ids[0] = 0; - prog_cnt = 2; - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - &attach_flags, prog_ids, &prog_cnt) == -1 && - errno == ENOSPC); - assert(prog_cnt == 4); - /* check that prog_ids are returned even when buffer is too small */ - assert(prog_ids[0] == saved_prog_id); - /* retrieve prog_id of single attached prog in cg5 */ - prog_ids[0] = 0; - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, - NULL, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 1); - assert(prog_ids[0] == saved_prog_id); - - /* detach bottom program and ping again */ - if (bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching prog from cg5"); - goto err; - } - value = 0; - assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 8 + 16); - - /* detach 3rd from bottom program and ping again */ - errno = 0; - if (!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS)) { - log_err("Unexpected success on detach from cg3"); - goto err; - } - if (bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching from cg3"); - goto err; - } - value = 0; - assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 16); - - /* detach 2nd from bottom program and ping again */ - if (bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS)) { - log_err("Detaching prog from cg4"); - goto err; - } - value = 0; - assert(bpf_map_update_elem(map_fd, &key, &value, 0) == 0); - assert(system(PING_CMD) == 0); - assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0); - assert(value == 1 + 2 + 4); - - prog_cnt = 4; - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, - &attach_flags, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 3); - assert(attach_flags == 0); - assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, - NULL, prog_ids, &prog_cnt) == 0); - assert(prog_cnt == 0); - goto out; -err: - rc = 1; - -out: - for (i = 0; i < 6; i++) - if (allow_prog[i] > 0) - close(allow_prog[i]); - close(cg1); - close(cg2); - close(cg3); - close(cg4); - close(cg5); - cleanup_cgroup_environment(); - if (!rc) - printf("#multi:PASS\n"); - else - printf("#multi:FAIL\n"); - return rc; -} - -static int test_autodetach(void) -{ - __u32 prog_cnt = 4, attach_flags; - int allow_prog[2] = {0}; - __u32 prog_ids[2] = {0}; - int cg = 0, i, rc = -1; - void *ptr = NULL; - int attempts; - - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { - allow_prog[i] = prog_load_cnt(1, 1 << i); - if (!allow_prog[i]) - goto err; - } - - if (setup_cgroup_environment()) - goto err; - - /* create a cgroup, attach two programs and remember their ids */ - cg = create_and_get_cgroup("/cg_autodetach"); - if (cg < 0) - goto err; - - if (join_cgroup("/cg_autodetach")) - goto err; - - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { - if (bpf_prog_attach(allow_prog[i], cg, BPF_CGROUP_INET_EGRESS, - BPF_F_ALLOW_MULTI)) { - log_err("Attaching prog[%d] to cg:egress", i); - goto err; - } - } - - /* make sure that programs are attached and run some traffic */ - assert(bpf_prog_query(cg, BPF_CGROUP_INET_EGRESS, 0, &attach_flags, - prog_ids, &prog_cnt) == 0); - assert(system(PING_CMD) == 0); - - /* allocate some memory (4Mb) to pin the original cgroup */ - ptr = malloc(4 * (1 << 20)); - if (!ptr) - goto err; - - /* close programs and cgroup fd */ - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) { - close(allow_prog[i]); - allow_prog[i] = 0; - } - - close(cg); - cg = 0; - - /* leave the cgroup and remove it. don't detach programs */ - cleanup_cgroup_environment(); - - /* wait for the asynchronous auto-detachment. - * wait for no more than 5 sec and give up. - */ - for (i = 0; i < ARRAY_SIZE(prog_ids); i++) { - for (attempts = 5; attempts >= 0; attempts--) { - int fd = bpf_prog_get_fd_by_id(prog_ids[i]); - - if (fd < 0) - break; - - /* don't leave the fd open */ - close(fd); - - if (!attempts) - goto err; - - sleep(1); - } - } - - rc = 0; -err: - for (i = 0; i < ARRAY_SIZE(allow_prog); i++) - if (allow_prog[i] > 0) - close(allow_prog[i]); - if (cg) - close(cg); - free(ptr); - cleanup_cgroup_environment(); - if (!rc) - printf("#autodetach:PASS\n"); - else - printf("#autodetach:FAIL\n"); - return rc; -} - -int main(void) -{ - int (*tests[])(void) = { - test_foo_bar, - test_multiprog, - test_autodetach, - }; - int errors = 0; - int i; - - for (i = 0; i < ARRAY_SIZE(tests); i++) - if (tests[i]()) - errors++; - - if (errors) - printf("test_cgroup_attach:FAIL\n"); - else - printf("test_cgroup_attach:PASS\n"); - - return errors ? EXIT_FAILURE : EXIT_SUCCESS; -} diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp index f0eb2727b766..6fe23a10d48a 100644 --- a/tools/testing/selftests/bpf/test_cpp.cpp +++ b/tools/testing/selftests/bpf/test_cpp.cpp @@ -1,12 +1,16 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#include <iostream> #include "libbpf.h" #include "bpf.h" #include "btf.h" +#include "test_core_extern.skel.h" /* do nothing, just make sure we can link successfully */ int main(int argc, char *argv[]) { + struct test_core_extern *skel; + /* libbpf.h */ libbpf_set_print(NULL); @@ -16,5 +20,11 @@ int main(int argc, char *argv[]) /* btf.h */ btf__new(NULL, 0); + /* BPF skeleton */ + skel = test_core_extern__open_and_load(); + test_core_extern__destroy(skel); + + std::cout << "DONE!" << std::endl; + return 0; } diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 8477df835979..de1fdaa4e7b4 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -100,6 +100,7 @@ extern struct ipv6_packet pkt_v6; #define _CHECK(condition, tag, duration, format...) ({ \ int __ret = !!(condition); \ + int __save_errno = errno; \ if (__ret) { \ test__fail(); \ printf("%s:FAIL:%s ", __func__, tag); \ @@ -108,15 +109,18 @@ extern struct ipv6_packet pkt_v6; printf("%s:PASS:%s %d nsec\n", \ __func__, tag, duration); \ } \ + errno = __save_errno; \ __ret; \ }) #define CHECK_FAIL(condition) ({ \ int __ret = !!(condition); \ + int __save_errno = errno; \ if (__ret) { \ test__fail(); \ printf("%s:FAIL:%d\n", __func__, __LINE__); \ } \ + errno = __save_errno; \ __ret; \ }) diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh index b4efb023ae51..d88d8e47d11b 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh @@ -50,6 +50,8 @@ ALL_TESTS=" ipv6_mc_dip_reserved_scope_test ipv6_mc_dip_interface_local_scope_test blackhole_route_test + irif_disabled_test + erif_disabled_test " NUM_NETIFS=4 @@ -553,6 +555,116 @@ blackhole_route_test() __blackhole_route_test "6" "2001:db8:2::/120" "ipv6" $h2_ipv6 "icmpv6" } +irif_disabled_test() +{ + local trap_name="irif_disabled" + local group_name="l3_drops" + local t0_packets t0_bytes + local t1_packets t1_bytes + local mz_pid + + RET=0 + + ping_check $trap_name + + devlink_trap_action_set $trap_name "trap" + + # When RIF of a physical port ("Sub-port RIF") is destroyed, we first + # block the STP of the {Port, VLAN} so packets cannot get into the RIF. + # Using bridge enables us to see this trap because when bridge is + # destroyed, there is a small time window that packets can go into the + # RIF, while it is disabled. + ip link add dev br0 type bridge + ip link set dev $rp1 master br0 + ip address flush dev $rp1 + __addr_add_del br0 add 192.0.2.2/24 + ip li set dev br0 up + + t0_packets=$(devlink_trap_rx_packets_get $trap_name) + t0_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + # Generate packets to h2 through br0 RIF that will be removed later + $MZ $h1 -t udp "sp=54321,dp=12345" -c 0 -p 100 -a own -b $rp1mac \ + -B $h2_ipv4 -q & + mz_pid=$! + + # Wait before removing br0 RIF to allow packets to go into the bridge. + sleep 1 + + # Flushing address will dismantle the RIF + ip address flush dev br0 + + t1_packets=$(devlink_trap_rx_packets_get $trap_name) + t1_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then + check_err 1 "Trap stats idle when packets should be trapped" + fi + + log_test "Ingress RIF disabled" + + kill $mz_pid && wait $mz_pid &> /dev/null + ip link set dev $rp1 nomaster + __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 + ip link del dev br0 type bridge + devlink_trap_action_set $trap_name "drop" +} + +erif_disabled_test() +{ + local trap_name="erif_disabled" + local group_name="l3_drops" + local t0_packets t0_bytes + local t1_packets t1_bytes + local mz_pid + + RET=0 + + ping_check $trap_name + + devlink_trap_action_set $trap_name "trap" + ip link add dev br0 type bridge + ip add flush dev $rp1 + ip link set dev $rp1 master br0 + __addr_add_del br0 add 192.0.2.2/24 + ip link set dev br0 up + + t0_packets=$(devlink_trap_rx_packets_get $trap_name) + t0_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + rp2mac=$(mac_get $rp2) + + # Generate packets that should go out through br0 RIF that will be + # removed later + $MZ $h2 -t udp "sp=54321,dp=12345" -c 0 -p 100 -a own -b $rp2mac \ + -B 192.0.2.1 -q & + mz_pid=$! + + sleep 5 + # In order to see this trap we need a route that points to disabled RIF. + # When ipv6 address is flushed, there is a delay and the routes are + # deleted before the RIF and we cannot get state that we have route + # to disabled RIF. + # Delete IPv6 address first and then check this trap with flushing IPv4. + ip -6 add flush dev br0 + ip -4 add flush dev br0 + + t1_packets=$(devlink_trap_rx_packets_get $trap_name) + t1_bytes=$(devlink_trap_rx_bytes_get $trap_name) + + if [[ $t0_packets -eq $t1_packets && $t0_bytes -eq $t1_bytes ]]; then + check_err 1 "Trap stats idle when packets should be trapped" + fi + + log_test "Egress RIF disabled" + + kill $mz_pid && wait $mz_pid &> /dev/null + ip link set dev $rp1 nomaster + __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 + ip link del dev br0 type bridge + devlink_trap_action_set $trap_name "drop" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh new file mode 100755 index 000000000000..039629bb92a3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -0,0 +1,265 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap tunnel exceptions functionality over mlxsw. +# Check all exception traps to make sure they are triggered under the right +# conditions. + +# +-------------------------+ +# | H1 | +# | $h1 + | +# | 192.0.2.1/28 | | +# +-------------------|-----+ +# | +# +-------------------|-----+ +# | SW1 | | +# | $swp1 + | +# | 192.0.2.2/28 | +# | | +# | + g1a (gre) | +# | loc=192.0.2.65 | +# | rem=192.0.2.66 | +# | tos=inherit | +# | | +# | + $rp1 | +# | | 198.51.100.1/28 | +# +--|----------------------+ +# | +# +--|----------------------+ +# | | VRF2 | +# | + $rp2 | +# | 198.51.100.2/28 | +# +-------------------------+ + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + decap_error_test +" + +NUM_NETIFS=4 +source $lib_dir/lib.sh +source $lib_dir/tc_common.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +vrf2_create() +{ + simple_if_init $rp2 198.51.100.2/28 +} + +vrf2_destroy() +{ + simple_if_fini $rp2 198.51.100.2/28 +} + +switch_create() +{ + __addr_add_del $swp1 add 192.0.2.2/28 + tc qdisc add dev $swp1 clsact + ip link set dev $swp1 up + + tunnel_create g1 gre 192.0.2.65 192.0.2.66 tos inherit + __addr_add_del g1 add 192.0.2.65/32 + ip link set dev g1 up + + __addr_add_del $rp1 add 198.51.100.1/28 + ip link set dev $rp1 up +} + +switch_destroy() +{ + ip link set dev $rp1 down + __addr_add_del $rp1 del 198.51.100.1/28 + + ip link set dev g1 down + __addr_add_del g1 del 192.0.2.65/32 + tunnel_destroy g1 + + ip link set dev $swp1 down + tc qdisc del dev $swp1 clsact + __addr_add_del $swp1 del 192.0.2.2/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + forwarding_enable + vrf_prepare + h1_create + switch_create + vrf2_create +} + +cleanup() +{ + pre_cleanup + + vrf2_destroy + switch_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +ecn_payload_get() +{ + p=$(: + )"0"$( : GRE flags + )"0:00:"$( : Reserved + version + )"08:00:"$( : ETH protocol type + )"4"$( : IP version + )"5:"$( : IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"30:"$( : IP TTL + )"01:"$( : IP proto + )"E7:E6:"$( : IP header csum + )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 + )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 + ) + echo $p +} + +ecn_decap_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local ecn_desc=$1; shift + local outer_tos=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_ip 192.0.1.1 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ecn_payload_get) + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A 192.0.2.66 -B 192.0.2.65 -t ip \ + len=48,tos=$outer_tos,proto=47,p=$payload -q & + + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +ipip_payload_get() +{ + local flags=$1; shift + local key=$1; shift + + p=$(: + )"$flags"$( : GRE flags + )"0:00:"$( : Reserved + version + )"08:00:"$( : ETH protocol type + )"$key"$( : Key + )"4"$( : IP version + )"5:"$( : IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"30:"$( : IP TTL + )"01:"$( : IP proto + )"E7:E6:"$( : IP header csum + )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 + )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 + ) + echo $p +} + +no_matching_tunnel_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local sip=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_ip 192.0.1.1 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ipip_payload_get "$@") + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A $sip -B 192.0.2.65 -t ip len=48,proto=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +decap_error_test() +{ + # Correct source IP - the remote address + local sip=192.0.2.66 + + ecn_decap_test "Decap error" "ECT(1)" 01 + ecn_decap_test "Decap error" "ECT(0)" 02 + ecn_decap_test "Decap error" "CE" 03 + + no_matching_tunnel_test "Decap error: Source IP check failed" \ + 192.0.2.68 "0" + no_matching_tunnel_test \ + "Decap error: Key exists but was not expected" $sip "2" ":E9:" + + # Destroy the tunnel and create new one with key + __addr_add_del g1 del 192.0.2.65/32 + tunnel_destroy g1 + + tunnel_create g1 gre 192.0.2.65 192.0.2.66 tos inherit key 233 + __addr_add_del g1 add 192.0.2.65/32 + + no_matching_tunnel_test \ + "Decap error: Key does not exist but was expected" $sip "0" + no_matching_tunnel_test \ + "Decap error: Packet has a wrong key field" $sip "2" "E8:" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh new file mode 100755 index 000000000000..fd19161dd4ec --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh @@ -0,0 +1,330 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap tunnel drops and exceptions functionality over mlxsw. +# Check all traps to make sure they are triggered under the right +# conditions. + +# +--------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|---------------+ +# | +# +----|----------------------------------------------------------------------+ +# | SW | | +# | +--|--------------------------------------------------------------------+ | +# | | + $swp1 BR1 (802.1d) | | +# | | | | +# | | + vx1 (vxlan) | | +# | | local 192.0.2.17 | | +# | | id 1000 dstport $VXPORT | | +# | +-----------------------------------------------------------------------+ | +# | | +# | + $rp1 | +# | | 192.0.2.17/28 | +# +----|----------------------------------------------------------------------+ +# | +# +----|--------------------------------------------------------+ +# | | VRF2 | +# | + $rp2 | +# | 192.0.2.18/28 | +# | | +# +-------------------------------------------------------------+ + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + decap_error_test + overlay_smac_is_mc_test +" + +NUM_NETIFS=4 +source $lib_dir/lib.sh +source $lib_dir/tc_common.sh +source $lib_dir/devlink_lib.sh + +: ${VXPORT:=4789} +export VXPORT + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +switch_create() +{ + ip link add name br1 type bridge vlan_filtering 0 mcast_snooping 0 + # Make sure the bridge uses the MAC address of the local port and not + # that of the VxLAN's device. + ip link set dev br1 address $(mac_get $swp1) + ip link set dev br1 up + + tc qdisc add dev $swp1 clsact + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link add name vx1 type vxlan id 1000 local 192.0.2.17 \ + dstport "$VXPORT" nolearning noudpcsum tos inherit ttl 100 + ip link set dev vx1 master br1 + ip link set dev vx1 up + + ip address add dev $rp1 192.0.2.17/28 + ip link set dev $rp1 up +} + +switch_destroy() +{ + ip link set dev $rp1 down + ip address del dev $rp1 192.0.2.17/28 + + ip link set dev vx1 down + ip link set dev vx1 nomaster + ip link del dev vx1 + + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + tc qdisc del dev $swp1 clsact + + ip link set dev br1 down + ip link del dev br1 +} + +vrf2_create() +{ + simple_if_init $rp2 192.0.2.18/28 +} + +vrf2_destroy() +{ + simple_if_fini $rp2 192.0.2.18/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + vrf_prepare + forwarding_enable + h1_create + switch_create + vrf2_create +} + +cleanup() +{ + pre_cleanup + + vrf2_destroy + switch_destroy + h1_destroy + forwarding_restore + vrf_cleanup +} + +ecn_payload_get() +{ + dest_mac=$(mac_get $h1) + p=$(: + )"08:"$( : VXLAN flags + )"00:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"00:00:00:00:00:00:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"00:"$( : IP proto + )"D6:E5:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + ) + echo $p +} + +ecn_decap_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local ecn_desc=$1; shift + local outer_tos=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_ip 192.0.2.3 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + payload=$(ecn_payload_get) + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac -B 192.0.2.17 \ + -t udp sp=12345,dp=$VXPORT,tos=$outer_tos,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +reserved_bits_payload_get() +{ + dest_mac=$(mac_get $h1) + p=$(: + )"08:"$( : VXLAN flags + )"01:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"00:00:00:00:00:00:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"00:"$( : IP proto + )"00:00:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + ) + echo $p +} + +short_payload_get() +{ + dest_mac=$(mac_get $h1) + p=$(: + )"08:"$( : VXLAN flags + )"01:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + ) + echo $p +} + +corrupted_packet_test() +{ + local trap_name="decap_error" + local group_name="tunnel_drops" + local desc=$1; shift + local payload_get=$1; shift + local mz_pid + + RET=0 + + # In case of too short packet, there is no any inner packet, + # so the matching will always succeed + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower skip_hw src_ip 192.0.2.3 dst_ip 192.0.2.1 action pass + + rp1_mac=$(mac_get $rp1) + payload=$($payload_get) + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac \ + -B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name $group_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower +} + +decap_error_test() +{ + ecn_decap_test "Decap error" "ECT(1)" 01 + ecn_decap_test "Decap error" "ECT(0)" 02 + ecn_decap_test "Decap error" "CE" 03 + + corrupted_packet_test "Decap error: Reserved bits in use" \ + "reserved_bits_payload_get" + corrupted_packet_test "Decap error: No L2 header" "short_payload_get" +} + +mc_smac_payload_get() +{ + dest_mac=$(mac_get $h1) + source_mac=01:02:03:04:05:06 + p=$(: + )"08:"$( : VXLAN flags + )"00:00:00:"$( : VXLAN reserved + )"00:03:e8:"$( : VXLAN VNI : 1000 + )"00:"$( : VXLAN reserved + )"$dest_mac:"$( : ETH daddr + )"$source_mac:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:14:"$( : IP total length + )"00:00:"$( : IP identification + )"20:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"00:"$( : IP proto + )"00:00:"$( : IP header csum + )"c0:00:02:03:"$( : IP saddr: 192.0.2.3 + )"c0:00:02:01:"$( : IP daddr: 192.0.2.1 + ) + echo $p +} + +overlay_smac_is_mc_test() +{ + local trap_name="overlay_smac_is_mc" + local group_name="tunnel_drops" + local mz_pid + + RET=0 + + # The matching will be checked on devlink_trap_drop_test() + # and the filter will be removed on devlink_trap_drop_cleanup() + tc filter add dev $swp1 egress protocol ip pref 1 handle 101 \ + flower src_mac 01:02:03:04:05:06 action pass + + rp1_mac=$(mac_get $rp1) + payload=$(mc_smac_payload_get) + + ip vrf exec v$rp2 $MZ $rp2 -c 0 -d 1msec -b $rp1_mac \ + -B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q & + mz_pid=$! + + devlink_trap_drop_test $trap_name $group_name $swp1 + + log_test "Overlay source MAC is multicast" + + devlink_trap_drop_cleanup $mz_pid $swp1 "ip" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/fib.sh b/tools/testing/selftests/drivers/net/mlxsw/fib.sh new file mode 100755 index 000000000000..45115f81c2b1 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/fib.sh @@ -0,0 +1,180 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking the FIB offload API on top of mlxsw. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + ipv4_identical_routes + ipv4_tos + ipv4_metric + ipv4_replace + ipv4_delete + ipv4_plen + ipv4_replay + ipv4_flush + ipv6_add + ipv6_metric + ipv6_append_single + ipv6_replace_single + ipv6_metric_multipath + ipv6_append_multipath + ipv6_replace_multipath + ipv6_append_multipath_to_single + ipv6_delete_single + ipv6_delete_multipath + ipv6_replay_single + ipv6_replay_multipath +" +NUM_NETIFS=0 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh +source $lib_dir/fib_offload_lib.sh + +ipv4_identical_routes() +{ + fib_ipv4_identical_routes_test "testns1" +} + +ipv4_tos() +{ + fib_ipv4_tos_test "testns1" +} + +ipv4_metric() +{ + fib_ipv4_metric_test "testns1" +} + +ipv4_replace() +{ + fib_ipv4_replace_test "testns1" +} + +ipv4_delete() +{ + fib_ipv4_delete_test "testns1" +} + +ipv4_plen() +{ + fib_ipv4_plen_test "testns1" +} + +ipv4_replay_metric() +{ + fib_ipv4_replay_metric_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_tos() +{ + fib_ipv4_replay_tos_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_plen() +{ + fib_ipv4_replay_plen_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay() +{ + ipv4_replay_metric + ipv4_replay_tos + ipv4_replay_plen +} + +ipv4_flush() +{ + fib_ipv4_flush_test "testns1" +} + +ipv6_add() +{ + fib_ipv6_add_test "testns1" +} + +ipv6_metric() +{ + fib_ipv6_metric_test "testns1" +} + +ipv6_append_single() +{ + fib_ipv6_append_single_test "testns1" +} + +ipv6_replace_single() +{ + fib_ipv6_replace_single_test "testns1" +} + +ipv6_metric_multipath() +{ + fib_ipv6_metric_multipath_test "testns1" +} + +ipv6_append_multipath() +{ + fib_ipv6_append_multipath_test "testns1" +} + +ipv6_replace_multipath() +{ + fib_ipv6_replace_multipath_test "testns1" +} + +ipv6_append_multipath_to_single() +{ + fib_ipv6_append_multipath_to_single_test "testns1" +} + +ipv6_delete_single() +{ + fib_ipv6_delete_single_test "testns1" +} + +ipv6_delete_multipath() +{ + fib_ipv6_delete_multipath_test "testns1" +} + +ipv6_replay_single() +{ + fib_ipv6_replay_single_test "testns1" "$DEVLINK_DEV" +} + +ipv6_replay_multipath() +{ + fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV" +} + +setup_prepare() +{ + ip netns add testns1 + if [ $? -ne 0 ]; then + echo "Failed to add netns \"testns1\"" + exit 1 + fi + + devlink dev reload $DEVLINK_DEV netns testns1 + if [ $? -ne 0 ]; then + echo "Failed to reload into netns \"testns1\"" + exit 1 + fi +} + +cleanup() +{ + pre_cleanup + devlink -N testns1 dev reload $DEVLINK_DEV netns $$ + ip netns del testns1 +} + +trap cleanup EXIT + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh new file mode 100755 index 000000000000..eff6393ce974 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh @@ -0,0 +1,176 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test for port-default priority. Non-IP packets ingress $swp1 and are +# prioritized according to the default priority specified at the port. +# rx_octets_prio_* counters are used to verify the prioritization. +# +# +-----------------------+ +# | H1 | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|------------------+ +# | +# +----|------------------+ +# | SW | | +# | + $swp1 | +# | 192.0.2.2/28 | +# | APP=<prio>,1,0 | +# +-----------------------+ + +ALL_TESTS=" + ping_ipv4 + test_defprio +" + +lib_dir=$(dirname $0)/../../../net/forwarding + +NUM_NETIFS=2 +: ${HIT_TIMEOUT:=1000} # ms +source $lib_dir/lib.sh + +declare -a APP + +defprio_install() +{ + local dev=$1; shift + local prio=$1; shift + local app="app=$prio,1,0" + + lldptool -T -i $dev -V APP $app >/dev/null + lldpad_app_wait_set $dev + APP[$prio]=$app +} + +defprio_uninstall() +{ + local dev=$1; shift + local prio=$1; shift + local app=${APP[$prio]} + + lldptool -T -i $dev -V APP -d $app >/dev/null + lldpad_app_wait_del + unset APP[$prio] +} + +defprio_flush() +{ + local dev=$1; shift + local prio + + if ((${#APP[@]})); then + lldptool -T -i $dev -V APP -d ${APP[@]} >/dev/null + fi + lldpad_app_wait_del + APP=() +} + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +switch_create() +{ + ip link set dev $swp1 up + ip addr add dev $swp1 192.0.2.2/28 +} + +switch_destroy() +{ + defprio_flush $swp1 + ip addr del dev $swp1 192.0.2.2/28 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + vrf_prepare + + h1_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +wait_for_packets() +{ + local t0=$1; shift + local prio_observe=$1; shift + + local t1=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe) + local delta=$((t1 - t0)) + echo $delta + ((delta >= 10)) +} + +__test_defprio() +{ + local prio_install=$1; shift + local prio_observe=$1; shift + local delta + local key + local i + + RET=0 + + defprio_install $swp1 $prio_install + + local t0=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe) + mausezahn -q $h1 -d 100m -c 10 -t arp reply + delta=$(busywait "$HIT_TIMEOUT" wait_for_packets $t0 $prio_observe) + + check_err $? "Default priority $prio_install/$prio_observe: Expected to capture 10 packets, got $delta." + log_test "Default priority $prio_install/$prio_observe" + + defprio_uninstall $swp1 $prio_install +} + +test_defprio() +{ + local prio + + for prio in {0..7}; do + __test_defprio $prio $prio + done + + defprio_install $swp1 3 + __test_defprio 0 3 + __test_defprio 1 3 + __test_defprio 2 3 + __test_defprio 4 4 + __test_defprio 5 5 + __test_defprio 6 6 + __test_defprio 7 7 + defprio_uninstall $swp1 3 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh index e80be65799ad..a5937069ac16 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh @@ -24,24 +24,6 @@ rate() echo $((8 * (t1 - t0) / interval)) } -start_traffic() -{ - local h_in=$1; shift # Where the traffic egresses the host - local sip=$1; shift - local dip=$1; shift - local dmac=$1; shift - - $MZ $h_in -p 8000 -A $sip -B $dip -c 0 \ - -a own -b $dmac -t udp -q & - sleep 1 -} - -stop_traffic() -{ - # Suppress noise from killing mausezahn. - { kill %% && wait %%; } 2>/dev/null -} - check_rate() { local rate=$1; shift @@ -96,3 +78,31 @@ measure_rate() echo $ir $er return $ret } + +bail_on_lldpad() +{ + if systemctl is-active --quiet lldpad; then + + cat >/dev/stderr <<-EOF + WARNING: lldpad is running + + lldpad will likely configure DCB, and this test will + configure Qdiscs. mlxsw does not support both at the + same time, one of them is arbitrarily going to overwrite + the other. That will cause spurious failures (or, + unlikely, passes) of this test. + EOF + + if [[ -z $ALLOW_LLDPAD ]]; then + cat >/dev/stderr <<-EOF + + If you want to run the test anyway, please set + an environment variable ALLOW_LLDPAD to a + non-empty string. + EOF + exit 1 + else + return + fi + fi +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh new file mode 100755 index 000000000000..c9fc4d4885c1 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh @@ -0,0 +1,67 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# A driver for the ETS selftest that implements testing in offloaded datapath. +lib_dir=$(dirname $0)/../../../net/forwarding +source $lib_dir/sch_ets_core.sh +source $lib_dir/devlink_lib.sh +source qos_lib.sh + +ALL_TESTS=" + ping_ipv4 + priomap_mode + ets_test_strict + ets_test_mixed + ets_test_dwrr +" + +switch_create() +{ + ets_switch_create + + # Create a bottleneck so that the DWRR process can kick in. + ethtool -s $h2 speed 1000 autoneg off + ethtool -s $swp2 speed 1000 autoneg off + + # Set the ingress quota high and use the three egress TCs to limit the + # amount of traffic that is admitted to the shared buffers. This makes + # sure that there is always enough traffic of all types to select from + # for the DWRR process. + devlink_port_pool_th_set $swp1 0 12 + devlink_tc_bind_pool_th_set $swp1 0 ingress 0 12 + devlink_port_pool_th_set $swp2 4 12 + devlink_tc_bind_pool_th_set $swp2 7 egress 4 5 + devlink_tc_bind_pool_th_set $swp2 6 egress 4 5 + devlink_tc_bind_pool_th_set $swp2 5 egress 4 5 + + # Note: sch_ets_core.sh uses VLAN ingress-qos-map to assign packet + # priorities at $swp1 based on their 802.1p headers. ingress-qos-map is + # not offloaded by mlxsw as of this writing, but the mapping used is + # 1:1, which is the mapping currently hard-coded by the driver. +} + +switch_destroy() +{ + devlink_tc_bind_pool_th_restore $swp2 5 egress + devlink_tc_bind_pool_th_restore $swp2 6 egress + devlink_tc_bind_pool_th_restore $swp2 7 egress + devlink_port_pool_th_restore $swp2 4 + devlink_tc_bind_pool_th_restore $swp1 0 ingress + devlink_port_pool_th_restore $swp1 0 + + ethtool -s $swp2 autoneg on + ethtool -s $h2 autoneg on + + ets_switch_destroy +} + +# Callback from sch_ets_tests.sh +get_stats() +{ + local band=$1; shift + + ethtool_stats_get "$h2" rx_octets_prio_$band +} + +bail_on_lldpad +ets_run diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib.sh b/tools/testing/selftests/drivers/net/netdevsim/fib.sh new file mode 100755 index 000000000000..2f87c3be76a9 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/fib.sh @@ -0,0 +1,341 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking the FIB offload API. It makes use of netdevsim +# which registers a listener to the FIB notification chain. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + ipv4_identical_routes + ipv4_tos + ipv4_metric + ipv4_replace + ipv4_delete + ipv4_plen + ipv4_replay + ipv4_flush + ipv4_error_path + ipv6_add + ipv6_metric + ipv6_append_single + ipv6_replace_single + ipv6_metric_multipath + ipv6_append_multipath + ipv6_replace_multipath + ipv6_append_multipath_to_single + ipv6_delete_single + ipv6_delete_multipath + ipv6_replay_single + ipv6_replay_multipath + ipv6_error_path +" +NETDEVSIM_PATH=/sys/bus/netdevsim/ +DEV_ADDR=1337 +DEV=netdevsim${DEV_ADDR} +DEVLINK_DEV=netdevsim/${DEV} +SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/ +NUM_NETIFS=0 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh +source $lib_dir/fib_offload_lib.sh + +ipv4_identical_routes() +{ + fib_ipv4_identical_routes_test "testns1" +} + +ipv4_tos() +{ + fib_ipv4_tos_test "testns1" +} + +ipv4_metric() +{ + fib_ipv4_metric_test "testns1" +} + +ipv4_replace() +{ + fib_ipv4_replace_test "testns1" +} + +ipv4_delete() +{ + fib_ipv4_delete_test "testns1" +} + +ipv4_plen() +{ + fib_ipv4_plen_test "testns1" +} + +ipv4_replay_metric() +{ + fib_ipv4_replay_metric_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_tos() +{ + fib_ipv4_replay_tos_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay_plen() +{ + fib_ipv4_replay_plen_test "testns1" "$DEVLINK_DEV" +} + +ipv4_replay() +{ + ipv4_replay_metric + ipv4_replay_tos + ipv4_replay_plen +} + +ipv4_flush() +{ + fib_ipv4_flush_test "testns1" +} + +ipv4_error_path_add() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 192.0.2.${lsb}/32 dev dummy1 \ + &> /dev/null + done + + log_test "IPv4 error path - add" + + ip -n testns1 link del dev dummy1 +} + +ipv4_error_path_replay() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 192.0.2.${lsb}/32 dev dummy1 + done + + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV &> /dev/null + + log_test "IPv4 error path - replay" + + ip -n testns1 link del dev dummy1 + + # Successfully reload after deleting all the routes. + devlink -N testns1 resource set $DEVLINK_DEV path IPv4/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV +} + +ipv4_error_path() +{ + # Test the different error paths of the notifiers by limiting the size + # of the "IPv4/fib" resource. + ipv4_error_path_add + ipv4_error_path_replay +} + +ipv6_add() +{ + fib_ipv6_add_test "testns1" +} + +ipv6_metric() +{ + fib_ipv6_metric_test "testns1" +} + +ipv6_append_single() +{ + fib_ipv6_append_single_test "testns1" +} + +ipv6_replace_single() +{ + fib_ipv6_replace_single_test "testns1" +} + +ipv6_metric_multipath() +{ + fib_ipv6_metric_multipath_test "testns1" +} + +ipv6_append_multipath() +{ + fib_ipv6_append_multipath_test "testns1" +} + +ipv6_replace_multipath() +{ + fib_ipv6_replace_multipath_test "testns1" +} + +ipv6_append_multipath_to_single() +{ + fib_ipv6_append_multipath_to_single_test "testns1" +} + +ipv6_delete_single() +{ + fib_ipv6_delete_single_test "testns1" +} + +ipv6_delete_multipath() +{ + fib_ipv6_delete_multipath_test "testns1" +} + +ipv6_replay_single() +{ + fib_ipv6_replay_single_test "testns1" "$DEVLINK_DEV" +} + +ipv6_replay_multipath() +{ + fib_ipv6_replay_multipath_test "testns1" "$DEVLINK_DEV" +} + +ipv6_error_path_add_single() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 2001:db8:1::${lsb}/128 dev dummy1 \ + &> /dev/null + done + + log_test "IPv6 error path - add single" + + ip -n testns1 link del dev dummy1 +} + +ipv6_error_path_add_multipath() +{ + local lsb + + RET=0 + + for i in $(seq 1 2); do + ip -n testns1 link add name dummy$i type dummy + ip -n testns1 link set dev dummy$i up + ip -n testns1 address add 2001:db8:$i::1/64 dev dummy$i + done + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 2001:db8:10::${lsb}/128 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 &> /dev/null + done + + log_test "IPv6 error path - add multipath" + + for i in $(seq 1 2); do + ip -n testns1 link del dev dummy$i + done +} + +ipv6_error_path_replay() +{ + local lsb + + RET=0 + + ip -n testns1 link add name dummy1 type dummy + ip -n testns1 link set dev dummy1 up + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV + + for lsb in $(seq 1 20); do + ip -n testns1 route add 2001:db8:1::${lsb}/128 dev dummy1 + done + + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 10 + devlink -N testns1 dev reload $DEVLINK_DEV &> /dev/null + + log_test "IPv6 error path - replay" + + ip -n testns1 link del dev dummy1 + + # Successfully reload after deleting all the routes. + devlink -N testns1 resource set $DEVLINK_DEV path IPv6/fib size 100 + devlink -N testns1 dev reload $DEVLINK_DEV +} + +ipv6_error_path() +{ + # Test the different error paths of the notifiers by limiting the size + # of the "IPv6/fib" resource. + ipv6_error_path_add_single + ipv6_error_path_add_multipath + ipv6_error_path_replay +} + +setup_prepare() +{ + local netdev + + modprobe netdevsim &> /dev/null + + echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device + while [ ! -d $SYSFS_NET_DIR ] ; do :; done + + ip netns add testns1 + if [ $? -ne 0 ]; then + echo "Failed to add netns \"testns1\"" + exit 1 + fi + + devlink dev reload $DEVLINK_DEV netns testns1 + if [ $? -ne 0 ]; then + echo "Failed to reload into netns \"testns1\"" + exit 1 + fi +} + +cleanup() +{ + pre_cleanup + ip netns del testns1 + echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device + modprobe -r netdevsim &> /dev/null +} + +trap cleanup EXIT + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 9fd3a0b97f0d..fb5c55dd6df8 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -32,12 +32,17 @@ # lo2: 127.0.0.1/8, ::1/128 # 172.16.2.2/32, 2001:db8:2::2/128 # +# ns-A to ns-C connection - only for VRF and same config +# as ns-A to ns-B +# # server / client nomenclature relative to ns-A VERBOSE=0 NSA_DEV=eth1 +NSA_DEV2=eth2 NSB_DEV=eth1 +NSC_DEV=eth2 VRF=red VRF_TABLE=1101 @@ -45,17 +50,22 @@ VRF_TABLE=1101 NSA_IP=172.16.1.1 NSB_IP=172.16.1.2 VRF_IP=172.16.3.1 +NS_NET=172.16.1.0/24 # IPv6 config NSA_IP6=2001:db8:1::1 NSB_IP6=2001:db8:1::2 VRF_IP6=2001:db8:3::1 +NS_NET6=2001:db8:1::/120 NSA_LO_IP=172.16.2.1 NSB_LO_IP=172.16.2.2 NSA_LO_IP6=2001:db8:2::1 NSB_LO_IP6=2001:db8:2::2 +MD5_PW=abc123 +MD5_WRONG_PW=abc1234 + MCAST=ff02::1 # set after namespace create NSA_LINKIP6= @@ -63,9 +73,11 @@ NSB_LINKIP6= NSA=ns-A NSB=ns-B +NSC=ns-C NSA_CMD="ip netns exec ${NSA}" NSB_CMD="ip netns exec ${NSB}" +NSC_CMD="ip netns exec ${NSC}" which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) @@ -195,6 +207,11 @@ run_cmd_nsb() do_run_cmd ${NSB_CMD} $* } +run_cmd_nsc() +{ + do_run_cmd ${NSC_CMD} $* +} + setup_cmd() { local cmd="$*" @@ -401,6 +418,7 @@ cleanup() fi ip netns del ${NSB} + ip netns del ${NSC} >/dev/null 2>&1 } setup() @@ -432,6 +450,12 @@ setup() ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV} ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} + + # some VRF tests use ns-C which has the same config as + # ns-B but for a device NOT in the VRF + create_ns ${NSC} "-" "-" + connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \ + ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 else ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} @@ -714,6 +738,218 @@ ipv4_ping() ################################################################################ # IPv4 TCP +# +# MD5 tests without VRF +# +ipv4_tcp_md5_novrf() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -s -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -s & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -s -M ${MD5_PW} -r ${NSB_LO_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -l ${NSB_LO_IP} -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: Prefix config, client address not in configured prefix" +} + +# +# MD5 tests with VRF +# +ipv4_tcp_md5() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout since server does not have MD5 auth" + run_cmd nettest -s -d ${VRF} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout since server config differs from client" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_LO_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout since client address is outside of prefix" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -l ${NSB_LO_IP} -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config, client address not in configured prefix" + + # + # duplicate config between default VRF and a VRF + # + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -r ${NSB_IP} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF with default VRF pw" + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET} & + run_cmd nettest -s -M ${MD5_WRONG_PW} -m ${NS_NET} & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF with default VRF pw" + + # + # negative tests + # + log_start + run_cmd nettest -s -d ${NSA_DEV} -M ${MD5_PW} -r ${NSB_IP} + log_test $? 1 "MD5: VRF: Device must be a VRF - single address" + + log_start + run_cmd nettest -s -d ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET} + log_test $? 1 "MD5: VRF: Device must be a VRF - prefix" + +} + ipv4_tcp_novrf() { local a @@ -831,6 +1067,8 @@ ipv4_tcp_novrf() show_hint "Should fail 'Connection refused'" run_cmd nettest -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" + + ipv4_tcp_md5_novrf } ipv4_tcp_vrf() @@ -883,6 +1121,9 @@ ipv4_tcp_vrf() run_cmd nettest -r ${a} -d ${NSA_DEV} log_test_addr ${a} $? 1 "Global server, local connection" + # run MD5 tests + ipv4_tcp_md5 + # # enable VRF global server # @@ -924,8 +1165,8 @@ ipv4_tcp_vrf() for a in ${NSA_IP} ${VRF_IP} do log_start - show_hint "Should fail 'No route to host' since client is not bound to VRF" - run_cmd nettest -s -2 ${VRF} & + show_hint "Should fail 'Connection refused' since client is not bound to VRF" + run_cmd nettest -s -d ${VRF} & sleep 1 run_cmd nettest -r ${a} log_test_addr ${a} $? 1 "Global server, local connection" @@ -1961,6 +2202,218 @@ ipv6_ping() ################################################################################ # IPv6 TCP +# +# MD5 tests without VRF +# +ipv6_tcp_md5_novrf() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -6 -s -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -6 -s & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -6 -s -M ${MD5_PW} -r ${NSB_LO_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout due to MD5 mismatch" + run_cmd nettest -6 -s -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -l ${NSB_LO_IP6} -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: Prefix config, client address not in configured prefix" +} + +# +# MD5 tests with VRF +# +ipv6_tcp_md5() +{ + # + # single address + # + + # basic use case + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config" + + # client sends MD5, server not configured + log_start + show_hint "Should timeout since server does not have MD5 auth" + run_cmd nettest -6 -s -d ${VRF} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Server no config, client uses password" + + # wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Client uses wrong password" + + # client from different address + log_start + show_hint "Should timeout since server config differs from client" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_LO_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Client address does not match address configured with password" + + # + # MD5 extension - prefix length + # + + # client in prefix + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config" + + # client in prefix, wrong password + log_start + show_hint "Should timeout since client uses wrong password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config, client uses wrong password" + + # client outside of prefix + log_start + show_hint "Should timeout since client address is outside of prefix" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -l ${NSB_LO_IP6} -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config, client address not in configured prefix" + + # + # duplicate config between default VRF and a VRF + # + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -r ${NSB_IP6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -r ${NSB_IP6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Single address config in default VRF and VRF, conn in VRF with default VRF pw" + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF" + + log_start + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 0 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF" + + log_start + show_hint "Should timeout since client in default VRF uses VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsc nettest -6 -r ${NSA_IP6} -M ${MD5_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in default VRF with VRF pw" + + log_start + show_hint "Should timeout since client in VRF uses default VRF password" + run_cmd nettest -6 -s -d ${VRF} -M ${MD5_PW} -m ${NS_NET6} & + run_cmd nettest -6 -s -M ${MD5_WRONG_PW} -m ${NS_NET6} & + sleep 1 + run_cmd_nsb nettest -6 -r ${NSA_IP6} -M ${MD5_WRONG_PW} + log_test $? 2 "MD5: VRF: Prefix config in default VRF and VRF, conn in VRF with default VRF pw" + + # + # negative tests + # + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -M ${MD5_PW} -r ${NSB_IP6} + log_test $? 1 "MD5: VRF: Device must be a VRF - single address" + + log_start + run_cmd nettest -6 -s -d ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET6} + log_test $? 1 "MD5: VRF: Device must be a VRF - prefix" + +} + ipv6_tcp_novrf() { local a @@ -2077,6 +2530,8 @@ ipv6_tcp_novrf() run_cmd nettest -6 -d ${NSA_DEV} -r ${a} log_test_addr ${a} $? 1 "No server, device client, local conn" done + + ipv6_tcp_md5_novrf } ipv6_tcp_vrf() @@ -2145,6 +2600,9 @@ ipv6_tcp_vrf() run_cmd nettest -6 -r ${a} -d ${NSA_DEV} log_test_addr ${a} $? 1 "Global server, local connection" + # run MD5 tests + ipv6_tcp_md5 + # # enable VRF global server # @@ -2205,8 +2663,8 @@ ipv6_tcp_vrf() for a in ${NSA_IP6} ${VRF_IP6} do log_start - show_hint "Fails 'No route to host' since client is not in VRF" - run_cmd nettest -6 -s -2 ${VRF} & + show_hint "Fails 'Connection refused' since client is not in VRF" + run_cmd nettest -6 -s -d ${VRF} & sleep 1 run_cmd nettest -6 -r ${a} log_test_addr ${a} $? 1 "Global server, local connection" diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh new file mode 100644 index 000000000000..66496659bea7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh @@ -0,0 +1,873 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Various helpers and tests to verify FIB offload. + +__fib_trap_check() +{ + local ns=$1; shift + local family=$1; shift + local route=$1; shift + local should_fail=$1; shift + local ret + + ip -n $ns -j -p -$family route show $route \ + | jq -e '.[]["flags"] | contains(["trap"])' &> /dev/null + ret=$? + if [[ $should_fail == "true" ]]; then + if [[ $ret -ne 0 ]]; then + return 0 + else + return 1 + fi + fi + + return $ret +} + +fib_trap_check() +{ + local ns=$1; shift + local family=$1; shift + local route=$1; shift + local should_fail=$1; shift + + busywait 5000 __fib_trap_check $ns $family "$route" $should_fail +} + +fib4_trap_check() +{ + local ns=$1; shift + local route=$1; shift + local should_fail=$1; shift + + fib_trap_check $ns 4 "$route" $should_fail +} + +fib6_trap_check() +{ + local ns=$1; shift + local route=$1; shift + local should_fail=$1; shift + + fib_trap_check $ns 6 "$route" $should_fail +} + +fib_ipv4_identical_routes_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 3); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 192.0.2.0/24 dev dummy2 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 tos 0 metric 1024" true + check_err $? "Appended route in hardware when should not" + + ip -n $ns route prepend 192.0.2.0/24 dev dummy3 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy3 tos 0 metric 1024" false + check_err $? "Prepended route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true + check_err $? "Route was not replaced in hardware by prepended one" + + log_test "IPv4 identical routes" + + for i in $(seq 1 3); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv4_tos_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 2 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 2 metric 1024" false + check_err $? "Highest TOS route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true + check_err $? "Lowest TOS route still in hardware when should not" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1 metric 1024" true + check_err $? "Middle TOS route in hardware when should not" + + log_test "IPv4 routes with TOS" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_metric_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1022 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1022" false + check_err $? "Lowest metric route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" true + check_err $? "Highest metric route still in hardware when should not" + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1023 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1023" true + check_err $? "Middle metric route in hardware when should not" + + log_test "IPv4 routes with metric" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replace_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route replace 192.0.2.0/24 dev dummy2 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1024" false + check_err $? "Replacement route not in hardware when should" + + # Add a route with an higher metric and make sure that replacing it + # does not affect the lower metric one. + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1025 + ip -n $ns route replace 192.0.2.0/24 dev dummy2 metric 1025 + + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + fib4_trap_check $ns "192.0.2.0/24 dev dummy2 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv4 route replace" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv4_delete_test() +{ + local ns=$1; shift + local metric + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + # Insert multiple routes with the same prefix and length and varying + # metrics. Make sure that throughout delete operations the lowest + # metric route is the one in hardware. + for metric in $(seq 1024 1026); do + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric $metric + done + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route del 192.0.2.0/24 dev dummy1 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" false + check_err $? "Lowest metric route not in hardware when should" + + ip -n $ns route del 192.0.2.0/24 dev dummy1 metric 1026 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" false + check_err $? "Sole route not in hardware when should" + + log_test "IPv4 route delete" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_plen_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + # Add two routes with the same key and different prefix length and + # make sure both are in hardware. It can be verfied that both are + # sharing the same leaf by checking the /proc/net/fib_trie + ip -n $ns route add 192.0.2.0/24 dev dummy1 + ip -n $ns route add 192.0.2.0/25 dev dummy1 + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1" false + check_err $? "/24 not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/25 dev dummy1" false + check_err $? "/25 not in hardware when should" + + log_test "IPv4 routes with different prefix length" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replay_metric_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1024 + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric 1025 + + devlink -N $ns dev reload $devlink_dev + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv4 routes replay - metric" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replay_tos_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 + + devlink -N $ns dev reload $devlink_dev + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1" false + check_err $? "Highest TOS route not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0" true + check_err $? "Lowest TOS route in hardware when should not" + + log_test "IPv4 routes replay - TOS" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_replay_plen_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 192.0.2.0/24 dev dummy1 + ip -n $ns route add 192.0.2.0/25 dev dummy1 + + devlink -N $ns dev reload $devlink_dev + + fib4_trap_check $ns "192.0.2.0/24 dev dummy1" false + check_err $? "/24 not in hardware when should" + + fib4_trap_check $ns "192.0.2.0/25 dev dummy1" false + check_err $? "/25 not in hardware when should" + + log_test "IPv4 routes replay - prefix length" + + ip -n $ns link del dev dummy1 +} + +fib_ipv4_flush_test() +{ + local ns=$1; shift + local metric + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + # Exercise the routes flushing code paths by inserting various + # prefix routes on a netdev and then deleting it. + for metric in $(seq 1 20); do + ip -n $ns route add 192.0.2.0/24 dev dummy1 metric $metric + done + + ip -n $ns link del dev dummy1 + + log_test "IPv4 routes flushing" +} + +fib_ipv6_add_test() +{ + local ns=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:1::/64 dev dummy2 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" true + check_err $? "Route in hardware when should not" + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware after appending route" + + log_test "IPv6 single route add" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_metric_test() +{ + local ns=$1; shift + + RET=0 + + ip -n $ns link add name dummy1 type dummy + ip -n $ns link set dev dummy1 up + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1022 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1022" false + check_err $? "Lowest metric route not in hardware when should" + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" true + check_err $? "Highest metric route still in hardware when should not" + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1023 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1023" true + check_err $? "Middle metric route in hardware when should not" + + log_test "IPv6 routes with metric" + + ip -n $ns link del dev dummy1 +} + +fib_ipv6_append_single_test() +{ + local ns=$1; shift + + # When an IPv6 multipath route is added without the 'nexthop' keyword, + # different code paths are taken compared to when the keyword is used. + # This test tries to verify the former. + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 via 2001:db8:1::2 metric 1024 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:10::/64 via 2001:db8:2::2 metric 1024 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after appending" + + ip -n $ns route add 2001:db8:10::/64 via 2001:db8:1::2 metric 1025 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not" + + ip -n $ns route append 2001:db8:10::/64 via 2001:db8:2::2 metric 1025 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not after appending" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + + log_test "IPv6 append single route without 'nexthop' keyword" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replace_single_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route replace 2001:db8:1::/64 dev dummy2 metric 1024 + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" false + check_err $? "Replacement route not in hardware when should" + + # Add a route with an higher metric and make sure that replacing it + # does not affect the lower metric one. + ip -n $ns route add 2001:db8:1::/64 dev dummy1 metric 1025 + ip -n $ns route replace 2001:db8:1::/64 dev dummy2 metric 1025 + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv6 single route replace" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_metric_multipath_test() +{ + local ns=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route add 2001:db8:10::/64 metric 1022 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1022" false + check_err $? "Lowest metric route not in hardware when should" + + ip -n $ns route add 2001:db8:10::/64 metric 1023 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" true + check_err $? "Highest metric route still in hardware when should not" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1023" true + check_err $? "Middle metric route in hardware when should not" + + log_test "IPv6 multipath routes with metric" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_append_multipath_test() +{ + local ns=$1; shift + + RET=0 + + for i in $(seq 1 3); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:2::2 dev dummy2 \ + nexthop via 2001:db8:3::2 dev dummy3 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after appending" + + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not" + + ip -n $ns route append 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:2::2 dev dummy2 \ + nexthop via 2001:db8:3::2 dev dummy3 + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Route in hardware when should not after appending" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + + log_test "IPv6 append multipath route with 'nexthop' keyword" + + for i in $(seq 1 3); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replace_multipath_test() +{ + local ns=$1; shift + local i + + RET=0 + + for i in $(seq 1 3); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route replace 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:3::2 dev dummy3 + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Replacement route not in hardware when should" + + # Add a route with an higher metric and make sure that replacing it + # does not affect the lower metric one. + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route replace 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:3::2 dev dummy3 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Lowest metric route not in hardware when should" + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Highest metric route in hardware when should not" + + log_test "IPv6 multipath route replace" + + for i in $(seq 1 3); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_append_multipath_to_single_test() +{ + local ns=$1; shift + + # Test that when the first route in the leaf is not a multipath route + # and we try to append a multipath route with the same metric to it, it + # is not notified. + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware when should" + + ip -n $ns route append 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:2::2 dev dummy2 + fib6_trap_check $ns "2001:db8:10::/64 dev dummy2 metric 1024" true + check_err $? "Route in hardware when should not" + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware after append" + + log_test "IPv6 append multipath route to non-multipath route" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_delete_single_test() +{ + local ns=$1; shift + + # Test various deletion scenarios, where only a single route is + # deleted from the FIB node. + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + # Test deletion of a single route when it is the only route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + log_test "IPv6 delete sole single route" + + # Test that deletion of last route does not affect the first one. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025 + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1024" false + check_err $? "Route not in hardware after deleting higher metric route" + + log_test "IPv6 delete single route not in hardware" + + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + # Test that first route is replaced by next single route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete single route - replaced by single" + + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025 + + # Test that first route is replaced by next multipath route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1024 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete single route - replaced by multipath" + + ip -n $ns route del 2001:db8:10::/64 metric 1025 + + # Test deletion of a single nexthop from a multipath route. + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after deleting a single nexthop" + + log_test "IPv6 delete single nexthop" + + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_delete_multipath_test() +{ + local ns=$1; shift + + # Test various deletion scenarios, where an entire multipath route is + # deleted from the FIB node. + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + # Test deletion of a multipath route when it is the only route in the + # FIB node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + log_test "IPv6 delete sole multipath route" + + # Test that deletion of last route does not affect the first one. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1025 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "Route not in hardware after deleting higher metric route" + + log_test "IPv6 delete multipath route not in hardware" + + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + # Test that first route is replaced by next single route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 dev dummy1 metric 1025 + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 dev dummy1 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete multipath route - replaced by single" + + ip -n $ns route del 2001:db8:10::/64 dev dummy1 metric 1025 + + # Test that first route is replaced by next multipath route in the FIB + # node. + RET=0 + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route del 2001:db8:10::/64 metric 1024 + + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" false + check_err $? "Route not in hardware after deleting lowest metric route" + + log_test "IPv6 delete multipath route - replaced by multipath" + + ip -n $ns route del 2001:db8:10::/64 metric 1025 + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replay_single_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + done + + ip -n $ns route add 2001:db8:1::/64 dev dummy1 + ip -n $ns route append 2001:db8:1::/64 dev dummy2 + + devlink -N $ns dev reload $devlink_dev + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy1" false + check_err $? "First route not in hardware when should" + + fib6_trap_check $ns "2001:db8:1::/64 dev dummy2" true + check_err $? "Second route in hardware when should not" + + log_test "IPv6 routes replay - single route" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} + +fib_ipv6_replay_multipath_test() +{ + local ns=$1; shift + local devlink_dev=$1; shift + + RET=0 + + for i in $(seq 1 2); do + ip -n $ns link add name dummy$i type dummy + ip -n $ns link set dev dummy$i up + ip -n $ns address add 2001:db8:$i::1/64 dev dummy$i + done + + ip -n $ns route add 2001:db8:10::/64 metric 1024 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + ip -n $ns route add 2001:db8:10::/64 metric 1025 \ + nexthop via 2001:db8:1::2 dev dummy1 \ + nexthop via 2001:db8:2::2 dev dummy2 + + devlink -N $ns dev reload $devlink_dev + + fib6_trap_check $ns "2001:db8:10::/64 metric 1024" false + check_err $? "First route not in hardware when should" + + fib6_trap_check $ns "2001:db8:10::/64 metric 1025" true + check_err $? "Second route in hardware when should not" + + log_test "IPv6 routes replay - multipath route" + + for i in $(seq 1 2); do + ip -n $ns link del dev dummy$i + done +} diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 1f64e7348f69..8dc5fac98cbc 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -225,6 +225,29 @@ log_info() echo "INFO: $msg" } +busywait() +{ + local timeout=$1; shift + + local start_time="$(date -u +%s%3N)" + while true + do + local out + out=$("$@") + local ret=$? + if ((!ret)); then + echo -n "$out" + return 0 + fi + + local current_time="$(date -u +%s%3N)" + if ((current_time - start_time > timeout)); then + echo -n "$out" + return 1 + fi + done +} + setup_wait_dev() { local dev=$1; shift @@ -1065,3 +1088,21 @@ flood_test() flood_unicast_test $br_port $host1_if $host2_if flood_multicast_test $br_port $host1_if $host2_if } + +start_traffic() +{ + local h_in=$1; shift # Where the traffic egresses the host + local sip=$1; shift + local dip=$1; shift + local dmac=$1; shift + + $MZ $h_in -p 8000 -A $sip -B $dip -c 0 \ + -a own -b $dmac -t udp -q & + sleep 1 +} + +stop_traffic() +{ + # Suppress noise from killing mausezahn. + { kill %% && wait %%; } 2>/dev/null +} diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh index a75cb51cc5bd..057f91b05098 100755 --- a/tools/testing/selftests/net/forwarding/router.sh +++ b/tools/testing/selftests/net/forwarding/router.sh @@ -1,9 +1,23 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="ping_ipv4 ping_ipv6" +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + sip_in_class_e + mc_mac_mismatch + ipv4_sip_equal_dip + ipv6_sip_equal_dip + ipv4_dip_link_local +" + NUM_NETIFS=4 source lib.sh +source tc_common.sh + +require_command $MCD +require_command $MC_CLI +table_name=selftests h1_create() { @@ -64,6 +78,8 @@ router_create() ip link set dev $rp1 up ip link set dev $rp2 up + tc qdisc add dev $rp2 clsact + ip address add 192.0.2.1/24 dev $rp1 ip address add 2001:db8:1::1/64 dev $rp1 @@ -79,10 +95,31 @@ router_destroy() ip address del 2001:db8:1::1/64 dev $rp1 ip address del 192.0.2.1/24 dev $rp1 + tc qdisc del dev $rp2 clsact + ip link set dev $rp2 down ip link set dev $rp1 down } +start_mcd() +{ + SMCROUTEDIR="$(mktemp -d)" + + for ((i = 1; i <= $NUM_NETIFS; ++i)); do + echo "phyint ${NETIFS[p$i]} enable" >> \ + $SMCROUTEDIR/$table_name.conf + done + + $MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \ + -P $SMCROUTEDIR/$table_name.pid +} + +kill_mcd() +{ + pkill $MCD + rm -rf $SMCROUTEDIR +} + setup_prepare() { h1=${NETIFS[p1]} @@ -91,6 +128,10 @@ setup_prepare() rp2=${NETIFS[p3]} h2=${NETIFS[p4]} + rp1mac=$(mac_get $rp1) + + start_mcd + vrf_prepare h1_create @@ -113,6 +154,8 @@ cleanup() h1_destroy vrf_cleanup + + kill_mcd } ping_ipv4() @@ -125,6 +168,150 @@ ping_ipv6() ping6_test $h1 2001:db8:2::2 } +sip_in_class_e() +{ + RET=0 + + # Disable rpfilter to prevent packets to be dropped because of it. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$rp1.rp_filter 0 + + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \ + flower src_ip 240.0.0.1 ip_proto udp action pass + + $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \ + -A 240.0.0.1 -b $rp1mac -B 198.51.100.2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Source IP in class E" + + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower + sysctl_restore net.ipv4.conf.$rp1.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + +create_mcast_sg() +{ + local if_name=$1; shift + local s_addr=$1; shift + local mcast=$1; shift + local dest_ifs=${@} + + $MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs +} + +delete_mcast_sg() +{ + local if_name=$1; shift + local s_addr=$1; shift + local mcast=$1; shift + local dest_ifs=${@} + + $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs +} + +__mc_mac_mismatch() +{ + local desc=$1; shift + local proto=$1; shift + local sip=$1; shift + local dip=$1; shift + local flags=${1:-""}; shift + local dmac=01:02:03:04:05:06 + + RET=0 + + tc filter add dev $rp2 egress protocol $proto pref 1 handle 101 \ + flower dst_ip $dip action pass + + create_mcast_sg $rp1 $sip $dip $rp2 + + $MZ $flags $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b $dmac \ + -B $dip -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Multicast MAC mismatch: $desc" + + delete_mcast_sg $rp1 $sip $dip $rp2 + tc filter del dev $rp2 egress protocol $proto pref 1 handle 101 flower +} + +mc_mac_mismatch() +{ + __mc_mac_mismatch "IPv4" "ip" 192.0.2.2 225.1.2.3 + __mc_mac_mismatch "IPv6" "ipv6" 2001:db8:1::2 ff0e::3 "-6" +} + +ipv4_sip_equal_dip() +{ + RET=0 + + # Disable rpfilter to prevent packets to be dropped because of it. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$rp1.rp_filter 0 + + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \ + flower src_ip 198.51.100.2 action pass + + $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \ + -A 198.51.100.2 -b $rp1mac -B 198.51.100.2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Source IP is equal to destination IP: IPv4" + + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower + sysctl_restore net.ipv4.conf.$rp1.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + +ipv6_sip_equal_dip() +{ + RET=0 + + tc filter add dev $rp2 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::2 action pass + + $MZ -6 $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec \ + -A 2001:db8:2::2 -b $rp1mac -B 2001:db8:2::2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "Source IP is equal to destination IP: IPv6" + + tc filter del dev $rp2 egress protocol ipv6 pref 1 handle 101 flower +} + +ipv4_dip_link_local() +{ + local dip=169.254.1.1 + + RET=0 + + tc filter add dev $rp2 egress protocol ip pref 1 handle 101 \ + flower dst_ip $dip action pass + + ip neigh add 169.254.1.1 lladdr 00:11:22:33:44:55 dev $rp2 + ip route add 169.254.1.0/24 dev $rp2 + + $MZ $h1 -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b $rp1mac -B $dip -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "IPv4 destination IP is link-local" + + ip route del 169.254.1.0/24 dev $rp2 + ip neigh del 169.254.1.1 lladdr 00:11:22:33:44:55 dev $rp2 + tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/sch_ets.sh b/tools/testing/selftests/net/forwarding/sch_ets.sh new file mode 100755 index 000000000000..40e0ad1bc4f2 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_ets.sh @@ -0,0 +1,44 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# A driver for the ETS selftest that implements testing in slowpath. +lib_dir=. +source sch_ets_core.sh + +ALL_TESTS=" + ping_ipv4 + priomap_mode + ets_test_strict + ets_test_mixed + ets_test_dwrr + classifier_mode + ets_test_strict + ets_test_mixed + ets_test_dwrr +" + +switch_create() +{ + ets_switch_create + + # Create a bottleneck so that the DWRR process can kick in. + tc qdisc add dev $swp2 root handle 1: tbf \ + rate 1Gbit burst 1Mbit latency 100ms + PARENT="parent 1:" +} + +switch_destroy() +{ + ets_switch_destroy + tc qdisc del dev $swp2 root +} + +# Callback from sch_ets_tests.sh +get_stats() +{ + local stream=$1; shift + + link_stats_get $h2.1$stream rx bytes +} + +ets_run diff --git a/tools/testing/selftests/net/forwarding/sch_ets_core.sh b/tools/testing/selftests/net/forwarding/sch_ets_core.sh new file mode 100644 index 000000000000..f906fcc66572 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_ets_core.sh @@ -0,0 +1,300 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This is a template for ETS Qdisc test. +# +# This test sends from H1 several traffic streams with 802.1p-tagged packets. +# The tags are used at $swp1 to prioritize the traffic. Each stream is then +# queued at a different ETS band according to the assigned priority. After +# runnig for a while, counters at H2 are consulted to determine whether the +# traffic scheduling was according to the ETS configuration. +# +# This template is supposed to be embedded by a test driver, which implements +# statistics collection, any HW-specific stuff, and prominently configures the +# system to assure that there is overcommitment at $swp2. That is necessary so +# that the ETS traffic selection algorithm kicks in and has to schedule some +# traffic at the expense of other. +# +# A driver for veth-based testing is in sch_ets.sh, an example of a driver for +# an offloaded data path is in selftests/drivers/net/mlxsw/sch_ets.sh. +# +# +---------------------------------------------------------------------+ +# | H1 | +# | + $h1.10 + $h1.11 + $h1.12 | +# | | 192.0.2.1/28 | 192.0.2.17/28 | 192.0.2.33/28 | +# | | egress-qos-map | egress-qos-map | egress-qos-map | +# | | 0:0 | 0:1 | 0:2 | +# | \____________________ | ____________________/ | +# | \|/ | +# | + $h1 | +# +---------------------------|-----------------------------------------+ +# | +# +---------------------------|-----------------------------------------+ +# | SW + $swp1 | +# | | >1Gbps | +# | ____________________/|\____________________ | +# | / | \ | +# | +--|----------------+ +--|----------------+ +--|----------------+ | +# | | + $swp1.10 | | + $swp1.11 | | + $swp1.12 | | +# | | ingress-qos-map| | ingress-qos-map| | ingress-qos-map| | +# | | 0:0 1:1 2:2 | | 0:0 1:1 2:2 | | 0:0 1:1 2:2 | | +# | | | | | | | | +# | | BR10 | | BR11 | | BR12 | | +# | | | | | | | | +# | | + $swp2.10 | | + $swp2.11 | | + $swp2.12 | | +# | +--|----------------+ +--|----------------+ +--|----------------+ | +# | \____________________ | ____________________/ | +# | \|/ | +# | + $swp2 | +# | | 1Gbps (ethtool or HTB qdisc) | +# | | qdisc ets quanta $W0 $W1 $W2 | +# | | priomap 0 1 2 | +# +---------------------------|-----------------------------------------+ +# | +# +---------------------------|-----------------------------------------+ +# | H2 + $h2 | +# | ____________________/|\____________________ | +# | / | \ | +# | + $h2.10 + $h2.11 + $h2.12 | +# | 192.0.2.2/28 192.0.2.18/28 192.0.2.34/28 | +# +---------------------------------------------------------------------+ + +NUM_NETIFS=4 +CHECK_TC=yes +source $lib_dir/lib.sh +source $lib_dir/sch_ets_tests.sh + +PARENT=root +QDISC_DEV= + +sip() +{ + echo 192.0.2.$((16 * $1 + 1)) +} + +dip() +{ + echo 192.0.2.$((16 * $1 + 2)) +} + +# Callback from sch_ets_tests.sh +ets_start_traffic() +{ + local dst_mac=$(mac_get $h2) + local i=$1; shift + + start_traffic $h1.1$i $(sip $i) $(dip $i) $dst_mac +} + +ETS_CHANGE_QDISC= + +priomap_mode() +{ + echo "Running in priomap mode" + ets_delete_qdisc + ETS_CHANGE_QDISC=ets_change_qdisc_priomap +} + +classifier_mode() +{ + echo "Running in classifier mode" + ets_delete_qdisc + ETS_CHANGE_QDISC=ets_change_qdisc_classifier +} + +ets_change_qdisc_priomap() +{ + local dev=$1; shift + local nstrict=$1; shift + local priomap=$1; shift + local quanta=("${@}") + + local op=$(if [[ -n $QDISC_DEV ]]; then echo change; else echo add; fi) + + tc qdisc $op dev $dev $PARENT handle 10: ets \ + $(if ((nstrict)); then echo strict $nstrict; fi) \ + $(if ((${#quanta[@]})); then echo quanta ${quanta[@]}; fi) \ + priomap $priomap + QDISC_DEV=$dev +} + +ets_change_qdisc_classifier() +{ + local dev=$1; shift + local nstrict=$1; shift + local priomap=$1; shift + local quanta=("${@}") + + local op=$(if [[ -n $QDISC_DEV ]]; then echo change; else echo add; fi) + + tc qdisc $op dev $dev $PARENT handle 10: ets \ + $(if ((nstrict)); then echo strict $nstrict; fi) \ + $(if ((${#quanta[@]})); then echo quanta ${quanta[@]}; fi) + + if [[ $op == add ]]; then + local prio=0 + local band + + for band in $priomap; do + tc filter add dev $dev parent 10: basic \ + match "meta(priority eq $prio)" \ + flowid 10:$((band + 1)) + ((prio++)) + done + fi + QDISC_DEV=$dev +} + +# Callback from sch_ets_tests.sh +ets_change_qdisc() +{ + if [[ -z "$ETS_CHANGE_QDISC" ]]; then + exit 1 + fi + $ETS_CHANGE_QDISC "$@" +} + +ets_delete_qdisc() +{ + if [[ -n $QDISC_DEV ]]; then + tc qdisc del dev $QDISC_DEV $PARENT + QDISC_DEV= + fi +} + +h1_create() +{ + local i; + + simple_if_init $h1 + mtu_set $h1 9900 + for i in {0..2}; do + vlan_create $h1 1$i v$h1 $(sip $i)/28 + ip link set dev $h1.1$i type vlan egress 0:$i + done +} + +h1_destroy() +{ + local i + + for i in {0..2}; do + vlan_destroy $h1 1$i + done + mtu_restore $h1 + simple_if_fini $h1 +} + +h2_create() +{ + local i + + simple_if_init $h2 + mtu_set $h2 9900 + for i in {0..2}; do + vlan_create $h2 1$i v$h2 $(dip $i)/28 + done +} + +h2_destroy() +{ + local i + + for i in {0..2}; do + vlan_destroy $h2 1$i + done + mtu_restore $h2 + simple_if_fini $h2 +} + +ets_switch_create() +{ + local i + + ip link set dev $swp1 up + mtu_set $swp1 9900 + + ip link set dev $swp2 up + mtu_set $swp2 9900 + + for i in {0..2}; do + vlan_create $swp1 1$i + ip link set dev $swp1.1$i type vlan ingress 0:0 1:1 2:2 + + vlan_create $swp2 1$i + + ip link add dev br1$i type bridge + ip link set dev $swp1.1$i master br1$i + ip link set dev $swp2.1$i master br1$i + + ip link set dev br1$i up + ip link set dev $swp1.1$i up + ip link set dev $swp2.1$i up + done +} + +ets_switch_destroy() +{ + local i + + ets_delete_qdisc + + for i in {0..2}; do + ip link del dev br1$i + vlan_destroy $swp2 1$i + vlan_destroy $swp1 1$i + done + + mtu_restore $swp2 + ip link set dev $swp2 down + + mtu_restore $swp1 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + put=$swp2 + hut=$h2 + + vrf_prepare + + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.10 $(dip 0) " vlan 10" + ping_test $h1.11 $(dip 1) " vlan 11" + ping_test $h1.12 $(dip 2) " vlan 12" +} + +ets_run() +{ + trap cleanup EXIT + + setup_prepare + setup_wait + + tests_run + + exit $EXIT_STATUS +} diff --git a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh new file mode 100644 index 000000000000..3c3b204d47e8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh @@ -0,0 +1,227 @@ +# SPDX-License-Identifier: GPL-2.0 + +# Global interface: +# $put -- port under test (e.g. $swp2) +# get_stats($band) -- A function to collect stats for band +# ets_start_traffic($band) -- Start traffic for this band +# ets_change_qdisc($op, $dev, $nstrict, $quanta...) -- Add or change qdisc + +# WS describes the Qdisc configuration. It has one value per band (so the +# number of array elements indicates the number of bands). If the value is +# 0, it is a strict band, otherwise the it's a DRR band and the value is +# that band's quantum. +declare -a WS + +qdisc_describe() +{ + local nbands=${#WS[@]} + local nstrict=0 + local i + + for ((i = 0; i < nbands; i++)); do + if ((!${WS[$i]})); then + : $((nstrict++)) + fi + done + + echo -n "ets bands $nbands" + if ((nstrict)); then + echo -n " strict $nstrict" + fi + if ((nstrict < nbands)); then + echo -n " quanta" + for ((i = nstrict; i < nbands; i++)); do + echo -n " ${WS[$i]}" + done + fi +} + +__strict_eval() +{ + local desc=$1; shift + local d=$1; shift + local total=$1; shift + local above=$1; shift + + RET=0 + + if ((! total)); then + check_err 1 "No traffic observed" + log_test "$desc" + return + fi + + local ratio=$(echo "scale=2; 100 * $d / $total" | bc -l) + if ((above)); then + test $(echo "$ratio > 95.0" | bc -l) -eq 1 + check_err $? "Not enough traffic" + log_test "$desc" + log_info "Expected ratio >95% Measured ratio $ratio" + else + test $(echo "$ratio < 5" | bc -l) -eq 1 + check_err $? "Too much traffic" + log_test "$desc" + log_info "Expected ratio <5% Measured ratio $ratio" + fi +} + +strict_eval() +{ + __strict_eval "$@" 1 +} + +notraf_eval() +{ + __strict_eval "$@" 0 +} + +__ets_dwrr_test() +{ + local -a streams=("$@") + + local low_stream=${streams[0]} + local seen_strict=0 + local -a t0 t1 d + local stream + local total + local i + + echo "Testing $(qdisc_describe), streams ${streams[@]}" + + for stream in ${streams[@]}; do + ets_start_traffic $stream + done + + sleep 10 + + t0=($(for stream in ${streams[@]}; do + get_stats $stream + done)) + + sleep 10 + + t1=($(for stream in ${streams[@]}; do + get_stats $stream + done)) + d=($(for ((i = 0; i < ${#streams[@]}; i++)); do + echo $((${t1[$i]} - ${t0[$i]})) + done)) + total=$(echo ${d[@]} | sed 's/ /+/g' | bc) + + for ((i = 0; i < ${#streams[@]}; i++)); do + local stream=${streams[$i]} + if ((seen_strict)); then + notraf_eval "band $stream" ${d[$i]} $total + elif ((${WS[$stream]} == 0)); then + strict_eval "band $stream" ${d[$i]} $total + seen_strict=1 + elif ((stream == low_stream)); then + # Low stream is used as DWRR evaluation reference. + continue + else + multipath_eval "bands $low_stream:$stream" \ + ${WS[$low_stream]} ${WS[$stream]} \ + ${d[0]} ${d[$i]} + fi + done + + for stream in ${streams[@]}; do + stop_traffic + done +} + +ets_dwrr_test_012() +{ + __ets_dwrr_test 0 1 2 +} + +ets_dwrr_test_01() +{ + __ets_dwrr_test 0 1 +} + +ets_dwrr_test_12() +{ + __ets_dwrr_test 1 2 +} + +ets_qdisc_setup() +{ + local dev=$1; shift + local nstrict=$1; shift + local -a quanta=("$@") + + local ndwrr=${#quanta[@]} + local nbands=$((nstrict + ndwrr)) + local nstreams=$(if ((nbands > 3)); then echo 3; else echo $nbands; fi) + local priomap=$(seq 0 $((nstreams - 1))) + local i + + WS=($( + for ((i = 0; i < nstrict; i++)); do + echo 0 + done + for ((i = 0; i < ndwrr; i++)); do + echo ${quanta[$i]} + done + )) + + ets_change_qdisc $dev $nstrict "$priomap" ${quanta[@]} +} + +ets_set_dwrr_uniform() +{ + ets_qdisc_setup $put 0 3300 3300 3300 +} + +ets_set_dwrr_varying() +{ + ets_qdisc_setup $put 0 5000 3500 1500 +} + +ets_set_strict() +{ + ets_qdisc_setup $put 3 +} + +ets_set_mixed() +{ + ets_qdisc_setup $put 1 5000 2500 1500 +} + +ets_change_quantum() +{ + tc class change dev $put classid 10:2 ets quantum 8000 + WS[1]=8000 +} + +ets_set_dwrr_two_bands() +{ + ets_qdisc_setup $put 0 5000 2500 +} + +ets_test_strict() +{ + ets_set_strict + ets_dwrr_test_01 + ets_dwrr_test_12 +} + +ets_test_mixed() +{ + ets_set_mixed + ets_dwrr_test_01 + ets_dwrr_test_12 +} + +ets_test_dwrr() +{ + ets_set_dwrr_uniform + ets_dwrr_test_012 + ets_set_dwrr_varying + ets_dwrr_test_012 + ets_change_quantum + ets_dwrr_test_012 + ets_set_dwrr_two_bands + ets_dwrr_test_01 +} diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index c08f4db8330d..93208caacbe6 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -74,7 +74,14 @@ struct sock_args { int use_cmsg; const char *dev; int ifindex; + const char *password; + /* prefix for MD5 password */ + union { + struct sockaddr_in v4; + struct sockaddr_in6 v6; + } md5_prefix; + unsigned int prefix_len; /* expected addresses and device index for connection */ int expected_ifindex; @@ -200,20 +207,33 @@ static void log_address(const char *desc, struct sockaddr *sa) fflush(stdout); } -static int tcp_md5sig(int sd, void *addr, socklen_t alen, const char *password) +static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args) { - struct tcp_md5sig md5sig; - int keylen = password ? strlen(password) : 0; + int keylen = strlen(args->password); + struct tcp_md5sig md5sig = {}; + int opt = TCP_MD5SIG; int rc; - memset(&md5sig, 0, sizeof(md5sig)); - memcpy(&md5sig.tcpm_addr, addr, alen); md5sig.tcpm_keylen = keylen; + memcpy(md5sig.tcpm_key, args->password, keylen); + + if (args->prefix_len) { + opt = TCP_MD5SIG_EXT; + md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_PREFIX; + + md5sig.tcpm_prefixlen = args->prefix_len; + addr = &args->md5_prefix; + } + memcpy(&md5sig.tcpm_addr, addr, alen); + + if (args->ifindex) { + opt = TCP_MD5SIG_EXT; + md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_IFINDEX; - if (keylen) - memcpy(md5sig.tcpm_key, password, keylen); + md5sig.tcpm_ifindex = args->ifindex; + } - rc = setsockopt(sd, IPPROTO_TCP, TCP_MD5SIG, &md5sig, sizeof(md5sig)); + rc = setsockopt(sd, IPPROTO_TCP, opt, &md5sig, sizeof(md5sig)); if (rc < 0) { /* ENOENT is harmless. Returned when a password is cleared */ if (errno == ENOENT) @@ -254,7 +274,7 @@ static int tcp_md5_remote(int sd, struct sock_args *args) exit(1); } - if (tcp_md5sig(sd, addr, alen, args->password)) + if (tcp_md5sig(sd, addr, alen, args)) return -1; return 0; @@ -1194,7 +1214,7 @@ static int do_server(struct sock_args *args) if (args->password && tcp_md5_remote(lsd, args)) { close(lsd); - return -1; + return 1; } while (1) { @@ -1313,7 +1333,7 @@ static int connectsock(void *addr, socklen_t alen, struct sock_args *args) if (args->type != SOCK_STREAM) goto out; - if (args->password && tcp_md5sig(sd, addr, alen, args->password)) + if (args->password && tcp_md5sig(sd, addr, alen, args)) goto err; if (args->bind_test_only) @@ -1405,16 +1425,18 @@ enum addr_type { ADDR_TYPE_MCAST, ADDR_TYPE_EXPECTED_LOCAL, ADDR_TYPE_EXPECTED_REMOTE, + ADDR_TYPE_MD5_PREFIX, }; static int convert_addr(struct sock_args *args, const char *_str, enum addr_type atype) { + int pfx_len_max = args->version == AF_INET6 ? 128 : 32; int family = args->version; + char *str, *dev, *sep; struct in6_addr *in6; struct in_addr *in; const char *desc; - char *str, *dev; void *addr; int rc = 0; @@ -1443,6 +1465,30 @@ static int convert_addr(struct sock_args *args, const char *_str, desc = "expected remote"; addr = &args->expected_raddr; break; + case ADDR_TYPE_MD5_PREFIX: + desc = "md5 prefix"; + if (family == AF_INET) { + args->md5_prefix.v4.sin_family = AF_INET; + addr = &args->md5_prefix.v4.sin_addr; + } else if (family == AF_INET6) { + args->md5_prefix.v6.sin6_family = AF_INET6; + addr = &args->md5_prefix.v6.sin6_addr; + } else + return 1; + + sep = strchr(str, '/'); + if (sep) { + *sep = '\0'; + sep++; + if (str_to_uint(sep, 1, pfx_len_max, + &args->prefix_len) != 0) { + fprintf(stderr, "Invalid port\n"); + return 1; + } + } else { + args->prefix_len = pfx_len_max; + } + break; default: log_error("unknown address type"); exit(1); @@ -1522,7 +1568,7 @@ static char *random_msg(int len) return m; } -#define GETOPT_STR "sr:l:p:t:g:P:DRn:M:d:SCi6L:0:1:2:Fbq" +#define GETOPT_STR "sr:l:p:t:g:P:DRn:M:m:d:SCi6L:0:1:2:Fbq" static void print_usage(char *prog) { @@ -1551,6 +1597,7 @@ static void print_usage(char *prog) " -n num number of times to send message\n" "\n" " -M password use MD5 sum protection\n" + " -m prefix/len prefix and length to use for MD5 key\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" "\n" @@ -1642,6 +1689,10 @@ int main(int argc, char *argv[]) case 'M': args.password = optarg; break; + case 'm': + if (convert_addr(&args, optarg, ADDR_TYPE_MD5_PREFIX) < 0) + return 1; + break; case 'S': args.use_setsockopt = 1; break; @@ -1706,11 +1757,16 @@ int main(int argc, char *argv[]) } if (args.password && - (!args.has_remote_ip || args.type != SOCK_STREAM)) { + ((!args.has_remote_ip && !args.prefix_len) || args.type != SOCK_STREAM)) { log_error("MD5 passwords apply to TCP only and require a remote ip for the password\n"); return 1; } + if (args.prefix_len && !args.password) { + log_error("Prefix range for MD5 protection specified without a password\n"); + return 1; + } + if ((args.use_setsockopt || args.use_cmsg) && !args.ifindex) { fprintf(stderr, "Device binding not specified\n"); return 1; diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 34df4c8882af..383bac05ac32 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -12,7 +12,11 @@ #include <arpa/inet.h> #include <error.h> #include <errno.h> +#include <inttypes.h> #include <linux/net_tstamp.h> +#include <linux/errqueue.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> #include <stdbool.h> #include <stdlib.h> #include <stdio.h> @@ -28,7 +32,7 @@ static int cfg_clockid = CLOCK_TAI; static bool cfg_do_ipv4; static bool cfg_do_ipv6; static uint16_t cfg_port = 8000; -static int cfg_variance_us = 2000; +static int cfg_variance_us = 4000; static uint64_t glob_tstart; @@ -43,6 +47,9 @@ static struct timed_send cfg_in[MAX_NUM_PKT]; static struct timed_send cfg_out[MAX_NUM_PKT]; static int cfg_num_pkt; +static int cfg_errq_level; +static int cfg_errq_type; + static uint64_t gettime_ns(void) { struct timespec ts; @@ -90,13 +97,15 @@ static void do_send_one(int fdt, struct timed_send *ts) } -static void do_recv_one(int fdr, struct timed_send *ts) +static bool do_recv_one(int fdr, struct timed_send *ts) { int64_t tstop, texpect; char rbuf[2]; int ret; ret = recv(fdr, rbuf, sizeof(rbuf), 0); + if (ret == -1 && errno == EAGAIN) + return true; if (ret == -1) error(1, errno, "read"); if (ret != 1) @@ -113,6 +122,8 @@ static void do_recv_one(int fdr, struct timed_send *ts) if (labs(tstop - texpect) > cfg_variance_us) error(1, 0, "exceeds variance (%d us)", cfg_variance_us); + + return false; } static void do_recv_verify_empty(int fdr) @@ -125,12 +136,70 @@ static void do_recv_verify_empty(int fdr) error(1, 0, "recv: not empty as expected (%d, %d)", ret, errno); } +static void do_recv_errqueue_timeout(int fdt) +{ + char control[CMSG_SPACE(sizeof(struct sock_extended_err)) + + CMSG_SPACE(sizeof(struct sockaddr_in6))] = {0}; + char data[sizeof(struct ipv6hdr) + + sizeof(struct tcphdr) + 1]; + struct sock_extended_err *err; + struct msghdr msg = {0}; + struct iovec iov = {0}; + struct cmsghdr *cm; + int64_t tstamp = 0; + int ret; + + iov.iov_base = data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + while (1) { + ret = recvmsg(fdt, &msg, MSG_ERRQUEUE); + if (ret == -1 && errno == EAGAIN) + break; + if (ret == -1) + error(1, errno, "errqueue"); + if (msg.msg_flags != MSG_ERRQUEUE) + error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags); + + cm = CMSG_FIRSTHDR(&msg); + if (cm->cmsg_level != cfg_errq_level || + cm->cmsg_type != cfg_errq_type) + error(1, 0, "errqueue: type 0x%x.0x%x\n", + cm->cmsg_level, cm->cmsg_type); + + err = (struct sock_extended_err *)CMSG_DATA(cm); + if (err->ee_origin != SO_EE_ORIGIN_TXTIME) + error(1, 0, "errqueue: origin 0x%x\n", err->ee_origin); + if (err->ee_code != ECANCELED) + error(1, 0, "errqueue: code 0x%x\n", err->ee_code); + + tstamp = ((int64_t) err->ee_data) << 32 | err->ee_info; + tstamp -= (int64_t) glob_tstart; + tstamp /= 1000 * 1000; + fprintf(stderr, "send: pkt %c at %" PRId64 "ms dropped\n", + data[ret - 1], tstamp); + + msg.msg_flags = 0; + msg.msg_controllen = sizeof(control); + } + + error(1, 0, "recv: timeout"); +} + static void setsockopt_txtime(int fd) { struct sock_txtime so_txtime_val = { .clockid = cfg_clockid }; struct sock_txtime so_txtime_val_read = { 0 }; socklen_t vallen = sizeof(so_txtime_val); + so_txtime_val.flags = SOF_TXTIME_REPORT_ERRORS; + if (setsockopt(fd, SOL_SOCKET, SO_TXTIME, &so_txtime_val, sizeof(so_txtime_val))) error(1, errno, "setsockopt txtime"); @@ -194,7 +263,8 @@ static void do_test(struct sockaddr *addr, socklen_t alen) for (i = 0; i < cfg_num_pkt; i++) do_send_one(fdt, &cfg_in[i]); for (i = 0; i < cfg_num_pkt; i++) - do_recv_one(fdr, &cfg_out[i]); + if (do_recv_one(fdr, &cfg_out[i])) + do_recv_errqueue_timeout(fdt); do_recv_verify_empty(fdr); @@ -280,6 +350,10 @@ int main(int argc, char **argv) addr6.sin6_family = AF_INET6; addr6.sin6_port = htons(cfg_port); addr6.sin6_addr = in6addr_loopback; + + cfg_errq_level = SOL_IPV6; + cfg_errq_type = IPV6_RECVERR; + do_test((void *)&addr6, sizeof(addr6)); } @@ -289,6 +363,10 @@ int main(int argc, char **argv) addr4.sin_family = AF_INET; addr4.sin_port = htons(cfg_port); addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + + cfg_errq_level = SOL_IP; + cfg_errq_type = IP_RECVERR; + do_test((void *)&addr4, sizeof(addr4)); } diff --git a/tools/testing/selftests/net/so_txtime.sh b/tools/testing/selftests/net/so_txtime.sh index 5aa519328a5b..3f7800eaecb1 100755 --- a/tools/testing/selftests/net/so_txtime.sh +++ b/tools/testing/selftests/net/so_txtime.sh @@ -5,7 +5,12 @@ # Run in network namespace if [[ $# -eq 0 ]]; then - ./in_netns.sh $0 __subprocess + if ! ./in_netns.sh $0 __subprocess; then + # test is time sensitive, can be flaky + echo "test failed: retry once" + ./in_netns.sh $0 __subprocess + fi + exit $? fi @@ -18,7 +23,7 @@ tc qdisc add dev lo root fq ./so_txtime -4 -6 -c mono a,10,b,20 a,10,b,20 ./so_txtime -4 -6 -c mono a,20,b,10 b,20,a,20 -if tc qdisc replace dev lo root etf clockid CLOCK_TAI delta 200000; then +if tc qdisc replace dev lo root etf clockid CLOCK_TAI delta 400000; then ! ./so_txtime -4 -6 -c tai a,-1 a,-1 ! ./so_txtime -4 -6 -c tai a,0 a,0 ./so_txtime -4 -6 -c tai a,10 a,10 diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json new file mode 100644 index 000000000000..180593010675 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/ets.json @@ -0,0 +1,940 @@ +[ + { + "id": "e90e", + "name": "Add ETS qdisc using bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 2", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "b059", + "name": "Add ETS qdisc using quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 900 800 700", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 4 quanta 1000 900 800 700", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e8e7", + "name": "Add ETS qdisc using strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 3", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "233c", + "name": "Add ETS qdisc using bands + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 quanta 1000 900 800 700", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 4 quanta 1000 900 800 700 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "3d35", + "name": "Add ETS qdisc using bands + strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 3", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 3 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7f3b", + "name": "Add ETS qdisc using strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3 quanta 1500 750", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 5 strict 3 quanta 1500 750 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "4593", + "name": "Add ETS qdisc using strict 0 + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 0 quanta 1500 750", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 2 quanta 1500 750 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "8938", + "name": "Add ETS qdisc using bands + strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 strict 3 quanta 1500 750", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 5 .*strict 3 quanta 1500 750 priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "0782", + "name": "Add ETS qdisc with more bands than quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 quanta 1000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 2 .*quanta 1000 [1-9][0-9]* priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "501b", + "name": "Add ETS qdisc with more bands than strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 1 quanta ([1-9][0-9]* ){2}priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "671a", + "name": "Add ETS qdisc with more bands than strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 3 strict 1 quanta 1000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 3 strict 1 quanta 1000 [1-9][0-9]* priomap", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "2a23", + "name": "Add ETS qdisc with 16 bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 16", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 16", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "8daf", + "name": "Add ETS qdisc with 17 bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 17", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7f95", + "name": "Add ETS qdisc with 17 strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 17", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "837a", + "name": "Add ETS qdisc with 16 quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 16", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "65b6", + "name": "Add ETS qdisc with 17 quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "b9e9", + "name": "Add ETS qdisc with 16 strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 8 quanta 1 2 3 4 5 6 7 8", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .* bands 16", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "9877", + "name": "Add ETS qdisc with 17 strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 9 quanta 1 2 3 4 5 6 7 8", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "c696", + "name": "Add ETS qdisc with priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "30c4", + "name": "Add ETS qdisc with quanta + priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000 4000 5000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*quanta 1000 2000 3000 4000 5000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e8ac", + "name": "Add ETS qdisc with strict + priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*bands 5 strict 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "5a7e", + "name": "Add ETS qdisc with quanta + strict + priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 2 quanta 1000 2000 3000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*strict 2 quanta 1000 2000 3000 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "cb8b", + "name": "Show ETS class :1", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:1", + "matchPattern": "class ets 1:1 root quantum 4000", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "1b4e", + "name": "Show ETS class :2", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:2", + "matchPattern": "class ets 1:2 root quantum 3000", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "f642", + "name": "Show ETS class :3", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 4000 3000 2000", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:3", + "matchPattern": "class ets 1:3 root quantum 2000", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "0a5f", + "name": "Show ETS strict class", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 3", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY classid 1:1", + "matchPattern": "class ets 1:1 root $", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root", + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "f7c8", + "name": "Add ETS qdisc with too many quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 quanta 1000 2000 3000", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "2389", + "name": "Add ETS qdisc with too many strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 strict 3", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "fe3c", + "name": "Add ETS qdisc with too many strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 2 quanta 1000 2000 3000", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "cb04", + "name": "Add ETS qdisc with excess priomap elements", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 5 priomap 0 0 1 0 1 2 0 1 2 3 0 1 2 3 4 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "c32e", + "name": "Add ETS qdisc with priomap above bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 priomap 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "744c", + "name": "Add ETS qdisc with priomap above quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 500 priomap 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "7b33", + "name": "Add ETS qdisc with priomap above strict", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 2 priomap 0 1 2", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "dbe6", + "name": "Add ETS qdisc with priomap above strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets strict 1 quanta 1000 500 priomap 0 1 2 3", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "bdb2", + "name": "Add ETS qdisc with priomap within bands with strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 1 quanta 1000 500 priomap 0 1 2 3", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "39a3", + "name": "Add ETS qdisc with priomap above bands with strict + quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 strict 1 quanta 1000 500 priomap 0 1 2 3 4", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "557c", + "name": "Unset priorities default to the last band", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4 priomap 0 0 0 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*priomap 0 0 0 0 3 3 3 3 3 3 3 3 3 3 3 3", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "a347", + "name": "Unset priorities default to the last band -- no priomap", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 4", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*priomap 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "39c4", + "name": "Add ETS qdisc with too few bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 0", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "930b", + "name": "Add ETS qdisc with too many bands", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets bands 17", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "406a", + "name": "Add ETS qdisc without parameters", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e51a", + "name": "Zero element in quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 0 800 700", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "e7f2", + "name": "Sole zero element in quanta", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta 0", + "expExitCode": "1", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "d6e6", + "name": "No values after the quanta keyword", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root ets quanta", + "expExitCode": "255", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets", + "matchCount": "0", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "28c6", + "name": "Change ETS band quantum", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:1 ets quantum 1500", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*quanta 1500 2000 3000 priomap ", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "4714", + "name": "Change ETS band without quantum", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets quanta 1000 2000 3000" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:1 ets", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets 1: root .*quanta 1000 2000 3000 priomap ", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "6979", + "name": "Change quantum of a strict ETS band", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets strict 5" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:2 ets quantum 1500", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*bands 5 .*strict 5", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + }, + { + "id": "9a7d", + "name": "Change ETS strict band without quantum", + "category": [ + "qdisc", + "ets" + ], + "setup": [ + "$IP link add dev $DUMMY type dummy || /bin/true", + "$TC qdisc add dev $DUMMY handle 1: root ets strict 5" + ], + "cmdUnderTest": "$TC class change dev $DUMMY classid 1:2 ets", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc ets .*bands 5 .*strict 5", + "matchCount": "1", + "teardown": [ + "$IP link del dev $DUMMY type dummy" + ] + } +] diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh new file mode 100755 index 000000000000..d5c85c7494f2 --- /dev/null +++ b/tools/testing/selftests/wireguard/netns.sh @@ -0,0 +1,534 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. +# +# This script tests the below topology: +# +# ┌─────────────────────┐ ┌──────────────────────────────────┐ ┌─────────────────────┐ +# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │ +# │ │ │ │ │ │ +# │┌────────┐ │ │ ┌────────┐ │ │ ┌────────┐│ +# ││ wg0 │───────────┼───┼────────────│ lo │────────────┼───┼───────────│ wg0 ││ +# │├────────┴──────────┐│ │ ┌───────┴────────┴────────┐ │ │┌──────────┴────────┤│ +# ││192.168.241.1/24 ││ │ │(ns1) (ns2) │ │ ││192.168.241.2/24 ││ +# ││fd00::1/24 ││ │ │127.0.0.1:1 127.0.0.1:2│ │ ││fd00::2/24 ││ +# │└───────────────────┘│ │ │[::]:1 [::]:2 │ │ │└───────────────────┘│ +# └─────────────────────┘ │ └─────────────────────────┘ │ └─────────────────────┘ +# └──────────────────────────────────┘ +# +# After the topology is prepared we run a series of TCP/UDP iperf3 tests between the +# wireguard peers in $ns1 and $ns2. Note that $ns0 is the endpoint for the wg0 +# interfaces in $ns1 and $ns2. See https://www.wireguard.com/netns/ for further +# details on how this is accomplished. +set -e + +exec 3>&1 +export WG_HIDE_KEYS=never +netns0="wg-test-$$-0" +netns1="wg-test-$$-1" +netns2="wg-test-$$-2" +pretty() { echo -e "\x1b[32m\x1b[1m[+] ${1:+NS$1: }${2}\x1b[0m" >&3; } +pp() { pretty "" "$*"; "$@"; } +maybe_exec() { if [[ $BASHPID -eq $$ ]]; then "$@"; else exec "$@"; fi; } +n0() { pretty 0 "$*"; maybe_exec ip netns exec $netns0 "$@"; } +n1() { pretty 1 "$*"; maybe_exec ip netns exec $netns1 "$@"; } +n2() { pretty 2 "$*"; maybe_exec ip netns exec $netns2 "$@"; } +ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; } +ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; } +ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; } +sleep() { read -t "$1" -N 1 || true; } +waitiperf() { pretty "${1//*-}" "wait for iperf:5201"; while [[ $(ss -N "$1" -tlp 'sport = 5201') != *iperf3* ]]; do sleep 0.1; done; } +waitncatudp() { pretty "${1//*-}" "wait for udp:1111"; while [[ $(ss -N "$1" -ulp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } +waitncattcp() { pretty "${1//*-}" "wait for tcp:1111"; while [[ $(ss -N "$1" -tlp 'sport = 1111') != *ncat* ]]; do sleep 0.1; done; } +waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } + +cleanup() { + set +e + exec 2>/dev/null + printf "$orig_message_cost" > /proc/sys/net/core/message_cost + ip0 link del dev wg0 + ip1 link del dev wg0 + ip2 link del dev wg0 + local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)" + [[ -n $to_kill ]] && kill $to_kill + pp ip netns del $netns1 + pp ip netns del $netns2 + pp ip netns del $netns0 + exit +} + +orig_message_cost="$(< /proc/sys/net/core/message_cost)" +trap cleanup EXIT +printf 0 > /proc/sys/net/core/message_cost + +ip netns del $netns0 2>/dev/null || true +ip netns del $netns1 2>/dev/null || true +ip netns del $netns2 2>/dev/null || true +pp ip netns add $netns0 +pp ip netns add $netns1 +pp ip netns add $netns2 +ip0 link set up dev lo + +ip0 link add dev wg0 type wireguard +ip0 link set wg0 netns $netns1 +ip0 link add dev wg0 type wireguard +ip0 link set wg0 netns $netns2 +key1="$(pp wg genkey)" +key2="$(pp wg genkey)" +key3="$(pp wg genkey)" +pub1="$(pp wg pubkey <<<"$key1")" +pub2="$(pp wg pubkey <<<"$key2")" +pub3="$(pp wg pubkey <<<"$key3")" +psk="$(pp wg genpsk)" +[[ -n $key1 && -n $key2 && -n $psk ]] + +configure_peers() { + ip1 addr add 192.168.241.1/24 dev wg0 + ip1 addr add fd00::1/24 dev wg0 + + ip2 addr add 192.168.241.2/24 dev wg0 + ip2 addr add fd00::2/24 dev wg0 + + n1 wg set wg0 \ + private-key <(echo "$key1") \ + listen-port 1 \ + peer "$pub2" \ + preshared-key <(echo "$psk") \ + allowed-ips 192.168.241.2/32,fd00::2/128 + n2 wg set wg0 \ + private-key <(echo "$key2") \ + listen-port 2 \ + peer "$pub1" \ + preshared-key <(echo "$psk") \ + allowed-ips 192.168.241.1/32,fd00::1/128 + + ip1 link set up dev wg0 + ip2 link set up dev wg0 +} +configure_peers + +tests() { + # Ping over IPv4 + n2 ping -c 10 -f -W 1 192.168.241.1 + n1 ping -c 10 -f -W 1 192.168.241.2 + + # Ping over IPv6 + n2 ping6 -c 10 -f -W 1 fd00::1 + n1 ping6 -c 10 -f -W 1 fd00::2 + + # TCP over IPv4 + n2 iperf3 -s -1 -B 192.168.241.2 & + waitiperf $netns2 + n1 iperf3 -Z -t 3 -c 192.168.241.2 + + # TCP over IPv6 + n1 iperf3 -s -1 -B fd00::1 & + waitiperf $netns1 + n2 iperf3 -Z -t 3 -c fd00::1 + + # UDP over IPv4 + n1 iperf3 -s -1 -B 192.168.241.1 & + waitiperf $netns1 + n2 iperf3 -Z -t 3 -b 0 -u -c 192.168.241.1 + + # UDP over IPv6 + n2 iperf3 -s -1 -B fd00::2 & + waitiperf $netns2 + n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2 +} + +[[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}" +big_mtu=$(( 34816 - 1500 + $orig_mtu )) + +# Test using IPv4 as outer transport +n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 +n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 +# Before calling tests, we first make sure that the stats counters and timestamper are working +n2 ping -c 10 -f -W 1 192.168.241.1 +{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip2 -stats link show dev wg0) +(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) )) +{ read _; read _; read _; read rx_bytes _; read _; read tx_bytes _; } < <(ip1 -stats link show dev wg0) +(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) )) +read _ rx_bytes tx_bytes < <(n2 wg show wg0 transfer) +(( rx_bytes == 1372 && (tx_bytes == 1428 || tx_bytes == 1460) )) +read _ rx_bytes tx_bytes < <(n1 wg show wg0 transfer) +(( tx_bytes == 1372 && (rx_bytes == 1428 || rx_bytes == 1460) )) +read _ timestamp < <(n1 wg show wg0 latest-handshakes) +(( timestamp != 0 )) + +tests +ip1 link set wg0 mtu $big_mtu +ip2 link set wg0 mtu $big_mtu +tests + +ip1 link set wg0 mtu $orig_mtu +ip2 link set wg0 mtu $orig_mtu + +# Test using IPv6 as outer transport +n1 wg set wg0 peer "$pub2" endpoint [::1]:2 +n2 wg set wg0 peer "$pub1" endpoint [::1]:1 +tests +ip1 link set wg0 mtu $big_mtu +ip2 link set wg0 mtu $big_mtu +tests + +# Test that route MTUs work with the padding +ip1 link set wg0 mtu 1300 +ip2 link set wg0 mtu 1300 +n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 +n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 +n0 iptables -A INPUT -m length --length 1360 -j DROP +n1 ip route add 192.168.241.2/32 dev wg0 mtu 1299 +n2 ip route add 192.168.241.1/32 dev wg0 mtu 1299 +n2 ping -c 1 -W 1 -s 1269 192.168.241.1 +n2 ip route delete 192.168.241.1/32 dev wg0 mtu 1299 +n1 ip route delete 192.168.241.2/32 dev wg0 mtu 1299 +n0 iptables -F INPUT + +ip1 link set wg0 mtu $orig_mtu +ip2 link set wg0 mtu $orig_mtu + +# Test using IPv4 that roaming works +ip0 -4 addr del 127.0.0.1/8 dev lo +ip0 -4 addr add 127.212.121.99/8 dev lo +n1 wg set wg0 listen-port 9999 +n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 +n1 ping6 -W 1 -c 1 fd00::2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 127.212.121.99:9999" ]] + +# Test using IPv6 that roaming works +n1 wg set wg0 listen-port 9998 +n1 wg set wg0 peer "$pub2" endpoint [::1]:2 +n1 ping -W 1 -c 1 192.168.241.2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 [::1]:9998" ]] + +# Test that crypto-RP filter works +n1 wg set wg0 peer "$pub2" allowed-ips 192.168.241.0/24 +exec 4< <(n1 ncat -l -u -p 1111) +ncat_pid=$! +waitncatudp $netns1 +n2 ncat -u 192.168.241.1 1111 <<<"X" +read -r -N 1 -t 1 out <&4 && [[ $out == "X" ]] +kill $ncat_pid +more_specific_key="$(pp wg genkey | pp wg pubkey)" +n1 wg set wg0 peer "$more_specific_key" allowed-ips 192.168.241.2/32 +n2 wg set wg0 listen-port 9997 +exec 4< <(n1 ncat -l -u -p 1111) +ncat_pid=$! +waitncatudp $netns1 +n2 ncat -u 192.168.241.1 1111 <<<"X" +! read -r -N 1 -t 1 out <&4 || false +kill $ncat_pid +n1 wg set wg0 peer "$more_specific_key" remove +[[ $(n1 wg show wg0 endpoints) == "$pub2 [::1]:9997" ]] + +# Test that we can change private keys keys and immediately handshake +n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips 192.168.241.2/32 endpoint 127.0.0.1:2 +n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 +n1 ping -W 1 -c 1 192.168.241.2 +n1 wg set wg0 private-key <(echo "$key3") +n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove +n1 ping -W 1 -c 1 192.168.241.2 + +ip1 link del wg0 +ip2 link del wg0 + +# Test using NAT. We now change the topology to this: +# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐ +# │ $ns1 namespace │ │ $ns0 namespace │ │ $ns2 namespace │ +# │ │ │ │ │ │ +# │ ┌─────┐ ┌─────┐ │ │ ┌──────┐ ┌──────┐ │ │ ┌─────┐ ┌─────┐ │ +# │ │ wg0 │─────────────│vethc│───────────┼────┼────│vethrc│ │vethrs│──────────────┼─────┼──│veths│────────────│ wg0 │ │ +# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├──────┴─────────┐ ├──────┴────────────┐ │ │ ├─────┴──────────┐ ├─────┴──────────┐ │ +# │ │192.168.241.1/24│ │192.168.1.100/24││ │ │192.168.1.1/24 │ │10.0.0.1/24 │ │ │ │10.0.0.100/24 │ │192.168.241.2/24│ │ +# │ │fd00::1/24 │ │ ││ │ │ │ │SNAT:192.168.1.0/24│ │ │ │ │ │fd00::2/24 │ │ +# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └───────────────────┘ │ │ └────────────────┘ └────────────────┘ │ +# └────────────────────────────────────────┘ └────────────────────────────────────────────────┘ └────────────────────────────────────────┘ + +ip1 link add dev wg0 type wireguard +ip2 link add dev wg0 type wireguard +configure_peers + +ip0 link add vethrc type veth peer name vethc +ip0 link add vethrs type veth peer name veths +ip0 link set vethc netns $netns1 +ip0 link set veths netns $netns2 +ip0 link set vethrc up +ip0 link set vethrs up +ip0 addr add 192.168.1.1/24 dev vethrc +ip0 addr add 10.0.0.1/24 dev vethrs +ip1 addr add 192.168.1.100/24 dev vethc +ip1 link set vethc up +ip1 route add default via 192.168.1.1 +ip2 addr add 10.0.0.100/24 dev veths +ip2 link set veths up +waitiface $netns0 vethrc +waitiface $netns0 vethrs +waitiface $netns1 vethc +waitiface $netns2 veths + +n0 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' +n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout' +n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout_stream' +n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1 + +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.100:2 persistent-keepalive 1 +n1 ping -W 1 -c 1 192.168.241.2 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] +# Demonstrate n2 can still send packets to n1, since persistent-keepalive will prevent connection tracking entry from expiring (to see entries: `n0 conntrack -L`). +pp sleep 3 +n2 ping -W 1 -c 1 192.168.241.1 +n1 wg set wg0 peer "$pub2" persistent-keepalive 0 + +# Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs. +ip1 -6 addr add fc00::9/96 dev vethc +ip1 -6 route add default via fc00::1 +ip2 -4 addr add 192.168.99.7/32 dev wg0 +ip2 -6 addr add abab::1111/128 dev wg0 +n1 wg set wg0 fwmark 51820 peer "$pub2" allowed-ips 192.168.99.7,abab::1111 +ip1 -6 route add default dev wg0 table 51820 +ip1 -6 rule add not fwmark 51820 table 51820 +ip1 -6 rule add table main suppress_prefixlength 0 +ip1 -4 route add default dev wg0 table 51820 +ip1 -4 rule add not fwmark 51820 table 51820 +ip1 -4 rule add table main suppress_prefixlength 0 +# Flood the pings instead of sending just one, to trigger routing table reference counting bugs. +n1 ping -W 1 -c 100 -f 192.168.99.7 +n1 ping -W 1 -c 100 -f abab::1111 + +n0 iptables -t nat -F +ip0 link del vethrc +ip0 link del vethrs +ip1 link del wg0 +ip2 link del wg0 + +# Test that saddr routing is sticky but not too sticky, changing to this topology: +# ┌────────────────────────────────────────┐ ┌────────────────────────────────────────┐ +# │ $ns1 namespace │ │ $ns2 namespace │ +# │ │ │ │ +# │ ┌─────┐ ┌─────┐ │ │ ┌─────┐ ┌─────┐ │ +# │ │ wg0 │─────────────│veth1│───────────┼────┼──│veth2│────────────│ wg0 │ │ +# │ ├─────┴──────────┐ ├─────┴──────────┐│ │ ├─────┴──────────┐ ├─────┴──────────┐ │ +# │ │192.168.241.1/24│ │10.0.0.1/24 ││ │ │10.0.0.2/24 │ │192.168.241.2/24│ │ +# │ │fd00::1/24 │ │fd00:aa::1/96 ││ │ │fd00:aa::2/96 │ │fd00::2/24 │ │ +# │ └────────────────┘ └────────────────┘│ │ └────────────────┘ └────────────────┘ │ +# └────────────────────────────────────────┘ └────────────────────────────────────────┘ + +ip1 link add dev wg0 type wireguard +ip2 link add dev wg0 type wireguard +configure_peers +ip1 link add veth1 type veth peer name veth2 +ip1 link set veth2 netns $netns2 +n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad' +n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/all/accept_dad' +n1 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth1/accept_dad' +n2 bash -c 'printf 0 > /proc/sys/net/ipv6/conf/veth2/accept_dad' +n1 bash -c 'printf 1 > /proc/sys/net/ipv4/conf/veth1/promote_secondaries' + +# First we check that we aren't overly sticky and can fall over to new IPs when old ones are removed +ip1 addr add 10.0.0.1/24 dev veth1 +ip1 addr add fd00:aa::1/96 dev veth1 +ip2 addr add 10.0.0.2/24 dev veth2 +ip2 addr add fd00:aa::2/96 dev veth2 +ip1 link set veth1 up +ip2 link set veth2 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2 +n1 ping -W 1 -c 1 192.168.241.2 +ip1 addr add 10.0.0.10/24 dev veth1 +ip1 addr del 10.0.0.1/24 dev veth1 +n1 ping -W 1 -c 1 192.168.241.2 +n1 wg set wg0 peer "$pub2" endpoint [fd00:aa::2]:2 +n1 ping -W 1 -c 1 192.168.241.2 +ip1 addr add fd00:aa::10/96 dev veth1 +ip1 addr del fd00:aa::1/96 dev veth1 +n1 ping -W 1 -c 1 192.168.241.2 + +# Now we show that we can successfully do reply to sender routing +ip1 link set veth1 down +ip2 link set veth2 down +ip1 addr flush dev veth1 +ip2 addr flush dev veth2 +ip1 addr add 10.0.0.1/24 dev veth1 +ip1 addr add 10.0.0.2/24 dev veth1 +ip1 addr add fd00:aa::1/96 dev veth1 +ip1 addr add fd00:aa::2/96 dev veth1 +ip2 addr add 10.0.0.3/24 dev veth2 +ip2 addr add fd00:aa::3/96 dev veth2 +ip1 link set veth1 up +ip2 link set veth2 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +n2 wg set wg0 peer "$pub1" endpoint 10.0.0.1:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] +n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::1]:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::1]:1" ]] +n2 wg set wg0 peer "$pub1" endpoint 10.0.0.2:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.2:1" ]] +n2 wg set wg0 peer "$pub1" endpoint [fd00:aa::2]:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 [fd00:aa::2]:1" ]] + +# What happens if the inbound destination address belongs to a different interface as the default route? +ip1 link add dummy0 type dummy +ip1 addr add 10.50.0.1/24 dev dummy0 +ip1 link set dummy0 up +ip2 route add 10.50.0.0/24 dev veth2 +n2 wg set wg0 peer "$pub1" endpoint 10.50.0.1:1 +n2 ping -W 1 -c 1 192.168.241.1 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.50.0.1:1" ]] + +ip1 link del dummy0 +ip1 addr flush dev veth1 +ip2 addr flush dev veth2 +ip1 route flush dev veth1 +ip2 route flush dev veth2 + +# Now we see what happens if another interface route takes precedence over an ongoing one +ip1 link add veth3 type veth peer name veth4 +ip1 link set veth4 netns $netns2 +ip1 addr add 10.0.0.1/24 dev veth1 +ip2 addr add 10.0.0.2/24 dev veth2 +ip1 addr add 10.0.0.3/24 dev veth3 +ip1 link set veth1 up +ip2 link set veth2 up +ip1 link set veth3 up +ip2 link set veth4 up +waitiface $netns1 veth1 +waitiface $netns2 veth2 +waitiface $netns1 veth3 +waitiface $netns2 veth4 +ip1 route flush dev veth1 +ip1 route flush dev veth3 +ip1 route add 10.0.0.0/24 dev veth1 src 10.0.0.1 metric 2 +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.2:2 +n1 ping -W 1 -c 1 192.168.241.2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.1:1" ]] +ip1 route add 10.0.0.0/24 dev veth3 src 10.0.0.3 metric 1 +n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth1/rp_filter' +n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/veth4/rp_filter' +n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' +n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' +n1 ping -W 1 -c 1 192.168.241.2 +[[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.3:1" ]] + +ip1 link del veth1 +ip1 link del veth3 +ip1 link del wg0 +ip2 link del wg0 + +# We test that Netlink/IPC is working properly by doing things that usually cause split responses +ip0 link add dev wg0 type wireguard +config=( "[Interface]" "PrivateKey=$(wg genkey)" "[Peer]" "PublicKey=$(wg genkey)" ) +for a in {1..255}; do + for b in {0..255}; do + config+=( "AllowedIPs=$a.$b.0.0/16,$a::$b/128" ) + done +done +n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") +i=0 +for ip in $(n0 wg show wg0 allowed-ips); do + ((++i)) +done +((i == 255*256*2+1)) +ip0 link del wg0 +ip0 link add dev wg0 type wireguard +config=( "[Interface]" "PrivateKey=$(wg genkey)" ) +for a in {1..40}; do + config+=( "[Peer]" "PublicKey=$(wg genkey)" ) + for b in {1..52}; do + config+=( "AllowedIPs=$a.$b.0.0/16" ) + done +done +n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") +i=0 +while read -r line; do + j=0 + for ip in $line; do + ((++j)) + done + ((j == 53)) + ((++i)) +done < <(n0 wg show wg0 allowed-ips) +((i == 40)) +ip0 link del wg0 +ip0 link add wg0 type wireguard +config=( ) +for i in {1..29}; do + config+=( "[Peer]" "PublicKey=$(wg genkey)" ) +done +config+=( "[Peer]" "PublicKey=$(wg genkey)" "AllowedIPs=255.2.3.4/32,abcd::255/128" ) +n0 wg setconf wg0 <(printf '%s\n' "${config[@]}") +n0 wg showconf wg0 > /dev/null +ip0 link del wg0 + +allowedips=( ) +for i in {1..197}; do + allowedips+=( abcd::$i ) +done +saved_ifs="$IFS" +IFS=, +allowedips="${allowedips[*]}" +IFS="$saved_ifs" +ip0 link add wg0 type wireguard +n0 wg set wg0 peer "$pub1" +n0 wg set wg0 peer "$pub2" allowed-ips "$allowedips" +{ + read -r pub allowedips + [[ $pub == "$pub1" && $allowedips == "(none)" ]] + read -r pub allowedips + [[ $pub == "$pub2" ]] + i=0 + for _ in $allowedips; do + ((++i)) + done + ((i == 197)) +} < <(n0 wg show wg0 allowed-ips) +ip0 link del wg0 + +! n0 wg show doesnotexist || false + +ip0 link add wg0 type wireguard +n0 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") +[[ $(n0 wg show wg0 private-key) == "$key1" ]] +[[ $(n0 wg show wg0 preshared-keys) == "$pub2 $psk" ]] +n0 wg set wg0 private-key /dev/null peer "$pub2" preshared-key /dev/null +[[ $(n0 wg show wg0 private-key) == "(none)" ]] +[[ $(n0 wg show wg0 preshared-keys) == "$pub2 (none)" ]] +n0 wg set wg0 peer "$pub2" +n0 wg set wg0 private-key <(echo "$key2") +[[ $(n0 wg show wg0 public-key) == "$pub2" ]] +[[ -z $(n0 wg show wg0 peers) ]] +n0 wg set wg0 peer "$pub2" +[[ -z $(n0 wg show wg0 peers) ]] +n0 wg set wg0 private-key <(echo "$key1") +n0 wg set wg0 peer "$pub2" +[[ $(n0 wg show wg0 peers) == "$pub2" ]] +n0 wg set wg0 private-key <(echo "/${key1:1}") +[[ $(n0 wg show wg0 private-key) == "+${key1:1}" ]] +n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0,10.0.0.0/8,100.0.0.0/10,172.16.0.0/12,192.168.0.0/16 +n0 wg set wg0 peer "$pub2" allowed-ips 0.0.0.0/0 +n0 wg set wg0 peer "$pub2" allowed-ips ::/0,1700::/111,5000::/4,e000::/37,9000::/75 +n0 wg set wg0 peer "$pub2" allowed-ips ::/0 +ip0 link del wg0 + +declare -A objects +while read -t 0.1 -r line 2>/dev/null || [[ $? -ne 142 ]]; do + [[ $line =~ .*(wg[0-9]+:\ [A-Z][a-z]+\ [0-9]+)\ .*(created|destroyed).* ]] || continue + objects["${BASH_REMATCH[1]}"]+="${BASH_REMATCH[2]}" +done < /dev/kmsg +alldeleted=1 +for object in "${!objects[@]}"; do + if [[ ${objects["$object"]} != *createddestroyed ]]; then + echo "Error: $object: merely ${objects["$object"]}" >&3 + alldeleted=0 + fi +done +[[ $alldeleted -eq 1 ]] +pretty "" "Objects that were created were also destroyed." diff --git a/tools/testing/selftests/wireguard/qemu/.gitignore b/tools/testing/selftests/wireguard/qemu/.gitignore new file mode 100644 index 000000000000..415b542a9d59 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/.gitignore @@ -0,0 +1,2 @@ +build/ +distfiles/ diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile new file mode 100644 index 000000000000..f10aa3590adc --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -0,0 +1,387 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + +PWD := $(shell pwd) + +CHOST := $(shell gcc -dumpmachine) +HOST_ARCH := $(firstword $(subst -, ,$(CHOST))) +ifneq (,$(ARCH)) +CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc)))))) +ifeq (,$(CBUILD)) +$(error The toolchain for $(ARCH) is not installed) +endif +else +CBUILD := $(CHOST) +ARCH := $(firstword $(subst -, ,$(CBUILD))) +endif + +# Set these from the environment to override +KERNEL_PATH ?= $(PWD)/../../../../.. +BUILD_PATH ?= $(PWD)/build/$(ARCH) +DISTFILES_PATH ?= $(PWD)/distfiles +NR_CPUS ?= 4 + +MIRROR := https://download.wireguard.com/qemu-test/distfiles/ + +default: qemu + +# variable name, tarball project name, version, tarball extension, default URI base +define tar_download = +$(1)_VERSION := $(3) +$(1)_NAME := $(2)-$$($(1)_VERSION) +$(1)_TAR := $(DISTFILES_PATH)/$$($(1)_NAME)$(4) +$(1)_PATH := $(BUILD_PATH)/$$($(1)_NAME) +$(call file_download,$$($(1)_NAME)$(4),$(5),$(6)) +endef + +define file_download = +$(DISTFILES_PATH)/$(1): + mkdir -p $(DISTFILES_PATH) + flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp' + if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi +endef + +$(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3)) +$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81)) +$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) +$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) +$(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae)) +$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) +$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) +$(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) +$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f)) + +KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) +rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) +WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*) + +export CFLAGS ?= -O3 -pipe +export LDFLAGS ?= +export CPPFLAGS := -I$(BUILD_PATH)/include + +ifeq ($(HOST_ARCH),$(ARCH)) +CROSS_COMPILE_FLAG := --host=$(CHOST) +CFLAGS += -march=native +STRIP := strip +else +$(info Cross compilation: building for $(CBUILD) using $(CHOST)) +CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST) +export CROSS_COMPILE=$(CBUILD)- +STRIP := $(CBUILD)-strip +endif +ifeq ($(ARCH),aarch64) +QEMU_ARCH := aarch64 +KERNEL_ARCH := arm64 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a53 -machine virt +CFLAGS += -march=armv8-a -mtune=cortex-a53 +endif +else ifeq ($(ARCH),aarch64_be) +QEMU_ARCH := aarch64 +KERNEL_ARCH := arm64 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a53 -machine virt +CFLAGS += -march=armv8-a -mtune=cortex-a53 +endif +else ifeq ($(ARCH),arm) +QEMU_ARCH := arm +KERNEL_ARCH := arm +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a15 -machine virt +CFLAGS += -march=armv7-a -mtune=cortex-a15 -mabi=aapcs-linux +endif +else ifeq ($(ARCH),armeb) +QEMU_ARCH := arm +KERNEL_ARCH := arm +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm +else +QEMU_MACHINE := -cpu cortex-a15 -machine virt +CFLAGS += -march=armv7-a -mabi=aapcs-linux # We don't pass -mtune=cortex-a15 due to a compiler bug on big endian. +LDFLAGS += -Wl,--be8 +endif +else ifeq ($(ARCH),x86_64) +QEMU_ARCH := x86_64 +KERNEL_ARCH := x86_64 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine q35,accel=kvm +else +QEMU_MACHINE := -cpu Skylake-Server -machine q35 +CFLAGS += -march=skylake-avx512 +endif +else ifeq ($(ARCH),i686) +QEMU_ARCH := i386 +KERNEL_ARCH := x86 +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage +ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH)) +QEMU_MACHINE := -cpu host -machine q35,accel=kvm +else +QEMU_MACHINE := -cpu coreduo -machine q35 +CFLAGS += -march=prescott +endif +else ifeq ($(ARCH),mips64) +QEMU_ARCH := mips64 +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EB +else +QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 +CFLAGS += -march=mips64r2 -EB +endif +else ifeq ($(ARCH),mips64el) +QEMU_ARCH := mips64el +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EL +else +QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1 +CFLAGS += -march=mips64r2 -EL +endif +else ifeq ($(ARCH),mips) +QEMU_ARCH := mips +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EB +else +QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 +CFLAGS += -march=mips32r2 -EB +endif +else ifeq ($(ARCH),mipsel) +QEMU_ARCH := mipsel +KERNEL_ARCH := mips +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host -machine malta,accel=kvm +CFLAGS += -EL +else +QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1 +CFLAGS += -march=mips32r2 -EL +endif +else ifeq ($(ARCH),powerpc64le) +QEMU_ARCH := ppc64 +KERNEL_ARCH := powerpc +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine pseries +else +QEMU_MACHINE := -machine pseries +endif +CFLAGS += -mcpu=powerpc64le -mlong-double-64 +else ifeq ($(ARCH),powerpc) +QEMU_ARCH := ppc +KERNEL_ARCH := powerpc +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500 +else +QEMU_MACHINE := -machine ppce500 +endif +CFLAGS += -mcpu=powerpc -mlong-double-64 -msecure-plt +else ifeq ($(ARCH),m68k) +QEMU_ARCH := m68k +KERNEL_ARCH := m68k +KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux +KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/m68k.config) +ifeq ($(HOST_ARCH),$(ARCH)) +QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -smp 1 -append $(KERNEL_CMDLINE) +else +QEMU_MACHINE := -machine q800 -smp 1 -append $(KERNEL_CMDLINE) +endif +else +$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k) +endif + +REAL_CC := $(CBUILD)-gcc +MUSL_CC := $(BUILD_PATH)/musl-gcc +export CC := $(MUSL_CC) +USERSPACE_DEPS := $(MUSL_CC) $(BUILD_PATH)/include/.installed $(BUILD_PATH)/include/linux/.installed + +build: $(KERNEL_BZIMAGE) +qemu: $(KERNEL_BZIMAGE) + rm -f $(BUILD_PATH)/result + timeout --foreground 20m qemu-system-$(QEMU_ARCH) \ + -nodefaults \ + -nographic \ + -smp $(NR_CPUS) \ + $(QEMU_MACHINE) \ + -m $$(grep -q CONFIG_DEBUG_KMEMLEAK=y $(KERNEL_BUILD_PATH)/.config && echo 1G || echo 256M) \ + -serial stdio \ + -serial file:$(BUILD_PATH)/result \ + -no-reboot \ + -monitor none \ + -kernel $< + grep -Fq success $(BUILD_PATH)/result + +$(BUILD_PATH)/init-cpio-spec.txt: + mkdir -p $(BUILD_PATH) + echo "file /init $(BUILD_PATH)/init 755 0 0" > $@ + echo "file /init.sh $(PWD)/../netns.sh 755 0 0" >> $@ + echo "dir /dev 755 0 0" >> $@ + echo "nod /dev/console 644 0 0 c 5 1" >> $@ + echo "dir /bin 755 0 0" >> $@ + echo "file /bin/iperf3 $(IPERF_PATH)/src/iperf3 755 0 0" >> $@ + echo "file /bin/wg $(WIREGUARD_TOOLS_PATH)/src/wg 755 0 0" >> $@ + echo "file /bin/bash $(BASH_PATH)/bash 755 0 0" >> $@ + echo "file /bin/ip $(IPROUTE2_PATH)/ip/ip 755 0 0" >> $@ + echo "file /bin/ss $(IPROUTE2_PATH)/misc/ss 755 0 0" >> $@ + echo "file /bin/ping $(IPUTILS_PATH)/ping 755 0 0" >> $@ + echo "file /bin/ncat $(NMAP_PATH)/ncat/ncat 755 0 0" >> $@ + echo "file /bin/xtables-legacy-multi $(IPTABLES_PATH)/iptables/xtables-legacy-multi 755 0 0" >> $@ + echo "slink /bin/iptables xtables-legacy-multi 777 0 0" >> $@ + echo "slink /bin/ping6 ping 777 0 0" >> $@ + echo "dir /lib 755 0 0" >> $@ + echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@ + echo "slink /lib/ld-linux.so.1 libc.so 777 0 0" >> $@ + +$(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config + mkdir -p $(KERNEL_BUILD_PATH) + cp kernel.config $(KERNEL_BUILD_PATH)/minimal.config + printf 'CONFIG_NR_CPUS=$(NR_CPUS)\nCONFIG_INITRAMFS_SOURCE="$(BUILD_PATH)/init-cpio-spec.txt"\n' >> $(KERNEL_BUILD_PATH)/minimal.config + cat arch/$(ARCH).config >> $(KERNEL_BUILD_PATH)/minimal.config + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) allnoconfig + cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config + $(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,) + +$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES) + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) + +$(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install + touch $@ + +$(MUSL_PATH)/lib/libc.so: $(MUSL_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + cd $(MUSL_PATH) && CC=$(REAL_CC) ./configure --prefix=/ --disable-static --build=$(CBUILD) + $(MAKE) -C $(MUSL_PATH) + $(STRIP) -s $@ + +$(BUILD_PATH)/include/.installed: $(MUSL_PATH)/lib/libc.so + $(MAKE) -C $(MUSL_PATH) DESTDIR=$(BUILD_PATH) install-headers + touch $@ + +$(MUSL_CC): $(MUSL_PATH)/lib/libc.so + sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs + printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" "$$@"\n' > $(BUILD_PATH)/musl-gcc + chmod +x $(BUILD_PATH)/musl-gcc + +$(IPERF_PATH)/.installed: $(IPERF_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + sed -i '1s/^/#include <stdint.h>/' $(IPERF_PATH)/src/cjson.h $(IPERF_PATH)/src/timer.h + sed -i -r 's/-p?g//g' $(IPERF_PATH)/src/Makefile* + touch $@ + +$(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS) + cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --with-openssl=no + $(MAKE) -C $(IPERF_PATH) + $(STRIP) -s $@ + +$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS) + cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared + $(MAKE) -C $(LIBMNL_PATH) + sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc + +$(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) + LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg + $(STRIP) -s $@ + +$(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) + mkdir -p $(BUILD_PATH) + $(MUSL_CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $< + $(STRIP) -s $@ + +$(IPUTILS_PATH)/.installed: $(IPUTILS_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(IPUTILS_PATH)/ping: | $(IPUTILS_PATH)/.installed $(USERSPACE_DEPS) + sed -i /atexit/d $(IPUTILS_PATH)/ping.c + cd $(IPUTILS_PATH) && $(CC) $(CFLAGS) -std=c99 -o $@ ping.c ping_common.c ping6_common.c iputils_common.c -D_GNU_SOURCE -D'IPUTILS_VERSION(f)=f' -lresolv $(LDFLAGS) + $(STRIP) -s $@ + +$(BASH_PATH)/.installed: $(BASH_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS) + cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-multibyte --disable-progcomp --disable-readline --disable-mem-scramble + $(MAKE) -C $(BASH_PATH) + $(STRIP) -s $@ + +$(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk + printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile + touch $@ + +$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) + LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip + $(STRIP) -s $(IPROUTE2_PATH)/ip/ip + +$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) + LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss + $(STRIP) -s $(IPROUTE2_PATH)/misc/ss + +$(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure + touch $@ + +$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) + cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include + $(MAKE) -C $(IPTABLES_PATH) + $(STRIP) -s $@ + +$(NMAP_PATH)/.installed: $(NMAP_TAR) + mkdir -p $(BUILD_PATH) + flock -s $<.lock tar -C $(BUILD_PATH) -xf $< + touch $@ + +$(NMAP_PATH)/ncat/ncat: | $(NMAP_PATH)/.installed $(USERSPACE_DEPS) + cd $(NMAP_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --without-ndiff --without-zenmap --without-nping --with-libpcap=included --with-libpcre=included --with-libdnet=included --without-liblua --with-liblinear=included --without-nmap-update --without-openssl --with-pcap=linux --without-libssh + $(MAKE) -C $(NMAP_PATH)/libpcap + $(MAKE) -C $(NMAP_PATH)/ncat + $(STRIP) -s $@ + +clean: + rm -rf $(BUILD_PATH) + +distclean: clean + rm -rf $(DISTFILES_PATH) + +menuconfig: $(KERNEL_BUILD_PATH)/.config + $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) menuconfig + +.PHONY: qemu build clean distclean menuconfig +.DELETE_ON_ERROR: diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config new file mode 100644 index 000000000000..3d063bb247bb --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config @@ -0,0 +1,5 @@ +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config new file mode 100644 index 000000000000..dbdc7e406a7b --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config @@ -0,0 +1,6 @@ +CONFIG_CPU_BIG_ENDIAN=y +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/arm.config b/tools/testing/selftests/wireguard/qemu/arch/arm.config new file mode 100644 index 000000000000..148f49905418 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/arm.config @@ -0,0 +1,9 @@ +CONFIG_MMU=y +CONFIG_ARCH_MULTI_V7=y +CONFIG_ARCH_VIRT=y +CONFIG_THUMB2_KERNEL=n +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/armeb.config b/tools/testing/selftests/wireguard/qemu/arch/armeb.config new file mode 100644 index 000000000000..bd76b07d00a2 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/armeb.config @@ -0,0 +1,10 @@ +CONFIG_MMU=y +CONFIG_ARCH_MULTI_V7=y +CONFIG_ARCH_VIRT=y +CONFIG_THUMB2_KERNEL=n +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1" +CONFIG_CPU_BIG_ENDIAN=y +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/i686.config b/tools/testing/selftests/wireguard/qemu/arch/i686.config new file mode 100644 index 000000000000..a85025d7206e --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config @@ -0,0 +1,5 @@ +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/m68k.config b/tools/testing/selftests/wireguard/qemu/arch/m68k.config new file mode 100644 index 000000000000..62a15bdb877e --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config @@ -0,0 +1,9 @@ +CONFIG_MMU=y +CONFIG_M68KCLASSIC=y +CONFIG_M68040=y +CONFIG_MAC=y +CONFIG_SERIAL_PMACZILOG=y +CONFIG_SERIAL_PMACZILOG_TTYS=y +CONFIG_SERIAL_PMACZILOG_CONSOLE=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips.config b/tools/testing/selftests/wireguard/qemu/arch/mips.config new file mode 100644 index 000000000000..df71d6b95546 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mips.config @@ -0,0 +1,11 @@ +CONFIG_CPU_MIPS32_R2=y +CONFIG_MIPS_MALTA=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64.config b/tools/testing/selftests/wireguard/qemu/arch/mips64.config new file mode 100644 index 000000000000..90c783f725c4 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mips64.config @@ -0,0 +1,14 @@ +CONFIG_64BIT=y +CONFIG_CPU_MIPS64_R2=y +CONFIG_MIPS32_N32=y +CONFIG_CPU_HAS_MSA=y +CONFIG_MIPS_MALTA=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64el.config b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config new file mode 100644 index 000000000000..435b0b43e00c --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config @@ -0,0 +1,15 @@ +CONFIG_64BIT=y +CONFIG_CPU_MIPS64_R2=y +CONFIG_MIPS32_N32=y +CONFIG_CPU_HAS_MSA=y +CONFIG_MIPS_MALTA=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/mipsel.config b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config new file mode 100644 index 000000000000..62bb50c4a85f --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config @@ -0,0 +1,12 @@ +CONFIG_CPU_MIPS32_R2=y +CONFIG_MIPS_MALTA=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_MIPS_CPS=y +CONFIG_MIPS_FP_SUPPORT=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config new file mode 100644 index 000000000000..57957093b71b --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config @@ -0,0 +1,10 @@ +CONFIG_PPC_QEMU_E500=y +CONFIG_FSL_SOC_BOOKE=y +CONFIG_PPC_85xx=y +CONFIG_PHYS_64BIT=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_MATH_EMULATION=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1024 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config new file mode 100644 index 000000000000..990c510a9cfa --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config @@ -0,0 +1,12 @@ +CONFIG_PPC64=y +CONFIG_PPC_PSERIES=y +CONFIG_ALTIVEC=y +CONFIG_VSX=y +CONFIG_PPC_OF_BOOT_TRAMPOLINE=y +CONFIG_PPC_RADIX_MMU=y +CONFIG_HVC_CONSOLE=y +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" +CONFIG_SECTION_MISMATCH_WARN_ONLY=y +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config new file mode 100644 index 000000000000..00a1ef4869d5 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config @@ -0,0 +1,5 @@ +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1" +CONFIG_FRAME_WARN=1280 diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config new file mode 100644 index 000000000000..b9c72706fe4d --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -0,0 +1,67 @@ +CONFIG_LOCALVERSION="-debug" +CONFIG_ENABLE_WARN_DEPRECATED=y +CONFIG_ENABLE_MUST_CHECK=y +CONFIG_FRAME_POINTER=y +CONFIG_STACK_VALIDATION=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_PAGE_EXTENSION=y +CONFIG_PAGE_POISONING=y +CONFIG_DEBUG_OBJECTS=y +CONFIG_DEBUG_OBJECTS_FREE=y +CONFIG_DEBUG_OBJECTS_TIMERS=y +CONFIG_DEBUG_OBJECTS_WORK=y +CONFIG_DEBUG_OBJECTS_RCU_HEAD=y +CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y +CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 +CONFIG_SLUB_DEBUG_ON=y +CONFIG_DEBUG_VM=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_HAVE_DEBUG_STACKOVERFLOW=y +CONFIG_DEBUG_STACKOVERFLOW=y +CONFIG_HAVE_ARCH_KMEMCHECK=y +CONFIG_HAVE_ARCH_KASAN=y +CONFIG_KASAN=y +CONFIG_KASAN_INLINE=y +CONFIG_UBSAN=y +CONFIG_UBSAN_SANITIZE_ALL=y +CONFIG_UBSAN_NO_ALIGNMENT=y +CONFIG_UBSAN_NULL=y +CONFIG_DEBUG_KMEMLEAK=y +CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192 +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_SHIRQ=y +CONFIG_WQ_WATCHDOG=y +CONFIG_SCHED_DEBUG=y +CONFIG_SCHED_INFO=y +CONFIG_SCHEDSTATS=y +CONFIG_SCHED_STACK_END_CHECK=y +CONFIG_DEBUG_TIMEKEEPING=y +CONFIG_TIMER_STATS=y +CONFIG_DEBUG_PREEMPT=y +CONFIG_DEBUG_RT_MUTEXES=y +CONFIG_DEBUG_SPINLOCK=y +CONFIG_DEBUG_MUTEXES=y +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_LOCKING=y +CONFIG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_TRACE_IRQFLAGS=y +CONFIG_DEBUG_BUGVERBOSE=y +CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_PI_LIST=y +CONFIG_PROVE_RCU=y +CONFIG_SPARSE_RCU_POINTER=y +CONFIG_RCU_CPU_STALL_TIMEOUT=21 +CONFIG_RCU_TRACE=y +CONFIG_RCU_EQS_DEBUG=y +CONFIG_USER_STACKTRACE_SUPPORT=y +CONFIG_DEBUG_SG=y +CONFIG_DEBUG_NOTIFIERS=y +CONFIG_DOUBLEFAULT=y +CONFIG_X86_DEBUG_FPU=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT=y +CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y diff --git a/tools/testing/selftests/wireguard/qemu/init.c b/tools/testing/selftests/wireguard/qemu/init.c new file mode 100644 index 000000000000..90bc9813cadc --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/init.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. + */ + +#define _GNU_SOURCE +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> +#include <fcntl.h> +#include <sys/wait.h> +#include <sys/mount.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/io.h> +#include <sys/ioctl.h> +#include <sys/reboot.h> +#include <sys/utsname.h> +#include <sys/sendfile.h> +#include <sys/sysmacros.h> +#include <linux/random.h> +#include <linux/version.h> + +__attribute__((noreturn)) static void poweroff(void) +{ + fflush(stdout); + fflush(stderr); + reboot(RB_AUTOBOOT); + sleep(30); + fprintf(stderr, "\x1b[37m\x1b[41m\x1b[1mFailed to power off!!!\x1b[0m\n"); + exit(1); +} + +static void panic(const char *what) +{ + fprintf(stderr, "\n\n\x1b[37m\x1b[41m\x1b[1mSOMETHING WENT HORRIBLY WRONG\x1b[0m\n\n \x1b[31m\x1b[1m%s: %s\x1b[0m\n\n\x1b[37m\x1b[44m\x1b[1mPower off...\x1b[0m\n\n", what, strerror(errno)); + poweroff(); +} + +#define pretty_message(msg) puts("\x1b[32m\x1b[1m" msg "\x1b[0m") + +static void print_banner(void) +{ + struct utsname utsname; + int len; + + if (uname(&utsname) < 0) + panic("uname"); + + len = strlen(" WireGuard Test Suite on ") + strlen(utsname.sysname) + strlen(utsname.release) + strlen(utsname.machine); + printf("\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\x1b[45m\x1b[33m\x1b[1m WireGuard Test Suite on %s %s %s \x1b[0m\n\x1b[45m\x1b[33m\x1b[1m%*.s\x1b[0m\n\n", len, "", utsname.sysname, utsname.release, utsname.machine, len, ""); +} + +static void seed_rng(void) +{ + int fd; + struct { + int entropy_count; + int buffer_size; + unsigned char buffer[256]; + } entropy = { + .entropy_count = sizeof(entropy.buffer) * 8, + .buffer_size = sizeof(entropy.buffer), + .buffer = "Adding real entropy is not actually important for these tests. Don't try this at home, kids!" + }; + + if (mknod("/dev/urandom", S_IFCHR | 0644, makedev(1, 9))) + panic("mknod(/dev/urandom)"); + fd = open("/dev/urandom", O_WRONLY); + if (fd < 0) + panic("open(urandom)"); + for (int i = 0; i < 256; ++i) { + if (ioctl(fd, RNDADDENTROPY, &entropy) < 0) + panic("ioctl(urandom)"); + } + close(fd); +} + +static void mount_filesystems(void) +{ + pretty_message("[+] Mounting filesystems..."); + mkdir("/dev", 0755); + mkdir("/proc", 0755); + mkdir("/sys", 0755); + mkdir("/tmp", 0755); + mkdir("/run", 0755); + mkdir("/var", 0755); + if (mount("none", "/dev", "devtmpfs", 0, NULL)) + panic("devtmpfs mount"); + if (mount("none", "/proc", "proc", 0, NULL)) + panic("procfs mount"); + if (mount("none", "/sys", "sysfs", 0, NULL)) + panic("sysfs mount"); + if (mount("none", "/tmp", "tmpfs", 0, NULL)) + panic("tmpfs mount"); + if (mount("none", "/run", "tmpfs", 0, NULL)) + panic("tmpfs mount"); + if (mount("none", "/sys/kernel/debug", "debugfs", 0, NULL)) + ; /* Not a problem if it fails.*/ + if (symlink("/run", "/var/run")) + panic("run symlink"); + if (symlink("/proc/self/fd", "/dev/fd")) + panic("fd symlink"); +} + +static void enable_logging(void) +{ + int fd; + pretty_message("[+] Enabling logging..."); + fd = open("/proc/sys/kernel/printk", O_WRONLY); + if (fd >= 0) { + if (write(fd, "9\n", 2) != 2) + panic("write(printk)"); + close(fd); + } + fd = open("/proc/sys/debug/exception-trace", O_WRONLY); + if (fd >= 0) { + if (write(fd, "1\n", 2) != 2) + panic("write(exception-trace)"); + close(fd); + } + fd = open("/proc/sys/kernel/panic_on_warn", O_WRONLY); + if (fd >= 0) { + if (write(fd, "1\n", 2) != 2) + panic("write(panic_on_warn)"); + close(fd); + } +} + +static void kmod_selftests(void) +{ + FILE *file; + char line[2048], *start, *pass; + bool success = true; + pretty_message("[+] Module self-tests:"); + file = fopen("/proc/kmsg", "r"); + if (!file) + panic("fopen(kmsg)"); + if (fcntl(fileno(file), F_SETFL, O_NONBLOCK) < 0) + panic("fcntl(kmsg, nonblock)"); + while (fgets(line, sizeof(line), file)) { + start = strstr(line, "wireguard: "); + if (!start) + continue; + start += 11; + *strchrnul(start, '\n') = '\0'; + if (strstr(start, "www.wireguard.com")) + break; + pass = strstr(start, ": pass"); + if (!pass || pass[6] != '\0') { + success = false; + printf(" \x1b[31m* %s\x1b[0m\n", start); + } else + printf(" \x1b[32m* %s\x1b[0m\n", start); + } + fclose(file); + if (!success) { + puts("\x1b[31m\x1b[1m[-] Tests failed! \u2639\x1b[0m"); + poweroff(); + } +} + +static void launch_tests(void) +{ + char cmdline[4096], *success_dev; + int status, fd; + pid_t pid; + + pretty_message("[+] Launching tests..."); + pid = fork(); + if (pid == -1) + panic("fork"); + else if (pid == 0) { + execl("/init.sh", "init", NULL); + panic("exec"); + } + if (waitpid(pid, &status, 0) < 0) + panic("waitpid"); + if (WIFEXITED(status) && WEXITSTATUS(status) == 0) { + pretty_message("[+] Tests successful! :-)"); + fd = open("/proc/cmdline", O_RDONLY); + if (fd < 0) + panic("open(/proc/cmdline)"); + if (read(fd, cmdline, sizeof(cmdline) - 1) <= 0) + panic("read(/proc/cmdline)"); + cmdline[sizeof(cmdline) - 1] = '\0'; + for (success_dev = strtok(cmdline, " \n"); success_dev; success_dev = strtok(NULL, " \n")) { + if (strncmp(success_dev, "wg.success=", 11)) + continue; + memcpy(success_dev + 11 - 5, "/dev/", 5); + success_dev += 11 - 5; + break; + } + if (!success_dev || !strlen(success_dev)) + panic("Unable to find success device"); + + fd = open(success_dev, O_WRONLY); + if (fd < 0) + panic("open(success_dev)"); + if (write(fd, "success\n", 8) != 8) + panic("write(success_dev)"); + close(fd); + } else { + const char *why = "unknown cause"; + int what = -1; + + if (WIFEXITED(status)) { + why = "exit code"; + what = WEXITSTATUS(status); + } else if (WIFSIGNALED(status)) { + why = "signal"; + what = WTERMSIG(status); + } + printf("\x1b[31m\x1b[1m[-] Tests failed with %s %d! \u2639\x1b[0m\n", why, what); + } +} + +static void ensure_console(void) +{ + for (unsigned int i = 0; i < 1000; ++i) { + int fd = open("/dev/console", O_RDWR); + if (fd < 0) { + usleep(50000); + continue; + } + dup2(fd, 0); + dup2(fd, 1); + dup2(fd, 2); + close(fd); + if (write(1, "\0\0\0\0\n", 5) == 5) + return; + } + panic("Unable to open console device"); +} + +static void clear_leaks(void) +{ + int fd; + + fd = open("/sys/kernel/debug/kmemleak", O_WRONLY); + if (fd < 0) + return; + pretty_message("[+] Starting memory leak detection..."); + write(fd, "clear\n", 5); + close(fd); +} + +static void check_leaks(void) +{ + int fd; + + fd = open("/sys/kernel/debug/kmemleak", O_WRONLY); + if (fd < 0) + return; + pretty_message("[+] Scanning for memory leaks..."); + sleep(2); /* Wait for any grace periods. */ + write(fd, "scan\n", 5); + close(fd); + + fd = open("/sys/kernel/debug/kmemleak", O_RDONLY); + if (fd < 0) + return; + if (sendfile(1, fd, NULL, 0x7ffff000) > 0) + panic("Memory leaks encountered"); + close(fd); +} + +int main(int argc, char *argv[]) +{ + seed_rng(); + ensure_console(); + print_banner(); + mount_filesystems(); + kmod_selftests(); + enable_logging(); + clear_leaks(); + launch_tests(); + check_leaks(); + poweroff(); + return 1; +} diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config new file mode 100644 index 000000000000..af9323a0b6e0 --- /dev/null +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -0,0 +1,88 @@ +CONFIG_LOCALVERSION="" +CONFIG_NET=y +CONFIG_NETDEVICES=y +CONFIG_NET_CORE=y +CONFIG_NET_IPIP=y +CONFIG_DUMMY=y +CONFIG_VETH=y +CONFIG_MULTIUSER=y +CONFIG_NAMESPACES=y +CONFIG_NET_NS=y +CONFIG_UNIX=y +CONFIG_INET=y +CONFIG_IPV6=y +CONFIG_NETFILTER=y +CONFIG_NETFILTER_ADVANCED=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_NAT=y +CONFIG_NETFILTER_XTABLES=y +CONFIG_NETFILTER_XT_NAT=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_NF_NAT_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_TTY=y +CONFIG_BINFMT_ELF=y +CONFIG_BINFMT_SCRIPT=y +CONFIG_VDSO=y +CONFIG_VIRTUALIZATION=y +CONFIG_HYPERVISOR_GUEST=y +CONFIG_PARAVIRT=y +CONFIG_KVM_GUEST=y +CONFIG_PARAVIRT_SPINLOCKS=y +CONFIG_PRINTK=y +CONFIG_KALLSYMS=y +CONFIG_BUG=y +CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE=y +CONFIG_JUMP_LABEL=y +CONFIG_EMBEDDED=n +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_SHMEM=y +CONFIG_SLUB=y +CONFIG_SPARSEMEM_VMEMMAP=y +CONFIG_SMP=y +CONFIG_SCHED_SMT=y +CONFIG_SCHED_MC=y +CONFIG_NUMA=y +CONFIG_PREEMPT=y +CONFIG_NO_HZ=y +CONFIG_NO_HZ_IDLE=y +CONFIG_NO_HZ_FULL=n +CONFIG_HZ_PERIODIC=n +CONFIG_HIGH_RES_TIMERS=y +CONFIG_COMPAT_32BIT_TIME=y +CONFIG_ARCH_RANDOM=y +CONFIG_FILE_LOCKING=y +CONFIG_POSIX_TIMERS=y +CONFIG_DEVTMPFS=y +CONFIG_PROC_FS=y +CONFIG_PROC_SYSCTL=y +CONFIG_SYSFS=y +CONFIG_TMPFS=y +CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15 +CONFIG_PRINTK_TIME=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_LEGACY_VSYSCALL_NONE=y +CONFIG_KERNEL_GZIP=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_BUG_ON_DATA_CORRUPTION=y +CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y +CONFIG_WQ_WATCHDOG=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y +CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y +CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y +CONFIG_PANIC_TIMEOUT=-1 +CONFIG_STACKTRACE=y +CONFIG_EARLY_PRINTK=y +CONFIG_GDB_SCRIPTS=y +CONFIG_WIREGUARD=y +CONFIG_WIREGUARD_DEBUG=y diff --git a/tools/testing/vsock/.gitignore b/tools/testing/vsock/.gitignore index dc5f11faf530..7f7a2ccc30c4 100644 --- a/tools/testing/vsock/.gitignore +++ b/tools/testing/vsock/.gitignore @@ -1,2 +1,3 @@ *.d +vsock_test vsock_diag_test diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile index 5be687b1e16c..f8293c6910c9 100644 --- a/tools/testing/vsock/Makefile +++ b/tools/testing/vsock/Makefile @@ -1,10 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only all: test -test: vsock_diag_test -vsock_diag_test: vsock_diag_test.o timeout.o control.o +test: vsock_test vsock_diag_test +vsock_test: vsock_test.o timeout.o control.o util.o +vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o -CFLAGS += -g -O2 -Werror -Wall -I. -I../../include/uapi -I../../include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE +CFLAGS += -g -O2 -Werror -Wall -I. -I../../include -I../../../usr/include -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -D_GNU_SOURCE .PHONY: all test clean clean: - ${RM} *.o *.d vsock_diag_test + ${RM} *.o *.d vsock_test vsock_diag_test -include *.d diff --git a/tools/testing/vsock/README b/tools/testing/vsock/README index 2cc6d7302db6..4d5045e7d2c3 100644 --- a/tools/testing/vsock/README +++ b/tools/testing/vsock/README @@ -5,12 +5,13 @@ Hyper-V. The following tests are available: + * vsock_test - core AF_VSOCK socket functionality * vsock_diag_test - vsock_diag.ko module for listing open sockets The following prerequisite steps are not automated and must be performed prior to running tests: -1. Build the kernel and these tests. +1. Build the kernel, make headers_install, and build these tests. 2. Install the kernel and tests on the host. 3. Install the kernel and tests inside the guest. 4. Boot the guest and ensure that the AF_VSOCK transport is enabled. diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c index 45f328c6ff23..4874872fc5a3 100644 --- a/tools/testing/vsock/control.c +++ b/tools/testing/vsock/control.c @@ -205,11 +205,22 @@ void control_expectln(const char *str) char *line; line = control_readln(); - if (strcmp(str, line) != 0) { + + control_cmpln(line, str, true); + + free(line); +} + +bool control_cmpln(char *line, const char *str, bool fail) +{ + if (strcmp(str, line) == 0) + return true; + + if (fail) { fprintf(stderr, "expected \"%s\" on control socket, got \"%s\"\n", str, line); exit(EXIT_FAILURE); } - free(line); + return false; } diff --git a/tools/testing/vsock/control.h b/tools/testing/vsock/control.h index 54a07efd267c..51814b4f9ac1 100644 --- a/tools/testing/vsock/control.h +++ b/tools/testing/vsock/control.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef CONTROL_H #define CONTROL_H @@ -9,5 +10,6 @@ void control_cleanup(void); void control_writeln(const char *str); char *control_readln(void); void control_expectln(const char *str); +bool control_cmpln(char *line, const char *str, bool fail); #endif /* CONTROL_H */ diff --git a/tools/testing/vsock/timeout.h b/tools/testing/vsock/timeout.h index 77db9ce9860a..ecb7c840e65a 100644 --- a/tools/testing/vsock/timeout.h +++ b/tools/testing/vsock/timeout.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef TIMEOUT_H #define TIMEOUT_H diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c new file mode 100644 index 000000000000..93cbd6f603f9 --- /dev/null +++ b/tools/testing/vsock/util.c @@ -0,0 +1,375 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vsock test utilities + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi <stefanha@redhat.com> + */ + +#include <errno.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <signal.h> +#include <unistd.h> +#include <assert.h> +#include <sys/epoll.h> + +#include "timeout.h" +#include "control.h" +#include "util.h" + +/* Install signal handlers */ +void init_signals(void) +{ + struct sigaction act = { + .sa_handler = sigalrm, + }; + + sigaction(SIGALRM, &act, NULL); + signal(SIGPIPE, SIG_IGN); +} + +/* Parse a CID in string representation */ +unsigned int parse_cid(const char *str) +{ + char *endptr = NULL; + unsigned long n; + + errno = 0; + n = strtoul(str, &endptr, 10); + if (errno || *endptr != '\0') { + fprintf(stderr, "malformed CID \"%s\"\n", str); + exit(EXIT_FAILURE); + } + return n; +} + +/* Wait for the remote to close the connection */ +void vsock_wait_remote_close(int fd) +{ + struct epoll_event ev; + int epollfd, nfds; + + epollfd = epoll_create1(0); + if (epollfd == -1) { + perror("epoll_create1"); + exit(EXIT_FAILURE); + } + + ev.events = EPOLLRDHUP | EPOLLHUP; + ev.data.fd = fd; + if (epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev) == -1) { + perror("epoll_ctl"); + exit(EXIT_FAILURE); + } + + nfds = epoll_wait(epollfd, &ev, 1, TIMEOUT * 1000); + if (nfds == -1) { + perror("epoll_wait"); + exit(EXIT_FAILURE); + } + + if (nfds == 0) { + fprintf(stderr, "epoll_wait timed out\n"); + exit(EXIT_FAILURE); + } + + assert(nfds == 1); + assert(ev.events & (EPOLLRDHUP | EPOLLHUP)); + assert(ev.data.fd == fd); + + close(epollfd); +} + +/* Connect to <cid, port> and return the file descriptor. */ +int vsock_stream_connect(unsigned int cid, unsigned int port) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = port, + .svm_cid = cid, + }, + }; + int ret; + int fd; + + control_expectln("LISTENING"); + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + timeout_begin(TIMEOUT); + do { + ret = connect(fd, &addr.sa, sizeof(addr.svm)); + timeout_check("connect"); + } while (ret < 0 && errno == EINTR); + timeout_end(); + + if (ret < 0) { + int old_errno = errno; + + close(fd); + fd = -1; + errno = old_errno; + } + return fd; +} + +/* Listen on <cid, port> and return the first incoming connection. The remote + * address is stored to clientaddrp. clientaddrp may be NULL. + */ +int vsock_stream_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = port, + .svm_cid = cid, + }, + }; + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } clientaddr; + socklen_t clientaddr_len = sizeof(clientaddr.svm); + int fd; + int client_fd; + int old_errno; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { + perror("bind"); + exit(EXIT_FAILURE); + } + + if (listen(fd, 1) < 0) { + perror("listen"); + exit(EXIT_FAILURE); + } + + control_writeln("LISTENING"); + + timeout_begin(TIMEOUT); + do { + client_fd = accept(fd, &clientaddr.sa, &clientaddr_len); + timeout_check("accept"); + } while (client_fd < 0 && errno == EINTR); + timeout_end(); + + old_errno = errno; + close(fd); + errno = old_errno; + + if (client_fd < 0) + return client_fd; + + if (clientaddr_len != sizeof(clientaddr.svm)) { + fprintf(stderr, "unexpected addrlen from accept(2), %zu\n", + (size_t)clientaddr_len); + exit(EXIT_FAILURE); + } + if (clientaddr.sa.sa_family != AF_VSOCK) { + fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n", + clientaddr.sa.sa_family); + exit(EXIT_FAILURE); + } + + if (clientaddrp) + *clientaddrp = clientaddr.svm; + return client_fd; +} + +/* Transmit one byte and check the return value. + * + * expected_ret: + * <0 Negative errno (for testing errors) + * 0 End-of-file + * 1 Success + */ +void send_byte(int fd, int expected_ret, int flags) +{ + const uint8_t byte = 'A'; + ssize_t nwritten; + + timeout_begin(TIMEOUT); + do { + nwritten = send(fd, &byte, sizeof(byte), flags); + timeout_check("write"); + } while (nwritten < 0 && errno == EINTR); + timeout_end(); + + if (expected_ret < 0) { + if (nwritten != -1) { + fprintf(stderr, "bogus send(2) return value %zd\n", + nwritten); + exit(EXIT_FAILURE); + } + if (errno != -expected_ret) { + perror("write"); + exit(EXIT_FAILURE); + } + return; + } + + if (nwritten < 0) { + perror("write"); + exit(EXIT_FAILURE); + } + if (nwritten == 0) { + if (expected_ret == 0) + return; + + fprintf(stderr, "unexpected EOF while sending byte\n"); + exit(EXIT_FAILURE); + } + if (nwritten != sizeof(byte)) { + fprintf(stderr, "bogus send(2) return value %zd\n", nwritten); + exit(EXIT_FAILURE); + } +} + +/* Receive one byte and check the return value. + * + * expected_ret: + * <0 Negative errno (for testing errors) + * 0 End-of-file + * 1 Success + */ +void recv_byte(int fd, int expected_ret, int flags) +{ + uint8_t byte; + ssize_t nread; + + timeout_begin(TIMEOUT); + do { + nread = recv(fd, &byte, sizeof(byte), flags); + timeout_check("read"); + } while (nread < 0 && errno == EINTR); + timeout_end(); + + if (expected_ret < 0) { + if (nread != -1) { + fprintf(stderr, "bogus recv(2) return value %zd\n", + nread); + exit(EXIT_FAILURE); + } + if (errno != -expected_ret) { + perror("read"); + exit(EXIT_FAILURE); + } + return; + } + + if (nread < 0) { + perror("read"); + exit(EXIT_FAILURE); + } + if (nread == 0) { + if (expected_ret == 0) + return; + + fprintf(stderr, "unexpected EOF while receiving byte\n"); + exit(EXIT_FAILURE); + } + if (nread != sizeof(byte)) { + fprintf(stderr, "bogus recv(2) return value %zd\n", nread); + exit(EXIT_FAILURE); + } + if (byte != 'A') { + fprintf(stderr, "unexpected byte read %c\n", byte); + exit(EXIT_FAILURE); + } +} + +/* Run test cases. The program terminates if a failure occurs. */ +void run_tests(const struct test_case *test_cases, + const struct test_opts *opts) +{ + int i; + + for (i = 0; test_cases[i].name; i++) { + void (*run)(const struct test_opts *opts); + char *line; + + printf("%d - %s...", i, test_cases[i].name); + fflush(stdout); + + /* Full barrier before executing the next test. This + * ensures that client and server are executing the + * same test case. In particular, it means whoever is + * faster will not see the peer still executing the + * last test. This is important because port numbers + * can be used by multiple test cases. + */ + if (test_cases[i].skip) + control_writeln("SKIP"); + else + control_writeln("NEXT"); + + line = control_readln(); + if (control_cmpln(line, "SKIP", false) || test_cases[i].skip) { + + printf("skipped\n"); + + free(line); + continue; + } + + control_cmpln(line, "NEXT", true); + free(line); + + if (opts->mode == TEST_MODE_CLIENT) + run = test_cases[i].run_client; + else + run = test_cases[i].run_server; + + if (run) + run(opts); + + printf("ok\n"); + } +} + +void list_tests(const struct test_case *test_cases) +{ + int i; + + printf("ID\tTest name\n"); + + for (i = 0; test_cases[i].name; i++) + printf("%d\t%s\n", i, test_cases[i].name); + + exit(EXIT_FAILURE); +} + +void skip_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str) +{ + unsigned long test_id; + char *endptr = NULL; + + errno = 0; + test_id = strtoul(test_id_str, &endptr, 10); + if (errno || *endptr != '\0') { + fprintf(stderr, "malformed test ID \"%s\"\n", test_id_str); + exit(EXIT_FAILURE); + } + + if (test_id >= test_cases_len) { + fprintf(stderr, "test ID (%lu) larger than the max allowed (%lu)\n", + test_id, test_cases_len - 1); + exit(EXIT_FAILURE); + } + + test_cases[test_id].skip = true; +} diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h new file mode 100644 index 000000000000..e53dd09d26d9 --- /dev/null +++ b/tools/testing/vsock/util.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef UTIL_H +#define UTIL_H + +#include <sys/socket.h> +#include <linux/vm_sockets.h> + +/* Tests can either run as the client or the server */ +enum test_mode { + TEST_MODE_UNSET, + TEST_MODE_CLIENT, + TEST_MODE_SERVER +}; + +/* Test runner options */ +struct test_opts { + enum test_mode mode; + unsigned int peer_cid; +}; + +/* A test case definition. Test functions must print failures to stderr and + * terminate with exit(EXIT_FAILURE). + */ +struct test_case { + const char *name; /* human-readable name */ + + /* Called when test mode is TEST_MODE_CLIENT */ + void (*run_client)(const struct test_opts *opts); + + /* Called when test mode is TEST_MODE_SERVER */ + void (*run_server)(const struct test_opts *opts); + + bool skip; +}; + +void init_signals(void); +unsigned int parse_cid(const char *str); +int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_stream_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp); +void vsock_wait_remote_close(int fd); +void send_byte(int fd, int expected_ret, int flags); +void recv_byte(int fd, int expected_ret, int flags); +void run_tests(const struct test_case *test_cases, + const struct test_opts *opts); +void list_tests(const struct test_case *test_cases); +void skip_test(struct test_case *test_cases, size_t test_cases_len, + const char *test_id_str); +#endif /* UTIL_H */ diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c index c481101364a4..cec6f5a738e1 100644 --- a/tools/testing/vsock/vsock_diag_test.c +++ b/tools/testing/vsock/vsock_diag_test.c @@ -9,32 +9,22 @@ #include <getopt.h> #include <stdio.h> -#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <errno.h> #include <unistd.h> -#include <signal.h> -#include <sys/socket.h> #include <sys/stat.h> #include <sys/types.h> #include <linux/list.h> #include <linux/net.h> #include <linux/netlink.h> #include <linux/sock_diag.h> +#include <linux/vm_sockets_diag.h> #include <netinet/tcp.h> -#include "../../../include/uapi/linux/vm_sockets.h" -#include "../../../include/uapi/linux/vm_sockets_diag.h" - #include "timeout.h" #include "control.h" - -enum test_mode { - TEST_MODE_UNSET, - TEST_MODE_CLIENT, - TEST_MODE_SERVER -}; +#include "util.h" /* Per-socket status */ struct vsock_stat { @@ -335,7 +325,7 @@ static void free_sock_stat(struct list_head *sockets) free(st); } -static void test_no_sockets(unsigned int peer_cid) +static void test_no_sockets(const struct test_opts *opts) { LIST_HEAD(sockets); @@ -346,7 +336,7 @@ static void test_no_sockets(unsigned int peer_cid) free_sock_stat(&sockets); } -static void test_listen_socket_server(unsigned int peer_cid) +static void test_listen_socket_server(const struct test_opts *opts) { union { struct sockaddr sa; @@ -384,35 +374,14 @@ static void test_listen_socket_server(unsigned int peer_cid) free_sock_stat(&sockets); } -static void test_connect_client(unsigned int peer_cid) +static void test_connect_client(const struct test_opts *opts) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = 1234, - .svm_cid = peer_cid, - }, - }; int fd; - int ret; LIST_HEAD(sockets); struct vsock_stat *st; - control_expectln("LISTENING"); - - fd = socket(AF_VSOCK, SOCK_STREAM, 0); - - timeout_begin(TIMEOUT); - do { - ret = connect(fd, &addr.sa, sizeof(addr.svm)); - timeout_check("connect"); - } while (ret < 0 && errno == EINTR); - timeout_end(); - - if (ret < 0) { + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { perror("connect"); exit(EXIT_FAILURE); } @@ -430,68 +399,21 @@ static void test_connect_client(unsigned int peer_cid) free_sock_stat(&sockets); } -static void test_connect_server(unsigned int peer_cid) +static void test_connect_server(const struct test_opts *opts) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = 1234, - .svm_cid = VMADDR_CID_ANY, - }, - }; - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } clientaddr; - socklen_t clientaddr_len = sizeof(clientaddr.svm); - LIST_HEAD(sockets); struct vsock_stat *st; - int fd; + LIST_HEAD(sockets); int client_fd; - fd = socket(AF_VSOCK, SOCK_STREAM, 0); - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } - - if (listen(fd, 1) < 0) { - perror("listen"); - exit(EXIT_FAILURE); - } - - control_writeln("LISTENING"); - - timeout_begin(TIMEOUT); - do { - client_fd = accept(fd, &clientaddr.sa, &clientaddr_len); - timeout_check("accept"); - } while (client_fd < 0 && errno == EINTR); - timeout_end(); - + client_fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); if (client_fd < 0) { perror("accept"); exit(EXIT_FAILURE); } - if (clientaddr.sa.sa_family != AF_VSOCK) { - fprintf(stderr, "expected AF_VSOCK from accept(2), got %d\n", - clientaddr.sa.sa_family); - exit(EXIT_FAILURE); - } - if (clientaddr.svm.svm_cid != peer_cid) { - fprintf(stderr, "expected peer CID %u from accept(2), got %u\n", - peer_cid, clientaddr.svm.svm_cid); - exit(EXIT_FAILURE); - } read_vsock_stat(&sockets); - check_num_sockets(&sockets, 2); - find_vsock_stat(&sockets, fd); + check_num_sockets(&sockets, 1); st = find_vsock_stat(&sockets, client_fd); check_socket_state(st, TCP_ESTABLISHED); @@ -499,15 +421,10 @@ static void test_connect_server(unsigned int peer_cid) control_expectln("DONE"); close(client_fd); - close(fd); free_sock_stat(&sockets); } -static struct { - const char *name; - void (*run_client)(unsigned int peer_cid); - void (*run_server)(unsigned int peer_cid); -} test_cases[] = { +static struct test_case test_cases[] = { { .name = "No sockets", .run_server = test_no_sockets, @@ -524,30 +441,6 @@ static struct { {}, }; -static void init_signals(void) -{ - struct sigaction act = { - .sa_handler = sigalrm, - }; - - sigaction(SIGALRM, &act, NULL); - signal(SIGPIPE, SIG_IGN); -} - -static unsigned int parse_cid(const char *str) -{ - char *endptr = NULL; - unsigned long int n; - - errno = 0; - n = strtoul(str, &endptr, 10); - if (errno || *endptr != '\0') { - fprintf(stderr, "malformed CID \"%s\"\n", str); - exit(EXIT_FAILURE); - } - return n; -} - static const char optstring[] = ""; static const struct option longopts[] = { { @@ -571,6 +464,16 @@ static const struct option longopts[] = { .val = 'p', }, { + .name = "list", + .has_arg = no_argument, + .val = 'l', + }, + { + .name = "skip", + .has_arg = required_argument, + .val = 's', + }, + { .name = "help", .has_arg = no_argument, .val = '?', @@ -580,7 +483,7 @@ static const struct option longopts[] = { static void usage(void) { - fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid>\n" + fprintf(stderr, "Usage: vsock_diag_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid> [--list] [--skip=<test_id>]\n" "\n" " Server: vsock_diag_test --control-port=1234 --mode=server --peer-cid=3\n" " Client: vsock_diag_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n" @@ -594,7 +497,18 @@ static void usage(void) "listen address and the client requires an address to\n" "connect to.\n" "\n" - "The CID of the other side must be given with --peer-cid=<cid>.\n"); + "The CID of the other side must be given with --peer-cid=<cid>.\n" + "\n" + "Options:\n" + " --help This help message\n" + " --control-host <host> Server IP address to connect to\n" + " --control-port <port> Server port to listen on/connect to\n" + " --mode client|server Server or client mode\n" + " --peer-cid <cid> CID of the other side\n" + " --list List of tests that will be executed\n" + " --skip <test_id> Test ID to skip;\n" + " use multiple --skip options to skip more tests\n" + ); exit(EXIT_FAILURE); } @@ -602,9 +516,10 @@ int main(int argc, char **argv) { const char *control_host = NULL; const char *control_port = NULL; - int mode = TEST_MODE_UNSET; - unsigned int peer_cid = VMADDR_CID_ANY; - int i; + struct test_opts opts = { + .mode = TEST_MODE_UNSET, + .peer_cid = VMADDR_CID_ANY, + }; init_signals(); @@ -620,20 +535,27 @@ int main(int argc, char **argv) break; case 'm': if (strcmp(optarg, "client") == 0) - mode = TEST_MODE_CLIENT; + opts.mode = TEST_MODE_CLIENT; else if (strcmp(optarg, "server") == 0) - mode = TEST_MODE_SERVER; + opts.mode = TEST_MODE_SERVER; else { fprintf(stderr, "--mode must be \"client\" or \"server\"\n"); return EXIT_FAILURE; } break; case 'p': - peer_cid = parse_cid(optarg); + opts.peer_cid = parse_cid(optarg); break; case 'P': control_port = optarg; break; + case 'l': + list_tests(test_cases); + break; + case 's': + skip_test(test_cases, ARRAY_SIZE(test_cases) - 1, + optarg); + break; case '?': default: usage(); @@ -642,35 +564,21 @@ int main(int argc, char **argv) if (!control_port) usage(); - if (mode == TEST_MODE_UNSET) + if (opts.mode == TEST_MODE_UNSET) usage(); - if (peer_cid == VMADDR_CID_ANY) + if (opts.peer_cid == VMADDR_CID_ANY) usage(); if (!control_host) { - if (mode != TEST_MODE_SERVER) + if (opts.mode != TEST_MODE_SERVER) usage(); control_host = "0.0.0.0"; } - control_init(control_host, control_port, mode == TEST_MODE_SERVER); + control_init(control_host, control_port, + opts.mode == TEST_MODE_SERVER); - for (i = 0; test_cases[i].name; i++) { - void (*run)(unsigned int peer_cid); - - printf("%s...", test_cases[i].name); - fflush(stdout); - - if (mode == TEST_MODE_CLIENT) - run = test_cases[i].run_client; - else - run = test_cases[i].run_server; - - if (run) - run(peer_cid); - - printf("ok\n"); - } + run_tests(test_cases, &opts); control_cleanup(); return EXIT_SUCCESS; diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c new file mode 100644 index 000000000000..1d8b93f1af31 --- /dev/null +++ b/tools/testing/vsock/vsock_test.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * vsock_test - vsock.ko test suite + * + * Copyright (C) 2017 Red Hat, Inc. + * + * Author: Stefan Hajnoczi <stefanha@redhat.com> + */ + +#include <getopt.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <linux/kernel.h> + +#include "timeout.h" +#include "control.h" +#include "util.h" + +static void test_stream_connection_reset(const struct test_opts *opts) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = opts->peer_cid, + }, + }; + int ret; + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + timeout_begin(TIMEOUT); + do { + ret = connect(fd, &addr.sa, sizeof(addr.svm)); + timeout_check("connect"); + } while (ret < 0 && errno == EINTR); + timeout_end(); + + if (ret != -1) { + fprintf(stderr, "expected connect(2) failure, got %d\n", ret); + exit(EXIT_FAILURE); + } + if (errno != ECONNRESET) { + fprintf(stderr, "unexpected connect(2) errno %d\n", errno); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_client_close_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + send_byte(fd, 1, 0); + close(fd); +} + +static void test_stream_client_close_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + /* Wait for the remote to close the connection, before check + * -EPIPE error on send. + */ + vsock_wait_remote_close(fd); + + send_byte(fd, -EPIPE, 0); + recv_byte(fd, 1, 0); + recv_byte(fd, 0, 0); + close(fd); +} + +static void test_stream_server_close_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + /* Wait for the remote to close the connection, before check + * -EPIPE error on send. + */ + vsock_wait_remote_close(fd); + + send_byte(fd, -EPIPE, 0); + recv_byte(fd, 1, 0); + recv_byte(fd, 0, 0); + close(fd); +} + +static void test_stream_server_close_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + send_byte(fd, 1, 0); + close(fd); +} + +/* With the standard socket sizes, VMCI is able to support about 100 + * concurrent stream connections. + */ +#define MULTICONN_NFDS 100 + +static void test_stream_multiconn_client(const struct test_opts *opts) +{ + int fds[MULTICONN_NFDS]; + int i; + + for (i = 0; i < MULTICONN_NFDS; i++) { + fds[i] = vsock_stream_connect(opts->peer_cid, 1234); + if (fds[i] < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + } + + for (i = 0; i < MULTICONN_NFDS; i++) { + if (i % 2) + recv_byte(fds[i], 1, 0); + else + send_byte(fds[i], 1, 0); + } + + for (i = 0; i < MULTICONN_NFDS; i++) + close(fds[i]); +} + +static void test_stream_multiconn_server(const struct test_opts *opts) +{ + int fds[MULTICONN_NFDS]; + int i; + + for (i = 0; i < MULTICONN_NFDS; i++) { + fds[i] = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fds[i] < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + } + + for (i = 0; i < MULTICONN_NFDS; i++) { + if (i % 2) + send_byte(fds[i], 1, 0); + else + recv_byte(fds[i], 1, 0); + } + + for (i = 0; i < MULTICONN_NFDS; i++) + close(fds[i]); +} + +static void test_stream_msg_peek_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + send_byte(fd, 1, 0); + close(fd); +} + +static void test_stream_msg_peek_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + recv_byte(fd, 1, MSG_PEEK); + recv_byte(fd, 1, 0); + close(fd); +} + +static struct test_case test_cases[] = { + { + .name = "SOCK_STREAM connection reset", + .run_client = test_stream_connection_reset, + }, + { + .name = "SOCK_STREAM client close", + .run_client = test_stream_client_close_client, + .run_server = test_stream_client_close_server, + }, + { + .name = "SOCK_STREAM server close", + .run_client = test_stream_server_close_client, + .run_server = test_stream_server_close_server, + }, + { + .name = "SOCK_STREAM multiple connections", + .run_client = test_stream_multiconn_client, + .run_server = test_stream_multiconn_server, + }, + { + .name = "SOCK_STREAM MSG_PEEK", + .run_client = test_stream_msg_peek_client, + .run_server = test_stream_msg_peek_server, + }, + {}, +}; + +static const char optstring[] = ""; +static const struct option longopts[] = { + { + .name = "control-host", + .has_arg = required_argument, + .val = 'H', + }, + { + .name = "control-port", + .has_arg = required_argument, + .val = 'P', + }, + { + .name = "mode", + .has_arg = required_argument, + .val = 'm', + }, + { + .name = "peer-cid", + .has_arg = required_argument, + .val = 'p', + }, + { + .name = "list", + .has_arg = no_argument, + .val = 'l', + }, + { + .name = "skip", + .has_arg = required_argument, + .val = 's', + }, + { + .name = "help", + .has_arg = no_argument, + .val = '?', + }, + {}, +}; + +static void usage(void) +{ + fprintf(stderr, "Usage: vsock_test [--help] [--control-host=<host>] --control-port=<port> --mode=client|server --peer-cid=<cid> [--list] [--skip=<test_id>]\n" + "\n" + " Server: vsock_test --control-port=1234 --mode=server --peer-cid=3\n" + " Client: vsock_test --control-host=192.168.0.1 --control-port=1234 --mode=client --peer-cid=2\n" + "\n" + "Run vsock.ko tests. Must be launched in both guest\n" + "and host. One side must use --mode=client and\n" + "the other side must use --mode=server.\n" + "\n" + "A TCP control socket connection is used to coordinate tests\n" + "between the client and the server. The server requires a\n" + "listen address and the client requires an address to\n" + "connect to.\n" + "\n" + "The CID of the other side must be given with --peer-cid=<cid>.\n" + "\n" + "Options:\n" + " --help This help message\n" + " --control-host <host> Server IP address to connect to\n" + " --control-port <port> Server port to listen on/connect to\n" + " --mode client|server Server or client mode\n" + " --peer-cid <cid> CID of the other side\n" + " --list List of tests that will be executed\n" + " --skip <test_id> Test ID to skip;\n" + " use multiple --skip options to skip more tests\n" + ); + exit(EXIT_FAILURE); +} + +int main(int argc, char **argv) +{ + const char *control_host = NULL; + const char *control_port = NULL; + struct test_opts opts = { + .mode = TEST_MODE_UNSET, + .peer_cid = VMADDR_CID_ANY, + }; + + init_signals(); + + for (;;) { + int opt = getopt_long(argc, argv, optstring, longopts, NULL); + + if (opt == -1) + break; + + switch (opt) { + case 'H': + control_host = optarg; + break; + case 'm': + if (strcmp(optarg, "client") == 0) + opts.mode = TEST_MODE_CLIENT; + else if (strcmp(optarg, "server") == 0) + opts.mode = TEST_MODE_SERVER; + else { + fprintf(stderr, "--mode must be \"client\" or \"server\"\n"); + return EXIT_FAILURE; + } + break; + case 'p': + opts.peer_cid = parse_cid(optarg); + break; + case 'P': + control_port = optarg; + break; + case 'l': + list_tests(test_cases); + break; + case 's': + skip_test(test_cases, ARRAY_SIZE(test_cases) - 1, + optarg); + break; + case '?': + default: + usage(); + } + } + + if (!control_port) + usage(); + if (opts.mode == TEST_MODE_UNSET) + usage(); + if (opts.peer_cid == VMADDR_CID_ANY) + usage(); + + if (!control_host) { + if (opts.mode != TEST_MODE_SERVER) + usage(); + control_host = "0.0.0.0"; + } + + control_init(control_host, control_port, + opts.mode == TEST_MODE_SERVER); + + run_tests(test_cases, &opts); + + control_cleanup(); + return EXIT_SUCCESS; +} |