diff options
| author | David S. Miller <davem@davemloft.net> | 2019-04-28 08:42:41 -0400 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2019-04-28 08:42:41 -0400 |
| commit | 5f0d736e7f7db586141f974821b6ca6c1d906d5b (patch) | |
| tree | 8f62c1a24fd499a55deb455c6dd42bb51cd53275 /tools | |
| parent | b1a79360ee862f8ada4798ad2346fa45bb41b527 (diff) | |
| parent | 9076c49bdca2aa68c805f2677b2bccc4bde2bac1 (diff) | |
| download | lwn-5f0d736e7f7db586141f974821b6ca6c1d906d5b.tar.gz lwn-5f0d736e7f7db586141f974821b6ca6c1d906d5b.zip | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
pull-request: bpf-next 2019-04-28
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Introduce BPF socket local storage map so that BPF programs can store
private data they associate with a socket (instead of e.g. separate hash
table), from Martin.
2) Add support for bpftool to dump BTF types. This is done through a new
`bpftool btf dump` sub-command, from Andrii.
3) Enable BPF-based flow dissector for skb-less eth_get_headlen() calls which
was currently not supported since skb was used to lookup netns, from Stanislav.
4) Add an opt-in interface for tracepoints to expose a writable context
for attached BPF programs, used here for NBD sockets, from Matt.
5) BPF xadd related arm64 JIT fixes and scalability improvements, from Daniel.
6) Change the skb->protocol for bpf_skb_adjust_room() helper in order to
support tunnels such as sit. Add selftests as well, from Willem.
7) Various smaller misc fixes.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'tools')
40 files changed, 2669 insertions, 197 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst new file mode 100644 index 000000000000..2dbc1413fabd --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -0,0 +1,222 @@ +================ +bpftool-btf +================ +------------------------------------------------------------------------------- +tool for inspection of BTF data +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **btf** *COMMAND* + + *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] } + + *COMMANDS* := { **dump** | **help** } + +BTF COMMANDS +============= + +| **bpftool** **btf dump** *BTF_SRC* +| **bpftool** **btf help** +| +| *BTF_SRC* := { **id** *BTF_ID* | **prog** *PROG* | **map** *MAP* [{**key** | **value** | **kv** | **all**}] | **file** *FILE* } +| *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } + +DESCRIPTION +=========== + **bpftool btf dump** *BTF_SRC* + Dump BTF entries from a given *BTF_SRC*. + + When **id** is specified, BTF object with that ID will be + loaded and all its BTF types emitted. + + When **map** is provided, it's expected that map has + associated BTF object with BTF types describing key and + value. It's possible to select whether to dump only BTF + type(s) associated with key (**key**), value (**value**), + both key and value (**kv**), or all BTF types present in + associated BTF object (**all**). If not specified, **kv** + is assumed. + + When **prog** is provided, it's expected that program has + associated BTF object with BTF types. + + When specifying *FILE*, an ELF file is expected, containing + .BTF section with well-defined BTF binary format data, + typically produced by clang or pahole. + + **bpftool btf 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**. + +EXAMPLES +======== +**# bpftool btf dump id 1226** +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'dummy_tracepoint_args' size=16 vlen=2 + 'pad' type_id=3 bits_offset=0 + 'sock' type_id=4 bits_offset=64 + [3] INT 'long long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [4] PTR '(anon)' type_id=5 + [5] FWD 'sock' fwd_kind=union + +This gives an example of default output for all supported BTF kinds. + +**$ cat prog.c** +:: + + struct fwd_struct; + + enum my_enum { + VAL1 = 3, + VAL2 = 7, + }; + + typedef struct my_struct my_struct_t; + + struct my_struct { + const unsigned int const_int_field; + int bitfield_field: 4; + char arr_field[16]; + const struct fwd_struct *restrict fwd_field; + enum my_enum enum_field; + volatile my_struct_t *typedef_ptr_field; + }; + + union my_union { + int a; + struct my_struct b; + }; + + struct my_struct struct_global_var __attribute__((section("data_sec"))) = { + .bitfield_field = 3, + .enum_field = VAL1, + }; + int global_var __attribute__((section("data_sec"))) = 7; + + __attribute__((noinline)) + int my_func(union my_union *arg1, int arg2) + { + static int static_var __attribute__((section("data_sec"))) = 123; + static_var++; + return static_var; + } + +**$ bpftool btf dump file prog.o** +:: + + [1] PTR '(anon)' type_id=2 + [2] UNION 'my_union' size=48 vlen=2 + 'a' type_id=3 bits_offset=0 + 'b' type_id=4 bits_offset=0 + [3] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + [4] STRUCT 'my_struct' size=48 vlen=6 + 'const_int_field' type_id=5 bits_offset=0 + 'bitfield_field' type_id=3 bits_offset=32 bitfield_size=4 + 'arr_field' type_id=8 bits_offset=40 + 'fwd_field' type_id=10 bits_offset=192 + 'enum_field' type_id=14 bits_offset=256 + 'typedef_ptr_field' type_id=15 bits_offset=320 + [5] CONST '(anon)' type_id=6 + [6] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=SIGNED + [8] ARRAY '(anon)' type_id=7 index_type_id=9 nr_elems=16 + [9] INT '__ARRAY_SIZE_TYPE__' size=4 bits_offset=0 nr_bits=32 encoding=(none) + [10] RESTRICT '(anon)' type_id=11 + [11] PTR '(anon)' type_id=12 + [12] CONST '(anon)' type_id=13 + [13] FWD 'fwd_struct' fwd_kind=union + [14] ENUM 'my_enum' size=4 vlen=2 + 'VAL1' val=3 + 'VAL2' val=7 + [15] PTR '(anon)' type_id=16 + [16] VOLATILE '(anon)' type_id=17 + [17] TYPEDEF 'my_struct_t' type_id=4 + [18] FUNC_PROTO '(anon)' ret_type_id=3 vlen=2 + 'arg1' type_id=1 + 'arg2' type_id=3 + [19] FUNC 'my_func' type_id=18 + [20] VAR 'struct_global_var' type_id=4, linkage=global-alloc + [21] VAR 'global_var' type_id=3, linkage=global-alloc + [22] VAR 'my_func.static_var' type_id=3, linkage=static + [23] DATASEC 'data_sec' size=0 vlen=3 + type_id=20 offset=0 size=48 + type_id=21 offset=0 size=4 + type_id=22 offset=52 size=4 + +The following commands print BTF types associated with specified map's key, +value, both key and value, and all BTF types, respectively. By default, both +key and value types will be printed. + +**# bpftool btf dump map id 123 key** + +:: + + [39] TYPEDEF 'u32' type_id=37 + +**# bpftool btf dump map id 123 value** + +:: + + [86] PTR '(anon)' type_id=87 + +**# bpftool btf dump map id 123 kv** + +:: + + [39] TYPEDEF 'u32' type_id=37 + [86] PTR '(anon)' type_id=87 + +**# bpftool btf dump map id 123 all** + +:: + + [1] PTR '(anon)' type_id=0 + . + . + . + [2866] ARRAY '(anon)' type_id=52 index_type_id=51 nr_elems=4 + +All the standard ways to specify map or program are supported: + +**# bpftool btf dump map id 123** + +**# bpftool btf dump map pinned /sys/fs/bpf/map_name** + +**# bpftool btf dump prog id 456** + +**# bpftool btf dump prog tag b88e0a09b1d9759d** + +**# bpftool btf dump prog pinned /sys/fs/bpf/prog_name** + +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) diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 89b6b10e2183..ac26876389c2 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -145,4 +145,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index 10177343b7ce..14180e887082 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -82,4 +82,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (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 55ecf80ca03e..13ef27b39f20 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -258,4 +258,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index 6b692b428373..934580850f42 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -143,4 +143,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst index 86154740fabb..0c7576523a21 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -85,4 +85,5 @@ SEE ALSO **bpftool-map**\ (8), **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), - **bpftool-net**\ (8) + **bpftool-net**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 2f183ffd8351..e8118544d118 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -271,4 +271,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index deb2ca911ddf..3e562d7fd56f 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -76,4 +76,5 @@ SEE ALSO **bpftool-cgroup**\ (8), **bpftool-feature**\ (8), **bpftool-net**\ (8), - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), + **bpftool-btf**\ (8) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 9f3ffe1e26ab..50e402a5a9c8 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -217,6 +217,7 @@ _bpftool() done cur=${words[cword]} prev=${words[cword - 1]} + pprev=${words[cword - 2]} local object=${words[1]} command=${words[2]} @@ -272,17 +273,17 @@ _bpftool() "$cur" ) ) return 0 ;; - *) - _bpftool_once_attr 'file' - if _bpftool_search_list 'xlated'; then - COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \ - "$cur" ) ) - else - COMPREPLY+=( $( compgen -W 'opcodes linum' -- \ - "$cur" ) ) - fi - return 0 - ;; + *) + _bpftool_once_attr 'file' + if _bpftool_search_list 'xlated'; then + COMPREPLY+=( $( compgen -W 'opcodes visual linum' -- \ + "$cur" ) ) + else + COMPREPLY+=( $( compgen -W 'opcodes linum' -- \ + "$cur" ) ) + fi + return 0 + ;; esac ;; pin) @@ -607,6 +608,51 @@ _bpftool() ;; esac ;; + btf) + local PROG_TYPE='id pinned tag' + local MAP_TYPE='id pinned' + case $command in + dump) + case $prev in + $command) + COMPREPLY+=( $( compgen -W "id map prog file" -- \ + "$cur" ) ) + return 0 + ;; + prog) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + map) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + case $pprev in + prog) + _bpftool_get_prog_ids + ;; + map) + _bpftool_get_map_ids + ;; + esac + return 0 + ;; + *) + if [[ $cword == 6 ]] && [[ ${words[3]} == "map" ]]; then + COMPREPLY+=( $( compgen -W 'key value kv all' -- \ + "$cur" ) ) + fi + return 0 + ;; + esac + ;; + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'dump help' -- "$cur" ) ) + ;; + esac + ;; cgroup) case $command in show|list) diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c new file mode 100644 index 000000000000..58a2cd002a4b --- /dev/null +++ b/tools/bpf/bpftool/btf.c @@ -0,0 +1,586 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Facebook */ + +#include <errno.h> +#include <fcntl.h> +#include <linux/err.h> +#include <stdbool.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <gelf.h> +#include <bpf.h> +#include <linux/btf.h> + +#include "btf.h" +#include "json_writer.h" +#include "main.h" + +static const char * const btf_kind_str[NR_BTF_KINDS] = { + [BTF_KIND_UNKN] = "UNKNOWN", + [BTF_KIND_INT] = "INT", + [BTF_KIND_PTR] = "PTR", + [BTF_KIND_ARRAY] = "ARRAY", + [BTF_KIND_STRUCT] = "STRUCT", + [BTF_KIND_UNION] = "UNION", + [BTF_KIND_ENUM] = "ENUM", + [BTF_KIND_FWD] = "FWD", + [BTF_KIND_TYPEDEF] = "TYPEDEF", + [BTF_KIND_VOLATILE] = "VOLATILE", + [BTF_KIND_CONST] = "CONST", + [BTF_KIND_RESTRICT] = "RESTRICT", + [BTF_KIND_FUNC] = "FUNC", + [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", + [BTF_KIND_VAR] = "VAR", + [BTF_KIND_DATASEC] = "DATASEC", +}; + +static const char *btf_int_enc_str(__u8 encoding) +{ + switch (encoding) { + case 0: + return "(none)"; + case BTF_INT_SIGNED: + return "SIGNED"; + case BTF_INT_CHAR: + return "CHAR"; + case BTF_INT_BOOL: + return "BOOL"; + default: + return "UNKN"; + } +} + +static const char *btf_var_linkage_str(__u32 linkage) +{ + switch (linkage) { + case BTF_VAR_STATIC: + return "static"; + case BTF_VAR_GLOBAL_ALLOCATED: + return "global-alloc"; + default: + return "(unknown)"; + } +} + +static const char *btf_str(const struct btf *btf, __u32 off) +{ + if (!off) + return "(anon)"; + return btf__name_by_offset(btf, off) ? : "(invalid)"; +} + +static int dump_btf_type(const struct btf *btf, __u32 id, + const struct btf_type *t) +{ + json_writer_t *w = json_wtr; + int kind, safe_kind; + + kind = BTF_INFO_KIND(t->info); + safe_kind = kind <= BTF_KIND_MAX ? kind : BTF_KIND_UNKN; + + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "id", id); + jsonw_string_field(w, "kind", btf_kind_str[safe_kind]); + jsonw_string_field(w, "name", btf_str(btf, t->name_off)); + } else { + printf("[%u] %s '%s'", id, btf_kind_str[safe_kind], + btf_str(btf, t->name_off)); + } + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: { + __u32 v = *(__u32 *)(t + 1); + const char *enc; + + enc = btf_int_enc_str(BTF_INT_ENCODING(v)); + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "bits_offset", BTF_INT_OFFSET(v)); + jsonw_uint_field(w, "nr_bits", BTF_INT_BITS(v)); + jsonw_string_field(w, "encoding", enc); + } else { + printf(" size=%u bits_offset=%u nr_bits=%u encoding=%s", + t->size, BTF_INT_OFFSET(v), BTF_INT_BITS(v), + enc); + } + break; + } + case BTF_KIND_PTR: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_TYPEDEF: + if (json_output) + jsonw_uint_field(w, "type_id", t->type); + else + printf(" type_id=%u", t->type); + break; + case BTF_KIND_ARRAY: { + const struct btf_array *arr = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", arr->type); + jsonw_uint_field(w, "index_type_id", arr->index_type); + jsonw_uint_field(w, "nr_elems", arr->nelems); + } else { + printf(" type_id=%u index_type_id=%u nr_elems=%u", + arr->type, arr->index_type, arr->nelems); + } + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "members"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, m++) { + const char *name = btf_str(btf, m->name_off); + __u32 bit_off, bit_sz; + + if (BTF_INFO_KFLAG(t->info)) { + bit_off = BTF_MEMBER_BIT_OFFSET(m->offset); + bit_sz = BTF_MEMBER_BITFIELD_SIZE(m->offset); + } else { + bit_off = m->offset; + bit_sz = 0; + } + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "type_id", m->type); + jsonw_uint_field(w, "bits_offset", bit_off); + if (bit_sz) { + jsonw_uint_field(w, "bitfield_size", + bit_sz); + } + jsonw_end_object(w); + } else { + printf("\n\t'%s' type_id=%u bits_offset=%u", + name, m->type, bit_off); + if (bit_sz) + printf(" bitfield_size=%u", bit_sz); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_ENUM: { + const struct btf_enum *v = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "values"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + const char *name = btf_str(btf, v->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "val", v->val); + jsonw_end_object(w); + } else { + printf("\n\t'%s' val=%u", name, v->val); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_FWD: { + const char *fwd_kind = BTF_INFO_KIND(t->info) ? "union" + : "struct"; + + if (json_output) + jsonw_string_field(w, "fwd_kind", fwd_kind); + else + printf(" fwd_kind=%s", fwd_kind); + break; + } + case BTF_KIND_FUNC: + if (json_output) + jsonw_uint_field(w, "type_id", t->type); + else + printf(" type_id=%u", t->type); + break; + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = (const void *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "ret_type_id", t->type); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "params"); + jsonw_start_array(w); + } else { + printf(" ret_type_id=%u vlen=%u", t->type, vlen); + } + for (i = 0; i < vlen; i++, p++) { + const char *name = btf_str(btf, p->name_off); + + if (json_output) { + jsonw_start_object(w); + jsonw_string_field(w, "name", name); + jsonw_uint_field(w, "type_id", p->type); + jsonw_end_object(w); + } else { + printf("\n\t'%s' type_id=%u", name, p->type); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + case BTF_KIND_VAR: { + const struct btf_var *v = (const void *)(t + 1); + const char *linkage; + + linkage = btf_var_linkage_str(v->linkage); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_string_field(w, "linkage", linkage); + } else { + printf(" type_id=%u, linkage=%s", t->type, linkage); + } + break; + } + case BTF_KIND_DATASEC: { + const struct btf_var_secinfo *v = (const void *)(t+1); + __u16 vlen = BTF_INFO_VLEN(t->info); + int i; + + if (json_output) { + jsonw_uint_field(w, "size", t->size); + jsonw_uint_field(w, "vlen", vlen); + jsonw_name(w, "vars"); + jsonw_start_array(w); + } else { + printf(" size=%u vlen=%u", t->size, vlen); + } + for (i = 0; i < vlen; i++, v++) { + if (json_output) { + jsonw_start_object(w); + jsonw_uint_field(w, "type_id", v->type); + jsonw_uint_field(w, "offset", v->offset); + jsonw_uint_field(w, "size", v->size); + jsonw_end_object(w); + } else { + printf("\n\ttype_id=%u offset=%u size=%u", + v->type, v->offset, v->size); + } + } + if (json_output) + jsonw_end_array(w); + break; + } + default: + break; + } + + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + + return 0; +} + +static int dump_btf_raw(const struct btf *btf, + __u32 *root_type_ids, int root_type_cnt) +{ + const struct btf_type *t; + int i; + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "types"); + jsonw_start_array(json_wtr); + } + + if (root_type_cnt) { + for (i = 0; i < root_type_cnt; i++) { + t = btf__type_by_id(btf, root_type_ids[i]); + dump_btf_type(btf, root_type_ids[i], t); + } + } else { + int cnt = btf__get_nr_types(btf); + + for (i = 1; i <= cnt; i++) { + t = btf__type_by_id(btf, i); + dump_btf_type(btf, i, t); + } + } + + if (json_output) { + jsonw_end_array(json_wtr); + jsonw_end_object(json_wtr); + } + return 0; +} + +static bool check_btf_endianness(GElf_Ehdr *ehdr) +{ + static unsigned int const endian = 1; + + switch (ehdr->e_ident[EI_DATA]) { + case ELFDATA2LSB: + return *(unsigned char const *)&endian == 1; + case ELFDATA2MSB: + return *(unsigned char const *)&endian == 0; + default: + return 0; + } +} + +static int btf_load_from_elf(const char *path, struct btf **btf) +{ + int err = -1, fd = -1, idx = 0; + Elf_Data *btf_data = NULL; + Elf_Scn *scn = NULL; + Elf *elf = NULL; + GElf_Ehdr ehdr; + + if (elf_version(EV_CURRENT) == EV_NONE) { + p_err("failed to init libelf for %s", path); + return -1; + } + + fd = open(path, O_RDONLY); + if (fd < 0) { + p_err("failed to open %s: %s", path, strerror(errno)); + return -1; + } + + elf = elf_begin(fd, ELF_C_READ, NULL); + if (!elf) { + p_err("failed to open %s as ELF file", path); + goto done; + } + if (!gelf_getehdr(elf, &ehdr)) { + p_err("failed to get EHDR from %s", path); + goto done; + } + if (!check_btf_endianness(&ehdr)) { + p_err("non-native ELF endianness is not supported"); + goto done; + } + if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) { + p_err("failed to get e_shstrndx from %s\n", path); + goto done; + } + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + GElf_Shdr sh; + char *name; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + p_err("failed to get section(%d) header from %s", + idx, path); + goto done; + } + name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name); + if (!name) { + p_err("failed to get section(%d) name from %s", + idx, path); + goto done; + } + if (strcmp(name, BTF_ELF_SEC) == 0) { + btf_data = elf_getdata(scn, 0); + if (!btf_data) { + p_err("failed to get section(%d, %s) data from %s", + idx, name, path); + goto done; + } + break; + } + } + + if (!btf_data) { + p_err("%s ELF section not found in %s", BTF_ELF_SEC, path); + goto done; + } + + *btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(*btf)) { + err = PTR_ERR(*btf); + *btf = NULL; + p_err("failed to load BTF data from %s: %s", + path, strerror(err)); + goto done; + } + + err = 0; +done: + if (err) { + if (*btf) { + btf__free(*btf); + *btf = NULL; + } + } + if (elf) + elf_end(elf); + close(fd); + return err; +} + +static int do_dump(int argc, char **argv) +{ + struct btf *btf = NULL; + __u32 root_type_ids[2]; + int root_type_cnt = 0; + __u32 btf_id = -1; + const char *src; + int fd = -1; + int err; + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + src = GET_ARG(); + + if (is_prefix(src, "map")) { + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + fd = map_parse_fd_and_info(&argc, &argv, &info, &len); + if (fd < 0) + return -1; + + btf_id = info.btf_id; + if (argc && is_prefix(*argv, "key")) { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "value")) { + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "all")) { + NEXT_ARG(); + } else if (argc && is_prefix(*argv, "kv")) { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + NEXT_ARG(); + } else { + root_type_ids[root_type_cnt++] = info.btf_key_type_id; + root_type_ids[root_type_cnt++] = info.btf_value_type_id; + } + } else if (is_prefix(src, "prog")) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + + if (!REQ_ARGS(2)) { + usage(); + return -1; + } + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + p_err("can't get prog info: %s", strerror(errno)); + goto done; + } + + btf_id = info.btf_id; + } else if (is_prefix(src, "id")) { + char *endptr; + + btf_id = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as ID", **argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(src, "file")) { + err = btf_load_from_elf(*argv, &btf); + if (err) + goto done; + NEXT_ARG(); + } else { + err = -1; + p_err("unrecognized BTF source specifier: '%s'", src); + goto done; + } + + if (!btf) { + err = btf__get_from_id(btf_id, &btf); + if (err) { + p_err("get btf by id (%u): %s", btf_id, strerror(err)); + goto done; + } + if (!btf) { + err = ENOENT; + p_err("can't find btf with ID (%u)", btf_id); + goto done; + } + } + + dump_btf_raw(btf, root_type_ids, root_type_cnt); + +done: + close(fd); + btf__free(btf); + return err; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s btf dump BTF_SRC\n" + " %s btf help\n" + "\n" + " BTF_SRC := { id BTF_ID | prog PROG | map MAP [{key | value | kv | all}] | file FILE }\n" + " " HELP_SPEC_MAP "\n" + " " HELP_SPEC_PROGRAM "\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name, bin_name); + + return 0; +} + +static const struct cmd cmds[] = { + { "help", do_help }, + { "dump", do_dump }, + { 0 } +}; + +int do_btf(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 a9d5e9e6a732..1ac1fc520e6a 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -56,7 +56,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf | net | feature }\n" + " OBJECT := { prog | map | cgroup | perf | net | feature | btf }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -188,6 +188,7 @@ static const struct cmd cmds[] = { { "perf", do_perf }, { "net", do_net }, { "feature", do_feature }, + { "btf", do_btf }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 1ccc46169a19..3d63feb7f852 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -150,6 +150,7 @@ int do_perf(int argc, char **arg); 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 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 10b6c9d3e525..e951d45c0131 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -46,6 +46,7 @@ const char * const map_type_name[] = { [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", [BPF_MAP_TYPE_QUEUE] = "queue", [BPF_MAP_TYPE_STACK] = "stack", + [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", }; const size_t map_type_name_size = ARRAY_SIZE(map_type_name); @@ -724,7 +725,7 @@ static int dump_map_elem(int fd, void *key, void *value, } else { const char *msg = NULL; - if (errno == ENOENT) + if (lookup_errno == ENOENT) msg = "<no entry>"; else if (lookup_errno == ENOSPC && map_info->type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index db0e7de49d49..67e99c56bc88 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE #include <errno.h> +#include <fcntl.h> #include <stdlib.h> #include <string.h> #include <unistd.h> @@ -12,6 +13,8 @@ #include <linux/rtnetlink.h> #include <linux/tc_act/tc_bpf.h> #include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> #include <bpf.h> #include <nlattr.h> @@ -48,6 +51,10 @@ struct bpf_filter_t { int ifindex; }; +struct bpf_attach_info { + __u32 flow_dissector_id; +}; + static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb) { struct bpf_netdev_t *netinfo = cookie; @@ -180,8 +187,45 @@ out: return 0; } +static int query_flow_dissector(struct bpf_attach_info *attach_info) +{ + __u32 attach_flags; + __u32 prog_ids[1]; + __u32 prog_cnt; + int err; + int fd; + + fd = open("/proc/self/ns/net", O_RDONLY); + if (fd < 0) { + p_err("can't open /proc/self/ns/net: %d", + strerror(errno)); + return -1; + } + prog_cnt = ARRAY_SIZE(prog_ids); + err = bpf_prog_query(fd, BPF_FLOW_DISSECTOR, 0, + &attach_flags, prog_ids, &prog_cnt); + close(fd); + if (err) { + if (errno == EINVAL) { + /* Older kernel's don't support querying + * flow dissector programs. + */ + errno = 0; + return 0; + } + p_err("can't query prog: %s", strerror(errno)); + return -1; + } + + if (prog_cnt == 1) + attach_info->flow_dissector_id = prog_ids[0]; + + return 0; +} + static int do_show(int argc, char **argv) { + struct bpf_attach_info attach_info = {}; int i, sock, ret, filter_idx = -1; struct bpf_netdev_t dev_array; unsigned int nl_pid; @@ -199,6 +243,10 @@ static int do_show(int argc, char **argv) usage(); } + ret = query_flow_dissector(&attach_info); + if (ret) + return -1; + sock = libbpf_netlink_open(&nl_pid); if (sock < 0) { fprintf(stderr, "failed to open netlink sock\n"); @@ -227,6 +275,12 @@ static int do_show(int argc, char **argv) } NET_END_ARRAY("\n"); } + + NET_START_ARRAY("flow_dissector", "%s:\n"); + if (attach_info.flow_dissector_id > 0) + NET_DUMP_UINT("id", "id %u", attach_info.flow_dissector_id); + NET_END_ARRAY("\n"); + NET_END_OBJECT; if (json_output) jsonw_end_array(json_wtr); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 704bb69514a2..72336bac7573 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -133,6 +133,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, BPF_MAP_TYPE_STACK, + BPF_MAP_TYPE_SK_STORAGE, }; /* Note that tracing related programs such as @@ -168,6 +169,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_REUSEPORT, BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, }; enum bpf_attach_type { @@ -1737,12 +1739,19 @@ union bpf_attr { * error if an eBPF program tries to set a callback that is not * supported in the current kernel. * - * The supported callback values that *argval* can combine are: + * *argval* is a flag array which can combine these flags: * * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) * + * Therefore, this function can be used to clear a callback flag by + * setting the appropriate bit to zero. e.g. to disable the RTO + * callback: + * + * **bpf_sock_ops_cb_flags_set(bpf_sock,** + * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)** + * * Here are some examples of where one could call such eBPF * program: * @@ -2622,6 +2631,42 @@ union bpf_attr { * was provided. * * **-ERANGE** if resulting value was out of range. + * + * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * Description + * Get a bpf-local-storage from a sk. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem(map, &sk)** except this + * helper enforces the key must be a **bpf_fullsock()** + * and the map must be a BPF_MAP_TYPE_SK_STORAGE also. + * + * Underneath, the value is stored locally at *sk* instead of + * the map. The *map* is used as the bpf-local-storage **type**. + * The bpf-local-storage **type** (i.e. the *map*) is searched + * against all bpf-local-storages residing at sk. + * + * An optional *flags* (BPF_SK_STORAGE_GET_F_CREATE) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with BPF_SK_STORAGE_GET_F_CREATE to specify + * the initial value of a bpf-local-storage. If *value* is + * NULL, the new bpf-local-storage will be zero initialized. + * Return + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + * + * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * Description + * Delete a bpf-local-storage from a sk. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2730,7 +2775,9 @@ union bpf_attr { FN(sysctl_get_new_value), \ FN(sysctl_set_new_value), \ FN(strtol), \ - FN(strtoul), + FN(strtoul), \ + FN(sk_storage_get), \ + FN(sk_storage_delete), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2806,6 +2853,9 @@ enum bpf_func_id { /* BPF_FUNC_sysctl_get_name flags. */ #define BPF_F_SYSCTL_BASE_NAME (1ULL << 0) +/* BPF_FUNC_sk_storage_get flags */ +#define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index ff2506fe6bd2..9593fec75652 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -26,6 +26,7 @@ #include <linux/bpf.h> #include <stdbool.h> #include <stddef.h> +#include <stdint.h> #ifdef __cplusplus extern "C" { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d817bf20f3d6..11a65db4b93f 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -126,6 +126,8 @@ static inline __u64 ptr_to_u64(const void *ptr) struct bpf_capabilities { /* v4.14: kernel support for program & map names. */ __u32 name:1; + /* v5.2: kernel support for global data sections. */ + __u32 global_data:1; }; /* @@ -854,12 +856,15 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * * TODO: Detect array of map and report error. */ - if (obj->efile.data_shndx >= 0) - nr_maps_glob++; - if (obj->efile.rodata_shndx >= 0) - nr_maps_glob++; - if (obj->efile.bss_shndx >= 0) - nr_maps_glob++; + if (obj->caps.global_data) { + if (obj->efile.data_shndx >= 0) + nr_maps_glob++; + if (obj->efile.rodata_shndx >= 0) + nr_maps_glob++; + if (obj->efile.bss_shndx >= 0) + nr_maps_glob++; + } + for (i = 0; data && i < nr_syms; i++) { GElf_Sym sym; @@ -870,14 +875,14 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) nr_maps++; } - /* Alloc obj->maps and fill nr_maps. */ - pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, - nr_maps, data->d_size); if (!nr_maps && !nr_maps_glob) return 0; /* Assume equally sized map definitions */ if (data) { + pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, + nr_maps, data->d_size); + map_def_sz = data->d_size / nr_maps; if (!data->d_size || (data->d_size % nr_maps) != 0) { pr_warning("unable to determine map definition size " @@ -971,6 +976,9 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) map_idx++; } + if (!obj->caps.global_data) + goto finalize; + /* * Populate rest of obj->maps with libbpf internal maps. */ @@ -988,6 +996,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++], LIBBPF_MAP_BSS, obj->efile.bss, NULL); +finalize: if (!ret) qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); @@ -1333,11 +1342,17 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, if (bpf_object__shndx_is_maps(obj, shdr_idx) || bpf_object__shndx_is_data(obj, shdr_idx)) { type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); - if (type != LIBBPF_MAP_UNSPEC && - GELF_ST_BIND(sym.st_info) == STB_GLOBAL) { - pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n", - name, insn_idx, insns[insn_idx].code); - return -LIBBPF_ERRNO__RELOC; + if (type != LIBBPF_MAP_UNSPEC) { + if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) { + pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n", + name, insn_idx, insns[insn_idx].code); + return -LIBBPF_ERRNO__RELOC; + } + if (!obj->caps.global_data) { + pr_warning("bpf: 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++) { @@ -1496,9 +1511,67 @@ bpf_object__probe_name(struct bpf_object *obj) } static int +bpf_object__probe_global_data(struct bpf_object *obj) +{ + struct bpf_load_program_attr prg_attr; + struct bpf_create_map_attr map_attr; + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map; + + memset(&map_attr, 0, sizeof(map_attr)); + map_attr.map_type = BPF_MAP_TYPE_ARRAY; + map_attr.key_size = sizeof(int); + map_attr.value_size = 32; + map_attr.max_entries = 1; + + map = bpf_create_map_xattr(&map_attr); + if (map < 0) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warning("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, errno); + return -errno; + } + + insns[0].imm = map; + + memset(&prg_attr, 0, sizeof(prg_attr)); + prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + prg_attr.insns = insns; + prg_attr.insns_cnt = ARRAY_SIZE(insns); + prg_attr.license = "GPL"; + + ret = bpf_load_program_xattr(&prg_attr, NULL, 0); + if (ret >= 0) { + obj->caps.global_data = 1; + close(ret); + } + + close(map); + return 0; +} + +static int bpf_object__probe_caps(struct bpf_object *obj) { - return bpf_object__probe_name(obj); + int (*probe_fn[])(struct bpf_object *obj) = { + bpf_object__probe_name, + bpf_object__probe_global_data, + }; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(probe_fn); i++) { + ret = probe_fn[i](obj); + if (ret < 0) + return ret; + } + + return 0; } static int @@ -2063,6 +2136,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) case BPF_PROG_TYPE_UNSPEC: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_CGROUP_SYSCTL: return false; @@ -2100,6 +2174,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, 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, flags), err, out); CHECK_ERR(bpf_object__collect_reloc(obj), err, out); CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out); @@ -2193,7 +2268,6 @@ int bpf_object__load(struct bpf_object *obj) obj->loaded = true; - CHECK_ERR(bpf_object__probe_caps(obj), err, out); CHECK_ERR(bpf_object__create_maps(obj), err, out); CHECK_ERR(bpf_object__relocate(obj), err, out); CHECK_ERR(bpf_object__load_progs(obj), err, out); diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 0f25541632e3..a2c64a9ce1a6 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -9,6 +9,7 @@ #include <net/if.h> #include <sys/utsname.h> +#include <linux/btf.h> #include <linux/filter.h> #include <linux/kernel.h> @@ -93,6 +94,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_LIRC_MODE2: case BPF_PROG_TYPE_SK_REUSEPORT: @@ -130,11 +132,65 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex) return errno != EINVAL && errno != EOPNOTSUPP; } +static int load_btf(void) +{ +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) +#define BTF_TYPE_ENC(name, info, size_or_type) \ + (name), (info), (size_or_type) +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) +#define BTF_MEMBER_ENC(name, type, bits_offset) \ + (name), (type), (bits_offset) + + const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l"; + /* struct bpf_spin_lock { + * int val; + * }; + * struct val { + * int cnt; + * struct bpf_spin_lock l; + * }; + */ + __u32 btf_raw_types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct bpf_spin_lock */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4), + BTF_MEMBER_ENC(15, 1, 0), /* int val; */ + /* struct val */ /* [3] */ + BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ + BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + }; + struct btf_header btf_hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = sizeof(btf_raw_types), + .str_off = sizeof(btf_raw_types), + .str_len = sizeof(btf_str_sec), + }; + __u8 raw_btf[sizeof(struct btf_header) + sizeof(btf_raw_types) + + sizeof(btf_str_sec)]; + + memcpy(raw_btf, &btf_hdr, sizeof(btf_hdr)); + memcpy(raw_btf + sizeof(btf_hdr), btf_raw_types, sizeof(btf_raw_types)); + memcpy(raw_btf + sizeof(btf_hdr) + sizeof(btf_raw_types), + btf_str_sec, sizeof(btf_str_sec)); + + return bpf_load_btf(raw_btf, sizeof(raw_btf), 0, 0, 0); +} + bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) { int key_size, value_size, max_entries, map_flags; + __u32 btf_key_type_id = 0, btf_value_type_id = 0; struct bpf_create_map_attr attr = {}; - int fd = -1, fd_inner; + int fd = -1, btf_fd = -1, fd_inner; key_size = sizeof(__u32); value_size = sizeof(__u32); @@ -160,6 +216,16 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_STACK: key_size = 0; break; + case BPF_MAP_TYPE_SK_STORAGE: + btf_key_type_id = 1; + btf_value_type_id = 3; + value_size = 8; + max_entries = 0; + map_flags = BPF_F_NO_PREALLOC; + btf_fd = load_btf(); + if (btf_fd < 0) + return false; + break; case BPF_MAP_TYPE_UNSPEC: case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_ARRAY: @@ -205,11 +271,18 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) attr.max_entries = max_entries; attr.map_flags = map_flags; attr.map_ifindex = ifindex; + if (btf_fd >= 0) { + attr.btf_fd = btf_fd; + attr.btf_key_type_id = btf_key_type_id; + attr.btf_value_type_id = btf_value_type_id; + } fd = bpf_create_map_xattr(&attr); } if (fd >= 0) close(fd); + if (btf_fd >= 0) + close(btf_fd); return fd >= 0; } diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index f9d83ba7843e..66f2dca1dee1 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -74,6 +74,8 @@ all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/urandom_read: $(OUTPUT)/%: %.c $(CC) -o $@ $< -Wl,--build-id +$(OUTPUT)/test_maps: map_tests/*.c + BPFOBJ := $(OUTPUT)/libbpf.a $(TEST_GEN_PROGS): $(BPFOBJ) @@ -232,6 +234,27 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES) echo '#endif' \ ) > $(PROG_TESTS_H)) +TEST_MAPS_CFLAGS := -I. -I$(OUTPUT) +MAP_TESTS_DIR = $(OUTPUT)/map_tests +$(MAP_TESTS_DIR): + mkdir -p $@ +MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h +test_maps.c: $(MAP_TESTS_H) +$(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS) +MAP_TESTS_FILES := $(wildcard map_tests/*.c) +$(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES) + $(shell ( cd map_tests/; \ + echo '/* Generated header, do not edit */'; \ + echo '#ifdef DECLARE'; \ + ls *.c 2> /dev/null | \ + sed -e 's@\([^\.]*\)\.c@extern void test_\1(void);@'; \ + echo '#endif'; \ + echo '#ifdef CALL'; \ + ls *.c 2> /dev/null | \ + sed -e 's@\([^\.]*\)\.c@test_\1();@'; \ + echo '#endif' \ + ) > $(MAP_TESTS_H)) + VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h test_verifier.c: $(VERIFIER_TESTS_H) $(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) @@ -251,4 +274,4 @@ $(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES) ) > $(VERIFIER_TESTS_H)) EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) \ - $(VERIFIER_TESTS_H) $(PROG_TESTS_H) + $(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H) diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 59e221586cf7..6e80b66d7fb1 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -211,6 +211,11 @@ static int (*bpf_strtol)(const char *buf, unsigned long long buf_len, static int (*bpf_strtoul)(const char *buf, unsigned long long buf_len, unsigned long long flags, unsigned long *res) = (void *) BPF_FUNC_strtoul; +static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk, + void *value, __u64 flags) = + (void *) BPF_FUNC_sk_storage_get; +static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) = + (void *)BPF_FUNC_sk_storage_delete; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 8c976476f6fd..f7a0744db31e 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -33,3 +33,4 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_IPV6_SIT=m diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c index 7136ab9ffa73..3fd83b9dc1bf 100644 --- a/tools/testing/selftests/bpf/flow_dissector_load.c +++ b/tools/testing/selftests/bpf/flow_dissector_load.c @@ -26,7 +26,7 @@ static void load_and_attach_program(void) struct bpf_object *obj; ret = bpf_flow_load(&obj, cfg_path_name, cfg_section_name, - cfg_map_name, &prog_fd); + cfg_map_name, NULL, &prog_fd, NULL); if (ret) error(1, 0, "bpf_flow_load %s", cfg_path_name); diff --git a/tools/testing/selftests/bpf/flow_dissector_load.h b/tools/testing/selftests/bpf/flow_dissector_load.h index 41dd6959feb0..daeaeb518894 100644 --- a/tools/testing/selftests/bpf/flow_dissector_load.h +++ b/tools/testing/selftests/bpf/flow_dissector_load.h @@ -9,10 +9,12 @@ static inline int bpf_flow_load(struct bpf_object **obj, const char *path, const char *section_name, const char *map_name, - int *prog_fd) + const char *keys_map_name, + int *prog_fd, + int *keys_fd) { struct bpf_program *prog, *main_prog; - struct bpf_map *prog_array; + struct bpf_map *prog_array, *keys; int prog_array_fd; int ret, fd, i; @@ -23,19 +25,29 @@ static inline int bpf_flow_load(struct bpf_object **obj, main_prog = bpf_object__find_program_by_title(*obj, section_name); if (!main_prog) - return ret; + return -1; *prog_fd = bpf_program__fd(main_prog); if (*prog_fd < 0) - return ret; + return -1; prog_array = bpf_object__find_map_by_name(*obj, map_name); if (!prog_array) - return ret; + return -1; prog_array_fd = bpf_map__fd(prog_array); if (prog_array_fd < 0) - return ret; + return -1; + + if (keys_map_name && keys_fd) { + keys = bpf_object__find_map_by_name(*obj, keys_map_name); + if (!keys) + return -1; + + *keys_fd = bpf_map__fd(keys); + if (*keys_fd < 0) + return -1; + } i = 0; bpf_object__for_each_program(prog, *obj) { diff --git a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c new file mode 100644 index 000000000000..e569edc679d8 --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c @@ -0,0 +1,629 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include <linux/compiler.h> +#include <linux/err.h> + +#include <sys/resource.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <linux/btf.h> +#include <unistd.h> +#include <signal.h> +#include <errno.h> +#include <string.h> +#include <pthread.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include <test_btf.h> +#include <test_maps.h> + +static struct bpf_create_map_attr xattr = { + .name = "sk_storage_map", + .map_type = BPF_MAP_TYPE_SK_STORAGE, + .map_flags = BPF_F_NO_PREALLOC, + .max_entries = 0, + .key_size = 4, + .value_size = 8, + .btf_key_type_id = 1, + .btf_value_type_id = 3, + .btf_fd = -1, +}; + +static unsigned int nr_sk_threads_done; +static unsigned int nr_sk_threads_err; +static unsigned int nr_sk_per_thread = 4096; +static unsigned int nr_sk_threads = 4; +static int sk_storage_map = -1; +static unsigned int stop; +static int runtime_s = 5; + +static bool is_stopped(void) +{ + return READ_ONCE(stop); +} + +static unsigned int threads_err(void) +{ + return READ_ONCE(nr_sk_threads_err); +} + +static void notify_thread_err(void) +{ + __sync_add_and_fetch(&nr_sk_threads_err, 1); +} + +static bool wait_for_threads_err(void) +{ + while (!is_stopped() && !threads_err()) + usleep(500); + + return !is_stopped(); +} + +static unsigned int threads_done(void) +{ + return READ_ONCE(nr_sk_threads_done); +} + +static void notify_thread_done(void) +{ + __sync_add_and_fetch(&nr_sk_threads_done, 1); +} + +static void notify_thread_redo(void) +{ + __sync_sub_and_fetch(&nr_sk_threads_done, 1); +} + +static bool wait_for_threads_done(void) +{ + while (threads_done() != nr_sk_threads && !is_stopped() && + !threads_err()) + usleep(50); + + return !is_stopped() && !threads_err(); +} + +static bool wait_for_threads_redo(void) +{ + while (threads_done() && !is_stopped() && !threads_err()) + usleep(50); + + return !is_stopped() && !threads_err(); +} + +static bool wait_for_map(void) +{ + while (READ_ONCE(sk_storage_map) == -1 && !is_stopped()) + usleep(50); + + return !is_stopped(); +} + +static bool wait_for_map_close(void) +{ + while (READ_ONCE(sk_storage_map) != -1 && !is_stopped()) + ; + + return !is_stopped(); +} + +static int load_btf(void) +{ + const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l"; + __u32 btf_raw_types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct bpf_spin_lock */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4), + BTF_MEMBER_ENC(15, 1, 0), /* int val; */ + /* struct val */ /* [3] */ + BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ + BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + }; + struct btf_header btf_hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = sizeof(btf_raw_types), + .str_off = sizeof(btf_raw_types), + .str_len = sizeof(btf_str_sec), + }; + __u8 raw_btf[sizeof(struct btf_header) + sizeof(btf_raw_types) + + sizeof(btf_str_sec)]; + + memcpy(raw_btf, &btf_hdr, sizeof(btf_hdr)); + memcpy(raw_btf + sizeof(btf_hdr), btf_raw_types, sizeof(btf_raw_types)); + memcpy(raw_btf + sizeof(btf_hdr) + sizeof(btf_raw_types), + btf_str_sec, sizeof(btf_str_sec)); + + return bpf_load_btf(raw_btf, sizeof(raw_btf), 0, 0, 0); +} + +static int create_sk_storage_map(void) +{ + int btf_fd, map_fd; + + btf_fd = load_btf(); + CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n", + btf_fd, errno); + xattr.btf_fd = btf_fd; + + map_fd = bpf_create_map_xattr(&xattr); + xattr.btf_fd = -1; + close(btf_fd); + CHECK(map_fd == -1, + "bpf_create_map_xattr()", "errno:%d\n", errno); + + return map_fd; +} + +static void *insert_close_thread(void *arg) +{ + struct { + int cnt; + int lock; + } value = { .cnt = 0xeB9F, .lock = 0, }; + int i, map_fd, err, *sk_fds; + + sk_fds = malloc(sizeof(*sk_fds) * nr_sk_per_thread); + if (!sk_fds) { + notify_thread_err(); + return ERR_PTR(-ENOMEM); + } + + for (i = 0; i < nr_sk_per_thread; i++) + sk_fds[i] = -1; + + while (!is_stopped()) { + if (!wait_for_map()) + goto close_all; + + map_fd = READ_ONCE(sk_storage_map); + for (i = 0; i < nr_sk_per_thread && !is_stopped(); i++) { + sk_fds[i] = socket(AF_INET6, SOCK_STREAM, 0); + if (sk_fds[i] == -1) { + err = -errno; + fprintf(stderr, "socket(): errno:%d\n", errno); + goto errout; + } + err = bpf_map_update_elem(map_fd, &sk_fds[i], &value, + BPF_NOEXIST); + if (err) { + err = -errno; + fprintf(stderr, + "bpf_map_update_elem(): errno:%d\n", + errno); + goto errout; + } + } + + notify_thread_done(); + wait_for_map_close(); + +close_all: + for (i = 0; i < nr_sk_per_thread; i++) { + close(sk_fds[i]); + sk_fds[i] = -1; + } + + notify_thread_redo(); + } + + free(sk_fds); + return NULL; + +errout: + for (i = 0; i < nr_sk_per_thread && sk_fds[i] != -1; i++) + close(sk_fds[i]); + free(sk_fds); + notify_thread_err(); + return ERR_PTR(err); +} + +static int do_sk_storage_map_stress_free(void) +{ + int i, map_fd = -1, err = 0, nr_threads_created = 0; + pthread_t *sk_thread_ids; + void *thread_ret; + + sk_thread_ids = malloc(sizeof(pthread_t) * nr_sk_threads); + if (!sk_thread_ids) { + fprintf(stderr, "malloc(sk_threads): NULL\n"); + return -ENOMEM; + } + + for (i = 0; i < nr_sk_threads; i++) { + err = pthread_create(&sk_thread_ids[i], NULL, + insert_close_thread, NULL); + if (err) { + err = -errno; + goto done; + } + nr_threads_created++; + } + + while (!is_stopped()) { + map_fd = create_sk_storage_map(); + WRITE_ONCE(sk_storage_map, map_fd); + + if (!wait_for_threads_done()) + break; + + WRITE_ONCE(sk_storage_map, -1); + close(map_fd); + map_fd = -1; + + if (!wait_for_threads_redo()) + break; + } + +done: + WRITE_ONCE(stop, 1); + for (i = 0; i < nr_threads_created; i++) { + pthread_join(sk_thread_ids[i], &thread_ret); + if (IS_ERR(thread_ret) && !err) { + err = PTR_ERR(thread_ret); + fprintf(stderr, "threads#%u: err:%d\n", i, err); + } + } + free(sk_thread_ids); + + if (map_fd != -1) + close(map_fd); + + return err; +} + +static void *update_thread(void *arg) +{ + struct { + int cnt; + int lock; + } value = { .cnt = 0xeB9F, .lock = 0, }; + int map_fd = READ_ONCE(sk_storage_map); + int sk_fd = *(int *)arg; + int err = 0; /* Suppress compiler false alarm */ + + while (!is_stopped()) { + err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0); + if (err && errno != EAGAIN) { + err = -errno; + fprintf(stderr, "bpf_map_update_elem: %d %d\n", + err, errno); + break; + } + } + + if (!is_stopped()) { + notify_thread_err(); + return ERR_PTR(err); + } + + return NULL; +} + +static void *delete_thread(void *arg) +{ + int map_fd = READ_ONCE(sk_storage_map); + int sk_fd = *(int *)arg; + int err = 0; /* Suppress compiler false alarm */ + + while (!is_stopped()) { + err = bpf_map_delete_elem(map_fd, &sk_fd); + if (err && errno != ENOENT) { + err = -errno; + fprintf(stderr, "bpf_map_delete_elem: %d %d\n", + err, errno); + break; + } + } + + if (!is_stopped()) { + notify_thread_err(); + return ERR_PTR(err); + } + + return NULL; +} + +static int do_sk_storage_map_stress_change(void) +{ + int i, sk_fd, map_fd = -1, err = 0, nr_threads_created = 0; + pthread_t *sk_thread_ids; + void *thread_ret; + + sk_thread_ids = malloc(sizeof(pthread_t) * nr_sk_threads); + if (!sk_thread_ids) { + fprintf(stderr, "malloc(sk_threads): NULL\n"); + return -ENOMEM; + } + + sk_fd = socket(AF_INET6, SOCK_STREAM, 0); + if (sk_fd == -1) { + err = -errno; + goto done; + } + + map_fd = create_sk_storage_map(); + WRITE_ONCE(sk_storage_map, map_fd); + + for (i = 0; i < nr_sk_threads; i++) { + if (i & 0x1) + err = pthread_create(&sk_thread_ids[i], NULL, + update_thread, &sk_fd); + else + err = pthread_create(&sk_thread_ids[i], NULL, + delete_thread, &sk_fd); + if (err) { + err = -errno; + goto done; + } + nr_threads_created++; + } + + wait_for_threads_err(); + +done: + WRITE_ONCE(stop, 1); + for (i = 0; i < nr_threads_created; i++) { + pthread_join(sk_thread_ids[i], &thread_ret); + if (IS_ERR(thread_ret) && !err) { + err = PTR_ERR(thread_ret); + fprintf(stderr, "threads#%u: err:%d\n", i, err); + } + } + free(sk_thread_ids); + + if (sk_fd != -1) + close(sk_fd); + close(map_fd); + + return err; +} + +static void stop_handler(int signum) +{ + if (signum != SIGALRM) + printf("stopping...\n"); + WRITE_ONCE(stop, 1); +} + +#define BPF_SK_STORAGE_MAP_TEST_NR_THREADS "BPF_SK_STORAGE_MAP_TEST_NR_THREADS" +#define BPF_SK_STORAGE_MAP_TEST_SK_PER_THREAD "BPF_SK_STORAGE_MAP_TEST_SK_PER_THREAD" +#define BPF_SK_STORAGE_MAP_TEST_RUNTIME_S "BPF_SK_STORAGE_MAP_TEST_RUNTIME_S" +#define BPF_SK_STORAGE_MAP_TEST_NAME "BPF_SK_STORAGE_MAP_TEST_NAME" + +static void test_sk_storage_map_stress_free(void) +{ + struct rlimit rlim_old, rlim_new = {}; + int err; + + getrlimit(RLIMIT_NOFILE, &rlim_old); + + signal(SIGTERM, stop_handler); + signal(SIGINT, stop_handler); + if (runtime_s > 0) { + signal(SIGALRM, stop_handler); + alarm(runtime_s); + } + + if (rlim_old.rlim_cur < nr_sk_threads * nr_sk_per_thread) { + rlim_new.rlim_cur = nr_sk_threads * nr_sk_per_thread + 128; + rlim_new.rlim_max = rlim_new.rlim_cur + 128; + err = setrlimit(RLIMIT_NOFILE, &rlim_new); + CHECK(err, "setrlimit(RLIMIT_NOFILE)", "rlim_new:%lu errno:%d", + rlim_new.rlim_cur, errno); + } + + err = do_sk_storage_map_stress_free(); + + signal(SIGTERM, SIG_DFL); + signal(SIGINT, SIG_DFL); + if (runtime_s > 0) { + signal(SIGALRM, SIG_DFL); + alarm(0); + } + + if (rlim_new.rlim_cur) + setrlimit(RLIMIT_NOFILE, &rlim_old); + + CHECK(err, "test_sk_storage_map_stress_free", "err:%d\n", err); +} + +static void test_sk_storage_map_stress_change(void) +{ + int err; + + signal(SIGTERM, stop_handler); + signal(SIGINT, stop_handler); + if (runtime_s > 0) { + signal(SIGALRM, stop_handler); + alarm(runtime_s); + } + + err = do_sk_storage_map_stress_change(); + + signal(SIGTERM, SIG_DFL); + signal(SIGINT, SIG_DFL); + if (runtime_s > 0) { + signal(SIGALRM, SIG_DFL); + alarm(0); + } + + CHECK(err, "test_sk_storage_map_stress_change", "err:%d\n", err); +} + +static void test_sk_storage_map_basic(void) +{ + struct { + int cnt; + int lock; + } value = { .cnt = 0xeB9f, .lock = 0, }, lookup_value; + struct bpf_create_map_attr bad_xattr; + int btf_fd, map_fd, sk_fd, err; + + btf_fd = load_btf(); + CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n", + btf_fd, errno); + xattr.btf_fd = btf_fd; + + sk_fd = socket(AF_INET6, SOCK_STREAM, 0); + CHECK(sk_fd == -1, "socket()", "sk_fd:%d errno:%d\n", + sk_fd, errno); + + map_fd = bpf_create_map_xattr(&xattr); + CHECK(map_fd == -1, "bpf_create_map_xattr(good_xattr)", + "map_fd:%d errno:%d\n", map_fd, errno); + + /* Add new elem */ + memcpy(&lookup_value, &value, sizeof(value)); + err = bpf_map_update_elem(map_fd, &sk_fd, &value, + BPF_NOEXIST | BPF_F_LOCK); + CHECK(err, "bpf_map_update_elem(BPF_NOEXIST|BPF_F_LOCK)", + "err:%d errno:%d\n", err, errno); + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(err || lookup_value.cnt != value.cnt, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d cnt:%x(%x)\n", + err, errno, lookup_value.cnt, value.cnt); + + /* Bump the cnt and update with BPF_EXIST | BPF_F_LOCK */ + value.cnt += 1; + err = bpf_map_update_elem(map_fd, &sk_fd, &value, + BPF_EXIST | BPF_F_LOCK); + CHECK(err, "bpf_map_update_elem(BPF_EXIST|BPF_F_LOCK)", + "err:%d errno:%d\n", err, errno); + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(err || lookup_value.cnt != value.cnt, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d cnt:%x(%x)\n", + err, errno, lookup_value.cnt, value.cnt); + + /* Bump the cnt and update with BPF_EXIST */ + value.cnt += 1; + err = bpf_map_update_elem(map_fd, &sk_fd, &value, BPF_EXIST); + CHECK(err, "bpf_map_update_elem(BPF_EXIST)", + "err:%d errno:%d\n", err, errno); + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(err || lookup_value.cnt != value.cnt, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d cnt:%x(%x)\n", + err, errno, lookup_value.cnt, value.cnt); + + /* Update with BPF_NOEXIST */ + value.cnt += 1; + err = bpf_map_update_elem(map_fd, &sk_fd, &value, + BPF_NOEXIST | BPF_F_LOCK); + CHECK(!err || errno != EEXIST, + "bpf_map_update_elem(BPF_NOEXIST|BPF_F_LOCK)", + "err:%d errno:%d\n", err, errno); + err = bpf_map_update_elem(map_fd, &sk_fd, &value, BPF_NOEXIST); + CHECK(!err || errno != EEXIST, "bpf_map_update_elem(BPF_NOEXIST)", + "err:%d errno:%d\n", err, errno); + value.cnt -= 1; + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(err || lookup_value.cnt != value.cnt, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d cnt:%x(%x)\n", + err, errno, lookup_value.cnt, value.cnt); + + /* Bump the cnt again and update with map_flags == 0 */ + value.cnt += 1; + err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0); + CHECK(err, "bpf_map_update_elem()", "err:%d errno:%d\n", + err, errno); + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(err || lookup_value.cnt != value.cnt, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d cnt:%x(%x)\n", + err, errno, lookup_value.cnt, value.cnt); + + /* Test delete elem */ + err = bpf_map_delete_elem(map_fd, &sk_fd); + CHECK(err, "bpf_map_delete_elem()", "err:%d errno:%d\n", + err, errno); + err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value, + BPF_F_LOCK); + CHECK(!err || errno != ENOENT, + "bpf_map_lookup_elem_flags(BPF_F_LOCK)", + "err:%d errno:%d\n", err, errno); + err = bpf_map_delete_elem(map_fd, &sk_fd); + CHECK(!err || errno != ENOENT, "bpf_map_delete_elem()", + "err:%d errno:%d\n", err, errno); + + memcpy(&bad_xattr, &xattr, sizeof(xattr)); + bad_xattr.btf_key_type_id = 0; + err = bpf_create_map_xattr(&bad_xattr); + CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + "err:%d errno:%d\n", err, errno); + + memcpy(&bad_xattr, &xattr, sizeof(xattr)); + bad_xattr.btf_key_type_id = 3; + err = bpf_create_map_xattr(&bad_xattr); + CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + "err:%d errno:%d\n", err, errno); + + memcpy(&bad_xattr, &xattr, sizeof(xattr)); + bad_xattr.max_entries = 1; + err = bpf_create_map_xattr(&bad_xattr); + CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + "err:%d errno:%d\n", err, errno); + + memcpy(&bad_xattr, &xattr, sizeof(xattr)); + bad_xattr.map_flags = 0; + err = bpf_create_map_xattr(&bad_xattr); + CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + "err:%d errno:%d\n", err, errno); + + xattr.btf_fd = -1; + close(btf_fd); + close(map_fd); + close(sk_fd); +} + +void test_sk_storage_map(void) +{ + const char *test_name, *env_opt; + bool test_ran = false; + + test_name = getenv(BPF_SK_STORAGE_MAP_TEST_NAME); + + env_opt = getenv(BPF_SK_STORAGE_MAP_TEST_NR_THREADS); + if (env_opt) + nr_sk_threads = atoi(env_opt); + + env_opt = getenv(BPF_SK_STORAGE_MAP_TEST_SK_PER_THREAD); + if (env_opt) + nr_sk_per_thread = atoi(env_opt); + + env_opt = getenv(BPF_SK_STORAGE_MAP_TEST_RUNTIME_S); + if (env_opt) + runtime_s = atoi(env_opt); + + if (!test_name || !strcmp(test_name, "basic")) { + test_sk_storage_map_basic(); + test_ran = true; + } + if (!test_name || !strcmp(test_name, "stress_free")) { + test_sk_storage_map_stress_free(); + test_ran = true; + } + if (!test_name || !strcmp(test_name, "stress_change")) { + test_sk_storage_map_stress_change(); + test_ran = true; + } + + if (test_ran) + printf("%s:PASS\n", __func__); + else + CHECK(1, "Invalid test_name", "%s\n", test_name); +} diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 126319f9a97c..8b54adfd6264 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <error.h> +#include <linux/if.h> +#include <linux/if_tun.h> #define CHECK_FLOW_KEYS(desc, got, expected) \ CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0, \ @@ -79,8 +82,8 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = 0, - .thoff = sizeof(struct iphdr), + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr), .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP), @@ -95,8 +98,8 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = 0, - .thoff = sizeof(struct ipv6hdr), + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct ipv6hdr), .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6), @@ -113,8 +116,8 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = VLAN_HLEN, - .thoff = VLAN_HLEN + sizeof(struct iphdr), + .nhoff = ETH_HLEN + VLAN_HLEN, + .thoff = ETH_HLEN + VLAN_HLEN + sizeof(struct iphdr), .addr_proto = ETH_P_IP, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IP), @@ -131,8 +134,9 @@ struct test tests[] = { .tcp.doff = 5, }, .keys = { - .nhoff = VLAN_HLEN * 2, - .thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr), + .nhoff = ETH_HLEN + VLAN_HLEN * 2, + .thoff = ETH_HLEN + VLAN_HLEN * 2 + + sizeof(struct ipv6hdr), .addr_proto = ETH_P_IPV6, .ip_proto = IPPROTO_TCP, .n_proto = __bpf_constant_htons(ETH_P_IPV6), @@ -140,13 +144,73 @@ struct test tests[] = { }, }; +static int create_tap(const char *ifname) +{ + struct ifreq ifr = { + .ifr_flags = IFF_TAP | IFF_NO_PI | IFF_NAPI | IFF_NAPI_FRAGS, + }; + int fd, ret; + + strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name)); + + fd = open("/dev/net/tun", O_RDWR); + if (fd < 0) + return -1; + + ret = ioctl(fd, TUNSETIFF, &ifr); + if (ret) + return -1; + + return fd; +} + +static int tx_tap(int fd, void *pkt, size_t len) +{ + struct iovec iov[] = { + { + .iov_len = len, + .iov_base = pkt, + }, + }; + return writev(fd, iov, ARRAY_SIZE(iov)); +} + +static int ifup(const char *ifname) +{ + struct ifreq ifr = {}; + int sk, ret; + + strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name)); + + sk = socket(PF_INET, SOCK_DGRAM, 0); + if (sk < 0) + return -1; + + ret = ioctl(sk, SIOCGIFFLAGS, &ifr); + if (ret) { + close(sk); + return -1; + } + + ifr.ifr_flags |= IFF_UP; + ret = ioctl(sk, SIOCSIFFLAGS, &ifr); + if (ret) { + close(sk); + return -1; + } + + close(sk); + return 0; +} + void test_flow_dissector(void) { + int i, err, prog_fd, keys_fd = -1, tap_fd; struct bpf_object *obj; - int i, err, prog_fd; + __u32 duration = 0; err = bpf_flow_load(&obj, "./bpf_flow.o", "flow_dissector", - "jmp_table", &prog_fd); + "jmp_table", "last_dissection", &prog_fd, &keys_fd); if (err) { error_cnt++; return; @@ -171,5 +235,34 @@ void test_flow_dissector(void) CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); } + /* Do the same tests but for skb-less flow dissector. + * We use a known path in the net/tun driver that calls + * eth_get_headlen and we manually export bpf_flow_keys + * via BPF map in this case. + */ + + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + CHECK(err, "bpf_prog_attach", "err %d errno %d", err, errno); + + tap_fd = create_tap("tap0"); + CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d", tap_fd, errno); + err = ifup("tap0"); + CHECK(err, "ifup", "err %d errno %d", err, errno); + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + struct bpf_flow_keys flow_keys = {}; + struct bpf_prog_test_run_attr tattr = {}; + __u32 key = 0; + + err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt)); + CHECK(err < 0, "tx_tap", "err %d errno %d", err, errno); + + err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys); + CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err); + + CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err); + CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + } + bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c new file mode 100644 index 000000000000..dc5ef155ec28 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> + +void test_flow_dissector_load_bytes(void) +{ + struct bpf_flow_keys flow_keys; + __u32 duration = 0, retval, size; + struct bpf_insn prog[] = { + // BPF_REG_1 - 1st argument: context + // BPF_REG_2 - 2nd argument: offset, start at first byte + BPF_MOV64_IMM(BPF_REG_2, 0), + // BPF_REG_3 - 3rd argument: destination, reserve byte on stack + BPF_ALU64_REG(BPF_MOV, BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -1), + // BPF_REG_4 - 4th argument: copy one byte + BPF_MOV64_IMM(BPF_REG_4, 1), + // bpf_skb_load_bytes(ctx, sizeof(pkt_v4), ptr, 1) + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + // if (ret == 0) return BPF_DROP (2) + BPF_MOV64_IMM(BPF_REG_0, BPF_DROP), + BPF_EXIT_INSN(), + // if (ret != 0) return BPF_OK (0) + BPF_MOV64_IMM(BPF_REG_0, BPF_OK), + BPF_EXIT_INSN(), + }; + int fd, err; + + /* make sure bpf_skb_load_bytes is not allowed from skb-less context + */ + fd = bpf_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog, + ARRAY_SIZE(prog), "GPL", 0, NULL, 0); + CHECK(fd < 0, + "flow_dissector-bpf_skb_load_bytes-load", + "fd %d errno %d\n", + fd, errno); + + err = bpf_prog_test_run(fd, 1, &pkt_v4, sizeof(pkt_v4), + &flow_keys, &size, &retval, &duration); + CHECK(size != sizeof(flow_keys) || err || retval != 1, + "flow_dissector-bpf_skb_load_bytes", + "err %d errno %d retval %d duration %d size %u/%zu\n", + err, errno, retval, duration, size, sizeof(flow_keys)); + + if (fd >= -1) + close(fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c new file mode 100644 index 000000000000..9807336a3016 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <linux/nbd.h> + +void test_raw_tp_writable_reject_nbd_invalid(void) +{ + __u32 duration = 0; + char error[4096]; + int bpf_fd = -1, tp_fd = -1; + + const struct bpf_insn program[] = { + /* r6 is our tp buffer */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + /* one byte beyond the end of the nbd_request struct */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, + sizeof(struct nbd_request)), + BPF_EXIT_INSN(), + }; + + struct bpf_load_program_attr load_attr = { + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + .license = "GPL v2", + .insns = program, + .insns_cnt = sizeof(program) / sizeof(struct bpf_insn), + .log_level = 2, + }; + + bpf_fd = bpf_load_program_xattr(&load_attr, error, sizeof(error)); + if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable load", + "failed: %d errno %d\n", bpf_fd, errno)) + return; + + tp_fd = bpf_raw_tracepoint_open("nbd_send_request", bpf_fd); + if (CHECK(tp_fd >= 0, "bpf_raw_tracepoint_writable open", + "erroneously succeeded\n")) + goto out_bpffd; + + close(tp_fd); +out_bpffd: + close(bpf_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c new file mode 100644 index 000000000000..5c45424cac5f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c @@ -0,0 +1,80 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <linux/nbd.h> + +void test_raw_tp_writable_test_run(void) +{ + __u32 duration = 0; + char error[4096]; + + const struct bpf_insn trace_program[] = { + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + + struct bpf_load_program_attr load_attr = { + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + .license = "GPL v2", + .insns = trace_program, + .insns_cnt = sizeof(trace_program) / sizeof(struct bpf_insn), + .log_level = 2, + }; + + int bpf_fd = bpf_load_program_xattr(&load_attr, error, sizeof(error)); + if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable loaded", + "failed: %d errno %d\n", bpf_fd, errno)) + return; + + const struct bpf_insn skb_program[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + + struct bpf_load_program_attr skb_load_attr = { + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .license = "GPL v2", + .insns = skb_program, + .insns_cnt = sizeof(skb_program) / sizeof(struct bpf_insn), + }; + + int filter_fd = + bpf_load_program_xattr(&skb_load_attr, error, sizeof(error)); + if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n", + filter_fd, errno)) + goto out_bpffd; + + int tp_fd = bpf_raw_tracepoint_open("bpf_test_finish", bpf_fd); + if (CHECK(tp_fd < 0, "bpf_raw_tracepoint_writable opened", + "failed: %d errno %d\n", tp_fd, errno)) + goto out_filterfd; + + char test_skb[128] = { + 0, + }; + + __u32 prog_ret; + int err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, + 0, &prog_ret, 0); + CHECK(err != 42, "test_run", + "tracepoint did not modify return value\n"); + CHECK(prog_ret != 0, "test_run_ret", + "socket_filter did not return 0\n"); + + close(tp_fd); + + err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, 0, + &prog_ret, 0); + CHECK(err != 0, "test_run_notrace", + "test_run failed with %d errno %d\n", err, errno); + CHECK(prog_ret != 0, "test_run_ret_notrace", + "socket_filter did not return 0\n"); + +out_filterfd: + close(filter_fd); +out_bpffd: + close(bpf_fd); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 75b17cada539..81ad9a0b29d0 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -64,6 +64,25 @@ struct bpf_map_def SEC("maps") jmp_table = { .max_entries = 8 }; +struct bpf_map_def SEC("maps") last_dissection = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct bpf_flow_keys), + .max_entries = 1, +}; + +static __always_inline int export_flow_keys(struct bpf_flow_keys *keys, + int ret) +{ + struct bpf_flow_keys *val; + __u32 key = 0; + + val = bpf_map_lookup_elem(&last_dissection, &key); + if (val) + memcpy(val, keys, sizeof(*val)); + return ret; +} + static __always_inline void *bpf_flow_dissect_get_header(struct __sk_buff *skb, __u16 hdr_size, void *buffer) @@ -109,10 +128,10 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto) break; default: /* Protocol not supported */ - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); } - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); } SEC("flow_dissector") @@ -139,8 +158,8 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) case IPPROTO_ICMP: icmp = bpf_flow_dissect_get_header(skb, sizeof(*icmp), &_icmp); if (!icmp) - return BPF_DROP; - return BPF_OK; + return export_flow_keys(keys, BPF_DROP); + return export_flow_keys(keys, BPF_OK); case IPPROTO_IPIP: keys->is_encap = true; return parse_eth_proto(skb, bpf_htons(ETH_P_IP)); @@ -150,11 +169,11 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) case IPPROTO_GRE: gre = bpf_flow_dissect_get_header(skb, sizeof(*gre), &_gre); if (!gre) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); if (bpf_htons(gre->flags & GRE_VERSION)) /* Only inspect standard GRE packets with version 0 */ - return BPF_OK; + return export_flow_keys(keys, BPF_OK); keys->thoff += sizeof(*gre); /* Step over GRE Flags and Proto */ if (GRE_IS_CSUM(gre->flags)) @@ -170,7 +189,7 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) eth = bpf_flow_dissect_get_header(skb, sizeof(*eth), &_eth); if (!eth) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->thoff += sizeof(*eth); @@ -181,31 +200,31 @@ static __always_inline int parse_ip_proto(struct __sk_buff *skb, __u8 proto) case IPPROTO_TCP: tcp = bpf_flow_dissect_get_header(skb, sizeof(*tcp), &_tcp); if (!tcp) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); if (tcp->doff < 5) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); if ((__u8 *)tcp + (tcp->doff << 2) > data_end) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->sport = tcp->source; keys->dport = tcp->dest; - return BPF_OK; + return export_flow_keys(keys, BPF_OK); case IPPROTO_UDP: case IPPROTO_UDPLITE: udp = bpf_flow_dissect_get_header(skb, sizeof(*udp), &_udp); if (!udp) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->sport = udp->source; keys->dport = udp->dest; - return BPF_OK; + return export_flow_keys(keys, BPF_OK); default: - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); } - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); } static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr) @@ -225,7 +244,7 @@ static __always_inline int parse_ipv6_proto(struct __sk_buff *skb, __u8 nexthdr) return parse_ip_proto(skb, nexthdr); } - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); } PROG(IP)(struct __sk_buff *skb) @@ -238,11 +257,11 @@ PROG(IP)(struct __sk_buff *skb) iph = bpf_flow_dissect_get_header(skb, sizeof(*iph), &_iph); if (!iph) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); /* IP header cannot be smaller than 20 bytes */ if (iph->ihl < 5) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->addr_proto = ETH_P_IP; keys->ipv4_src = iph->saddr; @@ -250,7 +269,7 @@ PROG(IP)(struct __sk_buff *skb) keys->thoff += iph->ihl << 2; if (data + keys->thoff > data_end) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET)) { keys->is_frag = true; @@ -264,7 +283,7 @@ PROG(IP)(struct __sk_buff *skb) } if (done) - return BPF_OK; + return export_flow_keys(keys, BPF_OK); return parse_ip_proto(skb, iph->protocol); } @@ -276,7 +295,7 @@ PROG(IPV6)(struct __sk_buff *skb) ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h); if (!ip6h) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->addr_proto = ETH_P_IPV6; memcpy(&keys->ipv6_src, &ip6h->saddr, 2*sizeof(ip6h->saddr)); @@ -288,11 +307,12 @@ PROG(IPV6)(struct __sk_buff *skb) PROG(IPV6OP)(struct __sk_buff *skb) { + struct bpf_flow_keys *keys = skb->flow_keys; struct ipv6_opt_hdr *ip6h, _ip6h; ip6h = bpf_flow_dissect_get_header(skb, sizeof(*ip6h), &_ip6h); if (!ip6h) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); /* hlen is in 8-octets and does not include the first 8 bytes * of the header @@ -309,7 +329,7 @@ PROG(IPV6FR)(struct __sk_buff *skb) fragh = bpf_flow_dissect_get_header(skb, sizeof(*fragh), &_fragh); if (!fragh) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->thoff += sizeof(*fragh); keys->is_frag = true; @@ -321,13 +341,14 @@ PROG(IPV6FR)(struct __sk_buff *skb) PROG(MPLS)(struct __sk_buff *skb) { + struct bpf_flow_keys *keys = skb->flow_keys; struct mpls_label *mpls, _mpls; mpls = bpf_flow_dissect_get_header(skb, sizeof(*mpls), &_mpls); if (!mpls) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); - return BPF_OK; + return export_flow_keys(keys, BPF_OK); } PROG(VLAN)(struct __sk_buff *skb) @@ -339,10 +360,10 @@ PROG(VLAN)(struct __sk_buff *skb) if (keys->n_proto == bpf_htons(ETH_P_8021AD)) { vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan); if (!vlan) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q)) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->nhoff += sizeof(*vlan); keys->thoff += sizeof(*vlan); @@ -350,14 +371,14 @@ PROG(VLAN)(struct __sk_buff *skb) vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan); if (!vlan) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->nhoff += sizeof(*vlan); keys->thoff += sizeof(*vlan); /* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/ if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) || vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q)) - return BPF_DROP; + return export_flow_keys(keys, BPF_DROP); keys->n_proto = vlan->h_vlan_encapsulated_proto; return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto); diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c index 37328f148538..1c39e4ccb7f1 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c @@ -55,6 +55,31 @@ struct bpf_map_def SEC("maps") linum_map = { .max_entries = __NR_BPF_LINUM_ARRAY_IDX, }; +struct bpf_spinlock_cnt { + struct bpf_spin_lock lock; + __u32 cnt; +}; + +struct bpf_map_def SEC("maps") sk_pkt_out_cnt = { + .type = BPF_MAP_TYPE_SK_STORAGE, + .key_size = sizeof(int), + .value_size = sizeof(struct bpf_spinlock_cnt), + .max_entries = 0, + .map_flags = BPF_F_NO_PREALLOC, +}; + +BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt, int, struct bpf_spinlock_cnt); + +struct bpf_map_def SEC("maps") sk_pkt_out_cnt10 = { + .type = BPF_MAP_TYPE_SK_STORAGE, + .key_size = sizeof(int), + .value_size = sizeof(struct bpf_spinlock_cnt), + .max_entries = 0, + .map_flags = BPF_F_NO_PREALLOC, +}; + +BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt10, int, struct bpf_spinlock_cnt); + static bool is_loopback6(__u32 *a6) { return !a6[0] && !a6[1] && !a6[2] && a6[3] == bpf_htonl(1); @@ -120,7 +145,9 @@ static void tpcpy(struct bpf_tcp_sock *dst, SEC("cgroup_skb/egress") int egress_read_sock_fields(struct __sk_buff *skb) { + struct bpf_spinlock_cnt cli_cnt_init = { .lock = 0, .cnt = 0xeB9F }; __u32 srv_idx = ADDR_SRV_IDX, cli_idx = ADDR_CLI_IDX, result_idx; + struct bpf_spinlock_cnt *pkt_out_cnt, *pkt_out_cnt10; struct sockaddr_in6 *srv_sa6, *cli_sa6; struct bpf_tcp_sock *tp, *tp_ret; struct bpf_sock *sk, *sk_ret; @@ -161,6 +188,32 @@ int egress_read_sock_fields(struct __sk_buff *skb) skcpy(sk_ret, sk); tpcpy(tp_ret, tp); + if (result_idx == EGRESS_SRV_IDX) { + /* The userspace has created it for srv sk */ + pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, sk, 0, 0); + pkt_out_cnt10 = bpf_sk_storage_get(&sk_pkt_out_cnt10, sk, + 0, 0); + } else { + pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, sk, + &cli_cnt_init, + BPF_SK_STORAGE_GET_F_CREATE); + pkt_out_cnt10 = bpf_sk_storage_get(&sk_pkt_out_cnt10, + sk, &cli_cnt_init, + BPF_SK_STORAGE_GET_F_CREATE); + } + + if (!pkt_out_cnt || !pkt_out_cnt10) + RETURN; + + /* Even both cnt and cnt10 have lock defined in their BTF, + * intentionally one cnt takes lock while one does not + * as a test for the spinlock support in BPF_MAP_TYPE_SK_STORAGE. + */ + pkt_out_cnt->cnt += 1; + bpf_spin_lock(&pkt_out_cnt10->lock); + pkt_out_cnt10->cnt += 10; + bpf_spin_unlock(&pkt_out_cnt10->lock); + RETURN; } diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c index ab56a6a72b7a..74370e7e286d 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -77,17 +77,52 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, struct v4hdr h_outer; struct tcphdr tcph; int olen, l2_len; + int tcp_off; __u64 flags; - if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, - sizeof(iph_inner)) < 0) - return TC_ACT_OK; + /* Most tests encapsulate a packet into a tunnel with the same + * network protocol, and derive the outer header fields from + * the inner header. + * + * The 6in4 case tests different inner and outer protocols. As + * the inner is ipv6, but the outer expects an ipv4 header as + * input, manually build a struct iphdr based on the ipv6hdr. + */ + if (encap_proto == IPPROTO_IPV6) { + const __u32 saddr = (192 << 24) | (168 << 16) | (1 << 8) | 1; + const __u32 daddr = (192 << 24) | (168 << 16) | (1 << 8) | 2; + struct ipv6hdr iph6_inner; + + /* Read the IPv6 header */ + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph6_inner, + sizeof(iph6_inner)) < 0) + return TC_ACT_OK; + + /* Derive the IPv4 header fields from the IPv6 header */ + memset(&iph_inner, 0, sizeof(iph_inner)); + iph_inner.version = 4; + iph_inner.ihl = 5; + iph_inner.tot_len = bpf_htons(sizeof(iph6_inner) + + bpf_ntohs(iph6_inner.payload_len)); + iph_inner.ttl = iph6_inner.hop_limit - 1; + iph_inner.protocol = iph6_inner.nexthdr; + iph_inner.saddr = __bpf_constant_htonl(saddr); + iph_inner.daddr = __bpf_constant_htonl(daddr); + + tcp_off = sizeof(iph6_inner); + } else { + if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner, + sizeof(iph_inner)) < 0) + return TC_ACT_OK; + + tcp_off = sizeof(iph_inner); + } /* filter only packets we want */ if (iph_inner.ihl != 5 || iph_inner.protocol != IPPROTO_TCP) return TC_ACT_OK; - if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(iph_inner), + if (bpf_skb_load_bytes(skb, ETH_HLEN + tcp_off, &tcph, sizeof(tcph)) < 0) return TC_ACT_OK; @@ -129,6 +164,7 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, l2_len); break; case IPPROTO_IPIP: + case IPPROTO_IPV6: break; default: return TC_ACT_OK; @@ -164,6 +200,17 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, BPF_F_INVALIDATE_HASH) < 0) return TC_ACT_SHOT; + /* if changing outer proto type, update eth->h_proto */ + if (encap_proto == IPPROTO_IPV6) { + struct ethhdr eth; + + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth)) < 0) + return TC_ACT_SHOT; + eth.h_proto = bpf_htons(ETH_P_IP); + if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0) < 0) + return TC_ACT_SHOT; + } + return TC_ACT_OK; } @@ -325,6 +372,15 @@ int __encap_udp_eth(struct __sk_buff *skb) return TC_ACT_OK; } +SEC("encap_sit_none") +int __encap_sit_none(struct __sk_buff *skb) +{ + if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) + return encap_ipv4(skb, IPPROTO_IPV6, ETH_P_IP); + else + return TC_ACT_OK; +} + SEC("encap_ip6tnl_none") int __encap_ip6tnl_none(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index f8eb7987b794..42c1ce988945 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -24,6 +24,7 @@ #include "bpf_rlimit.h" #include "bpf_util.h" +#include "test_btf.h" #define MAX_INSNS 512 #define MAX_SUBPROGS 16 @@ -58,68 +59,6 @@ static int __base_pr(enum libbpf_print_level level __attribute__((unused)), return vfprintf(stderr, format, args); } -#define BTF_INFO_ENC(kind, kind_flag, vlen) \ - ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) - -#define BTF_TYPE_ENC(name, info, size_or_type) \ - (name), (info), (size_or_type) - -#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ - ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) -#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ - BTF_INT_ENC(encoding, bits_offset, bits) - -#define BTF_FWD_ENC(name, kind_flag) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FWD, kind_flag, 0), 0) - -#define BTF_ARRAY_ENC(type, index_type, nr_elems) \ - (type), (index_type), (nr_elems) -#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \ - BTF_ARRAY_ENC(type, index_type, nr_elems) - -#define BTF_STRUCT_ENC(name, nr_elems, sz) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, nr_elems), sz) - -#define BTF_UNION_ENC(name, nr_elems, sz) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz) - -#define BTF_VAR_ENC(name, type, linkage) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), type), (linkage) -#define BTF_VAR_SECINFO_ENC(type, offset, size) \ - (type), (offset), (size) - -#define BTF_MEMBER_ENC(name, type, bits_offset) \ - (name), (type), (bits_offset) -#define BTF_ENUM_ENC(name, val) (name), (val) -#define BTF_MEMBER_OFFSET(bitfield_size, bits_offset) \ - ((bitfield_size) << 24 | (bits_offset)) - -#define BTF_TYPEDEF_ENC(name, type) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type) - -#define BTF_PTR_ENC(type) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type) - -#define BTF_CONST_ENC(type) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type) - -#define BTF_VOLATILE_ENC(type) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), type) - -#define BTF_RESTRICT_ENC(type) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_RESTRICT, 0, 0), type) - -#define BTF_FUNC_PROTO_ENC(ret_type, nargs) \ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type) - -#define BTF_FUNC_PROTO_ARG_ENC(name, type) \ - (name), (type) - -#define BTF_FUNC_ENC(name, func_proto) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto) - #define BTF_END_RAW 0xdeadbeef #define NAME_TBD 0xdeadb33f diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h new file mode 100644 index 000000000000..2023725f1962 --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Facebook */ + +#ifndef _TEST_BTF_H +#define _TEST_BTF_H + +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) + +#define BTF_TYPE_ENC(name, info, size_or_type) \ + (name), (info), (size_or_type) + +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) + +#define BTF_FWD_ENC(name, kind_flag) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FWD, kind_flag, 0), 0) + +#define BTF_ARRAY_ENC(type, index_type, nr_elems) \ + (type), (index_type), (nr_elems) +#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \ + BTF_ARRAY_ENC(type, index_type, nr_elems) + +#define BTF_STRUCT_ENC(name, nr_elems, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, nr_elems), sz) + +#define BTF_UNION_ENC(name, nr_elems, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz) + +#define BTF_VAR_ENC(name, type, linkage) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), type), (linkage) +#define BTF_VAR_SECINFO_ENC(type, offset, size) \ + (type), (offset), (size) + +#define BTF_MEMBER_ENC(name, type, bits_offset) \ + (name), (type), (bits_offset) +#define BTF_ENUM_ENC(name, val) (name), (val) +#define BTF_MEMBER_OFFSET(bitfield_size, bits_offset) \ + ((bitfield_size) << 24 | (bits_offset)) + +#define BTF_TYPEDEF_ENC(name, type) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type) + +#define BTF_PTR_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type) + +#define BTF_CONST_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type) + +#define BTF_VOLATILE_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), type) + +#define BTF_RESTRICT_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_RESTRICT, 0, 0), type) + +#define BTF_FUNC_PROTO_ENC(ret_type, nargs) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type) + +#define BTF_FUNC_PROTO_ARG_ENC(name, type) \ + (name), (type) + +#define BTF_FUNC_ENC(name, func_proto) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto) + +#endif /* _TEST_BTF_H */ diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 3c627771f965..246f745cb006 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -27,6 +27,7 @@ #include "bpf_util.h" #include "bpf_rlimit.h" +#include "test_maps.h" #ifndef ENOTSUPP #define ENOTSUPP 524 @@ -36,15 +37,6 @@ static int skips; static int map_flags; -#define CHECK(condition, tag, format...) ({ \ - int __ret = !!(condition); \ - if (__ret) { \ - printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag); \ - printf(format); \ - exit(-1); \ - } \ -}) - static void test_hashmap(unsigned int task, void *data) { long long key, next_key, first_key, value; @@ -1703,6 +1695,10 @@ static void run_all_tests(void) test_map_in_map(); } +#define DECLARE +#include <map_tests/tests.h> +#undef DECLARE + int main(void) { srand(time(NULL)); @@ -1713,6 +1709,10 @@ int main(void) map_flags = BPF_F_NO_PREALLOC; run_all_tests(); +#define CALL +#include <map_tests/tests.h> +#undef CALL + printf("test_maps: OK, %d SKIPPED\n", skips); return 0; } diff --git a/tools/testing/selftests/bpf/test_maps.h b/tools/testing/selftests/bpf/test_maps.h new file mode 100644 index 000000000000..77d8587ac4ed --- /dev/null +++ b/tools/testing/selftests/bpf/test_maps.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TEST_MAPS_H +#define _TEST_MAPS_H + +#include <stdio.h> +#include <stdlib.h> + +#define CHECK(condition, tag, format...) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag); \ + printf(format); \ + exit(-1); \ + } \ +}) + +#endif diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c index dcae7f664dce..e089477fa0a3 100644 --- a/tools/testing/selftests/bpf/test_sock_fields.c +++ b/tools/testing/selftests/bpf/test_sock_fields.c @@ -35,6 +35,11 @@ enum bpf_linum_array_idx { __NR_BPF_LINUM_ARRAY_IDX, }; +struct bpf_spinlock_cnt { + struct bpf_spin_lock lock; + __u32 cnt; +}; + #define CHECK(condition, tag, format...) ({ \ int __ret = !!(condition); \ if (__ret) { \ @@ -50,6 +55,8 @@ enum bpf_linum_array_idx { #define DATA_LEN sizeof(DATA) static struct sockaddr_in6 srv_sa6, cli_sa6; +static int sk_pkt_out_cnt10_fd; +static int sk_pkt_out_cnt_fd; static int linum_map_fd; static int addr_map_fd; static int tp_map_fd; @@ -220,28 +227,90 @@ static void check_result(void) "Unexpected listen_tp", "Check listen_tp output. ingress_linum:%u", ingress_linum); - CHECK(srv_tp.data_segs_out != 1 || + CHECK(srv_tp.data_segs_out != 2 || srv_tp.data_segs_in || srv_tp.snd_cwnd != 10 || srv_tp.total_retrans || - srv_tp.bytes_acked != DATA_LEN, + srv_tp.bytes_acked != 2 * DATA_LEN, "Unexpected srv_tp", "Check srv_tp output. egress_linum:%u", egress_linum); CHECK(cli_tp.data_segs_out || - cli_tp.data_segs_in != 1 || + cli_tp.data_segs_in != 2 || cli_tp.snd_cwnd != 10 || cli_tp.total_retrans || - cli_tp.bytes_received != DATA_LEN, + cli_tp.bytes_received != 2 * DATA_LEN, "Unexpected cli_tp", "Check cli_tp output. egress_linum:%u", egress_linum); } +static void check_sk_pkt_out_cnt(int accept_fd, int cli_fd) +{ + struct bpf_spinlock_cnt pkt_out_cnt = {}, pkt_out_cnt10 = {}; + int err; + + pkt_out_cnt.cnt = ~0; + pkt_out_cnt10.cnt = ~0; + err = bpf_map_lookup_elem(sk_pkt_out_cnt_fd, &accept_fd, &pkt_out_cnt); + if (!err) + err = bpf_map_lookup_elem(sk_pkt_out_cnt10_fd, &accept_fd, + &pkt_out_cnt10); + + /* The bpf prog only counts for fullsock and + * passive conneciton did not become fullsock until 3WHS + * had been finished. + * The bpf prog only counted two data packet out but we + * specially init accept_fd's pkt_out_cnt by 2 in + * init_sk_storage(). Hence, 4 here. + */ + CHECK(err || pkt_out_cnt.cnt != 4 || pkt_out_cnt10.cnt != 40, + "bpf_map_lookup_elem(sk_pkt_out_cnt, &accept_fd)", + "err:%d errno:%d pkt_out_cnt:%u pkt_out_cnt10:%u", + err, errno, pkt_out_cnt.cnt, pkt_out_cnt10.cnt); + + pkt_out_cnt.cnt = ~0; + pkt_out_cnt10.cnt = ~0; + err = bpf_map_lookup_elem(sk_pkt_out_cnt_fd, &cli_fd, &pkt_out_cnt); + if (!err) + err = bpf_map_lookup_elem(sk_pkt_out_cnt10_fd, &cli_fd, + &pkt_out_cnt10); + /* Active connection is fullsock from the beginning. + * 1 SYN and 1 ACK during 3WHS + * 2 Acks on data packet. + * + * The bpf_prog initialized it to 0xeB9F. + */ + CHECK(err || pkt_out_cnt.cnt != 0xeB9F + 4 || + pkt_out_cnt10.cnt != 0xeB9F + 40, + "bpf_map_lookup_elem(sk_pkt_out_cnt, &cli_fd)", + "err:%d errno:%d pkt_out_cnt:%u pkt_out_cnt10:%u", + err, errno, pkt_out_cnt.cnt, pkt_out_cnt10.cnt); +} + +static void init_sk_storage(int sk_fd, __u32 pkt_out_cnt) +{ + struct bpf_spinlock_cnt scnt = {}; + int err; + + scnt.cnt = pkt_out_cnt; + err = bpf_map_update_elem(sk_pkt_out_cnt_fd, &sk_fd, &scnt, + BPF_NOEXIST); + CHECK(err, "bpf_map_update_elem(sk_pkt_out_cnt_fd)", + "err:%d errno:%d", err, errno); + + scnt.cnt *= 10; + err = bpf_map_update_elem(sk_pkt_out_cnt10_fd, &sk_fd, &scnt, + BPF_NOEXIST); + CHECK(err, "bpf_map_update_elem(sk_pkt_out_cnt10_fd)", + "err:%d errno:%d", err, errno); +} + static void test(void) { int listen_fd, cli_fd, accept_fd, epfd, err; struct epoll_event ev; socklen_t addrlen; + int i; addrlen = sizeof(struct sockaddr_in6); ev.events = EPOLLIN; @@ -308,24 +377,30 @@ static void test(void) accept_fd, errno); close(listen_fd); - /* Send some data from accept_fd to cli_fd */ - err = send(accept_fd, DATA, DATA_LEN, 0); - CHECK(err != DATA_LEN, "send(accept_fd)", "err:%d errno:%d", - err, errno); - - /* Have some timeout in recv(cli_fd). Just in case. */ ev.data.fd = cli_fd; err = epoll_ctl(epfd, EPOLL_CTL_ADD, cli_fd, &ev); CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, cli_fd)", "err:%d errno:%d", err, errno); - err = epoll_wait(epfd, &ev, 1, 1000); - CHECK(err != 1 || ev.data.fd != cli_fd, - "epoll_wait(cli_fd)", "err:%d errno:%d ev.data.fd:%d cli_fd:%d", - err, errno, ev.data.fd, cli_fd); + init_sk_storage(accept_fd, 2); - err = recv(cli_fd, NULL, 0, MSG_TRUNC); - CHECK(err, "recv(cli_fd)", "err:%d errno:%d", err, errno); + for (i = 0; i < 2; i++) { + /* Send some data from accept_fd to cli_fd */ + err = send(accept_fd, DATA, DATA_LEN, 0); + CHECK(err != DATA_LEN, "send(accept_fd)", "err:%d errno:%d", + err, errno); + + /* Have some timeout in recv(cli_fd). Just in case. */ + err = epoll_wait(epfd, &ev, 1, 1000); + CHECK(err != 1 || ev.data.fd != cli_fd, + "epoll_wait(cli_fd)", "err:%d errno:%d ev.data.fd:%d cli_fd:%d", + err, errno, ev.data.fd, cli_fd); + + err = recv(cli_fd, NULL, 0, MSG_TRUNC); + CHECK(err, "recv(cli_fd)", "err:%d errno:%d", err, errno); + } + + check_sk_pkt_out_cnt(accept_fd, cli_fd); close(epfd); close(accept_fd); @@ -395,6 +470,14 @@ int main(int argc, char **argv) CHECK(!map, "cannot find linum_map", "(null)"); linum_map_fd = bpf_map__fd(map); + map = bpf_object__find_map_by_name(obj, "sk_pkt_out_cnt"); + CHECK(!map, "cannot find sk_pkt_out_cnt", "(null)"); + sk_pkt_out_cnt_fd = bpf_map__fd(map); + + map = bpf_object__find_map_by_name(obj, "sk_pkt_out_cnt10"); + CHECK(!map, "cannot find sk_pkt_out_cnt10", "(null)"); + sk_pkt_out_cnt10_fd = bpf_map__fd(map); + test(); bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index d4d8d5d3b06e..ff0d31d38061 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -97,6 +97,9 @@ if [[ "$#" -eq "0" ]]; then echo "ip6ip6" $0 ipv6 ip6tnl none 100 + echo "sit" + $0 ipv6 sit none 100 + for mac in none mpls eth ; do echo "ip gre $mac" $0 ipv4 gre $mac 100 @@ -211,11 +214,20 @@ else targs="" fi +# tunnel address family differs from inner for SIT +if [[ "${tuntype}" == "sit" ]]; then + link_addr1="${ns1_v4}" + link_addr2="${ns2_v4}" +else + link_addr1="${addr1}" + link_addr2="${addr2}" +fi + # serverside, insert decap module # server is still running # client can connect again ip netns exec "${ns2}" ip link add name testtun0 type "${ttype}" \ - ${tmode} remote "${addr1}" local "${addr2}" $targs + ${tmode} remote "${link_addr1}" local "${link_addr2}" $targs expect_tun_fail=0 @@ -260,6 +272,12 @@ else server_listen fi +# bpf_skb_net_shrink does not take tunnel flags yet, cannot update L3. +if [[ "${tuntype}" == "sit" ]]; then + echo OK + exit 0 +fi + # serverside, use BPF for decap ip netns exec "${ns2}" ip link del dev testtun0 ip netns exec "${ns2}" tc qdisc add dev veth2 clsact diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index ed9e894afef3..ccd896b98cac 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -47,12 +47,13 @@ #include "bpf_rlimit.h" #include "bpf_rand.h" #include "bpf_util.h" +#include "test_btf.h" #include "../../../include/linux/filter.h" #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 17 +#define MAX_NR_MAPS 18 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -85,6 +86,7 @@ struct bpf_test { int fixup_map_array_ro[MAX_FIXUPS]; int fixup_map_array_wo[MAX_FIXUPS]; int fixup_map_array_small[MAX_FIXUPS]; + int fixup_sk_storage_map[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; uint32_t retval, retval_unpriv, insn_processed; @@ -497,24 +499,6 @@ static int create_cgroup_storage(bool percpu) return fd; } -#define BTF_INFO_ENC(kind, kind_flag, vlen) \ - ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) -#define BTF_TYPE_ENC(name, info, size_or_type) \ - (name), (info), (size_or_type) -#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ - ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) -#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ - BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ - BTF_INT_ENC(encoding, bits_offset, bits) -#define BTF_MEMBER_ENC(name, type, bits_offset) \ - (name), (type), (bits_offset) - -struct btf_raw_data { - __u32 raw_types[64]; - const char *str_sec; - __u32 str_sec_size; -}; - /* struct bpf_spin_lock { * int val; * }; @@ -589,6 +573,31 @@ static int create_map_spin_lock(void) return fd; } +static int create_sk_storage_map(void) +{ + struct bpf_create_map_attr attr = { + .name = "test_map", + .map_type = BPF_MAP_TYPE_SK_STORAGE, + .key_size = 4, + .value_size = 8, + .max_entries = 0, + .map_flags = BPF_F_NO_PREALLOC, + .btf_key_type_id = 1, + .btf_value_type_id = 3, + }; + int fd, btf_fd; + + btf_fd = load_btf(); + if (btf_fd < 0) + return -1; + attr.btf_fd = btf_fd; + fd = bpf_create_map_xattr(&attr); + close(attr.btf_fd); + if (fd < 0) + printf("Failed to create sk_storage_map\n"); + return fd; +} + static char bpf_vlog[UINT_MAX >> 8]; static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, @@ -611,6 +620,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_array_ro = test->fixup_map_array_ro; int *fixup_map_array_wo = test->fixup_map_array_wo; int *fixup_map_array_small = test->fixup_map_array_small; + int *fixup_sk_storage_map = test->fixup_sk_storage_map; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -765,6 +775,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_array_small++; } while (*fixup_map_array_small); } + if (*fixup_sk_storage_map) { + map_fds[17] = create_sk_storage_map(); + do { + prog[*fixup_sk_storage_map].imm = map_fds[17]; + fixup_sk_storage_map++; + } while (*fixup_sk_storage_map); + } } static int set_admin(bool admin) diff --git a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c new file mode 100644 index 000000000000..95b5d70a1dc1 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c @@ -0,0 +1,34 @@ +{ + "raw_tracepoint_writable: reject variable offset", + .insns = { + /* r6 is our tp buffer */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + + BPF_LD_MAP_FD(BPF_REG_1, 0), + /* move the key (== 0) to r10-8 */ + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0), + /* lookup in the map */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + + /* exit clean if null */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + + /* shift the buffer pointer to a variable location */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_0), + /* clobber whatever's there */ + BPF_MOV64_IMM(BPF_REG_7, 4242), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, 0), + + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 1, }, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + .errstr = "R6 invalid variable buffer offset: off=0, var_off=(0x0; 0xffffffff)", +}, diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index 416436231fab..b31cd2cf50d0 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -382,3 +382,119 @@ .result = REJECT, .errstr = "reference has not been acquired before", }, +{ + "sk_storage_get(map, skb->sk, NULL, 0): value == NULL", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_storage_get), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_sk_storage_map = { 11 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, +}, +{ + "sk_storage_get(map, skb->sk, 1, 1): value == 1", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_4, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_storage_get), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_sk_storage_map = { 11 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "R3 type=inv expected=fp", +}, +{ + "sk_storage_get(map, skb->sk, &stack_value, 1): stack_value", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_4, 1), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_storage_get), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_sk_storage_map = { 14 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, +}, +{ + "sk_storage_get(map, skb->sk, &stack_value, 1): partially init stack_value", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_4, 1), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_storage_get), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_sk_storage_map = { 14 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "invalid indirect read from stack", +}, +{ + "bpf_map_lookup_elem(smap, &key)", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_sk_storage_map = { 3 }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "cannot pass map_type 24 into func bpf_map_lookup_elem", +}, |