map event_pipe only accepts perf event arrays, leaving no built-in way to inspect records produced through the BPF ring buffer API. Extend it to consume queued and live BPF_MAP_TYPE_RINGBUF records in plain or JSON output, retaining the existing perf event array path.
Ring buffers have a shared consumer position and no implicit CPU or timestamp. Document that this command consumes records rather than observing them passively, and reject perf-only CPU/index selectors. A producer can keep ring_buffer__poll() busy after a stop signal, so return -EINTR from the record callback when stopping. Keep stdio out of the shared signal handler and preserve callback output errors. Link: https://github.com/libbpf/bpftool/issues/54 Assisted-by: LLM Signed-off-by: Tianyi Chen <[email protected]> --- .../bpf/bpftool/Documentation/bpftool-map.rst | 14 ++- tools/bpf/bpftool/bash-completion/bpftool | 59 +++++++------ tools/bpf/bpftool/map_perf_ring.c | 87 ++++++++++++++----- 3 files changed, 112 insertions(+), 48 deletions(-) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 5daf3de5c744..e4ed7e701c9e 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -120,7 +120,8 @@ bpftool map pin *MAP* *FILE* character ('.'), which is reserved for future extensions of *bpffs*. bpftool map event_pipe *MAP* [cpu *N* index *M*] - Read events from a **BPF_MAP_TYPE_PERF_EVENT_ARRAY** map. + Read events from a **BPF_MAP_TYPE_PERF_EVENT_ARRAY** or + **BPF_MAP_TYPE_RINGBUF** map. Install perf rings into a perf event array map and dump output of any **bpf_perf_event_output**\ () call in the kernel. By default read the @@ -134,6 +135,17 @@ bpftool map event_pipe *MAP* [cpu *N* index *M*] existing ring. Any other application will stop receiving events if it installed its rings earlier. + For a ring buffer map, consume records submitted by BPF programs, including + records already queued before the command starts. **cpu** and **index** + are not supported. Each record is printed in full, including embedded zero + bytes. Plain output reports the record size followed by hexadecimal + bytes; JSON output contains **size** and **data** fields, with **data** an + array of byte values. Ring buffer records have no implicit CPU or timestamp. + + Consuming a ring buffer advances its shared consumer position, so this + command must not run alongside another consumer of the same map. + **BPF_MAP_TYPE_USER_RINGBUF** maps are not supported. + bpftool map peek *MAP* Peek next value in the queue or stack. diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 75cbcb512eba..c9e8761e4ef2 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -50,12 +50,19 @@ _bpftool_get_map_ids() command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } -# Takes map type and adds matching map ids to the list of suggestions. -_bpftool_get_map_ids_for_type() +# Takes map types and prints a pattern matching their JSON type fields. +_bpftool_build_type_pattern() { - local type="$1" + local IFS='|' + printf '"type": "(%s)"\n' "$*" +} + +# Takes map types and adds matching map ids to the list of suggestions. +_bpftool_get_map_ids_for_types() +{ + local types=$(_bpftool_build_type_pattern "$@") COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ - command grep -C2 "$type" | \ + command grep -C2 -E "$types" | \ command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } @@ -65,12 +72,12 @@ _bpftool_get_map_names() command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) } -# Takes map type and adds matching map names to the list of suggestions. -_bpftool_get_map_names_for_type() +# Takes map types and adds matching map names to the list of suggestions. +_bpftool_get_map_names_for_types() { - local type="$1" + local types=$(_bpftool_build_type_pattern "$@") COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ - command grep -C2 "$type" | \ + command grep -C2 -E "$types" | \ command sed -n 's/.*"name": \(.*\),$/\1/p' )" -- "$cur" ) ) } @@ -139,7 +146,7 @@ _bpftool_map_guess_map_type() local keyword idx ref="" for (( idx=3; idx < ${#words[@]}-1; idx++ )); do case "${words[$((idx-2))]}" in - lookup|update) + lookup|update|event_pipe) keyword=${words[$((idx-1))]} ref=${words[$((idx))]} ;; @@ -177,10 +184,10 @@ _bpftool_map_update_get_id() if [[ $value -eq 0 ]]; then case "$command" in push) - _bpftool_get_map_ids_for_type stack + _bpftool_get_map_ids_for_types stack ;; enqueue) - _bpftool_get_map_ids_for_type queue + _bpftool_get_map_ids_for_types queue ;; *) _bpftool_get_map_ids @@ -223,10 +230,10 @@ _bpftool_map_update_get_name() if [[ $value -eq 0 ]]; then case "$command" in push) - _bpftool_get_map_names_for_type stack + _bpftool_get_map_names_for_types stack ;; enqueue) - _bpftool_get_map_names_for_type queue + _bpftool_get_map_names_for_types queue ;; *) _bpftool_get_map_names @@ -617,10 +624,10 @@ _bpftool() COMPREPLY=( $( compgen -W "$STRUCT_OPS_TYPE" -- "$cur" ) ) ;; id) - _bpftool_get_map_ids_for_type struct_ops + _bpftool_get_map_ids_for_types struct_ops ;; name) - _bpftool_get_map_names_for_type struct_ops + _bpftool_get_map_names_for_types struct_ops ;; esac return 0 @@ -679,14 +686,13 @@ _bpftool() id) case "$command" in peek) - _bpftool_get_map_ids_for_type stack - _bpftool_get_map_ids_for_type queue + _bpftool_get_map_ids_for_types stack queue ;; pop) - _bpftool_get_map_ids_for_type stack + _bpftool_get_map_ids_for_types stack ;; dequeue) - _bpftool_get_map_ids_for_type queue + _bpftool_get_map_ids_for_types queue ;; *) _bpftool_get_map_ids @@ -697,14 +703,13 @@ _bpftool() name) case "$command" in peek) - _bpftool_get_map_names_for_type stack - _bpftool_get_map_names_for_type queue + _bpftool_get_map_names_for_types stack queue ;; pop) - _bpftool_get_map_names_for_type stack + _bpftool_get_map_names_for_types stack ;; dequeue) - _bpftool_get_map_names_for_type queue + _bpftool_get_map_names_for_types queue ;; *) _bpftool_get_map_names @@ -878,11 +883,11 @@ _bpftool() return 0 ;; id) - _bpftool_get_map_ids_for_type perf_event_array + _bpftool_get_map_ids_for_types perf_event_array ringbuf return 0 ;; name) - _bpftool_get_map_names_for_type perf_event_array + _bpftool_get_map_names_for_types perf_event_array ringbuf return 0 ;; cpu) @@ -892,7 +897,9 @@ _bpftool() return 0 ;; *) - _bpftool_once_attr 'cpu index' + if [[ $(_bpftool_map_guess_map_type) != ringbuf ]]; then + _bpftool_once_attr 'cpu index' + fi return 0 ;; esac diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index bcb767e2d673..5878938cf8d9 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -27,7 +27,7 @@ #define MMAP_PAGE_CNT 16 -static volatile bool stop; +static volatile sig_atomic_t stop; struct perf_event_sample { struct perf_event_header header; @@ -44,7 +44,6 @@ struct perf_event_lost { static void int_exit(int signo) { - fprintf(stderr, "Stopping...\n"); stop = true; } @@ -107,6 +106,27 @@ print_bpf_output(void *private_data, int cpu, struct perf_event_header *event) return LIBBPF_PERF_EVENT_CONT; } +static int print_ringbuf_output(void *ctx, void *data, size_t size) +{ + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "size", size); + jsonw_name(json_wtr, "data"); + print_data_json(data, size); + jsonw_end_object(json_wtr); + } else { + printf("== size: %zu =====\n", size); + fprint_hex(stdout, data, size, " "); + printf("\n"); + } + + if (fflush(stdout)) + return errno ? -errno : -EIO; + + /* A producer can keep poll() busy even after a signal arrives. */ + return stop ? -EINTR : 0; +} + int do_event_pipe(int argc, char **argv) { struct perf_event_attr perf_attr = { @@ -123,18 +143,27 @@ int do_event_pipe(int argc, char **argv) .cpu = -1, .idx = -1, }; - struct perf_buffer *pb; + struct perf_buffer *pb = NULL; + struct ring_buffer *rb = NULL; __u32 map_info_len; int err, map_fd; + stop = false; map_info_len = sizeof(map_info); map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len, 0); if (map_fd < 0) return -1; - if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { - p_err("map is not a perf event array"); + if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY && + map_info.type != BPF_MAP_TYPE_RINGBUF) { + p_err("map is not a perf event array or ring buffer"); + goto err_close_map; + } + + if (map_info.type == BPF_MAP_TYPE_RINGBUF && argc && + (is_prefix(*argv, "cpu") || is_prefix(*argv, "index"))) { + p_err("ring buffer maps do not support cpu or index arguments"); goto err_close_map; } @@ -184,15 +213,24 @@ int do_event_pipe(int argc, char **argv) ctx.idx = 0; } - opts.cpu_cnt = ctx.all_cpus ? 0 : 1; - opts.cpus = &ctx.cpu; - opts.map_keys = &ctx.idx; - pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &perf_attr, - print_bpf_output, &ctx, &opts); - if (!pb) { - p_err("failed to create perf buffer: %s (%d)", - strerror(errno), errno); - goto err_close_map; + if (map_info.type == BPF_MAP_TYPE_RINGBUF) { + rb = ring_buffer__new(map_fd, print_ringbuf_output, NULL, NULL); + if (!rb) { + p_err("failed to create ring buffer: %s (%d)", + strerror(errno), errno); + goto err_close_map; + } + } else { + opts.cpu_cnt = ctx.all_cpus ? 0 : 1; + opts.cpus = &ctx.cpu; + opts.map_keys = &ctx.idx; + pb = perf_buffer__new_raw(map_fd, MMAP_PAGE_CNT, &perf_attr, + print_bpf_output, &ctx, &opts); + if (!pb) { + p_err("failed to create perf buffer: %s (%d)", + strerror(errno), errno); + goto err_close_map; + } } signal(SIGINT, int_exit); @@ -202,25 +240,32 @@ int do_event_pipe(int argc, char **argv) if (json_output) jsonw_start_array(json_wtr); + err = 0; while (!stop) { - err = perf_buffer__poll(pb, 200); + err = rb ? ring_buffer__poll(rb, 200) : perf_buffer__poll(pb, 200); if (err < 0 && err != -EINTR) { - p_err("perf buffer polling failed: %s (%d)", - strerror(errno), errno); - goto err_close_pb; + p_err("%s buffer polling failed: %s (%d)", + rb ? "ring" : "perf", strerror(-err), -err); + break; } + err = 0; } + if (stop) + fprintf(stderr, "Stopping...\n"); if (json_output) jsonw_end_array(json_wtr); + if (fflush(stdout)) { + p_err("failed to write events: %s", strerror(errno)); + err = -1; + } + ring_buffer__free(rb); perf_buffer__free(pb); close(map_fd); - return 0; + return err < 0 ? -1 : 0; -err_close_pb: - perf_buffer__free(pb); err_close_map: close(map_fd); return -1; -- 2.55.0
