diff --git a/include/linux/filter.h b/include/linux/filter.h index 834aa6e011dc70aace9069263964ecd7c027ce96..da6ccd833b7534eb61ff5402e941b279e341a78b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -23,6 +23,7 @@ #include +#include #include #include @@ -777,7 +778,19 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) return size <= size_default && (size & (size - 1)) == 0; } -#define bpf_ctx_wide_store_ok(off, size, type, field) \ +static inline u8 +bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) +{ + u8 access_off = off & (size_default - 1); + +#ifdef __LITTLE_ENDIAN + return access_off; +#else + return size_default - (access_off + size); +#endif +} + +#define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ off + sizeof(__u64) <= offsetofend(type, field) && \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ac787c72912985c8f8d41b25d5b7b9648e1af77a..57f96a592ad52eb5c3452cc0fa38cc8a9ed7c1ce 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3226,7 +3226,7 @@ struct bpf_sock_addr { __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 user_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __u32 user_port; /* Allows 4-byte read and write. @@ -3238,7 +3238,7 @@ struct bpf_sock_addr { __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __bpf_md_ptr(struct bpf_sock *, sk); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 8782379d99f7c494116c18a7c0ea094c5e1cbb70..a310a71f82a85b2e2d49ea25155ebc40a9dcf29a 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1073,11 +1073,18 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, !btf_type_is_var(size_type))) return NULL; - size = btf->resolved_sizes[size_type_id]; size_type_id = btf->resolved_ids[size_type_id]; size_type = btf_type_by_id(btf, size_type_id); if (btf_type_nosize_or_null(size_type)) return NULL; + else if (btf_type_has_size(size_type)) + size = size_type->size; + else if (btf_type_is_array(size_type)) + size = btf->resolved_sizes[size_type_id]; + else if (btf_type_is_ptr(size_type)) + size = sizeof(void *); + else + return NULL; } *type_id = size_type_id; @@ -1602,7 +1609,6 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, const struct btf_type *next_type; u32 next_type_id = t->type; struct btf *btf = env->btf; - u32 next_type_size = 0; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { @@ -1620,7 +1626,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, * save us a few type-following when we use it later (e.g. in * pretty print). */ - if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) { + if (!btf_type_id_size(btf, &next_type_id, NULL)) { if (env_type_is_resolved(env, next_type_id)) next_type = btf_type_id_resolve(btf, &next_type_id); @@ -1633,7 +1639,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, } } - env_stack_pop_resolved(env, next_type_id, next_type_size); + env_stack_pop_resolved(env, next_type_id, 0); return 0; } @@ -1645,7 +1651,6 @@ static int btf_var_resolve(struct btf_verifier_env *env, const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; - u32 next_type_size; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { @@ -1675,12 +1680,12 @@ static int btf_var_resolve(struct btf_verifier_env *env, * forward types or similar that would resolve to size of * zero is allowed. */ - if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) { + if (!btf_type_id_size(btf, &next_type_id, NULL)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } - env_stack_pop_resolved(env, next_type_id, next_type_size); + env_stack_pop_resolved(env, next_type_id, 0); return 0; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 8a3623733094d1e28550b165f30c8e75280286e4..122c6761758388bf0aef847023d4db420fffbccc 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1336,6 +1336,7 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; + u32 read_size; switch (si->off) { case offsetof(struct bpf_sysctl, write): @@ -1367,7 +1368,9 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, ppos)); *insn++ = BPF_STX_MEM( - BPF_SIZEOF(u32), treg, si->src_reg, 0); + BPF_SIZEOF(u32), treg, si->src_reg, + bpf_ctx_narrow_access_offset( + 0, sizeof(u32), sizeof(loff_t))); *insn++ = BPF_LDX_MEM( BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, tmp_reg)); @@ -1376,8 +1379,11 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type, BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), si->dst_reg, si->src_reg, offsetof(struct bpf_sysctl_kern, ppos)); + read_size = bpf_size_to_bytes(BPF_SIZE(si->code)); *insn++ = BPF_LDX_MEM( - BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0); + BPF_SIZE(si->code), si->dst_reg, si->dst_reg, + bpf_ctx_narrow_access_offset( + 0, read_size, sizeof(loff_t))); } *target_size = sizeof(u32); break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ebd14096aaad895145980ba72150c692e5dd9266..709c7a350a1d95417bd93d4d7048c51a307c6569 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6304,11 +6304,13 @@ static int check_return_code(struct bpf_verifier_env *env) if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG) range = tnum_range(1, 1); + break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { range = tnum_range(0, 3); enforce_attach_type_range = tnum_range(2, 3); } + break; case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: @@ -8821,8 +8823,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } if (is_narrower_load && size < target_size) { - u8 shift = (off & (size_default - 1)) * 8; - + u8 shift = bpf_ctx_narrow_access_offset( + off, size, size_default) * 8; if (ctx_field_size <= 4) { if (shift) insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH, diff --git a/net/core/filter.c b/net/core/filter.c index 289fca1671d02773783f1a8948abaab13fae7151..84ea1683e75153b663c04f21bb3399edae071391 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6838,20 +6838,30 @@ static bool sock_addr_is_valid_access(int off, int size, case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): - /* Only narrow read access allowed for now. */ if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); + + if (bpf_ctx_wide_access_ok(off, size, + struct bpf_sock_addr, + user_ip6)) + return true; + + if (bpf_ctx_wide_access_ok(off, size, + struct bpf_sock_addr, + msg_src_ip6)) + return true; + if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } else { - if (bpf_ctx_wide_store_ok(off, size, - struct bpf_sock_addr, - user_ip6)) + if (bpf_ctx_wide_access_ok(off, size, + struct bpf_sock_addr, + user_ip6)) return true; - if (bpf_ctx_wide_store_ok(off, size, - struct bpf_sock_addr, - msg_src_ip6)) + if (bpf_ctx_wide_access_ok(off, size, + struct bpf_sock_addr, + msg_src_ip6)) return true; if (size != size_default) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 1df637f85f9436dbac1662274f691dd7fefd67cd..7a374b3c851d0577afa9cf725ac6a7085187e9e4 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -29,6 +29,7 @@ PROG COMMANDS | **bpftool** **prog attach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog detach** *PROG* *ATTACH_TYPE* [*MAP*] | **bpftool** **prog tracelog** +| **bpftool** **prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*] | **bpftool** **prog help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } @@ -146,6 +147,39 @@ DESCRIPTION streaming data from BPF programs to user space, one can use perf events (see also **bpftool-map**\ (8)). + **bpftool prog run** *PROG* **data_in** *FILE* [**data_out** *FILE* [**data_size_out** *L*]] [**ctx_in** *FILE* [**ctx_out** *FILE* [**ctx_size_out** *M*]]] [**repeat** *N*] + Run BPF program *PROG* in the kernel testing infrastructure + for BPF, meaning that the program works on the data and + context provided by the user, and not on actual packets or + monitored functions etc. Return value and duration for the + test run are printed out to the console. + + Input data is read from the *FILE* passed with **data_in**. + If this *FILE* is "**-**", input data is read from standard + input. Input context, if any, is read from *FILE* passed with + **ctx_in**. Again, "**-**" can be used to read from standard + input, but only if standard input is not already in use for + input data. If a *FILE* is passed with **data_out**, output + data is written to that file. Similarly, output context is + written to the *FILE* passed with **ctx_out**. For both + output flows, "**-**" can be used to print to the standard + output (as plain text, or JSON if relevant option was + passed). If output keywords are omitted, output data and + context are discarded. Keywords **data_size_out** and + **ctx_size_out** are used to pass the size (in bytes) for the + output buffers to the kernel, although the default of 32 kB + should be more than enough for most cases. + + Keyword **repeat** is used to indicate the number of + consecutive runs to perform. Note that output data and + context printed to files correspond to the last of those + runs. The duration printed out at the end of the runs is an + average over all runs performed by the command. + + Not all program types support test run. Among those which do, + not all of them can take the **ctx_in**/**ctx_out** + arguments. bpftool does not perform checks on program types. + **bpftool prog help** Print short help message. diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 4ad1f0894d5312ef81e162cc5ecd34f114405725..453a9e1e8549e219682379df5875efdcf001b411 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -40,9 +40,8 @@ CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -Wno-missing-field-ini CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ - -I$(srctree)/tools/include/uapi \ -I$(srctree)/tools/lib/bpf \ - -I$(srctree)/tools/perf + -I$(srctree)/tools/include/uapi CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' ifneq ($(EXTRA_CFLAGS),) CFLAGS += $(EXTRA_CFLAGS) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index ba37095e1f62e64b2ebcb7d7c51c6ad8d48d22a2..c8f42e1fcbc994d859ede556b1a6a5a4e4e75e1b 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -342,6 +342,13 @@ _bpftool() load|loadall) local obj + # Propose "load/loadall" to complete "bpftool prog load", + # or bash tries to complete "load" as a filename below. + if [[ ${#words[@]} -eq 3 ]]; then + COMPREPLY=( $( compgen -W "load loadall" -- "$cur" ) ) + return 0 + fi + if [[ ${#words[@]} -lt 6 ]]; then _filedir return 0 @@ -408,10 +415,34 @@ _bpftool() tracelog) return 0 ;; + run) + if [[ ${#words[@]} -lt 5 ]]; then + _filedir + return 0 + fi + case $prev in + id) + _bpftool_get_prog_ids + return 0 + ;; + data_in|data_out|ctx_in|ctx_out) + _filedir + return 0 + ;; + repeat|data_size_out|ctx_size_out) + return 0 + ;; + *) + _bpftool_once_attr 'data_in data_out data_size_out \ + ctx_in ctx_out ctx_size_out repeat' + return 0 + ;; + esac + ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'dump help pin attach detach load \ - show list tracelog' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'dump help pin attach detach \ + load loadall show list tracelog run' -- "$cur" ) ) ;; esac ;; diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index d26c498b376c3666984acdb3e9198173610c07ce..68babde3cee6eddb719198003c0aa260b4a24787 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -117,6 +117,35 @@ bool is_prefix(const char *pfx, const char *str) return !memcmp(str, pfx, strlen(pfx)); } +/* Last argument MUST be NULL pointer */ +int detect_common_prefix(const char *arg, ...) +{ + unsigned int count = 0; + const char *ref; + char msg[256]; + va_list ap; + + snprintf(msg, sizeof(msg), "ambiguous prefix: '%s' could be '", arg); + va_start(ap, arg); + while ((ref = va_arg(ap, const char *))) { + if (!is_prefix(arg, ref)) + continue; + count++; + if (count > 1) + strncat(msg, "' or '", sizeof(msg) - strlen(msg) - 1); + strncat(msg, ref, sizeof(msg) - strlen(msg) - 1); + } + va_end(ap); + strncat(msg, "'", sizeof(msg) - strlen(msg) - 1); + + if (count >= 2) { + p_err("%s", msg); + return -1; + } + + return 0; +} + void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep) { unsigned char *data = arg; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 673869822c114ca842fc2cafde9e704f24d95ea4..cf76a6767d5340f1c387acd55f50eaf687f50f0e 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -102,6 +102,7 @@ void p_err(const char *fmt, ...); void p_info(const char *fmt, ...); bool is_prefix(const char *pfx, const char *str); +int detect_common_prefix(const char *arg, ...); void fprint_hex(FILE *f, void *arg, unsigned int n, const char *sep); void usage(void) __noreturn; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 0507dfaf7a8f93f5c0e2daf8de837e1163dff203..48924d4939cd6ad6b1a9eb8a6595fe14fe20997f 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -22,13 +22,12 @@ #include #include -#include #include "main.h" #define MMAP_PAGE_CNT 16 -static bool stop; +static volatile bool stop; struct event_ring_info { int fd; @@ -44,32 +43,44 @@ struct perf_event_sample { unsigned char data[]; }; +struct perf_event_lost { + struct perf_event_header header; + __u64 id; + __u64 lost; +}; + static void int_exit(int signo) { fprintf(stderr, "Stopping...\n"); stop = true; } +struct event_pipe_ctx { + bool all_cpus; + int cpu; + int idx; +}; + static enum bpf_perf_event_ret -print_bpf_output(struct perf_event_header *event, void *private_data) +print_bpf_output(void *private_data, int cpu, struct perf_event_header *event) { - struct perf_event_sample *e = container_of(event, struct perf_event_sample, + struct perf_event_sample *e = container_of(event, + struct perf_event_sample, header); - struct event_ring_info *ring = private_data; - struct { - struct perf_event_header header; - __u64 id; - __u64 lost; - } *lost = (typeof(lost))event; + struct perf_event_lost *lost = container_of(event, + struct perf_event_lost, + header); + struct event_pipe_ctx *ctx = private_data; + int idx = ctx->all_cpus ? cpu : ctx->idx; if (json_output) { jsonw_start_object(json_wtr); jsonw_name(json_wtr, "type"); jsonw_uint(json_wtr, e->header.type); jsonw_name(json_wtr, "cpu"); - jsonw_uint(json_wtr, ring->cpu); + jsonw_uint(json_wtr, cpu); jsonw_name(json_wtr, "index"); - jsonw_uint(json_wtr, ring->key); + jsonw_uint(json_wtr, idx); if (e->header.type == PERF_RECORD_SAMPLE) { jsonw_name(json_wtr, "timestamp"); jsonw_uint(json_wtr, e->time); @@ -89,7 +100,7 @@ print_bpf_output(struct perf_event_header *event, void *private_data) if (e->header.type == PERF_RECORD_SAMPLE) { printf("== @%lld.%09lld CPU: %d index: %d =====\n", e->time / 1000000000ULL, e->time % 1000000000ULL, - ring->cpu, ring->key); + cpu, idx); fprint_hex(stdout, e->data, e->size, " "); printf("\n"); } else if (e->header.type == PERF_RECORD_LOST) { @@ -103,87 +114,25 @@ print_bpf_output(struct perf_event_header *event, void *private_data) return LIBBPF_PERF_EVENT_CONT; } -static void -perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len) -{ - enum bpf_perf_event_ret ret; - - ret = bpf_perf_event_read_simple(ring->mem, - MMAP_PAGE_CNT * get_page_size(), - get_page_size(), buf, buf_len, - print_bpf_output, ring); - if (ret != LIBBPF_PERF_EVENT_CONT) { - fprintf(stderr, "perf read loop failed with %d\n", ret); - stop = true; - } -} - -static int perf_mmap_size(void) -{ - return get_page_size() * (MMAP_PAGE_CNT + 1); -} - -static void *perf_event_mmap(int fd) -{ - int mmap_size = perf_mmap_size(); - void *base; - - base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - if (base == MAP_FAILED) { - p_err("event mmap failed: %s\n", strerror(errno)); - return NULL; - } - - return base; -} - -static void perf_event_unmap(void *mem) -{ - if (munmap(mem, perf_mmap_size())) - fprintf(stderr, "Can't unmap ring memory!\n"); -} - -static int bpf_perf_event_open(int map_fd, int key, int cpu) +int do_event_pipe(int argc, char **argv) { - struct perf_event_attr attr = { + struct perf_event_attr perf_attr = { .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_TIME, .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_BPF_OUTPUT, + .sample_period = 1, + .wakeup_events = 1, }; - int pmu_fd; - - pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0); - if (pmu_fd < 0) { - p_err("failed to open perf event %d for CPU %d", key, cpu); - return -1; - } - - if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) { - p_err("failed to update map for event %d for CPU %d", key, cpu); - goto err_close; - } - if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { - p_err("failed to enable event %d for CPU %d", key, cpu); - goto err_close; - } - - return pmu_fd; - -err_close: - close(pmu_fd); - return -1; -} - -int do_event_pipe(int argc, char **argv) -{ - int i, nfds, map_fd, index = -1, cpu = -1; struct bpf_map_info map_info = {}; - struct event_ring_info *rings; - size_t tmp_buf_sz = 0; - void *tmp_buf = NULL; - struct pollfd *pfds; + struct perf_buffer_raw_opts opts = {}; + struct event_pipe_ctx ctx = { + .all_cpus = true, + .cpu = -1, + .idx = -1, + }; + struct perf_buffer *pb; __u32 map_info_len; - bool do_all = true; + int err, map_fd; map_info_len = sizeof(map_info); map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len); @@ -205,7 +154,7 @@ int do_event_pipe(int argc, char **argv) char *endptr; NEXT_ARG(); - cpu = strtoul(*argv, &endptr, 0); + ctx.cpu = strtoul(*argv, &endptr, 0); if (*endptr) { p_err("can't parse %s as CPU ID", **argv); goto err_close_map; @@ -216,7 +165,7 @@ int do_event_pipe(int argc, char **argv) char *endptr; NEXT_ARG(); - index = strtoul(*argv, &endptr, 0); + ctx.idx = strtoul(*argv, &endptr, 0); if (*endptr) { p_err("can't parse %s as index", **argv); goto err_close_map; @@ -228,45 +177,32 @@ int do_event_pipe(int argc, char **argv) goto err_close_map; } - do_all = false; + ctx.all_cpus = false; } - if (!do_all) { - if (index == -1 || cpu == -1) { + if (!ctx.all_cpus) { + if (ctx.idx == -1 || ctx.cpu == -1) { p_err("cpu and index must be specified together"); goto err_close_map; } - - nfds = 1; } else { - nfds = min(get_possible_cpus(), map_info.max_entries); - cpu = 0; - index = 0; + ctx.cpu = 0; + ctx.idx = 0; } - rings = calloc(nfds, sizeof(rings[0])); - if (!rings) + opts.attr = &perf_attr; + opts.event_cb = print_bpf_output; + opts.ctx = &ctx; + 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, &opts); + err = libbpf_get_error(pb); + if (err) { + p_err("failed to create perf buffer: %s (%d)", + strerror(err), err); goto err_close_map; - - pfds = calloc(nfds, sizeof(pfds[0])); - if (!pfds) - goto err_free_rings; - - for (i = 0; i < nfds; i++) { - rings[i].cpu = cpu + i; - rings[i].key = index + i; - - rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key, - rings[i].cpu); - if (rings[i].fd < 0) - goto err_close_fds_prev; - - rings[i].mem = perf_event_mmap(rings[i].fd); - if (!rings[i].mem) - goto err_close_fds_current; - - pfds[i].fd = rings[i].fd; - pfds[i].events = POLLIN; } signal(SIGINT, int_exit); @@ -277,34 +213,24 @@ int do_event_pipe(int argc, char **argv) jsonw_start_array(json_wtr); while (!stop) { - poll(pfds, nfds, 200); - for (i = 0; i < nfds; i++) - perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz); + err = perf_buffer__poll(pb, 200); + if (err < 0 && err != -EINTR) { + p_err("perf buffer polling failed: %s (%d)", + strerror(err), err); + goto err_close_pb; + } } - free(tmp_buf); if (json_output) jsonw_end_array(json_wtr); - for (i = 0; i < nfds; i++) { - perf_event_unmap(rings[i].mem); - close(rings[i].fd); - } - free(pfds); - free(rings); + perf_buffer__free(pb); close(map_fd); return 0; -err_close_fds_prev: - while (i--) { - perf_event_unmap(rings[i].mem); -err_close_fds_current: - close(rings[i].fd); - } - free(pfds); -err_free_rings: - free(rings); +err_close_pb: + perf_buffer__free(pb); err_close_map: close(map_fd); return -1; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 616a9c0b7f66073d6625c709a94eee0c9876bda8..43fdbbfe41bb24eef44e91c984c4dd30f41a6798 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -15,6 +15,7 @@ #include #include +#include #include #include @@ -750,6 +751,344 @@ static int do_detach(int argc, char **argv) return 0; } +static int check_single_stdin(char *file_data_in, char *file_ctx_in) +{ + if (file_data_in && file_ctx_in && + !strcmp(file_data_in, "-") && !strcmp(file_ctx_in, "-")) { + p_err("cannot use standard input for both data_in and ctx_in"); + return -1; + } + + return 0; +} + +static int get_run_data(const char *fname, void **data_ptr, unsigned int *size) +{ + size_t block_size = 256; + size_t buf_size = block_size; + size_t nb_read = 0; + void *tmp; + FILE *f; + + if (!fname) { + *data_ptr = NULL; + *size = 0; + return 0; + } + + if (!strcmp(fname, "-")) + f = stdin; + else + f = fopen(fname, "r"); + if (!f) { + p_err("failed to open %s: %s", fname, strerror(errno)); + return -1; + } + + *data_ptr = malloc(block_size); + if (!*data_ptr) { + p_err("failed to allocate memory for data_in/ctx_in: %s", + strerror(errno)); + goto err_fclose; + } + + while ((nb_read += fread(*data_ptr + nb_read, 1, block_size, f))) { + if (feof(f)) + break; + if (ferror(f)) { + p_err("failed to read data_in/ctx_in from %s: %s", + fname, strerror(errno)); + goto err_free; + } + if (nb_read > buf_size - block_size) { + if (buf_size == UINT32_MAX) { + p_err("data_in/ctx_in is too long (max: %d)", + UINT32_MAX); + goto err_free; + } + /* No space for fread()-ing next chunk; realloc() */ + buf_size *= 2; + tmp = realloc(*data_ptr, buf_size); + if (!tmp) { + p_err("failed to reallocate data_in/ctx_in: %s", + strerror(errno)); + goto err_free; + } + *data_ptr = tmp; + } + } + if (f != stdin) + fclose(f); + + *size = nb_read; + return 0; + +err_free: + free(*data_ptr); + *data_ptr = NULL; +err_fclose: + if (f != stdin) + fclose(f); + return -1; +} + +static void hex_print(void *data, unsigned int size, FILE *f) +{ + size_t i, j; + char c; + + for (i = 0; i < size; i += 16) { + /* Row offset */ + fprintf(f, "%07zx\t", i); + + /* Hexadecimal values */ + for (j = i; j < i + 16 && j < size; j++) + fprintf(f, "%02x%s", *(uint8_t *)(data + j), + j % 2 ? " " : ""); + for (; j < i + 16; j++) + fprintf(f, " %s", j % 2 ? " " : ""); + + /* ASCII values (if relevant), '.' otherwise */ + fprintf(f, "| "); + for (j = i; j < i + 16 && j < size; j++) { + c = *(char *)(data + j); + if (c < ' ' || c > '~') + c = '.'; + fprintf(f, "%c%s", c, j == i + 7 ? " " : ""); + } + + fprintf(f, "\n"); + } +} + +static int +print_run_output(void *data, unsigned int size, const char *fname, + const char *json_key) +{ + size_t nb_written; + FILE *f; + + if (!fname) + return 0; + + if (!strcmp(fname, "-")) { + f = stdout; + if (json_output) { + jsonw_name(json_wtr, json_key); + print_data_json(data, size); + } else { + hex_print(data, size, f); + } + return 0; + } + + f = fopen(fname, "w"); + if (!f) { + p_err("failed to open %s: %s", fname, strerror(errno)); + return -1; + } + + nb_written = fwrite(data, 1, size, f); + fclose(f); + if (nb_written != size) { + p_err("failed to write output data/ctx: %s", strerror(errno)); + return -1; + } + + return 0; +} + +static int alloc_run_data(void **data_ptr, unsigned int size_out) +{ + *data_ptr = calloc(size_out, 1); + if (!*data_ptr) { + p_err("failed to allocate memory for output data/ctx: %s", + strerror(errno)); + return -1; + } + + return 0; +} + +static int do_run(int argc, char **argv) +{ + char *data_fname_in = NULL, *data_fname_out = NULL; + char *ctx_fname_in = NULL, *ctx_fname_out = NULL; + struct bpf_prog_test_run_attr test_attr = {0}; + const unsigned int default_size = SZ_32K; + void *data_in = NULL, *data_out = NULL; + void *ctx_in = NULL, *ctx_out = NULL; + unsigned int repeat = 1; + int fd, err; + + if (!REQ_ARGS(4)) + return -1; + + fd = prog_parse_fd(&argc, &argv); + if (fd < 0) + return -1; + + while (argc) { + if (detect_common_prefix(*argv, "data_in", "data_out", + "data_size_out", NULL)) + return -1; + if (detect_common_prefix(*argv, "ctx_in", "ctx_out", + "ctx_size_out", NULL)) + return -1; + + if (is_prefix(*argv, "data_in")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + data_fname_in = GET_ARG(); + if (check_single_stdin(data_fname_in, ctx_fname_in)) + return -1; + } else if (is_prefix(*argv, "data_out")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + data_fname_out = GET_ARG(); + } else if (is_prefix(*argv, "data_size_out")) { + char *endptr; + + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + test_attr.data_size_out = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as output data size", + *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "ctx_in")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + ctx_fname_in = GET_ARG(); + if (check_single_stdin(data_fname_in, ctx_fname_in)) + return -1; + } else if (is_prefix(*argv, "ctx_out")) { + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + ctx_fname_out = GET_ARG(); + } else if (is_prefix(*argv, "ctx_size_out")) { + char *endptr; + + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + test_attr.ctx_size_out = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as output context size", + *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "repeat")) { + char *endptr; + + NEXT_ARG(); + if (!REQ_ARGS(1)) + return -1; + + repeat = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as repeat number", + *argv); + return -1; + } + NEXT_ARG(); + } else { + p_err("expected no more arguments, 'data_in', 'data_out', 'data_size_out', 'ctx_in', 'ctx_out', 'ctx_size_out' or 'repeat', got: '%s'?", + *argv); + return -1; + } + } + + err = get_run_data(data_fname_in, &data_in, &test_attr.data_size_in); + if (err) + return -1; + + if (data_in) { + if (!test_attr.data_size_out) + test_attr.data_size_out = default_size; + err = alloc_run_data(&data_out, test_attr.data_size_out); + if (err) + goto free_data_in; + } + + err = get_run_data(ctx_fname_in, &ctx_in, &test_attr.ctx_size_in); + if (err) + goto free_data_out; + + if (ctx_in) { + if (!test_attr.ctx_size_out) + test_attr.ctx_size_out = default_size; + err = alloc_run_data(&ctx_out, test_attr.ctx_size_out); + if (err) + goto free_ctx_in; + } + + test_attr.prog_fd = fd; + test_attr.repeat = repeat; + test_attr.data_in = data_in; + test_attr.data_out = data_out; + test_attr.ctx_in = ctx_in; + test_attr.ctx_out = ctx_out; + + err = bpf_prog_test_run_xattr(&test_attr); + if (err) { + p_err("failed to run program: %s", strerror(errno)); + goto free_ctx_out; + } + + err = 0; + + if (json_output) + jsonw_start_object(json_wtr); /* root */ + + /* Do not exit on errors occurring when printing output data/context, + * we still want to print return value and duration for program run. + */ + if (test_attr.data_size_out) + err += print_run_output(test_attr.data_out, + test_attr.data_size_out, + data_fname_out, "data_out"); + if (test_attr.ctx_size_out) + err += print_run_output(test_attr.ctx_out, + test_attr.ctx_size_out, + ctx_fname_out, "ctx_out"); + + if (json_output) { + jsonw_uint_field(json_wtr, "retval", test_attr.retval); + jsonw_uint_field(json_wtr, "duration", test_attr.duration); + jsonw_end_object(json_wtr); /* root */ + } else { + fprintf(stdout, "Return value: %u, duration%s: %uns\n", + test_attr.retval, + repeat > 1 ? " (average)" : "", test_attr.duration); + } + +free_ctx_out: + free(ctx_out); +free_ctx_in: + free(ctx_in); +free_data_out: + free(data_out); +free_data_in: + free(data_in); + + return err; +} + static int load_with_options(int argc, char **argv, bool first_prog_only) { struct bpf_object_load_attr load_attr = { 0 }; @@ -1060,6 +1399,11 @@ static int do_help(int argc, char **argv) " [pinmaps MAP_DIR]\n" " %s %s attach PROG ATTACH_TYPE [MAP]\n" " %s %s detach PROG ATTACH_TYPE [MAP]\n" + " %s %s run PROG \\\n" + " data_in FILE \\\n" + " [data_out FILE [data_size_out L]] \\\n" + " [ctx_in FILE [ctx_out FILE [ctx_size_out M]]] \\\n" + " [repeat N]\n" " %s %s tracelog\n" " %s %s help\n" "\n" @@ -1081,7 +1425,8 @@ static int do_help(int argc, char **argv) "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2]); return 0; } @@ -1097,6 +1442,7 @@ static const struct cmd cmds[] = { { "attach", do_attach }, { "detach", do_detach }, { "tracelog", do_tracelog }, + { "run", do_run }, { 0 } }; diff --git a/tools/include/linux/sizes.h b/tools/include/linux/sizes.h new file mode 100644 index 0000000000000000000000000000000000000000..1cbb4c4d016e37c23fa456f2b5e977ba357c385f --- /dev/null +++ b/tools/include/linux/sizes.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * include/linux/sizes.h + */ +#ifndef __LINUX_SIZES_H__ +#define __LINUX_SIZES_H__ + +#include + +#define SZ_1 0x00000001 +#define SZ_2 0x00000002 +#define SZ_4 0x00000004 +#define SZ_8 0x00000008 +#define SZ_16 0x00000010 +#define SZ_32 0x00000020 +#define SZ_64 0x00000040 +#define SZ_128 0x00000080 +#define SZ_256 0x00000100 +#define SZ_512 0x00000200 + +#define SZ_1K 0x00000400 +#define SZ_2K 0x00000800 +#define SZ_4K 0x00001000 +#define SZ_8K 0x00002000 +#define SZ_16K 0x00004000 +#define SZ_32K 0x00008000 +#define SZ_64K 0x00010000 +#define SZ_128K 0x00020000 +#define SZ_256K 0x00040000 +#define SZ_512K 0x00080000 + +#define SZ_1M 0x00100000 +#define SZ_2M 0x00200000 +#define SZ_4M 0x00400000 +#define SZ_8M 0x00800000 +#define SZ_16M 0x01000000 +#define SZ_32M 0x02000000 +#define SZ_64M 0x04000000 +#define SZ_128M 0x08000000 +#define SZ_256M 0x10000000 +#define SZ_512M 0x20000000 + +#define SZ_1G 0x40000000 +#define SZ_2G 0x80000000 + +#define SZ_4G _AC(0x100000000, ULL) + +#endif /* __LINUX_SIZES_H__ */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 46eed9ee7cca8350f170e9527e093b4485088eb6..5ac3af15dc9488e48fd4cc6df3c18db4b8069c11 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3223,7 +3223,7 @@ struct bpf_sock_addr { __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 user_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __u32 user_port; /* Allows 4-byte read and write. @@ -3235,7 +3235,7 @@ struct bpf_sock_addr { __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __bpf_md_ptr(struct bpf_sock *, sk); diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst index e9892da79e98917b2d5e65822631fcc42f856e2a..8e603565ccded907e4a90e4aa7df473c8cd2e87c 100644 --- a/tools/lib/bpf/README.rst +++ b/tools/lib/bpf/README.rst @@ -9,7 +9,8 @@ described here. It's recommended to follow these conventions whenever a new function or type is added to keep libbpf API clean and consistent. All types and functions provided by libbpf API should have one of the -following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``. +following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``, +``perf_buffer_``. System call wrappers -------------------- diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 3f21172d6d34981534fb95edb502a42c07312287..4d8ec9068c496d718c18c8152ebbcefec3918d45 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -33,7 +33,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -1379,8 +1381,13 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) if (!has_datasec && kind == BTF_KIND_VAR) { /* replace VAR with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); - t->size = sizeof(int); - *(int *)(t+1) = BTF_INT_ENC(0, 0, 32); + /* + * using size = 1 is the safest choice, 4 will be too + * big and cause kernel BTF validation failure if + * original variable took less than 4 bytes + */ + t->size = 1; + *(int *)(t+1) = BTF_INT_ENC(0, 0, 8); } else if (!has_datasec && kind == BTF_KIND_DATASEC) { /* replace DATASEC with STRUCT */ struct btf_var_secinfo *v = (void *)(t + 1); @@ -1776,15 +1783,22 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, (long long) sym.st_value, sym.st_name, name); shdr_idx = sym.st_shndx; + insn_idx = rel.r_offset / sizeof(struct bpf_insn); + pr_debug("relocation: insn_idx=%u, shdr_idx=%u\n", + insn_idx, shdr_idx); + + if (shdr_idx >= SHN_LORESERVE) { + pr_warning("relocation: not yet supported relo for non-static global \'%s\' variable in special section (0x%x) found in insns[%d].code 0x%x\n", + name, shdr_idx, insn_idx, + insns[insn_idx].code); + return -LIBBPF_ERRNO__RELOC; + } if (!bpf_object__relo_in_known_section(obj, shdr_idx)) { pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n", prog->section_name, shdr_idx); return -LIBBPF_ERRNO__RELOC; } - insn_idx = rel.r_offset / sizeof(struct bpf_insn); - pr_debug("relocation: insn_idx=%u\n", insn_idx); - if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) { if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) { pr_warning("incorrect bpf_call opcode\n"); @@ -2159,6 +2173,7 @@ static int bpf_object__create_maps(struct bpf_object *obj) { struct bpf_create_map_attr create_attr = {}; + int nr_cpus = 0; unsigned int i; int err; @@ -2181,7 +2196,22 @@ bpf_object__create_maps(struct bpf_object *obj) create_attr.map_flags = def->map_flags; create_attr.key_size = def->key_size; create_attr.value_size = def->value_size; - create_attr.max_entries = def->max_entries; + if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && + !def->max_entries) { + if (!nr_cpus) + nr_cpus = libbpf_num_possible_cpus(); + if (nr_cpus < 0) { + pr_warning("failed to determine number of system CPUs: %d\n", + nr_cpus); + err = nr_cpus; + goto err_out; + } + pr_debug("map '%s': setting size to %d\n", + map->name, nr_cpus); + create_attr.max_entries = nr_cpus; + } else { + create_attr.max_entries = def->max_entries; + } create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; @@ -2198,9 +2228,10 @@ bpf_object__create_maps(struct bpf_object *obj) *pfd = bpf_create_map_xattr(&create_attr); if (*pfd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", - map->name, cp, errno); + map->name, cp, err); create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; @@ -2212,11 +2243,11 @@ bpf_object__create_maps(struct bpf_object *obj) if (*pfd < 0) { size_t j; - err = *pfd; + err = -errno; err_out: - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("failed to create map (name: '%s'): %s\n", - map->name, cp); + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warning("failed to create map (name: '%s'): %s(%d)\n", + map->name, cp, err); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; @@ -4401,6 +4432,391 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, return ret; } +struct perf_buffer; + +struct perf_buffer_params { + struct perf_event_attr *attr; + /* if event_cb is specified, it takes precendence */ + perf_buffer_event_fn event_cb; + /* sample_cb and lost_cb are higher-level common-case callbacks */ + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; + int cpu_cnt; + int *cpus; + int *map_keys; +}; + +struct perf_cpu_buf { + struct perf_buffer *pb; + void *base; /* mmap()'ed memory */ + void *buf; /* for reconstructing segmented data */ + size_t buf_size; + int fd; + int cpu; + int map_key; +}; + +struct perf_buffer { + perf_buffer_event_fn event_cb; + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; /* passed into callbacks */ + + size_t page_size; + size_t mmap_size; + struct perf_cpu_buf **cpu_bufs; + struct epoll_event *events; + int cpu_cnt; /* number of allocated CPU buffers */ + int epoll_fd; /* perf event FD */ + int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */ +}; + +static void perf_buffer__free_cpu_buf(struct perf_buffer *pb, + struct perf_cpu_buf *cpu_buf) +{ + if (!cpu_buf) + return; + if (cpu_buf->base && + munmap(cpu_buf->base, pb->mmap_size + pb->page_size)) + pr_warning("failed to munmap cpu_buf #%d\n", cpu_buf->cpu); + if (cpu_buf->fd >= 0) { + ioctl(cpu_buf->fd, PERF_EVENT_IOC_DISABLE, 0); + close(cpu_buf->fd); + } + free(cpu_buf->buf); + free(cpu_buf); +} + +void perf_buffer__free(struct perf_buffer *pb) +{ + int i; + + if (!pb) + return; + if (pb->cpu_bufs) { + for (i = 0; i < pb->cpu_cnt; i++) { + struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i]; + + if (!cpu_buf) + continue; + + bpf_map_delete_elem(pb->map_fd, &cpu_buf->map_key); + perf_buffer__free_cpu_buf(pb, cpu_buf); + } + free(pb->cpu_bufs); + } + if (pb->epoll_fd >= 0) + close(pb->epoll_fd); + free(pb->events); + free(pb); +} + +static struct perf_cpu_buf * +perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, + int cpu, int map_key) +{ + struct perf_cpu_buf *cpu_buf; + char msg[STRERR_BUFSIZE]; + int err; + + cpu_buf = calloc(1, sizeof(*cpu_buf)); + if (!cpu_buf) + return ERR_PTR(-ENOMEM); + + cpu_buf->pb = pb; + cpu_buf->cpu = cpu; + cpu_buf->map_key = map_key; + + cpu_buf->fd = syscall(__NR_perf_event_open, attr, -1 /* pid */, cpu, + -1, PERF_FLAG_FD_CLOEXEC); + if (cpu_buf->fd < 0) { + err = -errno; + pr_warning("failed to open perf buffer event on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + cpu_buf->base = mmap(NULL, pb->mmap_size + pb->page_size, + PROT_READ | PROT_WRITE, MAP_SHARED, + cpu_buf->fd, 0); + if (cpu_buf->base == MAP_FAILED) { + cpu_buf->base = NULL; + err = -errno; + pr_warning("failed to mmap perf buffer on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + if (ioctl(cpu_buf->fd, PERF_EVENT_IOC_ENABLE, 0) < 0) { + err = -errno; + pr_warning("failed to enable perf buffer event on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + return cpu_buf; + +error: + perf_buffer__free_cpu_buf(pb, cpu_buf); + return (struct perf_cpu_buf *)ERR_PTR(err); +} + +static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, + struct perf_buffer_params *p); + +struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts) +{ + struct perf_buffer_params p = {}; + struct perf_event_attr attr = { 0, }; + + attr.config = PERF_COUNT_SW_BPF_OUTPUT, + attr.type = PERF_TYPE_SOFTWARE; + attr.sample_type = PERF_SAMPLE_RAW; + attr.sample_period = 1; + attr.wakeup_events = 1; + + p.attr = &attr; + p.sample_cb = opts ? opts->sample_cb : NULL; + p.lost_cb = opts ? opts->lost_cb : NULL; + p.ctx = opts ? opts->ctx : NULL; + + return __perf_buffer__new(map_fd, page_cnt, &p); +} + +struct perf_buffer * +perf_buffer__new_raw(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts) +{ + struct perf_buffer_params p = {}; + + p.attr = opts->attr; + p.event_cb = opts->event_cb; + p.ctx = opts->ctx; + p.cpu_cnt = opts->cpu_cnt; + p.cpus = opts->cpus; + p.map_keys = opts->map_keys; + + return __perf_buffer__new(map_fd, page_cnt, &p); +} + +static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, + struct perf_buffer_params *p) +{ + const char *online_cpus_file = "/sys/devices/system/cpu/online"; + struct bpf_map_info map = {}; + char msg[STRERR_BUFSIZE]; + struct perf_buffer *pb; + bool *online = NULL; + __u32 map_info_len; + int err, i, j, n; + + if (page_cnt & (page_cnt - 1)) { + pr_warning("page count should be power of two, but is %zu\n", + page_cnt); + return ERR_PTR(-EINVAL); + } + + map_info_len = sizeof(map); + err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len); + if (err) { + err = -errno; + pr_warning("failed to get map info for map FD %d: %s\n", + map_fd, libbpf_strerror_r(err, msg, sizeof(msg))); + return ERR_PTR(err); + } + + if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + pr_warning("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", + map.name); + return ERR_PTR(-EINVAL); + } + + pb = calloc(1, sizeof(*pb)); + if (!pb) + return ERR_PTR(-ENOMEM); + + pb->event_cb = p->event_cb; + pb->sample_cb = p->sample_cb; + pb->lost_cb = p->lost_cb; + pb->ctx = p->ctx; + + pb->page_size = getpagesize(); + pb->mmap_size = pb->page_size * page_cnt; + pb->map_fd = map_fd; + + pb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (pb->epoll_fd < 0) { + err = -errno; + pr_warning("failed to create epoll instance: %s\n", + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + if (p->cpu_cnt > 0) { + pb->cpu_cnt = p->cpu_cnt; + } else { + pb->cpu_cnt = libbpf_num_possible_cpus(); + if (pb->cpu_cnt < 0) { + err = pb->cpu_cnt; + goto error; + } + if (map.max_entries < pb->cpu_cnt) + pb->cpu_cnt = map.max_entries; + } + + pb->events = calloc(pb->cpu_cnt, sizeof(*pb->events)); + if (!pb->events) { + err = -ENOMEM; + pr_warning("failed to allocate events: out of memory\n"); + goto error; + } + pb->cpu_bufs = calloc(pb->cpu_cnt, sizeof(*pb->cpu_bufs)); + if (!pb->cpu_bufs) { + err = -ENOMEM; + pr_warning("failed to allocate buffers: out of memory\n"); + goto error; + } + + err = parse_cpu_mask_file(online_cpus_file, &online, &n); + if (err) { + pr_warning("failed to get online CPU mask: %d\n", err); + goto error; + } + + for (i = 0, j = 0; i < pb->cpu_cnt; i++) { + struct perf_cpu_buf *cpu_buf; + int cpu, map_key; + + cpu = p->cpu_cnt > 0 ? p->cpus[i] : i; + map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i; + + /* in case user didn't explicitly requested particular CPUs to + * be attached to, skip offline/not present CPUs + */ + if (p->cpu_cnt <= 0 && (cpu >= n || !online[cpu])) + continue; + + cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key); + if (IS_ERR(cpu_buf)) { + err = PTR_ERR(cpu_buf); + goto error; + } + + pb->cpu_bufs[j] = cpu_buf; + + err = bpf_map_update_elem(pb->map_fd, &map_key, + &cpu_buf->fd, 0); + if (err) { + err = -errno; + pr_warning("failed to set cpu #%d, key %d -> perf FD %d: %s\n", + cpu, map_key, cpu_buf->fd, + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + pb->events[j].events = EPOLLIN; + pb->events[j].data.ptr = cpu_buf; + if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd, + &pb->events[j]) < 0) { + err = -errno; + pr_warning("failed to epoll_ctl cpu #%d perf FD %d: %s\n", + cpu, cpu_buf->fd, + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + j++; + } + pb->cpu_cnt = j; + free(online); + + return pb; + +error: + free(online); + if (pb) + perf_buffer__free(pb); + return ERR_PTR(err); +} + +struct perf_sample_raw { + struct perf_event_header header; + uint32_t size; + char data[0]; +}; + +struct perf_sample_lost { + struct perf_event_header header; + uint64_t id; + uint64_t lost; + uint64_t sample_id; +}; + +static enum bpf_perf_event_ret +perf_buffer__process_record(struct perf_event_header *e, void *ctx) +{ + struct perf_cpu_buf *cpu_buf = ctx; + struct perf_buffer *pb = cpu_buf->pb; + void *data = e; + + /* user wants full control over parsing perf event */ + if (pb->event_cb) + return pb->event_cb(pb->ctx, cpu_buf->cpu, e); + + switch (e->type) { + case PERF_RECORD_SAMPLE: { + struct perf_sample_raw *s = data; + + if (pb->sample_cb) + pb->sample_cb(pb->ctx, cpu_buf->cpu, s->data, s->size); + break; + } + case PERF_RECORD_LOST: { + struct perf_sample_lost *s = data; + + if (pb->lost_cb) + pb->lost_cb(pb->ctx, cpu_buf->cpu, s->lost); + break; + } + default: + pr_warning("unknown perf sample type %d\n", e->type); + return LIBBPF_PERF_EVENT_ERROR; + } + return LIBBPF_PERF_EVENT_CONT; +} + +static int perf_buffer__process_records(struct perf_buffer *pb, + struct perf_cpu_buf *cpu_buf) +{ + enum bpf_perf_event_ret ret; + + ret = bpf_perf_event_read_simple(cpu_buf->base, pb->mmap_size, + pb->page_size, &cpu_buf->buf, + &cpu_buf->buf_size, + perf_buffer__process_record, cpu_buf); + if (ret != LIBBPF_PERF_EVENT_CONT) + return ret; + return 0; +} + +int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) +{ + int i, cnt, err; + + cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms); + for (i = 0; i < cnt; i++) { + struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr; + + err = perf_buffer__process_records(pb, cpu_buf); + if (err) { + pr_warning("error while processing records: %d\n", err); + return err; + } + } + return cnt < 0 ? -errno : cnt; +} + struct bpf_prog_info_array_desc { int array_offset; /* e.g. offset of jited_prog_insns */ int count_offset; /* e.g. offset of jited_prog_len */ @@ -4647,62 +5063,104 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) } } -int libbpf_num_possible_cpus(void) +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz) { - static const char *fcpu = "/sys/devices/system/cpu/possible"; - int len = 0, n = 0, il = 0, ir = 0; - unsigned int start = 0, end = 0; - int tmp_cpus = 0; - static int cpus; - char buf[128]; - int error = 0; - int fd = -1; + int err = 0, n, len, start, end = -1; + bool *tmp; - tmp_cpus = READ_ONCE(cpus); - if (tmp_cpus > 0) - return tmp_cpus; + *mask = NULL; + *mask_sz = 0; + + /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ + while (*s) { + if (*s == ',' || *s == '\n') { + s++; + continue; + } + n = sscanf(s, "%d%n-%d%n", &start, &len, &end, &len); + if (n <= 0 || n > 2) { + pr_warning("Failed to get CPU range %s: %d\n", s, n); + err = -EINVAL; + goto cleanup; + } else if (n == 1) { + end = start; + } + if (start < 0 || start > end) { + pr_warning("Invalid CPU range [%d,%d] in %s\n", + start, end, s); + err = -EINVAL; + goto cleanup; + } + tmp = realloc(*mask, end + 1); + if (!tmp) { + err = -ENOMEM; + goto cleanup; + } + *mask = tmp; + memset(tmp + *mask_sz, 0, start - *mask_sz); + memset(tmp + start, 1, end - start + 1); + *mask_sz = end + 1; + s += len; + } + if (!*mask_sz) { + pr_warning("Empty CPU range\n"); + return -EINVAL; + } + return 0; +cleanup: + free(*mask); + *mask = NULL; + return err; +} + +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz) +{ + int fd, err = 0, len; + char buf[128]; fd = open(fcpu, O_RDONLY); if (fd < 0) { - error = errno; - pr_warning("Failed to open file %s: %s\n", - fcpu, strerror(error)); - return -error; + err = -errno; + pr_warning("Failed to open cpu mask file %s: %d\n", fcpu, err); + return err; } len = read(fd, buf, sizeof(buf)); close(fd); if (len <= 0) { - error = len ? errno : EINVAL; - pr_warning("Failed to read # of possible cpus from %s: %s\n", - fcpu, strerror(error)); - return -error; + err = len ? -errno : -EINVAL; + pr_warning("Failed to read cpu mask from %s: %d\n", fcpu, err); + return err; } - if (len == sizeof(buf)) { - pr_warning("File %s size overflow\n", fcpu); - return -EOVERFLOW; + if (len >= sizeof(buf)) { + pr_warning("CPU mask is too big in file %s\n", fcpu); + return -E2BIG; } buf[len] = '\0'; - for (ir = 0, tmp_cpus = 0; ir <= len; ir++) { - /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ - if (buf[ir] == ',' || buf[ir] == '\0') { - buf[ir] = '\0'; - n = sscanf(&buf[il], "%u-%u", &start, &end); - if (n <= 0) { - pr_warning("Failed to get # CPUs from %s\n", - &buf[il]); - return -EINVAL; - } else if (n == 1) { - end = start; - } - tmp_cpus += end - start + 1; - il = ir + 1; - } - } - if (tmp_cpus <= 0) { - pr_warning("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu); - return -EINVAL; + return parse_cpu_mask_str(buf, mask, mask_sz); +} + +int libbpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + static int cpus; + int err, n, i, tmp_cpus; + bool *mask; + + tmp_cpus = READ_ONCE(cpus); + if (tmp_cpus > 0) + return tmp_cpus; + + err = parse_cpu_mask_file(fcpu, &mask, &n); + if (err) + return err; + + tmp_cpus = 0; + for (i = 0; i < n; i++) { + if (mask[i]) + tmp_cpus++; } + free(mask); WRITE_ONCE(cpus, tmp_cpus); return tmp_cpus; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index f55933784f95208b230b283355aad53bfc92708f..5cbf459ece0b29eb3e36981d0b3cfe5a951ae562 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -358,6 +358,26 @@ LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type, LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); +struct perf_buffer; + +typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu, + void *data, __u32 size); +typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); + +/* common use perf buffer options */ +struct perf_buffer_opts { + /* if specified, sample_cb is called for each sample */ + perf_buffer_sample_fn sample_cb; + /* if specified, lost_cb is called for each batch of lost samples */ + perf_buffer_lost_fn lost_cb; + /* ctx is provided to sample_cb and lost_cb */ + void *ctx; +}; + +LIBBPF_API struct perf_buffer * +perf_buffer__new(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts); + enum bpf_perf_event_ret { LIBBPF_PERF_EVENT_DONE = 0, LIBBPF_PERF_EVENT_ERROR = -1, @@ -365,6 +385,35 @@ enum bpf_perf_event_ret { }; struct perf_event_header; + +typedef enum bpf_perf_event_ret +(*perf_buffer_event_fn)(void *ctx, int cpu, struct perf_event_header *event); + +/* raw perf buffer options, giving most power and control */ +struct perf_buffer_raw_opts { + /* perf event attrs passed directly into perf_event_open() */ + struct perf_event_attr *attr; + /* raw event callback */ + perf_buffer_event_fn event_cb; + /* ctx is provided to event_cb */ + void *ctx; + /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of + * max_entries of given PERF_EVENT_ARRAY map) + */ + int cpu_cnt; + /* if cpu_cnt > 0, cpus is an array of CPUs to open ring buffers on */ + int *cpus; + /* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */ + int *map_keys; +}; + +LIBBPF_API struct perf_buffer * +perf_buffer__new_raw(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts); + +LIBBPF_API void perf_buffer__free(struct perf_buffer *pb); +LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms); + typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, void *private_data); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index e6b7d4edbc936e461cb960155047dab429951c5e..f9d316e873d8d2d7ff37d138fdef0cbbbd425bcd 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -179,4 +179,8 @@ LIBBPF_0.0.4 { btf_dump__new; btf__parse_elf; libbpf_num_possible_cpus; + perf_buffer__free; + perf_buffer__new; + perf_buffer__new_raw; + perf_buffer__poll; } LIBBPF_0.0.3; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 2ac29bd362269ad8f901e06bc03033c86fbf3474..86df374629144e0cc1665f84f1b4bd327539c37c 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -43,6 +43,8 @@ do { \ #define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) #define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 9dfaff57daea085f9cffb3a11a3d97152464d32d..f5357230e16c1fdac975c9bcbb598fdf1ae82c64 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -317,15 +317,14 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) static int xsk_get_max_queues(struct xsk_socket *xsk) { - struct ethtool_channels channels; - struct ifreq ifr; + struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; + struct ifreq ifr = {}; int fd, err, ret; fd = socket(AF_INET, SOCK_DGRAM, 0); if (fd < 0) return -errno; - channels.cmd = ETHTOOL_GCHANNELS; ifr.ifr_data = (void *)&channels; strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); ifr.ifr_name[IFNAMSIZ - 1] = '\0'; @@ -335,7 +334,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) goto out; } - if (channels.max_combined == 0 || errno == EOPNOTSUPP) + if (err || channels.max_combined == 0) /* If the device says it has no channels, then all traffic * is sent to a single stream, so max queues = 1. */ @@ -520,7 +519,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, err = -errno; goto out_socket; } - strncpy(xsk->ifname, ifname, IFNAMSIZ); + strncpy(xsk->ifname, ifname, IFNAMSIZ - 1); + xsk->ifname[IFNAMSIZ - 1] = '\0'; err = xsk_set_xdp_socket_config(&xsk->config, usr_config); if (err) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 4ee5694f5602eafa06c6a6cdc5c00fd88b4e1b5e..40ecae377d154f7d1c66c070725c3095b5768b44 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -26,7 +26,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \ test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_cgroup_attach test_sockopt \ - test_sockopt_sk test_sockopt_multi + test_sockopt_sk test_sockopt_multi test_tcp_rtt BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c))) TEST_GEN_FILES = $(BPF_OBJ_FILES) @@ -96,6 +96,7 @@ $(OUTPUT)/test_cgroup_attach: cgroup_helpers.c $(OUTPUT)/test_sockopt: cgroup_helpers.c $(OUTPUT)/test_sockopt_sk: cgroup_helpers.c $(OUTPUT)/test_sockopt_multi: cgroup_helpers.c +$(OUTPUT)/test_tcp_rtt: cgroup_helpers.c .PHONY: force diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c new file mode 100644 index 0000000000000000000000000000000000000000..233bdcb1659ef7ab3ce9a3be7d8745a865529f0d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; + +struct tcp_rtt_storage { + __u32 invoked; + __u32 dsack_dups; + __u32 delivered; + __u32 delivered_ce; + __u32 icsk_retransmits; +}; + +struct bpf_map_def SEC("maps") socket_storage_map = { + .type = BPF_MAP_TYPE_SK_STORAGE, + .key_size = sizeof(int), + .value_size = sizeof(struct tcp_rtt_storage), + .map_flags = BPF_F_NO_PREALLOC, +}; +BPF_ANNOTATE_KV_PAIR(socket_storage_map, int, struct tcp_rtt_storage); + +SEC("sockops") +int _sockops(struct bpf_sock_ops *ctx) +{ + struct tcp_rtt_storage *storage; + struct bpf_tcp_sock *tcp_sk; + int op = (int) ctx->op; + struct bpf_sock *sk; + + sk = ctx->sk; + if (!sk) + return 1; + + storage = bpf_sk_storage_get(&socket_storage_map, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 1; + + if (op == BPF_SOCK_OPS_TCP_CONNECT_CB) { + bpf_sock_ops_cb_flags_set(ctx, BPF_SOCK_OPS_RTT_CB_FLAG); + return 1; + } + + if (op != BPF_SOCK_OPS_RTT_CB) + return 1; + + tcp_sk = bpf_tcp_sock(sk); + if (!tcp_sk) + return 1; + + storage->invoked++; + + storage->dsack_dups = tcp_sk->dsack_dups; + storage->delivered = tcp_sk->delivered; + storage->delivered_ce = tcp_sk->delivered_ce; + storage->icsk_retransmits = tcp_sk->icsk_retransmits; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c new file mode 100644 index 0000000000000000000000000000000000000000..876c27deb65a3333e1cdfb460c8e4c6dda16cd03 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include +#include +#include "bpf_helpers.h" + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); +} perf_buf_map SEC(".maps"); + +SEC("kprobe/sys_nanosleep") +int handle_sys_nanosleep_entry(struct pt_regs *ctx) +{ + int cpu = bpf_get_smp_processor_id(); + + bpf_perf_event_output(ctx, &perf_buf_map, BPF_F_CURRENT_CPU, + &cpu, sizeof(cpu)); + return 0; +} + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c index 0ae7a741541464390d7e4a43aa941028d0f2a430..6cc29b58d6707e90411f8ca3b01162a72a65517d 100644 --- a/tools/testing/selftests/bpf/test_align.c +++ b/tools/testing/selftests/bpf/test_align.c @@ -180,7 +180,7 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {7, "R0=pkt(id=0,off=8,r=8,imm=0)"}, + {7, "R0_w=pkt(id=0,off=8,r=8,imm=0)"}, {7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, {8, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, {9, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, @@ -315,7 +315,7 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {8, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Offset is added to packet pointer R5, resulting in * known fixed offset, and variable offset from R6. @@ -405,7 +405,7 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {8, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, @@ -473,12 +473,12 @@ static struct bpf_align_test tests[] = { /* (4n) + 14 == (4n+2). We blow our bounds, because * the add could overflow. */ - {7, "R5=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, + {7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, /* packet pointer + nonnegative (4n+2) */ {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, - {13, "R4=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -486,7 +486,7 @@ static struct bpf_align_test tests[] = { * So we did not get a 'range' on R6, and the access * attempt will fail. */ - {15, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, } }, { @@ -521,7 +521,7 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {7, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, {9, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ {10, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, @@ -575,7 +575,7 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {7, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, {10, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, /* Adding 14 makes R6 be (4n+2) */ {11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index 781c7de343be005a92bffd7a2f6da0f0eaae22bb..1b25a7e348dc477caa4d806d6ed2168ea7e2da23 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -18,9 +18,11 @@ #include #include +#include #include "bpf_util.h" #include "bpf_rlimit.h" +#include "../../../include/linux/filter.h" #define LOCAL_FREE_TARGET (128) #define PERCPU_FREE_TARGET (4) @@ -40,6 +42,68 @@ static int create_map(int map_type, int map_flags, unsigned int size) return map_fd; } +static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, + void *value) +{ + struct bpf_load_program_attr prog; + struct bpf_create_map_attr map; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_9, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, fd), + BPF_LD_IMM64(BPF_REG_3, key), + 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_3, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_9, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + __u8 data[64] = {}; + int mfd, pfd, ret, zero = 0; + __u32 retval = 0; + + memset(&map, 0, sizeof(map)); + map.map_type = BPF_MAP_TYPE_ARRAY; + map.key_size = sizeof(int); + map.value_size = sizeof(unsigned long long); + map.max_entries = 1; + + mfd = bpf_create_map_xattr(&map); + if (mfd < 0) + return -1; + + insns[0].imm = mfd; + + memset(&prog, 0, sizeof(prog)); + prog.prog_type = BPF_PROG_TYPE_SCHED_CLS; + prog.insns = insns; + prog.insns_cnt = ARRAY_SIZE(insns); + prog.license = "GPL"; + + pfd = bpf_load_program_xattr(&prog, NULL, 0); + if (pfd < 0) { + close(mfd); + return -1; + } + + ret = bpf_prog_test_run(pfd, 1, data, sizeof(data), + NULL, NULL, &retval, NULL); + if (ret < 0 || retval != 42) { + ret = -1; + } else { + assert(!bpf_map_lookup_elem(mfd, &zero, value)); + ret = 0; + } + close(pfd); + close(mfd); + return ret; +} + static int map_subset(int map0, int map1) { unsigned long long next_key = 0; @@ -87,7 +151,7 @@ static int sched_next_online(int pid, int *next_to_try) return ret; } -/* Size of the LRU amp is 2 +/* Size of the LRU map is 2 * Add key=1 (+1 key) * Add key=2 (+1 key) * Lookup Key=1 @@ -157,7 +221,7 @@ static void test_lru_sanity0(int map_type, int map_flags) * stop LRU from removing key=1 */ key = 1; - assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); assert(value[0] == 1234); key = 3; @@ -167,7 +231,8 @@ static void test_lru_sanity0(int map_type, int map_flags) /* key=2 has been removed from the LRU */ key = 2; - assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1); + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && + errno == ENOENT); assert(map_equal(lru_map_fd, expected_map_fd)); @@ -221,7 +286,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) /* Lookup 1 to tgt_free/2 */ end_key = 1 + batch_size; for (key = 1; key < end_key; key++) { - assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); assert(!bpf_map_update_elem(expected_map_fd, &key, value, BPF_NOEXIST)); } @@ -322,10 +387,11 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) end_key = 1 + batch_size; value[0] = 4321; for (key = 1; key < end_key; key++) { - assert(bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && + errno == ENOENT); assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); assert(value[0] == 4321); assert(!bpf_map_update_elem(expected_map_fd, &key, value, BPF_NOEXIST)); @@ -404,7 +470,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) /* Lookup key 1 to tgt_free*3/2 */ end_key = tgt_free + batch_size; for (key = 1; key < end_key; key++) { - assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); assert(!bpf_map_update_elem(expected_map_fd, &key, value, BPF_NOEXIST)); } @@ -463,7 +529,7 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free) assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); for (key = 1; key <= tgt_free; key++) { - assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); assert(!bpf_map_update_elem(expected_map_fd, &key, value, BPF_NOEXIST)); } @@ -494,16 +560,16 @@ static void do_test_lru_sanity5(unsigned long long last_key, int map_fd) unsigned long long key, value[nr_cpus]; /* Ensure the last key inserted by previous CPU can be found */ - assert(!bpf_map_lookup_elem(map_fd, &last_key, value)); - + assert(!bpf_map_lookup_elem_with_ref_bit(map_fd, last_key, value)); value[0] = 1234; key = last_key + 1; assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST)); - assert(!bpf_map_lookup_elem(map_fd, &key, value)); + assert(!bpf_map_lookup_elem_with_ref_bit(map_fd, key, value)); /* Cannot find the last key because it was removed by LRU */ - assert(bpf_map_lookup_elem(map_fd, &last_key, value)); + assert(bpf_map_lookup_elem(map_fd, &last_key, value) == -1 && + errno == ENOENT); } /* Test map with only one element */ @@ -590,8 +656,8 @@ static void test_lru_sanity6(int map_type, int map_flags, int tgt_free) /* Make ref bit sticky for key: [1, tgt_free] */ for (stable_key = 1; stable_key <= tgt_free; stable_key++) { /* Mark the ref bit */ - assert(!bpf_map_lookup_elem(lru_map_fd, &stable_key, - value)); + assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, + stable_key, value)); } assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); @@ -612,6 +678,198 @@ static void test_lru_sanity6(int map_type, int map_flags, int tgt_free) printf("Pass\n"); } +/* Size of the LRU map is 2 + * Add key=1 (+1 key) + * Add key=2 (+1 key) + * Lookup Key=1 (datapath) + * Lookup Key=2 (syscall) + * Add Key=3 + * => Key=2 will be removed by LRU + * Iterate map. Only found key=1 and key=3 + */ +static void test_lru_sanity7(int map_type, int map_flags) +{ + unsigned long long key, value[nr_cpus]; + int lru_map_fd, expected_map_fd; + int next_cpu = 0; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, &next_cpu) != -1); + + if (map_flags & BPF_F_NO_COMMON_LRU) + lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus); + else + lru_map_fd = create_map(map_type, map_flags, 2); + assert(lru_map_fd != -1); + + expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, 2); + assert(expected_map_fd != -1); + + value[0] = 1234; + + /* insert key=1 element */ + + key = 1; + assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); + + /* BPF_NOEXIST means: add new element if it doesn't exist */ + assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST) == -1 + /* key=1 already exists */ + && errno == EEXIST); + + /* insert key=2 element */ + + /* check that key=2 is not found */ + key = 2; + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && + errno == ENOENT); + + /* BPF_EXIST means: update existing element */ + assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_EXIST) == -1 && + /* key=2 is not there */ + errno == ENOENT); + + assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); + + /* insert key=3 element */ + + /* check that key=3 is not found */ + key = 3; + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && + errno == ENOENT); + + /* check that key=1 can be found and mark the ref bit to + * stop LRU from removing key=1 + */ + key = 1; + assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); + assert(value[0] == 1234); + + /* check that key=2 can be found and do _not_ mark ref bit. + * this will be evicted on next update. + */ + key = 2; + assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(value[0] == 1234); + + key = 3; + assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); + + /* key=2 has been removed from the LRU */ + key = 2; + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && + errno == ENOENT); + + assert(map_equal(lru_map_fd, expected_map_fd)); + + close(expected_map_fd); + close(lru_map_fd); + + printf("Pass\n"); +} + +/* Size of the LRU map is 2 + * Add key=1 (+1 key) + * Add key=2 (+1 key) + * Lookup Key=1 (syscall) + * Lookup Key=2 (datapath) + * Add Key=3 + * => Key=1 will be removed by LRU + * Iterate map. Only found key=2 and key=3 + */ +static void test_lru_sanity8(int map_type, int map_flags) +{ + unsigned long long key, value[nr_cpus]; + int lru_map_fd, expected_map_fd; + int next_cpu = 0; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, &next_cpu) != -1); + + if (map_flags & BPF_F_NO_COMMON_LRU) + lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus); + else + lru_map_fd = create_map(map_type, map_flags, 2); + assert(lru_map_fd != -1); + + expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, 2); + assert(expected_map_fd != -1); + + value[0] = 1234; + + /* insert key=1 element */ + + key = 1; + assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); + + /* BPF_NOEXIST means: add new element if it doesn't exist */ + assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST) == -1 + /* key=1 already exists */ + && errno == EEXIST); + + /* insert key=2 element */ + + /* check that key=2 is not found */ + key = 2; + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && + errno == ENOENT); + + /* BPF_EXIST means: update existing element */ + assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_EXIST) == -1 && + /* key=2 is not there */ + errno == ENOENT); + + assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); + + /* insert key=3 element */ + + /* check that key=3 is not found */ + key = 3; + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && + errno == ENOENT); + + /* check that key=1 can be found and do _not_ mark ref bit. + * this will be evicted on next update. + */ + key = 1; + assert(!bpf_map_lookup_elem(lru_map_fd, &key, value)); + assert(value[0] == 1234); + + /* check that key=2 can be found and mark the ref bit to + * stop LRU from removing key=2 + */ + key = 2; + assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value)); + assert(value[0] == 1234); + + key = 3; + assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update_elem(expected_map_fd, &key, value, + BPF_NOEXIST)); + + /* key=1 has been removed from the LRU */ + key = 1; + assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && + errno == ENOENT); + + assert(map_equal(lru_map_fd, expected_map_fd)); + + close(expected_map_fd); + close(lru_map_fd); + + printf("Pass\n"); +} + int main(int argc, char **argv) { int map_types[] = {BPF_MAP_TYPE_LRU_HASH, @@ -637,6 +895,8 @@ int main(int argc, char **argv) test_lru_sanity4(map_types[t], map_flags[f], tgt_free); test_lru_sanity5(map_types[t], map_flags[f]); test_lru_sanity6(map_types[t], map_flags[f], tgt_free); + test_lru_sanity7(map_types[t], map_flags[f]); + test_lru_sanity8(map_types[t], map_flags[f]); printf("\n"); } diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index fb5566eb06808c1b372c9956a2769d009567cc74..bbe72073daee577233e430ce3be769aeb2c15f08 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -4,6 +4,8 @@ * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */ + +#define _GNU_SOURCE #include #include #include @@ -13,6 +15,7 @@ #include #include #include +#include #include typedef __u16 __sum16; @@ -34,6 +37,7 @@ typedef __u16 __sum16; #include #include #include +#include #include #include #include @@ -54,6 +58,12 @@ bool verifier_stats = false; #define MAGIC_BYTES 123 +#ifdef __x86_64__ +#define SYS_KPROBE_NAME "__x64_sys_nanosleep" +#else +#define SYS_KPROBE_NAME "sys_nanosleep" +#endif + /* ipv4 test vector */ static struct { struct ethhdr eth; @@ -2978,6 +2988,94 @@ static void test_send_signal(void) printf("test_send_signal:FAIL\n"); } +static void on_sample(void *ctx, int cpu, void *data, __u32 size) +{ + int cpu_data = *(int *)data, duration = 0; + cpu_set_t *cpu_seen = ctx; + + if (cpu_data != cpu) + CHECK(cpu_data != cpu, "check_cpu_data", + "cpu_data %d != cpu %d\n", cpu_data, cpu); + + CPU_SET(cpu, cpu_seen); +} + +static void test_perf_buffer(void) +{ + int err, prog_fd, nr_cpus, i, duration = 0; + const char *prog_name = "kprobe/sys_nanosleep"; + const char *file = "./test_perf_buffer.o"; + struct perf_buffer_opts pb_opts = {}; + struct bpf_map *perf_buf_map; + cpu_set_t cpu_set, cpu_seen; + struct bpf_program *prog; + struct bpf_object *obj; + struct perf_buffer *pb; + struct bpf_link *link; + + nr_cpus = libbpf_num_possible_cpus(); + if (CHECK(nr_cpus < 0, "nr_cpus", "err %d\n", nr_cpus)) + return; + + /* load program */ + err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd); + if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) + return; + + prog = bpf_object__find_program_by_title(obj, prog_name); + if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name)) + goto out_close; + + /* load map */ + perf_buf_map = bpf_object__find_map_by_name(obj, "perf_buf_map"); + if (CHECK(!perf_buf_map, "find_perf_buf_map", "not found\n")) + goto out_close; + + /* attach kprobe */ + link = bpf_program__attach_kprobe(prog, false /* retprobe */, + SYS_KPROBE_NAME); + if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link))) + goto out_close; + + /* set up perf buffer */ + pb_opts.sample_cb = on_sample; + pb_opts.ctx = &cpu_seen; + pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1, &pb_opts); + if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) + goto out_detach; + + /* trigger kprobe on every CPU */ + CPU_ZERO(&cpu_seen); + for (i = 0; i < nr_cpus; i++) { + CPU_ZERO(&cpu_set); + CPU_SET(i, &cpu_set); + + err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), + &cpu_set); + if (err && CHECK(err, "set_affinity", "cpu #%d, err %d\n", + i, err)) + goto out_detach; + + usleep(1); + } + + /* read perf buffer */ + err = perf_buffer__poll(pb, 100); + if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err)) + goto out_free_pb; + + if (CHECK(CPU_COUNT(&cpu_seen) != nr_cpus, "seen_cpu_cnt", + "expect %d, seen %d\n", nr_cpus, CPU_COUNT(&cpu_seen))) + goto out_free_pb; + +out_free_pb: + perf_buffer__free(pb); +out_detach: + bpf_link__destroy(link); +out_close: + bpf_object__close(obj); +} + int main(int ac, char **av) { srand(time(NULL)); @@ -3019,6 +3117,7 @@ int main(int ac, char **av) test_raw_tp_writable_reject_nbd_invalid(); test_raw_tp_writable_test_run(); test_send_signal(); + test_perf_buffer(); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c index a3bebd7c68ddc6262c5eaf6021bd8c8304b6a006..abc26248a7f182dc7d3a0e6372ef0196bae6b308 100644 --- a/tools/testing/selftests/bpf/test_sysctl.c +++ b/tools/testing/selftests/bpf/test_sysctl.c @@ -31,6 +31,7 @@ struct sysctl_test { enum bpf_attach_type attach_type; const char *sysctl; int open_flags; + int seek; const char *newval; const char *oldval; enum { @@ -139,7 +140,7 @@ static struct sysctl_test tests[] = { /* If (file_pos == X) */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, offsetof(struct bpf_sysctl, file_pos)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 3, 2), /* return ALLOW; */ BPF_MOV64_IMM(BPF_REG_0, 1), @@ -152,6 +153,7 @@ static struct sysctl_test tests[] = { .attach_type = BPF_CGROUP_SYSCTL, .sysctl = "kernel/ostype", .open_flags = O_RDONLY, + .seek = 3, .result = SUCCESS, }, { @@ -1442,6 +1444,11 @@ static int access_sysctl(const char *sysctl_path, if (fd < 0) return fd; + if (test->seek && lseek(fd, test->seek, SEEK_SET) == -1) { + log_err("lseek(%d) failed", test->seek); + goto err; + } + if (test->open_flags == O_RDONLY) { char buf[128]; diff --git a/tools/testing/selftests/bpf/test_tcp_rtt.c b/tools/testing/selftests/bpf/test_tcp_rtt.c new file mode 100644 index 0000000000000000000000000000000000000000..90c3862f74a856cc10685130a3313dedcdb1dd34 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcp_rtt.c @@ -0,0 +1,254 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "bpf_rlimit.h" +#include "bpf_util.h" +#include "cgroup_helpers.h" + +#define CG_PATH "/tcp_rtt" + +struct tcp_rtt_storage { + __u32 invoked; + __u32 dsack_dups; + __u32 delivered; + __u32 delivered_ce; + __u32 icsk_retransmits; +}; + +static void send_byte(int fd) +{ + char b = 0x55; + + if (write(fd, &b, sizeof(b)) != 1) + error(1, errno, "Failed to send single byte"); +} + +static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked, + __u32 dsack_dups, __u32 delivered, __u32 delivered_ce, + __u32 icsk_retransmits) +{ + int err = 0; + struct tcp_rtt_storage val; + + if (bpf_map_lookup_elem(map_fd, &client_fd, &val) < 0) + error(1, errno, "Failed to read socket storage"); + + if (val.invoked != invoked) { + log_err("%s: unexpected bpf_tcp_sock.invoked %d != %d", + msg, val.invoked, invoked); + err++; + } + + if (val.dsack_dups != dsack_dups) { + log_err("%s: unexpected bpf_tcp_sock.dsack_dups %d != %d", + msg, val.dsack_dups, dsack_dups); + err++; + } + + if (val.delivered != delivered) { + log_err("%s: unexpected bpf_tcp_sock.delivered %d != %d", + msg, val.delivered, delivered); + err++; + } + + if (val.delivered_ce != delivered_ce) { + log_err("%s: unexpected bpf_tcp_sock.delivered_ce %d != %d", + msg, val.delivered_ce, delivered_ce); + err++; + } + + if (val.icsk_retransmits != icsk_retransmits) { + log_err("%s: unexpected bpf_tcp_sock.icsk_retransmits %d != %d", + msg, val.icsk_retransmits, icsk_retransmits); + err++; + } + + return err; +} + +static int connect_to_server(int server_fd) +{ + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int fd; + + fd = socket(AF_INET, SOCK_STREAM, 0); + if (fd < 0) { + log_err("Failed to create client socket"); + return -1; + } + + if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + goto out; + } + + if (connect(fd, (const struct sockaddr *)&addr, len) < 0) { + log_err("Fail to connect to server"); + goto out; + } + + return fd; + +out: + close(fd); + return -1; +} + +static int run_test(int cgroup_fd, int server_fd) +{ + struct bpf_prog_load_attr attr = { + .prog_type = BPF_PROG_TYPE_SOCK_OPS, + .file = "./tcp_rtt.o", + .expected_attach_type = BPF_CGROUP_SOCK_OPS, + }; + struct bpf_object *obj; + struct bpf_map *map; + int client_fd; + int prog_fd; + int map_fd; + int err; + + err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + if (err) { + log_err("Failed to load BPF object"); + return -1; + } + + map = bpf_map__next(NULL, obj); + map_fd = bpf_map__fd(map); + + err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0); + if (err) { + log_err("Failed to attach BPF program"); + goto close_bpf_object; + } + + client_fd = connect_to_server(server_fd); + if (client_fd < 0) { + err = -1; + goto close_bpf_object; + } + + err += verify_sk(map_fd, client_fd, "syn-ack", + /*invoked=*/1, + /*dsack_dups=*/0, + /*delivered=*/1, + /*delivered_ce=*/0, + /*icsk_retransmits=*/0); + + send_byte(client_fd); + + err += verify_sk(map_fd, client_fd, "first payload byte", + /*invoked=*/2, + /*dsack_dups=*/0, + /*delivered=*/2, + /*delivered_ce=*/0, + /*icsk_retransmits=*/0); + + close(client_fd); + +close_bpf_object: + bpf_object__close(obj); + return err; +} + +static int start_server(void) +{ + struct sockaddr_in addr = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_LOOPBACK), + }; + int fd; + + fd = socket(AF_INET, SOCK_STREAM, 0); + if (fd < 0) { + log_err("Failed to create server socket"); + return -1; + } + + if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) < 0) { + log_err("Failed to bind socket"); + close(fd); + return -1; + } + + return fd; +} + +static void *server_thread(void *arg) +{ + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int fd = *(int *)arg; + int client_fd; + + if (listen(fd, 1) < 0) + error(1, errno, "Failed to listed on socket"); + + client_fd = accept(fd, (struct sockaddr *)&addr, &len); + if (client_fd < 0) + error(1, errno, "Failed to accept client"); + + /* Wait for the next connection (that never arrives) + * to keep this thread alive to prevent calling + * close() on client_fd. + */ + if (accept(fd, (struct sockaddr *)&addr, &len) >= 0) + error(1, errno, "Unexpected success in second accept"); + + close(client_fd); + + return NULL; +} + +int main(int args, char **argv) +{ + int server_fd, cgroup_fd; + int err = EXIT_SUCCESS; + pthread_t tid; + + if (setup_cgroup_environment()) + goto cleanup_obj; + + cgroup_fd = create_and_get_cgroup(CG_PATH); + if (cgroup_fd < 0) + goto cleanup_cgroup_env; + + if (join_cgroup(CG_PATH)) + goto cleanup_cgroup; + + server_fd = start_server(); + if (server_fd < 0) { + err = EXIT_FAILURE; + goto cleanup_cgroup; + } + + pthread_create(&tid, NULL, server_thread, (void *)&server_fd); + + if (run_test(cgroup_fd, server_fd)) + err = EXIT_FAILURE; + + close(server_fd); + + printf("test_sockopt_sk: %s\n", + err == EXIT_SUCCESS ? "PASSED" : "FAILED"); + +cleanup_cgroup: + close(cgroup_fd); +cleanup_cgroup_env: + cleanup_cgroup_environment(); +cleanup_obj: + return err; +} diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 2072b96cd3855ba0f009ac02a4ee35383bbeed72..0c255ee925b4cc83e46ed963533e9d5ebe41a5d9 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -108,6 +108,7 @@ struct bpf_test { __u64 data64[TEST_DATA_LEN / 8]; }; } retvals[MAX_TEST_RUNS]; + enum bpf_attach_type expected_attach_type; }; /* Note we want this to be 64 bit aligned so that the end of our array is @@ -17381,6 +17382,79 @@ static struct bpf_test tests[] = { .result = ACCEPT, .prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL, }, + #define BPF_SOCK_ADDR_STORE(field, off, res, err) \ + { \ + "wide store to bpf_sock_addr." #field "[" #off "]", \ + .insns = { \ + BPF_MOV64_IMM(BPF_REG_0, 1), \ + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \ + offsetof(struct bpf_sock_addr, field[off])), \ + BPF_EXIT_INSN(), \ + }, \ + .result = res, \ + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \ + .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \ + .errstr = err, \ + } + + /* user_ip6[0] is u64 aligned */ + BPF_SOCK_ADDR_STORE(user_ip6, 0, ACCEPT, + NULL), + BPF_SOCK_ADDR_STORE(user_ip6, 1, REJECT, + "invalid bpf_context access off=12 size=8"), + BPF_SOCK_ADDR_STORE(user_ip6, 2, ACCEPT, + NULL), + BPF_SOCK_ADDR_STORE(user_ip6, 3, REJECT, + "invalid bpf_context access off=20 size=8"), + + /* msg_src_ip6[0] is _not_ u64 aligned */ + BPF_SOCK_ADDR_STORE(msg_src_ip6, 0, REJECT, + "invalid bpf_context access off=44 size=8"), + BPF_SOCK_ADDR_STORE(msg_src_ip6, 1, ACCEPT, + NULL), + BPF_SOCK_ADDR_STORE(msg_src_ip6, 2, REJECT, + "invalid bpf_context access off=52 size=8"), + BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT, + "invalid bpf_context access off=56 size=8"), + + #undef BPF_SOCK_ADDR_STORE + + #define BPF_SOCK_ADDR_LOAD(field, off, res, err) \ + { \ + "wide load from bpf_sock_addr." #field "[" #off "]", \ + .insns = { \ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, \ + offsetof(struct bpf_sock_addr, field[off])), \ + BPF_MOV64_IMM(BPF_REG_0, 1), \ + BPF_EXIT_INSN(), \ + }, \ + .result = res, \ + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \ + .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \ + .errstr = err, \ + } + + /* user_ip6[0] is u64 aligned */ + BPF_SOCK_ADDR_LOAD(user_ip6, 0, ACCEPT, + NULL), + BPF_SOCK_ADDR_LOAD(user_ip6, 1, REJECT, + "invalid bpf_context access off=12 size=8"), + BPF_SOCK_ADDR_LOAD(user_ip6, 2, ACCEPT, + NULL), + BPF_SOCK_ADDR_LOAD(user_ip6, 3, REJECT, + "invalid bpf_context access off=20 size=8"), + + /* msg_src_ip6[0] is _not_ u64 aligned */ + BPF_SOCK_ADDR_LOAD(msg_src_ip6, 0, REJECT, + "invalid bpf_context access off=44 size=8"), + BPF_SOCK_ADDR_LOAD(msg_src_ip6, 1, ACCEPT, + NULL), + BPF_SOCK_ADDR_LOAD(msg_src_ip6, 2, REJECT, + "invalid bpf_context access off=52 size=8"), + BPF_SOCK_ADDR_LOAD(msg_src_ip6, 3, REJECT, + "invalid bpf_context access off=56 size=8"), + + #undef BPF_SOCK_ADDR_LOAD }; static int probe_filter_length(const struct bpf_insn *fp) @@ -17885,6 +17959,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, int fd_prog, expected_ret, alignment_prevented_execution; int prog_len, prog_type = test->prog_type; struct bpf_insn *prog = test->insns; + struct bpf_load_program_attr attr; int run_errs, run_successes; int map_fds[MAX_NR_MAPS]; const char *expected_err; @@ -17917,8 +17992,16 @@ static void do_test_single(struct bpf_test *test, bool unpriv, pflags |= BPF_F_STRICT_ALIGNMENT; if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) pflags |= BPF_F_ANY_ALIGNMENT; - fd_prog = bpf_verify_program(prog_type, prog, prog_len, pflags, - "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 4); + memset(&attr, 0, sizeof(attr)); + attr.prog_type = prog_type; + attr.expected_attach_type = test->expected_attach_type; + attr.insns = prog; + attr.insns_cnt = prog_len; + attr.license = "GPL"; + attr.log_level = 4; + attr.prog_flags = pflags; + + fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog)); saved_errno = errno; if (fd_prog < 0 && !bpf_probe_prog_type(prog_type, 0)) { printf("SKIP (unsupported program type %d)\n", prog_type); @@ -17949,7 +18032,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, printf("FAIL\nUnexpected success to load!\n"); goto fail_log; } - if (!strstr(bpf_vlog, expected_err)) { + if (!expected_err || !strstr(bpf_vlog, expected_err)) { printf("FAIL\nUnexpected error message!\n\tEXP: %s\n\tRES: %s\n", expected_err, bpf_vlog); goto fail_log;