diff options
Diffstat (limited to 'tools')
21 files changed, 1212 insertions, 38 deletions
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 1828bba19020..dc6daa193557 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -222,6 +222,11 @@ int mount_bpffs_for_pin(const char *name) int err = 0; file = malloc(strlen(name) + 1); + if (!file) { + p_err("mem alloc failed"); + return -1; + } + strcpy(file, name); dir = dirname(file); diff --git a/tools/io_uring/io_uring-cp.c b/tools/io_uring/io_uring-cp.c index 81461813ec62..d9bd6f5f8f46 100644 --- a/tools/io_uring/io_uring-cp.c +++ b/tools/io_uring/io_uring-cp.c @@ -131,8 +131,7 @@ static int copy_file(struct io_uring *ring, off_t insize) writes = reads = offset = 0; while (insize || write_left) { - unsigned long had_reads; - int got_comp; + int had_reads, got_comp; /* * Queue up as many reads as we can @@ -174,8 +173,13 @@ static int copy_file(struct io_uring *ring, off_t insize) if (!got_comp) { ret = io_uring_wait_cqe(ring, &cqe); got_comp = 1; - } else + } else { ret = io_uring_peek_cqe(ring, &cqe); + if (ret == -EAGAIN) { + cqe = NULL; + ret = 0; + } + } if (ret < 0) { fprintf(stderr, "io_uring_peek_cqe: %s\n", strerror(-ret)); @@ -194,7 +198,7 @@ static int copy_file(struct io_uring *ring, off_t insize) fprintf(stderr, "cqe failed: %s\n", strerror(-cqe->res)); return 1; - } else if ((size_t) cqe->res != data->iov.iov_len) { + } else if (cqe->res != data->iov.iov_len) { /* Short read/write, adjust and requeue */ data->iov.iov_base += cqe->res; data->iov.iov_len -= cqe->res; @@ -221,6 +225,25 @@ static int copy_file(struct io_uring *ring, off_t insize) } } + /* wait out pending writes */ + while (writes) { + struct io_data *data; + + ret = io_uring_wait_cqe(ring, &cqe); + if (ret) { + fprintf(stderr, "wait_cqe=%d\n", ret); + return 1; + } + if (cqe->res < 0) { + fprintf(stderr, "write res=%d\n", cqe->res); + return 1; + } + data = io_uring_cqe_get_data(cqe); + free(data); + writes--; + io_uring_cqe_seen(ring, cqe); + } + return 0; } diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index b46760b93bb4..7ff3d5ce44f9 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -804,6 +804,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) btf->nr_types = 0; btf->start_id = 1; btf->start_str_off = 0; + btf->fd = -1; if (base_btf) { btf->base_btf = base_btf; @@ -832,8 +833,6 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) if (err) goto done; - btf->fd = -1; - done: if (err) { btf__free(btf); diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index ecaae2927ab8..cd8c703dde71 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -75,6 +75,9 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT; break; + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + xattr.expected_attach_type = BPF_CGROUP_GETSOCKOPT; + break; case BPF_PROG_TYPE_SK_LOOKUP: xattr.expected_attach_type = BPF_SK_LOOKUP; break; @@ -104,7 +107,6 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: - case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 22f8326547eb..bc1f64873c8f 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -2434,6 +2434,22 @@ static int cs_etm__process_event(struct perf_session *session, return 0; } +static void dump_queued_data(struct cs_etm_auxtrace *etm, + struct perf_record_auxtrace *event) +{ + struct auxtrace_buffer *buf; + unsigned int i; + /* + * Find all buffers with same reference in the queues and dump them. + * This is because the queues can contain multiple entries of the same + * buffer that were split on aux records. + */ + for (i = 0; i < etm->queues.nr_queues; ++i) + list_for_each_entry(buf, &etm->queues.queue_array[i].head, list) + if (buf->reference == event->reference) + cs_etm__dump_event(etm, buf); +} + static int cs_etm__process_auxtrace_event(struct perf_session *session, union perf_event *event, struct perf_tool *tool __maybe_unused) @@ -2466,7 +2482,8 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, cs_etm__dump_event(etm, buffer); auxtrace_buffer__put_data(buffer); } - } + } else if (dump_trace) + dump_queued_data(etm, &event->auxtrace); return 0; } @@ -3042,7 +3059,6 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (dump_trace) { cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu); - return 0; } err = cs_etm__synth_events(etm, session); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 72e7f3616157..8af693d9678c 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -192,8 +192,6 @@ struct map *map__new(struct machine *machine, u64 start, u64 len, if (!(prot & PROT_EXEC)) dso__set_loaded(dso); } - - nsinfo__put(dso->nsinfo); dso->nsinfo = nsi; if (build_id__is_defined(bid)) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index a1bd7007a8b4..fc683bc41715 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -742,9 +742,13 @@ struct pmu_events_map *__weak pmu_events_map__find(void) return perf_pmu__find_map(NULL); } -static bool perf_pmu__valid_suffix(char *pmu_name, char *tok) +/* + * Suffix must be in form tok_{digits}, or tok{digits}, or same as pmu_name + * to be valid. + */ +static bool perf_pmu__valid_suffix(const char *pmu_name, char *tok) { - char *p; + const char *p; if (strncmp(pmu_name, tok, strlen(tok))) return false; @@ -753,12 +757,16 @@ static bool perf_pmu__valid_suffix(char *pmu_name, char *tok) if (*p == 0) return true; - if (*p != '_') - return false; + if (*p == '_') + ++p; - ++p; - if (*p == 0 || !isdigit(*p)) - return false; + /* Ensure we end in a number */ + while (1) { + if (!isdigit(*p)) + return false; + if (*(++p) == 0) + break; + } return true; } @@ -789,12 +797,19 @@ bool pmu_uncore_alias_match(const char *pmu_name, const char *name) * match "socket" in "socketX_pmunameY" and then "pmuname" in * "pmunameY". */ - for (; tok; name += strlen(tok), tok = strtok_r(NULL, ",", &tmp)) { + while (1) { + char *next_tok = strtok_r(NULL, ",", &tmp); + name = strstr(name, tok); - if (!name || !perf_pmu__valid_suffix((char *)name, tok)) { + if (!name || + (!next_tok && !perf_pmu__valid_suffix(name, tok))) { res = false; goto out; } + if (!next_tok) + break; + tok = next_tok; + name += strlen(tok); } res = true; diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index a3e593ddfafc..2debba4e8a3a 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -1,4 +1,233 @@ { + "map access: known scalar += value_ptr unknown vs const", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr const vs unknown", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2), + BPF_MOV64_IMM(BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr const vs const (ne)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2), + BPF_MOV64_IMM(BPF_REG_1, 3), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr const vs const (eq)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr unknown vs unknown (eq)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr unknown vs unknown (lt)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ + "map access: known scalar += value_ptr unknown vs unknown (gt)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps, paths or scalars", + .result = ACCEPT, + .retval = 1, +}, +{ "map access: known scalar += value_ptr from different maps", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 06a351b4f93b..0709af0144c8 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -38,6 +38,7 @@ /x86_64/xen_vmcall_test /x86_64/xss_msr_test /x86_64/vmx_pmu_msrs_test +/access_tracking_perf_test /demand_paging_test /dirty_log_test /dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index b853be2ae3c6..5832f510a16c 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -71,6 +71,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test +TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c index a16c8f05366c..cc898181faab 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -1019,7 +1019,8 @@ static __u64 sve_rejects_set[] = { #define VREGS_SUBLIST \ { "vregs", .regs = vregs, .regs_n = ARRAY_SIZE(vregs), } #define PMU_SUBLIST \ - { "pmu", .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), } + { "pmu", .capability = KVM_CAP_ARM_PMU_V3, .feature = KVM_ARM_VCPU_PMU_V3, \ + .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), } #define SVE_SUBLIST \ { "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \ .regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \ diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c new file mode 100644 index 000000000000..e2baa187a21e --- /dev/null +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -0,0 +1,429 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * access_tracking_perf_test + * + * Copyright (C) 2021, Google, Inc. + * + * This test measures the performance effects of KVM's access tracking. + * Access tracking is driven by the MMU notifiers test_young, clear_young, and + * clear_flush_young. These notifiers do not have a direct userspace API, + * however the clear_young notifier can be triggered by marking a pages as idle + * in /sys/kernel/mm/page_idle/bitmap. This test leverages that mechanism to + * enable access tracking on guest memory. + * + * To measure performance this test runs a VM with a configurable number of + * vCPUs that each touch every page in disjoint regions of memory. Performance + * is measured in the time it takes all vCPUs to finish touching their + * predefined region. + * + * Note that a deterministic correctness test of access tracking is not possible + * by using page_idle as it exists today. This is for a few reasons: + * + * 1. page_idle only issues clear_young notifiers, which lack a TLB flush. This + * means subsequent guest accesses are not guaranteed to see page table + * updates made by KVM until some time in the future. + * + * 2. page_idle only operates on LRU pages. Newly allocated pages are not + * immediately allocated to LRU lists. Instead they are held in a "pagevec", + * which is drained to LRU lists some time in the future. There is no + * userspace API to force this drain to occur. + * + * These limitations are worked around in this test by using a large enough + * region of memory for each vCPU such that the number of translations cached in + * the TLB and the number of pages held in pagevecs are a small fraction of the + * overall workload. And if either of those conditions are not true this test + * will fail rather than silently passing. + */ +#include <inttypes.h> +#include <limits.h> +#include <pthread.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include "kvm_util.h" +#include "test_util.h" +#include "perf_test_util.h" +#include "guest_modes.h" + +/* Global variable used to synchronize all of the vCPU threads. */ +static int iteration = -1; + +/* Defines what vCPU threads should do during a given iteration. */ +static enum { + /* Run the vCPU to access all its memory. */ + ITERATION_ACCESS_MEMORY, + /* Mark the vCPU's memory idle in page_idle. */ + ITERATION_MARK_IDLE, +} iteration_work; + +/* Set to true when vCPU threads should exit. */ +static bool done; + +/* The iteration that was last completed by each vCPU. */ +static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; + +/* Whether to overlap the regions of memory vCPUs access. */ +static bool overlap_memory_access; + +struct test_params { + /* The backing source for the region of memory. */ + enum vm_mem_backing_src_type backing_src; + + /* The amount of memory to allocate for each vCPU. */ + uint64_t vcpu_memory_bytes; + + /* The number of vCPUs to create in the VM. */ + int vcpus; +}; + +static uint64_t pread_uint64(int fd, const char *filename, uint64_t index) +{ + uint64_t value; + off_t offset = index * sizeof(value); + + TEST_ASSERT(pread(fd, &value, sizeof(value), offset) == sizeof(value), + "pread from %s offset 0x%" PRIx64 " failed!", + filename, offset); + + return value; + +} + +#define PAGEMAP_PRESENT (1ULL << 63) +#define PAGEMAP_PFN_MASK ((1ULL << 55) - 1) + +static uint64_t lookup_pfn(int pagemap_fd, struct kvm_vm *vm, uint64_t gva) +{ + uint64_t hva = (uint64_t) addr_gva2hva(vm, gva); + uint64_t entry; + uint64_t pfn; + + entry = pread_uint64(pagemap_fd, "pagemap", hva / getpagesize()); + if (!(entry & PAGEMAP_PRESENT)) + return 0; + + pfn = entry & PAGEMAP_PFN_MASK; + if (!pfn) { + print_skip("Looking up PFNs requires CAP_SYS_ADMIN"); + exit(KSFT_SKIP); + } + + return pfn; +} + +static bool is_page_idle(int page_idle_fd, uint64_t pfn) +{ + uint64_t bits = pread_uint64(page_idle_fd, "page_idle", pfn / 64); + + return !!((bits >> (pfn % 64)) & 1); +} + +static void mark_page_idle(int page_idle_fd, uint64_t pfn) +{ + uint64_t bits = 1ULL << (pfn % 64); + + TEST_ASSERT(pwrite(page_idle_fd, &bits, 8, 8 * (pfn / 64)) == 8, + "Set page_idle bits for PFN 0x%" PRIx64, pfn); +} + +static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id) +{ + uint64_t base_gva = perf_test_args.vcpu_args[vcpu_id].gva; + uint64_t pages = perf_test_args.vcpu_args[vcpu_id].pages; + uint64_t page; + uint64_t still_idle = 0; + uint64_t no_pfn = 0; + int page_idle_fd; + int pagemap_fd; + + /* If vCPUs are using an overlapping region, let vCPU 0 mark it idle. */ + if (overlap_memory_access && vcpu_id) + return; + + page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR); + TEST_ASSERT(page_idle_fd > 0, "Failed to open page_idle."); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + TEST_ASSERT(pagemap_fd > 0, "Failed to open pagemap."); + + for (page = 0; page < pages; page++) { + uint64_t gva = base_gva + page * perf_test_args.guest_page_size; + uint64_t pfn = lookup_pfn(pagemap_fd, vm, gva); + + if (!pfn) { + no_pfn++; + continue; + } + + if (is_page_idle(page_idle_fd, pfn)) { + still_idle++; + continue; + } + + mark_page_idle(page_idle_fd, pfn); + } + + /* + * Assumption: Less than 1% of pages are going to be swapped out from + * under us during this test. + */ + TEST_ASSERT(no_pfn < pages / 100, + "vCPU %d: No PFN for %" PRIu64 " out of %" PRIu64 " pages.", + vcpu_id, no_pfn, pages); + + /* + * Test that at least 90% of memory has been marked idle (the rest might + * not be marked idle because the pages have not yet made it to an LRU + * list or the translations are still cached in the TLB). 90% is + * arbitrary; high enough that we ensure most memory access went through + * access tracking but low enough as to not make the test too brittle + * over time and across architectures. + */ + TEST_ASSERT(still_idle < pages / 10, + "vCPU%d: Too many pages still idle (%"PRIu64 " out of %" + PRIu64 ").\n", + vcpu_id, still_idle, pages); + + close(page_idle_fd); + close(pagemap_fd); +} + +static void assert_ucall(struct kvm_vm *vm, uint32_t vcpu_id, + uint64_t expected_ucall) +{ + struct ucall uc; + uint64_t actual_ucall = get_ucall(vm, vcpu_id, &uc); + + TEST_ASSERT(expected_ucall == actual_ucall, + "Guest exited unexpectedly (expected ucall %" PRIu64 + ", got %" PRIu64 ")", + expected_ucall, actual_ucall); +} + +static bool spin_wait_for_next_iteration(int *current_iteration) +{ + int last_iteration = *current_iteration; + + do { + if (READ_ONCE(done)) + return false; + + *current_iteration = READ_ONCE(iteration); + } while (last_iteration == *current_iteration); + + return true; +} + +static void *vcpu_thread_main(void *arg) +{ + struct perf_test_vcpu_args *vcpu_args = arg; + struct kvm_vm *vm = perf_test_args.vm; + int vcpu_id = vcpu_args->vcpu_id; + int current_iteration = -1; + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + + while (spin_wait_for_next_iteration(¤t_iteration)) { + switch (READ_ONCE(iteration_work)) { + case ITERATION_ACCESS_MEMORY: + vcpu_run(vm, vcpu_id); + assert_ucall(vm, vcpu_id, UCALL_SYNC); + break; + case ITERATION_MARK_IDLE: + mark_vcpu_memory_idle(vm, vcpu_id); + break; + }; + + vcpu_last_completed_iteration[vcpu_id] = current_iteration; + } + + return NULL; +} + +static void spin_wait_for_vcpu(int vcpu_id, int target_iteration) +{ + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != + target_iteration) { + continue; + } +} + +/* The type of memory accesses to perform in the VM. */ +enum access_type { + ACCESS_READ, + ACCESS_WRITE, +}; + +static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description) +{ + struct timespec ts_start; + struct timespec ts_elapsed; + int next_iteration; + int vcpu_id; + + /* Kick off the vCPUs by incrementing iteration. */ + next_iteration = ++iteration; + + clock_gettime(CLOCK_MONOTONIC, &ts_start); + + /* Wait for all vCPUs to finish the iteration. */ + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) + spin_wait_for_vcpu(vcpu_id, next_iteration); + + ts_elapsed = timespec_elapsed(ts_start); + pr_info("%-30s: %ld.%09lds\n", + description, ts_elapsed.tv_sec, ts_elapsed.tv_nsec); +} + +static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access, + const char *description) +{ + perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1; + sync_global_to_guest(vm, perf_test_args); + iteration_work = ITERATION_ACCESS_MEMORY; + run_iteration(vm, vcpus, description); +} + +static void mark_memory_idle(struct kvm_vm *vm, int vcpus) +{ + /* + * Even though this parallelizes the work across vCPUs, this is still a + * very slow operation because page_idle forces the test to mark one pfn + * at a time and the clear_young notifier serializes on the KVM MMU + * lock. + */ + pr_debug("Marking VM memory idle (slow)...\n"); + iteration_work = ITERATION_MARK_IDLE; + run_iteration(vm, vcpus, "Mark memory idle"); +} + +static pthread_t *create_vcpu_threads(int vcpus) +{ + pthread_t *vcpu_threads; + int i; + + vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0])); + TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads."); + + for (i = 0; i < vcpus; i++) { + vcpu_last_completed_iteration[i] = iteration; + pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main, + &perf_test_args.vcpu_args[i]); + } + + return vcpu_threads; +} + +static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus) +{ + int i; + + /* Set done to signal the vCPU threads to exit */ + done = true; + + for (i = 0; i < vcpus; i++) + pthread_join(vcpu_threads[i], NULL); +} + +static void run_test(enum vm_guest_mode mode, void *arg) +{ + struct test_params *params = arg; + struct kvm_vm *vm; + pthread_t *vcpu_threads; + int vcpus = params->vcpus; + + vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, + params->backing_src); + + perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes, + !overlap_memory_access); + + vcpu_threads = create_vcpu_threads(vcpus); + + pr_info("\n"); + access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory"); + + /* As a control, read and write to the populated memory first. */ + access_memory(vm, vcpus, ACCESS_WRITE, "Writing to populated memory"); + access_memory(vm, vcpus, ACCESS_READ, "Reading from populated memory"); + + /* Repeat on memory that has been marked as idle. */ + mark_memory_idle(vm, vcpus); + access_memory(vm, vcpus, ACCESS_WRITE, "Writing to idle memory"); + mark_memory_idle(vm, vcpus); + access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory"); + + terminate_vcpu_threads(vcpu_threads, vcpus); + free(vcpu_threads); + perf_test_destroy_vm(vm); +} + +static void help(char *name) +{ + puts(""); + printf("usage: %s [-h] [-m mode] [-b vcpu_bytes] [-v vcpus] [-o] [-s mem_type]\n", + name); + puts(""); + printf(" -h: Display this help message."); + guest_modes_help(); + printf(" -b: specify the size of the memory region which should be\n" + " dirtied by each vCPU. e.g. 10M or 3G.\n" + " (default: 1G)\n"); + printf(" -v: specify the number of vCPUs to run.\n"); + printf(" -o: Overlap guest memory accesses instead of partitioning\n" + " them into a separate region of memory for each vCPU.\n"); + printf(" -s: specify the type of memory that should be used to\n" + " back the guest data region.\n\n"); + backing_src_help(); + puts(""); + exit(0); +} + +int main(int argc, char *argv[]) +{ + struct test_params params = { + .backing_src = VM_MEM_SRC_ANONYMOUS, + .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE, + .vcpus = 1, + }; + int page_idle_fd; + int opt; + + guest_modes_append_default(); + + while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) { + switch (opt) { + case 'm': + guest_modes_cmdline(optarg); + break; + case 'b': + params.vcpu_memory_bytes = parse_size(optarg); + break; + case 'v': + params.vcpus = atoi(optarg); + break; + case 'o': + overlap_memory_access = true; + break; + case 's': + params.backing_src = parse_backing_src_type(optarg); + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR); + if (page_idle_fd < 0) { + print_skip("CONFIG_IDLE_PAGE_TRACKING is not enabled"); + exit(KSFT_SKIP); + } + close(page_idle_fd); + + for_each_guest_mode(run_test, ¶ms); + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 04a2641261be..80cbd3a748c0 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -312,6 +312,7 @@ int main(int argc, char *argv[]) break; case 'o': p.partition_vcpu_memory_access = false; + break; case 's': p.backing_src = parse_backing_src_type(optarg); break; diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h index 412eaee7884a..b66910702c0a 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -117,7 +117,7 @@ #define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) #define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) #define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) -#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE BIT(4) +#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4) #define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) #define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) @@ -182,4 +182,7 @@ #define HV_STATUS_INVALID_CONNECTION_ID 18 #define HV_STATUS_INSUFFICIENT_BUFFERS 19 +/* hypercall options */ +#define HV_HYPERCALL_FAST_BIT BIT(16) + #endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index b0031f2d38fd..ecec30865a74 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -320,7 +320,7 @@ int main(int ac, char **av) run_delay = get_run_delay(); pthread_create(&thread, &attr, do_steal_time, NULL); do - pthread_yield(); + sched_yield(); while (get_run_delay() - run_delay < MIN_RUN_DELAY_NS); pthread_join(thread, NULL); run_delay = get_run_delay() - run_delay; diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index bab10ae787b6..e0b2bb1339b1 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -215,7 +215,7 @@ int main(void) vcpu_set_hv_cpuid(vm, VCPU_ID); tsc_page_gva = vm_vaddr_alloc_page(vm); - memset(addr_gpa2hva(vm, tsc_page_gva), 0x0, getpagesize()); + memset(addr_gva2hva(vm, tsc_page_gva), 0x0, getpagesize()); TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0, "TSC page has to be page aligned\n"); vcpu_args_set(vm, VCPU_ID, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva)); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index af27c7e829c1..91d88aaa9899 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -47,6 +47,7 @@ static void do_wrmsr(u32 idx, u64 val) } static int nr_gp; +static int nr_ud; static inline u64 hypercall(u64 control, vm_vaddr_t input_address, vm_vaddr_t output_address) @@ -80,6 +81,12 @@ static void guest_gp_handler(struct ex_regs *regs) regs->rip = (uint64_t)&wrmsr_end; } +static void guest_ud_handler(struct ex_regs *regs) +{ + nr_ud++; + regs->rip += 3; +} + struct msr_data { uint32_t idx; bool available; @@ -90,6 +97,7 @@ struct msr_data { struct hcall_data { uint64_t control; uint64_t expect; + bool ud_expected; }; static void guest_msr(struct msr_data *msr) @@ -117,13 +125,26 @@ static void guest_msr(struct msr_data *msr) static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) { int i = 0; + u64 res, input, output; wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID); wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa); while (hcall->control) { - GUEST_ASSERT(hypercall(hcall->control, pgs_gpa, - pgs_gpa + 4096) == hcall->expect); + nr_ud = 0; + if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) { + input = pgs_gpa; + output = pgs_gpa + 4096; + } else { + input = output = 0; + } + + res = hypercall(hcall->control, input, output); + if (hcall->ud_expected) + GUEST_ASSERT(nr_ud == 1); + else + GUEST_ASSERT(res == hcall->expect); + GUEST_SYNC(i++); } @@ -552,8 +573,18 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall recomm.ebx = 0xfff; hcall->expect = HV_STATUS_SUCCESS; break; - case 17: + /* XMM fast hypercall */ + hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT; + hcall->ud_expected = true; + break; + case 18: + feat.edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; + hcall->ud_expected = false; + hcall->expect = HV_STATUS_SUCCESS; + break; + + case 19: /* END */ hcall->control = 0; break; @@ -625,6 +656,10 @@ int main(void) /* Test hypercalls */ vm = vm_create_default(VCPU_ID, 0, guest_hcall); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); + /* Hypercall input/output */ hcall_page = vm_vaddr_alloc_pages(vm, 2); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c index f23438d512c5..3d7dde2c321b 100644 --- a/tools/testing/selftests/net/ipsec.c +++ b/tools/testing/selftests/net/ipsec.c @@ -484,13 +484,16 @@ enum desc_type { MONITOR_ACQUIRE, EXPIRE_STATE, EXPIRE_POLICY, + SPDINFO_ATTRS, }; const char *desc_name[] = { "create tunnel", "alloc spi", "monitor acquire", "expire state", - "expire policy" + "expire policy", + "spdinfo attributes", + "" }; struct xfrm_desc { enum desc_type type; @@ -1593,6 +1596,155 @@ out_close: return ret; } +static int xfrm_spdinfo_set_thresh(int xfrm_sock, uint32_t *seq, + unsigned thresh4_l, unsigned thresh4_r, + unsigned thresh6_l, unsigned thresh6_r, + bool add_bad_attr) + +{ + struct { + struct nlmsghdr nh; + union { + uint32_t unused; + int error; + }; + char attrbuf[MAX_PAYLOAD]; + } req; + struct xfrmu_spdhthresh thresh; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.unused)); + req.nh.nlmsg_type = XFRM_MSG_NEWSPDINFO; + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_seq = (*seq)++; + + thresh.lbits = thresh4_l; + thresh.rbits = thresh4_r; + if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SPD_IPV4_HTHRESH, &thresh, sizeof(thresh))) + return -1; + + thresh.lbits = thresh6_l; + thresh.rbits = thresh6_r; + if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SPD_IPV6_HTHRESH, &thresh, sizeof(thresh))) + return -1; + + if (add_bad_attr) { + BUILD_BUG_ON(XFRMA_IF_ID <= XFRMA_SPD_MAX + 1); + if (rtattr_pack(&req.nh, sizeof(req), XFRMA_IF_ID, NULL, 0)) { + pr_err("adding attribute failed: no space"); + return -1; + } + } + + if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) { + pr_err("send()"); + return -1; + } + + if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) { + pr_err("recv()"); + return -1; + } else if (req.nh.nlmsg_type != NLMSG_ERROR) { + printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type); + return -1; + } + + if (req.error) { + printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error)); + return -1; + } + + return 0; +} + +static int xfrm_spdinfo_attrs(int xfrm_sock, uint32_t *seq) +{ + struct { + struct nlmsghdr nh; + union { + uint32_t unused; + int error; + }; + char attrbuf[MAX_PAYLOAD]; + } req; + + if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 31, 120, 16, false)) { + pr_err("Can't set SPD HTHRESH"); + return KSFT_FAIL; + } + + memset(&req, 0, sizeof(req)); + + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.unused)); + req.nh.nlmsg_type = XFRM_MSG_GETSPDINFO; + req.nh.nlmsg_flags = NLM_F_REQUEST; + req.nh.nlmsg_seq = (*seq)++; + if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) { + pr_err("send()"); + return KSFT_FAIL; + } + + if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) { + pr_err("recv()"); + return KSFT_FAIL; + } else if (req.nh.nlmsg_type == XFRM_MSG_NEWSPDINFO) { + size_t len = NLMSG_PAYLOAD(&req.nh, sizeof(req.unused)); + struct rtattr *attr = (void *)req.attrbuf; + int got_thresh = 0; + + for (; RTA_OK(attr, len); attr = RTA_NEXT(attr, len)) { + if (attr->rta_type == XFRMA_SPD_IPV4_HTHRESH) { + struct xfrmu_spdhthresh *t = RTA_DATA(attr); + + got_thresh++; + if (t->lbits != 32 || t->rbits != 31) { + pr_err("thresh differ: %u, %u", + t->lbits, t->rbits); + return KSFT_FAIL; + } + } + if (attr->rta_type == XFRMA_SPD_IPV6_HTHRESH) { + struct xfrmu_spdhthresh *t = RTA_DATA(attr); + + got_thresh++; + if (t->lbits != 120 || t->rbits != 16) { + pr_err("thresh differ: %u, %u", + t->lbits, t->rbits); + return KSFT_FAIL; + } + } + } + if (got_thresh != 2) { + pr_err("only %d thresh returned by XFRM_MSG_GETSPDINFO", got_thresh); + return KSFT_FAIL; + } + } else if (req.nh.nlmsg_type != NLMSG_ERROR) { + printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type); + return KSFT_FAIL; + } else { + printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error)); + return -1; + } + + /* Restore the default */ + if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 32, 128, 128, false)) { + pr_err("Can't restore SPD HTHRESH"); + return KSFT_FAIL; + } + + /* + * At this moment xfrm uses nlmsg_parse_deprecated(), which + * implies NL_VALIDATE_LIBERAL - ignoring attributes with + * (type > maxtype). nla_parse_depricated_strict() would enforce + * it. Or even stricter nla_parse(). + * Right now it's not expected to fail, but to be ignored. + */ + if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 32, 128, 128, true)) + return KSFT_PASS; + + return KSFT_PASS; +} + static int child_serv(int xfrm_sock, uint32_t *seq, unsigned int nr, int cmd_fd, void *buf, struct xfrm_desc *desc) { @@ -1717,6 +1869,9 @@ static int child_f(unsigned int nr, int test_desc_fd, int cmd_fd, void *buf) case EXPIRE_POLICY: ret = xfrm_expire_policy(xfrm_sock, &seq, nr, &desc); break; + case SPDINFO_ATTRS: + ret = xfrm_spdinfo_attrs(xfrm_sock, &seq); + break; default: printk("Unknown desc type %d", desc.type); exit(KSFT_FAIL); @@ -1994,8 +2149,10 @@ static int write_proto_plan(int fd, int proto) * sizeof(xfrm_user_polexpire) = 168 | sizeof(xfrm_user_polexpire) = 176 * * Check the affected by the UABI difference structures. + * Also, check translation for xfrm_set_spdinfo: it has it's own attributes + * which needs to be correctly copied, but not translated. */ -const unsigned int compat_plan = 4; +const unsigned int compat_plan = 5; static int write_compat_struct_tests(int test_desc_fd) { struct xfrm_desc desc = {}; @@ -2019,6 +2176,10 @@ static int write_compat_struct_tests(int test_desc_fd) if (__write_desc(test_desc_fd, &desc)) return -1; + desc.type = SPDINFO_ATTRS; + if (__write_desc(test_desc_fd, &desc)) + return -1; + return 0; } diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index 6365c7fd1262..bd6288302094 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -11,9 +11,11 @@ #include <sys/socket.h> #include <sys/wait.h> #include <linux/tcp.h> +#include <linux/udp.h> #include <arpa/inet.h> #include <net/if.h> #include <netinet/in.h> +#include <netinet/ip.h> #include <netdb.h> #include <fcntl.h> #include <libgen.h> @@ -27,6 +29,10 @@ #include <time.h> #include <errno.h> +#include <linux/xfrm.h> +#include <linux/ipsec.h> +#include <linux/pfkeyv2.h> + #ifndef IPV6_UNICAST_IF #define IPV6_UNICAST_IF 76 #endif @@ -114,6 +120,9 @@ struct sock_args { struct in_addr in; struct in6_addr in6; } expected_raddr; + + /* ESP in UDP encap test */ + int use_xfrm; }; static int server_mode; @@ -1346,6 +1355,41 @@ static int bind_socket(int sd, struct sock_args *args) return 0; } +static int config_xfrm_policy(int sd, struct sock_args *args) +{ + struct xfrm_userpolicy_info policy = {}; + int type = UDP_ENCAP_ESPINUDP; + int xfrm_af = IP_XFRM_POLICY; + int level = SOL_IP; + + if (args->type != SOCK_DGRAM) { + log_error("Invalid socket type. Only DGRAM could be used for XFRM\n"); + return 1; + } + + policy.action = XFRM_POLICY_ALLOW; + policy.sel.family = args->version; + if (args->version == AF_INET6) { + xfrm_af = IPV6_XFRM_POLICY; + level = SOL_IPV6; + } + + policy.dir = XFRM_POLICY_OUT; + if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0) + return 1; + + policy.dir = XFRM_POLICY_IN; + if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0) + return 1; + + if (setsockopt(sd, IPPROTO_UDP, UDP_ENCAP, &type, sizeof(type)) < 0) { + log_err_errno("Failed to set xfrm encap"); + return 1; + } + + return 0; +} + static int lsock_init(struct sock_args *args) { long flags; @@ -1389,6 +1433,11 @@ static int lsock_init(struct sock_args *args) if (fcntl(sd, F_SETFD, FD_CLOEXEC) < 0) log_err_errno("Failed to set close-on-exec flag"); + if (args->use_xfrm && config_xfrm_policy(sd, args)) { + log_err_errno("Failed to set xfrm policy"); + goto err; + } + out: return sd; @@ -1772,7 +1821,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) return client_status; } -#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6L:0:1:2:3:Fbq" +#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq" static void print_usage(char *prog) { @@ -1795,6 +1844,7 @@ static void print_usage(char *prog) " -D|R datagram (D) / raw (R) socket (default stream)\n" " -l addr local address to bind to in server mode\n" " -c addr local address to bind to in client mode\n" + " -x configure XFRM policy on socket\n" "\n" " -d dev bind socket to given device name\n" " -I dev bind socket to given device name - server mode\n" @@ -1966,6 +2016,9 @@ int main(int argc, char *argv[]) case 'q': quiet = 1; break; + case 'x': + args.use_xfrm = 1; + break; default: print_usage(argv[0]); return 1; diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 64cd2e23c568..543ad7513a8e 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -118,6 +118,16 @@ # below for IPv6 doesn't apply here, because, on IPv4, administrative MTU # changes alone won't affect PMTU # +# - pmtu_vti4_udp_exception +# Same as pmtu_vti4_exception, but using ESP-in-UDP +# +# - pmtu_vti4_udp_routed_exception +# Set up vti tunnel on top of veth connected through routing namespace and +# add xfrm states and policies with ESP-in-UDP encapsulation. Check that +# route exception is not created if link layer MTU is not exceeded, then +# lower MTU on second part of routed environment and check that exception +# is created with the expected PMTU. +# # - pmtu_vti6_exception # Set up vti6 tunnel on top of veth, with xfrm states and policies, in two # namespaces with matching endpoints. Check that route exception is @@ -125,6 +135,13 @@ # decrease and increase MTU of tunnel, checking that route exception PMTU # changes accordingly # +# - pmtu_vti6_udp_exception +# Same as pmtu_vti6_exception, but using ESP-in-UDP +# +# - pmtu_vti6_udp_routed_exception +# Same as pmtu_vti6_udp_routed_exception but with routing between vti +# endpoints +# # - pmtu_vti4_default_mtu # Set up vti4 tunnel on top of veth, in two namespaces with matching # endpoints. Check that MTU assigned to vti interface is the MTU of the @@ -224,6 +241,10 @@ tests=" pmtu_ipv6_ipv6_exception IPv6 over IPv6: PMTU exceptions 1 pmtu_vti6_exception vti6: PMTU exceptions 0 pmtu_vti4_exception vti4: PMTU exceptions 0 + pmtu_vti6_udp_exception vti6: PMTU exceptions (ESP-in-UDP) 0 + pmtu_vti4_udp_exception vti4: PMTU exceptions (ESP-in-UDP) 0 + pmtu_vti6_udp_routed_exception vti6: PMTU exceptions, routed (ESP-in-UDP) 0 + pmtu_vti4_udp_routed_exception vti4: PMTU exceptions, routed (ESP-in-UDP) 0 pmtu_vti4_default_mtu vti4: default MTU assignment 0 pmtu_vti6_default_mtu vti6: default MTU assignment 0 pmtu_vti4_link_add_mtu vti4: MTU setting on link creation 0 @@ -246,7 +267,6 @@ ns_b="ip netns exec ${NS_B}" ns_c="ip netns exec ${NS_C}" ns_r1="ip netns exec ${NS_R1}" ns_r2="ip netns exec ${NS_R2}" - # Addressing and routing for tests with routers: four network segments, with # index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an # identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2). @@ -279,7 +299,6 @@ routes=" A ${prefix6}:${b_r2}::1 ${prefix6}:${a_r2}::2 B default ${prefix6}:${b_r1}::2 " - USE_NH="no" # ns family nh id destination gateway nexthops=" @@ -326,6 +345,7 @@ dummy6_mask="64" err_buf= tcpdump_pids= +nettest_pids= err() { err_buf="${err_buf}${1} @@ -548,6 +568,14 @@ setup_vti6() { setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask} } +setup_vti4routed() { + setup_vti 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask} +} + +setup_vti6routed() { + setup_vti 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask} +} + setup_vxlan_or_geneve() { type="${1}" a_addr="${2}" @@ -619,18 +647,36 @@ setup_xfrm() { proto=${1} veth_a_addr="${2}" veth_b_addr="${3}" + encap=${4} - run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 1 - run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel + run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} || return 1 + run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} run_cmd ${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel run_cmd ${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel - run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel - run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel + run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} + run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} run_cmd ${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel run_cmd ${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel } +setup_nettest_xfrm() { + which nettest >/dev/null + if [ $? -ne 0 ]; then + echo "'nettest' command not found; skipping tests" + return 1 + fi + + [ ${1} -eq 6 ] && proto="-6" || proto="" + port=${2} + + run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 & + nettest_pids="${nettest_pids} $!" + + run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 & + nettest_pids="${nettest_pids} $!" +} + setup_xfrm4() { setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} } @@ -639,6 +685,26 @@ setup_xfrm6() { setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} } +setup_xfrm4udp() { + setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" + setup_nettest_xfrm 4 4500 +} + +setup_xfrm6udp() { + setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" + setup_nettest_xfrm 6 4500 +} + +setup_xfrm4udprouted() { + setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" + setup_nettest_xfrm 4 4500 +} + +setup_xfrm6udprouted() { + setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" + setup_nettest_xfrm 6 4500 +} + setup_routing_old() { for i in ${routes}; do [ "${ns}" = "" ] && ns="${i}" && continue @@ -823,6 +889,11 @@ cleanup() { done tcpdump_pids= + for pid in ${nettest_pids}; do + kill ${pid} + done + nettest_pids= + for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do ip netns del ${n} 2> /dev/null done @@ -1432,6 +1503,135 @@ test_pmtu_vti6_exception() { return ${fail} } +test_pmtu_vti4_udp_exception() { + setup namespaces veth vti4 xfrm4udp || return $ksft_skip + trace "${ns_a}" veth_a "${ns_b}" veth_b \ + "${ns_a}" vti4_a "${ns_b}" vti4_b + + veth_mtu=1500 + vti_mtu=$((veth_mtu - 20)) + + # UDP SPI SN IV ICV pad length next header + esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1)) + ping_payload=$((esp_payload_rfc4106 - 28)) + + mtu "${ns_a}" veth_a ${veth_mtu} + mtu "${ns_b}" veth_b ${veth_mtu} + mtu "${ns_a}" vti4_a ${vti_mtu} + mtu "${ns_b}" vti4_b ${vti_mtu} + + # Send DF packet without exceeding link layer MTU, check that no + # exception is created + run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr} + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" + check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1 + + # Now exceed link layer MTU by one byte, check that exception is created + # with the right PMTU value + run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr} + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" + check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))" +} + +test_pmtu_vti6_udp_exception() { + setup namespaces veth vti6 xfrm6udp || return $ksft_skip + trace "${ns_a}" veth_a "${ns_b}" veth_b \ + "${ns_a}" vti6_a "${ns_b}" vti6_b + fail=0 + + # Create route exception by exceeding link layer MTU + mtu "${ns_a}" veth_a 4000 + mtu "${ns_b}" veth_b 4000 + mtu "${ns_a}" vti6_a 5000 + mtu "${ns_b}" vti6_b 5000 + run_cmd ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr} + + # Check that exception was created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" + check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1 + + # Decrease tunnel MTU, check for PMTU decrease in route exception + mtu "${ns_a}" vti6_a 3000 + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" + check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1 + + # Increase tunnel MTU, check for PMTU increase in route exception + mtu "${ns_a}" vti6_a 9000 + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" + check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1 + + return ${fail} +} + +test_pmtu_vti4_udp_routed_exception() { + setup namespaces routing vti4routed xfrm4udprouted || return $ksft_skip + trace "${ns_a}" veth_A-R1 "${ns_b}" veth_B-R1 \ + "${ns_a}" vti4_a "${ns_b}" vti4_b + + veth_mtu=1500 + vti_mtu=$((veth_mtu - 20)) + + # UDP SPI SN IV ICV pad length next header + esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1)) + ping_payload=$((esp_payload_rfc4106 - 28)) + + mtu "${ns_a}" veth_A-R1 ${veth_mtu} + mtu "${ns_r1}" veth_R1-A ${veth_mtu} + mtu "${ns_b}" veth_B-R1 ${veth_mtu} + mtu "${ns_r1}" veth_R1-B ${veth_mtu} + + mtu "${ns_a}" vti4_a ${vti_mtu} + mtu "${ns_b}" vti4_b ${vti_mtu} + + # Send DF packet without exceeding link layer MTU, check that no + # exception is created + run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr} + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" + check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1 + + # Now decrease link layer MTU by 8 bytes on R1, check that exception is created + # with the right PMTU value + mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8)) + run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel4_b_addr} + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" + check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))" +} + +test_pmtu_vti6_udp_routed_exception() { + setup namespaces routing vti6routed xfrm6udprouted || return $ksft_skip + trace "${ns_a}" veth_A-R1 "${ns_b}" veth_B-R1 \ + "${ns_a}" vti6_a "${ns_b}" vti6_b + + veth_mtu=1500 + vti_mtu=$((veth_mtu - 40)) + + # UDP SPI SN IV ICV pad length next header + esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1)) + ping_payload=$((esp_payload_rfc4106 - 48)) + + mtu "${ns_a}" veth_A-R1 ${veth_mtu} + mtu "${ns_r1}" veth_R1-A ${veth_mtu} + mtu "${ns_b}" veth_B-R1 ${veth_mtu} + mtu "${ns_r1}" veth_R1-B ${veth_mtu} + + # mtu "${ns_a}" vti6_a ${vti_mtu} + # mtu "${ns_b}" vti6_b ${vti_mtu} + + run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel6_b_addr} + + # Check that exception was not created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" + check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1 + + # Now decrease link layer MTU by 8 bytes on R1, check that exception is created + # with the right PMTU value + mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8)) + run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel6_b_addr} + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" + check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))" + +} + test_pmtu_vti4_default_mtu() { setup namespaces veth vti4 || return $ksft_skip diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index e363bdaff59d..2ea438e6b8b1 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -210,8 +210,10 @@ static void anon_release_pages(char *rel_area) static void anon_allocate_area(void **alloc_area) { - if (posix_memalign(alloc_area, page_size, nr_pages * page_size)) - err("posix_memalign() failed"); + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (*alloc_area == MAP_FAILED) + err("mmap of anonymous memory failed"); } static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) |