diff options
| author | Dave Airlie <airlied@redhat.com> | 2026-08-20 10:58:44 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2026-08-20 10:58:44 +1000 |
| commit | c44e278ce02efd0c4be79a8eda1ea6885c1ce5ec (patch) | |
| tree | b6b7324a56fb1869a094da177d6a41f4d2efe8e0 /tools/testing | |
| parent | 65b92bc671db7c222f8de1146c88e40fe8764d95 (diff) | |
| parent | 8d3ae59288f1e7d58d76558a6ee96d533bc5019f (diff) | |
| download | linux-next-c44e278ce02efd0c4be79a8eda1ea6885c1ce5ec.tar.gz linux-next-c44e278ce02efd0c4be79a8eda1ea6885c1ce5ec.zip | |
BackMerge tag 'v7.2' into drm-next
Linux 7.2
There was a lot of conflicts this round between fixes and next,
and I'd like to get the merge resolutions that we have in drm-tip.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Diffstat (limited to 'tools/testing')
87 files changed, 3152 insertions, 206 deletions
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 8d4db2241cc2..b622052ec3e9 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -42,6 +42,7 @@ TARGETS += filesystems/fuse TARGETS += filesystems/move_mount TARGETS += filesystems/empty_mntns TARGETS += filesystems/fsmount_ns +TARGETS += filesystems/fscontext_ns TARGETS += firmware TARGETS += fpu TARGETS += ftrace diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index d4f845c32804..a329f901c5ed 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -84,6 +84,7 @@ static void find_controls(void) if (err < 0) { ksft_print_msg("Failed to get hctl for card %d: %s\n", card, snd_strerror(err)); + free(card_data); goto next_card; } @@ -339,9 +340,9 @@ static bool ctl_value_index_valid(struct ctl_data *ctl, } if (int64_val > snd_ctl_elem_info_get_max64(ctl->info)) { - ksft_print_msg("%s.%d value %lld more than maximum %ld\n", + ksft_print_msg("%s.%d value %lld more than maximum %lld\n", ctl->name, index, int64_val, - snd_ctl_elem_info_get_max(ctl->info)); + snd_ctl_elem_info_get_max64(ctl->info)); return false; } diff --git a/tools/testing/selftests/arm64/gcs/libc-gcs.c b/tools/testing/selftests/arm64/gcs/libc-gcs.c index 72e82bfbecc9..ddb0b2b20155 100644 --- a/tools/testing/selftests/arm64/gcs/libc-gcs.c +++ b/tools/testing/selftests/arm64/gcs/libc-gcs.c @@ -130,7 +130,7 @@ TEST(gcs_find_terminator) * We can access a GCS via ptrace * * This could usefully have a fixture but note that each test is - * fork()ed into a new child whcih causes issues. Might be better to + * fork()ed into a new child which causes issues. Might be better to * lift at least some of this out into a separate, non-harness, test * program. */ diff --git a/tools/testing/selftests/arm64/pauth/pac.c b/tools/testing/selftests/arm64/pauth/pac.c index 67d138057707..f4b859c75a5a 100644 --- a/tools/testing/selftests/arm64/pauth/pac.c +++ b/tools/testing/selftests/arm64/pauth/pac.c @@ -292,7 +292,7 @@ TEST(single_thread_different_keys) /* * fork() does not change keys. Only exec() does so call a worker program. - * Its only job is to sign a value and report back the resutls + * Its only job is to sign a value and report back the results */ TEST(exec_changed_keys) { diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index adb25146e88c..ea7044f30adc 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -82,6 +82,7 @@ CONFIG_NET_SCH_BPF=y CONFIG_NET_SCH_FQ=y CONFIG_NET_SCH_INGRESS=y CONFIG_NET_SCH_HTB=y +CONFIG_NET_SCH_RED=y CONFIG_NET_SCHED=y CONFIG_NETDEVSIM=y CONFIG_NETFILTER=y diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_implicit_args_tracing.c b/tools/testing/selftests/bpf/prog_tests/kfunc_implicit_args_tracing.c new file mode 100644 index 000000000000..61cc5aaba025 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_implicit_args_tracing.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include "kfunc_implicit_args_tracing.skel.h" + +void test_kfunc_implicit_args_tracing(void) +{ + struct kfunc_implicit_args_tracing *skel; + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, fd; + + skel = kfunc_implicit_args_tracing__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + err = kfunc_implicit_args_tracing__attach(skel); + if (!ASSERT_OK(err, "attach")) + goto cleanup; + + fd = bpf_program__fd(skel->progs.trigger_implicit_arg); + err = bpf_prog_test_run_opts(fd, &topts); + if (!ASSERT_OK(err, "test_run")) + goto cleanup; + + ASSERT_EQ(topts.retval, 5, "kfunc_retval"); + ASSERT_EQ(skel->bss->fentry_arg_cnt, 2, "fentry_arg_cnt"); + ASSERT_NEQ(skel->bss->fentry_aux_arg, 0, "fentry_aux_arg"); + ASSERT_EQ(skel->bss->fentry_result, 1, "fentry_result"); + ASSERT_EQ(skel->bss->fexit_arg_cnt, 2, "fexit_arg_cnt"); + ASSERT_NEQ(skel->bss->fexit_aux_arg, 0, "fexit_aux_arg"); + ASSERT_EQ(skel->bss->fexit_result, 1, "fexit_result"); + +cleanup: + kfunc_implicit_args_tracing__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_bad_access.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_bad_access.c new file mode 100644 index 000000000000..b8538fc4fc3f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_bad_access.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "test_kmods/bpf_testmod.h" +#include "bpf_util.h" + +static void check_attach_reject(const struct bpf_insn *program, size_t prog_len) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts); + char error[4096]; + int bpf_fd, tp_fd; + + opts.log_level = 2; + opts.log_buf = error; + opts.log_size = sizeof(error); + + bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2", + program, prog_len, &opts); + if (!ASSERT_GE(bpf_fd, 0, "prog_load")) + return; + + tp_fd = bpf_raw_tracepoint_open("bpf_testmod_test_writable_bare_tp", bpf_fd); + ASSERT_EQ(tp_fd, -EINVAL, "bpf_raw_tracepoint_open"); + if (tp_fd >= 0) + close(tp_fd); + + close(bpf_fd); +} + +void test_raw_tp_writable_reject_bad_access(void) +{ + const struct bpf_insn program[] = { + /* r6 is our tp buffer */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + /* one byte beyond the end of the writable context */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, + sizeof(struct bpf_testmod_test_writable_ctx)), + BPF_EXIT_INSN(), + }; + + const struct bpf_insn negative_var_off_program[] = { + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + /* make var_off negative, but keep the effective access offset non-negative */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + /* one byte beyond the end of the writable context */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, + sizeof(struct bpf_testmod_test_writable_ctx) + 8), + BPF_EXIT_INSN(), + }; + + if (test__start_subtest("past_end")) + check_attach_reject(program, ARRAY_SIZE(program)); + + if (test__start_subtest("negative_var_off_past_end")) + check_attach_reject(negative_var_off_program, + ARRAY_SIZE(negative_var_off_program)); +} diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c deleted file mode 100644 index 216b0dfac0fe..000000000000 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c +++ /dev/null @@ -1,43 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <test_progs.h> -#include <linux/nbd.h> -#include "bpf_util.h" - -void test_raw_tp_writable_reject_nbd_invalid(void) -{ - __u32 duration = 0; - char error[4096]; - int bpf_fd = -1, tp_fd = -1; - - const struct bpf_insn program[] = { - /* r6 is our tp buffer */ - BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), - /* one byte beyond the end of the nbd_request struct */ - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, - sizeof(struct nbd_request)), - BPF_EXIT_INSN(), - }; - - LIBBPF_OPTS(bpf_prog_load_opts, opts, - .log_level = 2, - .log_buf = error, - .log_size = sizeof(error), - ); - - bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2", - program, ARRAY_SIZE(program), - &opts); - if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable load", - "failed: %d errno %d\n", bpf_fd, errno)) - return; - - tp_fd = bpf_raw_tracepoint_open("nbd_send_request", bpf_fd); - if (CHECK(tp_fd >= 0, "bpf_raw_tracepoint_writable open", - "erroneously succeeded\n")) - goto out_bpffd; - - close(tp_fd); -out_bpffd: - close(bpf_fd); -} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index cb3229711f93..e5fc038d747b 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -853,7 +853,7 @@ static void test_sockmap_many_socket(void) return; } - udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0); + udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK); if (udp < 0) { close(dgram); close(tcp); @@ -922,7 +922,7 @@ static void test_sockmap_many_maps(void) return; } - udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0); + udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK); if (udp < 0) { close(dgram); close(tcp); @@ -993,7 +993,7 @@ static void test_sockmap_same_sock(void) return; } - udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0); + udp = socket_loopback(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK); if (udp < 0) { close(dgram); close(tcp); @@ -1373,6 +1373,43 @@ end: test_sockmap_pass_prog__destroy(skel); } +/* A socket in a sockmap without a verdict program keeps its ingress data + * in sk_receive_queue: FIONREAD must account for it. + */ +static void test_sockmap_no_verdict_fionread(void) +{ + int err, map, zero = 0, sent, avail; + int c0 = -1, c1 = -1, p0 = -1, p1 = -1; + struct test_sockmap_pass_prog *skel; + char buf[256] = "0123456789"; + + skel = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + map = bpf_map__fd(skel->maps.sock_map_rx); + + err = create_socket_pairs(AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs()")) + goto out; + + err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c1)")) + goto out_close; + + sent = xsend(p1, &buf, sizeof(buf), 0); + ASSERT_EQ(sent, sizeof(buf), "xsend(p1)"); + avail = wait_for_fionread(c1, sizeof(buf), IO_TIMEOUT_SEC); + ASSERT_EQ(avail, sizeof(buf), "ioctl(FIONREAD)"); + +out_close: + close(c0); + close(p0); + close(c1); + close(p1); +out: + test_sockmap_pass_prog__destroy(skel); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -1415,6 +1452,8 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_shutdown(); if (test__start_subtest("sockmap skb_verdict fionread")) test_sockmap_skb_verdict_fionread(true); + if (test__start_subtest("sockmap no_verdict fionread")) + test_sockmap_no_verdict_fionread(); if (test__start_subtest("sockmap skb_verdict fionread on drop")) test_sockmap_skb_verdict_fionread(false); if (test__start_subtest("sockmap skb_verdict change tail")) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index cc0c68bab907..1c96a3cf4b97 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -53,8 +53,8 @@ static void test_insert_opened(struct test_sockmap_listen *skel __always_unused, int family, int sotype, int mapfd) { u32 key = 0; - u64 value; int err, s; + u64 value; s = xsocket(family, sotype, 0); if (s == -1) @@ -63,11 +63,8 @@ static void test_insert_opened(struct test_sockmap_listen *skel __always_unused, errno = 0; value = s; err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); - if (sotype == SOCK_STREAM) { - if (!err || errno != EOPNOTSUPP) - FAIL_ERRNO("map_update: expected EOPNOTSUPP"); - } else if (err) - FAIL_ERRNO("map_update: expected success"); + ASSERT_ERR(err, "map_update"); + ASSERT_EQ(errno, EOPNOTSUPP, "errno"); xclose(s); } @@ -77,8 +74,8 @@ static void test_insert_bound(struct test_sockmap_listen *skel __always_unused, struct sockaddr_storage addr; socklen_t len = 0; u32 key = 0; - u64 value; int err, s; + u64 value; init_addr_loopback(family, &addr, &len); @@ -93,8 +90,12 @@ static void test_insert_bound(struct test_sockmap_listen *skel __always_unused, errno = 0; value = s; err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); - if (!err || errno != EOPNOTSUPP) - FAIL_ERRNO("map_update: expected EOPNOTSUPP"); + if (sotype == SOCK_STREAM) { + ASSERT_ERR(err, "map_update"); + ASSERT_EQ(errno, EOPNOTSUPP, "errno"); + } else { + ASSERT_OK(err, "map_update"); + } close: xclose(s); } @@ -1289,7 +1290,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, /* insert */ TEST(test_insert_invalid), TEST(test_insert_opened), - TEST(test_insert_bound, SOCK_STREAM), + TEST(test_insert_bound), TEST(test_insert), /* delete */ TEST(test_delete_after_insert), diff --git a/tools/testing/selftests/bpf/prog_tests/tc_qevent.c b/tools/testing/selftests/bpf/prog_tests/tc_qevent.c new file mode 100644 index 000000000000..67e1d17567ab --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_qevent.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <network_helpers.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <unistd.h> +#include <string.h> + +#include "test_tc_qevent.skel.h" + +#define NS_TX "tc_qevent_tx" +#define NS_RX "tc_qevent_rx" +#define IP_TX "10.255.0.1" +#define IP_RX "10.255.0.2" +#define PIN_PATH "/sys/fs/bpf/tc_qevent_redirect" + +static void blast_udp(void) +{ + struct sockaddr_in dst = {}; + char buf[1400] = {}; + int fd, i; + + fd = socket(AF_INET, SOCK_DGRAM, 0); + if (!ASSERT_GE(fd, 0, "udp socket")) + return; + + dst.sin_family = AF_INET; + dst.sin_port = htons(12345); + inet_pton(AF_INET, IP_RX, &dst.sin_addr); + + /* + * Push far more than the RED queue can hold. Once qavg crosses qth_min + * every further packet hits the congestion_drop / early_drop qevent. + */ + for (i = 0; i < 50000; i++) + sendto(fd, buf, sizeof(buf), MSG_DONTWAIT, + (struct sockaddr *)&dst, sizeof(dst)); + + close(fd); +} + +static void run_qevent_redirect(struct bpf_program *prog, __u64 *counter) +{ + struct nstoken *tok = NULL; + int err; + + SYS_NOFAIL("ip netns del %s", NS_TX); + SYS_NOFAIL("ip netns del %s", NS_RX); + unlink(PIN_PATH); + + err = bpf_program__pin(prog, PIN_PATH); + if (!ASSERT_OK(err, "pin prog")) + return; + + SYS(unpin, "ip netns add %s", NS_TX); + SYS(del_tx, "ip netns add %s", NS_RX); + SYS(del_rx, "ip -n %s link add veth0 type veth peer name veth1 netns %s", NS_TX, NS_RX); + SYS(del_rx, "ip -n %s addr add %s/24 dev veth0", NS_TX, IP_TX); + SYS(del_rx, "ip -n %s link set veth0 up", NS_TX); + SYS(del_rx, "ip -n %s addr add %s/24 dev veth1", NS_RX, IP_RX); + SYS(del_rx, "ip -n %s link set veth1 up", NS_RX); + + tok = open_netns(NS_TX); + if (!ASSERT_OK_PTR(tok, "open_netns")) + goto del_rx; + + SYS(close_ns, "tc qdisc add dev veth0 root handle 1: htb default 1"); + SYS(close_ns, "tc class add dev veth0 parent 1: classid 1:1 htb rate 1mbit ceil 1mbit"); + + if (system("tc qdisc add dev veth0 parent 1:1 handle 11: red " + "limit 500000 avpkt 1000 probability 1 min 5000 max 6000 " + "burst 6 qevent early_drop block 10 2>/dev/null")) { + test__skip(); + goto close_ns; + } + + if (system("tc filter add block 10 bpf da object-pinned " + PIN_PATH " 2>/dev/null")) { + test__skip(); + goto close_ns; + } + + blast_udp(); + ASSERT_GT(*counter, 0, "qevent classifier ran"); +close_ns: + close_netns(tok); +del_rx: + SYS_NOFAIL("ip netns del %s", NS_RX); +del_tx: + SYS_NOFAIL("ip netns del %s", NS_TX); +unpin: + bpf_program__unpin(prog, PIN_PATH); +} + +void test_tc_qevent(void) +{ + struct test_tc_qevent *skel; + + skel = test_tc_qevent__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + if (test__start_subtest("redirect_verdict")) + run_qevent_redirect(skel->progs.qevent_redirect_verdict, + &skel->bss->verdict_calls); + if (test__start_subtest("redirect_helper")) + run_qevent_redirect(skel->progs.qevent_redirect_helper, + &skel->bss->helper_calls); + + test_tc_qevent__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c index 6eb9096d084c..38ce6060b8fa 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c +++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c @@ -427,14 +427,14 @@ static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pk } /* Search for the end of the packet in verbatim mode */ - if (!pkt_continues(pkt->options) || !pkt->valid) + if (!pkt_continues(pkt->options)) return nb_frags; next_frag = pkt_stream->current_pkt_nb; pkt++; while (next_frag++ < pkt_stream->nb_pkts) { nb_frags++; - if (!pkt_continues(pkt->options) || !pkt->valid) + if (!pkt_continues(pkt->options)) break; pkt++; } @@ -665,11 +665,11 @@ static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, s if (!frame->valid || !pkt_continues(frame->options)) payload++; } else { - if (frame->valid) + if (frame->valid) { len += frame->len; - if (frame->valid && pkt_continues(frame->options)) - continue; - + if (pkt_continues(frame->options)) + continue; + } pkt->pkt_nb = pkt_nb; pkt->len = len; pkt->valid = frame->valid; @@ -1250,10 +1250,9 @@ static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk, } } - if (pkt && pkt->valid) { + if (pkt && pkt->valid) valid_pkts++; - valid_frags += nb_frags; - } + valid_frags += nb_frags; } pthread_mutex_lock(&pacing_mutex); @@ -2099,13 +2098,16 @@ int testapp_invalid_desc_mb(struct test_spec *test) {0, 0, 0, false, 0}, /* Invalid address in the second frame */ {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {umem_sz, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {umem_sz * 2, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, MIN_PKT_SIZE, 0, false, 0}, /* Invalid len in the middle */ {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, MIN_PKT_SIZE, 0, false, 0}, /* Invalid options in the middle */ {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XSK_DESC__INVALID_OPTION}, + {0, MIN_PKT_SIZE, 0, false, 0}, /* Transmit 2 frags, receive 3 */ {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, XDP_PKT_CONTD}, {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, 0}, @@ -2117,8 +2119,8 @@ int testapp_invalid_desc_mb(struct test_spec *test) if (umem->unaligned_mode) { /* Crossing a chunk boundary allowed */ - pkts[12].valid = true; - pkts[13].valid = true; + pkts[15].valid = true; + pkts[16].valid = true; } test->mtu = MAX_ETH_JUMBO_SIZE; @@ -2270,7 +2272,7 @@ int testapp_too_many_frags(struct test_spec *test) max_frags += 1; } - pkts = calloc(2 * max_frags + 2, sizeof(struct pkt)); + pkts = calloc(2 * max_frags + 3, sizeof(struct pkt)); if (!pkts) return TEST_FAILURE; @@ -2288,24 +2290,30 @@ int testapp_too_many_frags(struct test_spec *test) } pkts[max_frags].options = 0; - /* An invalid packet with the max amount of frags but signals packet - * continues on the last frag - */ - for (i = max_frags + 1; i < 2 * max_frags + 1; i++) { + /* An invalid packet with the max + 1 amount of frags */ + for (i = max_frags + 1; i < 2 * max_frags + 2; i++) { pkts[i].len = MIN_PKT_SIZE; pkts[i].options = XDP_PKT_CONTD; - pkts[i].valid = false; + pkts[i].valid = true; } + pkts[2 * max_frags + 1].options = 0; /* Valid packet for synch */ - pkts[2 * max_frags + 1].len = MIN_PKT_SIZE; - pkts[2 * max_frags + 1].valid = true; + pkts[2 * max_frags + 2].len = MIN_PKT_SIZE; + pkts[2 * max_frags + 2].valid = true; - if (pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2)) { + if (pkt_stream_generate_custom(test, pkts, 2 * max_frags + 3)) { free(pkts); return TEST_FAILURE; } + /* The generated Tx stream must keep the too-big packet valid so that + * __send_pkts() accounts its descriptors in outstanding_tx. The Rx + * stream, however, must not expect this packet on the wire. + */ + test->ifobj_rx->xsk->pkt_stream->pkts[2].valid = false; + test->ifobj_rx->xsk->pkt_stream->nb_valid_entries--; + ret = testapp_validate_traffic(test); free(pkts); return ret; diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 8a3d69e2453c..be97f6887f0e 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -78,6 +78,7 @@ #include "verifier_precision.skel.h" #include "verifier_prevent_map_lookup.skel.h" #include "verifier_private_stack.skel.h" +#include "verifier_ptr_to_buf.skel.h" #include "verifier_raw_stack.skel.h" #include "verifier_raw_tp_writable.skel.h" #include "verifier_reg_equal.skel.h" @@ -230,6 +231,7 @@ void test_verifier_or_jmp32_k(void) { RUN(verifier_or_jmp32_k); } void test_verifier_precision(void) { RUN(verifier_precision); } void test_verifier_prevent_map_lookup(void) { RUN(verifier_prevent_map_lookup); } void test_verifier_private_stack(void) { RUN(verifier_private_stack); } +void test_verifier_ptr_to_buf(void) { RUN(verifier_ptr_to_buf); } void test_verifier_raw_stack(void) { RUN(verifier_raw_stack); } void test_verifier_raw_tp_writable(void) { RUN(verifier_raw_tp_writable); } void test_verifier_reg_equal(void) { RUN(verifier_reg_equal); } diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index 344fb2aa0813..29c6361d8820 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -1635,6 +1635,36 @@ static int callback(__u32 index, void *data) return 0; } +/* A commuted add should preserve the parent id of a dynptr data slice. */ +SEC("?raw_tp") +__failure __msg("invalid mem access 'scalar'") +int dynptr_slice_commuted_invalidate(void *ctx) +{ + struct bpf_dynptr ptr; + __u32 *slice, *derived; + + bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(__u32), 0, &ptr); + + slice = bpf_dynptr_data(&ptr, 0, sizeof(__u32)); + if (!slice) + goto done; + + asm volatile ("%[dst] = 0;" + "%[dst] += %[src];" + "%[src] = 0;" + : [dst]"=&r"(derived), [src]"+r"(slice) + : + : "memory"); + + bpf_ringbuf_discard_dynptr(&ptr, 0); + val = *derived; + return 0; + +done: + bpf_ringbuf_discard_dynptr(&ptr, 0); + return 0; +} + /* If the dynptr is written into in a callback function, its data * slices should be invalidated as well. */ diff --git a/tools/testing/selftests/bpf/progs/kfunc_implicit_args_tracing.c b/tools/testing/selftests/bpf/progs/kfunc_implicit_args_tracing.c new file mode 100644 index 000000000000..995f8b8b5b9e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_implicit_args_tracing.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <errno.h> + +extern int bpf_kfunc_implicit_arg(int a) __weak __ksym; + +char _license[] SEC("license") = "GPL"; + +/* Shared arg checks; reports arg count and aux, returns 1 on success. */ +static __always_inline __u64 +check_implicit_args(void *ctx, __u64 *arg_cnt, __u64 *aux_arg) +{ + __u64 a = 0, aux = 0, z = 0; + __u64 result; + __s64 err; + + *arg_cnt = bpf_get_func_arg_cnt(ctx); + result = *arg_cnt == 2; + + err = bpf_get_func_arg(ctx, 0, &a); + result &= err == 0 && (int)a == 5; + + err = bpf_get_func_arg(ctx, 1, &aux); + *aux_arg = aux; + result &= err == 0 && aux != 0; + + err = bpf_get_func_arg(ctx, 2, &z); + result &= err == -EINVAL; + + return result; +} + +__u64 fentry_result; +__u64 fentry_arg_cnt; +__u64 fentry_aux_arg; + +SEC("fentry/bpf_kfunc_implicit_arg") +int BPF_PROG(trace_implicit_arg_fentry) +{ + __u64 ret = 0; + __s64 err; + + fentry_result = check_implicit_args(ctx, &fentry_arg_cnt, &fentry_aux_arg); + + err = bpf_get_func_ret(ctx, &ret); + fentry_result &= err == -EOPNOTSUPP; + + return 0; +} + +__u64 fexit_result; +__u64 fexit_arg_cnt; +__u64 fexit_aux_arg; + +SEC("fexit/bpf_kfunc_implicit_arg") +int BPF_PROG(trace_implicit_arg_fexit) +{ + __u64 ret = 0; + __s64 err; + + fexit_result = check_implicit_args(ctx, &fexit_arg_cnt, &fexit_aux_arg); + + err = bpf_get_func_ret(ctx, &ret); + fexit_result &= err == 0 && ret == 5; + + return 0; +} + +SEC("syscall") +int trigger_implicit_arg(void *ctx) +{ + return bpf_kfunc_implicit_arg(5); +} diff --git a/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c index 5b4453747c23..f166fff8f217 100644 --- a/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c +++ b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c @@ -226,4 +226,21 @@ int null_check(void *ctx) return 0; } +SEC("socket") +__success +__retval(1) +int ldx_is_ok_commuted_addr(void *ctx) +{ + int v, *p, *derived; + + v = 1; + p = bpf_rdonly_cast(&v, 0); + asm volatile ("%[dst] = 0;" + "%[dst] += %[src];" + : [dst]"=&r"(derived) + : [src]"r"(p) + : "memory"); + return *derived; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_qevent.c b/tools/testing/selftests/bpf/progs/test_tc_qevent.c new file mode 100644 index 000000000000..1529c111f4aa --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_qevent.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +int redirect_ifindex = 1; +__u64 verdict_calls = 0; +__u64 helper_calls = 0; + +SEC("tc") +int qevent_redirect_verdict(struct __sk_buff *skb) +{ + __sync_fetch_and_add(&verdict_calls, 1); + return TCX_REDIRECT; +} + +SEC("tc") +int qevent_redirect_helper(struct __sk_buff *skb) +{ + __sync_fetch_and_add(&helper_calls, 1); + return bpf_redirect(redirect_ifindex, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c index fb62e09f2114..d3df7a9f1d8c 100644 --- a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c +++ b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c @@ -97,4 +97,45 @@ __naked void misaligned_read_from_stack(void) " ::: __clobber_all); } +SEC("socket") +__description("stack pointer arithmetic preserves frame number") +__failure __msg("R7 invalid mem access 'scalar'") +__naked void stack_ptr_arith_preserves_frameno(void) +{ + asm volatile ("\ + r3 = 0; \ + *(u64 *)(r10 - 8) = r3; \ + r1 = %[map_hash_8b] ll; \ + r2 = r10; \ + r2 += -8; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto +2; \ + r0 = 0; \ + exit; \ + r1 = r0; \ + r2 = 0; \ + r3 = 0; \ + call stack_ptr_arith_preserves_frameno_subprog;\ + r0 = 0; \ + exit; \ + ": + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +static __used __naked void stack_ptr_arith_preserves_frameno_subprog(void) +{ + asm volatile ("\ + *(u64 *)(r10 - 8) = r1; \ + r6 = -8; \ + r6 += r10; \ + *(u64 *)(r6 + 0) = r2; \ + r7 = *(u64 *)(r10 - 8); \ + *(u64 *)(r7 + 0) = r3; \ + r0 = 0; \ + exit; \ + "::: __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c index 75a2e3f48d0f..67dc352addfd 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c @@ -185,6 +185,16 @@ int arg_tag_nonnull_ptr_good(void *ctx) return subprog_nonnull_ptr_good(&x, &y); } +SEC("?raw_tp") +__failure __log_level(2) +__msg("R1 is expected to be non-NULL") +int arg_tag_nonnull_ptr_null_bad(void *ctx) +{ + int y = 74; + + return subprog_nonnull_ptr_good(NULL, &y); +} + /* this global subprog can be now called from many types of entry progs, each * with different context type */ diff --git a/tools/testing/selftests/bpf/progs/verifier_ptr_to_buf.c b/tools/testing/selftests/bpf/progs/verifier_ptr_to_buf.c new file mode 100644 index 000000000000..12cf24db46a0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_ptr_to_buf.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("iter/bpf_map_elem") +__description("PTR_TO_BUF: reject negative const offset") +__failure +__msg("invalid negative rdwr buffer offset") +__naked void ptr_to_buf_reject_negative_const_offset(void) +{ + asm volatile ("r0 = 0; \ + r2 = *(u64 *)(r1 + %[value_off]); \ + if r2 == 0 goto l0_%=; \ + r2 += -8; \ + r0 = *(u64 *)(r2 + 0); \ +l0_%=: \ + exit; \ + " + : + : __imm_const(value_off, + offsetof(struct bpf_iter__bpf_map_elem, value)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c b/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c index 14a0172e2141..4055a6443bc2 100644 --- a/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c +++ b/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c @@ -47,4 +47,20 @@ l0_%=: /* shift the buffer pointer to a variable location */\ : __clobber_all); } +SEC("raw_tracepoint.w") +__description("raw_tracepoint_writable: reject negative const offset") +__failure +__msg("invalid negative tracepoint buffer offset") +__naked void tracepoint_writable_reject_negative_const_offset(void) +{ + asm volatile (" \ + r6 = *(u64 *)(r1 + 0); \ + r6 += -8; \ + r0 = *(u64 *)(r6 + 0); \ + exit; \ +" : + : + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index c32da7bd8be2..6a2641ee7897 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -759,16 +759,15 @@ static void test_sockmap(unsigned int tasks, void *data) goto out_sockmap; } - /* Test update with unsupported UDP socket */ + /* Test update with unsupported unbound UDP socket */ udp = socket(AF_INET, SOCK_DGRAM, 0); - i = 0; - err = bpf_map_update_elem(fd, &i, &udp, BPF_ANY); - if (err) { - printf("Failed socket update SOCK_DGRAM '%i:%i'\n", - i, udp); + CHECK(udp < 0, "socket(AF_INET, SOCK_DGRAM)", "errno:%d\n", errno); + err = bpf_map_update_elem(fd, &(int){0}, &udp, BPF_ANY); + close(udp); + if (!err) { + printf("Unexpectedly succeeded unbound UDP update '0:%i'\n", udp); goto out_sockmap; } - close(udp); /* Test update without programs */ for (i = 0; i < 6; i++) { diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c index 5c944aee6b41..485efa7c9eed 100644 --- a/tools/testing/selftests/clone3/clone3_set_tid.c +++ b/tools/testing/selftests/clone3/clone3_set_tid.c @@ -141,7 +141,7 @@ int main(int argc, char *argv[]) { FILE *f; char buf; - char *line; + char *line = NULL; int status; int ret = -1; size_t len = 0; diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index 91d4fd410914..2070e890e064 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -4,6 +4,8 @@ CONFIG_DEBUG_INFO_BTF_MODULES=n CONFIG_INET_PSP=y CONFIG_IPV6=y CONFIG_MACSEC=m +CONFIG_NET_CLS_ACT=y +CONFIG_NET_CLS_BPF=y CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_NETCONSOLE_EXTENDED_LOG=y @@ -11,6 +13,7 @@ CONFIG_NETDEVSIM=m CONFIG_NETKIT=y CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_FQ=m +CONFIG_NET_SCH_INGRESS=y CONFIG_PPP=y CONFIG_PPPOE=y CONFIG_VLAN_8021Q=m diff --git a/tools/testing/selftests/drivers/net/netconsole/netcons_cmdline.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_cmdline.sh index 96d704b8d9d9..4436567abc94 100755 --- a/tools/testing/selftests/drivers/net/netconsole/netcons_cmdline.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_cmdline.sh @@ -50,7 +50,7 @@ do # Send the message echo "${MSG}: ${TARGET}" > /dev/kmsg # Wait until socat saves the file to disk - busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" || true # Make sure the message was received in the dst part # and exit validate_msg "${OUTPUT_FILE}" diff --git a/tools/testing/selftests/drivers/net/netconsole/netcons_fragmented_msg.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_fragmented_msg.sh index 0dc7280c3080..fc3db40c1df5 100755 --- a/tools/testing/selftests/drivers/net/netconsole/netcons_fragmented_msg.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_fragmented_msg.sh @@ -104,7 +104,7 @@ wait_local_port_listen "${NAMESPACE}" "${PORT}" udp # Send the message echo "${MSG}: ${TARGET}" > /dev/kmsg # Wait until socat saves the file to disk -busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" || true # Check if the message was not corrupted validate_fragmented_result "${OUTPUT_FILE}" @@ -117,6 +117,6 @@ disable_release_append listen_port_and_save_to "${OUTPUT_FILE}" & wait_local_port_listen "${NAMESPACE}" "${PORT}" udp echo "${MSG}: ${TARGET}" > /dev/kmsg -busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" || true validate_fragmented_result "${OUTPUT_FILE}" exit "${ksft_pass}" diff --git a/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh index cb59cf436dd0..b379dff9087e 100755 --- a/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh @@ -44,7 +44,8 @@ function trigger_reactivation() { # Restore MACs ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" \ address "${SAVED_DSTMAC}" - if [ "${BINDMODE}" == "mac" ]; then + if [ "${BINDMODE}" == "mac" ] && + [ "$(mac_get "${SRCIF}")" != "${SAVED_SRCMAC}" ]; then ip link set dev "${SRCIF}" down ip link set dev "${SRCIF}" address "${SAVED_SRCMAC}" # Rename device in order to trigger target resume, as initial @@ -107,7 +108,7 @@ do # Send the message echo "${MSG}: ${TARGET}" > /dev/kmsg # Wait until socat saves the file to disk - busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" || true # Make sure the message was received in the dst part # and exit validate_msg "${OUTPUT_FILE}" diff --git a/tools/testing/selftests/drivers/net/netconsole/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_sysdata.sh index 3fb8c4afe3d2..7089f7bd1e34 100755 --- a/tools/testing/selftests/drivers/net/netconsole/netcons_sysdata.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_sysdata.sh @@ -197,7 +197,7 @@ function runtest { # Send the message taskset -c "${CPU}" echo "${MSG}: ${TARGET}" > /dev/kmsg # Wait until socat saves the file to disk - busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" || true } # ========== # diff --git a/tools/testing/selftests/drivers/net/settings b/tools/testing/selftests/drivers/net/settings new file mode 100644 index 000000000000..eef533824a3c --- /dev/null +++ b/tools/testing/selftests/drivers/net/settings @@ -0,0 +1 @@ +timeout=360 diff --git a/tools/testing/selftests/drivers/ntsync/config b/tools/testing/selftests/drivers/ntsync/config index 60539c826d06..0aa68de147af 100644 --- a/tools/testing/selftests/drivers/ntsync/config +++ b/tools/testing/selftests/drivers/ntsync/config @@ -1 +1 @@ -CONFIG_WINESYNC=y +CONFIG_NTSYNC=y diff --git a/tools/testing/selftests/filesystems/fclog.c b/tools/testing/selftests/filesystems/fclog.c index 551c4a0f395a..593a5136e991 100644 --- a/tools/testing/selftests/filesystems/fclog.c +++ b/tools/testing/selftests/filesystems/fclog.c @@ -6,10 +6,8 @@ #include <assert.h> #include <errno.h> +#include <fcntl.h> #include <sched.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> #include <unistd.h> #include <sys/mount.h> diff --git a/tools/testing/selftests/filesystems/fscontext_ns/Makefile b/tools/testing/selftests/filesystems/fscontext_ns/Makefile new file mode 100644 index 000000000000..7e3506294757 --- /dev/null +++ b/tools/testing/selftests/filesystems/fscontext_ns/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_GEN_PROGS := fscontext_ns_test + +CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +LDLIBS := -lcap + +include ../../lib.mk + +$(OUTPUT)/fscontext_ns_test: fscontext_ns_test.c ../utils.c + $(CC) $(CFLAGS) -o $@ $^ $(LDLIBS) diff --git a/tools/testing/selftests/filesystems/fscontext_ns/fscontext_ns_test.c b/tools/testing/selftests/filesystems/fscontext_ns/fscontext_ns_test.c new file mode 100644 index 000000000000..0f30a3e6e197 --- /dev/null +++ b/tools/testing/selftests/filesystems/fscontext_ns/fscontext_ns_test.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026 Christian Brauner <brauner@kernel.org> + * + * Test that completing a filesystem context from another user namespace + * doesn't warn. + * + * fsopen() records the caller's user namespace in fc->user_ns and hands + * back an ordinary file descriptor. The task that issues + * FSCONFIG_CMD_CREATE need not be the one that created the context: the fd + * is inherited across fork() and exec() and it can be passed over a unix + * socket. vfs_cmd_create() authorizes the create with mount_capable(), + * which for FS_USERNS_MOUNT checks ns_capable(fc->user_ns, CAP_SYS_ADMIN), + * and that succeeds for a task holding CAP_SYS_ADMIN in an ancestor of + * fc->user_ns. + * + * binfmt_misc and overlayfs used to WARN_ON() that mismatch, which let an + * unprivileged user taint the kernel, flood the log and panic a kernel + * booted with panic_on_warn. The mount must still be refused, but it must + * not warn. + */ +#define _GNU_SOURCE + +#include <errno.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "../wrappers.h" +#include "../utils.h" +#include "../../kselftest_harness.h" + +#ifndef FSCONFIG_CMD_CREATE +#define FSCONFIG_CMD_CREATE 6 +#endif + +/* TAINT_WARN, i.e. bit 9 of /proc/sys/kernel/tainted. */ +#define TAINT_WARN_BIT 9 + +static bool taint_warn_set(void) +{ + unsigned long taint = 0; + FILE *f; + + f = fopen("/proc/sys/kernel/tainted", "r"); + if (!f) + return false; + if (fscanf(f, "%lu", &taint) != 1) + taint = 0; + fclose(f); + + return taint & (1UL << TAINT_WARN_BIT); +} + +static int send_fd(int sock, int fd) +{ + char cmsgbuf[CMSG_SPACE(sizeof(int))] = {}; + char b[1] = { 'x' }; + struct iovec iov = { .iov_base = b, .iov_len = sizeof(b) }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = cmsgbuf, + .msg_controllen = sizeof(cmsgbuf), + }; + struct cmsghdr *cmsg; + + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(int)); + memcpy(CMSG_DATA(cmsg), &fd, sizeof(int)); + + return sendmsg(sock, &msg, 0) < 0 ? -1 : 0; +} + +static int recv_fd(int sock) +{ + char cmsgbuf[CMSG_SPACE(sizeof(int))] = {}; + char b[1]; + struct iovec iov = { .iov_base = b, .iov_len = sizeof(b) }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = cmsgbuf, + .msg_controllen = sizeof(cmsgbuf), + }; + struct cmsghdr *cmsg; + int fd = -1; + + if (recvmsg(sock, &msg, 0) <= 0) + return -1; + + cmsg = CMSG_FIRSTHDR(&msg); + if (!cmsg || cmsg->cmsg_type != SCM_RIGHTS) + return -1; + memcpy(&fd, CMSG_DATA(cmsg), sizeof(int)); + + return fd; +} + +/* + * Create a context for @fsname in a child and complete it here. With @nest + * the child first creates its own user namespace, so that the context is + * created in a descendant of the namespace completing it. The child needs a + * mount namespace of its own as well: fsopen() gates on may_mount(), which + * asks for CAP_SYS_ADMIN in the user namespace owning the caller's mount + * namespace. + * + * Returns the result of FSCONFIG_CMD_CREATE with errno set, or -ENODATA if + * the child could not create the context at all. + */ +static int create_from_child(const char *fsname, bool nest) +{ + int sock[2], fd, ret, status; + pid_t pid; + + if (socketpair(AF_UNIX, SOCK_STREAM, 0, sock)) + return -ENODATA; + + pid = fork(); + if (pid < 0) { + close(sock[0]); + close(sock[1]); + return -ENODATA; + } + + if (pid == 0) { + close(sock[0]); + + if (nest && unshare(CLONE_NEWUSER | CLONE_NEWNS)) + _exit(1); + + fd = sys_fsopen(fsname, 0); + if (fd < 0) + _exit(1); + if (send_fd(sock[1], fd)) + _exit(1); + _exit(0); + } + + close(sock[1]); + fd = recv_fd(sock[0]); + close(sock[0]); + wait_for_pid(pid); + waitpid(pid, &status, WNOHANG); + + if (fd < 0) + return -ENODATA; + + errno = 0; + ret = sys_fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + status = errno; + close(fd); + errno = status; + + return ret; +} + +FIXTURE(fscontext_ns) { + bool warn_before; +}; + +FIXTURE_SETUP(fscontext_ns) +{ + self->warn_before = taint_warn_set(); + + if (setup_userns() != 0) + SKIP(return, "setup_userns failed"); +} + +FIXTURE_TEARDOWN(fscontext_ns) +{ +} + +/* + * The condition the kernel used to WARN about. It has to be refused, and it + * has to be refused quietly: an unprivileged task reaches this. + */ +FIXTURE_VARIANT(fscontext_ns) { + const char *fsname; + int expected_errno; +}; + +FIXTURE_VARIANT_ADD(fscontext_ns, binfmt_misc) { + .fsname = "binfmt_misc", + .expected_errno = EINVAL, +}; + +FIXTURE_VARIANT_ADD(fscontext_ns, overlay) { + .fsname = "overlay", + .expected_errno = EIO, +}; + +TEST_F(fscontext_ns, create_from_descendant_userns) +{ + int ret; + + ret = create_from_child(variant->fsname, true); + if (ret == -ENODATA) + SKIP(return, "%s unavailable", variant->fsname); + + ASSERT_EQ(-1, ret); + ASSERT_EQ(variant->expected_errno, errno); + + /* + * Only meaningful if nothing had warned before us. Note that an + * unrelated warning racing this test would look like a failure. + */ + if (self->warn_before) + TH_LOG("TAINT_WARN already set, not checking for a new warning"); + else + ASSERT_FALSE(taint_warn_set()); +} + +/* + * The same handover within one user namespace is a supported thing to do and + * has to keep working. binfmt_misc takes no options, so the create succeeds + * outright and this also shows the test really drives the create path. + */ +TEST(create_from_same_userns) +{ + int ret; + + if (setup_userns() != 0) + SKIP(return, "setup_userns failed"); + + ret = create_from_child("binfmt_misc", false); + if (ret == -ENODATA) + SKIP(return, "binfmt_misc unavailable"); + + ASSERT_EQ(0, ret); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/filesystems/fuse/Makefile b/tools/testing/selftests/filesystems/fuse/Makefile index 612aad69a93a..f47141484275 100644 --- a/tools/testing/selftests/filesystems/fuse/Makefile +++ b/tools/testing/selftests/filesystems/fuse/Makefile @@ -5,6 +5,13 @@ CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) TEST_GEN_PROGS := fusectl_test TEST_GEN_FILES := fuse_mnt +# fuse_acl_cache_test requires libfuse3; add it only when the library is present. +ACL_CFLAGS := $(shell pkg-config fuse3 --cflags 2>/dev/null) +ACL_LDLIBS := $(shell pkg-config fuse3 --libs 2>/dev/null) +ifneq ($(ACL_CFLAGS),) +TEST_GEN_PROGS += fuse_acl_cache_test +endif + include ../../lib.mk VAR_CFLAGS := $(shell pkg-config fuse --cflags 2>/dev/null) @@ -19,3 +26,6 @@ endif $(OUTPUT)/fuse_mnt: CFLAGS += $(VAR_CFLAGS) $(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS) + +$(OUTPUT)/fuse_acl_cache_test: CFLAGS += $(ACL_CFLAGS) +$(OUTPUT)/fuse_acl_cache_test: LDLIBS += $(ACL_LDLIBS) diff --git a/tools/testing/selftests/filesystems/fuse/fuse_acl_cache_test.c b/tools/testing/selftests/filesystems/fuse/fuse_acl_cache_test.c new file mode 100644 index 000000000000..2411a6e285f1 --- /dev/null +++ b/tools/testing/selftests/filesystems/fuse/fuse_acl_cache_test.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test: FUSE ACL caching bug triggered by AT_STATX_FORCE_SYNC + * + * A FUSE mount that does not negotiate FUSE_POSIX_ACL initialises every inode + * with i_acl = i_default_acl = ACL_DONT_CACHE. When a fresh stat is needed + * (e.g. AT_STATX_FORCE_SYNC), fuse_update_get_attr() calls + * forget_all_cached_acls() before issuing FUSE_GETATTR. On an unfixed kernel, + * __forget_cached_acl() replaces ACL_DONT_CACHE with ACL_NOT_CACHED, + * inadvertently enabling the kernel ACL cache for that inode. The next + * getxattr populates the cache. Because fuse_set_acl() skips + * forget_all_cached_acls() for !fc->posix_acl mounts, any subsequent change to + * the ACL leaves the stale kernel entry in place, and the next getxattr returns + * wrong data without ever reaching the FUSE daemon. + * + * Fix (fs/posix_acl.c): __forget_cached_acl() returns early when *p is + * ACL_DONT_CACHE, preserving the "never cache" invariant for the inode's + * lifetime. + * + * Test outline: + * 1. Mount a minimal FUSE fs (no FUSE_POSIX_ACL negotiated). + * 2. lgetxattr -> daemon called, ACL_A returned, NOT cached (ACL_DONT_CACHE). + * 3. statx(AT_STATX_FORCE_SYNC) -> forget_all_cached_acls() called. + * Buggy: ACL_DONT_CACHE -> ACL_NOT_CACHED (cache enabled). + * Fixed: ACL_DONT_CACHE preserved. + * 4. lgetxattr -> daemon called, ACL_A returned. + * Buggy: result now cached (ACL_NOT_CACHED -> cached). + * Fixed: result still not cached. + * 5. Daemon switches to ACL_B internally (different size). + * 6. lgetxattr -> should return ACL_B (44 bytes). + * Buggy: cache hit, returns stale ACL_A (28 bytes). FAIL. + * Fixed: no cache, daemon called, returns ACL_B (44 bytes). PASS. + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <linux/limits.h> +#include <pthread.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/stat.h> +#include <sys/xattr.h> +#include <unistd.h> + +#define FUSE_USE_VERSION 31 +#include <fuse_lowlevel.h> + +#include "kselftest_harness.h" + +/* ---- ACL binary encoding ------------------------------------------------ */ +/* + * POSIX ACL v2 xattr format (little-endian): + * header: u32 version (= 0x00000002) + * entry: u16 tag | u16 perm | u32 id + * + * Entries must appear in tag-ascending order; named USER/GROUP entries + * require a MASK entry. Both ACLs pass posix_acl_from_xattr() validation. + */ + +/* ACL_A: 3 entries (USER_OBJ:rwx, GROUP_OBJ:r-x, OTHER:r-x) = 28 bytes */ +static const uint8_t acl_a[] = { + 0x02, 0x00, 0x00, 0x00, /* v2 header */ + 0x01, 0x00, 0x07, 0x00, 0xff, 0xff, 0xff, 0xff, /* USER_OBJ rwx */ + 0x04, 0x00, 0x05, 0x00, 0xff, 0xff, 0xff, 0xff, /* GROUP_OBJ r-x */ + 0x20, 0x00, 0x05, 0x00, 0xff, 0xff, 0xff, 0xff, /* OTHER r-x */ +}; + +/* + * ACL_B: 5 entries — adds USER uid=1 and MASK = 44 bytes. + * A named USER entry requires a MASK; all tags in ascending order. + */ +static const uint8_t acl_b[] = { + 0x02, 0x00, 0x00, 0x00, /* v2 header */ + 0x01, 0x00, 0x07, 0x00, 0xff, 0xff, 0xff, 0xff, /* USER_OBJ rwx */ + 0x02, 0x00, 0x07, 0x00, 0x01, 0x00, 0x00, 0x00, /* USER uid=1 rwx */ + 0x04, 0x00, 0x05, 0x00, 0xff, 0xff, 0xff, 0xff, /* GROUP_OBJ r-x */ + 0x10, 0x00, 0x07, 0x00, 0xff, 0xff, 0xff, 0xff, /* MASK rwx */ + 0x20, 0x00, 0x05, 0x00, 0xff, 0xff, 0xff, 0xff, /* OTHER r-x */ +}; + +/* ---- Shared state (daemon thread <-> test thread) ----------------------- */ + +#define FILE_INO 2 +#define FILE_NAME "testfile" + +struct daemon_state { + pthread_mutex_t lock; + const uint8_t *acl; + size_t acl_size; + int getxattr_count; +}; + +/* + * Global: callbacks are stateless fns so we use a single global. + * Safe because only one test instance runs at a time. + */ +static struct daemon_state g_ds = { + .lock = PTHREAD_MUTEX_INITIALIZER, +}; + +/* ---- FUSE lowlevel callbacks -------------------------------------------- */ + +static void fs_lookup(fuse_req_t req, fuse_ino_t parent, const char *name) +{ + if (parent != FUSE_ROOT_ID || strcmp(name, FILE_NAME)) { + fuse_reply_err(req, ENOENT); + return; + } + struct fuse_entry_param e = {}; + + /* + * Long attr/entry timeouts so that normal stat() calls do not + * expire and trigger forget_all_cached_acls() on their own; + * only the explicit AT_STATX_FORCE_SYNC should trigger it. + */ + e.ino = FILE_INO; + e.generation = 1; + e.attr_timeout = 10.0; + e.entry_timeout = 10.0; + e.attr.st_ino = FILE_INO; + e.attr.st_mode = S_IFREG | 0644; + e.attr.st_nlink = 1; + fuse_reply_entry(req, &e); +} + +static void fs_getattr(fuse_req_t req, fuse_ino_t ino, + struct fuse_file_info *fi) +{ + struct stat st = {}; + + (void)fi; + if (ino == FUSE_ROOT_ID) { + st.st_ino = FUSE_ROOT_ID; + st.st_mode = S_IFDIR | 0755; + st.st_nlink = 2; + } else if (ino == FILE_INO) { + st.st_ino = FILE_INO; + st.st_mode = S_IFREG | 0644; + st.st_nlink = 1; + } else { + fuse_reply_err(req, ENOENT); + return; + } + fuse_reply_attr(req, &st, 10); +} + +static void fs_getxattr(fuse_req_t req, fuse_ino_t ino, const char *name, + size_t size) +{ + if (ino != FILE_INO || + strcmp(name, "system.posix_acl_access") != 0) { + fuse_reply_err(req, ENODATA); + return; + } + + pthread_mutex_lock(&g_ds.lock); + const uint8_t *acl = g_ds.acl; + size_t acl_size = g_ds.acl_size; + g_ds.getxattr_count++; + pthread_mutex_unlock(&g_ds.lock); + + if (size == 0) + fuse_reply_xattr(req, acl_size); + else if (size < acl_size) + fuse_reply_err(req, ERANGE); + else + fuse_reply_buf(req, (const char *)acl, acl_size); +} + +static const struct fuse_lowlevel_ops fs_ops = { + .lookup = fs_lookup, + .getattr = fs_getattr, + .getxattr = fs_getxattr, +}; + +/* ---- Daemon thread ------------------------------------------------------- */ + +static void *run_daemon(void *arg) +{ + fuse_session_loop((struct fuse_session *)arg); + return NULL; +} + +/* ---- kselftest harness --------------------------------------------------- */ + +FIXTURE(acl_cache) { + struct fuse_session *se; + char mountpoint[PATH_MAX]; + char file_path[PATH_MAX]; + pthread_t thread; +}; + +FIXTURE_SETUP(acl_cache) +{ + char *fuse_argv[] = { "fuse_acl_cache_test", NULL }; + struct fuse_args args = FUSE_ARGS_INIT(1, fuse_argv); + + g_ds.acl = acl_a; + g_ds.acl_size = sizeof(acl_a); + g_ds.getxattr_count = 0; + + strcpy(self->mountpoint, "/tmp/acl_cache_test_XXXXXX"); + if (!mkdtemp(self->mountpoint)) + SKIP(return, "mkdtemp: %s", strerror(errno)); + + snprintf(self->file_path, sizeof(self->file_path), + "%s/" FILE_NAME, self->mountpoint); + + self->se = fuse_session_new(&args, &fs_ops, sizeof(fs_ops), NULL); + if (!self->se) { + rmdir(self->mountpoint); + SKIP(return, "fuse_session_new failed"); + } + + if (fuse_session_mount(self->se, self->mountpoint)) { + fuse_session_destroy(self->se); + rmdir(self->mountpoint); + SKIP(return, "fuse_session_mount failed " + "(missing fusermount3 or insufficient privileges)"); + } + + if (pthread_create(&self->thread, NULL, run_daemon, self->se)) { + fuse_session_unmount(self->se); + fuse_session_destroy(self->se); + rmdir(self->mountpoint); + SKIP(return, "pthread_create: %s", strerror(errno)); + } + + fuse_opt_free_args(&args); +} + +FIXTURE_TEARDOWN(acl_cache) +{ + fuse_session_exit(self->se); + fuse_session_unmount(self->se); + pthread_join(self->thread, NULL); + fuse_session_destroy(self->se); + rmdir(self->mountpoint); +} + +static int do_force_statx(const char *path) +{ + struct statx stx; + + return statx(AT_FDCWD, path, AT_STATX_FORCE_SYNC, STATX_BASIC_STATS, + &stx); +} + +TEST_F(acl_cache, stale_after_force_sync) +{ + char buf[512]; + ssize_t sz; + int count; + + /* + * Step 1: two getxattr calls before any statx(FORCE_SYNC). + * i_acl == ACL_DONT_CACHE. __get_acl's cmpxchg(p, ACL_NOT_CACHED, + * sentinel) finds *p != ACL_NOT_CACHED on every call, so the sentinel + * is never placed and the result is never cached. Both calls must + * reach the daemon, proving ACL_DONT_CACHE suppresses caching. + */ + sz = lgetxattr(self->file_path, "system.posix_acl_access", + buf, sizeof(buf)); + ASSERT_EQ(sz, (ssize_t)sizeof(acl_a)); + + sz = lgetxattr(self->file_path, "system.posix_acl_access", + buf, sizeof(buf)); + ASSERT_EQ(sz, (ssize_t)sizeof(acl_a)); + + pthread_mutex_lock(&g_ds.lock); + count = g_ds.getxattr_count; + pthread_mutex_unlock(&g_ds.lock); + + ASSERT_EQ(count, 2); + TH_LOG("step 1 OK: both pre-trigger getxattrs reached daemon (count=%d), " + "ACL_DONT_CACHE is working", count); + + /* + * Step 2: statx(AT_STATX_FORCE_SYNC). + * fuse_update_get_attr() calls forget_all_cached_acls() before sending + * FUSE_GETATTR. + * Buggy kernel: ACL_DONT_CACHE -> ACL_NOT_CACHED (cache enabled) + * Fixed kernel: ACL_DONT_CACHE preserved (no effect) + */ + ASSERT_EQ(do_force_statx(self->file_path), 0); + TH_LOG("step 2 OK: statx(AT_STATX_FORCE_SYNC) succeeded"); + + /* + * Step 3: getxattr — cache population attempt after the trigger. + * Buggy: *p == ACL_NOT_CACHED -> sentinel placed -> fuse_get_inode_acl + * called -> ACL_A parsed and stored in the kernel cache. + * Fixed: *p == ACL_DONT_CACHE -> sentinel placement skipped -> + * fuse_get_inode_acl called but result not cached. + * Either way the correct ACL_A is returned here. + */ + sz = lgetxattr(self->file_path, "system.posix_acl_access", + buf, sizeof(buf)); + ASSERT_EQ(sz, (ssize_t)sizeof(acl_a)); + + pthread_mutex_lock(&g_ds.lock); + count = g_ds.getxattr_count; + pthread_mutex_unlock(&g_ds.lock); + + ASSERT_EQ(count, 3); + TH_LOG("step 3 OK: post-trigger getxattr reached daemon (count=%d), " + "returned correct ACL_A (%zd bytes)", count, sz); + + /* + * Step 4: switch daemon to ACL_B (different size: 44 vs 28 bytes). + * Simulates an ACL change that fuse_set_acl() would NOT invalidate for + * !fc->posix_acl mounts (it skips forget_all_cached_acls in that case). + * On a fixed kernel the ACL was never cached, so this is moot. + */ + pthread_mutex_lock(&g_ds.lock); + g_ds.acl = acl_b; + g_ds.acl_size = sizeof(acl_b); + pthread_mutex_unlock(&g_ds.lock); + TH_LOG("step 4: daemon switched to ACL_B (%zu bytes)", sizeof(acl_b)); + + /* + * Step 5: getxattr — the decisive check. + * Buggy kernel: cache hit -> stale ACL_A (28 bytes), count stays 3. + * Fixed kernel: no cache -> daemon called -> ACL_B (44 bytes), count 4. + */ + sz = lgetxattr(self->file_path, "system.posix_acl_access", + buf, sizeof(buf)); + + pthread_mutex_lock(&g_ds.lock); + count = g_ds.getxattr_count; + pthread_mutex_unlock(&g_ds.lock); + + if (sz == (ssize_t)sizeof(acl_a)) + TH_LOG("step 5 BUG: stale ACL_A (%zd bytes) from kernel cache " + "(count=%d); ACL_DONT_CACHE corrupted by " + "forget_all_cached_acls()", sz, count); + else + TH_LOG("step 5 OK: daemon reached (count=%d), " + "fresh ACL_B (%zd bytes)", count, sz); + + EXPECT_EQ(sz, (ssize_t)sizeof(acl_b)); + EXPECT_EQ(count, 4); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 0a56bf209f6c..8ad2c385407e 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -503,6 +503,7 @@ for t in $TEST_CASES; do done # Test on instance loop +(cd $TRACING_DIR; initialize_system) INSTANCE=" (instance) " for t in $TEST_CASES; do test_on_instance $t || continue diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc index c300eb020262..e2322693d0c3 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_eprobe.tc @@ -1,16 +1,16 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: Generic dynamic event - add/remove eprobe events -# requires: dynamic_events events/syscalls/sys_enter_openat "<attached-group>.<attached-event> [<args>]":README +# requires: dynamic_events events/syscalls/sys_enter_chdir "<attached-group>.<attached-event> [<args>]":README echo 0 > events/enable clear_dynamic_events SYSTEM="syscalls" -EVENT="sys_enter_openat" +EVENT="sys_enter_chdir" FIELD="filename" -EPROBE="eprobe_open" +EPROBE="eprobe_chdir" OPTIONS="file=+0(\$filename):ustring" echo "e:$EPROBE $SYSTEM/$EVENT $OPTIONS" >> dynamic_events @@ -18,20 +18,14 @@ grep -q "$EPROBE" dynamic_events test -d events/eprobes/$EPROBE echo 1 > events/eprobes/$EPROBE/enable -ls +cd /sys/kernel/tracing echo 0 > events/eprobes/$EPROBE/enable -content=`grep '^ *ls-' trace | grep 'file='` -nocontent=`grep '^ *ls-' trace | grep 'file=' | grep -v -e '"/' -e '"."' -e '(fault)' ` || true - +content=`grep -e 'file="/sys/kernel/tracing"\|(fault)' trace` if [ -z "$content" ]; then exit_fail fi -if [ ! -z "$nocontent" ]; then - exit_fail -fi - echo "-:$EPROBE" >> dynamic_events ! grep -q "$EPROBE" dynamic_events diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc index 2915206777b6..89660a9adf44 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe_module.tc @@ -16,23 +16,32 @@ echo > dynamic_events FUNC1='foo_bar*' FUNC2='vfs_read' +:;: "Save enabled functions count" ;: +ecount=`cat enabled_functions | wc -l` + +count_enabled_functions() { + count=`cat enabled_functions | wc -l` + count=$(($count-$ecount)) + echo $count +} + :;: "Add an event on the test module" ;: echo "f:test1 $FUNC1" >> dynamic_events echo 1 > events/fprobes/test1/enable :;: "Ensure it is enabled" ;: -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -ne 0 :;: "Check the enabled_functions is cleared on unloading" ;: rmmod trace-events-sample -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -eq 0 :;: "Check it is kept clean" ;: modprobe trace-events-sample echo 1 > events/fprobes/test1/enable || echo "OK" -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -eq 0 :;: "Add another event not on the test module" ;: @@ -40,19 +49,19 @@ echo "f:test2 $FUNC2" >> dynamic_events echo 1 > events/fprobes/test2/enable :;: "Ensure it is enabled" ;: -ofuncs=`cat enabled_functions | wc -l` +ofuncs=`count_enabled_functions` test $ofuncs -ne 0 :;: "Disable and remove the first event" echo 0 > events/fprobes/test1/enable echo "-:fprobes/test1" >> dynamic_events -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $ofuncs -eq $funcs :;: "Disable and remove other events" ;: echo 0 > events/fprobes/enable echo > dynamic_events -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -eq 0 rmmod trace-events-sample @@ -63,12 +72,12 @@ echo "f:test1 $FUNC1" >> dynamic_events echo 1 > events/fprobes/test1/enable echo "f:test2 $FUNC2" >> dynamic_events echo 1 > events/fprobes/test2/enable -ofuncs=`cat enabled_functions | wc -l` +ofuncs=`count_enabled_functions` test $ofuncs -ne 0 :;: "Unload module (ftrace entry should be removed)" ;: rmmod trace-events-sample -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -ne 0 test $ofuncs -ne $funcs @@ -77,7 +86,7 @@ echo 0 > events/fprobes/test2/enable echo "-:fprobes/test2" >> dynamic_events :;: "Ensure ftrace is disabled." ;: -funcs=`cat enabled_functions | wc -l` +funcs=`count_enabled_functions` test $funcs -eq 0 echo 0 > events/fprobes/enable diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc index f2048c244526..19430bd5864c 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc @@ -12,9 +12,32 @@ echo 0 > events/enable echo > dynamic_events REALBIN=`readlink -f /bin/sh` -ENTRYPOINT=`readelf -h ${REALBIN} | grep Entry | sed -e 's/[^0]*//'` -echo "p:myevent ${REALBIN}:${ENTRYPOINT}" >> uprobe_events +# Get the entry point virtual address from ELF header +ENTRY=`readelf -hW ${REALBIN} | grep "Entry point" | awk '{print $NF}'` + +# Convert virtual address to file offset: find the LOAD segment containing +# the entry point, then compute file_offset = e_entry - p_vaddr + p_offset. +# For PIE binaries this is a no-op (vaddr == file offset), but for non-PIE +# executables the virtual address is much larger than the file size and +# must be converted, otherwise uprobe_register() rejects it with -EINVAL. +ENTRY_DEC=$(printf '%d' "$ENTRY") +OFFSET=$ENTRY +while IFS= read -r line; do + set -- $line + [ "$1" = "LOAD" ] || continue + VA_DEC=$(printf '%d' "$3") + OFF_DEC=$(printf '%d' "$2") + FSZ_DEC=$(printf '%d' "$5") + if [ "$ENTRY_DEC" -ge "$VA_DEC" ] && [ "$ENTRY_DEC" -lt "$((VA_DEC + FSZ_DEC))" ]; then + OFFSET=$(printf '0x%x' "$((ENTRY_DEC - VA_DEC + OFF_DEC))") + break + fi +done << EOF +$(readelf -lW ${REALBIN} | grep LOAD) +EOF + +echo "p:myevent ${REALBIN}:${OFFSET}" >> uprobe_events grep -q myevent uprobe_events test -d events/uprobes/myevent diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc index 8d275e3238d9..04eb8546fc07 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc @@ -1,7 +1,7 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # description: event trigger - test poll wait on histogram -# requires: set_event events/sched/sched_process_free/trigger events/sched/sched_process_free/hist +# requires: set_event events/sched/sched_process_exit/trigger events/sched/sched_process_exit/hist # flags: instance POLL=${FTRACETEST_ROOT}/poll @@ -11,7 +11,7 @@ if [ ! -x ${POLL} ]; then exit_unresolved fi -EVENT=events/sched/sched_process_free/ +EVENT=events/sched/sched_process_exit/ # Check poll ops is supported. Before implementing poll on hist file, it # returns soon with POLLIN | POLLOUT, but not POLLPRI. diff --git a/tools/testing/selftests/gpio/.gitignore b/tools/testing/selftests/gpio/.gitignore index ededb077a3a6..16f74de479f1 100644 --- a/tools/testing/selftests/gpio/.gitignore +++ b/tools/testing/selftests/gpio/.gitignore @@ -2,3 +2,4 @@ gpio-mockup-cdev gpio-chip-info gpio-line-name +gpio-cdev-uaf diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile index 96071b4800e8..2f423de83147 100644 --- a/tools/testing/selftests/hid/Makefile +++ b/tools/testing/selftests/hid/Makefile @@ -24,7 +24,7 @@ CXX ?= $(CROSS_COMPILE)g++ HOSTPKG_CONFIG := pkg-config -CFLAGS += -g -O0 -rdynamic -Wall -Werror -I$(OUTPUT) +CFLAGS += -g -O0 -rdynamic -Wall -Werror -I$(OUTPUT) $(KHDR_INCLUDES) CFLAGS += -I$(OUTPUT)/tools/include LDLIBS += -lelf -lz -lrt -lpthread diff --git a/tools/testing/selftests/hid/hid_bpf.c b/tools/testing/selftests/hid/hid_bpf.c index 1e979fb3542b..b851339308c2 100644 --- a/tools/testing/selftests/hid/hid_bpf.c +++ b/tools/testing/selftests/hid/hid_bpf.c @@ -86,6 +86,20 @@ static void load_programs(const struct test_program programs[], self->skel = hid__open(); ASSERT_OK_PTR(self->skel) TEARDOWN_LOG("Error while calling hid__open"); + /* + * Disable all struct_ops maps by default so libbpf does not autoload + * programs referenced by maps that are unrelated to the current test. + */ + bpf_object__for_each_map(iter_map, *self->skel->skeleton->obj) { + if (bpf_map__type(iter_map) == BPF_MAP_TYPE_STRUCT_OPS) { + err = bpf_map__set_autocreate(iter_map, false); + ASSERT_OK(err) TH_LOG("can not disable struct_ops map '%s'", + bpf_map__name(iter_map)); + } + + bpf_map__set_autoattach(iter_map, false); + } + for (int i = 0; i < progs_count; i++) { struct bpf_program *prog; struct bpf_map *map; @@ -102,6 +116,10 @@ static void load_programs(const struct test_program programs[], ASSERT_OK_PTR(map) TH_LOG("can not find struct_ops by name '%s'", programs[i].name + 4); + err = bpf_map__set_autocreate(map, true); + ASSERT_OK(err) TH_LOG("can not enable struct_ops map '%s'", + programs[i].name + 4); + /* hid_id is the first field of struct hid_bpf_ops */ ops_hid_id = bpf_map__initial_value(map, NULL); ASSERT_OK_PTR(ops_hid_id) TH_LOG("unable to retrieve struct_ops data"); @@ -109,13 +127,6 @@ static void load_programs(const struct test_program programs[], *ops_hid_id = self->hid.hid_id; } - /* we disable the auto-attach feature of all maps because we - * only want the tested one to be manually attached in the next - * call to bpf_map__attach_struct_ops() - */ - bpf_object__for_each_map(iter_map, *self->skel->skeleton->obj) - bpf_map__set_autoattach(iter_map, false); - err = hid__load(self->skel); ASSERT_OK(err) TH_LOG("hid_skel_load failed: %d", err); @@ -887,6 +898,17 @@ TEST_F(hid_bpf, test_rdesc_fixup) ASSERT_EQ(rpt_desc.value[4], 0x42); } +TEST_F(hid_bpf, test_rdesc_fixup_get_data_overflow) +{ + const struct test_program progs[] = { + { .name = "hid_rdesc_fixup_get_data_overflow" }, + }; + + LOAD_PROGRAMS(progs); + + ASSERT_EQ(self->skel->bss->get_data_overflow_check, 1); +} + static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) { diff --git a/tools/testing/selftests/hid/progs/hid.c b/tools/testing/selftests/hid/progs/hid.c index 5ecc845ef792..b21fbb13c926 100644 --- a/tools/testing/selftests/hid/progs/hid.c +++ b/tools/testing/selftests/hid/progs/hid.c @@ -13,6 +13,7 @@ struct attach_prog_args { __u64 callback_check = 52; __u64 callback2_check = 52; +__u64 get_data_overflow_check; SEC("?struct_ops/hid_device_event") int BPF_PROG(hid_first_event, struct hid_bpf_ctx *hid_ctx, enum hid_report_type type) @@ -240,6 +241,20 @@ struct hid_bpf_ops rdesc_fixup = { .hid_rdesc_fixup = (void *)hid_rdesc_fixup, }; +SEC("?struct_ops.s/hid_rdesc_fixup") +int BPF_PROG(hid_rdesc_fixup_get_data_overflow, struct hid_bpf_ctx *hid_ctx) +{ + if (!hid_bpf_get_data(hid_ctx, 2 /* offset */, ~0ULL /* size */)) + get_data_overflow_check = 1; + + return 0; +} + +SEC(".struct_ops.link") +struct hid_bpf_ops rdesc_fixup_get_data_overflow = { + .hid_rdesc_fixup = (void *)hid_rdesc_fixup_get_data_overflow, +}; + SEC("?struct_ops/hid_device_event") int BPF_PROG(hid_test_insert1, struct hid_bpf_ctx *hid_ctx, enum hid_report_type type) { diff --git a/tools/testing/selftests/hid/tests/test_multitouch.py b/tools/testing/selftests/hid/tests/test_multitouch.py index fa4fb2054bd4..7897340118b4 100644 --- a/tools/testing/selftests/hid/tests/test_multitouch.py +++ b/tools/testing/selftests/hid/tests/test_multitouch.py @@ -513,6 +513,79 @@ class SmartTechDigitizer(Digitizer): return absinfo is not None and absinfo.resolution == 3 +class MinWin8TSParallelBigContactMax(Digitizer): + """A parallel Win8 touchscreen that advertises a ContactCountMaximum much + larger than the number of contacts it actually reports. + + Such firmware makes the driver allocate that many input slots (up to 255) + while the input report only carries a few contacts. This is what used to + drive the per-slot bit operations on mt_io_flags out of bounds. The number + of contacts a HID report can describe is limited by the descriptor size, + so a large ContactCountMaximum can only be expressed this way, decoupled + from the number of finger collections.""" + + def __init__(self, n_fingers=5, contact_max=250): + self.phys_max = 120, 90 + rdesc_finger_str = f""" + Usage Page (Digitizers) + Usage (Finger) + Collection (Logical) + Report Size (1) + Report Count (1) + Logical Minimum (0) + Logical Maximum (1) + Usage (Tip Switch) + Input (Data,Var,Abs) + Report Size (7) + Logical Maximum (127) + Input (Cnst,Var,Abs) + Report Size (8) + Logical Maximum (255) + Usage (Contact Id) + Input (Data,Var,Abs) + Report Size (16) + Unit Exponent (-1) + Unit (SILinear: cm) + Logical Maximum (4095) + Physical Minimum (0) + Physical Maximum ({self.phys_max[0]}) + Usage Page (Generic Desktop) + Usage (X) + Input (Data,Var,Abs) + Physical Maximum ({self.phys_max[1]}) + Usage (Y) + Input (Data,Var,Abs) + End Collection +""" + rdesc_str = f""" + Usage Page (Digitizers) + Usage (Touch Screen) + Collection (Application) + Report ID (1) + {rdesc_finger_str * n_fingers} + Unit Exponent (-4) + Unit (SILinear: s) + Logical Maximum (65535) + Physical Maximum (65535) + Usage Page (Digitizers) + Usage (Scan Time) + Input (Data,Var,Abs) + Report Size (8) + Logical Maximum (255) + Usage (Contact Count) + Input (Data,Var,Abs) + Report ID (2) + Logical Maximum ({contact_max}) + Usage (Contact Max) + Feature (Data,Var,Abs) + End Collection + {Digitizer.msCertificationBlob(68)} +""" + super().__init__( + f"uhid test parallel big contact max {contact_max}", rdesc_str + ) + + class BaseTest: class TestMultitouch(base.BaseTestCase.TestUhid): kernel_modules = [KERNEL_MODULE] @@ -1735,6 +1808,47 @@ class TestMinWin8TSParallel(BaseTest.TestWin8Multitouch): return MinWin8TSParallel(10) +class TestMinWin8TSParallelBigContactMax(base.BaseTestCase.TestUhid): + """Regression test for the out-of-bounds bit operations on + struct mt_device.mt_io_flags. + + A Win8 touchscreen may advertise a ContactCountMaximum much larger than + the number of contacts it reports. The driver used to keep the per-slot + active state in the bits of a single unsigned long while indexing + set_bit()/clear_bit() by the slot number, so such a device drove those bit + operations out of bounds. The sticky-fingers release timer made it fatal: + mt_release_contacts() cleared one bit per slot, overwrote the adjacent + struct mt_device members and panicked the kernel. + + Send a single contact, let the 100ms sticky-fingers timer release it, and + check that the kernel reports the release cleanly instead of crashing.""" + + kernel_modules = [KERNEL_MODULE] + + def create_device(self): + return MinWin8TSParallelBigContactMax() + + def test_sticky_fingers_release_big_contact_max(self): + uhdev = self.uhdev + evdev = uhdev.get_evdev() + + assert evdev.num_slots == uhdev.max_contacts + + t0 = Touch(1, 5, 10) + r = uhdev.event([t0]) + events = uhdev.next_sync_events() + self.debug_reports(r, uhdev, events) + assert evdev.slots[0][libevdev.EV_ABS.ABS_MT_TRACKING_ID] == 0 + + # do not release the contact; the sticky-fingers timer must do it + # after 100ms, which is where the out-of-bounds release used to hit + time.sleep(0.2) + events = uhdev.next_sync_events() + self.debug_reports(r, uhdev, events) + assert libevdev.InputEvent(libevdev.EV_KEY.BTN_TOUCH, 0) in events + assert evdev.slots[0][libevdev.EV_ABS.ABS_MT_TRACKING_ID] == -1 + + class TestMinWin8TSHybrid(BaseTest.TestWin8Multitouch): def create_device(self): return MinWin8TSHybrid() diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index d28a057fa6c2..6fc34e9bf8e1 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -174,6 +174,7 @@ TEST_GEN_PROGS_arm64 += arm64/hello_el2 TEST_GEN_PROGS_arm64 += arm64/host_sve TEST_GEN_PROGS_arm64 += arm64/hypercalls TEST_GEN_PROGS_arm64 += arm64/external_aborts +TEST_GEN_PROGS_arm64 += arm64/mmio_sign_ext TEST_GEN_PROGS_arm64 += arm64/page_fault_test TEST_GEN_PROGS_arm64 += arm64/psci_test TEST_GEN_PROGS_arm64 += arm64/sea_to_user diff --git a/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c b/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c new file mode 100644 index 000000000000..25196f1e6322 --- /dev/null +++ b/tools/testing/selftests/kvm/arm64/mmio_sign_ext.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * mmio_sign_ext - Test sign-extending MMIO load emulation (LDRSB/LDRSH/LDRSW) + * + * Copyright (c) 2026 Google LLC + * Author: Fuad Tabba <fuad.tabba@linux.dev> + */ + +#include <asm/ptrace.h> + +#include "processor.h" +#include "test_util.h" + +#define MMIO_ADDR 0x8000000ULL + +/* AP[1]: allow unprivileged (EL0) access to a mapping. */ +#define PTE_USER BIT(6) + +/* SPSR for ERET to EL0t with DAIF masked. */ +#define SPSR_EL0 (PSR_MODE_EL0t | PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) + +struct mmio_test { + const char *name; + uint64_t data; /* access-width value, host byte order */ + uint8_t len; + uint64_t expected; /* sign-extended result; same for LE and BE */ +}; + +/* Paired 1:1, in order, with the loads in guest_loads_le() and el0_be_loads. */ +static const struct mmio_test tests[] = { + /* LDRSB Xt: byte sign-extended to 64 bits */ + { "LDRSB Xt 0xFF", 0xFF, 1, 0xFFFFFFFFFFFFFFFFULL }, + { "LDRSB Xt 0x7F", 0x7F, 1, 0x7FULL }, + + /* LDRSB Wt: byte sign-extended to 32 bits, upper 32 bits zeroed */ + { "LDRSB Wt 0xFF", 0xFF, 1, 0xFFFFFFFFULL }, + { "LDRSB Wt 0x7F", 0x7F, 1, 0x7FULL }, + + /* LDRSH Xt: halfword sign-extended to 64 bits */ + { "LDRSH Xt 0x8001", 0x8001, 2, 0xFFFFFFFFFFFF8001ULL }, + { "LDRSH Xt 0x7FFF", 0x7FFF, 2, 0x7FFFULL }, + + /* LDRSH Wt: halfword sign-extended to 32 bits, upper 32 bits zeroed */ + { "LDRSH Wt 0x8001", 0x8001, 2, 0xFFFF8001ULL }, + { "LDRSH Wt 0x7FFF", 0x7FFF, 2, 0x7FFFULL }, + + /* LDRSW Xt: word sign-extended to 64 bits (no Wt form) */ + { "LDRSW Xt 0x80000001", 0x80000001, 4, 0xFFFFFFFF80000001ULL }, + { "LDRSW Xt 0x7FFFFFFF", 0x7FFFFFFF, 4, 0x7FFFFFFFULL }, +}; + +/* Issue one sign-extending load from MMIO and report the result. */ +#define GUEST_LDRS(load) do { \ + uint64_t val; \ + \ + asm volatile(load : "=r"(val) : "r"(MMIO_ADDR) : "memory"); \ + GUEST_SYNC(val); \ +} while (0) + +/* Little-endian pass: loads issued at EL1. */ +static void guest_loads_le(void) +{ + GUEST_LDRS("ldrsb %0, [%1]"); + GUEST_LDRS("ldrsb %0, [%1]"); + GUEST_LDRS("ldrsb %w0, [%1]"); + GUEST_LDRS("ldrsb %w0, [%1]"); + GUEST_LDRS("ldrsh %0, [%1]"); + GUEST_LDRS("ldrsh %0, [%1]"); + GUEST_LDRS("ldrsh %w0, [%1]"); + GUEST_LDRS("ldrsh %w0, [%1]"); + GUEST_LDRS("ldrsw %0, [%1]"); + GUEST_LDRS("ldrsw %0, [%1]"); +} + +/* + * Run the big-endian loads at EL0, where SCTLR_EL1.E0E flips only the data + * endianness; at EL1, SCTLR_EL1.EE would also flip the page-table walk and + * fault on the little-endian tables. x0 holds MMIO_ADDR; results return in + * x19..x28 (tests[] order) via a single SVC. + */ +extern char el0_be_loads[]; +asm( +" .pushsection .text, \"ax\"\n" +" .global el0_be_loads\n" +"el0_be_loads:\n" +" ldrsb x19, [x0]\n" +" ldrsb x20, [x0]\n" +" ldrsb w21, [x0]\n" +" ldrsb w22, [x0]\n" +" ldrsh x23, [x0]\n" +" ldrsh x24, [x0]\n" +" ldrsh w25, [x0]\n" +" ldrsh w26, [x0]\n" +" ldrsw x27, [x0]\n" +" ldrsw x28, [x0]\n" +" svc #0\n" +" .popsection\n" +); + +/* EL1 handler for the EL0 SVC: report the results, then finish. */ +static void el0_svc_handler(struct ex_regs *regs) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(tests); i++) + GUEST_SYNC(regs->regs[19 + i]); + + GUEST_DONE(); +} + +static bool guest_mixed_endian_el0(void) +{ + uint64_t mmfr0 = read_sysreg(id_aa64mmfr0_el1); + + return SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGEND, mmfr0) || + SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGENDEL0, mmfr0); +} + +static void guest_code(void) +{ + guest_loads_le(); + + if (guest_mixed_endian_el0()) { + write_sysreg(read_sysreg(sctlr_el1) | SCTLR_EL1_E0E, sctlr_el1); + isb(); + + asm volatile( + " msr elr_el1, %[pc]\n" + " msr spsr_el1, %[spsr]\n" + " mov x0, %[mmio]\n" + " isb\n" + " eret\n" + : + : [pc] "r"(el0_be_loads), + [spsr] "r"((uint64_t)SPSR_EL0), + [mmio] "r"(MMIO_ADDR) + : "x0", "memory"); + __builtin_unreachable(); /* el0_svc_handler ends the test */ + } + + GUEST_DONE(); +} + +static void handle_mmio(struct kvm_run *run, const struct mmio_test *t, bool be) +{ + int i; + + TEST_ASSERT_EQ(run->mmio.phys_addr, MMIO_ADDR); + TEST_ASSERT(!run->mmio.is_write, "Expected MMIO read for %s", t->name); + TEST_ASSERT_EQ(run->mmio.len, t->len); + + memset(run->mmio.data, 0, sizeof(run->mmio.data)); + if (be) { + /* The guest reads the device bytes most-significant first. */ + for (i = 0; i < t->len; i++) + run->mmio.data[i] = t->data >> (8 * (t->len - 1 - i)); + } else { + /* Works because arm64 KVM hosts are always little-endian. */ + memcpy(run->mmio.data, &t->data, t->len); + } +} + +static void expect_sync(struct kvm_vcpu *vcpu, struct ucall *uc, + const struct mmio_test *t) +{ + switch (get_ucall(vcpu, uc)) { + case UCALL_SYNC: + TEST_ASSERT(uc->args[1] == t->expected, + "%s: got %#lx, want %#lx", t->name, + (unsigned long)uc->args[1], (unsigned long)t->expected); + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(*uc); + break; + default: + TEST_FAIL("Unexpected ucall for %s", t->name); + } +} + +/* OR PTE_USER into the leaf descriptors covering [gva, gva + len). */ +static void make_el0_accessible(struct kvm_vm *vm, uint64_t gva, uint64_t len) +{ + uint64_t addr; + + for (addr = gva & ~((uint64_t)vm->page_size - 1); addr < gva + len; + addr += vm->page_size) + *virt_get_pte_hva(vm, addr) |= PTE_USER; +} + +static bool vcpu_mixed_endian_el0(struct kvm_vcpu *vcpu) +{ + uint64_t mmfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1)); + + return SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGEND, mmfr0) || + SYS_FIELD_GET(ID_AA64MMFR0_EL1, BIGENDEL0, mmfr0); +} + +int main(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + struct ucall uc; + unsigned int i; + bool be; + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + virt_map(vm, MMIO_ADDR, MMIO_ADDR, 1); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vcpu); + vm_install_sync_handler(vm, VECTOR_SYNC_LOWER_64, ESR_ELx_EC_SVC64, + el0_svc_handler); + + be = vcpu_mixed_endian_el0(vcpu); + if (be) + make_el0_accessible(vm, MMIO_ADDR, vm->page_size); + + ksft_print_header(); + ksft_set_plan(ARRAY_SIZE(tests) * (be ? 2 : 1)); + + /* Little-endian pass: one load and one result per iteration. */ + for (i = 0; i < ARRAY_SIZE(tests); i++) { + const struct mmio_test *t = &tests[i]; + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_MMIO); + handle_mmio(vcpu->run, t, false); + + vcpu_run(vcpu); + expect_sync(vcpu, &uc, t); + + ksft_test_result_pass("%s\n", t->name); + } + + if (be) { + /* The EL0 stub issues all the loads, then reports the results. */ + for (i = 0; i < ARRAY_SIZE(tests); i++) { + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_MMIO); + handle_mmio(vcpu->run, &tests[i], true); + } + for (i = 0; i < ARRAY_SIZE(tests); i++) { + vcpu_run(vcpu); + expect_sync(vcpu, &uc, &tests[i]); + ksft_test_result_pass("BE %s\n", tests[i].name); + } + } + + vcpu_run(vcpu); + TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE, "Expected UCALL_DONE"); + + kvm_vm_free(vm); + + ksft_finished(); +} diff --git a/tools/testing/selftests/kvm/x86/sev_init2_tests.c b/tools/testing/selftests/kvm/x86/sev_init2_tests.c index 8db88c355f16..689390c10f7c 100644 --- a/tools/testing/selftests/kvm/x86/sev_init2_tests.c +++ b/tools/testing/selftests/kvm/x86/sev_init2_tests.c @@ -130,12 +130,18 @@ int main(int argc, char *argv[]) KVM_X86_SEV_VMSA_FEATURES, &supported_vmsa_features); - have_sev = kvm_cpu_has(X86_FEATURE_SEV); - TEST_ASSERT(have_sev == !!(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM)), - "sev: KVM_CAP_VM_TYPES (%x) does not match cpuid (checking %x)", - kvm_check_cap(KVM_CAP_VM_TYPES), 1 << KVM_X86_SEV_VM); + /* + * Whether a VM type is available depends on KVM, not just CPUID: e.g. + * when all SEV ASIDs are assigned to SEV-SNP, KVM does not offer the + * SEV VM type even though X86_FEATURE_SEV is set. Derive availability + * from KVM_CAP_VM_TYPES and only assert the one-way implication that a + * type offered by KVM must also be reported in CPUID. + */ + have_sev = kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM); + TEST_ASSERT(!have_sev || kvm_cpu_has(X86_FEATURE_SEV), + "sev: SEV_VM supported without SEV in CPUID"); - TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM)); + TEST_REQUIRE(have_sev); have_sev_es = kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_ES_VM); TEST_ASSERT(!have_sev_es || kvm_cpu_has(X86_FEATURE_SEV_ES), diff --git a/tools/testing/selftests/kvm/x86/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c index 42bc023d5193..d59abb198d86 100644 --- a/tools/testing/selftests/kvm/x86/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c @@ -313,6 +313,49 @@ out: kvm_vm_free(vm_no_vcpu); } +static void test_sev_snp_migrate_reject(void) +{ + struct kvm_vm *src_vm, *dst_vm; + int ret; + + src_vm = vm_create_barebones_type(KVM_X86_SNP_VM); + snp_vm_init(src_vm); + __vm_vcpu_add(src_vm, 0); + vm_sev_launch(src_vm, snp_default_policy(), NULL); + + dst_vm = vm_create_barebones_type(KVM_X86_SNP_VM); + __vm_vcpu_add(dst_vm, 0); + + ret = __sev_migrate_from(dst_vm, src_vm); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "SNP VM migration should be rejected. ret: %d, errno: %d", + ret, errno); + + kvm_vm_free(src_vm); + kvm_vm_free(dst_vm); +} + +static void test_sev_snp_mirror_reject(void) +{ + struct kvm_vm *src_vm, *dst_vm; + int ret; + + src_vm = vm_create_barebones_type(KVM_X86_SNP_VM); + snp_vm_init(src_vm); + __vm_vcpu_add(src_vm, 0); + vm_sev_launch(src_vm, snp_default_policy(), NULL); + + dst_vm = aux_vm_create(false); + + ret = __sev_mirror_create(dst_vm, src_vm); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "SNP VM mirroring should be rejected. ret: %d, errno: %d", + ret, errno); + + kvm_vm_free(src_vm); + kvm_vm_free(dst_vm); +} + static void test_sev_move_copy(void) { struct kvm_vm *dst_vm, *dst2_vm, *dst3_vm, *sev_vm, *mirror_vm, @@ -384,12 +427,16 @@ int main(int argc, char *argv[]) test_sev_migrate_parameters(); if (kvm_has_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) test_sev_move_copy(); + if (kvm_cpu_has(X86_FEATURE_SEV_SNP)) + test_sev_snp_migrate_reject(); } if (kvm_has_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) { test_sev_mirror(/* es= */ false); if (have_sev_es) test_sev_mirror(/* es= */ true); test_sev_mirror_parameters(); + if (kvm_cpu_has(X86_FEATURE_SEV_SNP)) + test_sev_snp_mirror_reject(); } return 0; } diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c index 6b2cbe2a90b7..bf27b6187afa 100644 --- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c @@ -247,7 +247,14 @@ int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV)); - test_sev_smoke(guest_sev_code, KVM_X86_SEV_VM, 0); + /* + * Only exercise VM types the host actually offers. CPUID reporting + * SEV does not guarantee KVM offers the SEV VM type: when all SEV + * ASIDs are assigned to SEV-SNP, KVM_X86_SEV_VM is unavailable even + * though X86_FEATURE_SEV is set. Gate every type on KVM_CAP_VM_TYPES. + */ + if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_VM)) + test_sev_smoke(guest_sev_code, KVM_X86_SEV_VM, 0); if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SEV_ES_VM)) test_sev_smoke(guest_sev_es_code, KVM_X86_SEV_ES_VM, SEV_POLICY_ES); diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index 2ed1f76b7a8b..be2eb88092fb 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -1281,6 +1281,103 @@ TEST_F(protocol, connect_unspec) EXPECT_EQ(0, close(bind_fd)); } +TEST_F(protocol, tcp_fastopen) +{ + const bool restricted = variant->sandbox == TCP_SANDBOX && + variant->prot.type == SOCK_STREAM && + (variant->prot.protocol == IPPROTO_TCP || + variant->prot.protocol == IPPROTO_IP) && + (variant->prot.domain == AF_INET || + variant->prot.domain == AF_INET6); + const struct landlock_ruleset_attr ruleset_attr = { + .handled_access_net = LANDLOCK_ACCESS_NET_CONNECT_TCP, + }; + int bind_fd, client_fd, status; + char buf; + pid_t child; + + bind_fd = socket_variant(&self->srv0); + ASSERT_LE(0, bind_fd); + EXPECT_EQ(0, bind_variant(bind_fd, &self->srv0)); + if (self->srv0.protocol.type == SOCK_STREAM) + EXPECT_EQ(0, listen(bind_fd, backlog)); + + child = fork(); + ASSERT_LE(0, child); + if (child == 0) { + int connect_fd, ret; + + /* Closes listening socket for the child. */ + EXPECT_EQ(0, close(bind_fd)); + + connect_fd = socket_variant(&self->srv0); + ASSERT_LE(0, connect_fd); + + if (variant->sandbox == TCP_SANDBOX) { + const int ruleset_fd = landlock_create_ruleset( + &ruleset_attr, sizeof(ruleset_attr), 0); + ASSERT_LE(0, ruleset_fd); + + enforce_ruleset(_metadata, ruleset_fd); + EXPECT_EQ(0, close(ruleset_fd)); + } + + /* Fast Open with no address. */ + ret = sendto_variant(connect_fd, NULL, NULL, 0, MSG_FASTOPEN); + if (self->srv0.protocol.domain == AF_UNIX) { + EXPECT_EQ(-ENOTCONN, ret); + } else if (self->srv0.protocol.type == SOCK_DGRAM) { + EXPECT_EQ(-EDESTADDRREQ, ret); + } else { + EXPECT_EQ(-EINVAL, ret); + } + + /* Fast Open to a denied address. */ + ret = sendto_variant(connect_fd, &self->srv0, "A", 1, + MSG_FASTOPEN); + if (restricted) { + EXPECT_EQ(-EACCES, ret); + } else if (self->srv0.protocol.domain == AF_UNIX && + self->srv0.protocol.type == SOCK_STREAM) { + EXPECT_EQ(-EOPNOTSUPP, ret); + } else { + EXPECT_EQ(0, ret); + } + + EXPECT_EQ(0, close(connect_fd)); + _exit(_metadata->exit_code); + return; + } + + client_fd = bind_fd; + if (!restricted && self->srv0.protocol.type == SOCK_STREAM && + self->srv0.protocol.domain != AF_UNIX) { + client_fd = accept(bind_fd, NULL, 0); + ASSERT_LE(0, client_fd); + } + + if (restricted) { + EXPECT_EQ(-1, read(client_fd, &buf, 1)); + EXPECT_EQ(ENOTCONN, errno); + } else if (self->srv0.protocol.domain == AF_UNIX && + self->srv0.protocol.type == SOCK_STREAM) { + EXPECT_EQ(-1, read(client_fd, &buf, 1)); + EXPECT_EQ(EINVAL, errno); + } else { + EXPECT_EQ(1, read(client_fd, &buf, 1)); + EXPECT_EQ('A', buf); + } + + EXPECT_EQ(child, waitpid(child, &status, 0)); + EXPECT_EQ(1, WIFEXITED(status)); + EXPECT_EQ(EXIT_SUCCESS, WEXITSTATUS(status)); + + if (client_fd != bind_fd) + EXPECT_LE(0, close(client_fd)); + + EXPECT_EQ(0, close(bind_fd)); +} + TEST_F(protocol, sendmsg_stream) { int srv0_fd, tmp_fd, client_fd, res; diff --git a/tools/testing/selftests/landlock/scoped_signal_test.c b/tools/testing/selftests/landlock/scoped_signal_test.c index f24f2c28f62e..2d37d0c06c06 100644 --- a/tools/testing/selftests/landlock/scoped_signal_test.c +++ b/tools/testing/selftests/landlock/scoped_signal_test.c @@ -249,12 +249,12 @@ TEST_F(scoped_domains, check_access_signal) _metadata->exit_code = KSFT_FAIL; } -enum thread_return { - THREAD_INVALID = 0, - THREAD_SUCCESS = 1, - THREAD_ERROR = 2, - THREAD_TEST_FAILED = 3, -}; +/* clang-format off */ +#define THREAD_INVALID ((void *)0) +#define THREAD_SUCCESS ((void *)1) +#define THREAD_ERROR ((void *)2) +#define THREAD_TEST_FAILED ((void *)3) +/* clang-format on */ static void *thread_sync(void *arg) { @@ -262,15 +262,15 @@ static void *thread_sync(void *arg) char buf; if (read(pipe_read, &buf, 1) != 1) - return (void *)THREAD_ERROR; + return THREAD_ERROR; - return (void *)THREAD_SUCCESS; + return THREAD_SUCCESS; } TEST(signal_scoping_thread_before) { pthread_t no_sandbox_thread; - enum thread_return ret = THREAD_INVALID; + void *ret = THREAD_INVALID; int thread_pipe[2]; drop_caps(_metadata); @@ -285,7 +285,7 @@ TEST(signal_scoping_thread_before) EXPECT_EQ(0, pthread_kill(no_sandbox_thread, 0)); EXPECT_EQ(1, write(thread_pipe[1], ".", 1)); - EXPECT_EQ(0, pthread_join(no_sandbox_thread, (void **)&ret)); + EXPECT_EQ(0, pthread_join(no_sandbox_thread, &ret)); EXPECT_EQ(THREAD_SUCCESS, ret); EXPECT_EQ(0, close(thread_pipe[0])); @@ -295,7 +295,7 @@ TEST(signal_scoping_thread_before) TEST(signal_scoping_thread_after) { pthread_t scoped_thread; - enum thread_return ret = THREAD_INVALID; + void *ret = THREAD_INVALID; int thread_pipe[2]; drop_caps(_metadata); @@ -310,7 +310,7 @@ TEST(signal_scoping_thread_after) EXPECT_EQ(0, pthread_kill(scoped_thread, 0)); EXPECT_EQ(1, write(thread_pipe[1], ".", 1)); - EXPECT_EQ(0, pthread_join(scoped_thread, (void **)&ret)); + EXPECT_EQ(0, pthread_join(scoped_thread, &ret)); EXPECT_EQ(THREAD_SUCCESS, ret); EXPECT_EQ(0, close(thread_pipe[0])); @@ -327,20 +327,20 @@ void *thread_setuid(void *ptr) char buf; if (read(arg->pipe_read, &buf, 1) != 1) - return (void *)THREAD_ERROR; + return THREAD_ERROR; /* libc's setuid() should update all thread's credentials. */ if (getuid() != arg->new_uid) - return (void *)THREAD_TEST_FAILED; + return THREAD_TEST_FAILED; - return (void *)THREAD_SUCCESS; + return THREAD_SUCCESS; } TEST(signal_scoping_thread_setuid) { struct thread_setuid_args arg; pthread_t no_sandbox_thread; - enum thread_return ret = THREAD_INVALID; + void *ret = THREAD_INVALID; int pipe_parent[2]; int prev_uid; @@ -367,7 +367,7 @@ TEST(signal_scoping_thread_setuid) EXPECT_EQ(arg.new_uid, getuid()); EXPECT_EQ(1, write(pipe_parent[1], ".", 1)); - EXPECT_EQ(0, pthread_join(no_sandbox_thread, (void **)&ret)); + EXPECT_EQ(0, pthread_join(no_sandbox_thread, &ret)); EXPECT_EQ(THREAD_SUCCESS, ret); clear_cap(_metadata, CAP_SETUID); @@ -400,6 +400,24 @@ static int setup_signal_handler(int signal) return sigaction(SIGURG, &sa, NULL); } +/* + * MSG_OOB might be disabled in the kernel via the CONFIG_AF_UNIX_OOB + * switch, so this function can be used for probing for its availability. + */ +static bool has_af_unix_oob(void) +{ + bool available = false; + int sp[2]; + + if (socketpair(AF_UNIX, SOCK_STREAM, 0, sp) == 0) { + available = (send(sp[0], ".", 1, MSG_OOB) == 1); + close(sp[0]); + close(sp[1]); + } + + return available; +} + /* clang-format off */ FIXTURE(fown) {}; /* clang-format on */ @@ -462,6 +480,9 @@ TEST_F(fown, sigurg_socket) int pipe_parent[2], pipe_child[2]; pid_t child; + if (!has_af_unix_oob()) + SKIP(return, "CONFIG_AF_UNIX_OOB / MSG_OOB not available"); + memset(&server_address, 0, sizeof(server_address)); set_unix_address(&server_address, 0); @@ -667,20 +688,20 @@ static void *thread_setown_scoped(void *arg) ruleset_fd = landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); if (ruleset_fd < 0) - return (void *)THREAD_ERROR; + return THREAD_ERROR; if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) || landlock_restrict_self(ruleset_fd, 0)) { close(ruleset_fd); - return (void *)THREAD_ERROR; + return THREAD_ERROR; } close(ruleset_fd); /* Makes this process group own the SIGIO source. */ if (fcntl(fd, F_SETSIG, SIGURG) || fcntl(fd, F_SETOWN, -getpgrp()) || fcntl(fd, F_SETFL, O_ASYNC)) - return (void *)THREAD_ERROR; + return THREAD_ERROR; - return (void *)THREAD_SUCCESS; + return THREAD_SUCCESS; } /* @@ -702,7 +723,7 @@ TEST(sigio_to_pgid_self) { int trigger[2]; pthread_t thread; - enum thread_return ret = THREAD_INVALID; + void *ret = THREAD_INVALID; int i; drop_caps(_metadata); @@ -722,7 +743,7 @@ TEST(sigio_to_pgid_self) */ ASSERT_EQ(0, pthread_create(&thread, NULL, thread_setown_scoped, &trigger[0])); - ASSERT_EQ(0, pthread_join(thread, (void **)&ret)); + ASSERT_EQ(0, pthread_join(thread, &ret)); ASSERT_EQ(THREAD_SUCCESS, ret); /* Fans SIGURG out to the process group. */ diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt index d8180bbe31e8..bec57a02913a 100644 --- a/tools/testing/selftests/lkdtm/tests.txt +++ b/tools/testing/selftests/lkdtm/tests.txt @@ -78,7 +78,7 @@ USERCOPY_STACK_FRAME_TO USERCOPY_STACK_FRAME_FROM USERCOPY_STACK_BEYOND USERCOPY_KERNEL -STACKLEAK_ERASING OK: the rest of the thread stack is properly erased +KSTACK_ERASE OK: the rest of the thread stack is properly erased CFI_FORWARD_PROTO CFI_BACKWARD call trace:|ok: control flow unchanged FORTIFY_STRSCPY detected buffer overflow diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index e4c49699f3f7..2f2b9879d100 100644 --- a/tools/testing/selftests/mm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c @@ -23,6 +23,7 @@ #include <time.h> #include <pthread.h> #include <limits.h> +#include <linux/mman.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/mman.h> diff --git a/tools/testing/selftests/mm/ksft_process_madv.sh b/tools/testing/selftests/mm/ksft_process_madv.sh index 2c3137ae8bc8..edad2d2d888f 100755 --- a/tools/testing/selftests/mm/ksft_process_madv.sh +++ b/tools/testing/selftests/mm/ksft_process_madv.sh @@ -1,4 +1,4 @@ #!/bin/sh -e # SPDX-License-Identifier: GPL-2.0 -./run_vmtests.sh -t mmap +./run_vmtests.sh -t process_madv diff --git a/tools/testing/selftests/mm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index 9d349c151360..16294bc7dae6 100644 --- a/tools/testing/selftests/mm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c @@ -84,7 +84,7 @@ int get_proc_locked_vm_size(void) int get_proc_page_size(unsigned long addr) { FILE *smaps; - char *line; + char *line = NULL; unsigned long mmupage_size = 0; size_t size; diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index 762306177ad8..f9bcff8e78fa 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -1051,6 +1051,57 @@ static void test_simple(void) ksft_test_result(i == TEST_ITERATIONS, "Test %s\n", __func__); } +/* + * A range that was populated and then MADV_DONTNEED'd is genuine pte_none + * with no uffd-wp marker. Such a pte must read the same regardless of which + * PAGEMAP_SCAN path serves the request: both the PAGE_IS_WRITTEN fast path and + * the generic path (reached e.g. via category_anyof_mask) must report every + * page written. + */ +static void unpopulated_scan_test(void) +{ + int npages = 16, i; + long mem_size = npages * page_size; + struct page_region regions[16]; + long fast = 0, slow = 0, ret; + char *mem; + + mem = mmap(NULL, mem_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("%s mmap failed\n", __func__); + + wp_init(mem, mem_size); + + /* Populate, then drop: the ptes become pte_none without a marker. */ + memset(mem, 1, mem_size); + if (madvise(mem, mem_size, MADV_DONTNEED)) + ksft_exit_fail_msg("%s MADV_DONTNEED failed\n", __func__); + + /* Fast path: category_mask == return_mask == PAGE_IS_WRITTEN. */ + ret = pagemap_ioctl(mem, mem_size, regions, npages, 0, 0, + PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); + if (ret < 0) + ksft_exit_fail_msg("%s fast scan failed\n", __func__); + for (i = 0; i < ret; i++) + fast += LEN(regions[i]); + + /* Generic path: same query expressed via category_anyof_mask. */ + ret = pagemap_ioctl(mem, mem_size, regions, npages, 0, 0, + 0, PAGE_IS_WRITTEN, 0, PAGE_IS_WRITTEN); + if (ret < 0) + ksft_exit_fail_msg("%s generic scan failed\n", __func__); + for (i = 0; i < ret; i++) + slow += LEN(regions[i]); + + ksft_test_result(fast == npages && slow == npages, + "%s unpopulated ptes reported written by both paths (%ld, %ld of %d)\n", + __func__, fast, slow, npages); + + wp_free(mem, mem_size); + munmap(mem, mem_size); +} + int sanity_tests(void) { unsigned long long mem_size, vec_size; @@ -1368,7 +1419,7 @@ void *thread_proc(void *mem) ksft_exit_fail_msg("pthread_barrier_wait\n"); for (i = 0; i < access_per_thread; ++i) - __atomic_add_fetch(m + i * (0x1000 / sizeof(*m)), 1, __ATOMIC_SEQ_CST); + __atomic_add_fetch(m + i * (page_size / sizeof(*m)), 1, __ATOMIC_SEQ_CST); ret = pthread_barrier_wait(&end_barrier); if (ret && ret != PTHREAD_BARRIER_SERIAL_THREAD) @@ -1403,15 +1454,15 @@ static void transact_test(int page_size) if (pthread_barrier_init(&end_barrier, NULL, nthreads + 1)) ksft_exit_fail_msg("pthread_barrier_init\n"); - mem = mmap(NULL, 0x1000 * nthreads * pages_per_thread, PROT_READ | PROT_WRITE, + mem = mmap(NULL, page_size * nthreads * pages_per_thread, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); if (mem == MAP_FAILED) ksft_exit_fail_msg("Error mmap %s.\n", strerror(errno)); - wp_init(mem, 0x1000 * nthreads * pages_per_thread); - wp_addr_range(mem, 0x1000 * nthreads * pages_per_thread); + wp_init(mem, page_size * nthreads * pages_per_thread); + wp_addr_range(mem, page_size * nthreads * pages_per_thread); - memset(mem, 0, 0x1000 * nthreads * pages_per_thread); + memset(mem, 0, page_size * nthreads * pages_per_thread); count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); ksft_test_result(count > 0, "%s count %u\n", __func__, count); @@ -1420,7 +1471,7 @@ static void transact_test(int page_size) finish = 0; for (i = 0; i < nthreads; ++i) - pthread_create(&th, NULL, thread_proc, mem + 0x1000 * i * pages_per_thread); + pthread_create(&th, NULL, thread_proc, mem + page_size * i * pages_per_thread); extra_pages = 0; for (i = 0; i < iter_count; ++i) { @@ -1559,7 +1610,7 @@ int main(int __attribute__((unused)) argc, char *argv[]) if (!hugetlb_setup_default(4)) ksft_print_msg("HugeTLB test will be skipped\n"); - ksft_set_plan(117); + ksft_set_plan(118); page_size = getpagesize(); hpage_size = read_pmd_pagesize(); @@ -1737,6 +1788,9 @@ int main(int __attribute__((unused)) argc, char *argv[]) /* 17. ZEROPFN tests */ zeropfn_tests(); + /* 18. Unpopulated pte scan-path consistency */ + unpopulated_scan_test(); + close(pagemap_fd); ksft_finished(); } diff --git a/tools/testing/selftests/net/af_unix/.gitignore b/tools/testing/selftests/net/af_unix/.gitignore index 240b26740c9e..973176644103 100644 --- a/tools/testing/selftests/net/af_unix/.gitignore +++ b/tools/testing/selftests/net/af_unix/.gitignore @@ -6,3 +6,4 @@ scm_rights so_peek_off unix_connect unix_connreset +unix_listen diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 4c0375e28bbe..57d159803a3a 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -14,6 +14,7 @@ TEST_GEN_PROGS := \ so_peek_off \ unix_connect \ unix_connreset \ + unix_listen \ # end of TEST_GEN_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/config b/tools/testing/selftests/net/af_unix/config index b5429c15a53c..41dbb03c747e 100644 --- a/tools/testing/selftests/net/af_unix/config +++ b/tools/testing/selftests/net/af_unix/config @@ -1,3 +1,4 @@ CONFIG_AF_UNIX_OOB=y CONFIG_UNIX=y CONFIG_UNIX_DIAG=m +CONFIG_USER_NS=y diff --git a/tools/testing/selftests/net/af_unix/unix_listen.c b/tools/testing/selftests/net/af_unix/unix_listen.c new file mode 100644 index 000000000000..416fa3e5bfe9 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/unix_listen.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Tests for the state checks in AF_UNIX listen(). + * + * The central case is a regression test: listen() on a bound socket that + * is already connected (i.e. not in TCP_CLOSE or TCP_LISTEN state) must + * fail with EINVAL. A prior change accidentally let it return success + * without doing anything, because a helper called in between reset the + * error code to 0. The neighbouring checks (unbound, already listening) + * are tested too so they cannot silently regress the same way. + * + * Every case runs for both listenable socket types (SOCK_STREAM and + * SOCK_SEQPACKET) and both pathname and abstract addresses. + */ +#define _GNU_SOURCE + +#include <errno.h> +#include <stddef.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> + +#include <sys/socket.h> +#include <sys/un.h> + +#include "kselftest_harness.h" + +#define SK_NAME "unix_listen_sk" +#define SRV_NAME "unix_listen_srv" + +FIXTURE(unix_listen) +{ + int sk; /* socket under test */ + int server; /* a listening peer, when a test needs one */ + struct sockaddr_un addr, srv_addr; + socklen_t addrlen, srv_addrlen; +}; + +FIXTURE_VARIANT(unix_listen) +{ + int type; + int abstract; +}; + +FIXTURE_VARIANT_ADD(unix_listen, stream_pathname) +{ + .type = SOCK_STREAM, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(unix_listen, stream_abstract) +{ + .type = SOCK_STREAM, + .abstract = 1, +}; + +FIXTURE_VARIANT_ADD(unix_listen, seqpacket_pathname) +{ + .type = SOCK_SEQPACKET, + .abstract = 0, +}; + +FIXTURE_VARIANT_ADD(unix_listen, seqpacket_abstract) +{ + .type = SOCK_SEQPACKET, + .abstract = 1, +}; + +/* Fill @addr with a pathname or abstract address named @name. */ +static socklen_t unix_set_addr(struct sockaddr_un *addr, const char *name, + int abstract) +{ + size_t len = strlen(name); + + memset(addr, 0, sizeof(*addr)); + addr->sun_family = AF_UNIX; + /* An abstract address leads with a NUL and has no filesystem entry. */ + memcpy(addr->sun_path + (abstract ? 1 : 0), name, len); + + return offsetof(struct sockaddr_un, sun_path) + len + 1; +} + +FIXTURE_SETUP(unix_listen) +{ + self->sk = -1; + self->server = -1; + self->addrlen = unix_set_addr(&self->addr, SK_NAME, variant->abstract); + self->srv_addrlen = unix_set_addr(&self->srv_addr, SRV_NAME, + variant->abstract); +} + +FIXTURE_TEARDOWN(unix_listen) +{ + if (self->sk >= 0) + close(self->sk); + if (self->server >= 0) + close(self->server); + + /* Pathname sockets leave a filesystem entry behind; abstract ones do not. */ + if (!variant->abstract) { + remove(SK_NAME); + remove(SRV_NAME); + } +} + +/* A bound socket in TCP_CLOSE is the normal, allowed case. */ +TEST_F(unix_listen, bound_is_ok) +{ + int err; + + self->sk = socket(AF_UNIX, variant->type, 0); + ASSERT_LE(0, self->sk); + + err = bind(self->sk, (struct sockaddr *)&self->addr, self->addrlen); + ASSERT_EQ(0, err); + + err = listen(self->sk, 8); + EXPECT_EQ(0, err); +} + +/* Listening again on an already-listening socket (TCP_LISTEN) is allowed. */ +TEST_F(unix_listen, relisten_is_ok) +{ + int err; + + self->sk = socket(AF_UNIX, variant->type, 0); + ASSERT_LE(0, self->sk); + + err = bind(self->sk, (struct sockaddr *)&self->addr, self->addrlen); + ASSERT_EQ(0, err); + + err = listen(self->sk, 8); + ASSERT_EQ(0, err); + + err = listen(self->sk, 16); + EXPECT_EQ(0, err); +} + +/* listen() on an unbound socket fails: there is nothing to listen on. */ +TEST_F(unix_listen, unbound_is_einval) +{ + int err; + + self->sk = socket(AF_UNIX, variant->type, 0); + ASSERT_LE(0, self->sk); + + err = listen(self->sk, 8); + EXPECT_EQ(-1, err); + EXPECT_EQ(EINVAL, errno); +} + +/* + * The regression: a bound socket that has already been connected is not in + * TCP_CLOSE or TCP_LISTEN, so listen() must reject it with EINVAL rather + * than quietly succeeding. + */ +TEST_F(unix_listen, connected_is_einval) +{ + int err; + + self->server = socket(AF_UNIX, variant->type, 0); + ASSERT_LE(0, self->server); + + err = bind(self->server, (struct sockaddr *)&self->srv_addr, + self->srv_addrlen); + ASSERT_EQ(0, err); + + err = listen(self->server, 8); + ASSERT_EQ(0, err); + + self->sk = socket(AF_UNIX, variant->type, 0); + ASSERT_LE(0, self->sk); + + /* Bind first so the unbound check does not mask the state check. */ + err = bind(self->sk, (struct sockaddr *)&self->addr, self->addrlen); + ASSERT_EQ(0, err); + + err = connect(self->sk, (struct sockaddr *)&self->srv_addr, + self->srv_addrlen); + ASSERT_EQ(0, err); + + err = listen(self->sk, 8); + EXPECT_EQ(-1, err); + EXPECT_EQ(EINVAL, errno); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/bridge_vlan_dump.sh b/tools/testing/selftests/net/bridge_vlan_dump.sh index ad66731d2a6f..90e18e2104e3 100755 --- a/tools/testing/selftests/net/bridge_vlan_dump.sh +++ b/tools/testing/selftests/net/bridge_vlan_dump.sh @@ -13,6 +13,7 @@ ALL_TESTS=" vlan_range_mcast_max_groups vlan_range_mcast_n_groups vlan_range_mcast_enabled + vlan_range_pvid " setup_prepare() @@ -191,6 +192,28 @@ vlan_range_mcast_enabled() log_test "VLAN range grouping with mcast_enabled" } +vlan_range_pvid() +{ + RET=0 + + ip -n "$NS" link set dev br0 type bridge vlan_default_pvid 1 + check_err $? "Failed to configure default PVID" + defer ip -n "$NS" link set dev br0 type bridge vlan_default_pvid 0 + + bridge -n "$NS" vlan add vid 2 dev dummy0 untagged + check_err $? "Failed to add VLAN 2" + defer bridge -n "$NS" vlan del vid 2 dev dummy0 + + bridge -n "$NS" -d vlan show dev dummy0 | + grep -Eq '(^|[[:space:]])2([[:space:]]|$)' + check_err $? "VLAN following PVID is missing from detailed dump" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "1-2" + check_fail $? "PVID was incorrectly included in a VLAN range" + + log_test "PVID is isolated from VLAN dump ranges" +} + # Verify the newest tested option is supported if ! bridge vlan help 2>&1 | grep -q "neigh_suppress"; then echo "SKIP: iproute2 too old, missing per-VLAN neighbor suppression support" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index b3827b43782b..d46d2cec89e4 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -70,12 +70,33 @@ ksft_exit_status_merge() $ksft_xfail $ksft_pass $ksft_skip $ksft_fail } +timestamp_ms() +{ + local now + local seconds + local nanoseconds + + now=$(date -u +%s:%N) || return + seconds=${now%:*} + nanoseconds=${now#*:} + + if [[ $nanoseconds =~ ^[0-9]+$ ]]; then + nanoseconds=${nanoseconds:0:9} + else + nanoseconds=0 + fi + + echo $((seconds * 1000 + 10#$nanoseconds / 1000000)) +} + loopy_wait() { local sleep_cmd=$1; shift local timeout_ms=$1; shift + local start_time + local current_time - local start_time="$(date -u +%s%3N)" + start_time=$(timestamp_ms) || return while true do local out @@ -84,7 +105,7 @@ loopy_wait() return 0 fi - local current_time="$(date -u +%s%3N)" + current_time=$(timestamp_ms) || return if ((current_time - start_time > timeout_ms)); then echo -n "$out" return 1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index c0aeffd5cb71..7dc91fac4917 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -584,7 +584,7 @@ check_transfer() mv "$tmpfile" "$out" tmpfile="" fi - cmp -l "$in" "$out" | while read -r i a b; do + while read -r i a b; do local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then fail_test "$what does not match (in, out):" @@ -595,7 +595,7 @@ check_transfer() else print_info "$what has inverted byte at ${i}" fi - done + done < <(cmp -l "$in" "$out") return 0 } diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index e9ae1806ab07..30a809752d1b 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -212,7 +212,7 @@ make_connection() ./mptcp_connect -s MPTCP -w 300 -p $app_port -l $listen_addr > /dev/null 2>&1 & local server_pid=$! - mptcp_lib_wait_local_port_listen "${ns1}" "${port}" + mptcp_lib_wait_local_port_listen "${ns1}" "${app_port}" # Run the client, transfer $file and stay connected to the server # to conduct tests diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index 08ad07500e8a..449c518bd947 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -617,7 +617,11 @@ ip -6 -net "$nsr2" route add default via fee1:3::1 ip -net "$ns2" route add default via 10.0.2.1 ip -6 -net "$ns2" route add default via dead:2::1 +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif tun0 tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun0 accept' +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif tun6 tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun6 accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward \ 'meta oif "veth0" tcp sport 12345 ct mark set 1 flow add @f1 counter name routed_repl accept' @@ -629,7 +633,7 @@ if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "IPIP tunnel"; then fi if test_tcp_forwarding "$ns1" "$ns2" 1 6 "[dead:2::99]" 12345; then - echo "PASS: flow offload for ns1/ns2 IP6IP6 tunnel" + check_counters "flow offload for ns1/ns2 IP6IP6 tunnel" else echo "FAIL: flow offload for ns1/ns2 with IP6IP6 tunnel" 1>&2 ip netns exec "$nsr1" nft list ruleset @@ -642,6 +646,8 @@ ip -net "$nsr1" link set veth1.10 up ip -net "$nsr1" addr add 192.168.20.1/24 dev veth1.10 ip -net "$nsr1" addr add fee1:4::1/64 dev veth1.10 nodad ip netns exec "$nsr1" sysctl net.ipv4.conf.veth1/10.forwarding=1 > /dev/null +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif veth1.10 tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif veth1.10 accept' ip -net "$nsr1" link add name tun0.10 type ipip local 192.168.20.1 remote 192.168.20.2 @@ -649,6 +655,8 @@ ip -net "$nsr1" link set tun0.10 up ip -net "$nsr1" addr add 192.168.200.1/24 dev tun0.10 ip -net "$nsr1" route change default via 192.168.200.2 ip netns exec "$nsr1" sysctl net.ipv4.conf.tun0/10.forwarding=1 > /dev/null +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif tun0.10 tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun0.10 accept' ip -net "$nsr1" link add name tun6.10 type ip6tnl local fee1:4::1 remote fee1:4::2 encaplimit none @@ -656,6 +664,8 @@ ip -net "$nsr1" link set tun6.10 up ip -net "$nsr1" addr add fee1:5::1/64 dev tun6.10 nodad ip -6 -net "$nsr1" route delete default ip -6 -net "$nsr1" route add default via fee1:5::2 +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif tun6.10 tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun6.10 accept' ip -net "$nsr2" link add link veth0 name veth0.10 type vlan id 10 @@ -683,7 +693,7 @@ if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "IPIP tunnel over vlan"; then fi if test_tcp_forwarding "$ns1" "$ns2" 1 6 "[dead:2::99]" 12345; then - echo "PASS: flow offload for ns1/ns2 IP6IP6 tunnel over vlan" + check_counters "flow offload for ns1/ns2 IP6IP6 tunnel over vlan" else echo "FAIL: flow offload for ns1/ns2 with IP6IP6 tunnel over vlan" 1>&2 ip netns exec "$nsr1" nft list ruleset @@ -736,6 +746,61 @@ if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "on bridge"; then ret=1 fi +if ip -net "$nsr1" link show tun0 > /dev/null 2>&1 && + ip -net "$nsr2" link show tun0 > /dev/null 2>&1; then + ip -net "$nsr1" route change default via 192.168.100.2 + ip -net "$nsr2" route change default via 192.168.100.1 + ip -6 -net "$nsr1" route delete default + ip -6 -net "$nsr1" route add default via fee1:3::2 + ip -6 -net "$nsr2" route delete default + ip -6 -net "$nsr2" route add default via fee1:3::1 + ip -net "$ns2" route add default via 10.0.2.1 + ip -6 -net "$ns2" route add default via dead:2::1 + + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "tun0" tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "tun6" tcp dport 12345 ct mark set 1 flow add @f1 counter name routed_orig accept' + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "veth0" tcp sport 12345 ct mark set 1 flow add @f1 counter name routed_repl accept' + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "br0" tcp sport 12345 ct mark set 1 flow add @f1 counter name routed_repl accept' + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "tun0" accept' + ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "tun6" accept' + + ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null + + if test_tcp_forwarding "$ns1" "$ns2" 1 4 10.0.2.99 12345; then + check_counters "bridge + IPIP tunnel" + else + echo "FAIL: flow offload for ns1/ns2 with bridge + IPIP tunnel" 1>&2 + ip netns exec "$nsr1" nft list ruleset + ret=1 + fi + + if test_tcp_forwarding "$ns1" "$ns2" 1 6 "[dead:2::99]" 12345; then + check_counters "bridge + IP6IP6 tunnel" + else + echo "FAIL: flow offload for ns1/ns2 with bridge + IP6IP6 tunnel" 1>&2 + ip netns exec "$nsr1" nft list ruleset + ret=1 + fi + + ip -net "$nsr1" route change default via 192.168.10.2 + ip -net "$nsr2" route change default via 192.168.10.1 + ip -net "$ns2" route del default via 10.0.2.1 + ip -6 -net "$nsr1" route delete default + ip -6 -net "$nsr1" route add default via fee1:2::2 + ip -6 -net "$nsr2" route delete default + ip -6 -net "$nsr2" route add default via fee1:2::1 + ip -6 -net "$ns2" route del default via dead:2::1 +else + echo "SKIP: bridge + tunnel flowtable regression (tun0 missing)" + [ "$ret" -eq 0 ] && ret=$ksft_skip +fi + # Another test: # Add bridge interface br0 to Router1, with NAT and VLAN. diff --git a/tools/testing/selftests/net/openvswitch/config b/tools/testing/selftests/net/openvswitch/config new file mode 100644 index 000000000000..c659749cd086 --- /dev/null +++ b/tools/testing/selftests/net/openvswitch/config @@ -0,0 +1,16 @@ +CONFIG_GENEVE=m +CONFIG_INET_DIAG=y +CONFIG_IPV6=y +CONFIG_NETFILTER=y +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_OVS=y +CONFIG_OPENVSWITCH=m +CONFIG_OPENVSWITCH_GENEVE=m +CONFIG_OPENVSWITCH_GRE=m +CONFIG_OPENVSWITCH_VXLAN=m +CONFIG_PSAMPLE=m +CONFIG_VETH=y +CONFIG_VLAN_8021Q=y +CONFIG_VXLAN=m diff --git a/tools/testing/selftests/net/ovpn/config b/tools/testing/selftests/net/ovpn/config index d6cf033d555e..6b424762e46e 100644 --- a/tools/testing/selftests/net/ovpn/config +++ b/tools/testing/selftests/net/ovpn/config @@ -4,6 +4,7 @@ CONFIG_CRYPTO_CHACHA20POLY1305=y CONFIG_CRYPTO_GCM=y CONFIG_DST_CACHE=y CONFIG_INET=y +CONFIG_IPV6=y CONFIG_NET=y CONFIG_NETFILTER=y CONFIG_NET_UDP_TUNNEL=y @@ -11,3 +12,4 @@ CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y CONFIG_OVPN=m CONFIG_STREAM_PARSER=y +CONFIG_VETH=y diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c index d40953375c86..f4effa7580c0 100644 --- a/tools/testing/selftests/net/ovpn/ovpn-cli.c +++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c @@ -1785,7 +1785,7 @@ static int ovpn_parse_remote(struct ovpn_ctx *ovpn, const char *host, const char *service, const char *vpnip) { int ret; - struct addrinfo *result; + struct addrinfo *result = NULL; struct addrinfo hints = { .ai_family = ovpn->sa_family, .ai_socktype = SOCK_DGRAM, @@ -1809,6 +1809,8 @@ static int ovpn_parse_remote(struct ovpn_ctx *ovpn, const char *host, } memcpy(&ovpn->remote, result->ai_addr, result->ai_addrlen); + freeaddrinfo(result); + result = NULL; } if (vpnip) { diff --git a/tools/testing/selftests/net/ovpn/settings b/tools/testing/selftests/net/ovpn/settings new file mode 100644 index 000000000000..ba4d85f74cd6 --- /dev/null +++ b/tools/testing/selftests/net/ovpn/settings @@ -0,0 +1 @@ +timeout=90 diff --git a/tools/testing/selftests/net/packetdrill/tcp_rfc5961_rst-syn-recv.pkt b/tools/testing/selftests/net/packetdrill/tcp_rfc5961_rst-syn-recv.pkt new file mode 100644 index 000000000000..3fc2de03658a --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rfc5961_rst-syn-recv.pkt @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// RFC 9293 Section 3.10.7.4: in SYN-RECEIVED, an exact RST resets +// the connection. A non-exact in-window RST elicits a challenge ACK, +// while an out-of-window RST is silently discarded. + +`./defaults.sh` + +// An exact RST removes the request socket. + 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 < S 0:0(0) win 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R 1:1(0) win 1000 + +.1 < . 1:1(0) ack 1 win 1000 + +0 > R 1:1(0) + +0 close(3) = 0 + +// A non-exact in-window RST gets a challenge ACK and the request survives. + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 < S 0:0(0) win 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R 2:2(0) win 1000 + +0 > . 1:1(0) ack 1 + +0 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 close(4) = 0 + +0 close(3) = 0 + +// RST sequence validation precedes ACK validation. Even an RST|ACK +// with an unacceptable ACK value gets a challenge ACK. + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 < S 0:0(0) win 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R. 2:2(0) ack 100 win 1000 + +0 > . 1:1(0) ack 1 + +0 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 close(4) = 0 + +0 close(3) = 0 + +// An out-of-window RST is silent and does not remove the request. + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 < S 0:0(0) win 1000 <mss 1000,sackOK,nop,nop,nop,wscale 0> + +0 > S. 0:0(0) ack 1 <...> + +0 < R 100001:100001(0) win 1000 + +.1 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 close(4) = 0 + +0 close(3) = 0 diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 4fcce5150850..2544ae35d07a 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -313,6 +313,8 @@ end: tcp_info_get_rcv_mss(fd)); } error: + if (ctx) + EVP_MD_CTX_free(ctx); munmap(buffer, buffer_sz); close(fd); if (zflg) @@ -606,6 +608,8 @@ int main(int argc, char *argv[]) EVP_DigestFinal_ex(ctx, digest, &digest_len); send(fd, digest, (size_t)SHA256_DIGEST_LENGTH, 0); } + if (ctx) + EVP_MD_CTX_free(ctx); close(fd); munmap(buffer, buffer_sz); return 0; diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index cbdd3ea28b99..9d3cd4fff062 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -24,6 +24,7 @@ #include "kselftest_harness.h" #define TLS_PAYLOAD_MAX_LEN 16384 +#define TLS_HDR_LEN 5 #define SOL_TLS 282 static int fips_enabled; @@ -835,6 +836,43 @@ TEST_F(tls, send_and_splice) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_onto_full_record) +{ + char mem_send[4608]; + char mem_recv[4608]; + int frag_len = 100; + int nfrags, i, off; + int p[2]; + + memrnd(mem_send, sizeof(mem_send)); + ASSERT_GE(pipe(p), 0); + + for (nfrags = 16; nfrags <= 44; nfrags++) { + for (i = 0, off = 0; i < nfrags; i++, off += frag_len) { + EXPECT_EQ(write(p[1], mem_send + off, frag_len), frag_len); + EXPECT_EQ(splice(p[0], NULL, self->fd, NULL, frag_len, + SPLICE_F_MORE), frag_len); + } + + EXPECT_EQ(send(self->fd, mem_send + off, 1, MSG_MORE), 1); + off++; + + EXPECT_EQ(write(p[1], mem_send + off, frag_len), frag_len); + EXPECT_EQ(splice(p[0], NULL, self->fd, NULL, frag_len, + SPLICE_F_MORE), frag_len); + off += frag_len; + + EXPECT_EQ(send(self->fd, mem_send + off, 1, 0), 1); + off++; + + EXPECT_EQ(recv(self->cfd, mem_recv, off, MSG_WAITALL), off); + EXPECT_EQ(memcmp(mem_send, mem_recv, off), 0); + } + + close(p[0]); + close(p[1]); +} + TEST_F(tls, splice_to_pipe) { int send_len = TLS_PAYLOAD_MAX_LEN; @@ -1802,6 +1840,63 @@ TEST_F(tls, recv_efault) } #define TLS_RECORD_TYPE_HANDSHAKE 0x16 + +TEST_F(tls_basic, recvmsg_nopad_retry_iov) +{ + char payload[32]; + char first_iov[sizeof(payload)]; + char later_iov[sizeof(payload) * 2]; + char expected_later_iov[sizeof(later_iov)]; + char cbuf[CMSG_SPACE(sizeof(char))]; + struct tls_crypto_info_keys tls13; + struct iovec iov[] = { + { .iov_base = first_iov, .iov_len = sizeof(first_iov) }, + { .iov_base = later_iov, .iov_len = sizeof(later_iov) }, + }; + struct msghdr msg = { + .msg_iov = iov, + .msg_iovlen = ARRAY_SIZE(iov), + .msg_control = cbuf, + .msg_controllen = sizeof(cbuf), + }; + int one = 1; + int ret; + int i; + + if (self->notls) + SKIP(return, "no TLS support"); + + tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128, + &tls13, 0); + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls13, tls13.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls13, tls13.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX_EXPECT_NO_PAD, + &one, sizeof(one)); + ASSERT_EQ(ret, 0); + + for (i = 0; i < sizeof(payload); i++) + payload[i] = 0x40 + i; + memset(first_iov, 0xa5, sizeof(first_iov)); + memset(later_iov, 0x5a, sizeof(later_iov)); + memset(expected_later_iov, 0x5a, sizeof(expected_later_iov)); + + /* A control record forces optimistic TLS 1.3 RX to retry. */ + ret = tls_send_cmsg(self->fd, TLS_RECORD_TYPE_HANDSHAKE, + payload, sizeof(payload), 0); + ASSERT_EQ(ret, sizeof(payload)); + + ret = recvmsg(self->cfd, &msg, 0); + ASSERT_EQ(ret, sizeof(payload)); + EXPECT_EQ(memcmp(first_iov, payload, sizeof(payload)), 0); + EXPECT_EQ(memcmp(later_iov, expected_later_iov, + sizeof(later_iov)), 0); +} + /* key_update, length 1, update_not_requested */ static const char key_update_msg[] = "\x18\x00\x00\x01\x00"; static void tls_send_keyupdate(struct __test_metadata *_metadata, int fd) @@ -2638,28 +2733,83 @@ TEST_F(tls_err, bad_rec) EXPECT_EQ(errno, EAGAIN); } +/* cfd carries a byte stream, so one recv() can return part of a + * record. Take the fragment length from the record header and wait + * for the remainder. + */ +static void tls_send_bad_auth(struct __test_metadata *_metadata, + int fd, int cfd, int fd2) +{ + char buf[128]; + int len; + + memrnd(buf, sizeof(buf) / 2); + ASSERT_EQ(send(fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2); + + ASSERT_EQ(recv(cfd, buf, TLS_HDR_LEN, MSG_WAITALL), TLS_HDR_LEN); + + len = ((unsigned char)buf[3] << 8) | (unsigned char)buf[4]; + ASSERT_GT(len, 0); + ASSERT_LE(len, (int)sizeof(buf) - TLS_HDR_LEN); + + ASSERT_EQ(recv(cfd, buf + TLS_HDR_LEN, len, MSG_WAITALL), len); + + buf[TLS_HDR_LEN + len - 1]++; + + ASSERT_EQ(send(fd2, buf, TLS_HDR_LEN + len, 0), TLS_HDR_LEN + len); +} + TEST_F(tls_err, bad_auth) { char buf[128]; - int n; if (self->notls) SKIP(return, "no TLS support"); - memrnd(buf, sizeof(buf) / 2); - EXPECT_EQ(send(self->fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2); - n = recv(self->cfd, buf, sizeof(buf), 0); - EXPECT_GT(n, sizeof(buf) / 2); - - buf[n - 1]++; + tls_send_bad_auth(_metadata, self->fd, self->cfd, self->fd2); - EXPECT_EQ(send(self->fd2, buf, n, 0), n); EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); EXPECT_EQ(errno, EBADMSG); EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); EXPECT_EQ(errno, EBADMSG); } +/* A record that did not authenticate breaks the connection for every + * reader, splice included. + * + * The two decrypt paths reach that result differently. A synchronous + * decrypt leaves the record parsed, so the splice re-runs the decrypt + * and fails on the record itself; the ctx->async_wait.err check in + * tls_sw_splice_read() is not what stops it. Only an asynchronous + * decrypt, which needs a TLS 1.2 socket and an AEAD advertising + * CRYPTO_ALG_ASYNC, consumes the record before the failure is + * recorded, leaving that check the sole reason the splice fails. + */ +TEST_F(tls_err, bad_auth_splice) +{ + char buf[128]; + ssize_t ret; + int p[2]; + + if (self->notls) + SKIP(return, "no TLS support"); + + tls_send_bad_auth(_metadata, self->fd, self->cfd, self->fd2); + + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + + ASSERT_GE(pipe(p), 0); + + ret = splice(self->cfd2, NULL, p[1], NULL, sizeof(buf), + SPLICE_F_NONBLOCK); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, EBADMSG); + + close(p[0]); + close(p[1]); +} + TEST_F(tls_err, bad_in_large_read) { char txt[3][64]; @@ -2915,7 +3065,6 @@ static size_t parse_tls_records(struct __test_metadata *_metadata, { const __u8 *rec = rx_buf; size_t total_plaintext_rx = 0; - const __u8 rec_header_len = 5; while (rec < rx_buf + rx_len) { __u16 record_payload_len; @@ -2935,7 +3084,7 @@ static size_t parse_tls_records(struct __test_metadata *_metadata, /* Plaintext must not exceed the specified limit */ ASSERT_LE(plaintext_len, max_payload_len); - rec += rec_header_len + record_payload_len; + rec += TLS_HDR_LEN + record_payload_len; } return total_plaintext_rx; diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c index cf106a49b55e..abe488bac50b 100644 --- a/tools/testing/selftests/net/tun.c +++ b/tools/testing/selftests/net/tun.c @@ -42,19 +42,19 @@ static struct in_addr param_ipaddr4_inner_src = { }; static struct in6_addr param_ipaddr6_outer_dst = { - { { 0x20, 0x02, 0x0d, 0xb8, 0x01, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1 } }, + { { 0xfd, 0x00, 0x0d, 0xb8, 0x01, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1 } }, }; static struct in6_addr param_ipaddr6_outer_src = { - { { 0x20, 0x02, 0x0d, 0xb8, 0x01, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2 } }, + { { 0xfd, 0x00, 0x0d, 0xb8, 0x01, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2 } }, }; static struct in6_addr param_ipaddr6_inner_dst = { - { { 0x20, 0x02, 0x0d, 0xb8, 0x02, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1 } }, + { { 0xfd, 0x00, 0x0d, 0xb8, 0x02, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1 } }, }; static struct in6_addr param_ipaddr6_inner_src = { - { { 0x20, 0x02, 0x0d, 0xb8, 0x02, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2 } }, + { { 0xfd, 0x00, 0x0d, 0xb8, 0x02, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2 } }, }; #ifndef BIT diff --git a/tools/testing/selftests/pidfd/pidfd_file_handle_test.c b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c index 68918734dcf3..1e03ae9575fe 100644 --- a/tools/testing/selftests/pidfd/pidfd_file_handle_test.c +++ b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c @@ -373,6 +373,7 @@ TEST_F(file_handle, open_by_handle_at_valid_flags) O_CLOEXEC | O_EXCL); ASSERT_GE(pidfd, 0); + ASSERT_NE(fcntl(pidfd, F_GETFL) & PIDFD_THREAD, 0); ASSERT_EQ(fstat(pidfd, &st2), 0); ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino); diff --git a/tools/testing/selftests/riscv/vector/validate_v_ptrace.c b/tools/testing/selftests/riscv/vector/validate_v_ptrace.c index 74b6f6bcf067..a388b7963d47 100644 --- a/tools/testing/selftests/riscv/vector/validate_v_ptrace.c +++ b/tools/testing/selftests/riscv/vector/validate_v_ptrace.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include <sys/ptrace.h> +#include <sys/syscall.h> #include <sys/types.h> #include <sys/wait.h> #include <sys/uio.h> @@ -25,9 +26,9 @@ TEST(ptrace_v_not_enabled) SKIP(return, "Vector not supported"); chld_lock = 1; - pid = fork(); + pid = (pid_t)syscall(SYS_clone, SIGCHLD, 0, NULL, 0, NULL); ASSERT_LE(0, pid) - TH_LOG("fork: %m"); + TH_LOG("clone: %m"); if (pid == 0) { while (chld_lock == 1) @@ -74,7 +75,7 @@ TEST(ptrace_v_not_enabled) ASSERT_EQ(-1, ret); /* cleanup */ - + free(regset_data); ASSERT_EQ(0, kill(pid, SIGKILL)); } } @@ -206,7 +207,7 @@ TEST(ptrace_v_early_debug) EXPECT_EQ(vl_csr, regset_data->vl); /* cleanup */ - + free(regset_data); ASSERT_EQ(0, kill(pid, SIGKILL)); } } @@ -330,7 +331,7 @@ TEST(ptrace_v_syscall_clobbering) EXPECT_EQ(0UL, regset_data->vl); /* cleanup */ - + free(regset_data); ASSERT_EQ(0, kill(pid, SIGKILL)); } } @@ -648,7 +649,7 @@ TEST_F(v_csr_invalid, ptrace_v_invalid_values) ASSERT_EQ(ret, -1); /* cleanup */ - + free(regset_data); ASSERT_EQ(0, kill(pid, SIGKILL)); } } @@ -910,7 +911,7 @@ TEST_F(v_csr_valid, ptrace_v_valid_values) EXPECT_EQ(regset_data->vlenb, vlenb); /* cleanup */ - + free(regset_data); ASSERT_EQ(0, kill(pid, SIGKILL)); } } diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 50d69e22ee7a..aba6317f6cb8 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -5,9 +5,13 @@ CLANG_FLAGS += -no-integrated-as endif top_srcdir = ../../../.. +include $(top_srcdir)/scripts/subarch.include +ARCH ?= $(SUBARCH) +LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include CFLAGS += -O2 -Wall -g -I./ $(KHDR_INCLUDES) -L$(OUTPUT) -Wl,-rpath=./ \ - $(CLANG_FLAGS) -I$(top_srcdir)/tools/include + $(CLANG_FLAGS) -I$(top_srcdir)/tools/include \ + -I$(LINUX_TOOL_ARCH_INCLUDE) LDLIBS += -lpthread -ldl # Own dependencies because we only want to build against 1st prerequisite, but diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 5d2dffca0e91..3cfe90e0f34f 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -176,6 +176,7 @@ auto-test-targets := \ maybe_null \ minimal \ non_scx_kfunc_deny \ + nohz_tick \ numa \ allowed_cpus \ peek_dsq \ diff --git a/tools/testing/selftests/sched_ext/nohz_tick.bpf.c b/tools/testing/selftests/sched_ext/nohz_tick.bpf.c new file mode 100644 index 000000000000..6998c5dd6bcb --- /dev/null +++ b/tools/testing/selftests/sched_ext/nohz_tick.bpf.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES + * + * Exercise tick dependency transitions between infinite and finite slices. + */ +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +const volatile s32 test_cpu; +bool finite_phase; +u64 nr_inf_running; +u64 nr_finite_running; +u64 nr_finite_ticks; + +UEI_DEFINE(uei); + +s32 BPF_STRUCT_OPS(nohz_tick_select_cpu, struct task_struct *p, s32 prev_cpu, + u64 wake_flags) +{ + return prev_cpu; +} + +void BPF_STRUCT_OPS(nohz_tick_enqueue, struct task_struct *p, u64 enq_flags) +{ + u64 slice = finite_phase ? 1000000ULL : SCX_SLICE_INF; + + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, slice, enq_flags); + if (enq_flags & SCX_ENQ_LAST) + scx_bpf_kick_cpu(test_cpu, SCX_KICK_IDLE); +} + +void BPF_STRUCT_OPS(nohz_tick_running, struct task_struct *p) +{ + if (bpf_get_smp_processor_id() != test_cpu) + return; + + if (finite_phase) + __sync_fetch_and_add(&nr_finite_running, 1); + else + __sync_fetch_and_add(&nr_inf_running, 1); +} + +void BPF_STRUCT_OPS(nohz_tick_tick, struct task_struct *p) +{ + if (bpf_get_smp_processor_id() == test_cpu && finite_phase) + __sync_fetch_and_add(&nr_finite_ticks, 1); +} + +void BPF_STRUCT_OPS(nohz_tick_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops nohz_tick_ops = { + .select_cpu = (void *)nohz_tick_select_cpu, + .enqueue = (void *)nohz_tick_enqueue, + .running = (void *)nohz_tick_running, + .tick = (void *)nohz_tick_tick, + .exit = (void *)nohz_tick_exit, + .name = "nohz_tick", + .timeout_ms = 1000U, +}; diff --git a/tools/testing/selftests/sched_ext/nohz_tick.c b/tools/testing/selftests/sched_ext/nohz_tick.c new file mode 100644 index 000000000000..028f54391c2c --- /dev/null +++ b/tools/testing/selftests/sched_ext/nohz_tick.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES + * + * Validate that a finite-slice EXT task restarts the scheduler tick when it + * follows an infinite-slice EXT task and an idle interval on a NOHZ_FULL CPU. + */ +#define _GNU_SOURCE + +#include <bpf/bpf.h> +#include <errno.h> +#include <sched.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/prctl.h> +#include <sys/wait.h> +#include <unistd.h> + +#include <scx/common.h> + +#include "nohz_tick.bpf.skel.h" +#include "scx_test.h" + +#ifndef SCHED_EXT +#define SCHED_EXT 7 +#endif + +#define MIN_FINITE_TICKS 3 +#define PHASE_TIMEOUT_MS 1000 + +struct nohz_tick_ctx { + struct nohz_tick *skel; + cpu_set_t original_mask; + int test_cpu; +}; + +static int first_allowed_cpu(const cpu_set_t *mask, int first, int last) +{ + int cpu; + + for (cpu = first; cpu <= last && cpu < CPU_SETSIZE; cpu++) + if (CPU_ISSET(cpu, mask)) + return cpu; + + return -1; +} + +static int find_nohz_full_cpu(const cpu_set_t *allowed) +{ + char buf[4096], *cur, *end; + FILE *file; + + file = fopen("/sys/devices/system/cpu/nohz_full", "r"); + if (!file) + return -1; + if (!fgets(buf, sizeof(buf), file)) { + fclose(file); + return -1; + } + fclose(file); + + cur = buf; + while (*cur) { + long first, last; + int cpu; + + while (*cur == ' ' || *cur == '\t' || *cur == ',') + cur++; + if (*cur < '0' || *cur > '9') + break; + + errno = 0; + first = strtol(cur, &end, 10); + if (errno || end == cur || first < 0 || first >= CPU_SETSIZE) + return -1; + cur = end; + last = first; + if (*cur == '-') { + cur++; + errno = 0; + last = strtol(cur, &end, 10); + if (errno || end == cur || last < first) + return -1; + cur = end; + } + + cpu = first_allowed_cpu(allowed, first, last); + if (cpu >= 0) + return cpu; + } + + return -1; +} + +static pid_t start_worker(int cpu) +{ + struct sched_param param = {}; + cpu_set_t mask; + pid_t parent; + pid_t pid; + + parent = getpid(); + pid = fork(); + if (pid != 0) + return pid; + if (prctl(PR_SET_PDEATHSIG, SIGKILL) || getppid() != parent) + _exit(1); + + /* + * Become EXT before touching the target so it stays idle until wakeup. + */ + if (sched_setscheduler(0, SCHED_EXT, ¶m)) + _exit(1); + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask)) + _exit(1); + + for (;;) + asm volatile("" ::: "memory"); +} + +static void stop_worker(pid_t pid) +{ + if (pid <= 0) + return; + + kill(pid, SIGKILL); + waitpid(pid, NULL, 0); +} + +static int pause_worker(pid_t pid) +{ + int status; + + if (kill(pid, SIGSTOP)) + return -errno; + if (waitpid(pid, &status, WUNTRACED) != pid) + return -errno; + if (!WIFSTOPPED(status)) + return -ECHILD; + + return 0; +} + +static bool wait_for_counter(const u64 *counter, u64 value, int timeout_ms) +{ + int elapsed; + + for (elapsed = 0; elapsed < timeout_ms; elapsed++) { + if (__atomic_load_n(counter, __ATOMIC_RELAXED) >= value) + return true; + usleep(1000); + } + + return false; +} + +static enum scx_test_status setup(void **ctx_ptr) +{ + struct nohz_tick_ctx *ctx; + cpu_set_t controller_mask; + int cpu; + + ctx = calloc(1, sizeof(*ctx)); + SCX_FAIL_IF(!ctx, "Failed to allocate context"); + if (sched_getaffinity(0, sizeof(ctx->original_mask), + &ctx->original_mask)) { + free(ctx); + SCX_FAIL("Failed to get affinity (%d)", errno); + } + + cpu = find_nohz_full_cpu(&ctx->original_mask); + if (cpu < 0) { + fprintf(stderr, "SKIP: no allowed NOHZ_FULL CPU\n"); + free(ctx); + return SCX_TEST_SKIP; + } + + controller_mask = ctx->original_mask; + CPU_CLR(cpu, &controller_mask); + if (CPU_COUNT(&controller_mask) == 0) { + fprintf(stderr, "SKIP: no housekeeping CPU available\n"); + free(ctx); + return SCX_TEST_SKIP; + } + + ctx->test_cpu = cpu; + ctx->skel = nohz_tick__open(); + if (!ctx->skel) { + free(ctx); + SCX_FAIL("Failed to open skeleton"); + } + + SCX_ENUM_INIT(ctx->skel); + ctx->skel->rodata->test_cpu = cpu; + ctx->skel->struct_ops.nohz_tick_ops->flags |= SCX_OPS_SWITCH_PARTIAL | + SCX_OPS_ENQ_LAST; + if (nohz_tick__load(ctx->skel)) { + nohz_tick__destroy(ctx->skel); + free(ctx); + SCX_FAIL("Failed to load skeleton"); + } + + if (sched_setaffinity(0, sizeof(controller_mask), &controller_mask)) { + nohz_tick__destroy(ctx->skel); + free(ctx); + SCX_FAIL("Failed to move controller off CPU %d (%d)", cpu, errno); + } + + *ctx_ptr = ctx; + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx_ptr) +{ + struct nohz_tick_ctx *ctx = ctx_ptr; + struct nohz_tick *skel = ctx->skel; + struct bpf_link *link = NULL; + enum scx_test_status status = SCX_TEST_FAIL; + pid_t finite_worker = -1; + pid_t inf_worker = -1; + u64 finite_running; + u64 finite_ticks; + int ret; + + link = bpf_map__attach_struct_ops(skel->maps.nohz_tick_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + goto out; + } + + /* + * Establish SCX_RQ_CAN_STOP_TICK with an infinite-slice task. + */ + inf_worker = start_worker(ctx->test_cpu); + if (inf_worker < 0) { + SCX_ERR("Failed to start infinite-slice worker (%d)", errno); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_inf_running, 1, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Infinite-slice worker was not scheduled"); + goto out; + } + + /* Block without exiting so the rq retains the infinite-slice state. */ + ret = pause_worker(inf_worker); + if (ret) { + SCX_ERR("Failed to stop infinite-slice worker (%d)", ret); + goto out; + } + + /* Let the target enter idle with its tick stopped. */ + usleep(100000); + + /* + * The next EXT task receives a finite slice and must restart the tick. + */ + __atomic_store_n(&skel->bss->finite_phase, true, __ATOMIC_RELEASE); + finite_worker = start_worker(ctx->test_cpu); + if (finite_worker < 0) { + SCX_ERR("Failed to start finite-slice worker (%d)", errno); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_running, 1, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Finite-slice worker was not scheduled"); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_ticks, MIN_FINITE_TICKS, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Finite-slice worker received only %llu scheduler ticks", + (unsigned long long)skel->bss->nr_finite_ticks); + goto out; + } + stop_worker(finite_worker); + finite_worker = -1; + + /* + * Leave the CPU idle after a finite-slice task. The next finite-slice + * task must restart the tick even though the slice type is unchanged. + */ + usleep(100000); + finite_running = __atomic_load_n(&skel->bss->nr_finite_running, + __ATOMIC_RELAXED); + finite_ticks = __atomic_load_n(&skel->bss->nr_finite_ticks, + __ATOMIC_RELAXED); + + finite_worker = start_worker(ctx->test_cpu); + if (finite_worker < 0) { + SCX_ERR("Failed to start second finite-slice worker (%d)", errno); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_running, + finite_running + 1, PHASE_TIMEOUT_MS)) { + SCX_ERR("Second finite-slice worker was not scheduled"); + goto out; + } + if (!wait_for_counter(&skel->bss->nr_finite_ticks, + finite_ticks + MIN_FINITE_TICKS, + PHASE_TIMEOUT_MS)) { + SCX_ERR("Second finite-slice worker received only %llu scheduler ticks", + (unsigned long long)(skel->bss->nr_finite_ticks - + finite_ticks)); + goto out; + } + + if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) { + SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)", + (unsigned long long)skel->data->uei.kind, + (long long)skel->data->uei.exit_code); + goto out; + } + + fprintf(stderr, "CPU %d received %llu finite-slice ticks\n", + ctx->test_cpu, + (unsigned long long)skel->bss->nr_finite_ticks); + status = SCX_TEST_PASS; +out: + stop_worker(finite_worker); + stop_worker(inf_worker); + if (link) + bpf_link__destroy(link); + return status; +} + +static void cleanup(void *ctx_ptr) +{ + struct nohz_tick_ctx *ctx = ctx_ptr; + + sched_setaffinity(0, sizeof(ctx->original_mask), &ctx->original_mask); + nohz_tick__destroy(ctx->skel); + free(ctx); +} + +struct scx_test nohz_tick = { + .name = "nohz_tick", + .description = "Verify finite EXT slices restart the NOHZ_FULL tick", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&nohz_tick) diff --git a/tools/testing/selftests/sched_ext/numa.bpf.c b/tools/testing/selftests/sched_ext/numa.bpf.c index 78cc49a7f9a6..6b4515c28aa0 100644 --- a/tools/testing/selftests/sched_ext/numa.bpf.c +++ b/tools/testing/selftests/sched_ext/numa.bpf.c @@ -34,7 +34,8 @@ static bool is_cpu_idle(s32 cpu, int node) s32 BPF_STRUCT_OPS(numa_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { - int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p)); + s32 task_cpu = scx_bpf_task_cpu(p); + int node = __COMPAT_scx_bpf_cpu_node(task_cpu); s32 cpu; /* @@ -48,6 +49,16 @@ s32 BPF_STRUCT_OPS(numa_select_cpu, cpu = __COMPAT_scx_bpf_pick_any_cpu_node(p->cpus_ptr, node, __COMPAT_SCX_PICK_IDLE_IN_NODE); + /* + * @task_cpu may be outside of p->cpus_ptr if @p's affinity + * changed while it was sleeping. This means it's possible for + * p->cpus_ptr to not include any CPUs from @node. + * If we failed to find a cpu in @node, check if @task_cpu + * is outside of p->cpus_ptr and just return @prev_cpu if it is. + */ + if (cpu < 0 && !bpf_cpumask_test_cpu(task_cpu, p->cpus_ptr)) + return prev_cpu; + if (is_cpu_idle(cpu, node)) scx_bpf_error("CPU %d should be marked as busy", cpu); diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 358b6c65e120..0622bc2acad4 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -5178,7 +5178,8 @@ FIXTURE_SETUP(UPROBE) ASSERT_GE(bit, 0); } - offset = get_uprobe_offset(variant->uretprobe ? probed_uretprobe : probed_uprobe); + offset = get_uprobe_offset(variant->uretprobe ? (void *)probed_uretprobe + : (void *)probed_uprobe); ASSERT_GE(offset, 0); if (variant->uretprobe) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json index da65f838bd52..8ab48def89b6 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json @@ -702,5 +702,45 @@ "$TC qdisc del dev $DUMMY clsact", "$TC qdisc del dev $DUMMY root handle 1:" ] + }, + { + "id": "c7a3", + "name": "Verify act_ct drops a packet whose header checks fail", + "category": [ + "actions", + "ct", + "scapy" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + [ + "$TC qdisc del dev $DEV1 clsact", + 0, + 1, + 2, + 255 + ], + "$TC qdisc add dev $DEV1 clsact" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress protocol all prio 1 matchall action ct", + "scapy": [ + { + "iface": "$DEV0", + "count": 10, + "packet": "Ether(type=0x86dd)/IPv6(nh=0, plen=0, src='::1', dst='::2')" + } + ], + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DEV1 clsact", + "matchPattern": "dropped 10", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/depth.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/depth.json new file mode 100644 index 000000000000..48f8683f0d1a --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/depth.json @@ -0,0 +1,74 @@ +[ + { + "id": "ad43", + "name": "Create qdisc hierarchy at maximum depth", + "category": [ + "qdisc", + "depth" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: htb default 1", + "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: htb default 1", + "$TC class add dev $DUMMY parent 2: classid 2:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 2:1 handle 3: htb default 1", + "$TC class add dev $DUMMY parent 3: classid 3:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 3:1 handle 4: htb default 1", + "$TC class add dev $DUMMY parent 4: classid 4:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 4:1 handle 5: htb default 1", + "$TC class add dev $DUMMY parent 5: classid 5:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 5:1 handle 6: htb default 1", + "$TC class add dev $DUMMY parent 6: classid 6:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 6:1 handle 7: htb default 1", + "$TC class add dev $DUMMY parent 7: classid 7:1 htb rate 10mbit" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 7:1 handle 8: htb default 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc htb 8: parent 7:1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] + }, + { + "id": "c519", + "name": "Reject qdisc hierarchy above maximum depth", + "category": [ + "qdisc", + "depth" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY root handle 1: htb default 1", + "$TC class add dev $DUMMY parent 1: classid 1:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: htb default 1", + "$TC class add dev $DUMMY parent 2: classid 2:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 2:1 handle 3: htb default 1", + "$TC class add dev $DUMMY parent 3: classid 3:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 3:1 handle 4: htb default 1", + "$TC class add dev $DUMMY parent 4: classid 4:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 4:1 handle 5: htb default 1", + "$TC class add dev $DUMMY parent 5: classid 5:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 5:1 handle 6: htb default 1", + "$TC class add dev $DUMMY parent 6: classid 6:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 6:1 handle 7: htb default 1", + "$TC class add dev $DUMMY parent 7: classid 7:1 htb rate 10mbit", + "$TC qdisc add dev $DUMMY parent 7:1 handle 8: htb default 1", + "$TC class add dev $DUMMY parent 8: classid 8:1 htb rate 10mbit" + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY parent 8:1 handle 9: htb default 1", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc htb 9:", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DUMMY root" + ] + } +] diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c index 85892b3b719c..b71813eaf5c0 100644 --- a/tools/testing/selftests/user_events/abi_test.c +++ b/tools/testing/selftests/user_events/abi_test.c @@ -132,6 +132,33 @@ static int event_delete(void) return ret; } +/* + * Deleting an event drops its last reference, but an unregister may defer + * that put (and the freeing of the associated enabler) past an RCU grace + * period. The delete can therefore transiently fail with -EBUSY while the + * previous reference is still being dropped. Retry only on that transient + * failure; treat an already-deleted event (-ENOENT) as success and return + * any other error immediately rather than spinning for the full timeout. + */ +static int wait_for_event_delete(void) +{ + int i, ret; + + for (i = 0; i < 10000; ++i) { + ret = event_delete(); + + if (ret == 0 || errno == ENOENT) + return 0; + + if (errno != EBUSY) + return ret; + + usleep(1000); + } + + return ret; +} + static int reg_enable_multi(void *enable, int size, int bit, int flags, char *args) { @@ -262,7 +289,7 @@ TEST_F(user, flags) { ASSERT_TRUE(event_exists()); /* Ensure we can delete it */ - ASSERT_EQ(0, event_delete()); + ASSERT_EQ(0, wait_for_event_delete()); /* USER_EVENT_REG_MAX or above is not allowed */ ASSERT_EQ(-1, reg_enable_flags(&self->check, sizeof(int), 0, diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index cafec0e52eb3..5727cb5b914c 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -85,6 +85,7 @@ static int get_offset(void) static int clear(int *check) { struct user_unreg unreg = {0}; + int i, ret; unreg.size = sizeof(unreg); unreg.disable_bit = 31; @@ -99,13 +100,32 @@ static int clear(int *check) if (errno != ENOENT) return -1; - if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1) - if (errno != ENOENT) + /* + * Deleting the event drops its last reference, but the unregister + * above defers that put (and the freeing of the enabler) past an RCU + * grace period. The delete can therefore transiently fail with -EBUSY + * until that reference is dropped. Retry for up to ~10 seconds so the + * event is actually gone before the next test registers the same name. + */ + for (i = 0; i < 10000; ++i) { + ret = ioctl(fd, DIAG_IOCSDEL, "__test_event"); + + if (ret == 0 || errno == ENOENT) { + ret = 0; + break; + } + + if (errno != EBUSY) { + close(fd); return -1; + } + + usleep(1000); + } close(fd); - return 0; + return ret; } FIXTURE(user) { diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 76be0e4a7f0e..b4ff9f946565 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -2347,6 +2347,88 @@ static void test_stream_tx_credit_bounds_server(const struct test_opts *opts) close(fd); } +/* Test that many small packets don't cause a connection reset under pressure + * and that data integrity is preserved. Packet sizes vary randomly between + * 129 and 512 bytes, above GOOD_COPY_LEN (128) to bypass in-place coalescing + * in recv_enqueue, forcing each one into its own skb. Without receive queue + * collapsing, the per-skb overhead eventually exceeds buf_alloc and the + * connection is reset. + */ +#define COLLAPSE_PKT_MIN 129 +#define COLLAPSE_PKT_MAX 512 +#define COLLAPSE_TOTAL (2 * 1024 * 1024) + +static void test_stream_collapse_client(const struct test_opts *opts) +{ + unsigned char *data; + unsigned long hash; + size_t offset = 0; + int i, fd; + + data = malloc(COLLAPSE_TOTAL); + if (!data) { + perror("malloc"); + exit(EXIT_FAILURE); + } + + for (i = 0; i < COLLAPSE_TOTAL; i++) + data[i] = rand() & 0xff; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + while (offset < COLLAPSE_TOTAL) { + size_t pkt_size = COLLAPSE_PKT_MIN + + rand() % (COLLAPSE_PKT_MAX - COLLAPSE_PKT_MIN + 1); + + pkt_size = min(pkt_size, COLLAPSE_TOTAL - offset); + + send_buf(fd, data + offset, pkt_size, 0, pkt_size); + offset += pkt_size; + } + + hash = hash_djb2(data, COLLAPSE_TOTAL); + control_writeulong(hash); + + free(data); + close(fd); +} + +static void test_stream_collapse_server(const struct test_opts *opts) +{ + unsigned long hash, remote_hash; + unsigned char *data; + int fd; + + data = malloc(COLLAPSE_TOTAL); + if (!data) { + perror("malloc"); + exit(EXIT_FAILURE); + } + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + recv_buf(fd, data, COLLAPSE_TOTAL, 0, COLLAPSE_TOTAL); + + hash = hash_djb2(data, COLLAPSE_TOTAL); + remote_hash = control_readulong(); + if (hash != remote_hash) { + fprintf(stderr, "hash mismatch: local %lu remote %lu\n", + hash, remote_hash); + exit(EXIT_FAILURE); + } + + free(data); + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -2546,6 +2628,11 @@ static struct test_case test_cases[] = { .run_client = test_stream_msg_peek_client, .run_server = test_stream_peek_after_recv_server, }, + { + .name = "SOCK_STREAM small packets backpressure", + .run_client = test_stream_collapse_client, + .run_server = test_stream_collapse_server, + }, {}, }; |
