diff options
Diffstat (limited to 'tools/testing')
39 files changed, 1037 insertions, 50 deletions
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/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/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_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/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 "${ksft_pass}" diff --git a/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh b/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh index d9111f2102bc..b379dff9087e 100755 --- a/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh +++ b/tools/testing/selftests/drivers/net/netconsole/netcons_resume.sh @@ -108,7 +108,7 @@ do # Send the message echo "${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/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/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_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/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/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 6f8971d5b3ce..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; @@ -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/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 $file and stay connected to the server # to conduct tests diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index fb1c59d45567..449c518bd947 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -617,7 +617,11 @@ ip -6 -net "$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 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/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/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/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, + }, {}, }; |