summaryrefslogtreecommitdiff
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rw-r--r--tools/testing/selftests/arm64/fp/fp-ptrace.c5
-rw-r--r--tools/testing/selftests/arm64/fp/sve-ptrace.c61
-rw-r--r--tools/testing/selftests/arm64/fp/zt-test.S2
-rw-r--r--tools/testing/selftests/cgroup/test_core.c7
-rw-r--r--tools/testing/selftests/cgroup/test_cpu.c7
-rw-r--r--tools/testing/selftests/cgroup/test_cpuset.c7
-rw-r--r--tools/testing/selftests/cgroup/test_freezer.c7
-rw-r--r--tools/testing/selftests/cgroup/test_kill.c7
-rw-r--r--tools/testing/selftests/cgroup/test_kmem.c7
-rw-r--r--tools/testing/selftests/cgroup/test_memcontrol.c7
-rw-r--r--tools/testing/selftests/cgroup/test_zswap.c7
-rw-r--r--tools/testing/selftests/coredump/.gitignore4
-rw-r--r--tools/testing/selftests/coredump/Makefile8
-rw-r--r--tools/testing/selftests/coredump/coredump_socket_protocol_test.c1568
-rw-r--r--tools/testing/selftests/coredump/coredump_socket_test.c742
-rw-r--r--tools/testing/selftests/coredump/coredump_test.h59
-rw-r--r--tools/testing/selftests/coredump/coredump_test_helpers.c383
-rw-r--r--tools/testing/selftests/coredump/stackdump_test.c1662
-rw-r--r--tools/testing/selftests/dma/dma_map_benchmark.c2
-rw-r--r--tools/testing/selftests/filesystems/utils.c2
-rw-r--r--tools/testing/selftests/ftrace/test.d/00basic/trace_marker_raw.tc107
-rw-r--r--tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc18
-rw-r--r--tools/testing/selftests/ftrace/test.d/dynevent/enable_disable_tprobe.tc40
-rw-r--r--tools/testing/selftests/kselftest/runner.sh14
-rw-r--r--tools/testing/selftests/kvm/arm64/set_id_regs.c10
-rw-r--r--tools/testing/selftests/livepatch/functions.sh6
-rw-r--r--tools/testing/selftests/mm/uffd-unit-tests.c15
-rw-r--r--tools/testing/selftests/namespaces/.gitignore9
-rw-r--r--tools/testing/selftests/namespaces/Makefile24
-rw-r--r--tools/testing/selftests/namespaces/cred_change_test.c814
-rw-r--r--tools/testing/selftests/namespaces/listns_efault_test.c530
-rw-r--r--tools/testing/selftests/namespaces/listns_pagination_bug.c138
-rw-r--r--tools/testing/selftests/namespaces/listns_permissions_test.c759
-rw-r--r--tools/testing/selftests/namespaces/listns_test.c679
-rw-r--r--tools/testing/selftests/namespaces/ns_active_ref_test.c2672
-rw-r--r--tools/testing/selftests/namespaces/nsid_test.c107
-rw-r--r--tools/testing/selftests/namespaces/regression_pidfd_setns_test.c113
-rw-r--r--tools/testing/selftests/namespaces/siocgskns_test.c1824
-rw-r--r--tools/testing/selftests/namespaces/stress_test.c626
-rw-r--r--tools/testing/selftests/namespaces/wrappers.h35
-rw-r--r--tools/testing/selftests/net/.gitignore1
-rw-r--r--tools/testing/selftests/net/af_unix/Makefile1
-rw-r--r--tools/testing/selftests/net/af_unix/so_peek_off.c162
-rwxr-xr-xtools/testing/selftests/net/forwarding/lib_sh_test.sh7
-rw-r--r--tools/testing/selftests/net/lib.sh2
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh27
-rw-r--r--tools/testing/selftests/nolibc/Makefile.nolibc6
-rw-r--r--tools/testing/selftests/nolibc/nolibc-test.c13
-rwxr-xr-xtools/testing/selftests/nolibc/run-tests.sh8
-rw-r--r--tools/testing/selftests/pidfd/pidfd.h15
-rw-r--r--tools/testing/selftests/pidfd/pidfd_info_test.c73
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-again.sh56
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-series.sh116
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh2
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE041
-rw-r--r--tools/testing/selftests/rseq/rseq-s390.h39
-rwxr-xr-xtools/testing/selftests/run_kselftest.sh14
-rw-r--r--tools/testing/selftests/sched_ext/Makefile1
-rw-r--r--tools/testing/selftests/sched_ext/peek_dsq.bpf.c251
-rw-r--r--tools/testing/selftests/sched_ext/peek_dsq.c224
-rw-r--r--tools/testing/selftests/timers/nanosleep.c55
-rw-r--r--tools/testing/selftests/timers/posix_timers.c32
-rw-r--r--tools/testing/selftests/user_events/perf_test.c2
-rw-r--r--tools/testing/selftests/vDSO/vdso_config.h4
-rw-r--r--tools/testing/selftests/x86/test_vsyscall.c21
65 files changed, 12343 insertions, 1884 deletions
diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c
index a85c19e9524e..0114108ab25f 100644
--- a/tools/testing/selftests/arm64/fp/fp-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c
@@ -1071,7 +1071,7 @@ static bool sve_write_supported(struct test_config *config)
static bool sve_write_fpsimd_supported(struct test_config *config)
{
- if (!sve_supported())
+ if (!sve_supported() && !sme_supported())
return false;
if ((config->svcr_in & SVCR_ZA) != (config->svcr_expected & SVCR_ZA))
@@ -1231,9 +1231,6 @@ static void sve_write_fpsimd(pid_t child, struct test_config *config)
vl = vl_expected(config);
vq = __sve_vq_from_vl(vl);
- if (!vl)
- return;
-
iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_FPSIMD);
iov.iov_base = malloc(iov.iov_len);
if (!iov.iov_base) {
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index e0fc3a001e28..f44d44618575 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -394,6 +394,58 @@ out:
free(svebuf);
}
+/* Write the FPSIMD registers via the SVE regset when SVE is not supported */
+static void ptrace_sve_fpsimd_no_sve(pid_t child)
+{
+ void *svebuf;
+ struct user_sve_header *sve;
+ struct user_fpsimd_state *fpsimd, new_fpsimd;
+ unsigned int i, j;
+ unsigned char *p;
+ int ret;
+
+ svebuf = malloc(SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD));
+ if (!svebuf) {
+ ksft_test_result_fail("Failed to allocate FPSIMD buffer\n");
+ return;
+ }
+
+ /* On a system without SVE the VL should be set to 0 */
+ memset(svebuf, 0, SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD));
+ sve = svebuf;
+ sve->flags = SVE_PT_REGS_FPSIMD;
+ sve->size = SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD);
+ sve->vl = 0;
+
+ /* Try to set a known FPSIMD state via PT_REGS_SVE */
+ fpsimd = (struct user_fpsimd_state *)((char *)sve +
+ SVE_PT_FPSIMD_OFFSET);
+ for (i = 0; i < 32; ++i) {
+ p = (unsigned char *)&fpsimd->vregs[i];
+
+ for (j = 0; j < sizeof(fpsimd->vregs[i]); ++j)
+ p[j] = j;
+ }
+
+ ret = set_sve(child, &vec_types[0], sve);
+ ksft_test_result(ret == 0, "FPSIMD write via SVE\n");
+ if (ret) {
+ ksft_test_result_skip("Verify FPSIMD write via SVE\n");
+ goto out;
+ }
+
+ /* Verify via the FPSIMD regset */
+ if (get_fpsimd(child, &new_fpsimd)) {
+ ksft_test_result_skip("Verify FPSIMD write via SVE\n");
+ goto out;
+ }
+ ksft_test_result(memcmp(fpsimd, &new_fpsimd, sizeof(*fpsimd)) == 0,
+ "Verify FPSIMD write via SVE\n");
+
+out:
+ free(svebuf);
+}
+
/* Validate attempting to set SVE data and read SVE data */
static void ptrace_set_sve_get_sve_data(pid_t child,
const struct vec_type *type,
@@ -826,6 +878,15 @@ static int do_parent(pid_t child)
}
}
+ /* We support SVE writes of FPSMID format on SME only systems */
+ if (!(getauxval(AT_HWCAP) & HWCAP_SVE) &&
+ (getauxval(AT_HWCAP2) & HWCAP2_SME)) {
+ ptrace_sve_fpsimd_no_sve(child);
+ } else {
+ ksft_test_result_skip("FPSIMD write via SVE\n");
+ ksft_test_result_skip("Verify FPSIMD write via SVE\n");
+ }
+
ret = EXIT_SUCCESS;
error:
diff --git a/tools/testing/selftests/arm64/fp/zt-test.S b/tools/testing/selftests/arm64/fp/zt-test.S
index 38080f3c3280..a8df05771670 100644
--- a/tools/testing/selftests/arm64/fp/zt-test.S
+++ b/tools/testing/selftests/arm64/fp/zt-test.S
@@ -276,7 +276,7 @@ function barf
bl putdec
puts ", iteration="
mov x0, x22
- bl putdec
+ bl putdecn
puts "\tExpected ["
mov x0, x10
mov x1, x12
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index a360e2eb2eef..1d778c8b7764 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -923,8 +923,10 @@ struct corecg_test {
int main(int argc, char *argv[])
{
char root[PATH_MAX];
- int i, ret = EXIT_SUCCESS;
+ int i;
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) {
if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME))
ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n");
@@ -946,12 +948,11 @@ post_v2_setup:
ksft_test_result_skip("%s\n", tests[i].name);
break;
default:
- ret = EXIT_FAILURE;
ksft_test_result_fail("%s\n", tests[i].name);
break;
}
}
cleanup_named_v1_root(root);
- return ret;
+ ksft_finished();
}
diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
index d54e2317efff..b1b30e82dd7c 100644
--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -796,8 +796,10 @@ struct cpucg_test {
int main(int argc, char *argv[])
{
char root[PATH_MAX];
- int i, ret = EXIT_SUCCESS;
+ int i;
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -814,11 +816,10 @@ int main(int argc, char *argv[])
ksft_test_result_skip("%s\n", tests[i].name);
break;
default:
- ret = EXIT_FAILURE;
ksft_test_result_fail("%s\n", tests[i].name);
break;
}
}
- return ret;
+ ksft_finished();
}
diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c
index 4034d14ba69a..8086d2ea394f 100644
--- a/tools/testing/selftests/cgroup/test_cpuset.c
+++ b/tools/testing/selftests/cgroup/test_cpuset.c
@@ -247,8 +247,10 @@ struct cpuset_test {
int main(int argc, char *argv[])
{
char root[PATH_MAX];
- int i, ret = EXIT_SUCCESS;
+ int i;
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -265,11 +267,10 @@ int main(int argc, char *argv[])
ksft_test_result_skip("%s\n", tests[i].name);
break;
default:
- ret = EXIT_FAILURE;
ksft_test_result_fail("%s\n", tests[i].name);
break;
}
}
- return ret;
+ ksft_finished();
}
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
index dfb763819581..465cdad2bfca 100644
--- a/tools/testing/selftests/cgroup/test_freezer.c
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -1488,8 +1488,10 @@ struct cgfreezer_test {
int main(int argc, char *argv[])
{
char root[PATH_MAX];
- int i, ret = EXIT_SUCCESS;
+ int i;
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
for (i = 0; i < ARRAY_SIZE(tests); i++) {
@@ -1501,11 +1503,10 @@ int main(int argc, char *argv[])
ksft_test_result_skip("%s\n", tests[i].name);
break;
default:
- ret = EXIT_FAILURE;
ksft_test_result_fail("%s\n", tests[i].name);
break;
}
}
- return ret;
+ ksft_finished();
}
diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c
index 0e5bb6c7307a..ed590b150a17 100644
--- a/tools/testing/selftests/cgroup/test_kill.c
+++ b/tools/testing/selftests/cgroup/test_kill.c
@@ -274,8 +274,10 @@ struct cgkill_test {
int main(int argc, char *argv[])
{
char root[PATH_MAX];
- int i, ret = EXIT_SUCCESS;
+ int i;
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
for (i = 0; i < ARRAY_SIZE(tests); i++) {
@@ -287,11 +289,10 @@ int main(int argc, char *argv[])
ksft_test_result_skip("%s\n", tests[i].name);
break;
default:
- ret = EXIT_FAILURE;
ksft_test_result_fail("%s\n", tests[i].name);
break;
}
}
- return ret;
+ ksft_finished();
}
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index 63b3c9aad399..d4c4a514ee43 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -421,8 +421,10 @@ struct kmem_test {
int main(int argc, char **argv)
{
char root[PATH_MAX];
- int i, ret = EXIT_SUCCESS;
+ int i;
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -446,11 +448,10 @@ int main(int argc, char **argv)
ksft_test_result_skip("%s\n", tests[i].name);
break;
default:
- ret = EXIT_FAILURE;
ksft_test_result_fail("%s\n", tests[i].name);
break;
}
}
- return ret;
+ ksft_finished();
}
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index a680f773f2d5..b117325c0439 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -1650,8 +1650,10 @@ struct memcg_test {
int main(int argc, char **argv)
{
char root[PATH_MAX];
- int i, proc_status, ret = EXIT_SUCCESS;
+ int i, proc_status;
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -1685,11 +1687,10 @@ int main(int argc, char **argv)
ksft_test_result_skip("%s\n", tests[i].name);
break;
default:
- ret = EXIT_FAILURE;
ksft_test_result_fail("%s\n", tests[i].name);
break;
}
}
- return ret;
+ ksft_finished();
}
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
index e1f578ca2841..86a8930b47e3 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -597,8 +597,10 @@ static bool zswap_configured(void)
int main(int argc, char **argv)
{
char root[PATH_MAX];
- int i, ret = EXIT_SUCCESS;
+ int i;
+ ksft_print_header();
+ ksft_set_plan(ARRAY_SIZE(tests));
if (cg_find_unified_root(root, sizeof(root), NULL))
ksft_exit_skip("cgroup v2 isn't mounted\n");
@@ -625,11 +627,10 @@ int main(int argc, char **argv)
ksft_test_result_skip("%s\n", tests[i].name);
break;
default:
- ret = EXIT_FAILURE;
ksft_test_result_fail("%s\n", tests[i].name);
break;
}
}
- return ret;
+ ksft_finished();
}
diff --git a/tools/testing/selftests/coredump/.gitignore b/tools/testing/selftests/coredump/.gitignore
new file mode 100644
index 000000000000..097f52db0be9
--- /dev/null
+++ b/tools/testing/selftests/coredump/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+stackdump_test
+coredump_socket_test
+coredump_socket_protocol_test
diff --git a/tools/testing/selftests/coredump/Makefile b/tools/testing/selftests/coredump/Makefile
index 77b3665c73c7..dece1a31d561 100644
--- a/tools/testing/selftests/coredump/Makefile
+++ b/tools/testing/selftests/coredump/Makefile
@@ -1,7 +1,13 @@
# SPDX-License-Identifier: GPL-2.0-only
CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
-TEST_GEN_PROGS := stackdump_test
+TEST_GEN_PROGS := stackdump_test \
+ coredump_socket_test \
+ coredump_socket_protocol_test
TEST_FILES := stackdump
include ../lib.mk
+
+$(OUTPUT)/stackdump_test: coredump_test_helpers.c
+$(OUTPUT)/coredump_socket_test: coredump_test_helpers.c
+$(OUTPUT)/coredump_socket_protocol_test: coredump_test_helpers.c
diff --git a/tools/testing/selftests/coredump/coredump_socket_protocol_test.c b/tools/testing/selftests/coredump/coredump_socket_protocol_test.c
new file mode 100644
index 000000000000..d19b6717c53e
--- /dev/null
+++ b/tools/testing/selftests/coredump/coredump_socket_protocol_test.c
@@ -0,0 +1,1568 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/stat.h>
+#include <sys/epoll.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+
+#include "coredump_test.h"
+
+#define NUM_CRASHING_COREDUMPS 5
+
+FIXTURE_SETUP(coredump)
+{
+ FILE *file;
+ int ret;
+
+ self->pid_coredump_server = -ESRCH;
+ self->fd_tmpfs_detached = -1;
+ file = fopen("/proc/sys/kernel/core_pattern", "r");
+ ASSERT_NE(NULL, file);
+
+ ret = fread(self->original_core_pattern, 1, sizeof(self->original_core_pattern), file);
+ ASSERT_TRUE(ret || feof(file));
+ ASSERT_LT(ret, sizeof(self->original_core_pattern));
+
+ self->original_core_pattern[ret] = '\0';
+ self->fd_tmpfs_detached = create_detached_tmpfs();
+ ASSERT_GE(self->fd_tmpfs_detached, 0);
+
+ ret = fclose(file);
+ ASSERT_EQ(0, ret);
+}
+
+FIXTURE_TEARDOWN(coredump)
+{
+ const char *reason;
+ FILE *file;
+ int ret, status;
+
+ if (self->pid_coredump_server > 0) {
+ kill(self->pid_coredump_server, SIGTERM);
+ waitpid(self->pid_coredump_server, &status, 0);
+ }
+ unlink("/tmp/coredump.file");
+ unlink("/tmp/coredump.socket");
+
+ file = fopen("/proc/sys/kernel/core_pattern", "w");
+ if (!file) {
+ reason = "Unable to open core_pattern";
+ goto fail;
+ }
+
+ ret = fprintf(file, "%s", self->original_core_pattern);
+ if (ret < 0) {
+ reason = "Unable to write to core_pattern";
+ goto fail;
+ }
+
+ ret = fclose(file);
+ if (ret) {
+ reason = "Unable to close core_pattern";
+ goto fail;
+ }
+
+ if (self->fd_tmpfs_detached >= 0) {
+ ret = close(self->fd_tmpfs_detached);
+ if (ret < 0) {
+ reason = "Unable to close detached tmpfs";
+ goto fail;
+ }
+ self->fd_tmpfs_detached = -1;
+ }
+
+ return;
+fail:
+ /* This should never happen */
+ fprintf(stderr, "Failed to cleanup coredump test: %s\n", reason);
+}
+
+TEST_F(coredump, socket_request_kernel)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct stat st;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ struct coredump_req req = {};
+ int fd_server = -1, fd_coredump = -1, fd_core_file = -1, fd_peer_pidfd = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_request_kernel: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_request_kernel: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_request_kernel: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_request_kernel: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_request_kernel: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_request_kernel: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_request_kernel: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ fd_core_file = creat("/tmp/coredump.file", 0644);
+ if (fd_core_file < 0) {
+ fprintf(stderr, "socket_request_kernel: creat coredump file failed: %m\n");
+ goto out;
+ }
+
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "socket_request_kernel: read_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+ COREDUMP_KERNEL | COREDUMP_USERSPACE |
+ COREDUMP_REJECT | COREDUMP_WAIT)) {
+ fprintf(stderr, "socket_request_kernel: check_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!send_coredump_ack(fd_coredump, &req,
+ COREDUMP_KERNEL | COREDUMP_WAIT, 0)) {
+ fprintf(stderr, "socket_request_kernel: send_coredump_ack failed\n");
+ goto out;
+ }
+
+ if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+ fprintf(stderr, "socket_request_kernel: read_marker COREDUMP_MARK_REQACK failed\n");
+ goto out;
+ }
+
+ for (;;) {
+ char buffer[4096];
+ ssize_t bytes_read, bytes_write;
+
+ bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+ if (bytes_read < 0) {
+ fprintf(stderr, "socket_request_kernel: read from coredump socket failed: %m\n");
+ goto out;
+ }
+
+ if (bytes_read == 0)
+ break;
+
+ bytes_write = write(fd_core_file, buffer, bytes_read);
+ if (bytes_read != bytes_write) {
+ if (bytes_write < 0 && errno == ENOSPC)
+ continue;
+ fprintf(stderr, "socket_request_kernel: write to core file failed (read=%zd, write=%zd): %m\n",
+ bytes_read, bytes_write);
+ goto out;
+ }
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_request_kernel: completed successfully\n");
+out:
+ if (fd_core_file >= 0)
+ close(fd_core_file);
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_TRUE(WCOREDUMP(status));
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+
+ ASSERT_EQ(stat("/tmp/coredump.file", &st), 0);
+ ASSERT_GT(st.st_size, 0);
+ system("file /tmp/coredump.file");
+}
+
+TEST_F(coredump, socket_request_userspace)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ struct coredump_req req = {};
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_request_userspace: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_request_userspace: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_request_userspace: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_request_userspace: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_request_userspace: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_request_userspace: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_request_userspace: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "socket_request_userspace: read_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+ COREDUMP_KERNEL | COREDUMP_USERSPACE |
+ COREDUMP_REJECT | COREDUMP_WAIT)) {
+ fprintf(stderr, "socket_request_userspace: check_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!send_coredump_ack(fd_coredump, &req,
+ COREDUMP_USERSPACE | COREDUMP_WAIT, 0)) {
+ fprintf(stderr, "socket_request_userspace: send_coredump_ack failed\n");
+ goto out;
+ }
+
+ if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+ fprintf(stderr, "socket_request_userspace: read_marker COREDUMP_MARK_REQACK failed\n");
+ goto out;
+ }
+
+ for (;;) {
+ char buffer[4096];
+ ssize_t bytes_read;
+
+ bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+ if (bytes_read > 0) {
+ fprintf(stderr, "socket_request_userspace: unexpected data received (expected no coredump data)\n");
+ goto out;
+ }
+
+ if (bytes_read < 0) {
+ fprintf(stderr, "socket_request_userspace: read from coredump socket failed: %m\n");
+ goto out;
+ }
+
+ if (bytes_read == 0)
+ break;
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_request_userspace: completed successfully\n");
+out:
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_TRUE(WCOREDUMP(status));
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_reject)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ struct coredump_req req = {};
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_request_reject: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_request_reject: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_request_reject: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_request_reject: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_request_reject: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_request_reject: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_request_reject: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "socket_request_reject: read_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+ COREDUMP_KERNEL | COREDUMP_USERSPACE |
+ COREDUMP_REJECT | COREDUMP_WAIT)) {
+ fprintf(stderr, "socket_request_reject: check_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!send_coredump_ack(fd_coredump, &req,
+ COREDUMP_REJECT | COREDUMP_WAIT, 0)) {
+ fprintf(stderr, "socket_request_reject: send_coredump_ack failed\n");
+ goto out;
+ }
+
+ if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+ fprintf(stderr, "socket_request_reject: read_marker COREDUMP_MARK_REQACK failed\n");
+ goto out;
+ }
+
+ for (;;) {
+ char buffer[4096];
+ ssize_t bytes_read;
+
+ bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+ if (bytes_read > 0) {
+ fprintf(stderr, "socket_request_reject: unexpected data received (expected no coredump data for REJECT)\n");
+ goto out;
+ }
+
+ if (bytes_read < 0) {
+ fprintf(stderr, "socket_request_reject: read from coredump socket failed: %m\n");
+ goto out;
+ }
+
+ if (bytes_read == 0)
+ break;
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_request_reject: completed successfully\n");
+out:
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_FALSE(WCOREDUMP(status));
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_invalid_flag_combination)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ struct coredump_req req = {};
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: read_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+ COREDUMP_KERNEL | COREDUMP_USERSPACE |
+ COREDUMP_REJECT | COREDUMP_WAIT)) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: check_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!send_coredump_ack(fd_coredump, &req,
+ COREDUMP_KERNEL | COREDUMP_REJECT | COREDUMP_WAIT, 0)) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: send_coredump_ack failed\n");
+ goto out;
+ }
+
+ if (!read_marker(fd_coredump, COREDUMP_MARK_CONFLICTING)) {
+ fprintf(stderr, "socket_request_invalid_flag_combination: read_marker COREDUMP_MARK_CONFLICTING failed\n");
+ goto out;
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_request_invalid_flag_combination: completed successfully\n");
+out:
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_FALSE(WCOREDUMP(status));
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_unknown_flag)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ struct coredump_req req = {};
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_request_unknown_flag: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_request_unknown_flag: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_request_unknown_flag: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_request_unknown_flag: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_request_unknown_flag: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_request_unknown_flag: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_request_unknown_flag: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "socket_request_unknown_flag: read_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+ COREDUMP_KERNEL | COREDUMP_USERSPACE |
+ COREDUMP_REJECT | COREDUMP_WAIT)) {
+ fprintf(stderr, "socket_request_unknown_flag: check_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!send_coredump_ack(fd_coredump, &req, (1ULL << 63), 0)) {
+ fprintf(stderr, "socket_request_unknown_flag: send_coredump_ack failed\n");
+ goto out;
+ }
+
+ if (!read_marker(fd_coredump, COREDUMP_MARK_UNSUPPORTED)) {
+ fprintf(stderr, "socket_request_unknown_flag: read_marker COREDUMP_MARK_UNSUPPORTED failed\n");
+ goto out;
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_request_unknown_flag: completed successfully\n");
+out:
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_FALSE(WCOREDUMP(status));
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_invalid_size_small)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ struct coredump_req req = {};
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_request_invalid_size_small: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_request_invalid_size_small: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_request_invalid_size_small: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_request_invalid_size_small: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_request_invalid_size_small: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_request_invalid_size_small: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_request_invalid_size_small: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "socket_request_invalid_size_small: read_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+ COREDUMP_KERNEL | COREDUMP_USERSPACE |
+ COREDUMP_REJECT | COREDUMP_WAIT)) {
+ fprintf(stderr, "socket_request_invalid_size_small: check_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!send_coredump_ack(fd_coredump, &req,
+ COREDUMP_REJECT | COREDUMP_WAIT,
+ COREDUMP_ACK_SIZE_VER0 / 2)) {
+ fprintf(stderr, "socket_request_invalid_size_small: send_coredump_ack failed\n");
+ goto out;
+ }
+
+ if (!read_marker(fd_coredump, COREDUMP_MARK_MINSIZE)) {
+ fprintf(stderr, "socket_request_invalid_size_small: read_marker COREDUMP_MARK_MINSIZE failed\n");
+ goto out;
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_request_invalid_size_small: completed successfully\n");
+out:
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_FALSE(WCOREDUMP(status));
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_invalid_size_large)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ struct coredump_req req = {};
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_request_invalid_size_large: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_request_invalid_size_large: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_request_invalid_size_large: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_request_invalid_size_large: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_request_invalid_size_large: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_request_invalid_size_large: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_request_invalid_size_large: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "socket_request_invalid_size_large: read_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+ COREDUMP_KERNEL | COREDUMP_USERSPACE |
+ COREDUMP_REJECT | COREDUMP_WAIT)) {
+ fprintf(stderr, "socket_request_invalid_size_large: check_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!send_coredump_ack(fd_coredump, &req,
+ COREDUMP_REJECT | COREDUMP_WAIT,
+ COREDUMP_ACK_SIZE_VER0 + PAGE_SIZE)) {
+ fprintf(stderr, "socket_request_invalid_size_large: send_coredump_ack failed\n");
+ goto out;
+ }
+
+ if (!read_marker(fd_coredump, COREDUMP_MARK_MAXSIZE)) {
+ fprintf(stderr, "socket_request_invalid_size_large: read_marker COREDUMP_MARK_MAXSIZE failed\n");
+ goto out;
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_request_invalid_size_large: completed successfully\n");
+out:
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_FALSE(WCOREDUMP(status));
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+/*
+ * Test: PIDFD_INFO_COREDUMP_SIGNAL via socket coredump with SIGSEGV
+ *
+ * Verify that when using socket-based coredump protocol,
+ * the coredump_signal field is correctly exposed as SIGSEGV.
+ */
+TEST_F(coredump, socket_coredump_signal_sigsegv)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ struct coredump_req req = {};
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ /* Verify coredump_signal is available and correct */
+ if (!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_INFO_COREDUMP_SIGNAL not set in mask\n");
+ goto out;
+ }
+
+ if (info.coredump_signal != SIGSEGV) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: coredump_signal=%d, expected SIGSEGV=%d\n",
+ info.coredump_signal, SIGSEGV);
+ goto out;
+ }
+
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: read_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!send_coredump_ack(fd_coredump, &req,
+ COREDUMP_REJECT | COREDUMP_WAIT, 0)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: send_coredump_ack failed\n");
+ goto out;
+ }
+
+ if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: read_marker COREDUMP_MARK_REQACK failed\n");
+ goto out;
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_coredump_signal_sigsegv: completed successfully\n");
+out:
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_EQ(WTERMSIG(status), SIGSEGV);
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP));
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL));
+ ASSERT_EQ(info.coredump_signal, SIGSEGV);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+/*
+ * Test: PIDFD_INFO_COREDUMP_SIGNAL via socket coredump with SIGABRT
+ *
+ * Verify that when using socket-based coredump protocol,
+ * the coredump_signal field is correctly exposed as SIGABRT.
+ */
+TEST_F(coredump, socket_coredump_signal_sigabrt)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ struct coredump_req req = {};
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ /* Verify coredump_signal is available and correct */
+ if (!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_INFO_COREDUMP_SIGNAL not set in mask\n");
+ goto out;
+ }
+
+ if (info.coredump_signal != SIGABRT) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: coredump_signal=%d, expected SIGABRT=%d\n",
+ info.coredump_signal, SIGABRT);
+ goto out;
+ }
+
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: read_coredump_req failed\n");
+ goto out;
+ }
+
+ if (!send_coredump_ack(fd_coredump, &req,
+ COREDUMP_REJECT | COREDUMP_WAIT, 0)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: send_coredump_ack failed\n");
+ goto out;
+ }
+
+ if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: read_marker COREDUMP_MARK_REQACK failed\n");
+ goto out;
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_coredump_signal_sigabrt: completed successfully\n");
+out:
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ abort();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_EQ(WTERMSIG(status), SIGABRT);
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP));
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL));
+ ASSERT_EQ(info.coredump_signal, SIGABRT);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F_TIMEOUT(coredump, socket_multiple_crashing_coredumps, 500)
+{
+ int pidfd[NUM_CRASHING_COREDUMPS], status[NUM_CRASHING_COREDUMPS];
+ pid_t pid[NUM_CRASHING_COREDUMPS], pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+ int exit_code = EXIT_FAILURE;
+ struct coredump_req req = {};
+
+ close(ipc_sockets[0]);
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "Failed to create and listen on unix socket\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "Failed to notify parent via ipc socket\n");
+ goto out;
+ }
+ close(ipc_sockets[1]);
+
+ for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "get_peer_pidfd failed for fd %d: %m\n", fd_coredump);
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "get_pidfd_info failed for fd %d\n", fd_peer_pidfd);
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "pidfd info missing PIDFD_INFO_COREDUMP for fd %d\n", fd_peer_pidfd);
+ goto out;
+ }
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "pidfd info missing PIDFD_COREDUMPED for fd %d\n", fd_peer_pidfd);
+ goto out;
+ }
+
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "read_coredump_req failed for fd %d\n", fd_coredump);
+ goto out;
+ }
+
+ if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+ COREDUMP_KERNEL | COREDUMP_USERSPACE |
+ COREDUMP_REJECT | COREDUMP_WAIT)) {
+ fprintf(stderr, "check_coredump_req failed for fd %d\n", fd_coredump);
+ goto out;
+ }
+
+ if (!send_coredump_ack(fd_coredump, &req,
+ COREDUMP_KERNEL | COREDUMP_WAIT, 0)) {
+ fprintf(stderr, "send_coredump_ack failed for fd %d\n", fd_coredump);
+ goto out;
+ }
+
+ if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+ fprintf(stderr, "read_marker failed for fd %d\n", fd_coredump);
+ goto out;
+ }
+
+ fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
+ if (fd_core_file < 0) {
+ fprintf(stderr, "%m - open_coredump_tmpfile failed for fd %d\n", fd_coredump);
+ goto out;
+ }
+
+ for (;;) {
+ char buffer[4096];
+ ssize_t bytes_read, bytes_write;
+
+ bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+ if (bytes_read < 0) {
+ fprintf(stderr, "read failed for fd %d: %m\n", fd_coredump);
+ goto out;
+ }
+
+ if (bytes_read == 0)
+ break;
+
+ bytes_write = write(fd_core_file, buffer, bytes_read);
+ if (bytes_read != bytes_write) {
+ if (bytes_write < 0 && errno == ENOSPC)
+ continue;
+ fprintf(stderr, "write failed for fd %d: %m\n", fd_core_file);
+ goto out;
+ }
+ }
+
+ close(fd_core_file);
+ close(fd_peer_pidfd);
+ close(fd_coredump);
+ fd_peer_pidfd = -1;
+ fd_coredump = -1;
+ }
+
+ exit_code = EXIT_SUCCESS;
+out:
+ if (fd_core_file >= 0)
+ close(fd_core_file);
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+ pid[i] = fork();
+ ASSERT_GE(pid[i], 0);
+ if (pid[i] == 0)
+ crashing_child();
+ pidfd[i] = sys_pidfd_open(pid[i], 0);
+ ASSERT_GE(pidfd[i], 0);
+ }
+
+ for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+ waitpid(pid[i], &status[i], 0);
+ ASSERT_TRUE(WIFSIGNALED(status[i]));
+ ASSERT_TRUE(WCOREDUMP(status[i]));
+ }
+
+ for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+ info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+ ASSERT_EQ(ioctl(pidfd[i], PIDFD_GET_INFO, &info), 0);
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+ }
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F_TIMEOUT(coredump, socket_multiple_crashing_coredumps_epoll_workers, 500)
+{
+ int pidfd[NUM_CRASHING_COREDUMPS], status[NUM_CRASHING_COREDUMPS];
+ pid_t pid[NUM_CRASHING_COREDUMPS], pid_coredump_server, worker_pids[NUM_CRASHING_COREDUMPS];
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ int fd_server = -1, exit_code = EXIT_FAILURE, n_conns = 0;
+ fd_server = -1;
+ exit_code = EXIT_FAILURE;
+ n_conns = 0;
+ close(ipc_sockets[0]);
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+ close(ipc_sockets[1]);
+
+ while (n_conns < NUM_CRASHING_COREDUMPS) {
+ int fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+ struct coredump_req req = {};
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ if (errno == EAGAIN || errno == EWOULDBLOCK)
+ continue;
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: accept4 failed: %m\n");
+ goto out;
+ }
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: get_peer_pidfd failed\n");
+ goto out;
+ }
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: get_pidfd_info failed\n");
+ goto out;
+ }
+ if (!(info.mask & PIDFD_INFO_COREDUMP) || !(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: missing PIDFD_INFO_COREDUMP or PIDFD_COREDUMPED\n");
+ goto out;
+ }
+ if (!read_coredump_req(fd_coredump, &req)) {
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: read_coredump_req failed\n");
+ goto out;
+ }
+ if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+ COREDUMP_KERNEL | COREDUMP_USERSPACE |
+ COREDUMP_REJECT | COREDUMP_WAIT)) {
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: check_coredump_req failed\n");
+ goto out;
+ }
+ if (!send_coredump_ack(fd_coredump, &req, COREDUMP_KERNEL | COREDUMP_WAIT, 0)) {
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: send_coredump_ack failed\n");
+ goto out;
+ }
+ if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: read_marker failed\n");
+ goto out;
+ }
+ fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
+ if (fd_core_file < 0) {
+ fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: open_coredump_tmpfile failed: %m\n");
+ goto out;
+ }
+ pid_t worker = fork();
+ if (worker == 0) {
+ close(fd_server);
+ process_coredump_worker(fd_coredump, fd_peer_pidfd, fd_core_file);
+ }
+ worker_pids[n_conns] = worker;
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_core_file >= 0)
+ close(fd_core_file);
+ n_conns++;
+ }
+ exit_code = EXIT_SUCCESS;
+out:
+ if (fd_server >= 0)
+ close(fd_server);
+
+ // Reap all worker processes
+ for (int i = 0; i < n_conns; i++) {
+ int wstatus;
+ if (waitpid(worker_pids[i], &wstatus, 0) < 0) {
+ fprintf(stderr, "Failed to wait for worker %d: %m\n", worker_pids[i]);
+ } else if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) != EXIT_SUCCESS) {
+ fprintf(stderr, "Worker %d exited with error code %d\n", worker_pids[i], WEXITSTATUS(wstatus));
+ exit_code = EXIT_FAILURE;
+ }
+ }
+
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+ pid[i] = fork();
+ ASSERT_GE(pid[i], 0);
+ if (pid[i] == 0)
+ crashing_child();
+ pidfd[i] = sys_pidfd_open(pid[i], 0);
+ ASSERT_GE(pidfd[i], 0);
+ }
+
+ for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+ ASSERT_GE(waitpid(pid[i], &status[i], 0), 0);
+ ASSERT_TRUE(WIFSIGNALED(status[i]));
+ ASSERT_TRUE(WCOREDUMP(status[i]));
+ }
+
+ for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+ info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+ ASSERT_EQ(ioctl(pidfd[i], PIDFD_GET_INFO, &info), 0);
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+ }
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/coredump/coredump_socket_test.c b/tools/testing/selftests/coredump/coredump_socket_test.c
new file mode 100644
index 000000000000..7e26d4a6a15d
--- /dev/null
+++ b/tools/testing/selftests/coredump/coredump_socket_test.c
@@ -0,0 +1,742 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/stat.h>
+#include <sys/epoll.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+
+#include "coredump_test.h"
+
+FIXTURE_SETUP(coredump)
+{
+ FILE *file;
+ int ret;
+
+ self->pid_coredump_server = -ESRCH;
+ self->fd_tmpfs_detached = -1;
+ file = fopen("/proc/sys/kernel/core_pattern", "r");
+ ASSERT_NE(NULL, file);
+
+ ret = fread(self->original_core_pattern, 1, sizeof(self->original_core_pattern), file);
+ ASSERT_TRUE(ret || feof(file));
+ ASSERT_LT(ret, sizeof(self->original_core_pattern));
+
+ self->original_core_pattern[ret] = '\0';
+ self->fd_tmpfs_detached = create_detached_tmpfs();
+ ASSERT_GE(self->fd_tmpfs_detached, 0);
+
+ ret = fclose(file);
+ ASSERT_EQ(0, ret);
+}
+
+FIXTURE_TEARDOWN(coredump)
+{
+ const char *reason;
+ FILE *file;
+ int ret, status;
+
+ if (self->pid_coredump_server > 0) {
+ kill(self->pid_coredump_server, SIGTERM);
+ waitpid(self->pid_coredump_server, &status, 0);
+ }
+ unlink("/tmp/coredump.file");
+ unlink("/tmp/coredump.socket");
+
+ file = fopen("/proc/sys/kernel/core_pattern", "w");
+ if (!file) {
+ reason = "Unable to open core_pattern";
+ goto fail;
+ }
+
+ ret = fprintf(file, "%s", self->original_core_pattern);
+ if (ret < 0) {
+ reason = "Unable to write to core_pattern";
+ goto fail;
+ }
+
+ ret = fclose(file);
+ if (ret) {
+ reason = "Unable to close core_pattern";
+ goto fail;
+ }
+
+ if (self->fd_tmpfs_detached >= 0) {
+ ret = close(self->fd_tmpfs_detached);
+ if (ret < 0) {
+ reason = "Unable to close detached tmpfs";
+ goto fail;
+ }
+ self->fd_tmpfs_detached = -1;
+ }
+
+ return;
+fail:
+ /* This should never happen */
+ fprintf(stderr, "Failed to cleanup coredump test: %s\n", reason);
+}
+
+TEST_F(coredump, socket)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct stat st;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket test: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket test: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket test: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket test: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket test: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket test: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket test: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ fd_core_file = creat("/tmp/coredump.file", 0644);
+ if (fd_core_file < 0) {
+ fprintf(stderr, "socket test: creat coredump file failed: %m\n");
+ goto out;
+ }
+
+ for (;;) {
+ char buffer[4096];
+ ssize_t bytes_read, bytes_write;
+
+ bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+ if (bytes_read < 0) {
+ fprintf(stderr, "socket test: read from coredump socket failed: %m\n");
+ goto out;
+ }
+
+ if (bytes_read == 0)
+ break;
+
+ bytes_write = write(fd_core_file, buffer, bytes_read);
+ if (bytes_read != bytes_write) {
+ if (bytes_write < 0 && errno == ENOSPC)
+ continue;
+ fprintf(stderr, "socket test: write to core file failed (read=%zd, write=%zd): %m\n", bytes_read, bytes_write);
+ goto out;
+ }
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket test: completed successfully\n");
+out:
+ if (fd_core_file >= 0)
+ close(fd_core_file);
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_TRUE(WCOREDUMP(status));
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+
+ ASSERT_EQ(stat("/tmp/coredump.file", &st), 0);
+ ASSERT_GT(st.st_size, 0);
+}
+
+TEST_F(coredump, socket_detect_userspace_client)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct stat st;
+ struct pidfd_info info = {
+ .mask = PIDFD_INFO_COREDUMP,
+ };
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_detect_userspace_client: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_detect_userspace_client: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_detect_userspace_client: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_detect_userspace_client: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_detect_userspace_client: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_detect_userspace_client: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (info.coredump_mask & PIDFD_COREDUMPED) {
+ fprintf(stderr, "socket_detect_userspace_client: PIDFD_COREDUMPED incorrectly set (should be userspace client)\n");
+ goto out;
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_detect_userspace_client: completed successfully\n");
+out:
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0) {
+ int fd_socket;
+ ssize_t ret;
+ const struct sockaddr_un coredump_sk = {
+ .sun_family = AF_UNIX,
+ .sun_path = "/tmp/coredump.socket",
+ };
+ size_t coredump_sk_len =
+ offsetof(struct sockaddr_un, sun_path) +
+ sizeof("/tmp/coredump.socket");
+
+ fd_socket = socket(AF_UNIX, SOCK_STREAM, 0);
+ if (fd_socket < 0) {
+ fprintf(stderr, "socket_detect_userspace_client (client): socket failed: %m\n");
+ _exit(EXIT_FAILURE);
+ }
+
+ ret = connect(fd_socket, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
+ if (ret < 0) {
+ fprintf(stderr, "socket_detect_userspace_client (client): connect failed: %m\n");
+ _exit(EXIT_FAILURE);
+ }
+
+ close(fd_socket);
+ pause();
+ fprintf(stderr, "socket_detect_userspace_client (client): completed successfully\n");
+ _exit(EXIT_SUCCESS);
+ }
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+ ASSERT_EQ((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+
+ ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0), 0);
+ ASSERT_EQ(close(pidfd), 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_EQ(WTERMSIG(status), SIGKILL);
+
+ ASSERT_NE(stat("/tmp/coredump.file", &st), 0);
+ ASSERT_EQ(errno, ENOENT);
+}
+
+TEST_F(coredump, socket_enoent)
+{
+ int pidfd, status;
+ pid_t pid;
+
+ ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_FALSE(WCOREDUMP(status));
+}
+
+TEST_F(coredump, socket_no_listener)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ int ipc_sockets[2];
+ char c;
+ const struct sockaddr_un coredump_sk = {
+ .sun_family = AF_UNIX,
+ .sun_path = "/tmp/coredump.socket",
+ };
+ size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) +
+ sizeof("/tmp/coredump.socket");
+
+ ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ int fd_server = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_no_listener: socket failed: %m\n");
+ goto out;
+ }
+
+ ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
+ if (ret < 0) {
+ fprintf(stderr, "socket_no_listener: bind failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_no_listener: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_no_listener: completed successfully\n");
+out:
+ if (fd_server >= 0)
+ close(fd_server);
+ close(ipc_sockets[1]);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_FALSE(WCOREDUMP(status));
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+/*
+ * Test: PIDFD_INFO_COREDUMP_SIGNAL via simple socket coredump
+ *
+ * Verify that when using simple socket-based coredump (@ pattern),
+ * the coredump_signal field is correctly exposed as SIGSEGV.
+ */
+TEST_F(coredump, socket_coredump_signal_sigsegv)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ /* Verify coredump_signal is available and correct */
+ if (!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL)) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_INFO_COREDUMP_SIGNAL not set in mask\n");
+ goto out;
+ }
+
+ if (info.coredump_signal != SIGSEGV) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: coredump_signal=%d, expected SIGSEGV=%d\n",
+ info.coredump_signal, SIGSEGV);
+ goto out;
+ }
+
+ fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
+ if (fd_core_file < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: open_coredump_tmpfile failed: %m\n");
+ goto out;
+ }
+
+ for (;;) {
+ char buffer[4096];
+ ssize_t bytes_read, bytes_write;
+
+ bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+ if (bytes_read < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: read from coredump socket failed: %m\n");
+ goto out;
+ }
+
+ if (bytes_read == 0)
+ break;
+
+ bytes_write = write(fd_core_file, buffer, bytes_read);
+ if (bytes_read != bytes_write) {
+ fprintf(stderr, "socket_coredump_signal_sigsegv: write to core file failed (read=%zd, write=%zd): %m\n",
+ bytes_read, bytes_write);
+ goto out;
+ }
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_coredump_signal_sigsegv: completed successfully\n");
+out:
+ if (fd_core_file >= 0)
+ close(fd_core_file);
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ crashing_child();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_EQ(WTERMSIG(status), SIGSEGV);
+ ASSERT_TRUE(WCOREDUMP(status));
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP));
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL));
+ ASSERT_EQ(info.coredump_signal, SIGSEGV);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+/*
+ * Test: PIDFD_INFO_COREDUMP_SIGNAL via simple socket coredump with SIGABRT
+ *
+ * Verify that when using simple socket-based coredump (@ pattern),
+ * the coredump_signal field is correctly exposed as SIGABRT.
+ */
+TEST_F(coredump, socket_coredump_signal_sigabrt)
+{
+ int pidfd, ret, status;
+ pid_t pid, pid_coredump_server;
+ struct pidfd_info info = {};
+ int ipc_sockets[2];
+ char c;
+
+ ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+ ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ ASSERT_EQ(ret, 0);
+
+ pid_coredump_server = fork();
+ ASSERT_GE(pid_coredump_server, 0);
+ if (pid_coredump_server == 0) {
+ int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+ int exit_code = EXIT_FAILURE;
+
+ close(ipc_sockets[0]);
+
+ fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+ if (fd_server < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: create_and_listen_unix_socket failed: %m\n");
+ goto out;
+ }
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: write_nointr to ipc socket failed: %m\n");
+ goto out;
+ }
+
+ close(ipc_sockets[1]);
+
+ fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+ if (fd_coredump < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: accept4 failed: %m\n");
+ goto out;
+ }
+
+ fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+ if (fd_peer_pidfd < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: get_peer_pidfd failed\n");
+ goto out;
+ }
+
+ if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: get_pidfd_info failed\n");
+ goto out;
+ }
+
+ if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_INFO_COREDUMP not set in mask\n");
+ goto out;
+ }
+
+ if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_COREDUMPED not set in coredump_mask\n");
+ goto out;
+ }
+
+ /* Verify coredump_signal is available and correct */
+ if (!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL)) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_INFO_COREDUMP_SIGNAL not set in mask\n");
+ goto out;
+ }
+
+ if (info.coredump_signal != SIGABRT) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: coredump_signal=%d, expected SIGABRT=%d\n",
+ info.coredump_signal, SIGABRT);
+ goto out;
+ }
+
+ fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
+ if (fd_core_file < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: open_coredump_tmpfile failed: %m\n");
+ goto out;
+ }
+
+ for (;;) {
+ char buffer[4096];
+ ssize_t bytes_read, bytes_write;
+
+ bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+ if (bytes_read < 0) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: read from coredump socket failed: %m\n");
+ goto out;
+ }
+
+ if (bytes_read == 0)
+ break;
+
+ bytes_write = write(fd_core_file, buffer, bytes_read);
+ if (bytes_read != bytes_write) {
+ fprintf(stderr, "socket_coredump_signal_sigabrt: write to core file failed (read=%zd, write=%zd): %m\n",
+ bytes_read, bytes_write);
+ goto out;
+ }
+ }
+
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "socket_coredump_signal_sigabrt: completed successfully\n");
+out:
+ if (fd_core_file >= 0)
+ close(fd_core_file);
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ if (fd_server >= 0)
+ close(fd_server);
+ _exit(exit_code);
+ }
+ self->pid_coredump_server = pid_coredump_server;
+
+ EXPECT_EQ(close(ipc_sockets[1]), 0);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+ if (pid == 0)
+ abort();
+
+ pidfd = sys_pidfd_open(pid, 0);
+ ASSERT_GE(pidfd, 0);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_EQ(WTERMSIG(status), SIGABRT);
+ ASSERT_TRUE(WCOREDUMP(status));
+
+ ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP));
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL));
+ ASSERT_EQ(info.coredump_signal, SIGABRT);
+
+ wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_invalid_paths)
+{
+ ASSERT_FALSE(set_core_pattern("@ /tmp/coredump.socket"));
+ ASSERT_FALSE(set_core_pattern("@/tmp/../coredump.socket"));
+ ASSERT_FALSE(set_core_pattern("@../coredump.socket"));
+ ASSERT_FALSE(set_core_pattern("@/tmp/coredump.socket/.."));
+ ASSERT_FALSE(set_core_pattern("@.."));
+
+ ASSERT_FALSE(set_core_pattern("@@ /tmp/coredump.socket"));
+ ASSERT_FALSE(set_core_pattern("@@/tmp/../coredump.socket"));
+ ASSERT_FALSE(set_core_pattern("@@../coredump.socket"));
+ ASSERT_FALSE(set_core_pattern("@@/tmp/coredump.socket/.."));
+ ASSERT_FALSE(set_core_pattern("@@.."));
+
+ ASSERT_FALSE(set_core_pattern("@@@/tmp/coredump.socket"));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/coredump/coredump_test.h b/tools/testing/selftests/coredump/coredump_test.h
new file mode 100644
index 000000000000..ed47f01fa53c
--- /dev/null
+++ b/tools/testing/selftests/coredump/coredump_test.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __COREDUMP_TEST_H
+#define __COREDUMP_TEST_H
+
+#include <stdbool.h>
+#include <sys/types.h>
+#include <linux/coredump.h>
+
+#include "../kselftest_harness.h"
+#include "../pidfd/pidfd.h"
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE 4096
+#endif
+
+#define NUM_THREAD_SPAWN 128
+
+/* Coredump fixture */
+FIXTURE(coredump)
+{
+ char original_core_pattern[256];
+ pid_t pid_coredump_server;
+ int fd_tmpfs_detached;
+};
+
+/* Shared helper function declarations */
+void *do_nothing(void *arg);
+void crashing_child(void);
+int create_detached_tmpfs(void);
+int create_and_listen_unix_socket(const char *path);
+bool set_core_pattern(const char *pattern);
+int get_peer_pidfd(int fd);
+bool get_pidfd_info(int fd_peer_pidfd, struct pidfd_info *info);
+
+/* Inline helper that uses harness types */
+static inline void wait_and_check_coredump_server(pid_t pid_coredump_server,
+ struct __test_metadata *const _metadata,
+ FIXTURE_DATA(coredump) *self)
+{
+ int status;
+ waitpid(pid_coredump_server, &status, 0);
+ self->pid_coredump_server = -ESRCH;
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+}
+
+/* Protocol helper function declarations */
+ssize_t recv_marker(int fd);
+bool read_marker(int fd, enum coredump_mark mark);
+bool read_coredump_req(int fd, struct coredump_req *req);
+bool send_coredump_ack(int fd, const struct coredump_req *req,
+ __u64 mask, size_t size_ack);
+bool check_coredump_req(const struct coredump_req *req, size_t min_size,
+ __u64 required_mask);
+int open_coredump_tmpfile(int fd_tmpfs_detached);
+void process_coredump_worker(int fd_coredump, int fd_peer_pidfd, int fd_core_file);
+
+#endif /* __COREDUMP_TEST_H */
diff --git a/tools/testing/selftests/coredump/coredump_test_helpers.c b/tools/testing/selftests/coredump/coredump_test_helpers.c
new file mode 100644
index 000000000000..a6f6d5f2ae07
--- /dev/null
+++ b/tools/testing/selftests/coredump/coredump_test_helpers.c
@@ -0,0 +1,383 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/coredump.h>
+#include <linux/fs.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "../filesystems/wrappers.h"
+#include "../pidfd/pidfd.h"
+
+/* Forward declarations to avoid including harness header */
+struct __test_metadata;
+
+/* Match the fixture definition from coredump_test.h */
+struct _fixture_coredump_data {
+ char original_core_pattern[256];
+ pid_t pid_coredump_server;
+ int fd_tmpfs_detached;
+};
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE 4096
+#endif
+
+#define NUM_THREAD_SPAWN 128
+
+void *do_nothing(void *arg)
+{
+ (void)arg;
+ while (1)
+ pause();
+
+ return NULL;
+}
+
+void crashing_child(void)
+{
+ pthread_t thread;
+ int i;
+
+ for (i = 0; i < NUM_THREAD_SPAWN; ++i)
+ pthread_create(&thread, NULL, do_nothing, NULL);
+
+ /* crash on purpose */
+ i = *(int *)NULL;
+}
+
+int create_detached_tmpfs(void)
+{
+ int fd_context, fd_tmpfs;
+
+ fd_context = sys_fsopen("tmpfs", 0);
+ if (fd_context < 0)
+ return -1;
+
+ if (sys_fsconfig(fd_context, FSCONFIG_CMD_CREATE, NULL, NULL, 0) < 0)
+ return -1;
+
+ fd_tmpfs = sys_fsmount(fd_context, 0, 0);
+ close(fd_context);
+ return fd_tmpfs;
+}
+
+int create_and_listen_unix_socket(const char *path)
+{
+ struct sockaddr_un addr = {
+ .sun_family = AF_UNIX,
+ };
+ assert(strlen(path) < sizeof(addr.sun_path) - 1);
+ strncpy(addr.sun_path, path, sizeof(addr.sun_path) - 1);
+ size_t addr_len =
+ offsetof(struct sockaddr_un, sun_path) + strlen(path) + 1;
+ int fd, ret;
+
+ fd = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+ if (fd < 0)
+ goto out;
+
+ ret = bind(fd, (const struct sockaddr *)&addr, addr_len);
+ if (ret < 0)
+ goto out;
+
+ ret = listen(fd, 128);
+ if (ret < 0)
+ goto out;
+
+ return fd;
+
+out:
+ if (fd >= 0)
+ close(fd);
+ return -1;
+}
+
+bool set_core_pattern(const char *pattern)
+{
+ int fd;
+ ssize_t ret;
+
+ fd = open("/proc/sys/kernel/core_pattern", O_WRONLY | O_CLOEXEC);
+ if (fd < 0)
+ return false;
+
+ ret = write(fd, pattern, strlen(pattern));
+ close(fd);
+ if (ret < 0)
+ return false;
+
+ fprintf(stderr, "Set core_pattern to '%s' | %zu == %zu\n", pattern, ret, strlen(pattern));
+ return ret == strlen(pattern);
+}
+
+int get_peer_pidfd(int fd)
+{
+ int fd_peer_pidfd;
+ socklen_t fd_peer_pidfd_len = sizeof(fd_peer_pidfd);
+ int ret = getsockopt(fd, SOL_SOCKET, SO_PEERPIDFD, &fd_peer_pidfd,
+ &fd_peer_pidfd_len);
+ if (ret < 0) {
+ fprintf(stderr, "get_peer_pidfd: getsockopt(SO_PEERPIDFD) failed: %m\n");
+ return -1;
+ }
+ fprintf(stderr, "get_peer_pidfd: successfully retrieved pidfd %d\n", fd_peer_pidfd);
+ return fd_peer_pidfd;
+}
+
+bool get_pidfd_info(int fd_peer_pidfd, struct pidfd_info *info)
+{
+ int ret;
+ memset(info, 0, sizeof(*info));
+ info->mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP | PIDFD_INFO_COREDUMP_SIGNAL;
+ ret = ioctl(fd_peer_pidfd, PIDFD_GET_INFO, info);
+ if (ret < 0) {
+ fprintf(stderr, "get_pidfd_info: ioctl(PIDFD_GET_INFO) failed: %m\n");
+ return false;
+ }
+ fprintf(stderr, "get_pidfd_info: mask=0x%llx, coredump_mask=0x%x, coredump_signal=%d\n",
+ (unsigned long long)info->mask, info->coredump_mask, info->coredump_signal);
+ return true;
+}
+
+/* Protocol helper functions */
+
+ssize_t recv_marker(int fd)
+{
+ enum coredump_mark mark = COREDUMP_MARK_REQACK;
+ ssize_t ret;
+
+ ret = recv(fd, &mark, sizeof(mark), MSG_WAITALL);
+ if (ret != sizeof(mark))
+ return -1;
+
+ switch (mark) {
+ case COREDUMP_MARK_REQACK:
+ fprintf(stderr, "Received marker: ReqAck\n");
+ return COREDUMP_MARK_REQACK;
+ case COREDUMP_MARK_MINSIZE:
+ fprintf(stderr, "Received marker: MinSize\n");
+ return COREDUMP_MARK_MINSIZE;
+ case COREDUMP_MARK_MAXSIZE:
+ fprintf(stderr, "Received marker: MaxSize\n");
+ return COREDUMP_MARK_MAXSIZE;
+ case COREDUMP_MARK_UNSUPPORTED:
+ fprintf(stderr, "Received marker: Unsupported\n");
+ return COREDUMP_MARK_UNSUPPORTED;
+ case COREDUMP_MARK_CONFLICTING:
+ fprintf(stderr, "Received marker: Conflicting\n");
+ return COREDUMP_MARK_CONFLICTING;
+ default:
+ fprintf(stderr, "Received unknown marker: %u\n", mark);
+ break;
+ }
+ return -1;
+}
+
+bool read_marker(int fd, enum coredump_mark mark)
+{
+ ssize_t ret;
+
+ ret = recv_marker(fd);
+ if (ret < 0)
+ return false;
+ return ret == mark;
+}
+
+bool read_coredump_req(int fd, struct coredump_req *req)
+{
+ ssize_t ret;
+ size_t field_size, user_size, ack_size, kernel_size, remaining_size;
+
+ memset(req, 0, sizeof(*req));
+ field_size = sizeof(req->size);
+
+ /* Peek the size of the coredump request. */
+ ret = recv(fd, req, field_size, MSG_PEEK | MSG_WAITALL);
+ if (ret != field_size) {
+ fprintf(stderr, "read_coredump_req: peek failed (got %zd, expected %zu): %m\n",
+ ret, field_size);
+ return false;
+ }
+ kernel_size = req->size;
+
+ if (kernel_size < COREDUMP_ACK_SIZE_VER0) {
+ fprintf(stderr, "read_coredump_req: kernel_size %zu < min %d\n",
+ kernel_size, COREDUMP_ACK_SIZE_VER0);
+ return false;
+ }
+ if (kernel_size >= PAGE_SIZE) {
+ fprintf(stderr, "read_coredump_req: kernel_size %zu >= PAGE_SIZE %d\n",
+ kernel_size, PAGE_SIZE);
+ return false;
+ }
+
+ /* Use the minimum of user and kernel size to read the full request. */
+ user_size = sizeof(struct coredump_req);
+ ack_size = user_size < kernel_size ? user_size : kernel_size;
+ ret = recv(fd, req, ack_size, MSG_WAITALL);
+ if (ret != ack_size)
+ return false;
+
+ fprintf(stderr, "Read coredump request with size %u and mask 0x%llx\n",
+ req->size, (unsigned long long)req->mask);
+
+ if (user_size > kernel_size)
+ remaining_size = user_size - kernel_size;
+ else
+ remaining_size = kernel_size - user_size;
+
+ if (PAGE_SIZE <= remaining_size)
+ return false;
+
+ /*
+ * Discard any additional data if the kernel's request was larger than
+ * what we knew about or cared about.
+ */
+ if (remaining_size) {
+ char buffer[PAGE_SIZE];
+
+ ret = recv(fd, buffer, sizeof(buffer), MSG_WAITALL);
+ if (ret != remaining_size)
+ return false;
+ fprintf(stderr, "Discarded %zu bytes of data after coredump request\n", remaining_size);
+ }
+
+ return true;
+}
+
+bool send_coredump_ack(int fd, const struct coredump_req *req,
+ __u64 mask, size_t size_ack)
+{
+ ssize_t ret;
+ /*
+ * Wrap struct coredump_ack in a larger struct so we can
+ * simulate sending to much data to the kernel.
+ */
+ struct large_ack_for_size_testing {
+ struct coredump_ack ack;
+ char buffer[PAGE_SIZE];
+ } large_ack = {};
+
+ if (!size_ack)
+ size_ack = sizeof(struct coredump_ack) < req->size_ack ?
+ sizeof(struct coredump_ack) :
+ req->size_ack;
+ large_ack.ack.mask = mask;
+ large_ack.ack.size = size_ack;
+ ret = send(fd, &large_ack, size_ack, MSG_NOSIGNAL);
+ if (ret != size_ack)
+ return false;
+
+ fprintf(stderr, "Sent coredump ack with size %zu and mask 0x%llx\n",
+ size_ack, (unsigned long long)mask);
+ return true;
+}
+
+bool check_coredump_req(const struct coredump_req *req, size_t min_size,
+ __u64 required_mask)
+{
+ if (req->size < min_size)
+ return false;
+ if ((req->mask & required_mask) != required_mask)
+ return false;
+ if (req->mask & ~required_mask)
+ return false;
+ return true;
+}
+
+int open_coredump_tmpfile(int fd_tmpfs_detached)
+{
+ return openat(fd_tmpfs_detached, ".", O_TMPFILE | O_RDWR | O_EXCL, 0600);
+}
+
+void process_coredump_worker(int fd_coredump, int fd_peer_pidfd, int fd_core_file)
+{
+ int epfd = -1;
+ int exit_code = EXIT_FAILURE;
+ struct epoll_event ev;
+ int flags;
+
+ /* Set socket to non-blocking mode for edge-triggered epoll */
+ flags = fcntl(fd_coredump, F_GETFL, 0);
+ if (flags < 0) {
+ fprintf(stderr, "Worker: fcntl(F_GETFL) failed: %m\n");
+ goto out;
+ }
+ if (fcntl(fd_coredump, F_SETFL, flags | O_NONBLOCK) < 0) {
+ fprintf(stderr, "Worker: fcntl(F_SETFL, O_NONBLOCK) failed: %m\n");
+ goto out;
+ }
+
+ epfd = epoll_create1(0);
+ if (epfd < 0) {
+ fprintf(stderr, "Worker: epoll_create1() failed: %m\n");
+ goto out;
+ }
+
+ ev.events = EPOLLIN | EPOLLRDHUP | EPOLLET;
+ ev.data.fd = fd_coredump;
+ if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd_coredump, &ev) < 0) {
+ fprintf(stderr, "Worker: epoll_ctl(EPOLL_CTL_ADD) failed: %m\n");
+ goto out;
+ }
+
+ for (;;) {
+ struct epoll_event events[1];
+ int n = epoll_wait(epfd, events, 1, -1);
+ if (n < 0) {
+ fprintf(stderr, "Worker: epoll_wait() failed: %m\n");
+ break;
+ }
+
+ if (events[0].events & (EPOLLIN | EPOLLRDHUP)) {
+ for (;;) {
+ char buffer[4096];
+ ssize_t bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+ if (bytes_read < 0) {
+ if (errno == EAGAIN || errno == EWOULDBLOCK)
+ break;
+ fprintf(stderr, "Worker: read() failed: %m\n");
+ goto out;
+ }
+ if (bytes_read == 0)
+ goto done;
+ ssize_t bytes_write = write(fd_core_file, buffer, bytes_read);
+ if (bytes_write != bytes_read) {
+ if (bytes_write < 0 && errno == ENOSPC)
+ continue;
+ fprintf(stderr, "Worker: write() failed (read=%zd, write=%zd): %m\n",
+ bytes_read, bytes_write);
+ goto out;
+ }
+ }
+ }
+ }
+
+done:
+ exit_code = EXIT_SUCCESS;
+ fprintf(stderr, "Worker: completed successfully\n");
+out:
+ if (epfd >= 0)
+ close(epfd);
+ if (fd_core_file >= 0)
+ close(fd_core_file);
+ if (fd_peer_pidfd >= 0)
+ close(fd_peer_pidfd);
+ if (fd_coredump >= 0)
+ close(fd_coredump);
+ _exit(exit_code);
+}
diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c
index a4ac80bb1003..c2e895bcc160 100644
--- a/tools/testing/selftests/coredump/stackdump_test.c
+++ b/tools/testing/selftests/coredump/stackdump_test.c
@@ -23,57 +23,15 @@
#include "../filesystems/wrappers.h"
#include "../pidfd/pidfd.h"
+#include "coredump_test.h"
+
#define STACKDUMP_FILE "stack_values"
#define STACKDUMP_SCRIPT "stackdump"
-#define NUM_THREAD_SPAWN 128
#ifndef PAGE_SIZE
#define PAGE_SIZE 4096
#endif
-static void *do_nothing(void *)
-{
- while (1)
- pause();
-
- return NULL;
-}
-
-static void crashing_child(void)
-{
- pthread_t thread;
- int i;
-
- for (i = 0; i < NUM_THREAD_SPAWN; ++i)
- pthread_create(&thread, NULL, do_nothing, NULL);
-
- /* crash on purpose */
- i = *(int *)NULL;
-}
-
-FIXTURE(coredump)
-{
- char original_core_pattern[256];
- pid_t pid_coredump_server;
- int fd_tmpfs_detached;
-};
-
-static int create_detached_tmpfs(void)
-{
- int fd_context, fd_tmpfs;
-
- fd_context = sys_fsopen("tmpfs", 0);
- if (fd_context < 0)
- return -1;
-
- if (sys_fsconfig(fd_context, FSCONFIG_CMD_CREATE, NULL, NULL, 0) < 0)
- return -1;
-
- fd_tmpfs = sys_fsmount(fd_context, 0, 0);
- close(fd_context);
- return fd_tmpfs;
-}
-
FIXTURE_SETUP(coredump)
{
FILE *file;
@@ -208,1620 +166,4 @@ TEST_F_TIMEOUT(coredump, stackdump, 120)
fclose(file);
}
-static int create_and_listen_unix_socket(const char *path)
-{
- struct sockaddr_un addr = {
- .sun_family = AF_UNIX,
- };
- assert(strlen(path) < sizeof(addr.sun_path) - 1);
- strncpy(addr.sun_path, path, sizeof(addr.sun_path) - 1);
- size_t addr_len =
- offsetof(struct sockaddr_un, sun_path) + strlen(path) + 1;
- int fd, ret;
-
- fd = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
- if (fd < 0)
- goto out;
-
- ret = bind(fd, (const struct sockaddr *)&addr, addr_len);
- if (ret < 0)
- goto out;
-
- ret = listen(fd, 128);
- if (ret < 0)
- goto out;
-
- return fd;
-
-out:
- if (fd >= 0)
- close(fd);
- return -1;
-}
-
-static bool set_core_pattern(const char *pattern)
-{
- int fd;
- ssize_t ret;
-
- fd = open("/proc/sys/kernel/core_pattern", O_WRONLY | O_CLOEXEC);
- if (fd < 0)
- return false;
-
- ret = write(fd, pattern, strlen(pattern));
- close(fd);
- if (ret < 0)
- return false;
-
- fprintf(stderr, "Set core_pattern to '%s' | %zu == %zu\n", pattern, ret, strlen(pattern));
- return ret == strlen(pattern);
-}
-
-static int get_peer_pidfd(int fd)
-{
- int fd_peer_pidfd;
- socklen_t fd_peer_pidfd_len = sizeof(fd_peer_pidfd);
- int ret = getsockopt(fd, SOL_SOCKET, SO_PEERPIDFD, &fd_peer_pidfd,
- &fd_peer_pidfd_len);
- if (ret < 0) {
- fprintf(stderr, "%m - Failed to retrieve peer pidfd for coredump socket connection\n");
- return -1;
- }
- return fd_peer_pidfd;
-}
-
-static bool get_pidfd_info(int fd_peer_pidfd, struct pidfd_info *info)
-{
- memset(info, 0, sizeof(*info));
- info->mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
- return ioctl(fd_peer_pidfd, PIDFD_GET_INFO, info) == 0;
-}
-
-static void
-wait_and_check_coredump_server(pid_t pid_coredump_server,
- struct __test_metadata *const _metadata,
- FIXTURE_DATA(coredump)* self)
-{
- int status;
- waitpid(pid_coredump_server, &status, 0);
- self->pid_coredump_server = -ESRCH;
- ASSERT_TRUE(WIFEXITED(status));
- ASSERT_EQ(WEXITSTATUS(status), 0);
-}
-
-TEST_F(coredump, socket)
-{
- int pidfd, ret, status;
- pid_t pid, pid_coredump_server;
- struct stat st;
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
-
- ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
- ASSERT_EQ(ret, 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
- int exit_code = EXIT_FAILURE;
-
- close(ipc_sockets[0]);
-
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
-
- close(ipc_sockets[1]);
-
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0)
- goto out;
-
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0)
- goto out;
-
- if (!get_pidfd_info(fd_peer_pidfd, &info))
- goto out;
-
- if (!(info.mask & PIDFD_INFO_COREDUMP))
- goto out;
-
- if (!(info.coredump_mask & PIDFD_COREDUMPED))
- goto out;
-
- fd_core_file = creat("/tmp/coredump.file", 0644);
- if (fd_core_file < 0)
- goto out;
-
- for (;;) {
- char buffer[4096];
- ssize_t bytes_read, bytes_write;
-
- bytes_read = read(fd_coredump, buffer, sizeof(buffer));
- if (bytes_read < 0)
- goto out;
-
- if (bytes_read == 0)
- break;
-
- bytes_write = write(fd_core_file, buffer, bytes_read);
- if (bytes_read != bytes_write)
- goto out;
- }
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_core_file >= 0)
- close(fd_core_file);
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_server >= 0)
- close(fd_server);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0)
- crashing_child();
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFSIGNALED(status));
- ASSERT_TRUE(WCOREDUMP(status));
-
- ASSERT_TRUE(get_pidfd_info(pidfd, &info));
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-
- ASSERT_EQ(stat("/tmp/coredump.file", &st), 0);
- ASSERT_GT(st.st_size, 0);
- system("file /tmp/coredump.file");
-}
-
-TEST_F(coredump, socket_detect_userspace_client)
-{
- int pidfd, ret, status;
- pid_t pid, pid_coredump_server;
- struct stat st;
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
-
- ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
- ASSERT_EQ(ret, 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
- int exit_code = EXIT_FAILURE;
-
- close(ipc_sockets[0]);
-
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
-
- close(ipc_sockets[1]);
-
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0)
- goto out;
-
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0)
- goto out;
-
- if (!get_pidfd_info(fd_peer_pidfd, &info))
- goto out;
-
- if (!(info.mask & PIDFD_INFO_COREDUMP))
- goto out;
-
- if (info.coredump_mask & PIDFD_COREDUMPED)
- goto out;
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_server >= 0)
- close(fd_server);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0) {
- int fd_socket;
- ssize_t ret;
- const struct sockaddr_un coredump_sk = {
- .sun_family = AF_UNIX,
- .sun_path = "/tmp/coredump.socket",
- };
- size_t coredump_sk_len =
- offsetof(struct sockaddr_un, sun_path) +
- sizeof("/tmp/coredump.socket");
-
- fd_socket = socket(AF_UNIX, SOCK_STREAM, 0);
- if (fd_socket < 0)
- _exit(EXIT_FAILURE);
-
- ret = connect(fd_socket, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
- if (ret < 0)
- _exit(EXIT_FAILURE);
-
- close(fd_socket);
- _exit(EXIT_SUCCESS);
- }
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFEXITED(status));
- ASSERT_EQ(WEXITSTATUS(status), 0);
-
- ASSERT_TRUE(get_pidfd_info(pidfd, &info));
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_EQ((info.coredump_mask & PIDFD_COREDUMPED), 0);
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-
- ASSERT_NE(stat("/tmp/coredump.file", &st), 0);
- ASSERT_EQ(errno, ENOENT);
-}
-
-TEST_F(coredump, socket_enoent)
-{
- int pidfd, status;
- pid_t pid;
-
- ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0)
- crashing_child();
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFSIGNALED(status));
- ASSERT_FALSE(WCOREDUMP(status));
-}
-
-TEST_F(coredump, socket_no_listener)
-{
- int pidfd, ret, status;
- pid_t pid, pid_coredump_server;
- int ipc_sockets[2];
- char c;
- const struct sockaddr_un coredump_sk = {
- .sun_family = AF_UNIX,
- .sun_path = "/tmp/coredump.socket",
- };
- size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) +
- sizeof("/tmp/coredump.socket");
-
- ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
-
- ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
- ASSERT_EQ(ret, 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- int fd_server = -1;
- int exit_code = EXIT_FAILURE;
-
- close(ipc_sockets[0]);
-
- fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
- if (fd_server < 0)
- goto out;
-
- ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
- if (ret < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_server >= 0)
- close(fd_server);
- close(ipc_sockets[1]);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0)
- crashing_child();
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFSIGNALED(status));
- ASSERT_FALSE(WCOREDUMP(status));
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-}
-
-static ssize_t recv_marker(int fd)
-{
- enum coredump_mark mark = COREDUMP_MARK_REQACK;
- ssize_t ret;
-
- ret = recv(fd, &mark, sizeof(mark), MSG_WAITALL);
- if (ret != sizeof(mark))
- return -1;
-
- switch (mark) {
- case COREDUMP_MARK_REQACK:
- fprintf(stderr, "Received marker: ReqAck\n");
- return COREDUMP_MARK_REQACK;
- case COREDUMP_MARK_MINSIZE:
- fprintf(stderr, "Received marker: MinSize\n");
- return COREDUMP_MARK_MINSIZE;
- case COREDUMP_MARK_MAXSIZE:
- fprintf(stderr, "Received marker: MaxSize\n");
- return COREDUMP_MARK_MAXSIZE;
- case COREDUMP_MARK_UNSUPPORTED:
- fprintf(stderr, "Received marker: Unsupported\n");
- return COREDUMP_MARK_UNSUPPORTED;
- case COREDUMP_MARK_CONFLICTING:
- fprintf(stderr, "Received marker: Conflicting\n");
- return COREDUMP_MARK_CONFLICTING;
- default:
- fprintf(stderr, "Received unknown marker: %u\n", mark);
- break;
- }
- return -1;
-}
-
-static bool read_marker(int fd, enum coredump_mark mark)
-{
- ssize_t ret;
-
- ret = recv_marker(fd);
- if (ret < 0)
- return false;
- return ret == mark;
-}
-
-static bool read_coredump_req(int fd, struct coredump_req *req)
-{
- ssize_t ret;
- size_t field_size, user_size, ack_size, kernel_size, remaining_size;
-
- memset(req, 0, sizeof(*req));
- field_size = sizeof(req->size);
-
- /* Peek the size of the coredump request. */
- ret = recv(fd, req, field_size, MSG_PEEK | MSG_WAITALL);
- if (ret != field_size)
- return false;
- kernel_size = req->size;
-
- if (kernel_size < COREDUMP_ACK_SIZE_VER0)
- return false;
- if (kernel_size >= PAGE_SIZE)
- return false;
-
- /* Use the minimum of user and kernel size to read the full request. */
- user_size = sizeof(struct coredump_req);
- ack_size = user_size < kernel_size ? user_size : kernel_size;
- ret = recv(fd, req, ack_size, MSG_WAITALL);
- if (ret != ack_size)
- return false;
-
- fprintf(stderr, "Read coredump request with size %u and mask 0x%llx\n",
- req->size, (unsigned long long)req->mask);
-
- if (user_size > kernel_size)
- remaining_size = user_size - kernel_size;
- else
- remaining_size = kernel_size - user_size;
-
- if (PAGE_SIZE <= remaining_size)
- return false;
-
- /*
- * Discard any additional data if the kernel's request was larger than
- * what we knew about or cared about.
- */
- if (remaining_size) {
- char buffer[PAGE_SIZE];
-
- ret = recv(fd, buffer, sizeof(buffer), MSG_WAITALL);
- if (ret != remaining_size)
- return false;
- fprintf(stderr, "Discarded %zu bytes of data after coredump request\n", remaining_size);
- }
-
- return true;
-}
-
-static bool send_coredump_ack(int fd, const struct coredump_req *req,
- __u64 mask, size_t size_ack)
-{
- ssize_t ret;
- /*
- * Wrap struct coredump_ack in a larger struct so we can
- * simulate sending to much data to the kernel.
- */
- struct large_ack_for_size_testing {
- struct coredump_ack ack;
- char buffer[PAGE_SIZE];
- } large_ack = {};
-
- if (!size_ack)
- size_ack = sizeof(struct coredump_ack) < req->size_ack ?
- sizeof(struct coredump_ack) :
- req->size_ack;
- large_ack.ack.mask = mask;
- large_ack.ack.size = size_ack;
- ret = send(fd, &large_ack, size_ack, MSG_NOSIGNAL);
- if (ret != size_ack)
- return false;
-
- fprintf(stderr, "Sent coredump ack with size %zu and mask 0x%llx\n",
- size_ack, (unsigned long long)mask);
- return true;
-}
-
-static bool check_coredump_req(const struct coredump_req *req, size_t min_size,
- __u64 required_mask)
-{
- if (req->size < min_size)
- return false;
- if ((req->mask & required_mask) != required_mask)
- return false;
- if (req->mask & ~required_mask)
- return false;
- return true;
-}
-
-TEST_F(coredump, socket_request_kernel)
-{
- int pidfd, ret, status;
- pid_t pid, pid_coredump_server;
- struct stat st;
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
-
- ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
- ASSERT_EQ(ret, 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- struct coredump_req req = {};
- int fd_server = -1, fd_coredump = -1, fd_core_file = -1, fd_peer_pidfd = -1;
- int exit_code = EXIT_FAILURE;
-
- close(ipc_sockets[0]);
-
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
-
- close(ipc_sockets[1]);
-
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0)
- goto out;
-
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0)
- goto out;
-
- if (!get_pidfd_info(fd_peer_pidfd, &info))
- goto out;
-
- if (!(info.mask & PIDFD_INFO_COREDUMP))
- goto out;
-
- if (!(info.coredump_mask & PIDFD_COREDUMPED))
- goto out;
-
- fd_core_file = creat("/tmp/coredump.file", 0644);
- if (fd_core_file < 0)
- goto out;
-
- if (!read_coredump_req(fd_coredump, &req))
- goto out;
-
- if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
- COREDUMP_KERNEL | COREDUMP_USERSPACE |
- COREDUMP_REJECT | COREDUMP_WAIT))
- goto out;
-
- if (!send_coredump_ack(fd_coredump, &req,
- COREDUMP_KERNEL | COREDUMP_WAIT, 0))
- goto out;
-
- if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK))
- goto out;
-
- for (;;) {
- char buffer[4096];
- ssize_t bytes_read, bytes_write;
-
- bytes_read = read(fd_coredump, buffer, sizeof(buffer));
- if (bytes_read < 0)
- goto out;
-
- if (bytes_read == 0)
- break;
-
- bytes_write = write(fd_core_file, buffer, bytes_read);
- if (bytes_read != bytes_write)
- goto out;
- }
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_core_file >= 0)
- close(fd_core_file);
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_server >= 0)
- close(fd_server);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0)
- crashing_child();
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFSIGNALED(status));
- ASSERT_TRUE(WCOREDUMP(status));
-
- ASSERT_TRUE(get_pidfd_info(pidfd, &info));
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-
- ASSERT_EQ(stat("/tmp/coredump.file", &st), 0);
- ASSERT_GT(st.st_size, 0);
- system("file /tmp/coredump.file");
-}
-
-TEST_F(coredump, socket_request_userspace)
-{
- int pidfd, ret, status;
- pid_t pid, pid_coredump_server;
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
-
- ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
- ASSERT_EQ(ret, 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- struct coredump_req req = {};
- int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
- int exit_code = EXIT_FAILURE;
-
- close(ipc_sockets[0]);
-
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
-
- close(ipc_sockets[1]);
-
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0)
- goto out;
-
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0)
- goto out;
-
- if (!get_pidfd_info(fd_peer_pidfd, &info))
- goto out;
-
- if (!(info.mask & PIDFD_INFO_COREDUMP))
- goto out;
-
- if (!(info.coredump_mask & PIDFD_COREDUMPED))
- goto out;
-
- if (!read_coredump_req(fd_coredump, &req))
- goto out;
-
- if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
- COREDUMP_KERNEL | COREDUMP_USERSPACE |
- COREDUMP_REJECT | COREDUMP_WAIT))
- goto out;
-
- if (!send_coredump_ack(fd_coredump, &req,
- COREDUMP_USERSPACE | COREDUMP_WAIT, 0))
- goto out;
-
- if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK))
- goto out;
-
- for (;;) {
- char buffer[4096];
- ssize_t bytes_read;
-
- bytes_read = read(fd_coredump, buffer, sizeof(buffer));
- if (bytes_read > 0)
- goto out;
-
- if (bytes_read < 0)
- goto out;
-
- if (bytes_read == 0)
- break;
- }
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_server >= 0)
- close(fd_server);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0)
- crashing_child();
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFSIGNALED(status));
- ASSERT_TRUE(WCOREDUMP(status));
-
- ASSERT_TRUE(get_pidfd_info(pidfd, &info));
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-}
-
-TEST_F(coredump, socket_request_reject)
-{
- int pidfd, ret, status;
- pid_t pid, pid_coredump_server;
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
-
- ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
- ASSERT_EQ(ret, 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- struct coredump_req req = {};
- int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
- int exit_code = EXIT_FAILURE;
-
- close(ipc_sockets[0]);
-
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
-
- close(ipc_sockets[1]);
-
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0)
- goto out;
-
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0)
- goto out;
-
- if (!get_pidfd_info(fd_peer_pidfd, &info))
- goto out;
-
- if (!(info.mask & PIDFD_INFO_COREDUMP))
- goto out;
-
- if (!(info.coredump_mask & PIDFD_COREDUMPED))
- goto out;
-
- if (!read_coredump_req(fd_coredump, &req))
- goto out;
-
- if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
- COREDUMP_KERNEL | COREDUMP_USERSPACE |
- COREDUMP_REJECT | COREDUMP_WAIT))
- goto out;
-
- if (!send_coredump_ack(fd_coredump, &req,
- COREDUMP_REJECT | COREDUMP_WAIT, 0))
- goto out;
-
- if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK))
- goto out;
-
- for (;;) {
- char buffer[4096];
- ssize_t bytes_read;
-
- bytes_read = read(fd_coredump, buffer, sizeof(buffer));
- if (bytes_read > 0)
- goto out;
-
- if (bytes_read < 0)
- goto out;
-
- if (bytes_read == 0)
- break;
- }
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_server >= 0)
- close(fd_server);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0)
- crashing_child();
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFSIGNALED(status));
- ASSERT_FALSE(WCOREDUMP(status));
-
- ASSERT_TRUE(get_pidfd_info(pidfd, &info));
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-}
-
-TEST_F(coredump, socket_request_invalid_flag_combination)
-{
- int pidfd, ret, status;
- pid_t pid, pid_coredump_server;
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
-
- ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
- ASSERT_EQ(ret, 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- struct coredump_req req = {};
- int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
- int exit_code = EXIT_FAILURE;
-
- close(ipc_sockets[0]);
-
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
-
- close(ipc_sockets[1]);
-
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0)
- goto out;
-
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0)
- goto out;
-
- if (!get_pidfd_info(fd_peer_pidfd, &info))
- goto out;
-
- if (!(info.mask & PIDFD_INFO_COREDUMP))
- goto out;
-
- if (!(info.coredump_mask & PIDFD_COREDUMPED))
- goto out;
-
- if (!read_coredump_req(fd_coredump, &req))
- goto out;
-
- if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
- COREDUMP_KERNEL | COREDUMP_USERSPACE |
- COREDUMP_REJECT | COREDUMP_WAIT))
- goto out;
-
- if (!send_coredump_ack(fd_coredump, &req,
- COREDUMP_KERNEL | COREDUMP_REJECT | COREDUMP_WAIT, 0))
- goto out;
-
- if (!read_marker(fd_coredump, COREDUMP_MARK_CONFLICTING))
- goto out;
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_server >= 0)
- close(fd_server);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0)
- crashing_child();
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFSIGNALED(status));
- ASSERT_FALSE(WCOREDUMP(status));
-
- ASSERT_TRUE(get_pidfd_info(pidfd, &info));
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-}
-
-TEST_F(coredump, socket_request_unknown_flag)
-{
- int pidfd, ret, status;
- pid_t pid, pid_coredump_server;
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
-
- ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
- ASSERT_EQ(ret, 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- struct coredump_req req = {};
- int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
- int exit_code = EXIT_FAILURE;
-
- close(ipc_sockets[0]);
-
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
-
- close(ipc_sockets[1]);
-
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0)
- goto out;
-
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0)
- goto out;
-
- if (!get_pidfd_info(fd_peer_pidfd, &info))
- goto out;
-
- if (!(info.mask & PIDFD_INFO_COREDUMP))
- goto out;
-
- if (!(info.coredump_mask & PIDFD_COREDUMPED))
- goto out;
-
- if (!read_coredump_req(fd_coredump, &req))
- goto out;
-
- if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
- COREDUMP_KERNEL | COREDUMP_USERSPACE |
- COREDUMP_REJECT | COREDUMP_WAIT))
- goto out;
-
- if (!send_coredump_ack(fd_coredump, &req, (1ULL << 63), 0))
- goto out;
-
- if (!read_marker(fd_coredump, COREDUMP_MARK_UNSUPPORTED))
- goto out;
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_server >= 0)
- close(fd_server);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0)
- crashing_child();
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFSIGNALED(status));
- ASSERT_FALSE(WCOREDUMP(status));
-
- ASSERT_TRUE(get_pidfd_info(pidfd, &info));
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-}
-
-TEST_F(coredump, socket_request_invalid_size_small)
-{
- int pidfd, ret, status;
- pid_t pid, pid_coredump_server;
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
-
- ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
- ASSERT_EQ(ret, 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- struct coredump_req req = {};
- int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
- int exit_code = EXIT_FAILURE;
-
- close(ipc_sockets[0]);
-
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
-
- close(ipc_sockets[1]);
-
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0)
- goto out;
-
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0)
- goto out;
-
- if (!get_pidfd_info(fd_peer_pidfd, &info))
- goto out;
-
- if (!(info.mask & PIDFD_INFO_COREDUMP))
- goto out;
-
- if (!(info.coredump_mask & PIDFD_COREDUMPED))
- goto out;
-
- if (!read_coredump_req(fd_coredump, &req))
- goto out;
-
- if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
- COREDUMP_KERNEL | COREDUMP_USERSPACE |
- COREDUMP_REJECT | COREDUMP_WAIT))
- goto out;
-
- if (!send_coredump_ack(fd_coredump, &req,
- COREDUMP_REJECT | COREDUMP_WAIT,
- COREDUMP_ACK_SIZE_VER0 / 2))
- goto out;
-
- if (!read_marker(fd_coredump, COREDUMP_MARK_MINSIZE))
- goto out;
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_server >= 0)
- close(fd_server);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0)
- crashing_child();
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFSIGNALED(status));
- ASSERT_FALSE(WCOREDUMP(status));
-
- ASSERT_TRUE(get_pidfd_info(pidfd, &info));
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-}
-
-TEST_F(coredump, socket_request_invalid_size_large)
-{
- int pidfd, ret, status;
- pid_t pid, pid_coredump_server;
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
-
- ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
- ASSERT_EQ(ret, 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- struct coredump_req req = {};
- int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
- int exit_code = EXIT_FAILURE;
-
- close(ipc_sockets[0]);
-
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
-
- close(ipc_sockets[1]);
-
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0)
- goto out;
-
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0)
- goto out;
-
- if (!get_pidfd_info(fd_peer_pidfd, &info))
- goto out;
-
- if (!(info.mask & PIDFD_INFO_COREDUMP))
- goto out;
-
- if (!(info.coredump_mask & PIDFD_COREDUMPED))
- goto out;
-
- if (!read_coredump_req(fd_coredump, &req))
- goto out;
-
- if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
- COREDUMP_KERNEL | COREDUMP_USERSPACE |
- COREDUMP_REJECT | COREDUMP_WAIT))
- goto out;
-
- if (!send_coredump_ack(fd_coredump, &req,
- COREDUMP_REJECT | COREDUMP_WAIT,
- COREDUMP_ACK_SIZE_VER0 + PAGE_SIZE))
- goto out;
-
- if (!read_marker(fd_coredump, COREDUMP_MARK_MAXSIZE))
- goto out;
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_server >= 0)
- close(fd_server);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- pid = fork();
- ASSERT_GE(pid, 0);
- if (pid == 0)
- crashing_child();
-
- pidfd = sys_pidfd_open(pid, 0);
- ASSERT_GE(pidfd, 0);
-
- waitpid(pid, &status, 0);
- ASSERT_TRUE(WIFSIGNALED(status));
- ASSERT_FALSE(WCOREDUMP(status));
-
- ASSERT_TRUE(get_pidfd_info(pidfd, &info));
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-}
-
-static int open_coredump_tmpfile(int fd_tmpfs_detached)
-{
- return openat(fd_tmpfs_detached, ".", O_TMPFILE | O_RDWR | O_EXCL, 0600);
-}
-
-#define NUM_CRASHING_COREDUMPS 5
-
-TEST_F_TIMEOUT(coredump, socket_multiple_crashing_coredumps, 500)
-{
- int pidfd[NUM_CRASHING_COREDUMPS], status[NUM_CRASHING_COREDUMPS];
- pid_t pid[NUM_CRASHING_COREDUMPS], pid_coredump_server;
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
-
- ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
- int exit_code = EXIT_FAILURE;
- struct coredump_req req = {};
-
- close(ipc_sockets[0]);
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0) {
- fprintf(stderr, "Failed to create and listen on unix socket\n");
- goto out;
- }
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
- fprintf(stderr, "Failed to notify parent via ipc socket\n");
- goto out;
- }
- close(ipc_sockets[1]);
-
- for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0) {
- fprintf(stderr, "accept4 failed: %m\n");
- goto out;
- }
-
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0) {
- fprintf(stderr, "get_peer_pidfd failed for fd %d: %m\n", fd_coredump);
- goto out;
- }
-
- if (!get_pidfd_info(fd_peer_pidfd, &info)) {
- fprintf(stderr, "get_pidfd_info failed for fd %d\n", fd_peer_pidfd);
- goto out;
- }
-
- if (!(info.mask & PIDFD_INFO_COREDUMP)) {
- fprintf(stderr, "pidfd info missing PIDFD_INFO_COREDUMP for fd %d\n", fd_peer_pidfd);
- goto out;
- }
- if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
- fprintf(stderr, "pidfd info missing PIDFD_COREDUMPED for fd %d\n", fd_peer_pidfd);
- goto out;
- }
-
- if (!read_coredump_req(fd_coredump, &req)) {
- fprintf(stderr, "read_coredump_req failed for fd %d\n", fd_coredump);
- goto out;
- }
-
- if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
- COREDUMP_KERNEL | COREDUMP_USERSPACE |
- COREDUMP_REJECT | COREDUMP_WAIT)) {
- fprintf(stderr, "check_coredump_req failed for fd %d\n", fd_coredump);
- goto out;
- }
-
- if (!send_coredump_ack(fd_coredump, &req,
- COREDUMP_KERNEL | COREDUMP_WAIT, 0)) {
- fprintf(stderr, "send_coredump_ack failed for fd %d\n", fd_coredump);
- goto out;
- }
-
- if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
- fprintf(stderr, "read_marker failed for fd %d\n", fd_coredump);
- goto out;
- }
-
- fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
- if (fd_core_file < 0) {
- fprintf(stderr, "%m - open_coredump_tmpfile failed for fd %d\n", fd_coredump);
- goto out;
- }
-
- for (;;) {
- char buffer[4096];
- ssize_t bytes_read, bytes_write;
-
- bytes_read = read(fd_coredump, buffer, sizeof(buffer));
- if (bytes_read < 0) {
- fprintf(stderr, "read failed for fd %d: %m\n", fd_coredump);
- goto out;
- }
-
- if (bytes_read == 0)
- break;
-
- bytes_write = write(fd_core_file, buffer, bytes_read);
- if (bytes_read != bytes_write) {
- fprintf(stderr, "write failed for fd %d: %m\n", fd_core_file);
- goto out;
- }
- }
-
- close(fd_core_file);
- close(fd_peer_pidfd);
- close(fd_coredump);
- fd_peer_pidfd = -1;
- fd_coredump = -1;
- }
-
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_core_file >= 0)
- close(fd_core_file);
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_server >= 0)
- close(fd_server);
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
- pid[i] = fork();
- ASSERT_GE(pid[i], 0);
- if (pid[i] == 0)
- crashing_child();
- pidfd[i] = sys_pidfd_open(pid[i], 0);
- ASSERT_GE(pidfd[i], 0);
- }
-
- for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
- waitpid(pid[i], &status[i], 0);
- ASSERT_TRUE(WIFSIGNALED(status[i]));
- ASSERT_TRUE(WCOREDUMP(status[i]));
- }
-
- for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
- info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
- ASSERT_EQ(ioctl(pidfd[i], PIDFD_GET_INFO, &info), 0);
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
- }
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-}
-
-#define MAX_EVENTS 128
-
-static void process_coredump_worker(int fd_coredump, int fd_peer_pidfd, int fd_core_file)
-{
- int epfd = -1;
- int exit_code = EXIT_FAILURE;
-
- epfd = epoll_create1(0);
- if (epfd < 0)
- goto out;
-
- struct epoll_event ev;
- ev.events = EPOLLIN | EPOLLRDHUP | EPOLLET;
- ev.data.fd = fd_coredump;
- if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd_coredump, &ev) < 0)
- goto out;
-
- for (;;) {
- struct epoll_event events[1];
- int n = epoll_wait(epfd, events, 1, -1);
- if (n < 0)
- break;
-
- if (events[0].events & (EPOLLIN | EPOLLRDHUP)) {
- for (;;) {
- char buffer[4096];
- ssize_t bytes_read = read(fd_coredump, buffer, sizeof(buffer));
- if (bytes_read < 0) {
- if (errno == EAGAIN || errno == EWOULDBLOCK)
- break;
- goto out;
- }
- if (bytes_read == 0)
- goto done;
- ssize_t bytes_write = write(fd_core_file, buffer, bytes_read);
- if (bytes_write != bytes_read)
- goto out;
- }
- }
- }
-
-done:
- exit_code = EXIT_SUCCESS;
-out:
- if (epfd >= 0)
- close(epfd);
- if (fd_core_file >= 0)
- close(fd_core_file);
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_coredump >= 0)
- close(fd_coredump);
- _exit(exit_code);
-}
-
-TEST_F_TIMEOUT(coredump, socket_multiple_crashing_coredumps_epoll_workers, 500)
-{
- int pidfd[NUM_CRASHING_COREDUMPS], status[NUM_CRASHING_COREDUMPS];
- pid_t pid[NUM_CRASHING_COREDUMPS], pid_coredump_server, worker_pids[NUM_CRASHING_COREDUMPS];
- struct pidfd_info info = {};
- int ipc_sockets[2];
- char c;
-
- ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
- ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
-
- pid_coredump_server = fork();
- ASSERT_GE(pid_coredump_server, 0);
- if (pid_coredump_server == 0) {
- int fd_server = -1, exit_code = EXIT_FAILURE, n_conns = 0;
- fd_server = -1;
- exit_code = EXIT_FAILURE;
- n_conns = 0;
- close(ipc_sockets[0]);
- fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
- if (fd_server < 0)
- goto out;
-
- if (write_nointr(ipc_sockets[1], "1", 1) < 0)
- goto out;
- close(ipc_sockets[1]);
-
- while (n_conns < NUM_CRASHING_COREDUMPS) {
- int fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
- struct coredump_req req = {};
- fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
- if (fd_coredump < 0) {
- if (errno == EAGAIN || errno == EWOULDBLOCK)
- continue;
- goto out;
- }
- fd_peer_pidfd = get_peer_pidfd(fd_coredump);
- if (fd_peer_pidfd < 0)
- goto out;
- if (!get_pidfd_info(fd_peer_pidfd, &info))
- goto out;
- if (!(info.mask & PIDFD_INFO_COREDUMP) || !(info.coredump_mask & PIDFD_COREDUMPED))
- goto out;
- if (!read_coredump_req(fd_coredump, &req))
- goto out;
- if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
- COREDUMP_KERNEL | COREDUMP_USERSPACE |
- COREDUMP_REJECT | COREDUMP_WAIT))
- goto out;
- if (!send_coredump_ack(fd_coredump, &req, COREDUMP_KERNEL | COREDUMP_WAIT, 0))
- goto out;
- if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK))
- goto out;
- fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
- if (fd_core_file < 0)
- goto out;
- pid_t worker = fork();
- if (worker == 0) {
- close(fd_server);
- process_coredump_worker(fd_coredump, fd_peer_pidfd, fd_core_file);
- }
- worker_pids[n_conns] = worker;
- if (fd_coredump >= 0)
- close(fd_coredump);
- if (fd_peer_pidfd >= 0)
- close(fd_peer_pidfd);
- if (fd_core_file >= 0)
- close(fd_core_file);
- n_conns++;
- }
- exit_code = EXIT_SUCCESS;
-out:
- if (fd_server >= 0)
- close(fd_server);
-
- // Reap all worker processes
- for (int i = 0; i < n_conns; i++) {
- int wstatus;
- if (waitpid(worker_pids[i], &wstatus, 0) < 0) {
- fprintf(stderr, "Failed to wait for worker %d: %m\n", worker_pids[i]);
- } else if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) != EXIT_SUCCESS) {
- fprintf(stderr, "Worker %d exited with error code %d\n", worker_pids[i], WEXITSTATUS(wstatus));
- exit_code = EXIT_FAILURE;
- }
- }
-
- _exit(exit_code);
- }
- self->pid_coredump_server = pid_coredump_server;
-
- EXPECT_EQ(close(ipc_sockets[1]), 0);
- ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
- EXPECT_EQ(close(ipc_sockets[0]), 0);
-
- for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
- pid[i] = fork();
- ASSERT_GE(pid[i], 0);
- if (pid[i] == 0)
- crashing_child();
- pidfd[i] = sys_pidfd_open(pid[i], 0);
- ASSERT_GE(pidfd[i], 0);
- }
-
- for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
- ASSERT_GE(waitpid(pid[i], &status[i], 0), 0);
- ASSERT_TRUE(WIFSIGNALED(status[i]));
- ASSERT_TRUE(WCOREDUMP(status[i]));
- }
-
- for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
- info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
- ASSERT_EQ(ioctl(pidfd[i], PIDFD_GET_INFO, &info), 0);
- ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
- ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
- }
-
- wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
-}
-
-TEST_F(coredump, socket_invalid_paths)
-{
- ASSERT_FALSE(set_core_pattern("@ /tmp/coredump.socket"));
- ASSERT_FALSE(set_core_pattern("@/tmp/../coredump.socket"));
- ASSERT_FALSE(set_core_pattern("@../coredump.socket"));
- ASSERT_FALSE(set_core_pattern("@/tmp/coredump.socket/.."));
- ASSERT_FALSE(set_core_pattern("@.."));
-
- ASSERT_FALSE(set_core_pattern("@@ /tmp/coredump.socket"));
- ASSERT_FALSE(set_core_pattern("@@/tmp/../coredump.socket"));
- ASSERT_FALSE(set_core_pattern("@@../coredump.socket"));
- ASSERT_FALSE(set_core_pattern("@@/tmp/coredump.socket/.."));
- ASSERT_FALSE(set_core_pattern("@@.."));
-
- ASSERT_FALSE(set_core_pattern("@@@/tmp/coredump.socket"));
-}
-
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c
index b12f1f9babf8..b925756373ce 100644
--- a/tools/testing/selftests/dma/dma_map_benchmark.c
+++ b/tools/testing/selftests/dma/dma_map_benchmark.c
@@ -118,7 +118,7 @@ int main(int argc, char **argv)
}
printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule: %d\n",
- threads, seconds, node, dir[directions], granule);
+ threads, seconds, node, directions[dir], granule);
printf("average map latency(us):%.1f standard deviation:%.1f\n",
map.avg_map_100ns/10.0, map.map_stddev/10.0);
printf("average unmap latency(us):%.1f standard deviation:%.1f\n",
diff --git a/tools/testing/selftests/filesystems/utils.c b/tools/testing/selftests/filesystems/utils.c
index c43a69dffd83..a0c64f415a7f 100644
--- a/tools/testing/selftests/filesystems/utils.c
+++ b/tools/testing/selftests/filesystems/utils.c
@@ -487,7 +487,7 @@ int setup_userns(void)
uid_t uid = getuid();
gid_t gid = getgid();
- ret = unshare(CLONE_NEWNS|CLONE_NEWUSER|CLONE_NEWPID);
+ ret = unshare(CLONE_NEWNS|CLONE_NEWUSER);
if (ret) {
ksft_exit_fail_msg("unsharing mountns and userns: %s\n",
strerror(errno));
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/trace_marker_raw.tc b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker_raw.tc
new file mode 100644
index 000000000000..7daf7292209e
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker_raw.tc
@@ -0,0 +1,107 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Basic tests on writing to trace_marker_raw
+# requires: trace_marker_raw
+# flags: instance
+
+is_little_endian() {
+ if lscpu | grep -q 'Little Endian'; then
+ echo 1;
+ else
+ echo 0;
+ fi
+}
+
+little=`is_little_endian`
+
+make_str() {
+ id=$1
+ cnt=$2
+
+ if [ $little -eq 1 ]; then
+ val=`printf "\\%03o\\%03o\\%03o\\%03o" \
+ $(($id & 0xff)) \
+ $((($id >> 8) & 0xff)) \
+ $((($id >> 16) & 0xff)) \
+ $((($id >> 24) & 0xff))`
+ else
+ val=`printf "\\%03o\\%03o\\%03o\\%03o" \
+ $((($id >> 24) & 0xff)) \
+ $((($id >> 16) & 0xff)) \
+ $((($id >> 8) & 0xff)) \
+ $(($id & 0xff))`
+ fi
+
+ data=`printf -- 'X%.0s' $(seq $cnt)`
+
+ printf "${val}${data}"
+}
+
+write_buffer() {
+ id=$1
+ size=$2
+
+ # write the string into the raw marker
+ make_str $id $size > trace_marker_raw
+}
+
+
+test_multiple_writes() {
+
+ # Write a bunch of data where the id is the count of
+ # data to write
+ for i in `seq 1 10` `seq 101 110` `seq 1001 1010`; do
+ write_buffer $i $i
+ done
+
+ # add a little buffer
+ echo stop > trace_marker
+
+ # Check to make sure the number of entries is the id (rounded up by 4)
+ awk '/.*: # [0-9a-f]* / {
+ print;
+ cnt = -1;
+ for (i = 0; i < NF; i++) {
+ # The counter is after the "#" marker
+ if ( $i == "#" ) {
+ i++;
+ cnt = strtonum("0x" $i);
+ num = NF - (i + 1);
+ # The number of items is always rounded up by 4
+ cnt2 = int((cnt + 3) / 4) * 4;
+ if (cnt2 != num) {
+ exit 1;
+ }
+ break;
+ }
+ }
+ }
+ // { if (NR > 30) { exit 0; } } ' trace_pipe;
+}
+
+
+get_buffer_data_size() {
+ sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page
+}
+
+test_buffer() {
+
+ # The id must be four bytes, test that 3 bytes fails a write
+ if echo -n abc > ./trace_marker_raw ; then
+ echo "Too small of write expected to fail but did not"
+ exit_fail
+ fi
+
+ size=`get_buffer_data_size`
+ echo size = $size
+
+ # Now add a little more than what it can handle
+
+ if write_buffer 0xdeadbeef $size ; then
+ echo "Too big of write expected to fail but did not"
+ exit_fail
+ fi
+}
+
+test_buffer
+test_multiple_writes
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
index 2506f464811b..47067a5e3cb0 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
@@ -28,25 +28,21 @@ test -d events/fprobes/myevent1
test -d events/fprobes/myevent2
echo 1 > events/fprobes/myevent1/enable
-# Make sure the event is attached and is the only one
+# Make sure the event is attached.
grep -q $PLACE enabled_functions
cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne $((ocnt + 1)) ]; then
+if [ $cnt -eq $ocnt ]; then
exit_fail
fi
echo 1 > events/fprobes/myevent2/enable
-# It should till be the only attached function
-cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne $((ocnt + 1)) ]; then
- exit_fail
-fi
+cnt2=`cat enabled_functions | wc -l`
echo 1 > events/fprobes/myevent3/enable
# If the function is different, the attached function should be increased
grep -q $PLACE2 enabled_functions
cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne $((ocnt + 2)) ]; then
+if [ $cnt -eq $cnt2 ]; then
exit_fail
fi
@@ -56,12 +52,6 @@ echo "-:myevent2" >> dynamic_events
grep -q myevent1 dynamic_events
! grep -q myevent2 dynamic_events
-# should still have 2 left
-cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne $((ocnt + 2)) ]; then
- exit_fail
-fi
-
echo 0 > events/fprobes/enable
echo > dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/enable_disable_tprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/enable_disable_tprobe.tc
new file mode 100644
index 000000000000..c1f1cafa30f3
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/enable_disable_tprobe.tc
@@ -0,0 +1,40 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Generic dynamic event - enable/disable tracepoint probe events
+# requires: dynamic_events "t[:[<group>/][<event>]] <tracepoint> [<args>]":README
+
+echo 0 > events/enable
+echo > dynamic_events
+
+TRACEPOINT=sched_switch
+ENABLEFILE=events/tracepoints/myprobe/enable
+
+:;: "Add tracepoint event on $TRACEPOINT" ;:
+
+echo "t:myprobe ${TRACEPOINT}" >> dynamic_events
+
+:;: "Check enable/disable to ensure it works" ;:
+
+echo 1 > $ENABLEFILE
+
+grep -q $TRACEPOINT trace
+
+echo 0 > $ENABLEFILE
+
+echo > trace
+
+! grep -q $TRACEPOINT trace
+
+:;: "Repeat enable/disable to ensure it works" ;:
+
+echo 1 > $ENABLEFILE
+
+grep -q $TRACEPOINT trace
+
+echo 0 > $ENABLEFILE
+
+echo > trace
+
+! grep -q $TRACEPOINT trace
+
+exit 0
diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index 2c3c58e65a41..3a62039fa621 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -44,6 +44,12 @@ tap_timeout()
fi
}
+report_failure()
+{
+ echo "not ok $*"
+ echo "$*" >> "$kselftest_failures_file"
+}
+
run_one()
{
DIR="$1"
@@ -105,7 +111,7 @@ run_one()
echo "# $TEST_HDR_MSG"
if [ ! -e "$TEST" ]; then
echo "# Warning: file $TEST is missing!"
- echo "not ok $test_num $TEST_HDR_MSG"
+ report_failure "$test_num $TEST_HDR_MSG"
else
if [ -x /usr/bin/stdbuf ]; then
stdbuf="/usr/bin/stdbuf --output=L "
@@ -123,7 +129,7 @@ run_one()
interpreter=$(head -n 1 "$TEST" | cut -c 3-)
cmd="$stdbuf $interpreter ./$BASENAME_TEST"
else
- echo "not ok $test_num $TEST_HDR_MSG"
+ report_failure "$test_num $TEST_HDR_MSG"
return
fi
fi
@@ -137,9 +143,9 @@ run_one()
echo "ok $test_num $TEST_HDR_MSG # SKIP"
elif [ $rc -eq $timeout_rc ]; then \
echo "#"
- echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT $kselftest_timeout seconds"
+ report_failure "$test_num $TEST_HDR_MSG # TIMEOUT $kselftest_timeout seconds"
else
- echo "not ok $test_num $TEST_HDR_MSG # exit=$rc"
+ report_failure "$test_num $TEST_HDR_MSG # exit=$rc"
fi)
cd - >/dev/null
fi
diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index 5e24f77868b5..c4815d365816 100644
--- a/tools/testing/selftests/kvm/arm64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -268,7 +268,9 @@ static void guest_code(void)
/* Return a safe value to a given ftr_bits an ftr value */
uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
{
- uint64_t ftr_max = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
+ uint64_t ftr_max = ftr_bits->mask >> ftr_bits->shift;
+
+ TEST_ASSERT(ftr_max > 1, "This test doesn't support single bit features");
if (ftr_bits->sign == FTR_UNSIGNED) {
switch (ftr_bits->type) {
@@ -320,7 +322,9 @@ uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
/* Return an invalid value to a given ftr_bits an ftr value */
uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
{
- uint64_t ftr_max = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
+ uint64_t ftr_max = ftr_bits->mask >> ftr_bits->shift;
+
+ TEST_ASSERT(ftr_max > 1, "This test doesn't support single bit features");
if (ftr_bits->sign == FTR_UNSIGNED) {
switch (ftr_bits->type) {
@@ -672,7 +676,7 @@ static void test_clidr(struct kvm_vcpu *vcpu)
clidr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1));
/* find the first empty level in the cache hierarchy */
- for (level = 1; level < 7; level++) {
+ for (level = 1; level <= 7; level++) {
if (!CLIDR_CTYPE(clidr, level))
break;
}
diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh
index 46991a029f7c..8ec0cb64ad94 100644
--- a/tools/testing/selftests/livepatch/functions.sh
+++ b/tools/testing/selftests/livepatch/functions.sh
@@ -10,7 +10,11 @@ SYSFS_KERNEL_DIR="/sys/kernel"
SYSFS_KLP_DIR="$SYSFS_KERNEL_DIR/livepatch"
SYSFS_DEBUG_DIR="$SYSFS_KERNEL_DIR/debug"
SYSFS_KPROBES_DIR="$SYSFS_DEBUG_DIR/kprobes"
-SYSFS_TRACING_DIR="$SYSFS_DEBUG_DIR/tracing"
+if [[ -e /sys/kernel/tracing/trace ]]; then
+ SYSFS_TRACING_DIR="$SYSFS_KERNEL_DIR/tracing"
+else
+ SYSFS_TRACING_DIR="$SYSFS_DEBUG_DIR/tracing"
+fi
# Kselftest framework requirement - SKIP code is 4
ksft_skip=4
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index 9e3be2ee7f1b..f917b4c4c943 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -1758,10 +1758,15 @@ int main(int argc, char *argv[])
uffd_test_ops = mem_type->mem_ops;
uffd_test_case_ops = test->test_case_ops;
- if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB))
+ if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) {
gopts.page_size = default_huge_page_size();
- else
+ if (gopts.page_size == 0) {
+ uffd_test_skip("huge page size is 0, feature missing?");
+ continue;
+ }
+ } else {
gopts.page_size = psize();
+ }
/* Ensure we have at least 2 pages */
gopts.nr_pages = MAX(UFFD_TEST_MEM_SIZE, gopts.page_size * 2)
@@ -1776,12 +1781,6 @@ int main(int argc, char *argv[])
continue;
uffd_test_start("%s on %s", test->name, mem_type->name);
- if ((mem_type->mem_flag == MEM_HUGETLB ||
- mem_type->mem_flag == MEM_HUGETLB_PRIVATE) &&
- (default_huge_page_size() == 0)) {
- uffd_test_skip("huge page size is 0, feature missing?");
- continue;
- }
if (!uffd_feature_supported(test)) {
uffd_test_skip("feature missing");
continue;
diff --git a/tools/testing/selftests/namespaces/.gitignore b/tools/testing/selftests/namespaces/.gitignore
index ccfb40837a73..0989e80da457 100644
--- a/tools/testing/selftests/namespaces/.gitignore
+++ b/tools/testing/selftests/namespaces/.gitignore
@@ -1,3 +1,12 @@
nsid_test
file_handle_test
init_ino_test
+ns_active_ref_test
+listns_test
+listns_permissions_test
+listns_efault_test
+siocgskns_test
+cred_change_test
+stress_test
+listns_pagination_bug
+regression_pidfd_setns_test
diff --git a/tools/testing/selftests/namespaces/Makefile b/tools/testing/selftests/namespaces/Makefile
index 5fe4b3dc07d3..fbb821652c17 100644
--- a/tools/testing/selftests/namespaces/Makefile
+++ b/tools/testing/selftests/namespaces/Makefile
@@ -1,7 +1,29 @@
# SPDX-License-Identifier: GPL-2.0-only
CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
+LDLIBS += -lcap
-TEST_GEN_PROGS := nsid_test file_handle_test init_ino_test
+TEST_GEN_PROGS := nsid_test \
+ file_handle_test \
+ init_ino_test \
+ ns_active_ref_test \
+ listns_test \
+ listns_permissions_test \
+ listns_efault_test \
+ siocgskns_test \
+ cred_change_test \
+ stress_test \
+ listns_pagination_bug \
+ regression_pidfd_setns_test
include ../lib.mk
+$(OUTPUT)/ns_active_ref_test: ../filesystems/utils.c
+$(OUTPUT)/listns_test: ../filesystems/utils.c
+$(OUTPUT)/listns_permissions_test: ../filesystems/utils.c
+$(OUTPUT)/listns_efault_test: ../filesystems/utils.c
+$(OUTPUT)/siocgskns_test: ../filesystems/utils.c
+$(OUTPUT)/cred_change_test: ../filesystems/utils.c
+$(OUTPUT)/stress_test: ../filesystems/utils.c
+$(OUTPUT)/listns_pagination_bug: ../filesystems/utils.c
+$(OUTPUT)/regression_pidfd_setns_test: ../filesystems/utils.c
+
diff --git a/tools/testing/selftests/namespaces/cred_change_test.c b/tools/testing/selftests/namespaces/cred_change_test.c
new file mode 100644
index 000000000000..7b4f5ad3f725
--- /dev/null
+++ b/tools/testing/selftests/namespaces/cred_change_test.c
@@ -0,0 +1,814 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/capability.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <linux/nsfs.h>
+#include "../kselftest_harness.h"
+#include "../filesystems/utils.h"
+#include "wrappers.h"
+
+/*
+ * Test credential changes and their impact on namespace active references.
+ */
+
+/*
+ * Test setuid() in a user namespace properly swaps active references.
+ * Create a user namespace with multiple UIDs mapped, then setuid() between them.
+ * Verify that the user namespace remains active throughout.
+ */
+TEST(setuid_preserves_active_refs)
+{
+ pid_t pid;
+ int status;
+ __u64 userns_id;
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[256];
+ ssize_t ret;
+ int i;
+ bool found = false;
+ int pipefd[2];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ int fd, userns_fd;
+ __u64 child_userns_id;
+ uid_t orig_uid = getuid();
+ int setuid_count;
+
+ close(pipefd[0]);
+
+ /* Create new user namespace with multiple UIDs mapped (0-9) */
+ userns_fd = get_userns_fd(0, orig_uid, 10);
+ if (userns_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (setns(userns_fd, CLONE_NEWUSER) < 0) {
+ close(userns_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(userns_fd);
+
+ /* Get user namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &child_userns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Send namespace ID to parent */
+ write(pipefd[1], &child_userns_id, sizeof(child_userns_id));
+
+ /*
+ * Perform multiple setuid() calls.
+ * Each setuid() triggers commit_creds() which should properly
+ * swap active references via switch_cred_namespaces().
+ */
+ for (setuid_count = 0; setuid_count < 50; setuid_count++) {
+ uid_t target_uid = (setuid_count % 10);
+ if (setuid(target_uid) < 0) {
+ if (errno != EPERM) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ }
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ if (read(pipefd[0], &userns_id, sizeof(userns_id)) != sizeof(userns_id)) {
+ close(pipefd[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to get namespace ID from child");
+ }
+ close(pipefd[0]);
+
+ TH_LOG("Child user namespace ID: %llu", (unsigned long long)userns_id);
+
+ /* Verify namespace is active while child is running */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret, 0);
+ }
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == userns_id) {
+ found = true;
+ break;
+ }
+ }
+ ASSERT_TRUE(found);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Verify namespace becomes inactive after child exits */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ ASSERT_GE(ret, 0);
+
+ found = false;
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == userns_id) {
+ found = true;
+ break;
+ }
+ }
+
+ ASSERT_FALSE(found);
+ TH_LOG("setuid() correctly preserved active references (no leak)");
+}
+
+/*
+ * Test setgid() in a user namespace properly handles active references.
+ */
+TEST(setgid_preserves_active_refs)
+{
+ pid_t pid;
+ int status;
+ __u64 userns_id;
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[256];
+ ssize_t ret;
+ int i;
+ bool found = false;
+ int pipefd[2];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ int fd, userns_fd;
+ __u64 child_userns_id;
+ uid_t orig_uid = getuid();
+ int setgid_count;
+
+ close(pipefd[0]);
+
+ /* Create new user namespace with multiple GIDs mapped */
+ userns_fd = get_userns_fd(0, orig_uid, 10);
+ if (userns_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (setns(userns_fd, CLONE_NEWUSER) < 0) {
+ close(userns_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(userns_fd);
+
+ /* Get user namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &child_userns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ write(pipefd[1], &child_userns_id, sizeof(child_userns_id));
+
+ /* Perform multiple setgid() calls */
+ for (setgid_count = 0; setgid_count < 50; setgid_count++) {
+ gid_t target_gid = (setgid_count % 10);
+ if (setgid(target_gid) < 0) {
+ if (errno != EPERM) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ }
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ if (read(pipefd[0], &userns_id, sizeof(userns_id)) != sizeof(userns_id)) {
+ close(pipefd[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to get namespace ID from child");
+ }
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Verify namespace becomes inactive */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret, 0);
+ }
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == userns_id) {
+ found = true;
+ break;
+ }
+ }
+
+ ASSERT_FALSE(found);
+ TH_LOG("setgid() correctly preserved active references (no leak)");
+}
+
+/*
+ * Test setresuid() which changes real, effective, and saved UIDs.
+ * This should properly swap active references via commit_creds().
+ */
+TEST(setresuid_preserves_active_refs)
+{
+ pid_t pid;
+ int status;
+ __u64 userns_id;
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[256];
+ ssize_t ret;
+ int i;
+ bool found = false;
+ int pipefd[2];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ int fd, userns_fd;
+ __u64 child_userns_id;
+ uid_t orig_uid = getuid();
+ int setres_count;
+
+ close(pipefd[0]);
+
+ /* Create new user namespace */
+ userns_fd = get_userns_fd(0, orig_uid, 10);
+ if (userns_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (setns(userns_fd, CLONE_NEWUSER) < 0) {
+ close(userns_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(userns_fd);
+
+ /* Get user namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &child_userns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ write(pipefd[1], &child_userns_id, sizeof(child_userns_id));
+
+ /* Perform multiple setresuid() calls */
+ for (setres_count = 0; setres_count < 30; setres_count++) {
+ uid_t uid1 = (setres_count % 5);
+ uid_t uid2 = ((setres_count + 1) % 5);
+ uid_t uid3 = ((setres_count + 2) % 5);
+
+ if (setresuid(uid1, uid2, uid3) < 0) {
+ if (errno != EPERM) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ }
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ if (read(pipefd[0], &userns_id, sizeof(userns_id)) != sizeof(userns_id)) {
+ close(pipefd[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to get namespace ID from child");
+ }
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Verify namespace becomes inactive */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret, 0);
+ }
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == userns_id) {
+ found = true;
+ break;
+ }
+ }
+
+ ASSERT_FALSE(found);
+ TH_LOG("setresuid() correctly preserved active references (no leak)");
+}
+
+/*
+ * Test credential changes across multiple user namespaces.
+ * Create nested user namespaces and verify active reference tracking.
+ */
+TEST(cred_change_nested_userns)
+{
+ pid_t pid;
+ int status;
+ __u64 parent_userns_id, child_userns_id;
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[256];
+ ssize_t ret;
+ int i;
+ bool found_parent = false, found_child = false;
+ int pipefd[2];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ int fd, userns_fd;
+ __u64 parent_id, child_id;
+ uid_t orig_uid = getuid();
+
+ close(pipefd[0]);
+
+ /* Create first user namespace */
+ userns_fd = get_userns_fd(0, orig_uid, 1);
+ if (userns_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (setns(userns_fd, CLONE_NEWUSER) < 0) {
+ close(userns_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(userns_fd);
+
+ /* Get first namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &parent_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Create nested user namespace */
+ userns_fd = get_userns_fd(0, 0, 1);
+ if (userns_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (setns(userns_fd, CLONE_NEWUSER) < 0) {
+ close(userns_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(userns_fd);
+
+ /* Get nested namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &child_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Send both IDs to parent */
+ write(pipefd[1], &parent_id, sizeof(parent_id));
+ write(pipefd[1], &child_id, sizeof(child_id));
+
+ /* Perform some credential changes in nested namespace */
+ setuid(0);
+ setgid(0);
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ /* Read both namespace IDs */
+ if (read(pipefd[0], &parent_userns_id, sizeof(parent_userns_id)) != sizeof(parent_userns_id)) {
+ close(pipefd[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to get parent namespace ID");
+ }
+
+ if (read(pipefd[0], &child_userns_id, sizeof(child_userns_id)) != sizeof(child_userns_id)) {
+ close(pipefd[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to get child namespace ID");
+ }
+ close(pipefd[0]);
+
+ TH_LOG("Parent userns: %llu, Child userns: %llu",
+ (unsigned long long)parent_userns_id,
+ (unsigned long long)child_userns_id);
+
+ /* Verify both namespaces are active */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret, 0);
+ }
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == parent_userns_id)
+ found_parent = true;
+ if (ns_ids[i] == child_userns_id)
+ found_child = true;
+ }
+
+ ASSERT_TRUE(found_parent);
+ ASSERT_TRUE(found_child);
+
+ /* Wait for child */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Verify both namespaces become inactive */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ ASSERT_GE(ret, 0);
+
+ found_parent = false;
+ found_child = false;
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == parent_userns_id)
+ found_parent = true;
+ if (ns_ids[i] == child_userns_id)
+ found_child = true;
+ }
+
+ ASSERT_FALSE(found_parent);
+ ASSERT_FALSE(found_child);
+ TH_LOG("Nested user namespace credential changes preserved active refs (no leak)");
+}
+
+/*
+ * Test rapid credential changes don't cause refcount imbalances.
+ * This stress-tests the switch_cred_namespaces() logic.
+ */
+TEST(rapid_cred_changes_no_leak)
+{
+ pid_t pid;
+ int status;
+ __u64 userns_id;
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[256];
+ ssize_t ret;
+ int i;
+ bool found = false;
+ int pipefd[2];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ int fd, userns_fd;
+ __u64 child_userns_id;
+ uid_t orig_uid = getuid();
+ int change_count;
+
+ close(pipefd[0]);
+
+ /* Create new user namespace with wider range of UIDs/GIDs */
+ userns_fd = get_userns_fd(0, orig_uid, 100);
+ if (userns_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (setns(userns_fd, CLONE_NEWUSER) < 0) {
+ close(userns_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(userns_fd);
+
+ /* Get user namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &child_userns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ write(pipefd[1], &child_userns_id, sizeof(child_userns_id));
+
+ /*
+ * Perform many rapid credential changes.
+ * Mix setuid, setgid, setreuid, setregid, setresuid, setresgid.
+ */
+ for (change_count = 0; change_count < 200; change_count++) {
+ switch (change_count % 6) {
+ case 0:
+ setuid(change_count % 50);
+ break;
+ case 1:
+ setgid(change_count % 50);
+ break;
+ case 2:
+ setreuid(change_count % 50, (change_count + 1) % 50);
+ break;
+ case 3:
+ setregid(change_count % 50, (change_count + 1) % 50);
+ break;
+ case 4:
+ setresuid(change_count % 50, (change_count + 1) % 50, (change_count + 2) % 50);
+ break;
+ case 5:
+ setresgid(change_count % 50, (change_count + 1) % 50, (change_count + 2) % 50);
+ break;
+ }
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ if (read(pipefd[0], &userns_id, sizeof(userns_id)) != sizeof(userns_id)) {
+ close(pipefd[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to get namespace ID from child");
+ }
+ close(pipefd[0]);
+
+ TH_LOG("Testing with user namespace ID: %llu", (unsigned long long)userns_id);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Verify namespace becomes inactive (no leaked active refs) */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret, 0);
+ }
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == userns_id) {
+ found = true;
+ break;
+ }
+ }
+
+ ASSERT_FALSE(found);
+ TH_LOG("200 rapid credential changes completed with no active ref leak");
+}
+
+/*
+ * Test setfsuid/setfsgid which change filesystem UID/GID.
+ * These also trigger credential changes but may have different code paths.
+ */
+TEST(setfsuid_preserves_active_refs)
+{
+ pid_t pid;
+ int status;
+ __u64 userns_id;
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[256];
+ ssize_t ret;
+ int i;
+ bool found = false;
+ int pipefd[2];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ int fd, userns_fd;
+ __u64 child_userns_id;
+ uid_t orig_uid = getuid();
+ int change_count;
+
+ close(pipefd[0]);
+
+ /* Create new user namespace */
+ userns_fd = get_userns_fd(0, orig_uid, 10);
+ if (userns_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (setns(userns_fd, CLONE_NEWUSER) < 0) {
+ close(userns_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(userns_fd);
+
+ /* Get user namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &child_userns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ write(pipefd[1], &child_userns_id, sizeof(child_userns_id));
+
+ /* Perform multiple setfsuid/setfsgid calls */
+ for (change_count = 0; change_count < 50; change_count++) {
+ setfsuid(change_count % 10);
+ setfsgid(change_count % 10);
+ }
+
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ if (read(pipefd[0], &userns_id, sizeof(userns_id)) != sizeof(userns_id)) {
+ close(pipefd[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to get namespace ID from child");
+ }
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Verify namespace becomes inactive */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret, 0);
+ }
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == userns_id) {
+ found = true;
+ break;
+ }
+ }
+
+ ASSERT_FALSE(found);
+ TH_LOG("setfsuid/setfsgid correctly preserved active references (no leak)");
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/listns_efault_test.c b/tools/testing/selftests/namespaces/listns_efault_test.c
new file mode 100644
index 000000000000..c7ed4023d7a8
--- /dev/null
+++ b/tools/testing/selftests/namespaces/listns_efault_test.c
@@ -0,0 +1,530 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/nsfs.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/mount.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "../kselftest_harness.h"
+#include "../filesystems/utils.h"
+#include "../pidfd/pidfd.h"
+#include "wrappers.h"
+
+/*
+ * Test listns() error handling with invalid buffer addresses.
+ *
+ * When the buffer pointer is invalid (e.g., crossing page boundaries
+ * into unmapped memory), listns() returns EINVAL.
+ *
+ * This test also creates mount namespaces that get destroyed during
+ * iteration, testing that namespace cleanup happens outside the RCU
+ * read lock.
+ */
+TEST(listns_partial_fault_with_ns_cleanup)
+{
+ void *map;
+ __u64 *ns_ids;
+ ssize_t ret;
+ long page_size;
+ pid_t pid, iter_pid;
+ int pidfds[5];
+ int sv[5][2];
+ int iter_pidfd;
+ int i, status;
+ char c;
+
+ page_size = sysconf(_SC_PAGESIZE);
+ ASSERT_GT(page_size, 0);
+
+ /*
+ * Map two pages:
+ * - First page: readable and writable
+ * - Second page: will be unmapped to trigger EFAULT
+ */
+ map = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(map, MAP_FAILED);
+
+ /* Unmap the second page */
+ ret = munmap((char *)map + page_size, page_size);
+ ASSERT_EQ(ret, 0);
+
+ /*
+ * Position the buffer pointer so there's room for exactly one u64
+ * before the page boundary. The second u64 would fall into the
+ * unmapped page.
+ */
+ ns_ids = ((__u64 *)((char *)map + page_size)) - 1;
+
+ /*
+ * Create a separate process to run listns() in a loop concurrently
+ * with namespace creation and destruction.
+ */
+ iter_pid = create_child(&iter_pidfd, 0);
+ ASSERT_NE(iter_pid, -1);
+
+ if (iter_pid == 0) {
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0, /* All types */
+ .spare2 = 0,
+ .user_ns_id = 0, /* Global listing */
+ };
+ int iter_ret;
+
+ /*
+ * Loop calling listns() until killed.
+ * The kernel should:
+ * 1. Successfully write the first namespace ID (within valid page)
+ * 2. Fail with EFAULT when trying to write the second ID (unmapped page)
+ * 3. Handle concurrent namespace destruction without deadlock
+ */
+ while (1) {
+ iter_ret = sys_listns(&req, ns_ids, 2, 0);
+
+ if (iter_ret == -1 && errno == ENOSYS)
+ _exit(PIDFD_SKIP);
+ }
+ }
+
+ /* Small delay to let iterator start looping */
+ usleep(50000);
+
+ /*
+ * Create several child processes, each in its own mount namespace.
+ * These will be destroyed while the iterator is running listns().
+ */
+ for (i = 0; i < 5; i++) {
+ /* Create socketpair for synchronization */
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sv[i]), 0);
+
+ pid = create_child(&pidfds[i], CLONE_NEWNS);
+ ASSERT_NE(pid, -1);
+
+ if (pid == 0) {
+ close(sv[i][0]); /* Close parent end */
+
+ if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0))
+ _exit(1);
+
+ /* Child: create a couple of tmpfs mounts */
+ if (mkdir("/tmp/test_mnt1", 0755) == -1 && errno != EEXIST)
+ _exit(1);
+ if (mkdir("/tmp/test_mnt2", 0755) == -1 && errno != EEXIST)
+ _exit(1);
+
+ if (mount("tmpfs", "/tmp/test_mnt1", "tmpfs", 0, NULL) == -1)
+ _exit(1);
+ if (mount("tmpfs", "/tmp/test_mnt2", "tmpfs", 0, NULL) == -1)
+ _exit(1);
+
+ /* Signal parent that setup is complete */
+ if (write_nointr(sv[i][1], "R", 1) != 1)
+ _exit(1);
+
+ /* Wait for parent to signal us to exit */
+ if (read_nointr(sv[i][1], &c, 1) != 1)
+ _exit(1);
+
+ close(sv[i][1]);
+ _exit(0);
+ }
+
+ close(sv[i][1]); /* Close child end */
+ }
+
+ /* Wait for all children to finish setup */
+ for (i = 0; i < 5; i++) {
+ ret = read_nointr(sv[i][0], &c, 1);
+ ASSERT_EQ(ret, 1);
+ ASSERT_EQ(c, 'R');
+ }
+
+ /*
+ * Signal children to exit. This will destroy their mount namespaces
+ * while listns() is iterating the namespace tree.
+ * This tests that cleanup happens outside the RCU read lock.
+ */
+ for (i = 0; i < 5; i++)
+ write_nointr(sv[i][0], "X", 1);
+
+ /* Wait for all mount namespace children to exit and cleanup */
+ for (i = 0; i < 5; i++) {
+ waitpid(-1, NULL, 0);
+ close(sv[i][0]);
+ close(pidfds[i]);
+ }
+
+ /* Kill iterator and wait for it */
+ sys_pidfd_send_signal(iter_pidfd, SIGKILL, NULL, 0);
+ ret = waitpid(iter_pid, &status, 0);
+ ASSERT_EQ(ret, iter_pid);
+ close(iter_pidfd);
+
+ /* Should have been killed */
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_EQ(WTERMSIG(status), SIGKILL);
+
+ /* Clean up */
+ munmap(map, page_size);
+}
+
+/*
+ * Test listns() error handling when the entire buffer is invalid.
+ * This is a sanity check that basic invalid pointer detection works.
+ */
+TEST(listns_complete_fault)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 *ns_ids;
+ ssize_t ret;
+
+ /* Use a clearly invalid pointer */
+ ns_ids = (__u64 *)0xdeadbeef;
+
+ ret = sys_listns(&req, ns_ids, 10, 0);
+
+ if (ret == -1 && errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+
+ /* Should fail with EFAULT */
+ ASSERT_EQ(ret, -1);
+ ASSERT_EQ(errno, EFAULT);
+}
+
+/*
+ * Test listns() error handling when the buffer is NULL.
+ */
+TEST(listns_null_buffer)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ ssize_t ret;
+
+ /* NULL buffer with non-zero count should fail */
+ ret = sys_listns(&req, NULL, 10, 0);
+
+ if (ret == -1 && errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+
+ /* Should fail with EFAULT */
+ ASSERT_EQ(ret, -1);
+ ASSERT_EQ(errno, EFAULT);
+}
+
+/*
+ * Test listns() with a buffer that becomes invalid mid-iteration
+ * (after several successful writes), combined with mount namespace
+ * destruction to test RCU cleanup logic.
+ */
+TEST(listns_late_fault_with_ns_cleanup)
+{
+ void *map;
+ __u64 *ns_ids;
+ ssize_t ret;
+ long page_size;
+ pid_t pid, iter_pid;
+ int pidfds[10];
+ int sv[10][2];
+ int iter_pidfd;
+ int i, status;
+ char c;
+
+ page_size = sysconf(_SC_PAGESIZE);
+ ASSERT_GT(page_size, 0);
+
+ /* Map two pages */
+ map = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(map, MAP_FAILED);
+
+ /* Unmap the second page */
+ ret = munmap((char *)map + page_size, page_size);
+ ASSERT_EQ(ret, 0);
+
+ /*
+ * Position buffer so we can write several u64s successfully
+ * before hitting the page boundary.
+ */
+ ns_ids = ((__u64 *)((char *)map + page_size)) - 5;
+
+ /*
+ * Create a separate process to run listns() concurrently.
+ */
+ iter_pid = create_child(&iter_pidfd, 0);
+ ASSERT_NE(iter_pid, -1);
+
+ if (iter_pid == 0) {
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ int iter_ret;
+
+ /*
+ * Loop calling listns() until killed.
+ * Request 10 namespace IDs while namespaces are being destroyed.
+ * This tests:
+ * 1. EFAULT handling when buffer becomes invalid
+ * 2. Namespace cleanup outside RCU read lock during iteration
+ */
+ while (1) {
+ iter_ret = sys_listns(&req, ns_ids, 10, 0);
+
+ if (iter_ret == -1 && errno == ENOSYS)
+ _exit(PIDFD_SKIP);
+ }
+ }
+
+ /* Small delay to let iterator start looping */
+ usleep(50000);
+
+ /*
+ * Create more children with mount namespaces to increase the
+ * likelihood that namespace cleanup happens during iteration.
+ */
+ for (i = 0; i < 10; i++) {
+ /* Create socketpair for synchronization */
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sv[i]), 0);
+
+ pid = create_child(&pidfds[i], CLONE_NEWNS);
+ ASSERT_NE(pid, -1);
+
+ if (pid == 0) {
+ close(sv[i][0]); /* Close parent end */
+
+ if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0))
+ _exit(1);
+
+ /* Child: create tmpfs mounts */
+ if (mkdir("/tmp/test_mnt1", 0755) == -1 && errno != EEXIST)
+ _exit(1);
+ if (mkdir("/tmp/test_mnt2", 0755) == -1 && errno != EEXIST)
+ _exit(1);
+
+ if (mount("tmpfs", "/tmp/test_mnt1", "tmpfs", 0, NULL) == -1)
+ _exit(1);
+ if (mount("tmpfs", "/tmp/test_mnt2", "tmpfs", 0, NULL) == -1)
+ _exit(1);
+
+ /* Signal parent that setup is complete */
+ if (write_nointr(sv[i][1], "R", 1) != 1)
+ _exit(1);
+
+ /* Wait for parent to signal us to exit */
+ if (read_nointr(sv[i][1], &c, 1) != 1)
+ _exit(1);
+
+ close(sv[i][1]);
+ _exit(0);
+ }
+
+ close(sv[i][1]); /* Close child end */
+ }
+
+ /* Wait for all children to finish setup */
+ for (i = 0; i < 10; i++) {
+ ret = read_nointr(sv[i][0], &c, 1);
+ ASSERT_EQ(ret, 1);
+ ASSERT_EQ(c, 'R');
+ }
+
+ /* Kill half the children */
+ for (i = 0; i < 5; i++)
+ write_nointr(sv[i][0], "X", 1);
+
+ /* Small delay to let some exit */
+ usleep(10000);
+
+ /* Kill remaining children */
+ for (i = 5; i < 10; i++)
+ write_nointr(sv[i][0], "X", 1);
+
+ /* Wait for all children and cleanup */
+ for (i = 0; i < 10; i++) {
+ waitpid(-1, NULL, 0);
+ close(sv[i][0]);
+ close(pidfds[i]);
+ }
+
+ /* Kill iterator and wait for it */
+ sys_pidfd_send_signal(iter_pidfd, SIGKILL, NULL, 0);
+ ret = waitpid(iter_pid, &status, 0);
+ ASSERT_EQ(ret, iter_pid);
+ close(iter_pidfd);
+
+ /* Should have been killed */
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_EQ(WTERMSIG(status), SIGKILL);
+
+ /* Clean up */
+ munmap(map, page_size);
+}
+
+/*
+ * Test specifically focused on mount namespace cleanup during EFAULT.
+ * Filter for mount namespaces only.
+ */
+TEST(listns_mnt_ns_cleanup_on_fault)
+{
+ void *map;
+ __u64 *ns_ids;
+ ssize_t ret;
+ long page_size;
+ pid_t pid, iter_pid;
+ int pidfds[8];
+ int sv[8][2];
+ int iter_pidfd;
+ int i, status;
+ char c;
+
+ page_size = sysconf(_SC_PAGESIZE);
+ ASSERT_GT(page_size, 0);
+
+ /* Set up partial fault buffer */
+ map = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(map, MAP_FAILED);
+
+ ret = munmap((char *)map + page_size, page_size);
+ ASSERT_EQ(ret, 0);
+
+ /* Position for 3 successful writes, then fault */
+ ns_ids = ((__u64 *)((char *)map + page_size)) - 3;
+
+ /*
+ * Create a separate process to run listns() concurrently.
+ */
+ iter_pid = create_child(&iter_pidfd, 0);
+ ASSERT_NE(iter_pid, -1);
+
+ if (iter_pid == 0) {
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWNS, /* Only mount namespaces */
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ int iter_ret;
+
+ /*
+ * Loop calling listns() until killed.
+ * Call listns() to race with namespace destruction.
+ */
+ while (1) {
+ iter_ret = sys_listns(&req, ns_ids, 10, 0);
+
+ if (iter_ret == -1 && errno == ENOSYS)
+ _exit(PIDFD_SKIP);
+ }
+ }
+
+ /* Small delay to let iterator start looping */
+ usleep(50000);
+
+ /* Create children with mount namespaces */
+ for (i = 0; i < 8; i++) {
+ /* Create socketpair for synchronization */
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sv[i]), 0);
+
+ pid = create_child(&pidfds[i], CLONE_NEWNS);
+ ASSERT_NE(pid, -1);
+
+ if (pid == 0) {
+ close(sv[i][0]); /* Close parent end */
+
+ if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0))
+ _exit(1);
+
+ /* Do some mount operations to make cleanup more interesting */
+ if (mkdir("/tmp/test_mnt1", 0755) == -1 && errno != EEXIST)
+ _exit(1);
+ if (mkdir("/tmp/test_mnt2", 0755) == -1 && errno != EEXIST)
+ _exit(1);
+
+ if (mount("tmpfs", "/tmp/test_mnt1", "tmpfs", 0, NULL) == -1)
+ _exit(1);
+ if (mount("tmpfs", "/tmp/test_mnt2", "tmpfs", 0, NULL) == -1)
+ _exit(1);
+
+ /* Signal parent that setup is complete */
+ if (write_nointr(sv[i][1], "R", 1) != 1)
+ _exit(1);
+
+ /* Wait for parent to signal us to exit */
+ if (read_nointr(sv[i][1], &c, 1) != 1)
+ _exit(1);
+
+ close(sv[i][1]);
+ _exit(0);
+ }
+
+ close(sv[i][1]); /* Close child end */
+ }
+
+ /* Wait for all children to finish setup */
+ for (i = 0; i < 8; i++) {
+ ret = read_nointr(sv[i][0], &c, 1);
+ ASSERT_EQ(ret, 1);
+ ASSERT_EQ(c, 'R');
+ }
+
+ /* Kill children to trigger namespace destruction during iteration */
+ for (i = 0; i < 8; i++)
+ write_nointr(sv[i][0], "X", 1);
+
+ /* Wait for children and cleanup */
+ for (i = 0; i < 8; i++) {
+ waitpid(-1, NULL, 0);
+ close(sv[i][0]);
+ close(pidfds[i]);
+ }
+
+ /* Kill iterator and wait for it */
+ sys_pidfd_send_signal(iter_pidfd, SIGKILL, NULL, 0);
+ ret = waitpid(iter_pid, &status, 0);
+ ASSERT_EQ(ret, iter_pid);
+ close(iter_pidfd);
+
+ /* Should have been killed */
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_EQ(WTERMSIG(status), SIGKILL);
+
+ munmap(map, page_size);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/listns_pagination_bug.c b/tools/testing/selftests/namespaces/listns_pagination_bug.c
new file mode 100644
index 000000000000..da7d33f96397
--- /dev/null
+++ b/tools/testing/selftests/namespaces/listns_pagination_bug.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/socket.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "../kselftest_harness.h"
+#include "../filesystems/utils.h"
+#include "wrappers.h"
+
+/*
+ * Minimal test case to reproduce KASAN out-of-bounds in listns pagination.
+ *
+ * The bug occurs when:
+ * 1. Filtering by a specific namespace type (e.g., CLONE_NEWUSER)
+ * 2. Using pagination (req.ns_id != 0)
+ * 3. The lookup_ns_id_at() call in do_listns() passes ns_type=0 instead of
+ * the filtered type, causing it to search the unified tree and potentially
+ * return a namespace of the wrong type.
+ */
+TEST(pagination_with_type_filter)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER, /* Filter by user namespace */
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ pid_t pids[10];
+ int num_children = 10;
+ int i;
+ int sv[2];
+ __u64 first_batch[3];
+ ssize_t ret;
+
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sv), 0);
+
+ /* Create children with user namespaces */
+ for (i = 0; i < num_children; i++) {
+ pids[i] = fork();
+ ASSERT_GE(pids[i], 0);
+
+ if (pids[i] == 0) {
+ char c;
+ close(sv[0]);
+
+ if (setup_userns() < 0) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ /* Signal parent we're ready */
+ if (write(sv[1], &c, 1) != 1) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ /* Wait for parent signal to exit */
+ if (read(sv[1], &c, 1) != 1) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ close(sv[1]);
+ exit(0);
+ }
+ }
+
+ close(sv[1]);
+
+ /* Wait for all children to signal ready */
+ for (i = 0; i < num_children; i++) {
+ char c;
+ if (read(sv[0], &c, 1) != 1) {
+ close(sv[0]);
+ for (int j = 0; j < num_children; j++)
+ kill(pids[j], SIGKILL);
+ for (int j = 0; j < num_children; j++)
+ waitpid(pids[j], NULL, 0);
+ ASSERT_TRUE(false);
+ }
+ }
+
+ /* First batch - this should work */
+ ret = sys_listns(&req, first_batch, 3, 0);
+ if (ret < 0) {
+ if (errno == ENOSYS) {
+ close(sv[0]);
+ for (i = 0; i < num_children; i++)
+ kill(pids[i], SIGKILL);
+ for (i = 0; i < num_children; i++)
+ waitpid(pids[i], NULL, 0);
+ SKIP(return, "listns() not supported");
+ }
+ ASSERT_GE(ret, 0);
+ }
+
+ TH_LOG("First batch returned %zd entries", ret);
+
+ if (ret == 3) {
+ __u64 second_batch[3];
+
+ /* Second batch - pagination triggers the bug */
+ req.ns_id = first_batch[2]; /* Continue from last ID */
+ ret = sys_listns(&req, second_batch, 3, 0);
+
+ TH_LOG("Second batch returned %zd entries", ret);
+ ASSERT_GE(ret, 0);
+ }
+
+ /* Signal all children to exit */
+ for (i = 0; i < num_children; i++) {
+ char c = 'X';
+ if (write(sv[0], &c, 1) != 1) {
+ close(sv[0]);
+ for (int j = i; j < num_children; j++)
+ kill(pids[j], SIGKILL);
+ for (int j = 0; j < num_children; j++)
+ waitpid(pids[j], NULL, 0);
+ ASSERT_TRUE(false);
+ }
+ }
+
+ close(sv[0]);
+
+ /* Cleanup */
+ for (i = 0; i < num_children; i++) {
+ int status;
+ waitpid(pids[i], &status, 0);
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/listns_permissions_test.c b/tools/testing/selftests/namespaces/listns_permissions_test.c
new file mode 100644
index 000000000000..82d818751a5f
--- /dev/null
+++ b/tools/testing/selftests/namespaces/listns_permissions_test.c
@@ -0,0 +1,759 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/nsfs.h>
+#include <sys/capability.h>
+#include <sys/ioctl.h>
+#include <sys/prctl.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "../kselftest_harness.h"
+#include "../filesystems/utils.h"
+#include "wrappers.h"
+
+/*
+ * Test that unprivileged users can only see namespaces they're currently in.
+ * Create a namespace, drop privileges, verify we can only see our own namespaces.
+ */
+TEST(listns_unprivileged_current_only)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWNET,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[100];
+ ssize_t ret;
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ bool found_ours;
+ int unexpected_count;
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ int fd;
+ __u64 our_netns_id;
+ bool found_ours;
+ int unexpected_count;
+
+ close(pipefd[0]);
+
+ /* Create user namespace to be unprivileged */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Create a network namespace */
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Get our network namespace ID */
+ fd = open("/proc/self/ns/net", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &our_netns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Now we're unprivileged - list all network namespaces */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* We should only see our own network namespace */
+ found_ours = false;
+ unexpected_count = 0;
+
+ for (ssize_t i = 0; i < ret; i++) {
+ if (ns_ids[i] == our_netns_id) {
+ found_ours = true;
+ } else {
+ /* This is either init_net (which we can see) or unexpected */
+ unexpected_count++;
+ }
+ }
+
+ /* Send results to parent */
+ write(pipefd[1], &found_ours, sizeof(found_ours));
+ write(pipefd[1], &unexpected_count, sizeof(unexpected_count));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(pipefd[1]);
+
+ found_ours = false;
+ unexpected_count = 0;
+ read(pipefd[0], &found_ours, sizeof(found_ours));
+ read(pipefd[0], &unexpected_count, sizeof(unexpected_count));
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Child should have seen its own namespace */
+ ASSERT_TRUE(found_ours);
+
+ TH_LOG("Unprivileged child saw its own namespace, plus %d others (likely init_net)",
+ unexpected_count);
+}
+
+/*
+ * Test that users with CAP_SYS_ADMIN in a user namespace can see
+ * all namespaces owned by that user namespace.
+ */
+TEST(listns_cap_sys_admin_in_userns)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0, /* All types */
+ .spare2 = 0,
+ .user_ns_id = 0, /* Will be set to our created user namespace */
+ };
+ __u64 ns_ids[100];
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ bool success;
+ ssize_t count;
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ int fd;
+ __u64 userns_id;
+ ssize_t ret;
+ int min_expected;
+ bool success;
+
+ close(pipefd[0]);
+
+ /* Create user namespace - we'll have CAP_SYS_ADMIN in it */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Get the user namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &userns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Create several namespaces owned by this user namespace */
+ unshare(CLONE_NEWNET);
+ unshare(CLONE_NEWUTS);
+ unshare(CLONE_NEWIPC);
+
+ /* List namespaces owned by our user namespace */
+ req.user_ns_id = userns_id;
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /*
+ * We have CAP_SYS_ADMIN in this user namespace,
+ * so we should see all namespaces owned by it.
+ * That includes: net, uts, ipc, and the user namespace itself.
+ */
+ min_expected = 4;
+ success = (ret >= min_expected);
+
+ write(pipefd[1], &success, sizeof(success));
+ write(pipefd[1], &ret, sizeof(ret));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(pipefd[1]);
+
+ success = false;
+ count = 0;
+ read(pipefd[0], &success, sizeof(success));
+ read(pipefd[0], &count, sizeof(count));
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_TRUE(success);
+ TH_LOG("User with CAP_SYS_ADMIN saw %zd namespaces owned by their user namespace",
+ count);
+}
+
+/*
+ * Test that users cannot see namespaces from unrelated user namespaces.
+ * Create two sibling user namespaces, verify they can't see each other's
+ * owned namespaces.
+ */
+TEST(listns_cannot_see_sibling_userns_namespaces)
+{
+ int pipefd[2];
+ pid_t pid1, pid2;
+ int status;
+ __u64 netns_a_id;
+ int pipefd2[2];
+ bool found_sibling_netns;
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ /* Fork first child - creates user namespace A */
+ pid1 = fork();
+ ASSERT_GE(pid1, 0);
+
+ if (pid1 == 0) {
+ int fd;
+ __u64 netns_a_id;
+ char buf;
+
+ close(pipefd[0]);
+
+ /* Create user namespace A */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Create network namespace owned by user namespace A */
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Get network namespace ID */
+ fd = open("/proc/self/ns/net", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &netns_a_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Send namespace ID to parent */
+ write(pipefd[1], &netns_a_id, sizeof(netns_a_id));
+
+ /* Keep alive for sibling to check */
+ read(pipefd[1], &buf, 1);
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent reads namespace A ID */
+ close(pipefd[1]);
+ netns_a_id = 0;
+ read(pipefd[0], &netns_a_id, sizeof(netns_a_id));
+
+ TH_LOG("User namespace A created network namespace with ID %llu",
+ (unsigned long long)netns_a_id);
+
+ /* Fork second child - creates user namespace B */
+ ASSERT_EQ(pipe(pipefd2), 0);
+
+ pid2 = fork();
+ ASSERT_GE(pid2, 0);
+
+ if (pid2 == 0) {
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWNET,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[100];
+ ssize_t ret;
+ bool found_sibling_netns;
+
+ close(pipefd[0]);
+ close(pipefd2[0]);
+
+ /* Create user namespace B (sibling to A) */
+ if (setup_userns() < 0) {
+ close(pipefd2[1]);
+ exit(1);
+ }
+
+ /* Try to list all network namespaces */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+
+ found_sibling_netns = false;
+ if (ret > 0) {
+ for (ssize_t i = 0; i < ret; i++) {
+ if (ns_ids[i] == netns_a_id) {
+ found_sibling_netns = true;
+ break;
+ }
+ }
+ }
+
+ /* We should NOT see the sibling's network namespace */
+ write(pipefd2[1], &found_sibling_netns, sizeof(found_sibling_netns));
+ close(pipefd2[1]);
+ exit(0);
+ }
+
+ /* Parent reads result from second child */
+ close(pipefd2[1]);
+ found_sibling_netns = false;
+ read(pipefd2[0], &found_sibling_netns, sizeof(found_sibling_netns));
+ close(pipefd2[0]);
+
+ /* Signal first child to exit */
+ close(pipefd[0]);
+
+ /* Wait for both children */
+ waitpid(pid2, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+
+ waitpid(pid1, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+
+ /* Second child should NOT have seen first child's namespace */
+ ASSERT_FALSE(found_sibling_netns);
+ TH_LOG("User namespace B correctly could not see sibling namespace A's network namespace");
+}
+
+/*
+ * Test permission checking with LISTNS_CURRENT_USER.
+ * Verify that listing with LISTNS_CURRENT_USER respects permissions.
+ */
+TEST(listns_current_user_permissions)
+{
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ bool success;
+ ssize_t count;
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0,
+ .spare2 = 0,
+ .user_ns_id = LISTNS_CURRENT_USER,
+ };
+ __u64 ns_ids[100];
+ ssize_t ret;
+ bool success;
+
+ close(pipefd[0]);
+
+ /* Create user namespace */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Create some namespaces owned by this user namespace */
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (unshare(CLONE_NEWUTS) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* List with LISTNS_CURRENT_USER - should see our owned namespaces */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+
+ success = (ret >= 3); /* At least user, net, uts */
+ write(pipefd[1], &success, sizeof(success));
+ write(pipefd[1], &ret, sizeof(ret));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(pipefd[1]);
+
+ success = false;
+ count = 0;
+ read(pipefd[0], &success, sizeof(success));
+ read(pipefd[0], &count, sizeof(count));
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_TRUE(success);
+ TH_LOG("LISTNS_CURRENT_USER returned %zd namespaces", count);
+}
+
+/*
+ * Test that CAP_SYS_ADMIN in parent user namespace allows seeing
+ * child user namespace's owned namespaces.
+ */
+TEST(listns_parent_userns_cap_sys_admin)
+{
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ bool found_child_userns;
+ ssize_t count;
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ int fd;
+ __u64 parent_userns_id;
+ __u64 child_userns_id;
+ struct ns_id_req req;
+ __u64 ns_ids[100];
+ ssize_t ret;
+ bool found_child_userns;
+
+ close(pipefd[0]);
+
+ /* Create parent user namespace - we have CAP_SYS_ADMIN in it */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Get parent user namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &parent_userns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Create child user namespace */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Get child user namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &child_userns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Create namespaces owned by child user namespace */
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* List namespaces owned by parent user namespace */
+ req.size = sizeof(req);
+ req.spare = 0;
+ req.ns_id = 0;
+ req.ns_type = 0;
+ req.spare2 = 0;
+ req.user_ns_id = parent_userns_id;
+
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+
+ /* Should see child user namespace in the list */
+ found_child_userns = false;
+ if (ret > 0) {
+ for (ssize_t i = 0; i < ret; i++) {
+ if (ns_ids[i] == child_userns_id) {
+ found_child_userns = true;
+ break;
+ }
+ }
+ }
+
+ write(pipefd[1], &found_child_userns, sizeof(found_child_userns));
+ write(pipefd[1], &ret, sizeof(ret));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(pipefd[1]);
+
+ found_child_userns = false;
+ count = 0;
+ read(pipefd[0], &found_child_userns, sizeof(found_child_userns));
+ read(pipefd[0], &count, sizeof(count));
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_TRUE(found_child_userns);
+ TH_LOG("Process with CAP_SYS_ADMIN in parent user namespace saw child user namespace (total: %zd)",
+ count);
+}
+
+/*
+ * Test that we can see user namespaces we have CAP_SYS_ADMIN inside of.
+ * This is different from seeing namespaces owned by a user namespace.
+ */
+TEST(listns_cap_sys_admin_inside_userns)
+{
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ bool found_ours;
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ int fd;
+ __u64 our_userns_id;
+ struct ns_id_req req;
+ __u64 ns_ids[100];
+ ssize_t ret;
+ bool found_ours;
+
+ close(pipefd[0]);
+
+ /* Create user namespace - we have CAP_SYS_ADMIN inside it */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Get our user namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &our_userns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* List all user namespaces globally */
+ req.size = sizeof(req);
+ req.spare = 0;
+ req.ns_id = 0;
+ req.ns_type = CLONE_NEWUSER;
+ req.spare2 = 0;
+ req.user_ns_id = 0;
+
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+
+ /* We should be able to see our own user namespace */
+ found_ours = false;
+ if (ret > 0) {
+ for (ssize_t i = 0; i < ret; i++) {
+ if (ns_ids[i] == our_userns_id) {
+ found_ours = true;
+ break;
+ }
+ }
+ }
+
+ write(pipefd[1], &found_ours, sizeof(found_ours));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(pipefd[1]);
+
+ found_ours = false;
+ read(pipefd[0], &found_ours, sizeof(found_ours));
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_TRUE(found_ours);
+ TH_LOG("Process can see user namespace it has CAP_SYS_ADMIN inside of");
+}
+
+/*
+ * Test that dropping CAP_SYS_ADMIN restricts what we can see.
+ */
+TEST(listns_drop_cap_sys_admin)
+{
+ cap_t caps;
+ cap_value_t cap_list[1] = { CAP_SYS_ADMIN };
+
+ /* This test needs to start with CAP_SYS_ADMIN */
+ caps = cap_get_proc();
+ if (!caps) {
+ SKIP(return, "Cannot get capabilities");
+ }
+
+ cap_flag_value_t cap_val;
+ if (cap_get_flag(caps, CAP_SYS_ADMIN, CAP_EFFECTIVE, &cap_val) < 0) {
+ cap_free(caps);
+ SKIP(return, "Cannot check CAP_SYS_ADMIN");
+ }
+
+ if (cap_val != CAP_SET) {
+ cap_free(caps);
+ SKIP(return, "Test needs CAP_SYS_ADMIN to start");
+ }
+ cap_free(caps);
+
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ bool correct;
+ ssize_t count_before, count_after;
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWNET,
+ .spare2 = 0,
+ .user_ns_id = LISTNS_CURRENT_USER,
+ };
+ __u64 ns_ids_before[100];
+ ssize_t count_before;
+ __u64 ns_ids_after[100];
+ ssize_t count_after;
+ bool correct;
+
+ close(pipefd[0]);
+
+ /* Create user namespace */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Count namespaces with CAP_SYS_ADMIN */
+ count_before = sys_listns(&req, ns_ids_before, ARRAY_SIZE(ns_ids_before), 0);
+
+ /* Drop CAP_SYS_ADMIN */
+ caps = cap_get_proc();
+ if (caps) {
+ cap_set_flag(caps, CAP_EFFECTIVE, 1, cap_list, CAP_CLEAR);
+ cap_set_flag(caps, CAP_PERMITTED, 1, cap_list, CAP_CLEAR);
+ cap_set_proc(caps);
+ cap_free(caps);
+ }
+
+ /* Ensure we can't regain the capability */
+ prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+
+ /* Count namespaces without CAP_SYS_ADMIN */
+ count_after = sys_listns(&req, ns_ids_after, ARRAY_SIZE(ns_ids_after), 0);
+
+ /* Without CAP_SYS_ADMIN, we should see same or fewer namespaces */
+ correct = (count_after <= count_before);
+
+ write(pipefd[1], &correct, sizeof(correct));
+ write(pipefd[1], &count_before, sizeof(count_before));
+ write(pipefd[1], &count_after, sizeof(count_after));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(pipefd[1]);
+
+ correct = false;
+ count_before = 0;
+ count_after = 0;
+ read(pipefd[0], &correct, sizeof(correct));
+ read(pipefd[0], &count_before, sizeof(count_before));
+ read(pipefd[0], &count_after, sizeof(count_after));
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_TRUE(correct);
+ TH_LOG("With CAP_SYS_ADMIN: %zd namespaces, without: %zd namespaces",
+ count_before, count_after);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/listns_test.c b/tools/testing/selftests/namespaces/listns_test.c
new file mode 100644
index 000000000000..8a95789d6a87
--- /dev/null
+++ b/tools/testing/selftests/namespaces/listns_test.c
@@ -0,0 +1,679 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/nsfs.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "../kselftest_harness.h"
+#include "../filesystems/utils.h"
+#include "wrappers.h"
+
+/*
+ * Test basic listns() functionality with the unified namespace tree.
+ * List all active namespaces globally.
+ */
+TEST(listns_basic_unified)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0, /* All types */
+ .spare2 = 0,
+ .user_ns_id = 0, /* Global listing */
+ };
+ __u64 ns_ids[100];
+ ssize_t ret;
+
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ TH_LOG("listns failed: %s (errno=%d)", strerror(errno), errno);
+ ASSERT_TRUE(false);
+ }
+
+ /* Should find at least the initial namespaces */
+ ASSERT_GT(ret, 0);
+ TH_LOG("Found %zd active namespaces", ret);
+
+ /* Verify all returned IDs are non-zero */
+ for (ssize_t i = 0; i < ret; i++) {
+ ASSERT_NE(ns_ids[i], 0);
+ TH_LOG(" [%zd] ns_id: %llu", i, (unsigned long long)ns_ids[i]);
+ }
+}
+
+/*
+ * Test listns() with type filtering.
+ * List only network namespaces.
+ */
+TEST(listns_filter_by_type)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWNET, /* Only network namespaces */
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[100];
+ ssize_t ret;
+
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ TH_LOG("listns failed: %s (errno=%d)", strerror(errno), errno);
+ ASSERT_TRUE(false);
+ }
+ ASSERT_GE(ret, 0);
+
+ /* Should find at least init_net */
+ ASSERT_GT(ret, 0);
+ TH_LOG("Found %zd active network namespaces", ret);
+
+ /* Verify we can open each namespace and it's actually a network namespace */
+ for (ssize_t i = 0; i < ret && i < 5; i++) {
+ struct nsfs_file_handle nsfh = {
+ .ns_id = ns_ids[i],
+ .ns_type = CLONE_NEWNET,
+ .ns_inum = 0,
+ };
+ struct file_handle *fh;
+ int fd;
+
+ fh = (struct file_handle *)malloc(sizeof(*fh) + sizeof(nsfh));
+ ASSERT_NE(fh, NULL);
+ fh->handle_bytes = sizeof(nsfh);
+ fh->handle_type = 0;
+ memcpy(fh->f_handle, &nsfh, sizeof(nsfh));
+
+ fd = open_by_handle_at(-10003, fh, O_RDONLY);
+ free(fh);
+
+ if (fd >= 0) {
+ int ns_type;
+ /* Verify it's a network namespace via ioctl */
+ ns_type = ioctl(fd, NS_GET_NSTYPE);
+ if (ns_type >= 0) {
+ ASSERT_EQ(ns_type, CLONE_NEWNET);
+ }
+ close(fd);
+ }
+ }
+}
+
+/*
+ * Test listns() pagination.
+ * List namespaces in batches.
+ */
+TEST(listns_pagination)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 batch1[2], batch2[2];
+ ssize_t ret1, ret2;
+
+ /* Get first batch */
+ ret1 = sys_listns(&req, batch1, ARRAY_SIZE(batch1), 0);
+ if (ret1 < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ TH_LOG("listns failed: %s (errno=%d)", strerror(errno), errno);
+ ASSERT_TRUE(false);
+ }
+ ASSERT_GE(ret1, 0);
+
+ if (ret1 == 0)
+ SKIP(return, "No namespaces found");
+
+ TH_LOG("First batch: %zd namespaces", ret1);
+
+ /* Get second batch using last ID from first batch */
+ if (ret1 == ARRAY_SIZE(batch1)) {
+ req.ns_id = batch1[ret1 - 1];
+ ret2 = sys_listns(&req, batch2, ARRAY_SIZE(batch2), 0);
+ ASSERT_GE(ret2, 0);
+
+ TH_LOG("Second batch: %zd namespaces (after ns_id=%llu)",
+ ret2, (unsigned long long)req.ns_id);
+
+ /* If we got more results, verify IDs are monotonically increasing */
+ if (ret2 > 0) {
+ ASSERT_GT(batch2[0], batch1[ret1 - 1]);
+ TH_LOG("Pagination working: %llu > %llu",
+ (unsigned long long)batch2[0],
+ (unsigned long long)batch1[ret1 - 1]);
+ }
+ } else {
+ TH_LOG("All namespaces fit in first batch");
+ }
+}
+
+/*
+ * Test listns() with LISTNS_CURRENT_USER.
+ * List namespaces owned by current user namespace.
+ */
+TEST(listns_current_user)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0,
+ .spare2 = 0,
+ .user_ns_id = LISTNS_CURRENT_USER,
+ };
+ __u64 ns_ids[100];
+ ssize_t ret;
+
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ TH_LOG("listns failed: %s (errno=%d)", strerror(errno), errno);
+ ASSERT_TRUE(false);
+ }
+ ASSERT_GE(ret, 0);
+
+ /* Should find at least the initial namespaces if we're in init_user_ns */
+ TH_LOG("Found %zd namespaces owned by current user namespace", ret);
+
+ for (ssize_t i = 0; i < ret; i++)
+ TH_LOG(" [%zd] ns_id: %llu", i, (unsigned long long)ns_ids[i]);
+}
+
+/*
+ * Test that listns() only returns active namespaces.
+ * Create a namespace, let it become inactive, verify it's not listed.
+ */
+TEST(listns_only_active)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWNET,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids_before[100], ns_ids_after[100];
+ ssize_t ret_before, ret_after;
+ int pipefd[2];
+ pid_t pid;
+ __u64 new_ns_id = 0;
+ int status;
+
+ /* Get initial list */
+ ret_before = sys_listns(&req, ns_ids_before, ARRAY_SIZE(ns_ids_before), 0);
+ if (ret_before < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ TH_LOG("listns failed: %s (errno=%d)", strerror(errno), errno);
+ ASSERT_TRUE(false);
+ }
+ ASSERT_GE(ret_before, 0);
+
+ TH_LOG("Before: %zd active network namespaces", ret_before);
+
+ /* Create a new namespace in a child process and get its ID */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ int fd;
+ __u64 ns_id;
+
+ close(pipefd[0]);
+
+ /* Create new network namespace */
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Get its ID */
+ fd = open("/proc/self/ns/net", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &ns_id) < 0) {
+ close(fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Send ID to parent */
+ write(pipefd[1], &ns_id, sizeof(ns_id));
+ close(pipefd[1]);
+
+ /* Keep namespace active briefly */
+ usleep(100000);
+ exit(0);
+ }
+
+ /* Parent reads the new namespace ID */
+ {
+ int bytes;
+
+ close(pipefd[1]);
+ bytes = read(pipefd[0], &new_ns_id, sizeof(new_ns_id));
+ close(pipefd[0]);
+
+ if (bytes == sizeof(new_ns_id)) {
+ __u64 ns_ids_during[100];
+ int ret_during;
+
+ TH_LOG("Child created namespace with ID %llu", (unsigned long long)new_ns_id);
+
+ /* List namespaces while child is still alive - should see new one */
+ ret_during = sys_listns(&req, ns_ids_during, ARRAY_SIZE(ns_ids_during), 0);
+ ASSERT_GE(ret_during, 0);
+ TH_LOG("During: %d active network namespaces", ret_during);
+
+ /* Should have more namespaces than before */
+ ASSERT_GE(ret_during, ret_before);
+ }
+ }
+
+ /* Wait for child to exit */
+ waitpid(pid, &status, 0);
+
+ /* Give time for namespace to become inactive */
+ usleep(100000);
+
+ /* List namespaces after child exits - should not see new one */
+ ret_after = sys_listns(&req, ns_ids_after, ARRAY_SIZE(ns_ids_after), 0);
+ ASSERT_GE(ret_after, 0);
+ TH_LOG("After: %zd active network namespaces", ret_after);
+
+ /* Verify the new namespace ID is not in the after list */
+ if (new_ns_id != 0) {
+ bool found = false;
+
+ for (ssize_t i = 0; i < ret_after; i++) {
+ if (ns_ids_after[i] == new_ns_id) {
+ found = true;
+ break;
+ }
+ }
+ ASSERT_FALSE(found);
+ }
+}
+
+/*
+ * Test listns() with specific user namespace ID.
+ * Create a user namespace and list namespaces it owns.
+ */
+TEST(listns_specific_userns)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0,
+ .spare2 = 0,
+ .user_ns_id = 0, /* Will be filled with created userns ID */
+ };
+ __u64 ns_ids[100];
+ int sv[2];
+ pid_t pid;
+ int status;
+ __u64 user_ns_id = 0;
+ int bytes;
+ ssize_t ret;
+
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sv), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ int fd;
+ __u64 ns_id;
+ char buf;
+
+ close(sv[0]);
+
+ /* Create new user namespace */
+ if (setup_userns() < 0) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ /* Get user namespace ID */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &ns_id) < 0) {
+ close(fd);
+ close(sv[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Send ID to parent */
+ if (write(sv[1], &ns_id, sizeof(ns_id)) != sizeof(ns_id)) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ /* Create some namespaces owned by this user namespace */
+ unshare(CLONE_NEWNET);
+ unshare(CLONE_NEWUTS);
+
+ /* Wait for parent signal */
+ if (read(sv[1], &buf, 1) != 1) {
+ close(sv[1]);
+ exit(1);
+ }
+ close(sv[1]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(sv[1]);
+ bytes = read(sv[0], &user_ns_id, sizeof(user_ns_id));
+
+ if (bytes != sizeof(user_ns_id)) {
+ close(sv[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to get user namespace ID from child");
+ }
+
+ TH_LOG("Child created user namespace with ID %llu", (unsigned long long)user_ns_id);
+
+ /* List namespaces owned by this user namespace */
+ req.user_ns_id = user_ns_id;
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+
+ if (ret < 0) {
+ TH_LOG("listns failed: %s (errno=%d)", strerror(errno), errno);
+ close(sv[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ if (errno == ENOSYS) {
+ SKIP(return, "listns() not supported");
+ }
+ ASSERT_GE(ret, 0);
+ }
+
+ TH_LOG("Found %zd namespaces owned by user namespace %llu", ret,
+ (unsigned long long)user_ns_id);
+
+ /* Should find at least the network and UTS namespaces we created */
+ if (ret > 0) {
+ for (ssize_t i = 0; i < ret && i < 10; i++)
+ TH_LOG(" [%zd] ns_id: %llu", i, (unsigned long long)ns_ids[i]);
+ }
+
+ /* Signal child to exit */
+ if (write(sv[0], "X", 1) != 1) {
+ close(sv[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ ASSERT_TRUE(false);
+ }
+ close(sv[0]);
+ waitpid(pid, &status, 0);
+}
+
+/*
+ * Test listns() with multiple namespace types filter.
+ */
+TEST(listns_multiple_types)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWNET | CLONE_NEWUTS, /* Network and UTS */
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[100];
+ ssize_t ret;
+
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ TH_LOG("listns failed: %s (errno=%d)", strerror(errno), errno);
+ ASSERT_TRUE(false);
+ }
+ ASSERT_GE(ret, 0);
+
+ TH_LOG("Found %zd active network/UTS namespaces", ret);
+
+ for (ssize_t i = 0; i < ret; i++)
+ TH_LOG(" [%zd] ns_id: %llu", i, (unsigned long long)ns_ids[i]);
+}
+
+/*
+ * Test that hierarchical active reference propagation keeps parent
+ * user namespaces visible in listns().
+ */
+TEST(listns_hierarchical_visibility)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 parent_ns_id = 0, child_ns_id = 0;
+ int sv[2];
+ pid_t pid;
+ int status;
+ int bytes;
+ __u64 ns_ids[100];
+ ssize_t ret;
+ bool found_parent, found_child;
+
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sv), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ int fd;
+ char buf;
+
+ close(sv[0]);
+
+ /* Create parent user namespace */
+ if (setup_userns() < 0) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &parent_ns_id) < 0) {
+ close(fd);
+ close(sv[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Create child user namespace */
+ if (setup_userns() < 0) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ if (ioctl(fd, NS_GET_ID, &child_ns_id) < 0) {
+ close(fd);
+ close(sv[1]);
+ exit(1);
+ }
+ close(fd);
+
+ /* Send both IDs to parent */
+ if (write(sv[1], &parent_ns_id, sizeof(parent_ns_id)) != sizeof(parent_ns_id)) {
+ close(sv[1]);
+ exit(1);
+ }
+ if (write(sv[1], &child_ns_id, sizeof(child_ns_id)) != sizeof(child_ns_id)) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ /* Wait for parent signal */
+ if (read(sv[1], &buf, 1) != 1) {
+ close(sv[1]);
+ exit(1);
+ }
+ close(sv[1]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(sv[1]);
+
+ /* Read both namespace IDs */
+ bytes = read(sv[0], &parent_ns_id, sizeof(parent_ns_id));
+ bytes += read(sv[0], &child_ns_id, sizeof(child_ns_id));
+
+ if (bytes != (int)(2 * sizeof(__u64))) {
+ close(sv[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to get namespace IDs from child");
+ }
+
+ TH_LOG("Parent user namespace ID: %llu", (unsigned long long)parent_ns_id);
+ TH_LOG("Child user namespace ID: %llu", (unsigned long long)child_ns_id);
+
+ /* List all user namespaces */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+
+ if (ret < 0 && errno == ENOSYS) {
+ close(sv[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "listns() not supported");
+ }
+
+ ASSERT_GE(ret, 0);
+ TH_LOG("Found %zd active user namespaces", ret);
+
+ /* Both parent and child should be visible (active due to child process) */
+ found_parent = false;
+ found_child = false;
+ for (ssize_t i = 0; i < ret; i++) {
+ if (ns_ids[i] == parent_ns_id)
+ found_parent = true;
+ if (ns_ids[i] == child_ns_id)
+ found_child = true;
+ }
+
+ TH_LOG("Parent namespace %s, child namespace %s",
+ found_parent ? "found" : "NOT FOUND",
+ found_child ? "found" : "NOT FOUND");
+
+ ASSERT_TRUE(found_child);
+ /* With hierarchical propagation, parent should also be active */
+ ASSERT_TRUE(found_parent);
+
+ /* Signal child to exit */
+ if (write(sv[0], "X", 1) != 1) {
+ close(sv[0]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ ASSERT_TRUE(false);
+ }
+ close(sv[0]);
+ waitpid(pid, &status, 0);
+}
+
+/*
+ * Test error cases for listns().
+ */
+TEST(listns_error_cases)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[10];
+ int ret;
+
+ /* Test with invalid flags */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0xFFFF);
+ if (errno == ENOSYS) {
+ /* listns() not supported, skip this check */
+ } else {
+ ASSERT_LT(ret, 0);
+ ASSERT_EQ(errno, EINVAL);
+ }
+
+ /* Test with NULL ns_ids array */
+ ret = sys_listns(&req, NULL, 10, 0);
+ ASSERT_LT(ret, 0);
+
+ /* Test with invalid spare field */
+ req.spare = 1;
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (errno == ENOSYS) {
+ /* listns() not supported, skip this check */
+ } else {
+ ASSERT_LT(ret, 0);
+ ASSERT_EQ(errno, EINVAL);
+ }
+ req.spare = 0;
+
+ /* Test with huge nr_ns_ids */
+ ret = sys_listns(&req, ns_ids, 2000000, 0);
+ if (errno == ENOSYS) {
+ /* listns() not supported, skip this check */
+ } else {
+ ASSERT_LT(ret, 0);
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/ns_active_ref_test.c b/tools/testing/selftests/namespaces/ns_active_ref_test.c
new file mode 100644
index 000000000000..093268f0efaa
--- /dev/null
+++ b/tools/testing/selftests/namespaces/ns_active_ref_test.c
@@ -0,0 +1,2672 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/nsfs.h>
+#include <sys/mount.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <pthread.h>
+#include "../kselftest_harness.h"
+#include "../filesystems/utils.h"
+#include "wrappers.h"
+
+#ifndef FD_NSFS_ROOT
+#define FD_NSFS_ROOT -10003 /* Root of the nsfs filesystem */
+#endif
+
+#ifndef FILEID_NSFS
+#define FILEID_NSFS 0xf1
+#endif
+
+/*
+ * Test that initial namespaces can be reopened via file handle.
+ * Initial namespaces should have active ref count of 1 from boot.
+ */
+TEST(init_ns_always_active)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd1, fd2;
+ struct stat st1, st2;
+
+ handle = malloc(sizeof(*handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(handle, NULL);
+
+ /* Open initial network namespace */
+ fd1 = open("/proc/1/ns/net", O_RDONLY);
+ ASSERT_GE(fd1, 0);
+
+ /* Get file handle for initial namespace */
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(fd1, "", handle, &mount_id, AT_EMPTY_PATH);
+ if (ret < 0 && errno == EOPNOTSUPP) {
+ SKIP(free(handle); close(fd1);
+ return, "nsfs doesn't support file handles");
+ }
+ ASSERT_EQ(ret, 0);
+
+ /* Close the namespace fd */
+ close(fd1);
+
+ /* Try to reopen via file handle - should succeed since init ns is always active */
+ fd2 = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (fd2 < 0 && (errno == EINVAL || errno == EOPNOTSUPP)) {
+ SKIP(free(handle);
+ return, "open_by_handle_at with FD_NSFS_ROOT not supported");
+ }
+ ASSERT_GE(fd2, 0);
+
+ /* Verify we opened the same namespace */
+ fd1 = open("/proc/1/ns/net", O_RDONLY);
+ ASSERT_GE(fd1, 0);
+ ASSERT_EQ(fstat(fd1, &st1), 0);
+ ASSERT_EQ(fstat(fd2, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+
+ close(fd1);
+ close(fd2);
+ free(handle);
+}
+
+/*
+ * Test namespace lifecycle: create a namespace in a child process,
+ * get a file handle while it's active, then try to reopen after
+ * the process exits (namespace becomes inactive).
+ */
+TEST(ns_inactive_after_exit)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ char buf[sizeof(*handle) + MAX_HANDLE_SZ];
+
+ /* Create pipe for passing file handle from child */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new network namespace */
+ ret = unshare(CLONE_NEWNET);
+ if (ret < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Open our new namespace */
+ fd = open("/proc/self/ns/net", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Get file handle for the namespace */
+ handle = (struct file_handle *)buf;
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ close(fd);
+
+ if (ret < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Send handle to parent */
+ write(pipefd[1], buf, sizeof(*handle) + handle->handle_bytes);
+ close(pipefd[1]);
+
+ /* Exit - namespace should become inactive */
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ /* Read file handle from child */
+ ret = read(pipefd[0], buf, sizeof(buf));
+ close(pipefd[0]);
+
+ /* Wait for child to exit */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_GT(ret, 0);
+ handle = (struct file_handle *)buf;
+
+ /* Try to reopen namespace - should fail with ENOENT since it's inactive */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_LT(fd, 0);
+ /* Should fail with ENOENT (namespace inactive) or ESTALE */
+ ASSERT_TRUE(errno == ENOENT || errno == ESTALE);
+}
+
+/*
+ * Test that a namespace remains active while a process is using it,
+ * even after the creating process exits.
+ */
+TEST(ns_active_with_multiple_processes)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int pipefd[2];
+ int syncpipe[2];
+ pid_t pid1, pid2;
+ int status;
+ char buf[sizeof(*handle) + MAX_HANDLE_SZ];
+ char sync_byte;
+
+ /* Create pipes for communication */
+ ASSERT_EQ(pipe(pipefd), 0);
+ ASSERT_EQ(pipe(syncpipe), 0);
+
+ pid1 = fork();
+ ASSERT_GE(pid1, 0);
+
+ if (pid1 == 0) {
+ /* First child - creates namespace */
+ close(pipefd[0]);
+ close(syncpipe[1]);
+
+ /* Create new network namespace */
+ ret = unshare(CLONE_NEWNET);
+ if (ret < 0) {
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+
+ /* Open and get handle */
+ fd = open("/proc/self/ns/net", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+
+ handle = (struct file_handle *)buf;
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ close(fd);
+
+ if (ret < 0) {
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+
+ /* Send handle to parent */
+ write(pipefd[1], buf, sizeof(*handle) + handle->handle_bytes);
+ close(pipefd[1]);
+
+ /* Wait for signal before exiting */
+ read(syncpipe[0], &sync_byte, 1);
+ close(syncpipe[0]);
+ exit(0);
+ }
+
+ /* Parent reads handle */
+ close(pipefd[1]);
+ ret = read(pipefd[0], buf, sizeof(buf));
+ close(pipefd[0]);
+ ASSERT_GT(ret, 0);
+
+ handle = (struct file_handle *)buf;
+
+ /* Create second child that will keep namespace active */
+ pid2 = fork();
+ ASSERT_GE(pid2, 0);
+
+ if (pid2 == 0) {
+ /* Second child - reopens the namespace */
+ close(syncpipe[0]);
+ close(syncpipe[1]);
+
+ /* Open the namespace via handle */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (fd < 0) {
+ exit(1);
+ }
+
+ /* Join the namespace */
+ ret = setns(fd, CLONE_NEWNET);
+ close(fd);
+ if (ret < 0) {
+ exit(1);
+ }
+
+ /* Sleep to keep namespace active */
+ sleep(1);
+ exit(0);
+ }
+
+ /* Let second child enter the namespace */
+ usleep(100000); /* 100ms */
+
+ /* Signal first child to exit */
+ close(syncpipe[0]);
+ sync_byte = 'X';
+ write(syncpipe[1], &sync_byte, 1);
+ close(syncpipe[1]);
+
+ /* Wait for first child */
+ waitpid(pid1, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+
+ /* Namespace should still be active because second child is using it */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_GE(fd, 0);
+ close(fd);
+
+ /* Wait for second child */
+ waitpid(pid2, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+}
+
+/*
+ * Test user namespace active ref tracking via credential lifecycle
+ */
+TEST(userns_active_ref_lifecycle)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ char buf[sizeof(*handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new user namespace */
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Set up uid/gid mappings */
+ int uid_map_fd = open("/proc/self/uid_map", O_WRONLY);
+ int gid_map_fd = open("/proc/self/gid_map", O_WRONLY);
+ int setgroups_fd = open("/proc/self/setgroups", O_WRONLY);
+
+ if (uid_map_fd >= 0 && gid_map_fd >= 0 && setgroups_fd >= 0) {
+ write(setgroups_fd, "deny", 4);
+ close(setgroups_fd);
+
+ char mapping[64];
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getuid());
+ write(uid_map_fd, mapping, strlen(mapping));
+ close(uid_map_fd);
+
+ snprintf(mapping, sizeof(mapping), "0 %d 1", getgid());
+ write(gid_map_fd, mapping, strlen(mapping));
+ close(gid_map_fd);
+ }
+
+ /* Get file handle */
+ fd = open("/proc/self/ns/user", O_RDONLY);
+ if (fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ handle = (struct file_handle *)buf;
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ close(fd);
+
+ if (ret < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Send handle to parent */
+ write(pipefd[1], buf, sizeof(*handle) + handle->handle_bytes);
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(pipefd[1]);
+ ret = read(pipefd[0], buf, sizeof(buf));
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_GT(ret, 0);
+ handle = (struct file_handle *)buf;
+
+ /* Namespace should be inactive after all tasks exit */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_LT(fd, 0);
+ ASSERT_TRUE(errno == ENOENT || errno == ESTALE);
+}
+
+/*
+ * Test PID namespace active ref tracking
+ */
+TEST(pidns_active_ref_lifecycle)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ char buf[sizeof(*handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Create new PID namespace */
+ ret = unshare(CLONE_NEWPID);
+ if (ret < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ /* Fork to actually enter the PID namespace */
+ pid_t child = fork();
+ if (child < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ if (child == 0) {
+ /* Grandchild - in new PID namespace */
+ fd = open("/proc/self/ns/pid", O_RDONLY);
+ if (fd < 0) {
+ exit(1);
+ }
+
+ handle = (struct file_handle *)buf;
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ close(fd);
+
+ if (ret < 0) {
+ exit(1);
+ }
+
+ /* Send handle to grandparent */
+ write(pipefd[1], buf, sizeof(*handle) + handle->handle_bytes);
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Wait for grandchild */
+ waitpid(child, NULL, 0);
+ exit(0);
+ }
+
+ /* Parent */
+ close(pipefd[1]);
+ ret = read(pipefd[0], buf, sizeof(buf));
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_GT(ret, 0);
+ handle = (struct file_handle *)buf;
+
+ /* Namespace should be inactive after all processes exit */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_LT(fd, 0);
+ ASSERT_TRUE(errno == ENOENT || errno == ESTALE);
+}
+
+/*
+ * Test that an open file descriptor keeps a namespace active.
+ * Even after the creating process exits, the namespace should remain
+ * active as long as an fd is held open.
+ */
+TEST(ns_fd_keeps_active)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int nsfd;
+ int pipe_child_ready[2];
+ int pipe_parent_ready[2];
+ pid_t pid;
+ int status;
+ char buf[sizeof(*handle) + MAX_HANDLE_SZ];
+ char sync_byte;
+ char proc_path[64];
+
+ ASSERT_EQ(pipe(pipe_child_ready), 0);
+ ASSERT_EQ(pipe(pipe_parent_ready), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipe_child_ready[0]);
+ close(pipe_parent_ready[1]);
+
+ TH_LOG("Child: creating new network namespace");
+
+ /* Create new network namespace */
+ ret = unshare(CLONE_NEWNET);
+ if (ret < 0) {
+ TH_LOG("Child: unshare(CLONE_NEWNET) failed: %s", strerror(errno));
+ close(pipe_child_ready[1]);
+ close(pipe_parent_ready[0]);
+ exit(1);
+ }
+
+ TH_LOG("Child: network namespace created successfully");
+
+ /* Get file handle for the namespace */
+ nsfd = open("/proc/self/ns/net", O_RDONLY);
+ if (nsfd < 0) {
+ TH_LOG("Child: failed to open /proc/self/ns/net: %s", strerror(errno));
+ close(pipe_child_ready[1]);
+ close(pipe_parent_ready[0]);
+ exit(1);
+ }
+
+ TH_LOG("Child: opened namespace fd %d", nsfd);
+
+ handle = (struct file_handle *)buf;
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(nsfd, "", handle, &mount_id, AT_EMPTY_PATH);
+ close(nsfd);
+
+ if (ret < 0) {
+ TH_LOG("Child: name_to_handle_at failed: %s", strerror(errno));
+ close(pipe_child_ready[1]);
+ close(pipe_parent_ready[0]);
+ exit(1);
+ }
+
+ TH_LOG("Child: got file handle (bytes=%u)", handle->handle_bytes);
+
+ /* Send file handle to parent */
+ ret = write(pipe_child_ready[1], buf, sizeof(*handle) + handle->handle_bytes);
+ TH_LOG("Child: sent %d bytes of file handle to parent", ret);
+ close(pipe_child_ready[1]);
+
+ /* Wait for parent to open the fd */
+ TH_LOG("Child: waiting for parent to open fd");
+ ret = read(pipe_parent_ready[0], &sync_byte, 1);
+ close(pipe_parent_ready[0]);
+
+ TH_LOG("Child: parent signaled (read %d bytes), exiting now", ret);
+ /* Exit - namespace should stay active because parent holds fd */
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipe_child_ready[1]);
+ close(pipe_parent_ready[0]);
+
+ TH_LOG("Parent: reading file handle from child");
+
+ /* Read file handle from child */
+ ret = read(pipe_child_ready[0], buf, sizeof(buf));
+ close(pipe_child_ready[0]);
+ ASSERT_GT(ret, 0);
+ handle = (struct file_handle *)buf;
+
+ TH_LOG("Parent: received %d bytes, handle size=%u", ret, handle->handle_bytes);
+
+ /* Open the child's namespace while it's still alive */
+ snprintf(proc_path, sizeof(proc_path), "/proc/%d/ns/net", pid);
+ TH_LOG("Parent: opening child's namespace at %s", proc_path);
+ nsfd = open(proc_path, O_RDONLY);
+ if (nsfd < 0) {
+ TH_LOG("Parent: failed to open %s: %s", proc_path, strerror(errno));
+ close(pipe_parent_ready[1]);
+ kill(pid, SIGKILL);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to open child's namespace");
+ }
+
+ TH_LOG("Parent: opened child's namespace, got fd %d", nsfd);
+
+ /* Signal child that we have the fd */
+ sync_byte = 'G';
+ write(pipe_parent_ready[1], &sync_byte, 1);
+ close(pipe_parent_ready[1]);
+ TH_LOG("Parent: signaled child that we have the fd");
+
+ /* Wait for child to exit */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ TH_LOG("Child exited, parent holds fd %d to namespace", nsfd);
+
+ /*
+ * Namespace should still be ACTIVE because we hold an fd.
+ * We should be able to reopen it via file handle.
+ */
+ TH_LOG("Attempting to reopen namespace via file handle (should succeed - fd held)");
+ int fd2 = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_GE(fd2, 0);
+
+ TH_LOG("Successfully reopened namespace via file handle, got fd %d", fd2);
+
+ /* Verify it's the same namespace */
+ struct stat st1, st2;
+ ASSERT_EQ(fstat(nsfd, &st1), 0);
+ ASSERT_EQ(fstat(fd2, &st2), 0);
+ TH_LOG("Namespace inodes: nsfd=%lu, fd2=%lu", st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ close(fd2);
+
+ /* Now close the fd - namespace should become inactive */
+ TH_LOG("Closing fd %d - namespace should become inactive", nsfd);
+ close(nsfd);
+
+ /* Now reopening should fail - namespace is inactive */
+ TH_LOG("Attempting to reopen namespace via file handle (should fail - inactive)");
+ fd2 = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_LT(fd2, 0);
+ /* Should fail with ENOENT (inactive) or ESTALE (gone) */
+ TH_LOG("Reopen failed as expected: %s (errno=%d)", strerror(errno), errno);
+ ASSERT_TRUE(errno == ENOENT || errno == ESTALE);
+}
+
+/*
+ * Test hierarchical active reference propagation.
+ * When a child namespace is active, its owning user namespace should also
+ * be active automatically due to hierarchical active reference propagation.
+ * This ensures parents are always reachable when children are active.
+ */
+TEST(ns_parent_always_reachable)
+{
+ struct file_handle *parent_handle, *child_handle;
+ int ret;
+ int child_nsfd;
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ __u64 parent_id, child_id;
+ char parent_buf[sizeof(*parent_handle) + MAX_HANDLE_SZ];
+ char child_buf[sizeof(*child_handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ TH_LOG("Child: creating parent user namespace and setting up mappings");
+
+ /* Create parent user namespace with mappings */
+ ret = setup_userns();
+ if (ret < 0) {
+ TH_LOG("Child: setup_userns() for parent failed: %s", strerror(errno));
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ TH_LOG("Child: parent user namespace created, now uid=%d gid=%d", getuid(), getgid());
+
+ /* Get namespace ID for parent user namespace */
+ int parent_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (parent_fd < 0) {
+ TH_LOG("Child: failed to open parent /proc/self/ns/user: %s", strerror(errno));
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ TH_LOG("Child: opened parent userns fd %d", parent_fd);
+
+ if (ioctl(parent_fd, NS_GET_ID, &parent_id) < 0) {
+ TH_LOG("Child: NS_GET_ID for parent failed: %s", strerror(errno));
+ close(parent_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(parent_fd);
+
+ TH_LOG("Child: got parent namespace ID %llu", (unsigned long long)parent_id);
+
+ /* Create child user namespace within parent */
+ TH_LOG("Child: creating nested child user namespace");
+ ret = setup_userns();
+ if (ret < 0) {
+ TH_LOG("Child: setup_userns() for child failed: %s", strerror(errno));
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ TH_LOG("Child: nested child user namespace created, uid=%d gid=%d", getuid(), getgid());
+
+ /* Get namespace ID for child user namespace */
+ int child_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (child_fd < 0) {
+ TH_LOG("Child: failed to open child /proc/self/ns/user: %s", strerror(errno));
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ TH_LOG("Child: opened child userns fd %d", child_fd);
+
+ if (ioctl(child_fd, NS_GET_ID, &child_id) < 0) {
+ TH_LOG("Child: NS_GET_ID for child failed: %s", strerror(errno));
+ close(child_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(child_fd);
+
+ TH_LOG("Child: got child namespace ID %llu", (unsigned long long)child_id);
+
+ /* Send both namespace IDs to parent */
+ TH_LOG("Child: sending both namespace IDs to parent");
+ write(pipefd[1], &parent_id, sizeof(parent_id));
+ write(pipefd[1], &child_id, sizeof(child_id));
+ close(pipefd[1]);
+
+ TH_LOG("Child: exiting - parent userns should become inactive");
+ /* Exit - parent user namespace should become inactive */
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+
+ TH_LOG("Parent: reading both namespace IDs from child");
+
+ /* Read both namespace IDs - fixed size, no parsing needed */
+ ret = read(pipefd[0], &parent_id, sizeof(parent_id));
+ if (ret != sizeof(parent_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read parent namespace ID from child");
+ }
+
+ ret = read(pipefd[0], &child_id, sizeof(child_id));
+ close(pipefd[0]);
+ if (ret != sizeof(child_id)) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read child namespace ID from child");
+ }
+
+ TH_LOG("Parent: received parent_id=%llu, child_id=%llu",
+ (unsigned long long)parent_id, (unsigned long long)child_id);
+
+ /* Construct file handles from namespace IDs */
+ parent_handle = (struct file_handle *)parent_buf;
+ parent_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ parent_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *parent_fh = (struct nsfs_file_handle *)parent_handle->f_handle;
+ parent_fh->ns_id = parent_id;
+ parent_fh->ns_type = 0;
+ parent_fh->ns_inum = 0;
+
+ child_handle = (struct file_handle *)child_buf;
+ child_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ child_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *child_fh = (struct nsfs_file_handle *)child_handle->f_handle;
+ child_fh->ns_id = child_id;
+ child_fh->ns_type = 0;
+ child_fh->ns_inum = 0;
+
+ TH_LOG("Parent: opening child namespace BEFORE child exits");
+
+ /* Open child namespace while child is still alive to keep it active */
+ child_nsfd = open_by_handle_at(FD_NSFS_ROOT, child_handle, O_RDONLY);
+ if (child_nsfd < 0) {
+ TH_LOG("Failed to open child namespace: %s (errno=%d)", strerror(errno), errno);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to open child namespace");
+ }
+
+ TH_LOG("Opened child namespace fd %d", child_nsfd);
+
+ /* Now wait for child to exit */
+ TH_LOG("Parent: waiting for child to exit");
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ TH_LOG("Child process exited, parent holds fd to child namespace");
+
+ /*
+ * With hierarchical active reference propagation:
+ * Since the child namespace is active (parent process holds fd),
+ * the parent user namespace should ALSO be active automatically.
+ * This is because when we took an active reference on the child,
+ * it propagated up to the owning user namespace.
+ */
+ TH_LOG("Attempting to reopen parent namespace (should SUCCEED - hierarchical propagation)");
+ int parent_fd = open_by_handle_at(FD_NSFS_ROOT, parent_handle, O_RDONLY);
+ ASSERT_GE(parent_fd, 0);
+
+ TH_LOG("SUCCESS: Parent namespace is active (fd=%d) due to active child", parent_fd);
+
+ /* Verify we can also get parent via NS_GET_USERNS */
+ TH_LOG("Verifying NS_GET_USERNS also works");
+ int parent_fd2 = ioctl(child_nsfd, NS_GET_USERNS);
+ if (parent_fd2 < 0) {
+ close(parent_fd);
+ close(child_nsfd);
+ TH_LOG("NS_GET_USERNS failed: %s (errno=%d)", strerror(errno), errno);
+ SKIP(return, "NS_GET_USERNS not supported or failed");
+ }
+
+ TH_LOG("NS_GET_USERNS succeeded, got parent fd %d", parent_fd2);
+
+ /* Verify both methods give us the same namespace */
+ struct stat st1, st2;
+ ASSERT_EQ(fstat(parent_fd, &st1), 0);
+ ASSERT_EQ(fstat(parent_fd2, &st2), 0);
+ TH_LOG("Parent namespace inodes: parent_fd=%lu, parent_fd2=%lu", st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+
+ /*
+ * Close child fd - parent should remain active because we still
+ * hold direct references to it (parent_fd and parent_fd2).
+ */
+ TH_LOG("Closing child fd - parent should remain active (direct refs held)");
+ close(child_nsfd);
+
+ /* Parent should still be openable */
+ TH_LOG("Verifying parent still active via file handle");
+ int parent_fd3 = open_by_handle_at(FD_NSFS_ROOT, parent_handle, O_RDONLY);
+ ASSERT_GE(parent_fd3, 0);
+ close(parent_fd3);
+
+ TH_LOG("Closing all fds to parent namespace");
+ close(parent_fd);
+ close(parent_fd2);
+
+ /* Both should now be inactive */
+ TH_LOG("Attempting to reopen parent (should fail - inactive, no refs)");
+ parent_fd = open_by_handle_at(FD_NSFS_ROOT, parent_handle, O_RDONLY);
+ ASSERT_LT(parent_fd, 0);
+ TH_LOG("Parent inactive as expected: %s (errno=%d)", strerror(errno), errno);
+ ASSERT_TRUE(errno == ENOENT || errno == ESTALE);
+}
+
+/*
+ * Test that bind mounts keep namespaces in the tree even when inactive
+ */
+TEST(ns_bind_mount_keeps_in_tree)
+{
+ struct file_handle *handle;
+ int mount_id;
+ int ret;
+ int fd;
+ int pipefd[2];
+ pid_t pid;
+ int status;
+ char buf[sizeof(*handle) + MAX_HANDLE_SZ];
+ char tmpfile[] = "/tmp/ns-test-XXXXXX";
+ int tmpfd;
+
+ /* Create temporary file for bind mount */
+ tmpfd = mkstemp(tmpfile);
+ if (tmpfd < 0) {
+ SKIP(return, "Cannot create temporary file");
+ }
+ close(tmpfd);
+
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+
+ /* Unshare mount namespace and make mounts private to avoid propagation */
+ ret = unshare(CLONE_NEWNS);
+ if (ret < 0) {
+ close(pipefd[1]);
+ unlink(tmpfile);
+ exit(1);
+ }
+ ret = mount(NULL, "/", NULL, MS_PRIVATE | MS_REC, NULL);
+ if (ret < 0) {
+ close(pipefd[1]);
+ unlink(tmpfile);
+ exit(1);
+ }
+
+ /* Create new network namespace */
+ ret = unshare(CLONE_NEWNET);
+ if (ret < 0) {
+ close(pipefd[1]);
+ unlink(tmpfile);
+ exit(1);
+ }
+
+ /* Bind mount the namespace */
+ ret = mount("/proc/self/ns/net", tmpfile, NULL, MS_BIND, NULL);
+ if (ret < 0) {
+ close(pipefd[1]);
+ unlink(tmpfile);
+ exit(1);
+ }
+
+ /* Get file handle */
+ fd = open("/proc/self/ns/net", O_RDONLY);
+ if (fd < 0) {
+ umount(tmpfile);
+ close(pipefd[1]);
+ unlink(tmpfile);
+ exit(1);
+ }
+
+ handle = (struct file_handle *)buf;
+ handle->handle_bytes = MAX_HANDLE_SZ;
+ ret = name_to_handle_at(fd, "", handle, &mount_id, AT_EMPTY_PATH);
+ close(fd);
+
+ if (ret < 0) {
+ umount(tmpfile);
+ close(pipefd[1]);
+ unlink(tmpfile);
+ exit(1);
+ }
+
+ /* Send handle to parent */
+ write(pipefd[1], buf, sizeof(*handle) + handle->handle_bytes);
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(pipefd[1]);
+ ret = read(pipefd[0], buf, sizeof(buf));
+ close(pipefd[0]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ ASSERT_GT(ret, 0);
+ handle = (struct file_handle *)buf;
+
+ /*
+ * Namespace should be inactive but still in tree due to bind mount.
+ * Reopening should fail with ENOENT (inactive) not ESTALE (not in tree).
+ */
+ fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_LT(fd, 0);
+ /* Should be ENOENT (inactive) since bind mount keeps it in tree */
+ if (errno != ENOENT && errno != ESTALE) {
+ TH_LOG("Unexpected error: %d", errno);
+ }
+
+ /* Cleanup */
+ umount(tmpfile);
+ unlink(tmpfile);
+}
+
+/*
+ * Test multi-level hierarchy (3+ levels deep).
+ * Grandparent → Parent → Child
+ * When child is active, both parent AND grandparent should be active.
+ */
+TEST(ns_multilevel_hierarchy)
+{
+ struct file_handle *gp_handle, *p_handle, *c_handle;
+ int ret, pipefd[2];
+ pid_t pid;
+ int status;
+ __u64 gp_id, p_id, c_id;
+ char gp_buf[sizeof(*gp_handle) + MAX_HANDLE_SZ];
+ char p_buf[sizeof(*p_handle) + MAX_HANDLE_SZ];
+ char c_buf[sizeof(*c_handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ close(pipefd[0]);
+
+ /* Create grandparent user namespace */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int gp_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (gp_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(gp_fd, NS_GET_ID, &gp_id) < 0) {
+ close(gp_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(gp_fd);
+
+ /* Create parent user namespace */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int p_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (p_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(p_fd, NS_GET_ID, &p_id) < 0) {
+ close(p_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(p_fd);
+
+ /* Create child user namespace */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int c_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (c_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(c_fd, NS_GET_ID, &c_id) < 0) {
+ close(c_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(c_fd);
+
+ /* Send all three namespace IDs */
+ write(pipefd[1], &gp_id, sizeof(gp_id));
+ write(pipefd[1], &p_id, sizeof(p_id));
+ write(pipefd[1], &c_id, sizeof(c_id));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ close(pipefd[1]);
+
+ /* Read all three namespace IDs - fixed size, no parsing needed */
+ ret = read(pipefd[0], &gp_id, sizeof(gp_id));
+ if (ret != sizeof(gp_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read grandparent namespace ID from child");
+ }
+
+ ret = read(pipefd[0], &p_id, sizeof(p_id));
+ if (ret != sizeof(p_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read parent namespace ID from child");
+ }
+
+ ret = read(pipefd[0], &c_id, sizeof(c_id));
+ close(pipefd[0]);
+ if (ret != sizeof(c_id)) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read child namespace ID from child");
+ }
+
+ /* Construct file handles from namespace IDs */
+ gp_handle = (struct file_handle *)gp_buf;
+ gp_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ gp_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *gp_fh = (struct nsfs_file_handle *)gp_handle->f_handle;
+ gp_fh->ns_id = gp_id;
+ gp_fh->ns_type = 0;
+ gp_fh->ns_inum = 0;
+
+ p_handle = (struct file_handle *)p_buf;
+ p_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ p_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *p_fh = (struct nsfs_file_handle *)p_handle->f_handle;
+ p_fh->ns_id = p_id;
+ p_fh->ns_type = 0;
+ p_fh->ns_inum = 0;
+
+ c_handle = (struct file_handle *)c_buf;
+ c_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ c_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *c_fh = (struct nsfs_file_handle *)c_handle->f_handle;
+ c_fh->ns_id = c_id;
+ c_fh->ns_type = 0;
+ c_fh->ns_inum = 0;
+
+ /* Open child before process exits */
+ int c_fd = open_by_handle_at(FD_NSFS_ROOT, c_handle, O_RDONLY);
+ if (c_fd < 0) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to open child namespace");
+ }
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /*
+ * With 3-level hierarchy and child active:
+ * - Child is active (we hold fd)
+ * - Parent should be active (propagated from child)
+ * - Grandparent should be active (propagated from parent)
+ */
+ TH_LOG("Testing parent active when child is active");
+ int p_fd = open_by_handle_at(FD_NSFS_ROOT, p_handle, O_RDONLY);
+ ASSERT_GE(p_fd, 0);
+
+ TH_LOG("Testing grandparent active when child is active");
+ int gp_fd = open_by_handle_at(FD_NSFS_ROOT, gp_handle, O_RDONLY);
+ ASSERT_GE(gp_fd, 0);
+
+ close(c_fd);
+ close(p_fd);
+ close(gp_fd);
+}
+
+/*
+ * Test multiple children sharing same parent.
+ * Parent should stay active as long as ANY child is active.
+ */
+TEST(ns_multiple_children_same_parent)
+{
+ struct file_handle *p_handle, *c1_handle, *c2_handle;
+ int ret, pipefd[2];
+ pid_t pid;
+ int status;
+ __u64 p_id, c1_id, c2_id;
+ char p_buf[sizeof(*p_handle) + MAX_HANDLE_SZ];
+ char c1_buf[sizeof(*c1_handle) + MAX_HANDLE_SZ];
+ char c2_buf[sizeof(*c2_handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ close(pipefd[0]);
+
+ /* Create parent user namespace */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int p_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (p_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(p_fd, NS_GET_ID, &p_id) < 0) {
+ close(p_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(p_fd);
+
+ /* Create first child user namespace */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int c1_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (c1_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(c1_fd, NS_GET_ID, &c1_id) < 0) {
+ close(c1_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(c1_fd);
+
+ /* Return to parent user namespace and create second child */
+ /* We can't actually do this easily, so let's create a sibling namespace
+ * by creating a network namespace instead */
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int c2_fd = open("/proc/self/ns/net", O_RDONLY);
+ if (c2_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(c2_fd, NS_GET_ID, &c2_id) < 0) {
+ close(c2_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(c2_fd);
+
+ /* Send all namespace IDs */
+ write(pipefd[1], &p_id, sizeof(p_id));
+ write(pipefd[1], &c1_id, sizeof(c1_id));
+ write(pipefd[1], &c2_id, sizeof(c2_id));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ close(pipefd[1]);
+
+ /* Read all three namespace IDs - fixed size, no parsing needed */
+ ret = read(pipefd[0], &p_id, sizeof(p_id));
+ if (ret != sizeof(p_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read parent namespace ID");
+ }
+
+ ret = read(pipefd[0], &c1_id, sizeof(c1_id));
+ if (ret != sizeof(c1_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read first child namespace ID");
+ }
+
+ ret = read(pipefd[0], &c2_id, sizeof(c2_id));
+ close(pipefd[0]);
+ if (ret != sizeof(c2_id)) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read second child namespace ID");
+ }
+
+ /* Construct file handles from namespace IDs */
+ p_handle = (struct file_handle *)p_buf;
+ p_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ p_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *p_fh = (struct nsfs_file_handle *)p_handle->f_handle;
+ p_fh->ns_id = p_id;
+ p_fh->ns_type = 0;
+ p_fh->ns_inum = 0;
+
+ c1_handle = (struct file_handle *)c1_buf;
+ c1_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ c1_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *c1_fh = (struct nsfs_file_handle *)c1_handle->f_handle;
+ c1_fh->ns_id = c1_id;
+ c1_fh->ns_type = 0;
+ c1_fh->ns_inum = 0;
+
+ c2_handle = (struct file_handle *)c2_buf;
+ c2_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ c2_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *c2_fh = (struct nsfs_file_handle *)c2_handle->f_handle;
+ c2_fh->ns_id = c2_id;
+ c2_fh->ns_type = 0;
+ c2_fh->ns_inum = 0;
+
+ /* Open both children before process exits */
+ int c1_fd = open_by_handle_at(FD_NSFS_ROOT, c1_handle, O_RDONLY);
+ int c2_fd = open_by_handle_at(FD_NSFS_ROOT, c2_handle, O_RDONLY);
+
+ if (c1_fd < 0 || c2_fd < 0) {
+ if (c1_fd >= 0) close(c1_fd);
+ if (c2_fd >= 0) close(c2_fd);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to open child namespaces");
+ }
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Parent should be active (both children active) */
+ TH_LOG("Both children active - parent should be active");
+ int p_fd = open_by_handle_at(FD_NSFS_ROOT, p_handle, O_RDONLY);
+ ASSERT_GE(p_fd, 0);
+ close(p_fd);
+
+ /* Close first child - parent should STILL be active */
+ TH_LOG("Closing first child - parent should still be active");
+ close(c1_fd);
+ p_fd = open_by_handle_at(FD_NSFS_ROOT, p_handle, O_RDONLY);
+ ASSERT_GE(p_fd, 0);
+ close(p_fd);
+
+ /* Close second child - NOW parent should become inactive */
+ TH_LOG("Closing second child - parent should become inactive");
+ close(c2_fd);
+ p_fd = open_by_handle_at(FD_NSFS_ROOT, p_handle, O_RDONLY);
+ ASSERT_LT(p_fd, 0);
+}
+
+/*
+ * Test that different namespace types with same owner all contribute
+ * active references to the owning user namespace.
+ */
+TEST(ns_different_types_same_owner)
+{
+ struct file_handle *u_handle, *n_handle, *ut_handle;
+ int ret, pipefd[2];
+ pid_t pid;
+ int status;
+ __u64 u_id, n_id, ut_id;
+ char u_buf[sizeof(*u_handle) + MAX_HANDLE_SZ];
+ char n_buf[sizeof(*n_handle) + MAX_HANDLE_SZ];
+ char ut_buf[sizeof(*ut_handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ close(pipefd[0]);
+
+ /* Create user namespace */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int u_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (u_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(u_fd, NS_GET_ID, &u_id) < 0) {
+ close(u_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(u_fd);
+
+ /* Create network namespace (owned by user namespace) */
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int n_fd = open("/proc/self/ns/net", O_RDONLY);
+ if (n_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(n_fd, NS_GET_ID, &n_id) < 0) {
+ close(n_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(n_fd);
+
+ /* Create UTS namespace (also owned by user namespace) */
+ if (unshare(CLONE_NEWUTS) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int ut_fd = open("/proc/self/ns/uts", O_RDONLY);
+ if (ut_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(ut_fd, NS_GET_ID, &ut_id) < 0) {
+ close(ut_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(ut_fd);
+
+ /* Send all namespace IDs */
+ write(pipefd[1], &u_id, sizeof(u_id));
+ write(pipefd[1], &n_id, sizeof(n_id));
+ write(pipefd[1], &ut_id, sizeof(ut_id));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ close(pipefd[1]);
+
+ /* Read all three namespace IDs - fixed size, no parsing needed */
+ ret = read(pipefd[0], &u_id, sizeof(u_id));
+ if (ret != sizeof(u_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read user namespace ID");
+ }
+
+ ret = read(pipefd[0], &n_id, sizeof(n_id));
+ if (ret != sizeof(n_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read network namespace ID");
+ }
+
+ ret = read(pipefd[0], &ut_id, sizeof(ut_id));
+ close(pipefd[0]);
+ if (ret != sizeof(ut_id)) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read UTS namespace ID");
+ }
+
+ /* Construct file handles from namespace IDs */
+ u_handle = (struct file_handle *)u_buf;
+ u_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ u_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *u_fh = (struct nsfs_file_handle *)u_handle->f_handle;
+ u_fh->ns_id = u_id;
+ u_fh->ns_type = 0;
+ u_fh->ns_inum = 0;
+
+ n_handle = (struct file_handle *)n_buf;
+ n_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ n_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *n_fh = (struct nsfs_file_handle *)n_handle->f_handle;
+ n_fh->ns_id = n_id;
+ n_fh->ns_type = 0;
+ n_fh->ns_inum = 0;
+
+ ut_handle = (struct file_handle *)ut_buf;
+ ut_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ ut_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *ut_fh = (struct nsfs_file_handle *)ut_handle->f_handle;
+ ut_fh->ns_id = ut_id;
+ ut_fh->ns_type = 0;
+ ut_fh->ns_inum = 0;
+
+ /* Open both non-user namespaces before process exits */
+ int n_fd = open_by_handle_at(FD_NSFS_ROOT, n_handle, O_RDONLY);
+ int ut_fd = open_by_handle_at(FD_NSFS_ROOT, ut_handle, O_RDONLY);
+
+ if (n_fd < 0 || ut_fd < 0) {
+ if (n_fd >= 0) close(n_fd);
+ if (ut_fd >= 0) close(ut_fd);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to open namespaces");
+ }
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /*
+ * Both network and UTS namespaces are active.
+ * User namespace should be active (gets 2 active refs).
+ */
+ TH_LOG("Both net and uts active - user namespace should be active");
+ int u_fd = open_by_handle_at(FD_NSFS_ROOT, u_handle, O_RDONLY);
+ ASSERT_GE(u_fd, 0);
+ close(u_fd);
+
+ /* Close network namespace - user namespace should STILL be active */
+ TH_LOG("Closing network ns - user ns should still be active (uts still active)");
+ close(n_fd);
+ u_fd = open_by_handle_at(FD_NSFS_ROOT, u_handle, O_RDONLY);
+ ASSERT_GE(u_fd, 0);
+ close(u_fd);
+
+ /* Close UTS namespace - user namespace should become inactive */
+ TH_LOG("Closing uts ns - user ns should become inactive");
+ close(ut_fd);
+ u_fd = open_by_handle_at(FD_NSFS_ROOT, u_handle, O_RDONLY);
+ ASSERT_LT(u_fd, 0);
+}
+
+/*
+ * Test hierarchical propagation with deep namespace hierarchy.
+ * Create: init_user_ns -> user_A -> user_B -> net_ns
+ * When net_ns is active, both user_A and user_B should be active.
+ * This verifies the conditional recursion in __ns_ref_active_put() works.
+ */
+TEST(ns_deep_hierarchy_propagation)
+{
+ struct file_handle *ua_handle, *ub_handle, *net_handle;
+ int ret, pipefd[2];
+ pid_t pid;
+ int status;
+ __u64 ua_id, ub_id, net_id;
+ char ua_buf[sizeof(*ua_handle) + MAX_HANDLE_SZ];
+ char ub_buf[sizeof(*ub_handle) + MAX_HANDLE_SZ];
+ char net_buf[sizeof(*net_handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ close(pipefd[0]);
+
+ /* Create user_A -> user_B -> net hierarchy */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int ua_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (ua_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(ua_fd, NS_GET_ID, &ua_id) < 0) {
+ close(ua_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(ua_fd);
+
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int ub_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (ub_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(ub_fd, NS_GET_ID, &ub_id) < 0) {
+ close(ub_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(ub_fd);
+
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int net_fd = open("/proc/self/ns/net", O_RDONLY);
+ if (net_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(net_fd, NS_GET_ID, &net_id) < 0) {
+ close(net_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(net_fd);
+
+ /* Send all three namespace IDs */
+ write(pipefd[1], &ua_id, sizeof(ua_id));
+ write(pipefd[1], &ub_id, sizeof(ub_id));
+ write(pipefd[1], &net_id, sizeof(net_id));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ close(pipefd[1]);
+
+ /* Read all three namespace IDs - fixed size, no parsing needed */
+ ret = read(pipefd[0], &ua_id, sizeof(ua_id));
+ if (ret != sizeof(ua_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read user_A namespace ID");
+ }
+
+ ret = read(pipefd[0], &ub_id, sizeof(ub_id));
+ if (ret != sizeof(ub_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read user_B namespace ID");
+ }
+
+ ret = read(pipefd[0], &net_id, sizeof(net_id));
+ close(pipefd[0]);
+ if (ret != sizeof(net_id)) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read network namespace ID");
+ }
+
+ /* Construct file handles from namespace IDs */
+ ua_handle = (struct file_handle *)ua_buf;
+ ua_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ ua_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *ua_fh = (struct nsfs_file_handle *)ua_handle->f_handle;
+ ua_fh->ns_id = ua_id;
+ ua_fh->ns_type = 0;
+ ua_fh->ns_inum = 0;
+
+ ub_handle = (struct file_handle *)ub_buf;
+ ub_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ ub_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *ub_fh = (struct nsfs_file_handle *)ub_handle->f_handle;
+ ub_fh->ns_id = ub_id;
+ ub_fh->ns_type = 0;
+ ub_fh->ns_inum = 0;
+
+ net_handle = (struct file_handle *)net_buf;
+ net_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ net_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *net_fh = (struct nsfs_file_handle *)net_handle->f_handle;
+ net_fh->ns_id = net_id;
+ net_fh->ns_type = 0;
+ net_fh->ns_inum = 0;
+
+ /* Open net_ns before child exits to keep it active */
+ int net_fd = open_by_handle_at(FD_NSFS_ROOT, net_handle, O_RDONLY);
+ if (net_fd < 0) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to open network namespace");
+ }
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* With net_ns active, both user_A and user_B should be active */
+ TH_LOG("Testing user_B active (net_ns active causes propagation)");
+ int ub_fd = open_by_handle_at(FD_NSFS_ROOT, ub_handle, O_RDONLY);
+ ASSERT_GE(ub_fd, 0);
+
+ TH_LOG("Testing user_A active (propagated through user_B)");
+ int ua_fd = open_by_handle_at(FD_NSFS_ROOT, ua_handle, O_RDONLY);
+ ASSERT_GE(ua_fd, 0);
+
+ /* Close net_ns - user_B should stay active (we hold direct ref) */
+ TH_LOG("Closing net_ns, user_B should remain active (direct ref held)");
+ close(net_fd);
+ int ub_fd2 = open_by_handle_at(FD_NSFS_ROOT, ub_handle, O_RDONLY);
+ ASSERT_GE(ub_fd2, 0);
+ close(ub_fd2);
+
+ /* Close user_B - user_A should stay active (we hold direct ref) */
+ TH_LOG("Closing user_B, user_A should remain active (direct ref held)");
+ close(ub_fd);
+ int ua_fd2 = open_by_handle_at(FD_NSFS_ROOT, ua_handle, O_RDONLY);
+ ASSERT_GE(ua_fd2, 0);
+ close(ua_fd2);
+
+ /* Close user_A - everything should become inactive */
+ TH_LOG("Closing user_A, all should become inactive");
+ close(ua_fd);
+
+ /* All should now be inactive */
+ ua_fd = open_by_handle_at(FD_NSFS_ROOT, ua_handle, O_RDONLY);
+ ASSERT_LT(ua_fd, 0);
+}
+
+/*
+ * Test that parent stays active as long as ANY child is active.
+ * Create parent user namespace with two child net namespaces.
+ * Parent should remain active until BOTH children are inactive.
+ */
+TEST(ns_parent_multiple_children_refcount)
+{
+ struct file_handle *parent_handle, *net1_handle, *net2_handle;
+ int ret, pipefd[2], syncpipe[2];
+ pid_t pid;
+ int status;
+ __u64 p_id, n1_id, n2_id;
+ char p_buf[sizeof(*parent_handle) + MAX_HANDLE_SZ];
+ char n1_buf[sizeof(*net1_handle) + MAX_HANDLE_SZ];
+ char n2_buf[sizeof(*net2_handle) + MAX_HANDLE_SZ];
+ char sync_byte;
+
+ ASSERT_EQ(pipe(pipefd), 0);
+ ASSERT_EQ(pipe(syncpipe), 0);
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ close(pipefd[0]);
+ close(syncpipe[1]);
+
+ /* Create parent user namespace */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int p_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (p_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(p_fd, NS_GET_ID, &p_id) < 0) {
+ close(p_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(p_fd);
+
+ /* Create first network namespace */
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+
+ int n1_fd = open("/proc/self/ns/net", O_RDONLY);
+ if (n1_fd < 0) {
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+ if (ioctl(n1_fd, NS_GET_ID, &n1_id) < 0) {
+ close(n1_fd);
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+ /* Keep n1_fd open so first namespace stays active */
+
+ /* Create second network namespace */
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(n1_fd);
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+
+ int n2_fd = open("/proc/self/ns/net", O_RDONLY);
+ if (n2_fd < 0) {
+ close(n1_fd);
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+ if (ioctl(n2_fd, NS_GET_ID, &n2_id) < 0) {
+ close(n1_fd);
+ close(n2_fd);
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+ /* Keep both n1_fd and n2_fd open */
+
+ /* Send all namespace IDs */
+ write(pipefd[1], &p_id, sizeof(p_id));
+ write(pipefd[1], &n1_id, sizeof(n1_id));
+ write(pipefd[1], &n2_id, sizeof(n2_id));
+ close(pipefd[1]);
+
+ /* Wait for parent to signal before exiting */
+ read(syncpipe[0], &sync_byte, 1);
+ close(syncpipe[0]);
+ exit(0);
+ }
+
+ close(pipefd[1]);
+ close(syncpipe[0]);
+
+ /* Read all three namespace IDs - fixed size, no parsing needed */
+ ret = read(pipefd[0], &p_id, sizeof(p_id));
+ if (ret != sizeof(p_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read parent namespace ID");
+ }
+
+ ret = read(pipefd[0], &n1_id, sizeof(n1_id));
+ if (ret != sizeof(n1_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read first network namespace ID");
+ }
+
+ ret = read(pipefd[0], &n2_id, sizeof(n2_id));
+ close(pipefd[0]);
+ if (ret != sizeof(n2_id)) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read second network namespace ID");
+ }
+
+ /* Construct file handles from namespace IDs */
+ parent_handle = (struct file_handle *)p_buf;
+ parent_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ parent_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *p_fh = (struct nsfs_file_handle *)parent_handle->f_handle;
+ p_fh->ns_id = p_id;
+ p_fh->ns_type = 0;
+ p_fh->ns_inum = 0;
+
+ net1_handle = (struct file_handle *)n1_buf;
+ net1_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ net1_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *n1_fh = (struct nsfs_file_handle *)net1_handle->f_handle;
+ n1_fh->ns_id = n1_id;
+ n1_fh->ns_type = 0;
+ n1_fh->ns_inum = 0;
+
+ net2_handle = (struct file_handle *)n2_buf;
+ net2_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ net2_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *n2_fh = (struct nsfs_file_handle *)net2_handle->f_handle;
+ n2_fh->ns_id = n2_id;
+ n2_fh->ns_type = 0;
+ n2_fh->ns_inum = 0;
+
+ /* Open both net namespaces while child is still alive */
+ int n1_fd = open_by_handle_at(FD_NSFS_ROOT, net1_handle, O_RDONLY);
+ int n2_fd = open_by_handle_at(FD_NSFS_ROOT, net2_handle, O_RDONLY);
+ if (n1_fd < 0 || n2_fd < 0) {
+ if (n1_fd >= 0) close(n1_fd);
+ if (n2_fd >= 0) close(n2_fd);
+ sync_byte = 'G';
+ write(syncpipe[1], &sync_byte, 1);
+ close(syncpipe[1]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to open net namespaces");
+ }
+
+ /* Signal child that we have opened the namespaces */
+ sync_byte = 'G';
+ write(syncpipe[1], &sync_byte, 1);
+ close(syncpipe[1]);
+
+ /* Wait for child to exit */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Parent should be active (has 2 active children) */
+ TH_LOG("Both net namespaces active - parent should be active");
+ int p_fd = open_by_handle_at(FD_NSFS_ROOT, parent_handle, O_RDONLY);
+ ASSERT_GE(p_fd, 0);
+ close(p_fd);
+
+ /* Close first net namespace - parent should STILL be active */
+ TH_LOG("Closing first net ns - parent should still be active");
+ close(n1_fd);
+ p_fd = open_by_handle_at(FD_NSFS_ROOT, parent_handle, O_RDONLY);
+ ASSERT_GE(p_fd, 0);
+ close(p_fd);
+
+ /* Close second net namespace - parent should become inactive */
+ TH_LOG("Closing second net ns - parent should become inactive");
+ close(n2_fd);
+ p_fd = open_by_handle_at(FD_NSFS_ROOT, parent_handle, O_RDONLY);
+ ASSERT_LT(p_fd, 0);
+}
+
+/*
+ * Test that user namespace as a child also propagates correctly.
+ * Create user_A -> user_B, verify when user_B is active that user_A
+ * is also active. This is different from non-user namespace children.
+ */
+TEST(ns_userns_child_propagation)
+{
+ struct file_handle *ua_handle, *ub_handle;
+ int ret, pipefd[2];
+ pid_t pid;
+ int status;
+ __u64 ua_id, ub_id;
+ char ua_buf[sizeof(*ua_handle) + MAX_HANDLE_SZ];
+ char ub_buf[sizeof(*ub_handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ close(pipefd[0]);
+
+ /* Create user_A */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int ua_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (ua_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(ua_fd, NS_GET_ID, &ua_id) < 0) {
+ close(ua_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(ua_fd);
+
+ /* Create user_B (child of user_A) */
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int ub_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (ub_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(ub_fd, NS_GET_ID, &ub_id) < 0) {
+ close(ub_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(ub_fd);
+
+ /* Send both namespace IDs */
+ write(pipefd[1], &ua_id, sizeof(ua_id));
+ write(pipefd[1], &ub_id, sizeof(ub_id));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ close(pipefd[1]);
+
+ /* Read both namespace IDs - fixed size, no parsing needed */
+ ret = read(pipefd[0], &ua_id, sizeof(ua_id));
+ if (ret != sizeof(ua_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read user_A namespace ID");
+ }
+
+ ret = read(pipefd[0], &ub_id, sizeof(ub_id));
+ close(pipefd[0]);
+ if (ret != sizeof(ub_id)) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read user_B namespace ID");
+ }
+
+ /* Construct file handles from namespace IDs */
+ ua_handle = (struct file_handle *)ua_buf;
+ ua_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ ua_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *ua_fh = (struct nsfs_file_handle *)ua_handle->f_handle;
+ ua_fh->ns_id = ua_id;
+ ua_fh->ns_type = 0;
+ ua_fh->ns_inum = 0;
+
+ ub_handle = (struct file_handle *)ub_buf;
+ ub_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ ub_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *ub_fh = (struct nsfs_file_handle *)ub_handle->f_handle;
+ ub_fh->ns_id = ub_id;
+ ub_fh->ns_type = 0;
+ ub_fh->ns_inum = 0;
+
+ /* Open user_B before child exits */
+ int ub_fd = open_by_handle_at(FD_NSFS_ROOT, ub_handle, O_RDONLY);
+ if (ub_fd < 0) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to open user_B");
+ }
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* With user_B active, user_A should also be active */
+ TH_LOG("Testing user_A active when child user_B is active");
+ int ua_fd = open_by_handle_at(FD_NSFS_ROOT, ua_handle, O_RDONLY);
+ ASSERT_GE(ua_fd, 0);
+
+ /* Close user_B */
+ TH_LOG("Closing user_B");
+ close(ub_fd);
+
+ /* user_A should remain active (we hold direct ref) */
+ int ua_fd2 = open_by_handle_at(FD_NSFS_ROOT, ua_handle, O_RDONLY);
+ ASSERT_GE(ua_fd2, 0);
+ close(ua_fd2);
+
+ /* Close user_A - should become inactive */
+ TH_LOG("Closing user_A - should become inactive");
+ close(ua_fd);
+
+ ua_fd = open_by_handle_at(FD_NSFS_ROOT, ua_handle, O_RDONLY);
+ ASSERT_LT(ua_fd, 0);
+}
+
+/*
+ * Test different namespace types (net, uts, ipc) all contributing
+ * active references to the same owning user namespace.
+ */
+TEST(ns_mixed_types_same_owner)
+{
+ struct file_handle *user_handle, *net_handle, *uts_handle;
+ int ret, pipefd[2];
+ pid_t pid;
+ int status;
+ __u64 u_id, n_id, ut_id;
+ char u_buf[sizeof(*user_handle) + MAX_HANDLE_SZ];
+ char n_buf[sizeof(*net_handle) + MAX_HANDLE_SZ];
+ char ut_buf[sizeof(*uts_handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ close(pipefd[0]);
+
+ if (setup_userns() < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int u_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (u_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(u_fd, NS_GET_ID, &u_id) < 0) {
+ close(u_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(u_fd);
+
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int n_fd = open("/proc/self/ns/net", O_RDONLY);
+ if (n_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(n_fd, NS_GET_ID, &n_id) < 0) {
+ close(n_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(n_fd);
+
+ if (unshare(CLONE_NEWUTS) < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+
+ int ut_fd = open("/proc/self/ns/uts", O_RDONLY);
+ if (ut_fd < 0) {
+ close(pipefd[1]);
+ exit(1);
+ }
+ if (ioctl(ut_fd, NS_GET_ID, &ut_id) < 0) {
+ close(ut_fd);
+ close(pipefd[1]);
+ exit(1);
+ }
+ close(ut_fd);
+
+ /* Send all namespace IDs */
+ write(pipefd[1], &u_id, sizeof(u_id));
+ write(pipefd[1], &n_id, sizeof(n_id));
+ write(pipefd[1], &ut_id, sizeof(ut_id));
+ close(pipefd[1]);
+ exit(0);
+ }
+
+ close(pipefd[1]);
+
+ /* Read all three namespace IDs - fixed size, no parsing needed */
+ ret = read(pipefd[0], &u_id, sizeof(u_id));
+ if (ret != sizeof(u_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read user namespace ID");
+ }
+
+ ret = read(pipefd[0], &n_id, sizeof(n_id));
+ if (ret != sizeof(n_id)) {
+ close(pipefd[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read network namespace ID");
+ }
+
+ ret = read(pipefd[0], &ut_id, sizeof(ut_id));
+ close(pipefd[0]);
+ if (ret != sizeof(ut_id)) {
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read UTS namespace ID");
+ }
+
+ /* Construct file handles from namespace IDs */
+ user_handle = (struct file_handle *)u_buf;
+ user_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ user_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *u_fh = (struct nsfs_file_handle *)user_handle->f_handle;
+ u_fh->ns_id = u_id;
+ u_fh->ns_type = 0;
+ u_fh->ns_inum = 0;
+
+ net_handle = (struct file_handle *)n_buf;
+ net_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ net_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *n_fh = (struct nsfs_file_handle *)net_handle->f_handle;
+ n_fh->ns_id = n_id;
+ n_fh->ns_type = 0;
+ n_fh->ns_inum = 0;
+
+ uts_handle = (struct file_handle *)ut_buf;
+ uts_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ uts_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *ut_fh = (struct nsfs_file_handle *)uts_handle->f_handle;
+ ut_fh->ns_id = ut_id;
+ ut_fh->ns_type = 0;
+ ut_fh->ns_inum = 0;
+
+ /* Open both non-user namespaces */
+ int n_fd = open_by_handle_at(FD_NSFS_ROOT, net_handle, O_RDONLY);
+ int ut_fd = open_by_handle_at(FD_NSFS_ROOT, uts_handle, O_RDONLY);
+ if (n_fd < 0 || ut_fd < 0) {
+ if (n_fd >= 0) close(n_fd);
+ if (ut_fd >= 0) close(ut_fd);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to open namespaces");
+ }
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* User namespace should be active (2 active children) */
+ TH_LOG("Both net and uts active - user ns should be active");
+ int u_fd = open_by_handle_at(FD_NSFS_ROOT, user_handle, O_RDONLY);
+ ASSERT_GE(u_fd, 0);
+ close(u_fd);
+
+ /* Close net - user ns should STILL be active (uts still active) */
+ TH_LOG("Closing net - user ns should still be active");
+ close(n_fd);
+ u_fd = open_by_handle_at(FD_NSFS_ROOT, user_handle, O_RDONLY);
+ ASSERT_GE(u_fd, 0);
+ close(u_fd);
+
+ /* Close uts - user ns should become inactive */
+ TH_LOG("Closing uts - user ns should become inactive");
+ close(ut_fd);
+ u_fd = open_by_handle_at(FD_NSFS_ROOT, user_handle, O_RDONLY);
+ ASSERT_LT(u_fd, 0);
+}
+
+/* Thread test helpers and structures */
+struct thread_ns_info {
+ __u64 ns_id;
+ int pipefd;
+ int syncfd_read;
+ int syncfd_write;
+ int exit_code;
+};
+
+static void *thread_create_namespace(void *arg)
+{
+ struct thread_ns_info *info = (struct thread_ns_info *)arg;
+ int ret;
+
+ /* Create new network namespace */
+ ret = unshare(CLONE_NEWNET);
+ if (ret < 0) {
+ info->exit_code = 1;
+ return NULL;
+ }
+
+ /* Get namespace ID */
+ int fd = open("/proc/thread-self/ns/net", O_RDONLY);
+ if (fd < 0) {
+ info->exit_code = 2;
+ return NULL;
+ }
+
+ ret = ioctl(fd, NS_GET_ID, &info->ns_id);
+ close(fd);
+ if (ret < 0) {
+ info->exit_code = 3;
+ return NULL;
+ }
+
+ /* Send namespace ID to main thread */
+ if (write(info->pipefd, &info->ns_id, sizeof(info->ns_id)) != sizeof(info->ns_id)) {
+ info->exit_code = 4;
+ return NULL;
+ }
+
+ /* Wait for signal to exit */
+ char sync_byte;
+ if (read(info->syncfd_read, &sync_byte, 1) != 1) {
+ info->exit_code = 5;
+ return NULL;
+ }
+
+ info->exit_code = 0;
+ return NULL;
+}
+
+/*
+ * Test that namespace becomes inactive after thread exits.
+ * This verifies active reference counting works with threads, not just processes.
+ */
+TEST(thread_ns_inactive_after_exit)
+{
+ pthread_t thread;
+ struct thread_ns_info info;
+ struct file_handle *handle;
+ int pipefd[2];
+ int syncpipe[2];
+ int ret;
+ char sync_byte;
+ char buf[sizeof(*handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+ ASSERT_EQ(pipe(syncpipe), 0);
+
+ info.pipefd = pipefd[1];
+ info.syncfd_read = syncpipe[0];
+ info.syncfd_write = -1;
+ info.exit_code = -1;
+
+ /* Create thread that will create a namespace */
+ ret = pthread_create(&thread, NULL, thread_create_namespace, &info);
+ ASSERT_EQ(ret, 0);
+
+ /* Read namespace ID from thread */
+ __u64 ns_id;
+ ret = read(pipefd[0], &ns_id, sizeof(ns_id));
+ if (ret != sizeof(ns_id)) {
+ sync_byte = 'X';
+ write(syncpipe[1], &sync_byte, 1);
+ pthread_join(thread, NULL);
+ close(pipefd[0]);
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ close(syncpipe[1]);
+ SKIP(return, "Failed to read namespace ID from thread");
+ }
+
+ TH_LOG("Thread created namespace with ID %llu", (unsigned long long)ns_id);
+
+ /* Construct file handle */
+ handle = (struct file_handle *)buf;
+ handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *fh = (struct nsfs_file_handle *)handle->f_handle;
+ fh->ns_id = ns_id;
+ fh->ns_type = 0;
+ fh->ns_inum = 0;
+
+ /* Namespace should be active while thread is alive */
+ TH_LOG("Attempting to open namespace while thread is alive (should succeed)");
+ int nsfd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_GE(nsfd, 0);
+ close(nsfd);
+
+ /* Signal thread to exit */
+ TH_LOG("Signaling thread to exit");
+ sync_byte = 'X';
+ ASSERT_EQ(write(syncpipe[1], &sync_byte, 1), 1);
+ close(syncpipe[1]);
+
+ /* Wait for thread to exit */
+ ASSERT_EQ(pthread_join(thread, NULL), 0);
+ close(pipefd[0]);
+ close(pipefd[1]);
+ close(syncpipe[0]);
+
+ if (info.exit_code != 0)
+ SKIP(return, "Thread failed to create namespace");
+
+ TH_LOG("Thread exited, namespace should be inactive");
+
+ /* Namespace should now be inactive */
+ nsfd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_LT(nsfd, 0);
+ /* Should fail with ENOENT (inactive) or ESTALE (gone) */
+ TH_LOG("Namespace inactive as expected: %s (errno=%d)", strerror(errno), errno);
+ ASSERT_TRUE(errno == ENOENT || errno == ESTALE);
+}
+
+/*
+ * Test that a namespace remains active while a thread holds an fd to it.
+ * Even after the thread exits, the namespace should remain active as long as
+ * another thread holds a file descriptor to it.
+ */
+TEST(thread_ns_fd_keeps_active)
+{
+ pthread_t thread;
+ struct thread_ns_info info;
+ struct file_handle *handle;
+ int pipefd[2];
+ int syncpipe[2];
+ int ret;
+ char sync_byte;
+ char buf[sizeof(*handle) + MAX_HANDLE_SZ];
+
+ ASSERT_EQ(pipe(pipefd), 0);
+ ASSERT_EQ(pipe(syncpipe), 0);
+
+ info.pipefd = pipefd[1];
+ info.syncfd_read = syncpipe[0];
+ info.syncfd_write = -1;
+ info.exit_code = -1;
+
+ /* Create thread that will create a namespace */
+ ret = pthread_create(&thread, NULL, thread_create_namespace, &info);
+ ASSERT_EQ(ret, 0);
+
+ /* Read namespace ID from thread */
+ __u64 ns_id;
+ ret = read(pipefd[0], &ns_id, sizeof(ns_id));
+ if (ret != sizeof(ns_id)) {
+ sync_byte = 'X';
+ write(syncpipe[1], &sync_byte, 1);
+ pthread_join(thread, NULL);
+ close(pipefd[0]);
+ close(pipefd[1]);
+ close(syncpipe[0]);
+ close(syncpipe[1]);
+ SKIP(return, "Failed to read namespace ID from thread");
+ }
+
+ TH_LOG("Thread created namespace with ID %llu", (unsigned long long)ns_id);
+
+ /* Construct file handle */
+ handle = (struct file_handle *)buf;
+ handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *fh = (struct nsfs_file_handle *)handle->f_handle;
+ fh->ns_id = ns_id;
+ fh->ns_type = 0;
+ fh->ns_inum = 0;
+
+ /* Open namespace while thread is alive */
+ TH_LOG("Opening namespace while thread is alive");
+ int nsfd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_GE(nsfd, 0);
+
+ /* Signal thread to exit */
+ TH_LOG("Signaling thread to exit");
+ sync_byte = 'X';
+ write(syncpipe[1], &sync_byte, 1);
+ close(syncpipe[1]);
+
+ /* Wait for thread to exit */
+ pthread_join(thread, NULL);
+ close(pipefd[0]);
+ close(pipefd[1]);
+ close(syncpipe[0]);
+
+ if (info.exit_code != 0) {
+ close(nsfd);
+ SKIP(return, "Thread failed to create namespace");
+ }
+
+ TH_LOG("Thread exited, but main thread holds fd - namespace should remain active");
+
+ /* Namespace should still be active because we hold an fd */
+ int nsfd2 = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_GE(nsfd2, 0);
+
+ /* Verify it's the same namespace */
+ struct stat st1, st2;
+ ASSERT_EQ(fstat(nsfd, &st1), 0);
+ ASSERT_EQ(fstat(nsfd2, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ close(nsfd2);
+
+ TH_LOG("Closing fd - namespace should become inactive");
+ close(nsfd);
+
+ /* Now namespace should be inactive */
+ nsfd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_LT(nsfd, 0);
+ /* Should fail with ENOENT (inactive) or ESTALE (gone) */
+ TH_LOG("Namespace inactive as expected: %s (errno=%d)", strerror(errno), errno);
+ ASSERT_TRUE(errno == ENOENT || errno == ESTALE);
+}
+
+/* Structure for thread data in subprocess */
+struct thread_sleep_data {
+ int syncfd_read;
+};
+
+static void *thread_sleep_and_wait(void *arg)
+{
+ struct thread_sleep_data *data = (struct thread_sleep_data *)arg;
+ char sync_byte;
+
+ /* Wait for signal to exit - read will unblock when pipe is closed */
+ (void)read(data->syncfd_read, &sync_byte, 1);
+ return NULL;
+}
+
+/*
+ * Test that namespaces become inactive after subprocess with multiple threads exits.
+ * Create a subprocess that unshares user and network namespaces, then creates two
+ * threads that share those namespaces. Verify that after all threads and subprocess
+ * exit, the namespaces are no longer listed by listns() and cannot be opened by
+ * open_by_handle_at().
+ */
+TEST(thread_subprocess_ns_inactive_after_all_exit)
+{
+ int pipefd[2];
+ int sv[2];
+ pid_t pid;
+ int status;
+ __u64 user_id, net_id;
+ struct file_handle *user_handle, *net_handle;
+ char user_buf[sizeof(*user_handle) + MAX_HANDLE_SZ];
+ char net_buf[sizeof(*net_handle) + MAX_HANDLE_SZ];
+ char sync_byte;
+ int ret;
+
+ ASSERT_EQ(pipe(pipefd), 0);
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sv), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child process */
+ close(pipefd[0]);
+ close(sv[0]);
+
+ /* Create user namespace with mappings */
+ if (setup_userns() < 0) {
+ fprintf(stderr, "Child: setup_userns() failed: %s\n", strerror(errno));
+ close(pipefd[1]);
+ close(sv[1]);
+ exit(1);
+ }
+ fprintf(stderr, "Child: setup_userns() succeeded\n");
+
+ /* Get user namespace ID */
+ int user_fd = open("/proc/self/ns/user", O_RDONLY);
+ if (user_fd < 0) {
+ fprintf(stderr, "Child: open(/proc/self/ns/user) failed: %s\n", strerror(errno));
+ close(pipefd[1]);
+ close(sv[1]);
+ exit(1);
+ }
+
+ if (ioctl(user_fd, NS_GET_ID, &user_id) < 0) {
+ fprintf(stderr, "Child: ioctl(NS_GET_ID) for user ns failed: %s\n", strerror(errno));
+ close(user_fd);
+ close(pipefd[1]);
+ close(sv[1]);
+ exit(1);
+ }
+ close(user_fd);
+ fprintf(stderr, "Child: user ns ID = %llu\n", (unsigned long long)user_id);
+
+ /* Unshare network namespace */
+ if (unshare(CLONE_NEWNET) < 0) {
+ fprintf(stderr, "Child: unshare(CLONE_NEWNET) failed: %s\n", strerror(errno));
+ close(pipefd[1]);
+ close(sv[1]);
+ exit(1);
+ }
+ fprintf(stderr, "Child: unshare(CLONE_NEWNET) succeeded\n");
+
+ /* Get network namespace ID */
+ int net_fd = open("/proc/self/ns/net", O_RDONLY);
+ if (net_fd < 0) {
+ fprintf(stderr, "Child: open(/proc/self/ns/net) failed: %s\n", strerror(errno));
+ close(pipefd[1]);
+ close(sv[1]);
+ exit(1);
+ }
+
+ if (ioctl(net_fd, NS_GET_ID, &net_id) < 0) {
+ fprintf(stderr, "Child: ioctl(NS_GET_ID) for net ns failed: %s\n", strerror(errno));
+ close(net_fd);
+ close(pipefd[1]);
+ close(sv[1]);
+ exit(1);
+ }
+ close(net_fd);
+ fprintf(stderr, "Child: net ns ID = %llu\n", (unsigned long long)net_id);
+
+ /* Send namespace IDs to parent */
+ if (write(pipefd[1], &user_id, sizeof(user_id)) != sizeof(user_id)) {
+ fprintf(stderr, "Child: write(user_id) failed: %s\n", strerror(errno));
+ exit(1);
+ }
+ if (write(pipefd[1], &net_id, sizeof(net_id)) != sizeof(net_id)) {
+ fprintf(stderr, "Child: write(net_id) failed: %s\n", strerror(errno));
+ exit(1);
+ }
+ close(pipefd[1]);
+ fprintf(stderr, "Child: sent namespace IDs to parent\n");
+
+ /* Create two threads that share the namespaces */
+ pthread_t thread1, thread2;
+ struct thread_sleep_data data;
+ data.syncfd_read = sv[1];
+
+ int ret_thread = pthread_create(&thread1, NULL, thread_sleep_and_wait, &data);
+ if (ret_thread != 0) {
+ fprintf(stderr, "Child: pthread_create(thread1) failed: %s\n", strerror(ret_thread));
+ close(sv[1]);
+ exit(1);
+ }
+ fprintf(stderr, "Child: created thread1\n");
+
+ ret_thread = pthread_create(&thread2, NULL, thread_sleep_and_wait, &data);
+ if (ret_thread != 0) {
+ fprintf(stderr, "Child: pthread_create(thread2) failed: %s\n", strerror(ret_thread));
+ close(sv[1]);
+ pthread_cancel(thread1);
+ exit(1);
+ }
+ fprintf(stderr, "Child: created thread2\n");
+
+ /* Wait for threads to complete - they will unblock when parent writes */
+ fprintf(stderr, "Child: waiting for threads to exit\n");
+ pthread_join(thread1, NULL);
+ fprintf(stderr, "Child: thread1 exited\n");
+ pthread_join(thread2, NULL);
+ fprintf(stderr, "Child: thread2 exited\n");
+
+ close(sv[1]);
+
+ /* Exit - namespaces should become inactive */
+ fprintf(stderr, "Child: all threads joined, exiting with success\n");
+ exit(0);
+ }
+
+ /* Parent process */
+ close(pipefd[1]);
+ close(sv[1]);
+
+ TH_LOG("Parent: waiting to read namespace IDs from child");
+
+ /* Read namespace IDs from child */
+ ret = read(pipefd[0], &user_id, sizeof(user_id));
+ if (ret != sizeof(user_id)) {
+ TH_LOG("Parent: failed to read user_id, ret=%d, errno=%s", ret, strerror(errno));
+ close(pipefd[0]);
+ sync_byte = 'X';
+ (void)write(sv[0], &sync_byte, 1);
+ close(sv[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read user namespace ID from child");
+ }
+
+ ret = read(pipefd[0], &net_id, sizeof(net_id));
+ close(pipefd[0]);
+ if (ret != sizeof(net_id)) {
+ TH_LOG("Parent: failed to read net_id, ret=%d, errno=%s", ret, strerror(errno));
+ sync_byte = 'X';
+ (void)write(sv[0], &sync_byte, 1);
+ close(sv[0]);
+ waitpid(pid, NULL, 0);
+ SKIP(return, "Failed to read network namespace ID from child");
+ }
+
+ TH_LOG("Child created user ns %llu and net ns %llu with 2 threads",
+ (unsigned long long)user_id, (unsigned long long)net_id);
+
+ /* Construct file handles */
+ user_handle = (struct file_handle *)user_buf;
+ user_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ user_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *user_fh = (struct nsfs_file_handle *)user_handle->f_handle;
+ user_fh->ns_id = user_id;
+ user_fh->ns_type = 0;
+ user_fh->ns_inum = 0;
+
+ net_handle = (struct file_handle *)net_buf;
+ net_handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ net_handle->handle_type = FILEID_NSFS;
+ struct nsfs_file_handle *net_fh = (struct nsfs_file_handle *)net_handle->f_handle;
+ net_fh->ns_id = net_id;
+ net_fh->ns_type = 0;
+ net_fh->ns_inum = 0;
+
+ /* Verify namespaces are active while subprocess and threads are alive */
+ TH_LOG("Verifying namespaces are active while subprocess with threads is running");
+ int user_fd = open_by_handle_at(FD_NSFS_ROOT, user_handle, O_RDONLY);
+ ASSERT_GE(user_fd, 0);
+
+ int net_fd = open_by_handle_at(FD_NSFS_ROOT, net_handle, O_RDONLY);
+ ASSERT_GE(net_fd, 0);
+
+ close(user_fd);
+ close(net_fd);
+
+ /* Also verify they appear in listns() */
+ TH_LOG("Verifying namespaces appear in listns() while active");
+ struct ns_id_req req = {
+ .size = sizeof(struct ns_id_req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[256];
+ int nr_ids = sys_listns(&req, ns_ids, 256, 0);
+ if (nr_ids < 0) {
+ TH_LOG("listns() not available, skipping listns verification");
+ } else {
+ /* Check if user_id is in the list */
+ int found_user = 0;
+ for (int i = 0; i < nr_ids; i++) {
+ if (ns_ids[i] == user_id) {
+ found_user = 1;
+ break;
+ }
+ }
+ ASSERT_TRUE(found_user);
+ TH_LOG("User namespace found in listns() as expected");
+
+ /* Check network namespace */
+ req.ns_type = CLONE_NEWNET;
+ nr_ids = sys_listns(&req, ns_ids, 256, 0);
+ if (nr_ids >= 0) {
+ int found_net = 0;
+ for (int i = 0; i < nr_ids; i++) {
+ if (ns_ids[i] == net_id) {
+ found_net = 1;
+ break;
+ }
+ }
+ ASSERT_TRUE(found_net);
+ TH_LOG("Network namespace found in listns() as expected");
+ }
+ }
+
+ /* Signal threads to exit */
+ TH_LOG("Signaling threads to exit");
+ sync_byte = 'X';
+ /* Write two bytes - one for each thread */
+ ASSERT_EQ(write(sv[0], &sync_byte, 1), 1);
+ ASSERT_EQ(write(sv[0], &sync_byte, 1), 1);
+ close(sv[0]);
+
+ /* Wait for child process to exit */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ if (WEXITSTATUS(status) != 0) {
+ TH_LOG("Child process failed with exit code %d", WEXITSTATUS(status));
+ SKIP(return, "Child process failed");
+ }
+
+ TH_LOG("Subprocess and all threads have exited successfully");
+
+ /* Verify namespaces are now inactive - open_by_handle_at should fail */
+ TH_LOG("Verifying namespaces are inactive after subprocess and threads exit");
+ user_fd = open_by_handle_at(FD_NSFS_ROOT, user_handle, O_RDONLY);
+ ASSERT_LT(user_fd, 0);
+ TH_LOG("User namespace inactive as expected: %s (errno=%d)",
+ strerror(errno), errno);
+ ASSERT_TRUE(errno == ENOENT || errno == ESTALE);
+
+ net_fd = open_by_handle_at(FD_NSFS_ROOT, net_handle, O_RDONLY);
+ ASSERT_LT(net_fd, 0);
+ TH_LOG("Network namespace inactive as expected: %s (errno=%d)",
+ strerror(errno), errno);
+ ASSERT_TRUE(errno == ENOENT || errno == ESTALE);
+
+ /* Verify namespaces do NOT appear in listns() */
+ TH_LOG("Verifying namespaces do NOT appear in listns() when inactive");
+ memset(&req, 0, sizeof(req));
+ req.size = sizeof(struct ns_id_req);
+ req.ns_type = CLONE_NEWUSER;
+ nr_ids = sys_listns(&req, ns_ids, 256, 0);
+ if (nr_ids >= 0) {
+ int found_user = 0;
+ for (int i = 0; i < nr_ids; i++) {
+ if (ns_ids[i] == user_id) {
+ found_user = 1;
+ break;
+ }
+ }
+ ASSERT_FALSE(found_user);
+ TH_LOG("User namespace correctly not listed in listns()");
+
+ /* Check network namespace */
+ req.ns_type = CLONE_NEWNET;
+ nr_ids = sys_listns(&req, ns_ids, 256, 0);
+ if (nr_ids >= 0) {
+ int found_net = 0;
+ for (int i = 0; i < nr_ids; i++) {
+ if (ns_ids[i] == net_id) {
+ found_net = 1;
+ break;
+ }
+ }
+ ASSERT_FALSE(found_net);
+ TH_LOG("Network namespace correctly not listed in listns()");
+ }
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/nsid_test.c b/tools/testing/selftests/namespaces/nsid_test.c
index e28accd74a57..527ade0a8673 100644
--- a/tools/testing/selftests/namespaces/nsid_test.c
+++ b/tools/testing/selftests/namespaces/nsid_test.c
@@ -6,6 +6,7 @@
#include <libgen.h>
#include <limits.h>
#include <pthread.h>
+#include <signal.h>
#include <string.h>
#include <sys/mount.h>
#include <poll.h>
@@ -14,12 +15,30 @@
#include <sys/stat.h>
#include <sys/socket.h>
#include <sys/un.h>
+#include <sys/wait.h>
#include <unistd.h>
#include <linux/fs.h>
#include <linux/limits.h>
#include <linux/nsfs.h>
#include "../kselftest_harness.h"
+/* Fixture for tests that create child processes */
+FIXTURE(nsid) {
+ pid_t child_pid;
+};
+
+FIXTURE_SETUP(nsid) {
+ self->child_pid = 0;
+}
+
+FIXTURE_TEARDOWN(nsid) {
+ /* Clean up any child process that may still be running */
+ if (self->child_pid > 0) {
+ kill(self->child_pid, SIGKILL);
+ waitpid(self->child_pid, NULL, 0);
+ }
+}
+
TEST(nsid_mntns_basic)
{
__u64 mnt_ns_id = 0;
@@ -44,7 +63,7 @@ TEST(nsid_mntns_basic)
close(fd_mntns);
}
-TEST(nsid_mntns_separate)
+TEST_F(nsid, mntns_separate)
{
__u64 parent_mnt_ns_id = 0;
__u64 child_mnt_ns_id = 0;
@@ -90,6 +109,9 @@ TEST(nsid_mntns_separate)
_exit(0);
}
+ /* Track child for cleanup */
+ self->child_pid = pid;
+
/* Parent process */
close(pipefd[1]);
@@ -99,8 +121,6 @@ TEST(nsid_mntns_separate)
if (buf == 'S') {
/* Child couldn't create namespace, skip test */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
close(fd_parent_mntns);
SKIP(return, "No permission to create mount namespace");
}
@@ -123,10 +143,6 @@ TEST(nsid_mntns_separate)
close(fd_parent_mntns);
close(fd_child_mntns);
-
- /* Clean up child process */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
}
TEST(nsid_cgroupns_basic)
@@ -153,7 +169,7 @@ TEST(nsid_cgroupns_basic)
close(fd_cgroupns);
}
-TEST(nsid_cgroupns_separate)
+TEST_F(nsid, cgroupns_separate)
{
__u64 parent_cgroup_ns_id = 0;
__u64 child_cgroup_ns_id = 0;
@@ -199,6 +215,9 @@ TEST(nsid_cgroupns_separate)
_exit(0);
}
+ /* Track child for cleanup */
+ self->child_pid = pid;
+
/* Parent process */
close(pipefd[1]);
@@ -208,8 +227,6 @@ TEST(nsid_cgroupns_separate)
if (buf == 'S') {
/* Child couldn't create namespace, skip test */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
close(fd_parent_cgroupns);
SKIP(return, "No permission to create cgroup namespace");
}
@@ -232,10 +249,6 @@ TEST(nsid_cgroupns_separate)
close(fd_parent_cgroupns);
close(fd_child_cgroupns);
-
- /* Clean up child process */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
}
TEST(nsid_ipcns_basic)
@@ -262,7 +275,7 @@ TEST(nsid_ipcns_basic)
close(fd_ipcns);
}
-TEST(nsid_ipcns_separate)
+TEST_F(nsid, ipcns_separate)
{
__u64 parent_ipc_ns_id = 0;
__u64 child_ipc_ns_id = 0;
@@ -308,6 +321,9 @@ TEST(nsid_ipcns_separate)
_exit(0);
}
+ /* Track child for cleanup */
+ self->child_pid = pid;
+
/* Parent process */
close(pipefd[1]);
@@ -317,8 +333,6 @@ TEST(nsid_ipcns_separate)
if (buf == 'S') {
/* Child couldn't create namespace, skip test */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
close(fd_parent_ipcns);
SKIP(return, "No permission to create IPC namespace");
}
@@ -341,10 +355,6 @@ TEST(nsid_ipcns_separate)
close(fd_parent_ipcns);
close(fd_child_ipcns);
-
- /* Clean up child process */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
}
TEST(nsid_utsns_basic)
@@ -371,7 +381,7 @@ TEST(nsid_utsns_basic)
close(fd_utsns);
}
-TEST(nsid_utsns_separate)
+TEST_F(nsid, utsns_separate)
{
__u64 parent_uts_ns_id = 0;
__u64 child_uts_ns_id = 0;
@@ -417,6 +427,9 @@ TEST(nsid_utsns_separate)
_exit(0);
}
+ /* Track child for cleanup */
+ self->child_pid = pid;
+
/* Parent process */
close(pipefd[1]);
@@ -426,8 +439,6 @@ TEST(nsid_utsns_separate)
if (buf == 'S') {
/* Child couldn't create namespace, skip test */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
close(fd_parent_utsns);
SKIP(return, "No permission to create UTS namespace");
}
@@ -450,10 +461,6 @@ TEST(nsid_utsns_separate)
close(fd_parent_utsns);
close(fd_child_utsns);
-
- /* Clean up child process */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
}
TEST(nsid_userns_basic)
@@ -480,7 +487,7 @@ TEST(nsid_userns_basic)
close(fd_userns);
}
-TEST(nsid_userns_separate)
+TEST_F(nsid, userns_separate)
{
__u64 parent_user_ns_id = 0;
__u64 child_user_ns_id = 0;
@@ -526,6 +533,9 @@ TEST(nsid_userns_separate)
_exit(0);
}
+ /* Track child for cleanup */
+ self->child_pid = pid;
+
/* Parent process */
close(pipefd[1]);
@@ -535,8 +545,6 @@ TEST(nsid_userns_separate)
if (buf == 'S') {
/* Child couldn't create namespace, skip test */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
close(fd_parent_userns);
SKIP(return, "No permission to create user namespace");
}
@@ -559,10 +567,6 @@ TEST(nsid_userns_separate)
close(fd_parent_userns);
close(fd_child_userns);
-
- /* Clean up child process */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
}
TEST(nsid_timens_basic)
@@ -591,7 +595,7 @@ TEST(nsid_timens_basic)
close(fd_timens);
}
-TEST(nsid_timens_separate)
+TEST_F(nsid, timens_separate)
{
__u64 parent_time_ns_id = 0;
__u64 child_time_ns_id = 0;
@@ -652,6 +656,9 @@ TEST(nsid_timens_separate)
}
}
+ /* Track child for cleanup */
+ self->child_pid = pid;
+
/* Parent process */
close(pipefd[1]);
@@ -660,8 +667,6 @@ TEST(nsid_timens_separate)
if (buf == 'S') {
/* Child couldn't create namespace, skip test */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
close(fd_parent_timens);
close(pipefd[0]);
SKIP(return, "Cannot create time namespace");
@@ -689,10 +694,6 @@ TEST(nsid_timens_separate)
close(fd_parent_timens);
close(fd_child_timens);
-
- /* Clean up child process */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
}
TEST(nsid_pidns_basic)
@@ -719,7 +720,7 @@ TEST(nsid_pidns_basic)
close(fd_pidns);
}
-TEST(nsid_pidns_separate)
+TEST_F(nsid, pidns_separate)
{
__u64 parent_pid_ns_id = 0;
__u64 child_pid_ns_id = 0;
@@ -776,6 +777,9 @@ TEST(nsid_pidns_separate)
}
}
+ /* Track child for cleanup */
+ self->child_pid = pid;
+
/* Parent process */
close(pipefd[1]);
@@ -784,8 +788,6 @@ TEST(nsid_pidns_separate)
if (buf == 'S') {
/* Child couldn't create namespace, skip test */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
close(fd_parent_pidns);
close(pipefd[0]);
SKIP(return, "No permission to create PID namespace");
@@ -813,10 +815,6 @@ TEST(nsid_pidns_separate)
close(fd_parent_pidns);
close(fd_child_pidns);
-
- /* Clean up child process */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
}
TEST(nsid_netns_basic)
@@ -860,7 +858,7 @@ TEST(nsid_netns_basic)
close(fd_netns);
}
-TEST(nsid_netns_separate)
+TEST_F(nsid, netns_separate)
{
__u64 parent_net_ns_id = 0;
__u64 parent_netns_cookie = 0;
@@ -920,6 +918,9 @@ TEST(nsid_netns_separate)
_exit(0);
}
+ /* Track child for cleanup */
+ self->child_pid = pid;
+
/* Parent process */
close(pipefd[1]);
@@ -929,8 +930,6 @@ TEST(nsid_netns_separate)
if (buf == 'S') {
/* Child couldn't create namespace, skip test */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
close(fd_parent_netns);
close(parent_sock);
SKIP(return, "No permission to create network namespace");
@@ -977,10 +976,6 @@ TEST(nsid_netns_separate)
close(fd_parent_netns);
close(fd_child_netns);
close(parent_sock);
-
- /* Clean up child process */
- kill(pid, SIGTERM);
- waitpid(pid, NULL, 0);
}
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/regression_pidfd_setns_test.c b/tools/testing/selftests/namespaces/regression_pidfd_setns_test.c
new file mode 100644
index 000000000000..753fd29dffd8
--- /dev/null
+++ b/tools/testing/selftests/namespaces/regression_pidfd_setns_test.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <unistd.h>
+#include "../pidfd/pidfd.h"
+#include "../kselftest_harness.h"
+
+/*
+ * Regression tests for the setns(pidfd) active reference counting bug.
+ *
+ * These tests are based on the reproducers that triggered the race condition
+ * fixed by commit 1c465d0518dc ("ns: handle setns(pidfd, ...) cleanly").
+ *
+ * The bug: When using setns() with a pidfd, if the target task exits between
+ * prepare_nsset() and commit_nsset(), the namespaces would become inactive.
+ * Then ns_ref_active_get() would increment from 0 without properly resurrecting
+ * the owner chain, causing active reference count underflows.
+ */
+
+/*
+ * Simple pidfd setns test using create_child()+unshare().
+ *
+ * Without the fix, this would trigger active refcount warnings when the
+ * parent exits after doing setns(pidfd) on a child that has already exited.
+ */
+TEST(simple_pidfd_setns)
+{
+ pid_t child_pid;
+ int pidfd = -1;
+ int ret;
+ int sv[2];
+ char c;
+
+ /* Ignore SIGCHLD for autoreap */
+ ASSERT_NE(signal(SIGCHLD, SIG_IGN), SIG_ERR);
+
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sv), 0);
+
+ /* Create a child process without namespaces initially */
+ child_pid = create_child(&pidfd, 0);
+ ASSERT_GE(child_pid, 0);
+
+ if (child_pid == 0) {
+ close(sv[0]);
+
+ if (unshare(CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWNET | CLONE_NEWUSER) < 0) {
+ close(sv[1]);
+ _exit(1);
+ }
+
+ /* Signal parent that namespaces are ready */
+ if (write_nointr(sv[1], "1", 1) < 0) {
+ close(sv[1]);
+ _exit(1);
+ }
+
+ close(sv[1]);
+ _exit(0);
+ }
+ ASSERT_GE(pidfd, 0);
+ EXPECT_EQ(close(sv[1]), 0);
+
+ ret = read_nointr(sv[0], &c, 1);
+ ASSERT_EQ(ret, 1);
+ EXPECT_EQ(close(sv[0]), 0);
+
+ /* Set to child's namespaces via pidfd */
+ ret = setns(pidfd, CLONE_NEWUTS | CLONE_NEWIPC);
+ TH_LOG("setns() returned %d", ret);
+ close(pidfd);
+}
+
+/*
+ * Simple pidfd setns test using create_child().
+ *
+ * This variation uses create_child() with namespace flags directly.
+ * Namespaces are created immediately at clone time.
+ */
+TEST(simple_pidfd_setns_clone)
+{
+ pid_t child_pid;
+ int pidfd = -1;
+ int ret;
+
+ /* Ignore SIGCHLD for autoreap */
+ ASSERT_NE(signal(SIGCHLD, SIG_IGN), SIG_ERR);
+
+ /* Create a child process with new namespaces using create_child() */
+ child_pid = create_child(&pidfd, CLONE_NEWUSER | CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWNET);
+ ASSERT_GE(child_pid, 0);
+
+ if (child_pid == 0) {
+ /* Child: sleep for a while so parent can setns to us */
+ sleep(2);
+ _exit(0);
+ }
+
+ /* Parent: pidfd was already created by create_child() */
+ ASSERT_GE(pidfd, 0);
+
+ /* Set to child's namespaces via pidfd */
+ ret = setns(pidfd, CLONE_NEWUTS | CLONE_NEWIPC);
+ close(pidfd);
+ TH_LOG("setns() returned %d", ret);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/siocgskns_test.c b/tools/testing/selftests/namespaces/siocgskns_test.c
new file mode 100644
index 000000000000..ba689a22d82f
--- /dev/null
+++ b/tools/testing/selftests/namespaces/siocgskns_test.c
@@ -0,0 +1,1824 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <linux/if.h>
+#include <linux/sockios.h>
+#include <linux/nsfs.h>
+#include <arpa/inet.h>
+#include "../kselftest_harness.h"
+#include "../filesystems/utils.h"
+#include "wrappers.h"
+
+#ifndef SIOCGSKNS
+#define SIOCGSKNS 0x894C
+#endif
+
+#ifndef FD_NSFS_ROOT
+#define FD_NSFS_ROOT -10003
+#endif
+
+#ifndef FILEID_NSFS
+#define FILEID_NSFS 0xf1
+#endif
+
+/*
+ * Test basic SIOCGSKNS functionality.
+ * Create a socket and verify SIOCGSKNS returns the correct network namespace.
+ */
+TEST(siocgskns_basic)
+{
+ int sock_fd, netns_fd, current_netns_fd;
+ struct stat st1, st2;
+
+ /* Create a TCP socket */
+ sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GE(sock_fd, 0);
+
+ /* Use SIOCGSKNS to get network namespace */
+ netns_fd = ioctl(sock_fd, SIOCGSKNS);
+ if (netns_fd < 0) {
+ close(sock_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_fd, 0);
+ }
+
+ /* Get current network namespace */
+ current_netns_fd = open("/proc/self/ns/net", O_RDONLY);
+ ASSERT_GE(current_netns_fd, 0);
+
+ /* Verify they match */
+ ASSERT_EQ(fstat(netns_fd, &st1), 0);
+ ASSERT_EQ(fstat(current_netns_fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+
+ close(sock_fd);
+ close(netns_fd);
+ close(current_netns_fd);
+}
+
+/*
+ * Test that socket file descriptors keep network namespaces active.
+ * Create a network namespace, create a socket in it, then exit the namespace.
+ * The namespace should remain active while the socket FD is held.
+ */
+TEST(siocgskns_keeps_netns_active)
+{
+ int sock_fd, netns_fd, test_fd;
+ int ipc_sockets[2];
+ pid_t pid;
+ int status;
+ struct stat st;
+
+ EXPECT_EQ(socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child: create new netns and socket */
+ close(ipc_sockets[0]);
+
+ if (unshare(CLONE_NEWNET) < 0) {
+ TH_LOG("unshare(CLONE_NEWNET) failed: %s", strerror(errno));
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ /* Create a socket in the new network namespace */
+ sock_fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (sock_fd < 0) {
+ TH_LOG("socket() failed: %s", strerror(errno));
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ /* Send socket FD to parent via SCM_RIGHTS */
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1] = {'X'};
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ struct cmsghdr *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), &sock_fd, sizeof(int));
+
+ if (sendmsg(ipc_sockets[1], &msg, 0) < 0) {
+ close(sock_fd);
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ close(sock_fd);
+ close(ipc_sockets[1]);
+ exit(0);
+ }
+
+ /* Parent: receive socket FD */
+ close(ipc_sockets[1]);
+
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1];
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ ssize_t n = recvmsg(ipc_sockets[0], &msg, 0);
+ close(ipc_sockets[0]);
+ ASSERT_EQ(n, 1);
+
+ struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+ ASSERT_NE(cmsg, NULL);
+ ASSERT_EQ(cmsg->cmsg_type, SCM_RIGHTS);
+
+ memcpy(&sock_fd, CMSG_DATA(cmsg), sizeof(int));
+
+ /* Wait for child to exit */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Get network namespace from socket */
+ netns_fd = ioctl(sock_fd, SIOCGSKNS);
+ if (netns_fd < 0) {
+ close(sock_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_fd, 0);
+ }
+
+ ASSERT_EQ(fstat(netns_fd, &st), 0);
+
+ /*
+ * Namespace should still be active because socket FD keeps it alive.
+ * Try to access it via /proc/self/fd/<fd>.
+ */
+ char path[64];
+ snprintf(path, sizeof(path), "/proc/self/fd/%d", netns_fd);
+ test_fd = open(path, O_RDONLY);
+ ASSERT_GE(test_fd, 0);
+ close(test_fd);
+ close(netns_fd);
+
+ /* Close socket - namespace should become inactive */
+ close(sock_fd);
+
+ /* Try SIOCGSKNS again - should fail since socket is closed */
+ ASSERT_LT(ioctl(sock_fd, SIOCGSKNS), 0);
+}
+
+/*
+ * Test SIOCGSKNS with different socket types (TCP, UDP, RAW).
+ */
+TEST(siocgskns_socket_types)
+{
+ int sock_tcp, sock_udp, sock_raw;
+ int netns_tcp, netns_udp, netns_raw;
+ struct stat st_tcp, st_udp, st_raw;
+
+ /* TCP socket */
+ sock_tcp = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GE(sock_tcp, 0);
+
+ /* UDP socket */
+ sock_udp = socket(AF_INET, SOCK_DGRAM, 0);
+ ASSERT_GE(sock_udp, 0);
+
+ /* RAW socket (may require privileges) */
+ sock_raw = socket(AF_INET, SOCK_RAW, IPPROTO_ICMP);
+ if (sock_raw < 0 && (errno == EPERM || errno == EACCES)) {
+ sock_raw = -1; /* Skip raw socket test */
+ }
+
+ /* Test SIOCGSKNS on TCP */
+ netns_tcp = ioctl(sock_tcp, SIOCGSKNS);
+ if (netns_tcp < 0) {
+ close(sock_tcp);
+ close(sock_udp);
+ if (sock_raw >= 0) close(sock_raw);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_tcp, 0);
+ }
+
+ /* Test SIOCGSKNS on UDP */
+ netns_udp = ioctl(sock_udp, SIOCGSKNS);
+ ASSERT_GE(netns_udp, 0);
+
+ /* Test SIOCGSKNS on RAW (if available) */
+ if (sock_raw >= 0) {
+ netns_raw = ioctl(sock_raw, SIOCGSKNS);
+ ASSERT_GE(netns_raw, 0);
+ }
+
+ /* Verify all return the same network namespace */
+ ASSERT_EQ(fstat(netns_tcp, &st_tcp), 0);
+ ASSERT_EQ(fstat(netns_udp, &st_udp), 0);
+ ASSERT_EQ(st_tcp.st_ino, st_udp.st_ino);
+
+ if (sock_raw >= 0) {
+ ASSERT_EQ(fstat(netns_raw, &st_raw), 0);
+ ASSERT_EQ(st_tcp.st_ino, st_raw.st_ino);
+ close(netns_raw);
+ close(sock_raw);
+ }
+
+ close(netns_tcp);
+ close(netns_udp);
+ close(sock_tcp);
+ close(sock_udp);
+}
+
+/*
+ * Test SIOCGSKNS across setns.
+ * Create a socket in netns A, switch to netns B, verify SIOCGSKNS still
+ * returns netns A.
+ */
+TEST(siocgskns_across_setns)
+{
+ int sock_fd, netns_a_fd, netns_b_fd, result_fd;
+ struct stat st_a;
+
+ /* Get current netns (A) */
+ netns_a_fd = open("/proc/self/ns/net", O_RDONLY);
+ ASSERT_GE(netns_a_fd, 0);
+ ASSERT_EQ(fstat(netns_a_fd, &st_a), 0);
+
+ /* Create socket in netns A */
+ sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GE(sock_fd, 0);
+
+ /* Create new netns (B) */
+ ASSERT_EQ(unshare(CLONE_NEWNET), 0);
+
+ netns_b_fd = open("/proc/self/ns/net", O_RDONLY);
+ ASSERT_GE(netns_b_fd, 0);
+
+ /* Get netns from socket created in A */
+ result_fd = ioctl(sock_fd, SIOCGSKNS);
+ if (result_fd < 0) {
+ close(sock_fd);
+ setns(netns_a_fd, CLONE_NEWNET);
+ close(netns_a_fd);
+ close(netns_b_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(result_fd, 0);
+ }
+
+ /* Verify it still points to netns A */
+ struct stat st_result_stat;
+ ASSERT_EQ(fstat(result_fd, &st_result_stat), 0);
+ ASSERT_EQ(st_a.st_ino, st_result_stat.st_ino);
+
+ close(result_fd);
+ close(sock_fd);
+ close(netns_b_fd);
+
+ /* Restore original netns */
+ ASSERT_EQ(setns(netns_a_fd, CLONE_NEWNET), 0);
+ close(netns_a_fd);
+}
+
+/*
+ * Test SIOCGSKNS fails on non-socket file descriptors.
+ */
+TEST(siocgskns_non_socket)
+{
+ int fd;
+ int pipefd[2];
+
+ /* Test on regular file */
+ fd = open("/dev/null", O_RDONLY);
+ ASSERT_GE(fd, 0);
+
+ ASSERT_LT(ioctl(fd, SIOCGSKNS), 0);
+ ASSERT_TRUE(errno == ENOTTY || errno == EINVAL);
+ close(fd);
+
+ /* Test on pipe */
+ ASSERT_EQ(pipe(pipefd), 0);
+
+ ASSERT_LT(ioctl(pipefd[0], SIOCGSKNS), 0);
+ ASSERT_TRUE(errno == ENOTTY || errno == EINVAL);
+
+ close(pipefd[0]);
+ close(pipefd[1]);
+}
+
+/*
+ * Test multiple sockets keep the same network namespace active.
+ * Create multiple sockets, verify closing some doesn't affect others.
+ */
+TEST(siocgskns_multiple_sockets)
+{
+ int socks[5];
+ int netns_fds[5];
+ int i;
+ struct stat st;
+ ino_t netns_ino;
+
+ /* Create new network namespace */
+ ASSERT_EQ(unshare(CLONE_NEWNET), 0);
+
+ /* Create multiple sockets */
+ for (i = 0; i < 5; i++) {
+ socks[i] = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GE(socks[i], 0);
+ }
+
+ /* Get netns from all sockets */
+ for (i = 0; i < 5; i++) {
+ netns_fds[i] = ioctl(socks[i], SIOCGSKNS);
+ if (netns_fds[i] < 0) {
+ int j;
+ for (j = 0; j <= i; j++) {
+ close(socks[j]);
+ if (j < i && netns_fds[j] >= 0)
+ close(netns_fds[j]);
+ }
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_fds[i], 0);
+ }
+ }
+
+ /* Verify all point to same netns */
+ ASSERT_EQ(fstat(netns_fds[0], &st), 0);
+ netns_ino = st.st_ino;
+
+ for (i = 1; i < 5; i++) {
+ ASSERT_EQ(fstat(netns_fds[i], &st), 0);
+ ASSERT_EQ(st.st_ino, netns_ino);
+ }
+
+ /* Close some sockets */
+ for (i = 0; i < 3; i++) {
+ close(socks[i]);
+ }
+
+ /* Remaining netns FDs should still be valid */
+ for (i = 3; i < 5; i++) {
+ char path[64];
+ snprintf(path, sizeof(path), "/proc/self/fd/%d", netns_fds[i]);
+ int test_fd = open(path, O_RDONLY);
+ ASSERT_GE(test_fd, 0);
+ close(test_fd);
+ }
+
+ /* Cleanup */
+ for (i = 0; i < 5; i++) {
+ if (i >= 3)
+ close(socks[i]);
+ close(netns_fds[i]);
+ }
+}
+
+/*
+ * Test socket keeps netns active after creating process exits.
+ * Verify that as long as the socket FD exists, the namespace remains active.
+ */
+TEST(siocgskns_netns_lifecycle)
+{
+ int sock_fd, netns_fd;
+ int ipc_sockets[2];
+ int syncpipe[2];
+ pid_t pid;
+ int status;
+ char sync_byte;
+ struct stat st;
+ ino_t netns_ino;
+
+ EXPECT_EQ(socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+ ASSERT_EQ(pipe(syncpipe), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child */
+ close(ipc_sockets[0]);
+ close(syncpipe[1]);
+
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(ipc_sockets[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+
+ sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+ if (sock_fd < 0) {
+ close(ipc_sockets[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+
+ /* Send socket to parent */
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1] = {'X'};
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ struct cmsghdr *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), &sock_fd, sizeof(int));
+
+ if (sendmsg(ipc_sockets[1], &msg, 0) < 0) {
+ close(sock_fd);
+ close(ipc_sockets[1]);
+ close(syncpipe[0]);
+ exit(1);
+ }
+
+ close(sock_fd);
+ close(ipc_sockets[1]);
+
+ /* Wait for parent signal */
+ read(syncpipe[0], &sync_byte, 1);
+ close(syncpipe[0]);
+ exit(0);
+ }
+
+ /* Parent */
+ close(ipc_sockets[1]);
+ close(syncpipe[0]);
+
+ /* Receive socket FD */
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1];
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ ssize_t n = recvmsg(ipc_sockets[0], &msg, 0);
+ close(ipc_sockets[0]);
+ ASSERT_EQ(n, 1);
+
+ struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+ ASSERT_NE(cmsg, NULL);
+ memcpy(&sock_fd, CMSG_DATA(cmsg), sizeof(int));
+
+ /* Get netns from socket while child is alive */
+ netns_fd = ioctl(sock_fd, SIOCGSKNS);
+ if (netns_fd < 0) {
+ sync_byte = 'G';
+ write(syncpipe[1], &sync_byte, 1);
+ close(syncpipe[1]);
+ close(sock_fd);
+ waitpid(pid, NULL, 0);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_fd, 0);
+ }
+ ASSERT_EQ(fstat(netns_fd, &st), 0);
+ netns_ino = st.st_ino;
+
+ /* Signal child to exit */
+ sync_byte = 'G';
+ write(syncpipe[1], &sync_byte, 1);
+ close(syncpipe[1]);
+
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+
+ /*
+ * Socket FD should still keep namespace active even after
+ * the creating process exited.
+ */
+ int test_fd = ioctl(sock_fd, SIOCGSKNS);
+ ASSERT_GE(test_fd, 0);
+
+ struct stat st_test;
+ ASSERT_EQ(fstat(test_fd, &st_test), 0);
+ ASSERT_EQ(st_test.st_ino, netns_ino);
+
+ close(test_fd);
+ close(netns_fd);
+
+ /* Close socket - namespace should become inactive */
+ close(sock_fd);
+}
+
+/*
+ * Test IPv6 sockets also work with SIOCGSKNS.
+ */
+TEST(siocgskns_ipv6)
+{
+ int sock_fd, netns_fd, current_netns_fd;
+ struct stat st1, st2;
+
+ /* Create an IPv6 TCP socket */
+ sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
+ ASSERT_GE(sock_fd, 0);
+
+ /* Use SIOCGSKNS */
+ netns_fd = ioctl(sock_fd, SIOCGSKNS);
+ if (netns_fd < 0) {
+ close(sock_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_fd, 0);
+ }
+
+ /* Verify it matches current namespace */
+ current_netns_fd = open("/proc/self/ns/net", O_RDONLY);
+ ASSERT_GE(current_netns_fd, 0);
+
+ ASSERT_EQ(fstat(netns_fd, &st1), 0);
+ ASSERT_EQ(fstat(current_netns_fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+
+ close(sock_fd);
+ close(netns_fd);
+ close(current_netns_fd);
+}
+
+/*
+ * Test that socket-kept netns appears in listns() output.
+ * Verify that a network namespace kept alive by a socket FD appears in
+ * listns() output even after the creating process exits, and that it
+ * disappears when the socket is closed.
+ */
+TEST(siocgskns_listns_visibility)
+{
+ int sock_fd, netns_fd, owner_fd;
+ int ipc_sockets[2];
+ pid_t pid;
+ int status;
+ __u64 netns_id, owner_id;
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWNET,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[256];
+ int ret, i;
+ bool found_netns = false;
+
+ EXPECT_EQ(socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child: create new netns and socket */
+ close(ipc_sockets[0]);
+
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ sock_fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (sock_fd < 0) {
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ /* Send socket FD to parent via SCM_RIGHTS */
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1] = {'X'};
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ struct cmsghdr *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), &sock_fd, sizeof(int));
+
+ if (sendmsg(ipc_sockets[1], &msg, 0) < 0) {
+ close(sock_fd);
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ close(sock_fd);
+ close(ipc_sockets[1]);
+ exit(0);
+ }
+
+ /* Parent: receive socket FD */
+ close(ipc_sockets[1]);
+
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1];
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ ssize_t n = recvmsg(ipc_sockets[0], &msg, 0);
+ close(ipc_sockets[0]);
+ ASSERT_EQ(n, 1);
+
+ struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+ ASSERT_NE(cmsg, NULL);
+ memcpy(&sock_fd, CMSG_DATA(cmsg), sizeof(int));
+
+ /* Wait for child to exit */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Get network namespace from socket */
+ netns_fd = ioctl(sock_fd, SIOCGSKNS);
+ if (netns_fd < 0) {
+ close(sock_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_fd, 0);
+ }
+
+ /* Get namespace ID */
+ ret = ioctl(netns_fd, NS_GET_ID, &netns_id);
+ if (ret < 0) {
+ close(sock_fd);
+ close(netns_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "NS_GET_ID not supported");
+ ASSERT_EQ(ret, 0);
+ }
+
+ /* Get owner user namespace */
+ owner_fd = ioctl(netns_fd, NS_GET_USERNS);
+ if (owner_fd < 0) {
+ close(sock_fd);
+ close(netns_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "NS_GET_USERNS not supported");
+ ASSERT_GE(owner_fd, 0);
+ }
+
+ /* Get owner namespace ID */
+ ret = ioctl(owner_fd, NS_GET_ID, &owner_id);
+ if (ret < 0) {
+ close(owner_fd);
+ close(sock_fd);
+ close(netns_fd);
+ ASSERT_EQ(ret, 0);
+ }
+ close(owner_fd);
+
+ /* Namespace should appear in listns() output */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ close(sock_fd);
+ close(netns_fd);
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ TH_LOG("listns failed: %s", strerror(errno));
+ ASSERT_GE(ret, 0);
+ }
+
+ /* Search for our network namespace in the list */
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == netns_id) {
+ found_netns = true;
+ break;
+ }
+ }
+
+ ASSERT_TRUE(found_netns);
+ TH_LOG("Found netns %llu in listns() output (kept alive by socket)", netns_id);
+
+ /* Now verify with owner filtering */
+ req.user_ns_id = owner_id;
+ found_netns = false;
+
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ ASSERT_GE(ret, 0);
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == netns_id) {
+ found_netns = true;
+ break;
+ }
+ }
+
+ ASSERT_TRUE(found_netns);
+ TH_LOG("Found netns %llu owned by userns %llu", netns_id, owner_id);
+
+ /* Close socket - namespace should become inactive and disappear from listns() */
+ close(sock_fd);
+ close(netns_fd);
+
+ /* Verify it's no longer in listns() output */
+ req.user_ns_id = 0;
+ found_netns = false;
+
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ ASSERT_GE(ret, 0);
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == netns_id) {
+ found_netns = true;
+ break;
+ }
+ }
+
+ ASSERT_FALSE(found_netns);
+ TH_LOG("Netns %llu correctly disappeared from listns() after socket closed", netns_id);
+}
+
+/*
+ * Test that socket-kept netns can be reopened via file handle.
+ * Verify that a network namespace kept alive by a socket FD can be
+ * reopened using file handles even after the creating process exits.
+ */
+TEST(siocgskns_file_handle)
+{
+ int sock_fd, netns_fd, reopened_fd;
+ int ipc_sockets[2];
+ pid_t pid;
+ int status;
+ struct stat st1, st2;
+ ino_t netns_ino;
+ __u64 netns_id;
+ struct file_handle *handle;
+ struct nsfs_file_handle *nsfs_fh;
+ int ret;
+
+ /* Allocate file_handle structure for nsfs */
+ handle = malloc(sizeof(struct file_handle) + sizeof(struct nsfs_file_handle));
+ ASSERT_NE(handle, NULL);
+ handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ handle->handle_type = FILEID_NSFS;
+
+ EXPECT_EQ(socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child: create new netns and socket */
+ close(ipc_sockets[0]);
+
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ sock_fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (sock_fd < 0) {
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ /* Send socket FD to parent via SCM_RIGHTS */
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1] = {'X'};
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ struct cmsghdr *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), &sock_fd, sizeof(int));
+
+ if (sendmsg(ipc_sockets[1], &msg, 0) < 0) {
+ close(sock_fd);
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ close(sock_fd);
+ close(ipc_sockets[1]);
+ exit(0);
+ }
+
+ /* Parent: receive socket FD */
+ close(ipc_sockets[1]);
+
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1];
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ ssize_t n = recvmsg(ipc_sockets[0], &msg, 0);
+ close(ipc_sockets[0]);
+ ASSERT_EQ(n, 1);
+
+ struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+ ASSERT_NE(cmsg, NULL);
+ memcpy(&sock_fd, CMSG_DATA(cmsg), sizeof(int));
+
+ /* Wait for child to exit */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Get network namespace from socket */
+ netns_fd = ioctl(sock_fd, SIOCGSKNS);
+ if (netns_fd < 0) {
+ free(handle);
+ close(sock_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_fd, 0);
+ }
+
+ ASSERT_EQ(fstat(netns_fd, &st1), 0);
+ netns_ino = st1.st_ino;
+
+ /* Get namespace ID */
+ ret = ioctl(netns_fd, NS_GET_ID, &netns_id);
+ if (ret < 0) {
+ free(handle);
+ close(sock_fd);
+ close(netns_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "NS_GET_ID not supported");
+ ASSERT_EQ(ret, 0);
+ }
+
+ /* Construct file handle from namespace ID */
+ nsfs_fh = (struct nsfs_file_handle *)handle->f_handle;
+ nsfs_fh->ns_id = netns_id;
+ nsfs_fh->ns_type = 0; /* Type field not needed for reopening */
+ nsfs_fh->ns_inum = 0; /* Inum field not needed for reopening */
+
+ TH_LOG("Constructed file handle for netns %lu (id=%llu)", netns_ino, netns_id);
+
+ /* Reopen namespace using file handle (while socket still keeps it alive) */
+ reopened_fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (reopened_fd < 0) {
+ free(handle);
+ close(sock_fd);
+ if (errno == EOPNOTSUPP || errno == ENOSYS || errno == EBADF)
+ SKIP(return, "open_by_handle_at with FD_NSFS_ROOT not supported");
+ TH_LOG("open_by_handle_at failed: %s", strerror(errno));
+ ASSERT_GE(reopened_fd, 0);
+ }
+
+ /* Verify it's the same namespace */
+ ASSERT_EQ(fstat(reopened_fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+ TH_LOG("Successfully reopened netns %lu via file handle", netns_ino);
+
+ close(reopened_fd);
+
+ /* Close the netns FD */
+ close(netns_fd);
+
+ /* Try to reopen via file handle - should fail since namespace is now inactive */
+ reopened_fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_LT(reopened_fd, 0);
+ TH_LOG("Correctly failed to reopen inactive netns: %s", strerror(errno));
+
+ /* Get network namespace from socket */
+ netns_fd = ioctl(sock_fd, SIOCGSKNS);
+ if (netns_fd < 0) {
+ free(handle);
+ close(sock_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_fd, 0);
+ }
+
+ /* Reopen namespace using file handle (while socket still keeps it alive) */
+ reopened_fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (reopened_fd < 0) {
+ free(handle);
+ close(sock_fd);
+ if (errno == EOPNOTSUPP || errno == ENOSYS || errno == EBADF)
+ SKIP(return, "open_by_handle_at with FD_NSFS_ROOT not supported");
+ TH_LOG("open_by_handle_at failed: %s", strerror(errno));
+ ASSERT_GE(reopened_fd, 0);
+ }
+
+ /* Verify it's the same namespace */
+ ASSERT_EQ(fstat(reopened_fd, &st2), 0);
+ ASSERT_EQ(st1.st_ino, st2.st_ino);
+ ASSERT_EQ(st1.st_dev, st2.st_dev);
+
+ TH_LOG("Successfully reopened netns %lu via file handle", netns_ino);
+
+ /* Close socket - namespace should become inactive */
+ close(sock_fd);
+ free(handle);
+}
+
+/*
+ * Test combined listns() and file handle operations with socket-kept netns.
+ * Create a netns, keep it alive with a socket, verify it appears in listns(),
+ * then reopen it via file handle obtained from listns() entry.
+ */
+TEST(siocgskns_listns_and_file_handle)
+{
+ int sock_fd, netns_fd, userns_fd, reopened_fd;
+ int ipc_sockets[2];
+ pid_t pid;
+ int status;
+ struct stat st;
+ ino_t netns_ino;
+ __u64 netns_id, userns_id;
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWNET | CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[256];
+ int ret, i;
+ bool found_netns = false, found_userns = false;
+ struct file_handle *handle;
+ struct nsfs_file_handle *nsfs_fh;
+
+ /* Allocate file_handle structure for nsfs */
+ handle = malloc(sizeof(struct file_handle) + sizeof(struct nsfs_file_handle));
+ ASSERT_NE(handle, NULL);
+ handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ handle->handle_type = FILEID_NSFS;
+
+ EXPECT_EQ(socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child: create new userns and netns with socket */
+ close(ipc_sockets[0]);
+
+ if (setup_userns() < 0) {
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ sock_fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (sock_fd < 0) {
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ /* Send socket FD to parent via SCM_RIGHTS */
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1] = {'X'};
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ struct cmsghdr *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), &sock_fd, sizeof(int));
+
+ if (sendmsg(ipc_sockets[1], &msg, 0) < 0) {
+ close(sock_fd);
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ close(sock_fd);
+ close(ipc_sockets[1]);
+ exit(0);
+ }
+
+ /* Parent: receive socket FD */
+ close(ipc_sockets[1]);
+
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1];
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ ssize_t n = recvmsg(ipc_sockets[0], &msg, 0);
+ close(ipc_sockets[0]);
+ ASSERT_EQ(n, 1);
+
+ struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+ ASSERT_NE(cmsg, NULL);
+ memcpy(&sock_fd, CMSG_DATA(cmsg), sizeof(int));
+
+ /* Wait for child to exit */
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /* Get network namespace from socket */
+ netns_fd = ioctl(sock_fd, SIOCGSKNS);
+ if (netns_fd < 0) {
+ free(handle);
+ close(sock_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_fd, 0);
+ }
+
+ ASSERT_EQ(fstat(netns_fd, &st), 0);
+ netns_ino = st.st_ino;
+
+ /* Get namespace ID */
+ ret = ioctl(netns_fd, NS_GET_ID, &netns_id);
+ if (ret < 0) {
+ free(handle);
+ close(sock_fd);
+ close(netns_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "NS_GET_ID not supported");
+ ASSERT_EQ(ret, 0);
+ }
+
+ /* Get owner user namespace */
+ userns_fd = ioctl(netns_fd, NS_GET_USERNS);
+ if (userns_fd < 0) {
+ free(handle);
+ close(sock_fd);
+ close(netns_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "NS_GET_USERNS not supported");
+ ASSERT_GE(userns_fd, 0);
+ }
+
+ /* Get owner namespace ID */
+ ret = ioctl(userns_fd, NS_GET_ID, &userns_id);
+ if (ret < 0) {
+ close(userns_fd);
+ free(handle);
+ close(sock_fd);
+ close(netns_fd);
+ ASSERT_EQ(ret, 0);
+ }
+ close(userns_fd);
+
+ TH_LOG("Testing netns %lu (id=%llu) owned by userns id=%llu", netns_ino, netns_id, userns_id);
+
+ /* Verify namespace appears in listns() */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ free(handle);
+ close(sock_fd);
+ close(netns_fd);
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ TH_LOG("listns failed: %s", strerror(errno));
+ ASSERT_GE(ret, 0);
+ }
+
+ found_netns = false;
+ found_userns = false;
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == netns_id)
+ found_netns = true;
+ if (ns_ids[i] == userns_id)
+ found_userns = true;
+ }
+ ASSERT_TRUE(found_netns);
+ ASSERT_TRUE(found_userns);
+ TH_LOG("Found netns %llu in listns() output", netns_id);
+
+ /* Construct file handle from namespace ID */
+ nsfs_fh = (struct nsfs_file_handle *)handle->f_handle;
+ nsfs_fh->ns_id = netns_id;
+ nsfs_fh->ns_type = 0;
+ nsfs_fh->ns_inum = 0;
+
+ reopened_fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (reopened_fd < 0) {
+ free(handle);
+ close(sock_fd);
+ if (errno == EOPNOTSUPP || errno == ENOSYS || errno == EBADF)
+ SKIP(return, "open_by_handle_at with FD_NSFS_ROOT not supported");
+ TH_LOG("open_by_handle_at failed: %s", strerror(errno));
+ ASSERT_GE(reopened_fd, 0);
+ }
+
+ struct stat reopened_st;
+ ASSERT_EQ(fstat(reopened_fd, &reopened_st), 0);
+ ASSERT_EQ(reopened_st.st_ino, netns_ino);
+
+ TH_LOG("Successfully reopened netns %lu via file handle (socket-kept)", netns_ino);
+
+ close(reopened_fd);
+ close(netns_fd);
+
+ /* Try to reopen via file handle - should fail since namespace is now inactive */
+ reopened_fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ ASSERT_LT(reopened_fd, 0);
+ TH_LOG("Correctly failed to reopen inactive netns: %s", strerror(errno));
+
+ /* Get network namespace from socket */
+ netns_fd = ioctl(sock_fd, SIOCGSKNS);
+ if (netns_fd < 0) {
+ free(handle);
+ close(sock_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_fd, 0);
+ }
+
+ /* Verify namespace appears in listns() */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ free(handle);
+ close(sock_fd);
+ close(netns_fd);
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ TH_LOG("listns failed: %s", strerror(errno));
+ ASSERT_GE(ret, 0);
+ }
+
+ found_netns = false;
+ found_userns = false;
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == netns_id)
+ found_netns = true;
+ if (ns_ids[i] == userns_id)
+ found_userns = true;
+ }
+ ASSERT_TRUE(found_netns);
+ ASSERT_TRUE(found_userns);
+ TH_LOG("Found netns %llu in listns() output", netns_id);
+
+ close(netns_fd);
+
+ /* Verify namespace appears in listns() */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ free(handle);
+ close(sock_fd);
+ close(netns_fd);
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ TH_LOG("listns failed: %s", strerror(errno));
+ ASSERT_GE(ret, 0);
+ }
+
+ found_netns = false;
+ found_userns = false;
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == netns_id)
+ found_netns = true;
+ if (ns_ids[i] == userns_id)
+ found_userns = true;
+ }
+ ASSERT_FALSE(found_netns);
+ ASSERT_FALSE(found_userns);
+ TH_LOG("Netns %llu correctly disappeared from listns() after socket closed", netns_id);
+
+ close(sock_fd);
+ free(handle);
+}
+
+/*
+ * Test multi-level namespace resurrection across three user namespace levels.
+ *
+ * This test creates a complex namespace hierarchy with three levels of user
+ * namespaces and a network namespace at the deepest level. It verifies that
+ * the resurrection semantics work correctly when SIOCGSKNS is called on a
+ * socket from an inactive namespace tree, and that listns() and
+ * open_by_handle_at() correctly respect visibility rules.
+ *
+ * Hierarchy after child processes exit (all with 0 active refcount):
+ *
+ * net_L3A (0) <- Level 3 network namespace
+ * |
+ * +
+ * userns_L3 (0) <- Level 3 user namespace
+ * |
+ * +
+ * userns_L2 (0) <- Level 2 user namespace
+ * |
+ * +
+ * userns_L1 (0) <- Level 1 user namespace
+ * |
+ * x
+ * init_user_ns
+ *
+ * The test verifies:
+ * 1. SIOCGSKNS on a socket from inactive net_L3A resurrects the entire chain
+ * 2. After resurrection, all namespaces are visible in listns()
+ * 3. Resurrected namespaces can be reopened via file handles
+ * 4. Closing the netns FD cascades down: the entire ownership chain
+ * (userns_L3 -> userns_L2 -> userns_L1) becomes inactive again
+ * 5. Inactive namespaces disappear from listns() and cannot be reopened
+ * 6. Calling SIOCGSKNS again on the same socket resurrects the tree again
+ * 7. After second resurrection, namespaces are visible and can be reopened
+ */
+TEST(siocgskns_multilevel_resurrection)
+{
+ int ipc_sockets[2];
+ pid_t pid_l1, pid_l2, pid_l3;
+ int status;
+
+ /* Namespace file descriptors to be received from child */
+ int sock_L3A_fd = -1;
+ int netns_L3A_fd = -1;
+ __u64 netns_L3A_id;
+ __u64 userns_L1_id, userns_L2_id, userns_L3_id;
+
+ /* For listns() and file handle testing */
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWNET | CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids[256];
+ int ret, i;
+ struct file_handle *handle;
+ struct nsfs_file_handle *nsfs_fh;
+ int reopened_fd;
+
+ /* Allocate file handle for testing */
+ handle = malloc(sizeof(struct file_handle) + sizeof(struct nsfs_file_handle));
+ ASSERT_NE(handle, NULL);
+ handle->handle_bytes = sizeof(struct nsfs_file_handle);
+ handle->handle_type = FILEID_NSFS;
+
+ EXPECT_EQ(socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+ /*
+ * Fork level 1 child that creates userns_L1
+ */
+ pid_l1 = fork();
+ ASSERT_GE(pid_l1, 0);
+
+ if (pid_l1 == 0) {
+ /* Level 1 child */
+ int ipc_L2[2];
+ close(ipc_sockets[0]);
+
+ /* Create userns_L1 */
+ if (setup_userns() < 0) {
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ /* Create socketpair for communicating with L2 child */
+ if (socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_L2) < 0) {
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ /*
+ * Fork level 2 child that creates userns_L2
+ */
+ pid_l2 = fork();
+ if (pid_l2 < 0) {
+ close(ipc_sockets[1]);
+ close(ipc_L2[0]);
+ close(ipc_L2[1]);
+ exit(1);
+ }
+
+ if (pid_l2 == 0) {
+ /* Level 2 child */
+ int ipc_L3[2];
+ close(ipc_L2[0]);
+
+ /* Create userns_L2 (nested inside userns_L1) */
+ if (setup_userns() < 0) {
+ close(ipc_L2[1]);
+ exit(1);
+ }
+
+ /* Create socketpair for communicating with L3 child */
+ if (socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_L3) < 0) {
+ close(ipc_L2[1]);
+ exit(1);
+ }
+
+ /*
+ * Fork level 3 child that creates userns_L3 and network namespaces
+ */
+ pid_l3 = fork();
+ if (pid_l3 < 0) {
+ close(ipc_L2[1]);
+ close(ipc_L3[0]);
+ close(ipc_L3[1]);
+ exit(1);
+ }
+
+ if (pid_l3 == 0) {
+ /* Level 3 child - the deepest level */
+ int sock_fd;
+ close(ipc_L3[0]);
+
+ /* Create userns_L3 (nested inside userns_L2) */
+ if (setup_userns() < 0) {
+ close(ipc_L3[1]);
+ exit(1);
+ }
+
+ /* Create network namespace at level 3 */
+ if (unshare(CLONE_NEWNET) < 0) {
+ close(ipc_L3[1]);
+ exit(1);
+ }
+
+ /* Create socket in net_L3A */
+ sock_fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (sock_fd < 0) {
+ close(ipc_L3[1]);
+ exit(1);
+ }
+
+ /* Send socket FD to L2 parent */
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1] = {'X'};
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ struct cmsghdr *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), &sock_fd, sizeof(int));
+
+ if (sendmsg(ipc_L3[1], &msg, 0) < 0) {
+ close(sock_fd);
+ close(ipc_L3[1]);
+ exit(1);
+ }
+
+ close(sock_fd);
+ close(ipc_L3[1]);
+ exit(0);
+ }
+
+ /* Level 2 child - receive from L3 and forward to L1 */
+ close(ipc_L3[1]);
+
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1];
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+ int received_fd;
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ ssize_t n = recvmsg(ipc_L3[0], &msg, 0);
+ close(ipc_L3[0]);
+
+ if (n != 1) {
+ close(ipc_L2[1]);
+ waitpid(pid_l3, NULL, 0);
+ exit(1);
+ }
+
+ struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+ if (!cmsg) {
+ close(ipc_L2[1]);
+ waitpid(pid_l3, NULL, 0);
+ exit(1);
+ }
+ memcpy(&received_fd, CMSG_DATA(cmsg), sizeof(int));
+
+ /* Wait for L3 child */
+ waitpid(pid_l3, NULL, 0);
+
+ /* Forward the socket FD to L1 parent */
+ memset(&msg, 0, sizeof(msg));
+ buf[0] = 'Y';
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ 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), &received_fd, sizeof(int));
+
+ if (sendmsg(ipc_L2[1], &msg, 0) < 0) {
+ close(received_fd);
+ close(ipc_L2[1]);
+ exit(1);
+ }
+
+ close(received_fd);
+ close(ipc_L2[1]);
+ exit(0);
+ }
+
+ /* Level 1 child - receive from L2 and forward to parent */
+ close(ipc_L2[1]);
+
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1];
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+ int received_fd;
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ ssize_t n = recvmsg(ipc_L2[0], &msg, 0);
+ close(ipc_L2[0]);
+
+ if (n != 1) {
+ close(ipc_sockets[1]);
+ waitpid(pid_l2, NULL, 0);
+ exit(1);
+ }
+
+ struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+ if (!cmsg) {
+ close(ipc_sockets[1]);
+ waitpid(pid_l2, NULL, 0);
+ exit(1);
+ }
+ memcpy(&received_fd, CMSG_DATA(cmsg), sizeof(int));
+
+ /* Wait for L2 child */
+ waitpid(pid_l2, NULL, 0);
+
+ /* Forward the socket FD to parent */
+ memset(&msg, 0, sizeof(msg));
+ buf[0] = 'Z';
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ 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), &received_fd, sizeof(int));
+
+ if (sendmsg(ipc_sockets[1], &msg, 0) < 0) {
+ close(received_fd);
+ close(ipc_sockets[1]);
+ exit(1);
+ }
+
+ close(received_fd);
+ close(ipc_sockets[1]);
+ exit(0);
+ }
+
+ /* Parent - receive the socket from the deepest level */
+ close(ipc_sockets[1]);
+
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[1];
+ char cmsg_buf[CMSG_SPACE(sizeof(int))];
+
+ iov.iov_base = buf;
+ iov.iov_len = 1;
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsg_buf;
+ msg.msg_controllen = sizeof(cmsg_buf);
+
+ ssize_t n = recvmsg(ipc_sockets[0], &msg, 0);
+ close(ipc_sockets[0]);
+
+ if (n != 1) {
+ free(handle);
+ waitpid(pid_l1, NULL, 0);
+ SKIP(return, "Failed to receive socket from child");
+ }
+
+ struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+ if (!cmsg) {
+ free(handle);
+ waitpid(pid_l1, NULL, 0);
+ SKIP(return, "Failed to receive socket from child");
+ }
+ memcpy(&sock_L3A_fd, CMSG_DATA(cmsg), sizeof(int));
+
+ /* Wait for L1 child */
+ waitpid(pid_l1, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+
+ /*
+ * At this point, all child processes have exited. The socket itself
+ * doesn't keep the namespace active - we need to call SIOCGSKNS which
+ * will resurrect the entire namespace tree by taking active references.
+ */
+
+ /* Get network namespace from socket - this resurrects the tree */
+ netns_L3A_fd = ioctl(sock_L3A_fd, SIOCGSKNS);
+ if (netns_L3A_fd < 0) {
+ free(handle);
+ close(sock_L3A_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "SIOCGSKNS not supported");
+ ASSERT_GE(netns_L3A_fd, 0);
+ }
+
+ /* Get namespace ID for net_L3A */
+ ret = ioctl(netns_L3A_fd, NS_GET_ID, &netns_L3A_id);
+ if (ret < 0) {
+ free(handle);
+ close(sock_L3A_fd);
+ close(netns_L3A_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "NS_GET_ID not supported");
+ ASSERT_EQ(ret, 0);
+ }
+
+ /* Get owner user namespace chain: userns_L3 -> userns_L2 -> userns_L1 */
+ int userns_L3_fd = ioctl(netns_L3A_fd, NS_GET_USERNS);
+ if (userns_L3_fd < 0) {
+ free(handle);
+ close(sock_L3A_fd);
+ close(netns_L3A_fd);
+ if (errno == ENOTTY || errno == EINVAL)
+ SKIP(return, "NS_GET_USERNS not supported");
+ ASSERT_GE(userns_L3_fd, 0);
+ }
+
+ ret = ioctl(userns_L3_fd, NS_GET_ID, &userns_L3_id);
+ ASSERT_EQ(ret, 0);
+
+ int userns_L2_fd = ioctl(userns_L3_fd, NS_GET_USERNS);
+ ASSERT_GE(userns_L2_fd, 0);
+ ret = ioctl(userns_L2_fd, NS_GET_ID, &userns_L2_id);
+ ASSERT_EQ(ret, 0);
+
+ int userns_L1_fd = ioctl(userns_L2_fd, NS_GET_USERNS);
+ ASSERT_GE(userns_L1_fd, 0);
+ ret = ioctl(userns_L1_fd, NS_GET_ID, &userns_L1_id);
+ ASSERT_EQ(ret, 0);
+
+ close(userns_L1_fd);
+ close(userns_L2_fd);
+ close(userns_L3_fd);
+
+ TH_LOG("Multi-level hierarchy: net_L3A (id=%llu) -> userns_L3 (id=%llu) -> userns_L2 (id=%llu) -> userns_L1 (id=%llu)",
+ netns_L3A_id, userns_L3_id, userns_L2_id, userns_L1_id);
+
+ /*
+ * Test 1: Verify net_L3A is visible in listns() after resurrection.
+ * The entire ownership chain should be resurrected and visible.
+ */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ if (ret < 0) {
+ free(handle);
+ close(sock_L3A_fd);
+ close(netns_L3A_fd);
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret, 0);
+ }
+
+ bool found_netns_L3A = false;
+ bool found_userns_L1 = false;
+ bool found_userns_L2 = false;
+ bool found_userns_L3 = false;
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == netns_L3A_id)
+ found_netns_L3A = true;
+ if (ns_ids[i] == userns_L1_id)
+ found_userns_L1 = true;
+ if (ns_ids[i] == userns_L2_id)
+ found_userns_L2 = true;
+ if (ns_ids[i] == userns_L3_id)
+ found_userns_L3 = true;
+ }
+
+ ASSERT_TRUE(found_netns_L3A);
+ ASSERT_TRUE(found_userns_L1);
+ ASSERT_TRUE(found_userns_L2);
+ ASSERT_TRUE(found_userns_L3);
+ TH_LOG("Resurrection verified: all namespaces in hierarchy visible in listns()");
+
+ /*
+ * Test 2: Verify net_L3A can be reopened via file handle.
+ */
+ nsfs_fh = (struct nsfs_file_handle *)handle->f_handle;
+ nsfs_fh->ns_id = netns_L3A_id;
+ nsfs_fh->ns_type = 0;
+ nsfs_fh->ns_inum = 0;
+
+ reopened_fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (reopened_fd < 0) {
+ free(handle);
+ close(sock_L3A_fd);
+ close(netns_L3A_fd);
+ if (errno == EOPNOTSUPP || errno == ENOSYS || errno == EBADF)
+ SKIP(return, "open_by_handle_at with FD_NSFS_ROOT not supported");
+ TH_LOG("open_by_handle_at failed: %s", strerror(errno));
+ ASSERT_GE(reopened_fd, 0);
+ }
+
+ close(reopened_fd);
+ TH_LOG("File handle test passed: net_L3A can be reopened");
+
+ /*
+ * Test 3: Verify that when we close the netns FD (dropping the last
+ * active reference), the entire tree becomes inactive and disappears
+ * from listns(). The cascade goes: net_L3A drops -> userns_L3 drops ->
+ * userns_L2 drops -> userns_L1 drops.
+ */
+ close(netns_L3A_fd);
+
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ ASSERT_GE(ret, 0);
+
+ found_netns_L3A = false;
+ found_userns_L1 = false;
+ found_userns_L2 = false;
+ found_userns_L3 = false;
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == netns_L3A_id)
+ found_netns_L3A = true;
+ if (ns_ids[i] == userns_L1_id)
+ found_userns_L1 = true;
+ if (ns_ids[i] == userns_L2_id)
+ found_userns_L2 = true;
+ if (ns_ids[i] == userns_L3_id)
+ found_userns_L3 = true;
+ }
+
+ ASSERT_FALSE(found_netns_L3A);
+ ASSERT_FALSE(found_userns_L1);
+ ASSERT_FALSE(found_userns_L2);
+ ASSERT_FALSE(found_userns_L3);
+ TH_LOG("Cascade test passed: all namespaces disappeared after netns FD closed");
+
+ /*
+ * Test 4: Verify file handle no longer works for inactive namespace.
+ */
+ reopened_fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (reopened_fd >= 0) {
+ close(reopened_fd);
+ free(handle);
+ ASSERT_TRUE(false); /* Should have failed */
+ }
+ TH_LOG("Inactive namespace correctly cannot be reopened via file handle");
+
+ /*
+ * Test 5: Verify that calling SIOCGSKNS again resurrects the tree again.
+ * The socket is still valid, so we can call SIOCGSKNS on it to resurrect
+ * the namespace tree once more.
+ */
+ netns_L3A_fd = ioctl(sock_L3A_fd, SIOCGSKNS);
+ ASSERT_GE(netns_L3A_fd, 0);
+
+ TH_LOG("Called SIOCGSKNS again to resurrect the namespace tree");
+
+ /* Verify the namespace tree is resurrected and visible in listns() */
+ ret = sys_listns(&req, ns_ids, ARRAY_SIZE(ns_ids), 0);
+ ASSERT_GE(ret, 0);
+
+ found_netns_L3A = false;
+ found_userns_L1 = false;
+ found_userns_L2 = false;
+ found_userns_L3 = false;
+
+ for (i = 0; i < ret; i++) {
+ if (ns_ids[i] == netns_L3A_id)
+ found_netns_L3A = true;
+ if (ns_ids[i] == userns_L1_id)
+ found_userns_L1 = true;
+ if (ns_ids[i] == userns_L2_id)
+ found_userns_L2 = true;
+ if (ns_ids[i] == userns_L3_id)
+ found_userns_L3 = true;
+ }
+
+ ASSERT_TRUE(found_netns_L3A);
+ ASSERT_TRUE(found_userns_L1);
+ ASSERT_TRUE(found_userns_L2);
+ ASSERT_TRUE(found_userns_L3);
+ TH_LOG("Second resurrection verified: all namespaces in hierarchy visible in listns() again");
+
+ /* Verify we can reopen via file handle again */
+ reopened_fd = open_by_handle_at(FD_NSFS_ROOT, handle, O_RDONLY);
+ if (reopened_fd < 0) {
+ free(handle);
+ close(sock_L3A_fd);
+ close(netns_L3A_fd);
+ TH_LOG("open_by_handle_at failed after second resurrection: %s", strerror(errno));
+ ASSERT_GE(reopened_fd, 0);
+ }
+
+ close(reopened_fd);
+ TH_LOG("File handle test passed: net_L3A can be reopened after second resurrection");
+
+ /* Final cleanup */
+ close(sock_L3A_fd);
+ close(netns_L3A_fd);
+ free(handle);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/stress_test.c b/tools/testing/selftests/namespaces/stress_test.c
new file mode 100644
index 000000000000..dd7df7d6cb27
--- /dev/null
+++ b/tools/testing/selftests/namespaces/stress_test.c
@@ -0,0 +1,626 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <linux/nsfs.h>
+#include "../kselftest_harness.h"
+#include "../filesystems/utils.h"
+#include "wrappers.h"
+
+/*
+ * Stress tests for namespace active reference counting.
+ *
+ * These tests validate that the active reference counting system can handle
+ * high load scenarios including rapid namespace creation/destruction, large
+ * numbers of concurrent namespaces, and various edge cases under stress.
+ */
+
+/*
+ * Test rapid creation and destruction of user namespaces.
+ * Create and destroy namespaces in quick succession to stress the
+ * active reference tracking and ensure no leaks occur.
+ */
+TEST(rapid_namespace_creation_destruction)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids_before[256], ns_ids_after[256];
+ ssize_t ret_before, ret_after;
+ int i;
+
+ /* Get baseline count of active user namespaces */
+ ret_before = sys_listns(&req, ns_ids_before, ARRAY_SIZE(ns_ids_before), 0);
+ if (ret_before < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret_before, 0);
+ }
+
+ TH_LOG("Baseline: %zd active user namespaces", ret_before);
+
+ /* Rapidly create and destroy 100 user namespaces */
+ for (i = 0; i < 100; i++) {
+ pid_t pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child: create user namespace and immediately exit */
+ if (setup_userns() < 0)
+ exit(1);
+ exit(0);
+ }
+
+ /* Parent: wait for child */
+ int status;
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+ }
+
+ /* Verify we're back to baseline (no leaked namespaces) */
+ ret_after = sys_listns(&req, ns_ids_after, ARRAY_SIZE(ns_ids_after), 0);
+ ASSERT_GE(ret_after, 0);
+
+ TH_LOG("After 100 rapid create/destroy cycles: %zd active user namespaces", ret_after);
+ ASSERT_EQ(ret_before, ret_after);
+}
+
+/*
+ * Test creating many concurrent namespaces.
+ * Verify that listns() correctly tracks all of them and that they all
+ * become inactive after processes exit.
+ */
+TEST(many_concurrent_namespaces)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids_before[512], ns_ids_during[512], ns_ids_after[512];
+ ssize_t ret_before, ret_during, ret_after;
+ pid_t pids[50];
+ int num_children = 50;
+ int i;
+ int sv[2];
+
+ /* Get baseline */
+ ret_before = sys_listns(&req, ns_ids_before, ARRAY_SIZE(ns_ids_before), 0);
+ if (ret_before < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret_before, 0);
+ }
+
+ TH_LOG("Baseline: %zd active user namespaces", ret_before);
+
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sv), 0);
+
+ /* Create many children, each with their own user namespace */
+ for (i = 0; i < num_children; i++) {
+ pids[i] = fork();
+ ASSERT_GE(pids[i], 0);
+
+ if (pids[i] == 0) {
+ /* Child: create user namespace and wait for parent signal */
+ char c;
+
+ close(sv[0]);
+
+ if (setup_userns() < 0) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ /* Signal parent we're ready */
+ if (write(sv[1], &c, 1) != 1) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ /* Wait for parent signal to exit */
+ if (read(sv[1], &c, 1) != 1) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ close(sv[1]);
+ exit(0);
+ }
+ }
+
+ close(sv[1]);
+
+ /* Wait for all children to signal ready */
+ for (i = 0; i < num_children; i++) {
+ char c;
+ if (read(sv[0], &c, 1) != 1) {
+ /* If we fail to read, kill all children and exit */
+ close(sv[0]);
+ for (int j = 0; j < num_children; j++)
+ kill(pids[j], SIGKILL);
+ for (int j = 0; j < num_children; j++)
+ waitpid(pids[j], NULL, 0);
+ ASSERT_TRUE(false);
+ }
+ }
+
+ /* List namespaces while all children are running */
+ ret_during = sys_listns(&req, ns_ids_during, ARRAY_SIZE(ns_ids_during), 0);
+ ASSERT_GE(ret_during, 0);
+
+ TH_LOG("With %d children running: %zd active user namespaces", num_children, ret_during);
+
+ /* Should have at least num_children more namespaces than baseline */
+ ASSERT_GE(ret_during, ret_before + num_children);
+
+ /* Signal all children to exit */
+ for (i = 0; i < num_children; i++) {
+ char c = 'X';
+ if (write(sv[0], &c, 1) != 1) {
+ /* If we fail to write, kill remaining children */
+ close(sv[0]);
+ for (int j = i; j < num_children; j++)
+ kill(pids[j], SIGKILL);
+ for (int j = 0; j < num_children; j++)
+ waitpid(pids[j], NULL, 0);
+ ASSERT_TRUE(false);
+ }
+ }
+
+ close(sv[0]);
+
+ /* Wait for all children */
+ for (i = 0; i < num_children; i++) {
+ int status;
+ waitpid(pids[i], &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ }
+
+ /* Verify we're back to baseline */
+ ret_after = sys_listns(&req, ns_ids_after, ARRAY_SIZE(ns_ids_after), 0);
+ ASSERT_GE(ret_after, 0);
+
+ TH_LOG("After all children exit: %zd active user namespaces", ret_after);
+ ASSERT_EQ(ret_before, ret_after);
+}
+
+/*
+ * Test rapid namespace creation with different namespace types.
+ * Create multiple types of namespaces rapidly to stress the tracking system.
+ */
+TEST(rapid_mixed_namespace_creation)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0, /* All types */
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids_before[512], ns_ids_after[512];
+ ssize_t ret_before, ret_after;
+ int i;
+
+ /* Get baseline count */
+ ret_before = sys_listns(&req, ns_ids_before, ARRAY_SIZE(ns_ids_before), 0);
+ if (ret_before < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret_before, 0);
+ }
+
+ TH_LOG("Baseline: %zd active namespaces (all types)", ret_before);
+
+ /* Rapidly create and destroy namespaces with multiple types */
+ for (i = 0; i < 50; i++) {
+ pid_t pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* Child: create multiple namespace types */
+ if (setup_userns() < 0)
+ exit(1);
+
+ /* Create additional namespace types */
+ if (unshare(CLONE_NEWNET) < 0)
+ exit(1);
+ if (unshare(CLONE_NEWUTS) < 0)
+ exit(1);
+ if (unshare(CLONE_NEWIPC) < 0)
+ exit(1);
+
+ exit(0);
+ }
+
+ /* Parent: wait for child */
+ int status;
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ }
+
+ /* Verify we're back to baseline */
+ ret_after = sys_listns(&req, ns_ids_after, ARRAY_SIZE(ns_ids_after), 0);
+ ASSERT_GE(ret_after, 0);
+
+ TH_LOG("After 50 rapid mixed namespace cycles: %zd active namespaces", ret_after);
+ ASSERT_EQ(ret_before, ret_after);
+}
+
+/*
+ * Test nested namespace creation under stress.
+ * Create deeply nested namespace hierarchies and verify proper cleanup.
+ */
+TEST(nested_namespace_stress)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids_before[512], ns_ids_after[512];
+ ssize_t ret_before, ret_after;
+ int i;
+
+ /* Get baseline */
+ ret_before = sys_listns(&req, ns_ids_before, ARRAY_SIZE(ns_ids_before), 0);
+ if (ret_before < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret_before, 0);
+ }
+
+ TH_LOG("Baseline: %zd active user namespaces", ret_before);
+
+ /* Create 20 processes, each with nested user namespaces */
+ for (i = 0; i < 20; i++) {
+ pid_t pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ int userns_fd;
+ uid_t orig_uid = getuid();
+ int depth;
+
+ /* Create nested user namespaces (up to 5 levels) */
+ for (depth = 0; depth < 5; depth++) {
+ userns_fd = get_userns_fd(0, (depth == 0) ? orig_uid : 0, 1);
+ if (userns_fd < 0)
+ exit(1);
+
+ if (setns(userns_fd, CLONE_NEWUSER) < 0) {
+ close(userns_fd);
+ exit(1);
+ }
+ close(userns_fd);
+ }
+
+ exit(0);
+ }
+
+ /* Parent: wait for child */
+ int status;
+ waitpid(pid, &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ }
+
+ /* Verify we're back to baseline */
+ ret_after = sys_listns(&req, ns_ids_after, ARRAY_SIZE(ns_ids_after), 0);
+ ASSERT_GE(ret_after, 0);
+
+ TH_LOG("After 20 nested namespace hierarchies: %zd active user namespaces", ret_after);
+ ASSERT_EQ(ret_before, ret_after);
+}
+
+/*
+ * Test listns() pagination under stress.
+ * Create many namespaces and verify pagination works correctly.
+ */
+TEST(listns_pagination_stress)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ pid_t pids[30];
+ int num_children = 30;
+ int i;
+ int sv[2];
+ __u64 all_ns_ids[512];
+ int total_found = 0;
+
+ ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sv), 0);
+
+ /* Create many children with user namespaces */
+ for (i = 0; i < num_children; i++) {
+ pids[i] = fork();
+ ASSERT_GE(pids[i], 0);
+
+ if (pids[i] == 0) {
+ char c;
+ close(sv[0]);
+
+ if (setup_userns() < 0) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ /* Signal parent we're ready */
+ if (write(sv[1], &c, 1) != 1) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ /* Wait for parent signal to exit */
+ if (read(sv[1], &c, 1) != 1) {
+ close(sv[1]);
+ exit(1);
+ }
+
+ close(sv[1]);
+ exit(0);
+ }
+ }
+
+ close(sv[1]);
+
+ /* Wait for all children to signal ready */
+ for (i = 0; i < num_children; i++) {
+ char c;
+ if (read(sv[0], &c, 1) != 1) {
+ /* If we fail to read, kill all children and exit */
+ close(sv[0]);
+ for (int j = 0; j < num_children; j++)
+ kill(pids[j], SIGKILL);
+ for (int j = 0; j < num_children; j++)
+ waitpid(pids[j], NULL, 0);
+ ASSERT_TRUE(false);
+ }
+ }
+
+ /* Paginate through all namespaces using small batch sizes */
+ req.ns_id = 0;
+ while (1) {
+ __u64 batch[5]; /* Small batch size to force pagination */
+ ssize_t ret;
+
+ ret = sys_listns(&req, batch, ARRAY_SIZE(batch), 0);
+ if (ret < 0) {
+ if (errno == ENOSYS) {
+ close(sv[0]);
+ for (i = 0; i < num_children; i++)
+ kill(pids[i], SIGKILL);
+ for (i = 0; i < num_children; i++)
+ waitpid(pids[i], NULL, 0);
+ SKIP(return, "listns() not supported");
+ }
+ ASSERT_GE(ret, 0);
+ }
+
+ if (ret == 0)
+ break;
+
+ /* Store results */
+ for (i = 0; i < ret && total_found < 512; i++) {
+ all_ns_ids[total_found++] = batch[i];
+ }
+
+ /* Update cursor for next batch */
+ if (ret == ARRAY_SIZE(batch))
+ req.ns_id = batch[ret - 1];
+ else
+ break;
+ }
+
+ TH_LOG("Paginated through %d user namespaces", total_found);
+
+ /* Verify no duplicates in pagination */
+ for (i = 0; i < total_found; i++) {
+ for (int j = i + 1; j < total_found; j++) {
+ if (all_ns_ids[i] == all_ns_ids[j]) {
+ TH_LOG("Found duplicate ns_id: %llu at positions %d and %d",
+ (unsigned long long)all_ns_ids[i], i, j);
+ ASSERT_TRUE(false);
+ }
+ }
+ }
+
+ /* Signal all children to exit */
+ for (i = 0; i < num_children; i++) {
+ char c = 'X';
+ if (write(sv[0], &c, 1) != 1) {
+ close(sv[0]);
+ for (int j = i; j < num_children; j++)
+ kill(pids[j], SIGKILL);
+ for (int j = 0; j < num_children; j++)
+ waitpid(pids[j], NULL, 0);
+ ASSERT_TRUE(false);
+ }
+ }
+
+ close(sv[0]);
+
+ /* Wait for all children */
+ for (i = 0; i < num_children; i++) {
+ int status;
+ waitpid(pids[i], &status, 0);
+ }
+}
+
+/*
+ * Test concurrent namespace operations.
+ * Multiple processes creating, querying, and destroying namespaces concurrently.
+ */
+TEST(concurrent_namespace_operations)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = 0,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids_before[512], ns_ids_after[512];
+ ssize_t ret_before, ret_after;
+ pid_t pids[20];
+ int num_workers = 20;
+ int i;
+
+ /* Get baseline */
+ ret_before = sys_listns(&req, ns_ids_before, ARRAY_SIZE(ns_ids_before), 0);
+ if (ret_before < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret_before, 0);
+ }
+
+ TH_LOG("Baseline: %zd active namespaces", ret_before);
+
+ /* Create worker processes that do concurrent operations */
+ for (i = 0; i < num_workers; i++) {
+ pids[i] = fork();
+ ASSERT_GE(pids[i], 0);
+
+ if (pids[i] == 0) {
+ /* Each worker: create namespaces, list them, repeat */
+ int iterations;
+
+ for (iterations = 0; iterations < 10; iterations++) {
+ int userns_fd;
+ __u64 temp_ns_ids[100];
+ ssize_t ret;
+
+ /* Create a user namespace */
+ userns_fd = get_userns_fd(0, getuid(), 1);
+ if (userns_fd < 0)
+ continue;
+
+ /* List namespaces */
+ ret = sys_listns(&req, temp_ns_ids, ARRAY_SIZE(temp_ns_ids), 0);
+ (void)ret;
+
+ close(userns_fd);
+
+ /* Small delay */
+ usleep(1000);
+ }
+
+ exit(0);
+ }
+ }
+
+ /* Wait for all workers */
+ for (i = 0; i < num_workers; i++) {
+ int status;
+ waitpid(pids[i], &status, 0);
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(WEXITSTATUS(status), 0);
+ }
+
+ /* Verify we're back to baseline */
+ ret_after = sys_listns(&req, ns_ids_after, ARRAY_SIZE(ns_ids_after), 0);
+ ASSERT_GE(ret_after, 0);
+
+ TH_LOG("After concurrent operations: %zd active namespaces", ret_after);
+ ASSERT_EQ(ret_before, ret_after);
+}
+
+/*
+ * Test namespace churn - continuous creation and destruction.
+ * Simulates high-churn scenarios like container orchestration.
+ */
+TEST(namespace_churn)
+{
+ struct ns_id_req req = {
+ .size = sizeof(req),
+ .spare = 0,
+ .ns_id = 0,
+ .ns_type = CLONE_NEWUSER | CLONE_NEWNET | CLONE_NEWUTS,
+ .spare2 = 0,
+ .user_ns_id = 0,
+ };
+ __u64 ns_ids_before[512], ns_ids_after[512];
+ ssize_t ret_before, ret_after;
+ int cycle;
+
+ /* Get baseline */
+ ret_before = sys_listns(&req, ns_ids_before, ARRAY_SIZE(ns_ids_before), 0);
+ if (ret_before < 0) {
+ if (errno == ENOSYS)
+ SKIP(return, "listns() not supported");
+ ASSERT_GE(ret_before, 0);
+ }
+
+ TH_LOG("Baseline: %zd active namespaces", ret_before);
+
+ /* Simulate churn: batches of namespaces created and destroyed */
+ for (cycle = 0; cycle < 10; cycle++) {
+ pid_t batch_pids[10];
+ int i;
+
+ /* Create batch */
+ for (i = 0; i < 10; i++) {
+ batch_pids[i] = fork();
+ ASSERT_GE(batch_pids[i], 0);
+
+ if (batch_pids[i] == 0) {
+ /* Create multiple namespace types */
+ if (setup_userns() < 0)
+ exit(1);
+ if (unshare(CLONE_NEWNET) < 0)
+ exit(1);
+ if (unshare(CLONE_NEWUTS) < 0)
+ exit(1);
+
+ /* Keep namespaces alive briefly */
+ usleep(10000);
+ exit(0);
+ }
+ }
+
+ /* Wait for batch to complete */
+ for (i = 0; i < 10; i++) {
+ int status;
+ waitpid(batch_pids[i], &status, 0);
+ }
+ }
+
+ /* Verify we're back to baseline */
+ ret_after = sys_listns(&req, ns_ids_after, ARRAY_SIZE(ns_ids_after), 0);
+ ASSERT_GE(ret_after, 0);
+
+ TH_LOG("After 10 churn cycles (100 namespace sets): %zd active namespaces", ret_after);
+ ASSERT_EQ(ret_before, ret_after);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/namespaces/wrappers.h b/tools/testing/selftests/namespaces/wrappers.h
new file mode 100644
index 000000000000..9741a64a5b1d
--- /dev/null
+++ b/tools/testing/selftests/namespaces/wrappers.h
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/nsfs.h>
+#include <linux/types.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#ifndef __SELFTESTS_NAMESPACES_WRAPPERS_H__
+#define __SELFTESTS_NAMESPACES_WRAPPERS_H__
+
+#ifndef __NR_listns
+ #if defined __alpha__
+ #define __NR_listns 580
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_listns 4470
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_listns 6470
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_listns 5470
+ #endif
+ #else
+ #define __NR_listns 470
+ #endif
+#endif
+
+static inline int sys_listns(const struct ns_id_req *req, __u64 *ns_ids,
+ size_t nr_ns_ids, unsigned int flags)
+{
+ return syscall(__NR_listns, req, ns_ids, nr_ns_ids, flags);
+}
+
+#endif /* __SELFTESTS_NAMESPACES_WRAPPERS_H__ */
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 439101b518ee..8f9850a71f54 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -45,6 +45,7 @@ skf_net_off
socket
so_incoming_cpu
so_netns_cookie
+so_peek_off
so_txtime
so_rcv_listener
stress_reuseport_listen
diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile
index de805cbbdf69..528d14c598bb 100644
--- a/tools/testing/selftests/net/af_unix/Makefile
+++ b/tools/testing/selftests/net/af_unix/Makefile
@@ -6,6 +6,7 @@ TEST_GEN_PROGS := \
scm_inq \
scm_pidfd \
scm_rights \
+ so_peek_off \
unix_connect \
# end of TEST_GEN_PROGS
diff --git a/tools/testing/selftests/net/af_unix/so_peek_off.c b/tools/testing/selftests/net/af_unix/so_peek_off.c
new file mode 100644
index 000000000000..1a77728128e5
--- /dev/null
+++ b/tools/testing/selftests/net/af_unix/so_peek_off.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2025 Google LLC */
+
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+
+#include "../../kselftest_harness.h"
+
+FIXTURE(so_peek_off)
+{
+ int fd[2]; /* 0: sender, 1: receiver */
+};
+
+FIXTURE_VARIANT(so_peek_off)
+{
+ int type;
+};
+
+FIXTURE_VARIANT_ADD(so_peek_off, stream)
+{
+ .type = SOCK_STREAM,
+};
+
+FIXTURE_VARIANT_ADD(so_peek_off, dgram)
+{
+ .type = SOCK_DGRAM,
+};
+
+FIXTURE_VARIANT_ADD(so_peek_off, seqpacket)
+{
+ .type = SOCK_SEQPACKET,
+};
+
+FIXTURE_SETUP(so_peek_off)
+{
+ struct timeval timeout = {
+ .tv_sec = 0,
+ .tv_usec = 3000,
+ };
+ int ret;
+
+ ret = socketpair(AF_UNIX, variant->type, 0, self->fd);
+ ASSERT_EQ(0, ret);
+
+ ret = setsockopt(self->fd[1], SOL_SOCKET, SO_RCVTIMEO_NEW,
+ &timeout, sizeof(timeout));
+ ASSERT_EQ(0, ret);
+
+ ret = setsockopt(self->fd[1], SOL_SOCKET, SO_PEEK_OFF,
+ &(int){0}, sizeof(int));
+ ASSERT_EQ(0, ret);
+}
+
+FIXTURE_TEARDOWN(so_peek_off)
+{
+ close_range(self->fd[0], self->fd[1], 0);
+}
+
+#define sendeq(fd, str, flags) \
+ do { \
+ int bytes, len = strlen(str); \
+ \
+ bytes = send(fd, str, len, flags); \
+ ASSERT_EQ(len, bytes); \
+ } while (0)
+
+#define recveq(fd, str, buflen, flags) \
+ do { \
+ char buf[(buflen) + 1] = {}; \
+ int bytes; \
+ \
+ bytes = recv(fd, buf, buflen, flags); \
+ ASSERT_NE(-1, bytes); \
+ ASSERT_STREQ(str, buf); \
+ } while (0)
+
+#define async \
+ for (pid_t pid = (pid = fork(), \
+ pid < 0 ? \
+ __TH_LOG("Failed to start async {}"), \
+ _metadata->exit_code = KSFT_FAIL, \
+ __bail(1, _metadata), \
+ 0xdead : \
+ pid); \
+ !pid; exit(0))
+
+TEST_F(so_peek_off, single_chunk)
+{
+ sendeq(self->fd[0], "aaaabbbb", 0);
+
+ recveq(self->fd[1], "aaaa", 4, MSG_PEEK);
+ recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+TEST_F(so_peek_off, two_chunks)
+{
+ sendeq(self->fd[0], "aaaa", 0);
+ sendeq(self->fd[0], "bbbb", 0);
+
+ recveq(self->fd[1], "aaaa", 4, MSG_PEEK);
+ recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+TEST_F(so_peek_off, two_chunks_blocking)
+{
+ async {
+ usleep(1000);
+ sendeq(self->fd[0], "aaaa", 0);
+ }
+
+ recveq(self->fd[1], "aaaa", 4, MSG_PEEK);
+
+ async {
+ usleep(1000);
+ sendeq(self->fd[0], "bbbb", 0);
+ }
+
+ /* goto again; -> goto redo; in unix_stream_read_generic(). */
+ recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+TEST_F(so_peek_off, two_chunks_overlap)
+{
+ sendeq(self->fd[0], "aaaa", 0);
+ recveq(self->fd[1], "aa", 2, MSG_PEEK);
+
+ sendeq(self->fd[0], "bbbb", 0);
+
+ if (variant->type == SOCK_STREAM) {
+ /* SOCK_STREAM tries to fill the buffer. */
+ recveq(self->fd[1], "aabb", 4, MSG_PEEK);
+ recveq(self->fd[1], "bb", 100, MSG_PEEK);
+ } else {
+ /* SOCK_DGRAM and SOCK_SEQPACKET returns at the skb boundary. */
+ recveq(self->fd[1], "aa", 100, MSG_PEEK);
+ recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+ }
+}
+
+TEST_F(so_peek_off, two_chunks_overlap_blocking)
+{
+ async {
+ usleep(1000);
+ sendeq(self->fd[0], "aaaa", 0);
+ }
+
+ recveq(self->fd[1], "aa", 2, MSG_PEEK);
+
+ async {
+ usleep(1000);
+ sendeq(self->fd[0], "bbbb", 0);
+ }
+
+ /* Even SOCK_STREAM does not wait if at least one byte is read. */
+ recveq(self->fd[1], "aa", 100, MSG_PEEK);
+
+ recveq(self->fd[1], "bbbb", 100, MSG_PEEK);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/forwarding/lib_sh_test.sh b/tools/testing/selftests/net/forwarding/lib_sh_test.sh
index ff2accccaf4d..b4eda6c6199e 100755
--- a/tools/testing/selftests/net/forwarding/lib_sh_test.sh
+++ b/tools/testing/selftests/net/forwarding/lib_sh_test.sh
@@ -30,6 +30,11 @@ tfail()
do_test "tfail" false
}
+tfail2()
+{
+ do_test "tfail2" false
+}
+
txfail()
{
FAIL_TO_XFAIL=yes do_test "txfail" false
@@ -132,6 +137,8 @@ test_ret()
ret_subtest $ksft_fail "tfail" txfail tfail
ret_subtest $ksft_xfail "txfail" txfail txfail
+
+ ret_subtest $ksft_fail "tfail2" tfail2 tfail
}
exit_status_tests_run()
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index feba4ef69a54..f448bafb3f20 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -43,7 +43,7 @@ __ksft_status_merge()
weights[$i]=$((weight++))
done
- if [[ ${weights[$a]} > ${weights[$b]} ]]; then
+ if [[ ${weights[$a]} -ge ${weights[$b]} ]]; then
echo "$a"
return 0
else
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 41503c241989..43f31f8d587f 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3500,7 +3500,6 @@ fullmesh_tests()
fastclose_tests()
{
if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then
- MPTCP_LIB_SUBTEST_FLAKY=1
test_linkfail=1024 fastclose=client \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 0 0 0
@@ -3509,7 +3508,6 @@ fastclose_tests()
fi
if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then
- MPTCP_LIB_SUBTEST_FLAKY=1
test_linkfail=1024 fastclose=server \
run_tests $ns1 $ns2 10.0.1.1
join_rst_nr=1 \
@@ -3806,7 +3804,7 @@ userspace_tests()
continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
set_userspace_pm $ns1
pm_nl_set_limits $ns2 2 2
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
wait_mpj $ns1
@@ -3839,7 +3837,7 @@ userspace_tests()
continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
set_userspace_pm $ns2
pm_nl_set_limits $ns1 0 1
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
wait_mpj $ns2
@@ -3867,7 +3865,7 @@ userspace_tests()
continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
set_userspace_pm $ns2
pm_nl_set_limits $ns1 0 1
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
wait_mpj $ns2
@@ -3888,7 +3886,7 @@ userspace_tests()
continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
set_userspace_pm $ns2
pm_nl_set_limits $ns1 0 1
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
wait_mpj $ns2
@@ -3912,7 +3910,7 @@ userspace_tests()
continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
set_userspace_pm $ns1
pm_nl_set_limits $ns2 1 1
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
wait_mpj $ns1
@@ -3943,7 +3941,7 @@ endpoint_tests()
pm_nl_set_limits $ns1 2 2
pm_nl_set_limits $ns2 2 2
pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
- { test_linkfail=128 speed=slow \
+ { timeout_test=120 test_linkfail=128 speed=slow \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
@@ -3970,7 +3968,7 @@ endpoint_tests()
pm_nl_set_limits $ns2 0 3
pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow
pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
@@ -4048,7 +4046,7 @@ endpoint_tests()
# broadcast IP: no packet for this address will be received on ns1
pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
pm_nl_add_endpoint $ns1 10.0.1.1 id 42 flags signal
- { test_linkfail=128 speed=5 \
+ { timeout_test=120 test_linkfail=128 speed=5 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
@@ -4057,38 +4055,45 @@ endpoint_tests()
$ns1 10.0.2.1 id 1 flags signal
chk_subflow_nr "before delete" 2
chk_mptcp_info subflows 1 subflows 1
+ chk_mptcp_info add_addr_signal 2 add_addr_accepted 1
pm_nl_del_endpoint $ns1 1 10.0.2.1
pm_nl_del_endpoint $ns1 2 224.0.0.1
sleep 0.5
chk_subflow_nr "after delete" 1
chk_mptcp_info subflows 0 subflows 0
+ chk_mptcp_info add_addr_signal 0 add_addr_accepted 0
pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal
wait_mpj $ns2
chk_subflow_nr "after re-add" 3
chk_mptcp_info subflows 2 subflows 2
+ chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
pm_nl_del_endpoint $ns1 42 10.0.1.1
sleep 0.5
chk_subflow_nr "after delete ID 0" 2
chk_mptcp_info subflows 2 subflows 2
+ chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal
wait_mpj $ns2
chk_subflow_nr "after re-add ID 0" 3
chk_mptcp_info subflows 3 subflows 3
+ chk_mptcp_info add_addr_signal 3 add_addr_accepted 2
pm_nl_del_endpoint $ns1 99 10.0.1.1
sleep 0.5
chk_subflow_nr "after re-delete ID 0" 2
chk_mptcp_info subflows 2 subflows 2
+ chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
pm_nl_add_endpoint $ns1 10.0.1.1 id 88 flags signal
wait_mpj $ns2
chk_subflow_nr "after re-re-add ID 0" 3
chk_mptcp_info subflows 3 subflows 3
+ chk_mptcp_info add_addr_signal 3 add_addr_accepted 2
mptcp_lib_kill_group_wait $tests_pid
kill_events_pids
@@ -4121,7 +4126,7 @@ endpoint_tests()
# broadcast IP: no packet for this address will be received on ns1
pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
- { test_linkfail=128 speed=20 \
+ { timeout_test=120 test_linkfail=128 speed=20 \
run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
local tests_pid=$!
diff --git a/tools/testing/selftests/nolibc/Makefile.nolibc b/tools/testing/selftests/nolibc/Makefile.nolibc
index 330e000baeb1..f9d43cbdc894 100644
--- a/tools/testing/selftests/nolibc/Makefile.nolibc
+++ b/tools/testing/selftests/nolibc/Makefile.nolibc
@@ -87,7 +87,6 @@ IMAGE_riscv = arch/riscv/boot/Image
IMAGE_riscv32 = arch/riscv/boot/Image
IMAGE_riscv64 = arch/riscv/boot/Image
IMAGE_s390x = arch/s390/boot/bzImage
-IMAGE_s390 = arch/s390/boot/bzImage
IMAGE_loongarch = arch/loongarch/boot/vmlinuz.efi
IMAGE_sparc32 = arch/sparc/boot/image
IMAGE_sparc64 = arch/sparc/boot/image
@@ -117,7 +116,6 @@ DEFCONFIG_riscv = defconfig
DEFCONFIG_riscv32 = rv32_defconfig
DEFCONFIG_riscv64 = defconfig
DEFCONFIG_s390x = defconfig
-DEFCONFIG_s390 = defconfig compat.config
DEFCONFIG_loongarch = defconfig
DEFCONFIG_sparc32 = sparc32_defconfig
DEFCONFIG_sparc64 = sparc64_defconfig
@@ -156,7 +154,6 @@ QEMU_ARCH_riscv = riscv64
QEMU_ARCH_riscv32 = riscv32
QEMU_ARCH_riscv64 = riscv64
QEMU_ARCH_s390x = s390x
-QEMU_ARCH_s390 = s390x
QEMU_ARCH_loongarch = loongarch64
QEMU_ARCH_sparc32 = sparc
QEMU_ARCH_sparc64 = sparc64
@@ -197,7 +194,6 @@ QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_T
QEMU_ARGS_riscv32 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
QEMU_ARGS_riscv64 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
QEMU_ARGS_s390x = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
-QEMU_ARGS_s390 = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
QEMU_ARGS_sparc32 = -M SS-5 -m 256M -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
QEMU_ARGS_sparc64 = -M sun4u -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)"
@@ -223,13 +219,13 @@ CFLAGS_ppc = -m32 -mbig-endian -mno-vsx $(call cc-option,-mmultiple)
CFLAGS_ppc64 = -m64 -mbig-endian -mno-vsx $(call cc-option,-mmultiple)
CFLAGS_ppc64le = -m64 -mlittle-endian -mno-vsx $(call cc-option,-mabi=elfv2)
CFLAGS_s390x = -m64
-CFLAGS_s390 = -m31
CFLAGS_mips32le = -EL -mabi=32 -fPIC
CFLAGS_mips32be = -EB -mabi=32
CFLAGS_mipsn32le = -EL -mabi=n32 -fPIC -march=mips64r2
CFLAGS_mipsn32be = -EB -mabi=n32 -march=mips64r6
CFLAGS_mips64le = -EL -mabi=64 -march=mips64r6
CFLAGS_mips64be = -EB -mabi=64 -march=mips64r2
+CFLAGS_loongarch = $(if $(LLVM),-fuse-ld=lld)
CFLAGS_sparc32 = $(call cc-option,-m32)
CFLAGS_sh4 = -ml -m4
ifeq ($(origin XARCH),command line)
diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c
index 29de21595fc9..3c5a226dad3a 100644
--- a/tools/testing/selftests/nolibc/nolibc-test.c
+++ b/tools/testing/selftests/nolibc/nolibc-test.c
@@ -25,6 +25,7 @@
#include <sys/sysmacros.h>
#include <sys/time.h>
#include <sys/timerfd.h>
+#include <sys/uio.h>
#include <sys/utsname.h>
#include <sys/wait.h>
#include <dirent.h>
@@ -1282,6 +1283,10 @@ int run_syscall(int min, int max)
int proc;
int test;
int tmp;
+ struct iovec iov_one = {
+ .iov_base = &tmp,
+ .iov_len = 1,
+ };
int ret = 0;
void *p1, *p2;
int has_gettid = 1;
@@ -1343,6 +1348,8 @@ int run_syscall(int min, int max)
CASE_TEST(dup3_0); tmp = dup3(0, 100, 0); EXPECT_SYSNE(1, tmp, -1); close(tmp); break;
CASE_TEST(dup3_m1); tmp = dup3(-1, 100, 0); EXPECT_SYSER(1, tmp, -1, EBADF); if (tmp != -1) close(tmp); break;
CASE_TEST(execve_root); EXPECT_SYSER(1, execve("/", (char*[]){ [0] = "/", [1] = NULL }, NULL), -1, EACCES); break;
+ CASE_TEST(fchdir_stdin); EXPECT_SYSER(1, fchdir(STDIN_FILENO), -1, ENOTDIR); break;
+ CASE_TEST(fchdir_badfd); EXPECT_SYSER(1, fchdir(-1), -1, EBADF); break;
CASE_TEST(file_stream); EXPECT_SYSZR(1, test_file_stream()); break;
CASE_TEST(fork); EXPECT_SYSZR(1, test_fork(FORK_STANDARD)); break;
CASE_TEST(getdents64_root); EXPECT_SYSNE(1, test_getdents64("/"), -1); break;
@@ -1395,6 +1402,10 @@ int run_syscall(int min, int max)
CASE_TEST(waitpid_child); EXPECT_SYSER(1, waitpid(getpid(), &tmp, WNOHANG), -1, ECHILD); break;
CASE_TEST(write_badf); EXPECT_SYSER(1, write(-1, &tmp, 1), -1, EBADF); break;
CASE_TEST(write_zero); EXPECT_SYSZR(1, write(1, &tmp, 0)); break;
+ CASE_TEST(readv_badf); EXPECT_SYSER(1, readv(-1, &iov_one, 1), -1, EBADF); break;
+ CASE_TEST(readv_zero); EXPECT_SYSZR(1, readv(1, NULL, 0)); break;
+ CASE_TEST(writev_badf); EXPECT_SYSER(1, writev(-1, &iov_one, 1), -1, EBADF); break;
+ CASE_TEST(writev_zero); EXPECT_SYSZR(1, writev(1, NULL, 0)); break;
CASE_TEST(syscall_noargs); EXPECT_SYSEQ(1, syscall(__NR_getpid), getpid()); break;
CASE_TEST(syscall_args); EXPECT_SYSER(1, syscall(__NR_statx, 0, NULL, 0, 0, NULL), -1, EFAULT); break;
CASE_TEST(namespace); EXPECT_SYSZR(euid0 && proc, test_namespace()); break;
@@ -1540,6 +1551,8 @@ int run_stdlib(int min, int max)
CASE_TEST(abs); EXPECT_EQ(1, abs(-10), 10); break;
CASE_TEST(abs_noop); EXPECT_EQ(1, abs(10), 10); break;
CASE_TEST(difftime); EXPECT_ZR(1, test_difftime()); break;
+ CASE_TEST(memchr_foobar6_o); EXPECT_STREQ(1, memchr("foobar", 'o', 6), "oobar"); break;
+ CASE_TEST(memchr_foobar3_b); EXPECT_STRZR(1, memchr("foobar", 'b', 3)); break;
case __LINE__:
return ret; /* must be last */
diff --git a/tools/testing/selftests/nolibc/run-tests.sh b/tools/testing/selftests/nolibc/run-tests.sh
index e8af1fb505cf..3917cfb8fdc4 100755
--- a/tools/testing/selftests/nolibc/run-tests.sh
+++ b/tools/testing/selftests/nolibc/run-tests.sh
@@ -23,7 +23,7 @@ all_archs=(
mips32le mips32be mipsn32le mipsn32be mips64le mips64be
ppc ppc64 ppc64le
riscv32 riscv64
- s390x s390
+ s390x
loongarch
sparc32 sparc64
m68k
@@ -169,7 +169,7 @@ test_arch() {
cross_compile=$(realpath "${download_location}gcc-${crosstool_version}-nolibc/${ct_arch}-${ct_abi}/bin/${ct_arch}-${ct_abi}-")
build_dir="${build_location}/${arch}"
if [ "$werror" -ne 0 ]; then
- CFLAGS_EXTRA="$CFLAGS_EXTRA -Werror"
+ CFLAGS_EXTRA="$CFLAGS_EXTRA -Werror -Wl,--fatal-warnings"
fi
MAKE=(make -f Makefile.nolibc -j"${nproc}" XARCH="${arch}" CROSS_COMPILE="${cross_compile}" LLVM="${llvm}" O="${build_dir}")
@@ -185,10 +185,6 @@ test_arch() {
exit 1
esac
printf '%-15s' "$arch:"
- if [ "$arch" = "s390" ] && ([ "$llvm" = "1" ] || [ "$test_mode" = "user" ]); then
- echo "Unsupported configuration"
- return
- fi
if [ "$arch" = "m68k" -o "$arch" = "sh4" ] && [ "$llvm" = "1" ]; then
echo "Unsupported configuration"
return
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index f87993def738..d60f10a873bb 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -148,6 +148,14 @@
#define PIDFD_INFO_COREDUMP (1UL << 4)
#endif
+#ifndef PIDFD_INFO_SUPPORTED_MASK
+#define PIDFD_INFO_SUPPORTED_MASK (1UL << 5)
+#endif
+
+#ifndef PIDFD_INFO_COREDUMP_SIGNAL
+#define PIDFD_INFO_COREDUMP_SIGNAL (1UL << 6)
+#endif
+
#ifndef PIDFD_COREDUMPED
#define PIDFD_COREDUMPED (1U << 0) /* Did crash and... */
#endif
@@ -183,8 +191,11 @@ struct pidfd_info {
__u32 fsuid;
__u32 fsgid;
__s32 exit_code;
- __u32 coredump_mask;
- __u32 __spare1;
+ struct {
+ __u32 coredump_mask;
+ __u32 coredump_signal;
+ };
+ __u64 supported_mask;
};
/*
diff --git a/tools/testing/selftests/pidfd/pidfd_info_test.c b/tools/testing/selftests/pidfd/pidfd_info_test.c
index a0eb6e81eaa2..cb5430a2fd75 100644
--- a/tools/testing/selftests/pidfd/pidfd_info_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_info_test.c
@@ -690,4 +690,77 @@ TEST_F(pidfd_info, thread_group_exec_thread)
EXPECT_EQ(close(pidfd_thread), 0);
}
+/*
+ * Test: PIDFD_INFO_SUPPORTED_MASK field
+ *
+ * Verify that when PIDFD_INFO_SUPPORTED_MASK is requested, the kernel
+ * returns the supported_mask field indicating which flags the kernel supports.
+ */
+TEST(supported_mask_field)
+{
+ struct pidfd_info info = {
+ .mask = PIDFD_INFO_SUPPORTED_MASK,
+ };
+ int pidfd;
+ pid_t pid;
+
+ pid = create_child(&pidfd, 0);
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0)
+ pause();
+
+ /* Request supported_mask field */
+ ASSERT_EQ(ioctl(pidfd, PIDFD_GET_INFO, &info), 0);
+
+ /* Verify PIDFD_INFO_SUPPORTED_MASK is set in the reply */
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_SUPPORTED_MASK));
+
+ /* Verify supported_mask contains expected flags */
+ ASSERT_TRUE(!!(info.supported_mask & PIDFD_INFO_PID));
+ ASSERT_TRUE(!!(info.supported_mask & PIDFD_INFO_CREDS));
+ ASSERT_TRUE(!!(info.supported_mask & PIDFD_INFO_CGROUPID));
+ ASSERT_TRUE(!!(info.supported_mask & PIDFD_INFO_EXIT));
+ ASSERT_TRUE(!!(info.supported_mask & PIDFD_INFO_COREDUMP));
+ ASSERT_TRUE(!!(info.supported_mask & PIDFD_INFO_SUPPORTED_MASK));
+ ASSERT_TRUE(!!(info.supported_mask & PIDFD_INFO_COREDUMP_SIGNAL));
+
+ /* Clean up */
+ sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0);
+ sys_waitid(P_PIDFD, pidfd, NULL, WEXITED);
+ close(pidfd);
+}
+
+/*
+ * Test: PIDFD_INFO_SUPPORTED_MASK always available
+ *
+ * Verify that supported_mask is returned even when other fields are requested.
+ */
+TEST(supported_mask_with_other_fields)
+{
+ struct pidfd_info info = {
+ .mask = PIDFD_INFO_CGROUPID | PIDFD_INFO_SUPPORTED_MASK,
+ };
+ int pidfd;
+ pid_t pid;
+
+ pid = create_child(&pidfd, 0);
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0)
+ pause();
+
+ ASSERT_EQ(ioctl(pidfd, PIDFD_GET_INFO, &info), 0);
+
+ /* Both fields should be present */
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_CGROUPID));
+ ASSERT_TRUE(!!(info.mask & PIDFD_INFO_SUPPORTED_MASK));
+ ASSERT_NE(info.supported_mask, 0);
+
+ /* Clean up */
+ sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0);
+ sys_waitid(P_PIDFD, pidfd, NULL, WEXITED);
+ close(pidfd);
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-again.sh b/tools/testing/selftests/rcutorture/bin/kvm-again.sh
index 88ca4e368489..b5239b52cb5d 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-again.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-again.sh
@@ -31,7 +31,7 @@ fi
if ! cp "$oldrun/scenarios" $T/scenarios.oldrun
then
# Later on, can reconstitute this from console.log files.
- echo Prior run batches file does not exist: $oldrun/batches
+ echo Prior run scenarios file does not exist: $oldrun/scenarios
exit 1
fi
@@ -68,7 +68,7 @@ usage () {
echo " --datestamp string"
echo " --dryrun"
echo " --duration minutes | <seconds>s | <hours>h | <days>d"
- echo " --link hard|soft|copy"
+ echo " --link hard|soft|copy|inplace|inplace-force"
echo " --remote"
echo " --rundir /new/res/path"
echo "Command line: $scriptname $args"
@@ -121,7 +121,7 @@ do
shift
;;
--link)
- checkarg --link "hard|soft|copy" "$#" "$2" 'hard\|soft\|copy' '^--'
+ checkarg --link "hard|soft|copy|inplace|inplace-force" "$#" "$2" 'hard\|soft\|copy\|inplace\|inplace-force' '^--'
case "$2" in
copy)
arg_link="cp -R"
@@ -132,6 +132,14 @@ do
soft)
arg_link="cp -Rs"
;;
+ inplace)
+ arg_link="inplace"
+ rundir="$oldrun"
+ ;;
+ inplace-force)
+ arg_link="inplace-force"
+ rundir="$oldrun"
+ ;;
esac
shift
;;
@@ -172,21 +180,37 @@ fi
echo ---- Re-run results directory: $rundir
-# Copy old run directory tree over and adjust.
-mkdir -p "`dirname "$rundir"`"
-if ! $arg_link "$oldrun" "$rundir"
-then
- echo "Cannot copy from $oldrun to $rundir."
- usage
-fi
-rm -f "$rundir"/*/{console.log,console.log.diags,qemu_pid,qemu-pid,qemu-retval,Warnings,kvm-test-1-run.sh.out,kvm-test-1-run-qemu.sh.out,vmlinux} "$rundir"/log
-touch "$rundir/log"
-echo $scriptname $args | tee -a "$rundir/log"
-echo $oldrun > "$rundir/re-run"
-if ! test -d "$rundir/../../bin"
+if test "$oldrun" != "$rundir"
then
- $arg_link "$oldrun/../../bin" "$rundir/../.."
+ # Copy old run directory tree over and adjust.
+ mkdir -p "`dirname "$rundir"`"
+ if ! $arg_link "$oldrun" "$rundir"
+ then
+ echo "Cannot copy from $oldrun to $rundir."
+ usage
+ fi
+ rm -f "$rundir"/*/{console.log,console.log.diags,qemu_pid,qemu-pid,qemu-retval,Warnings,kvm-test-1-run.sh.out,kvm-test-1-run-qemu.sh.out,vmlinux} "$rundir"/log
+ touch "$rundir/log"
+ echo $scriptname $args | tee -a "$rundir/log"
+ echo $oldrun > "$rundir/re-run"
+ if ! test -d "$rundir/../../bin"
+ then
+ $arg_link "$oldrun/../../bin" "$rundir/../.."
+ fi
+else
+ # Check for a run having already happened.
+ find "$rundir" -name console.log -print > $T/oldrun-console.log
+ if test -s $T/oldrun-console.log
+ then
+ echo Run already took place in $rundir
+ if test "$arg_link" = inplace
+ then
+ usage
+ fi
+ fi
fi
+
+# Find runs to be done based on their qemu-cmd files.
for i in $rundir/*/qemu-cmd
do
cp "$i" $T
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-series.sh b/tools/testing/selftests/rcutorture/bin/kvm-series.sh
new file mode 100755
index 000000000000..2ff905a1853b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-series.sh
@@ -0,0 +1,116 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Usage: kvm-series.sh config-list commit-id-list [ kvm.sh parameters ]
+#
+# Tests the specified list of unadorned configs ("TREE01 SRCU-P" but not
+# "CFLIST" or "3*TRACE01") and an indication of a set of commits to test,
+# then runs each commit through the specified list of commits using kvm.sh.
+# The runs are grouped into a -series/config/commit directory tree.
+# Each run defaults to a duration of one minute.
+#
+# Run in top-level Linux source directory. Please note that this is in
+# no way a replacement for "git bisect"!!!
+#
+# This script is intended to replace kvm-check-branches.sh by providing
+# ease of use and faster execution.
+
+T="`mktemp -d ${TMPDIR-/tmp}/kvm-series.sh.XXXXXX`"
+trap 'rm -rf $T' 0
+
+scriptname=$0
+args="$*"
+
+config_list="${1}"
+if test -z "${config_list}"
+then
+ echo "$0: Need a quoted list of --config arguments for first argument."
+ exit 1
+fi
+if test -z "${config_list}" || echo "${config_list}" | grep -q '\*'
+then
+ echo "$0: Repetition ('*') not allowed in config list."
+ exit 1
+fi
+
+commit_list="${2}"
+if test -z "${commit_list}"
+then
+ echo "$0: Need a list of commits (e.g., HEAD^^^..) for second argument."
+ exit 2
+fi
+git log --pretty=format:"%h" "${commit_list}" > $T/commits
+ret=$?
+if test "${ret}" -ne 0
+then
+ echo "$0: Invalid commit list ('${commit_list}')."
+ exit 2
+fi
+sha1_list=`cat $T/commits`
+
+shift
+shift
+
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
+. functions.sh
+
+ret=0
+nfail=0
+nsuccess=0
+faillist=
+successlist=
+cursha1="`git rev-parse --abbrev-ref HEAD`"
+ds="`date +%Y.%m.%d-%H.%M.%S`-series"
+startdate="`date`"
+starttime="`get_starttime`"
+
+echo " --- " $scriptname $args | tee -a $T/log
+echo " --- Results directory: " $ds | tee -a $T/log
+
+for config in ${config_list}
+do
+ sha_n=0
+ for sha in ${sha1_list}
+ do
+ sha1=${sha_n}.${sha} # Enable "sort -k1nr" to list commits in order.
+ echo Starting ${config}/${sha1} at `date` | tee -a $T/log
+ git checkout "${sha}"
+ time tools/testing/selftests/rcutorture/bin/kvm.sh --configs "$config" --datestamp "$ds/${config}/${sha1}" --duration 1 "$@"
+ curret=$?
+ if test "${curret}" -ne 0
+ then
+ nfail=$((nfail+1))
+ faillist="$faillist ${config}/${sha1}(${curret})"
+ else
+ nsuccess=$((nsuccess+1))
+ successlist="$successlist ${config}/${sha1}"
+ # Successful run, so remove large files.
+ rm -f ${RCUTORTURE}/$ds/${config}/${sha1}/{vmlinux,bzImage,System.map,Module.symvers}
+ fi
+ if test "${ret}" -eq 0
+ then
+ ret=${curret}
+ fi
+ sha_n=$((sha_n+1))
+ done
+done
+git checkout "${cursha1}"
+
+echo ${nsuccess} SUCCESSES: | tee -a $T/log
+echo ${successlist} | fmt | tee -a $T/log
+echo | tee -a $T/log
+echo ${nfail} FAILURES: | tee -a $T/log
+echo ${faillist} | fmt | tee -a $T/log
+if test -n "${faillist}"
+then
+ echo | tee -a $T/log
+ echo Failures across commits: | tee -a $T/log
+ echo ${faillist} | tr ' ' '\012' | sed -e 's,^[^/]*/,,' -e 's/([0-9]*)//' |
+ sort | uniq -c | sort -k2n | tee -a $T/log
+fi
+echo Started at $startdate, ended at `date`, duration `get_starttime_duration $starttime`. | tee -a $T/log
+echo Summary: Successes: ${nsuccess} Failures: ${nfail} | tee -a $T/log
+cp $T/log tools/testing/selftests/rcutorture/res/${ds}
+
+exit "${ret}"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 617cba339d28..fff15821c44c 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -199,7 +199,7 @@ do
fi
;;
--kconfig|--kconfigs)
- checkarg --kconfig "(Kconfig options)" $# "$2" '^\(#CHECK#\)\?CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\|"[^"]*"\)\( \+\(#CHECK#\)\?CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\|"[^"]*"\)\)* *$' '^error$'
+ checkarg --kconfig "(Kconfig options)" $# "$2" '^\(#CHECK#\)\?CONFIG_[A-Z0-9_]\+=\([ynm]\|-\?[0-9]\+\|"[^"]*"\)\( \+\(#CHECK#\)\?CONFIG_[A-Z0-9_]\+=\([ynm]\|-\?[0-9]\+\|"[^"]*"\)\)* *$' '^error$'
TORTURE_KCONFIG_ARG="`echo "$TORTURE_KCONFIG_ARG $2" | sed -e 's/^ *//' -e 's/ *$//'`"
shift
;;
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index dc4985064b3a..67caf4276bb0 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -16,3 +16,4 @@ CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_RCU_EXPERT=y
CONFIG_RCU_EQS_DEBUG=y
CONFIG_RCU_LAZY=y
+CONFIG_RCU_DYNTICKS_TORTURE=y
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
index 33baaa9f9997..e7b858cd3736 100644
--- a/tools/testing/selftests/rseq/rseq-s390.h
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -28,8 +28,6 @@ do { \
RSEQ_WRITE_ONCE(*(p), v); \
} while (0)
-#ifdef __s390x__
-
#define LONG_L "lg"
#define LONG_S "stg"
#define LONG_LT_R "ltgr"
@@ -63,43 +61,6 @@ do { \
".quad " __rseq_str(start_ip) ", " __rseq_str(exit_ip) "\n\t" \
".popsection\n\t"
-#elif __s390__
-
-#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \
- start_ip, post_commit_offset, abort_ip) \
- ".pushsection __rseq_cs, \"aw\"\n\t" \
- ".balign 32\n\t" \
- __rseq_str(label) ":\n\t" \
- ".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
- ".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) "\n\t" \
- ".popsection\n\t" \
- ".pushsection __rseq_cs_ptr_array, \"aw\"\n\t" \
- ".long 0x0, " __rseq_str(label) "b\n\t" \
- ".popsection\n\t"
-
-/*
- * Exit points of a rseq critical section consist of all instructions outside
- * of the critical section where a critical section can either branch to or
- * reach through the normal course of its execution. The abort IP and the
- * post-commit IP are already part of the __rseq_cs section and should not be
- * explicitly defined as additional exit points. Knowing all exit points is
- * useful to assist debuggers stepping over the critical section.
- */
-#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip) \
- ".pushsection __rseq_exit_point_array, \"aw\"\n\t" \
- ".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(exit_ip) "\n\t" \
- ".popsection\n\t"
-
-#define LONG_L "l"
-#define LONG_S "st"
-#define LONG_LT_R "ltr"
-#define LONG_CMP "c"
-#define LONG_CMP_R "cr"
-#define LONG_ADDI "ahi"
-#define LONG_ADD_R "ar"
-
-#endif
-
#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip, \
(post_commit_ip - start_ip), abort_ip)
diff --git a/tools/testing/selftests/run_kselftest.sh b/tools/testing/selftests/run_kselftest.sh
index 0443beacf362..d4be97498b32 100755
--- a/tools/testing/selftests/run_kselftest.sh
+++ b/tools/testing/selftests/run_kselftest.sh
@@ -33,6 +33,7 @@ Usage: $0 [OPTIONS]
-c | --collection COLLECTION Run all tests from COLLECTION
-l | --list List the available collection:test entries
-d | --dry-run Don't actually run any tests
+ -f | --no-error-on-fail Don't exit with an error just because tests failed
-n | --netns Run each test in namespace
-h | --help Show this usage info
-o | --override-timeout Number of seconds after which we timeout
@@ -44,6 +45,7 @@ COLLECTIONS=""
TESTS=""
dryrun=""
kselftest_override_timeout=""
+ERROR_ON_FAIL=true
while true; do
case "$1" in
-s | --summary)
@@ -65,6 +67,9 @@ while true; do
-d | --dry-run)
dryrun="echo"
shift ;;
+ -f | --no-error-on-fail)
+ ERROR_ON_FAIL=false
+ shift ;;
-n | --netns)
RUN_IN_NETNS=1
shift ;;
@@ -105,9 +110,18 @@ if [ -n "$TESTS" ]; then
available="$(echo "$valid" | sed -e 's/ /\n/g')"
fi
+kselftest_failures_file="$(mktemp --tmpdir kselftest-failures-XXXXXX)"
+export kselftest_failures_file
+
collections=$(echo "$available" | cut -d: -f1 | sort | uniq)
for collection in $collections ; do
[ -w /dev/kmsg ] && echo "kselftest: Running tests in $collection" >> /dev/kmsg
tests=$(echo "$available" | grep "^$collection:" | cut -d: -f2)
($dryrun cd "$collection" && $dryrun run_many $tests)
done
+
+failures="$(cat "$kselftest_failures_file")"
+rm "$kselftest_failures_file"
+if "$ERROR_ON_FAIL" && [ "$failures" ]; then
+ exit 1
+fi
diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 9d9d6b4c38b0..5fe45f9c5f8f 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -174,6 +174,7 @@ auto-test-targets := \
minimal \
numa \
allowed_cpus \
+ peek_dsq \
prog_run \
reload_loop \
select_cpu_dfl \
diff --git a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c
new file mode 100644
index 000000000000..a3faf5bb49d6
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A BPF program for testing DSQ operations and peek in particular.
+ *
+ * Copyright (c) 2025 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2025 Ryan Newton <ryan.newton@alum.mit.edu>
+ */
+
+#include <scx/common.bpf.h>
+#include <scx/compat.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei); /* Error handling */
+
+#define MAX_SAMPLES 100
+#define MAX_CPUS 512
+#define DSQ_POOL_SIZE 8
+int max_samples = MAX_SAMPLES;
+int max_cpus = MAX_CPUS;
+int dsq_pool_size = DSQ_POOL_SIZE;
+
+/* Global variables to store test results */
+int dsq_peek_result1 = -1;
+long dsq_inserted_pid = -1;
+int insert_test_cpu = -1; /* Set to the cpu that performs the test */
+long dsq_peek_result2 = -1;
+long dsq_peek_result2_pid = -1;
+long dsq_peek_result2_expected = -1;
+int test_dsq_id = 1234; /* Use a simple ID like create_dsq example */
+int real_dsq_id = 1235; /* DSQ for normal operation */
+int enqueue_count = -1;
+int dispatch_count = -1;
+bool debug_ksym_exists;
+
+/* DSQ pool for stress testing */
+int dsq_pool_base_id = 2000;
+int phase1_complete = -1;
+long total_peek_attempts = -1;
+long successful_peeks = -1;
+
+/* BPF map for sharing peek results with userspace */
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, MAX_SAMPLES);
+ __type(key, u32);
+ __type(value, long);
+} peek_results SEC(".maps");
+
+static int get_random_dsq_id(void)
+{
+ u64 time = bpf_ktime_get_ns();
+
+ return dsq_pool_base_id + (time % DSQ_POOL_SIZE);
+}
+
+static void record_peek_result(long pid)
+{
+ u32 slot_key;
+ long *slot_pid_ptr;
+ int ix;
+
+ if (pid <= 0)
+ return;
+
+ /* Find an empty slot or one with the same PID */
+ bpf_for(ix, 0, 10) {
+ slot_key = (pid + ix) % MAX_SAMPLES;
+ slot_pid_ptr = bpf_map_lookup_elem(&peek_results, &slot_key);
+ if (!slot_pid_ptr)
+ continue;
+
+ if (*slot_pid_ptr == -1 || *slot_pid_ptr == pid) {
+ *slot_pid_ptr = pid;
+ break;
+ }
+ }
+}
+
+/* Scan all DSQs in the pool and try to move a task to local */
+static int scan_dsq_pool(void)
+{
+ struct task_struct *task;
+ int moved = 0;
+ int i;
+
+ bpf_for(i, 0, DSQ_POOL_SIZE) {
+ int dsq_id = dsq_pool_base_id + i;
+
+ total_peek_attempts++;
+
+ task = __COMPAT_scx_bpf_dsq_peek(dsq_id);
+ if (task) {
+ successful_peeks++;
+ record_peek_result(task->pid);
+
+ /* Try to move this task to local */
+ if (!moved && scx_bpf_dsq_move_to_local(dsq_id) == 0) {
+ moved = 1;
+ break;
+ }
+ }
+ }
+ return moved;
+}
+
+/* Struct_ops scheduler for testing DSQ peek operations */
+void BPF_STRUCT_OPS(peek_dsq_enqueue, struct task_struct *p, u64 enq_flags)
+{
+ struct task_struct *peek_result;
+ int last_insert_test_cpu, cpu;
+
+ enqueue_count++;
+ cpu = bpf_get_smp_processor_id();
+ last_insert_test_cpu = __sync_val_compare_and_swap(&insert_test_cpu, -1, cpu);
+
+ /* Phase 1: Simple insert-then-peek test (only on first task) */
+ if (last_insert_test_cpu == -1) {
+ bpf_printk("peek_dsq_enqueue beginning phase 1 peek test on cpu %d", cpu);
+
+ /* Test 1: Peek empty DSQ - should return NULL */
+ peek_result = __COMPAT_scx_bpf_dsq_peek(test_dsq_id);
+ dsq_peek_result1 = (long)peek_result; /* Should be 0 (NULL) */
+
+ /* Test 2: Insert task into test DSQ for testing in dispatch callback */
+ dsq_inserted_pid = p->pid;
+ scx_bpf_dsq_insert(p, test_dsq_id, 0, enq_flags);
+ dsq_peek_result2_expected = (long)p; /* Expected the task we just inserted */
+ } else if (!phase1_complete) {
+ /* Still in phase 1, use real DSQ */
+ scx_bpf_dsq_insert(p, real_dsq_id, 0, enq_flags);
+ } else {
+ /* Phase 2: Random DSQ insertion for stress testing */
+ int random_dsq_id = get_random_dsq_id();
+
+ scx_bpf_dsq_insert(p, random_dsq_id, 0, enq_flags);
+ }
+}
+
+void BPF_STRUCT_OPS(peek_dsq_dispatch, s32 cpu, struct task_struct *prev)
+{
+ dispatch_count++;
+
+ /* Phase 1: Complete the simple peek test if we inserted a task but
+ * haven't tested peek yet
+ */
+ if (insert_test_cpu == cpu && dsq_peek_result2 == -1) {
+ struct task_struct *peek_result;
+
+ bpf_printk("peek_dsq_dispatch completing phase 1 peek test on cpu %d", cpu);
+
+ /* Test 3: Peek DSQ after insert - should return the task we inserted */
+ peek_result = __COMPAT_scx_bpf_dsq_peek(test_dsq_id);
+ /* Store the PID of the peeked task for comparison */
+ dsq_peek_result2 = (long)peek_result;
+ dsq_peek_result2_pid = peek_result ? peek_result->pid : -1;
+
+ /* Now consume the task since we've peeked at it */
+ scx_bpf_dsq_move_to_local(test_dsq_id);
+
+ /* Mark phase 1 as complete */
+ phase1_complete = 1;
+ bpf_printk("Phase 1 complete, starting phase 2 stress testing");
+ } else if (!phase1_complete) {
+ /* Still in phase 1, use real DSQ */
+ scx_bpf_dsq_move_to_local(real_dsq_id);
+ } else {
+ /* Phase 2: Scan all DSQs in the pool and try to move a task */
+ if (!scan_dsq_pool()) {
+ /* No tasks found in DSQ pool, fall back to real DSQ */
+ scx_bpf_dsq_move_to_local(real_dsq_id);
+ }
+ }
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(peek_dsq_init)
+{
+ s32 err;
+ int i;
+
+ /* Always set debug values so we can see which version we're using */
+ debug_ksym_exists = bpf_ksym_exists(scx_bpf_dsq_peek) ? 1 : 0;
+
+ /* Initialize state first */
+ insert_test_cpu = -1;
+ enqueue_count = 0;
+ dispatch_count = 0;
+ phase1_complete = 0;
+ total_peek_attempts = 0;
+ successful_peeks = 0;
+
+ /* Create the test and real DSQs */
+ err = scx_bpf_create_dsq(test_dsq_id, -1);
+ if (err) {
+ scx_bpf_error("Failed to create DSQ %d: %d", test_dsq_id, err);
+ return err;
+ }
+ err = scx_bpf_create_dsq(real_dsq_id, -1);
+ if (err) {
+ scx_bpf_error("Failed to create DSQ %d: %d", test_dsq_id, err);
+ return err;
+ }
+
+ /* Create the DSQ pool for stress testing */
+ bpf_for(i, 0, DSQ_POOL_SIZE) {
+ int dsq_id = dsq_pool_base_id + i;
+
+ err = scx_bpf_create_dsq(dsq_id, -1);
+ if (err) {
+ scx_bpf_error("Failed to create DSQ pool entry %d: %d", dsq_id, err);
+ return err;
+ }
+ }
+
+ /* Initialize the peek results map */
+ bpf_for(i, 0, MAX_SAMPLES) {
+ u32 key = i;
+ long pid = -1;
+
+ bpf_map_update_elem(&peek_results, &key, &pid, BPF_ANY);
+ }
+
+ return 0;
+}
+
+void BPF_STRUCT_OPS(peek_dsq_exit, struct scx_exit_info *ei)
+{
+ int i;
+
+ /* Destroy the primary DSQs */
+ scx_bpf_destroy_dsq(test_dsq_id);
+ scx_bpf_destroy_dsq(real_dsq_id);
+
+ /* Destroy the DSQ pool */
+ bpf_for(i, 0, DSQ_POOL_SIZE) {
+ int dsq_id = dsq_pool_base_id + i;
+
+ scx_bpf_destroy_dsq(dsq_id);
+ }
+
+ UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops peek_dsq_ops = {
+ .enqueue = (void *)peek_dsq_enqueue,
+ .dispatch = (void *)peek_dsq_dispatch,
+ .init = (void *)peek_dsq_init,
+ .exit = (void *)peek_dsq_exit,
+ .name = "peek_dsq",
+};
diff --git a/tools/testing/selftests/sched_ext/peek_dsq.c b/tools/testing/selftests/sched_ext/peek_dsq.c
new file mode 100644
index 000000000000..a717384a3224
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/peek_dsq.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for DSQ operations including create, destroy, and peek operations.
+ *
+ * Copyright (c) 2025 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2025 Ryan Newton <ryan.newton@alum.mit.edu>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <pthread.h>
+#include <string.h>
+#include <sched.h>
+#include "peek_dsq.bpf.skel.h"
+#include "scx_test.h"
+
+#define NUM_WORKERS 4
+
+static bool workload_running = true;
+static pthread_t workload_threads[NUM_WORKERS];
+
+/**
+ * Background workload thread that sleeps and wakes rapidly to exercise
+ * the scheduler's enqueue operations and ensure DSQ operations get tested.
+ */
+static void *workload_thread_fn(void *arg)
+{
+ while (workload_running) {
+ /* Sleep for a very short time to trigger scheduler activity */
+ usleep(1000); /* 1ms sleep */
+ /* Yield to ensure we go through the scheduler */
+ sched_yield();
+ }
+ return NULL;
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+ struct peek_dsq *skel;
+
+ skel = peek_dsq__open();
+ SCX_FAIL_IF(!skel, "Failed to open");
+ SCX_ENUM_INIT(skel);
+ SCX_FAIL_IF(peek_dsq__load(skel), "Failed to load skel");
+
+ *ctx = skel;
+
+ return SCX_TEST_PASS;
+}
+
+static int print_observed_pids(struct bpf_map *map, int max_samples, const char *dsq_name)
+{
+ long count = 0;
+
+ printf("Observed %s DSQ peek pids:\n", dsq_name);
+ for (int i = 0; i < max_samples; i++) {
+ long pid;
+ int err;
+
+ err = bpf_map_lookup_elem(bpf_map__fd(map), &i, &pid);
+ if (err == 0) {
+ if (pid == 0) {
+ printf(" Sample %d: NULL peek\n", i);
+ } else if (pid > 0) {
+ printf(" Sample %d: pid %ld\n", i, pid);
+ count++;
+ }
+ } else {
+ printf(" Sample %d: error reading pid (err=%d)\n", i, err);
+ }
+ }
+ printf("Observed ~%ld pids in the %s DSQ(s)\n", count, dsq_name);
+ return count;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+ struct peek_dsq *skel = ctx;
+ bool failed = false;
+ int seconds = 3;
+ int err;
+
+ /* Enable the scheduler to test DSQ operations */
+ printf("Enabling scheduler to test DSQ insert operations...\n");
+
+ struct bpf_link *link =
+ bpf_map__attach_struct_ops(skel->maps.peek_dsq_ops);
+
+ if (!link) {
+ SCX_ERR("Failed to attach struct_ops");
+ return SCX_TEST_FAIL;
+ }
+
+ printf("Starting %d background workload threads...\n", NUM_WORKERS);
+ workload_running = true;
+ for (int i = 0; i < NUM_WORKERS; i++) {
+ err = pthread_create(&workload_threads[i], NULL, workload_thread_fn, NULL);
+ if (err) {
+ SCX_ERR("Failed to create workload thread %d: %s", i, strerror(err));
+ /* Stop already created threads */
+ workload_running = false;
+ for (int j = 0; j < i; j++)
+ pthread_join(workload_threads[j], NULL);
+ bpf_link__destroy(link);
+ return SCX_TEST_FAIL;
+ }
+ }
+
+ printf("Waiting for enqueue events.\n");
+ sleep(seconds);
+ while (skel->data->enqueue_count <= 0) {
+ printf(".");
+ fflush(stdout);
+ sleep(1);
+ seconds++;
+ if (seconds >= 30) {
+ printf("\n\u2717 Timeout waiting for enqueue events\n");
+ /* Stop workload threads and cleanup */
+ workload_running = false;
+ for (int i = 0; i < NUM_WORKERS; i++)
+ pthread_join(workload_threads[i], NULL);
+ bpf_link__destroy(link);
+ return SCX_TEST_FAIL;
+ }
+ }
+
+ workload_running = false;
+ for (int i = 0; i < NUM_WORKERS; i++) {
+ err = pthread_join(workload_threads[i], NULL);
+ if (err) {
+ SCX_ERR("Failed to join workload thread %d: %s", i, strerror(err));
+ bpf_link__destroy(link);
+ return SCX_TEST_FAIL;
+ }
+ }
+ printf("Background workload threads stopped.\n");
+
+ SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE));
+
+ /* Detach the scheduler */
+ bpf_link__destroy(link);
+
+ printf("Enqueue/dispatch count over %d seconds: %d / %d\n", seconds,
+ skel->data->enqueue_count, skel->data->dispatch_count);
+ printf("Debug: ksym_exists=%d\n",
+ skel->bss->debug_ksym_exists);
+
+ /* Check DSQ insert result */
+ printf("DSQ insert test done on cpu: %d\n", skel->data->insert_test_cpu);
+ if (skel->data->insert_test_cpu != -1)
+ printf("\u2713 DSQ insert succeeded !\n");
+ else {
+ printf("\u2717 DSQ insert failed or not attempted\n");
+ failed = true;
+ }
+
+ /* Check DSQ peek results */
+ printf(" DSQ peek result 1 (before insert): %d\n",
+ skel->data->dsq_peek_result1);
+ if (skel->data->dsq_peek_result1 == 0)
+ printf("\u2713 DSQ peek verification success: peek returned NULL!\n");
+ else {
+ printf("\u2717 DSQ peek verification failed\n");
+ failed = true;
+ }
+
+ printf(" DSQ peek result 2 (after insert): %ld\n",
+ skel->data->dsq_peek_result2);
+ printf(" DSQ peek result 2, expected: %ld\n",
+ skel->data->dsq_peek_result2_expected);
+ if (skel->data->dsq_peek_result2 ==
+ skel->data->dsq_peek_result2_expected)
+ printf("\u2713 DSQ peek verification success: peek returned the inserted task!\n");
+ else {
+ printf("\u2717 DSQ peek verification failed\n");
+ failed = true;
+ }
+
+ printf(" Inserted test task -> pid: %ld\n", skel->data->dsq_inserted_pid);
+ printf(" DSQ peek result 2 -> pid: %ld\n", skel->data->dsq_peek_result2_pid);
+
+ int pid_count;
+
+ pid_count = print_observed_pids(skel->maps.peek_results,
+ skel->data->max_samples, "DSQ pool");
+ printf("Total non-null peek observations: %ld out of %ld\n",
+ skel->data->successful_peeks, skel->data->total_peek_attempts);
+
+ if (skel->bss->debug_ksym_exists && pid_count == 0) {
+ printf("\u2717 DSQ pool test failed: no successful peeks in native mode\n");
+ failed = true;
+ }
+ if (skel->bss->debug_ksym_exists && pid_count > 0)
+ printf("\u2713 DSQ pool test success: observed successful peeks in native mode\n");
+
+ if (failed)
+ return SCX_TEST_FAIL;
+ else
+ return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+ struct peek_dsq *skel = ctx;
+
+ if (workload_running) {
+ workload_running = false;
+ for (int i = 0; i < NUM_WORKERS; i++)
+ pthread_join(workload_threads[i], NULL);
+ }
+
+ peek_dsq__destroy(skel);
+}
+
+struct scx_test peek_dsq = {
+ .name = "peek_dsq",
+ .description =
+ "Test DSQ create/destroy operations and future peek functionality",
+ .setup = setup,
+ .run = run,
+ .cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&peek_dsq)
diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c
index 252c6308c569..10badae13ebe 100644
--- a/tools/testing/selftests/timers/nanosleep.c
+++ b/tools/testing/selftests/timers/nanosleep.c
@@ -116,6 +116,56 @@ int nanosleep_test(int clockid, long long ns)
return 0;
}
+static void dummy_event_handler(int val)
+{
+ /* No action needed */
+}
+
+static int nanosleep_test_remaining(int clockid)
+{
+ struct timespec rqtp = {}, rmtp = {};
+ struct itimerspec itimer = {};
+ struct sigaction sa = {};
+ timer_t timer;
+ int ret;
+
+ sa.sa_handler = dummy_event_handler;
+ ret = sigaction(SIGALRM, &sa, NULL);
+ if (ret)
+ return -1;
+
+ ret = timer_create(clockid, NULL, &timer);
+ if (ret)
+ return -1;
+
+ itimer.it_value.tv_nsec = NSEC_PER_SEC / 4;
+ ret = timer_settime(timer, 0, &itimer, NULL);
+ if (ret)
+ return -1;
+
+ rqtp.tv_nsec = NSEC_PER_SEC / 2;
+ ret = clock_nanosleep(clockid, 0, &rqtp, &rmtp);
+ if (ret != EINTR)
+ return -1;
+
+ ret = timer_delete(timer);
+ if (ret)
+ return -1;
+
+ sa.sa_handler = SIG_DFL;
+ ret = sigaction(SIGALRM, &sa, NULL);
+ if (ret)
+ return -1;
+
+ if (!in_order((struct timespec) {}, rmtp))
+ return -1;
+
+ if (!in_order(rmtp, rqtp))
+ return -1;
+
+ return 0;
+}
+
int main(int argc, char **argv)
{
long long length;
@@ -150,6 +200,11 @@ int main(int argc, char **argv)
}
length *= 100;
}
+ ret = nanosleep_test_remaining(clockid);
+ if (ret < 0) {
+ ksft_test_result_fail("%-31s\n", clockstring(clockid));
+ ksft_exit_fail();
+ }
ksft_test_result_pass("%-31s\n", clockstring(clockid));
next:
ret = 0;
diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c
index f0eceb0faf34..a563c438ac79 100644
--- a/tools/testing/selftests/timers/posix_timers.c
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -18,6 +18,7 @@
#include <time.h>
#include <include/vdso/time64.h>
#include <pthread.h>
+#include <stdbool.h>
#include "../kselftest.h"
@@ -670,8 +671,14 @@ static void check_timer_create_exact(void)
int main(int argc, char **argv)
{
+ bool run_sig_ign_tests = ksft_min_kernel_version(6, 13);
+
ksft_print_header();
- ksft_set_plan(19);
+ if (run_sig_ign_tests) {
+ ksft_set_plan(19);
+ } else {
+ ksft_set_plan(10);
+ }
ksft_print_msg("Testing posix timers. False negative may happen on CPU execution \n");
ksft_print_msg("based timers if other threads run on the CPU...\n");
@@ -695,15 +702,20 @@ int main(int argc, char **argv)
check_timer_create(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID");
check_timer_distribution();
- check_sig_ign(0);
- check_sig_ign(1);
- check_rearm();
- check_delete();
- check_sigev_none(CLOCK_MONOTONIC, "CLOCK_MONOTONIC");
- check_sigev_none(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID");
- check_gettime(CLOCK_MONOTONIC, "CLOCK_MONOTONIC");
- check_gettime(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID");
- check_gettime(CLOCK_THREAD_CPUTIME_ID, "CLOCK_THREAD_CPUTIME_ID");
+ if (run_sig_ign_tests) {
+ check_sig_ign(0);
+ check_sig_ign(1);
+ check_rearm();
+ check_delete();
+ check_sigev_none(CLOCK_MONOTONIC, "CLOCK_MONOTONIC");
+ check_sigev_none(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID");
+ check_gettime(CLOCK_MONOTONIC, "CLOCK_MONOTONIC");
+ check_gettime(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID");
+ check_gettime(CLOCK_THREAD_CPUTIME_ID, "CLOCK_THREAD_CPUTIME_ID");
+ } else {
+ ksft_print_msg("Skipping SIG_IGN tests on kernel < 6.13\n");
+ }
+
check_overrun(CLOCK_MONOTONIC, "CLOCK_MONOTONIC");
check_overrun(CLOCK_PROCESS_CPUTIME_ID, "CLOCK_PROCESS_CPUTIME_ID");
check_overrun(CLOCK_THREAD_CPUTIME_ID, "CLOCK_THREAD_CPUTIME_ID");
diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c
index 5288e768b207..68625362add2 100644
--- a/tools/testing/selftests/user_events/perf_test.c
+++ b/tools/testing/selftests/user_events/perf_test.c
@@ -236,7 +236,7 @@ TEST_F(user, perf_empty_events) {
ASSERT_EQ(1 << reg.enable_bit, self->check);
/* Ensure write shows up at correct offset */
- ASSERT_NE(-1, write(self->data_fd, &reg.write_index,
+ ASSERT_NE(-1, write(self->data_fd, (void *)&reg.write_index,
sizeof(reg.write_index)));
val = (void *)(((char *)perf_page) + perf_page->data_offset);
ASSERT_EQ(PERF_RECORD_SAMPLE, *val);
diff --git a/tools/testing/selftests/vDSO/vdso_config.h b/tools/testing/selftests/vDSO/vdso_config.h
index 5fdd0f362337..50c261005111 100644
--- a/tools/testing/selftests/vDSO/vdso_config.h
+++ b/tools/testing/selftests/vDSO/vdso_config.h
@@ -25,10 +25,6 @@
#define VDSO_VERSION 1
#define VDSO_NAMES 0
#define VDSO_32BIT 1
-#elif defined (__s390__) && !defined(__s390x__)
-#define VDSO_VERSION 2
-#define VDSO_NAMES 0
-#define VDSO_32BIT 1
#elif defined (__s390x__)
#define VDSO_VERSION 2
#define VDSO_NAMES 0
diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c
index 05e1e6774fba..918eaec8bfbe 100644
--- a/tools/testing/selftests/x86/test_vsyscall.c
+++ b/tools/testing/selftests/x86/test_vsyscall.c
@@ -308,12 +308,13 @@ static void test_getcpu(int cpu)
#ifdef __x86_64__
static jmp_buf jmpbuf;
-static volatile unsigned long segv_err;
+static volatile unsigned long segv_err, segv_trapno;
static void sigsegv(int sig, siginfo_t *info, void *ctx_void)
{
ucontext_t *ctx = (ucontext_t *)ctx_void;
+ segv_trapno = ctx->uc_mcontext.gregs[REG_TRAPNO];
segv_err = ctx->uc_mcontext.gregs[REG_ERR];
siglongjmp(jmpbuf, 1);
}
@@ -336,7 +337,8 @@ static void test_vsys_r(void)
else if (can_read)
ksft_test_result_pass("We have read access\n");
else
- ksft_test_result_pass("We do not have read access: #PF(0x%lx)\n", segv_err);
+ ksft_test_result_pass("We do not have read access (trap=%ld, error=0x%lx)\n",
+ segv_trapno, segv_err);
}
static void test_vsys_x(void)
@@ -347,7 +349,7 @@ static void test_vsys_x(void)
return;
}
- ksft_print_msg("Make sure that vsyscalls really page fault\n");
+ ksft_print_msg("Make sure that vsyscalls really cause a fault\n");
bool can_exec;
if (sigsetjmp(jmpbuf, 1) == 0) {
@@ -358,13 +360,14 @@ static void test_vsys_x(void)
}
if (can_exec)
- ksft_test_result_fail("Executing the vsyscall did not page fault\n");
- else if (segv_err & (1 << 4)) /* INSTR */
- ksft_test_result_pass("Executing the vsyscall page failed: #PF(0x%lx)\n",
- segv_err);
+ ksft_test_result_fail("Executing the vsyscall did not fault\n");
+ /* #GP or #PF (with X86_PF_INSTR) */
+ else if ((segv_trapno == 13) || ((segv_trapno == 14) && (segv_err & (1 << 4))))
+ ksft_test_result_pass("Executing the vsyscall page failed (trap=%ld, error=0x%lx)\n",
+ segv_trapno, segv_err);
else
- ksft_test_result_fail("Execution failed with the wrong error: #PF(0x%lx)\n",
- segv_err);
+ ksft_test_result_fail("Execution failed with the wrong error (trap=%ld, error=0x%lx)\n",
+ segv_trapno, segv_err);
}
/*