summaryrefslogtreecommitdiff
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rw-r--r--tools/testing/selftests/Makefile1
-rw-r--r--tools/testing/selftests/dma/dma_map_benchmark.c21
-rw-r--r--tools/testing/selftests/kvm/.gitignore1
-rw-r--r--tools/testing/selftests/kvm/Makefile1
-rw-r--r--tools/testing/selftests/kvm/hardware_disable_test.c165
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c6
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c3
-rw-r--r--tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c159
-rw-r--r--tools/testing/selftests/mount_setattr/.gitignore1
-rw-r--r--tools/testing/selftests/mount_setattr/Makefile7
-rw-r--r--tools/testing/selftests/mount_setattr/config1
-rw-r--r--tools/testing/selftests/mount_setattr/mount_setattr_test.c1424
-rwxr-xr-xtools/testing/selftests/wireguard/netns.sh15
13 files changed, 1795 insertions, 10 deletions
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 41f0a0adbb80..6c575cf34a71 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -33,6 +33,7 @@ TARGETS += memfd
TARGETS += memory-hotplug
TARGETS += mincore
TARGETS += mount
+TARGETS += mount_setattr
TARGETS += mqueue
TARGETS += nci
TARGETS += net
diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c
index 537d65968c48..fb23ce9617ea 100644
--- a/tools/testing/selftests/dma/dma_map_benchmark.c
+++ b/tools/testing/selftests/dma/dma_map_benchmark.c
@@ -12,9 +12,12 @@
#include <sys/mman.h>
#include <linux/types.h>
+#define NSEC_PER_MSEC 1000000L
+
#define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark)
#define DMA_MAP_MAX_THREADS 1024
#define DMA_MAP_MAX_SECONDS 300
+#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC)
#define DMA_MAP_BIDIRECTIONAL 0
#define DMA_MAP_TO_DEVICE 1
@@ -36,7 +39,8 @@ struct map_benchmark {
__s32 node; /* which numa node this benchmark will run on */
__u32 dma_bits; /* DMA addressing capability */
__u32 dma_dir; /* DMA data direction */
- __u8 expansion[84]; /* For future use */
+ __u32 dma_trans_ns; /* time for DMA transmission in ns */
+ __u8 expansion[80]; /* For future use */
};
int main(int argc, char **argv)
@@ -46,12 +50,12 @@ int main(int argc, char **argv)
/* default single thread, run 20 seconds on NUMA_NO_NODE */
int threads = 1, seconds = 20, node = -1;
/* default dma mask 32bit, bidirectional DMA */
- int bits = 32, dir = DMA_MAP_BIDIRECTIONAL;
+ int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL;
int cmd = DMA_MAP_BENCHMARK;
char *p;
- while ((opt = getopt(argc, argv, "t:s:n:b:d:")) != -1) {
+ while ((opt = getopt(argc, argv, "t:s:n:b:d:x:")) != -1) {
switch (opt) {
case 't':
threads = atoi(optarg);
@@ -68,6 +72,9 @@ int main(int argc, char **argv)
case 'd':
dir = atoi(optarg);
break;
+ case 'x':
+ xdelay = atoi(optarg);
+ break;
default:
return -1;
}
@@ -85,6 +92,12 @@ int main(int argc, char **argv)
exit(1);
}
+ if (xdelay < 0 || xdelay > DMA_MAP_MAX_TRANS_DELAY) {
+ fprintf(stderr, "invalid transmit delay, must be in 0-%ld\n",
+ DMA_MAP_MAX_TRANS_DELAY);
+ exit(1);
+ }
+
/* suppose the mininum DMA zone is 1MB in the world */
if (bits < 20 || bits > 64) {
fprintf(stderr, "invalid dma mask bit, must be in 20-64\n");
@@ -109,6 +122,8 @@ int main(int argc, char **argv)
map.node = node;
map.dma_bits = bits;
map.dma_dir = dir;
+ map.dma_trans_ns = xdelay;
+
if (ioctl(fd, cmd, &map)) {
perror("ioctl");
exit(1);
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 3a84394829ea..32b87cc77c8e 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -33,6 +33,7 @@
/demand_paging_test
/dirty_log_test
/dirty_log_perf_test
+/hardware_disable_test
/kvm_create_max_vcpus
/memslot_modification_stress_test
/set_memory_region_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 8c8eda429576..a6d61f451f88 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -67,6 +67,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
TEST_GEN_PROGS_x86_64 += demand_paging_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
+TEST_GEN_PROGS_x86_64 += hardware_disable_test
TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test
TEST_GEN_PROGS_x86_64 += set_memory_region_test
diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c
new file mode 100644
index 000000000000..2f2eeb8a1d86
--- /dev/null
+++ b/tools/testing/selftests/kvm/hardware_disable_test.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This test is intended to reproduce a crash that happens when
+ * kvm_arch_hardware_disable is called and it attempts to unregister the user
+ * return notifiers.
+ */
+
+#define _GNU_SOURCE
+
+#include <fcntl.h>
+#include <pthread.h>
+#include <semaphore.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/wait.h>
+
+#include <test_util.h>
+
+#include "kvm_util.h"
+
+#define VCPU_NUM 4
+#define SLEEPING_THREAD_NUM (1 << 4)
+#define FORK_NUM (1ULL << 9)
+#define DELAY_US_MAX 2000
+#define GUEST_CODE_PIO_PORT 4
+
+sem_t *sem;
+
+/* Arguments for the pthreads */
+struct payload {
+ struct kvm_vm *vm;
+ uint32_t index;
+};
+
+static void guest_code(void)
+{
+ for (;;)
+ ; /* Some busy work */
+ printf("Should not be reached.\n");
+}
+
+static void *run_vcpu(void *arg)
+{
+ struct payload *payload = (struct payload *)arg;
+ struct kvm_run *state = vcpu_state(payload->vm, payload->index);
+
+ vcpu_run(payload->vm, payload->index);
+
+ TEST_ASSERT(false, "%s: exited with reason %d: %s\n",
+ __func__, state->exit_reason,
+ exit_reason_str(state->exit_reason));
+ pthread_exit(NULL);
+}
+
+static void *sleeping_thread(void *arg)
+{
+ int fd;
+
+ while (true) {
+ fd = open("/dev/null", O_RDWR);
+ close(fd);
+ }
+ TEST_ASSERT(false, "%s: exited\n", __func__);
+ pthread_exit(NULL);
+}
+
+static inline void check_create_thread(pthread_t *thread, pthread_attr_t *attr,
+ void *(*f)(void *), void *arg)
+{
+ int r;
+
+ r = pthread_create(thread, attr, f, arg);
+ TEST_ASSERT(r == 0, "%s: failed to create thread", __func__);
+}
+
+static inline void check_set_affinity(pthread_t thread, cpu_set_t *cpu_set)
+{
+ int r;
+
+ r = pthread_setaffinity_np(thread, sizeof(cpu_set_t), cpu_set);
+ TEST_ASSERT(r == 0, "%s: failed set affinity", __func__);
+}
+
+static inline void check_join(pthread_t thread, void **retval)
+{
+ int r;
+
+ r = pthread_join(thread, retval);
+ TEST_ASSERT(r == 0, "%s: failed to join thread", __func__);
+}
+
+static void run_test(uint32_t run)
+{
+ struct kvm_vm *vm;
+ cpu_set_t cpu_set;
+ pthread_t threads[VCPU_NUM];
+ pthread_t throw_away;
+ struct payload payloads[VCPU_NUM];
+ void *b;
+ uint32_t i, j;
+
+ CPU_ZERO(&cpu_set);
+ for (i = 0; i < VCPU_NUM; i++)
+ CPU_SET(i, &cpu_set);
+
+ vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+ kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+ vm_create_irqchip(vm);
+
+ fprintf(stderr, "%s: [%d] start vcpus\n", __func__, run);
+ for (i = 0; i < VCPU_NUM; ++i) {
+ vm_vcpu_add_default(vm, i, guest_code);
+ payloads[i].vm = vm;
+ payloads[i].index = i;
+
+ check_create_thread(&threads[i], NULL, run_vcpu,
+ (void *)&payloads[i]);
+ check_set_affinity(threads[i], &cpu_set);
+
+ for (j = 0; j < SLEEPING_THREAD_NUM; ++j) {
+ check_create_thread(&throw_away, NULL, sleeping_thread,
+ (void *)NULL);
+ check_set_affinity(throw_away, &cpu_set);
+ }
+ }
+ fprintf(stderr, "%s: [%d] all threads launched\n", __func__, run);
+ sem_post(sem);
+ for (i = 0; i < VCPU_NUM; ++i)
+ check_join(threads[i], &b);
+ /* Should not be reached */
+ TEST_ASSERT(false, "%s: [%d] child escaped the ninja\n", __func__, run);
+}
+
+int main(int argc, char **argv)
+{
+ uint32_t i;
+ int s, r;
+ pid_t pid;
+
+ sem = sem_open("vm_sem", O_CREAT | O_EXCL, 0644, 0);
+ sem_unlink("vm_sem");
+
+ for (i = 0; i < FORK_NUM; ++i) {
+ pid = fork();
+ TEST_ASSERT(pid >= 0, "%s: unable to fork", __func__);
+ if (pid == 0)
+ run_test(i); /* This function always exits */
+
+ fprintf(stderr, "%s: [%d] waiting semaphore\n", __func__, i);
+ sem_wait(sem);
+ r = (rand() % DELAY_US_MAX) + 1;
+ fprintf(stderr, "%s: [%d] waiting %dus\n", __func__, i, r);
+ usleep(r);
+ r = waitpid(pid, &s, WNOHANG);
+ TEST_ASSERT(r != pid,
+ "%s: [%d] child exited unexpectedly status: [%d]",
+ __func__, i, s);
+ fprintf(stderr, "%s: [%d] killing child\n", __func__, i);
+ kill(pid, SIGKILL);
+ }
+
+ sem_destroy(sem);
+ exit(0);
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index d787cb802b4a..e5fbf16f725b 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -21,6 +21,8 @@
#define KVM_UTIL_PGS_PER_HUGEPG 512
#define KVM_UTIL_MIN_PFN 2
+static int vcpu_mmap_sz(void);
+
/* Aligns x up to the next multiple of size. Size must be a power of 2. */
static void *align(void *x, size_t size)
{
@@ -509,7 +511,7 @@ static void vm_vcpu_rm(struct kvm_vm *vm, struct vcpu *vcpu)
vcpu->dirty_gfns = NULL;
}
- ret = munmap(vcpu->state, sizeof(*vcpu->state));
+ ret = munmap(vcpu->state, vcpu_mmap_sz());
TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i "
"errno: %i", ret, errno);
close(vcpu->fd);
@@ -978,7 +980,7 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid)
TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->state), "vcpu mmap size "
"smaller than expected, vcpu_mmap_sz: %i expected_min: %zi",
vcpu_mmap_sz(), sizeof(*vcpu->state));
- vcpu->state = (struct kvm_run *) mmap(NULL, sizeof(*vcpu->state),
+ vcpu->state = (struct kvm_run *) mmap(NULL, vcpu_mmap_sz(),
PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, 0);
TEST_ASSERT(vcpu->state != MAP_FAILED, "mmap vcpu_state failed, "
"vcpu id: %u errno: %i", vcpuid, errno);
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index de0c76177d02..a8906e60a108 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -720,7 +720,8 @@ struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
struct kvm_cpuid2 *cpuid;
- int rc, max_ent;
+ int max_ent;
+ int rc = -1;
TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 9246ea310587..804ff5ff022d 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -13,19 +13,27 @@
#include <stdint.h>
#include <time.h>
+#include <sched.h>
+#include <sys/syscall.h>
#define VCPU_ID 5
+#define SHINFO_REGION_GVA 0xc0000000ULL
#define SHINFO_REGION_GPA 0xc0000000ULL
#define SHINFO_REGION_SLOT 10
#define PAGE_SIZE 4096
#define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE)
+#define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20)
+
+#define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20)
static struct kvm_vm *vm;
#define XEN_HYPERCALL_MSR 0x40000000
+#define MIN_STEAL_TIME 50000
+
struct pvclock_vcpu_time_info {
u32 version;
u32 pad0;
@@ -43,11 +51,67 @@ struct pvclock_wall_clock {
u32 nsec;
} __attribute__((__packed__));
+struct vcpu_runstate_info {
+ uint32_t state;
+ uint64_t state_entry_time;
+ uint64_t time[4];
+};
+
+#define RUNSTATE_running 0
+#define RUNSTATE_runnable 1
+#define RUNSTATE_blocked 2
+#define RUNSTATE_offline 3
+
static void guest_code(void)
{
+ struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
+
+ /* Test having the host set runstates manually */
+ GUEST_SYNC(RUNSTATE_runnable);
+ GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0);
+ GUEST_ASSERT(rs->state == 0);
+
+ GUEST_SYNC(RUNSTATE_blocked);
+ GUEST_ASSERT(rs->time[RUNSTATE_blocked] != 0);
+ GUEST_ASSERT(rs->state == 0);
+
+ GUEST_SYNC(RUNSTATE_offline);
+ GUEST_ASSERT(rs->time[RUNSTATE_offline] != 0);
+ GUEST_ASSERT(rs->state == 0);
+
+ /* Test runstate time adjust */
+ GUEST_SYNC(4);
+ GUEST_ASSERT(rs->time[RUNSTATE_blocked] == 0x5a);
+ GUEST_ASSERT(rs->time[RUNSTATE_offline] == 0x6b6b);
+
+ /* Test runstate time set */
+ GUEST_SYNC(5);
+ GUEST_ASSERT(rs->state_entry_time >= 0x8000);
+ GUEST_ASSERT(rs->time[RUNSTATE_runnable] == 0);
+ GUEST_ASSERT(rs->time[RUNSTATE_blocked] == 0x6b6b);
+ GUEST_ASSERT(rs->time[RUNSTATE_offline] == 0x5a);
+
+ /* sched_yield() should result in some 'runnable' time */
+ GUEST_SYNC(6);
+ GUEST_ASSERT(rs->time[RUNSTATE_runnable] >= MIN_STEAL_TIME);
+
GUEST_DONE();
}
+static long get_run_delay(void)
+{
+ char path[64];
+ long val[2];
+ FILE *fp;
+
+ sprintf(path, "/proc/%ld/schedstat", syscall(SYS_gettid));
+ fp = fopen(path, "r");
+ fscanf(fp, "%ld %ld ", &val[0], &val[1]);
+ fclose(fp);
+
+ return val[1];
+}
+
static int cmp_timespec(struct timespec *a, struct timespec *b)
{
if (a->tv_sec > b->tv_sec)
@@ -66,12 +130,14 @@ int main(int argc, char *argv[])
{
struct timespec min_ts, max_ts, vm_ts;
- if (!(kvm_check_cap(KVM_CAP_XEN_HVM) &
- KVM_XEN_HVM_CONFIG_SHARED_INFO) ) {
+ int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM);
+ if (!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO) ) {
print_skip("KVM_XEN_HVM_CONFIG_SHARED_INFO not available");
exit(KSFT_SKIP);
}
+ bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE);
+
clock_gettime(CLOCK_REALTIME, &min_ts);
vm = vm_create_default(VCPU_ID, 0, (void *) guest_code);
@@ -80,6 +146,7 @@ int main(int argc, char *argv[])
/* Map a region for the shared_info page */
vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0);
+ virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2, 0);
struct kvm_xen_hvm_config hvmc = {
.flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL,
@@ -111,6 +178,17 @@ int main(int argc, char *argv[])
};
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock);
+ if (do_runstate_tests) {
+ struct kvm_xen_vcpu_attr st = {
+ .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR,
+ .u.gpa = RUNSTATE_ADDR,
+ };
+ vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
+ }
+
+ struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);;
+ rs->state = 0x5a;
+
for (;;) {
volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
struct ucall uc;
@@ -126,8 +204,56 @@ int main(int argc, char *argv[])
case UCALL_ABORT:
TEST_FAIL("%s", (const char *)uc.args[0]);
/* NOT REACHED */
- case UCALL_SYNC:
+ case UCALL_SYNC: {
+ struct kvm_xen_vcpu_attr rst;
+ long rundelay;
+
+ /* If no runstate support, bail out early */
+ if (!do_runstate_tests)
+ goto done;
+
+ TEST_ASSERT(rs->state_entry_time == rs->time[0] +
+ rs->time[1] + rs->time[2] + rs->time[3],
+ "runstate times don't add up");
+
+ switch (uc.args[1]) {
+ case RUNSTATE_running...RUNSTATE_offline:
+ rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT;
+ rst.u.runstate.state = uc.args[1];
+ vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
+ break;
+ case 4:
+ rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST;
+ memset(&rst.u, 0, sizeof(rst.u));
+ rst.u.runstate.state = (uint64_t)-1;
+ rst.u.runstate.time_blocked =
+ 0x5a - rs->time[RUNSTATE_blocked];
+ rst.u.runstate.time_offline =
+ 0x6b6b - rs->time[RUNSTATE_offline];
+ rst.u.runstate.time_runnable = -rst.u.runstate.time_blocked -
+ rst.u.runstate.time_offline;
+ vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
+ break;
+
+ case 5:
+ rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA;
+ memset(&rst.u, 0, sizeof(rst.u));
+ rst.u.runstate.state = RUNSTATE_running;
+ rst.u.runstate.state_entry_time = 0x6b6b + 0x5a;
+ rst.u.runstate.time_blocked = 0x6b6b;
+ rst.u.runstate.time_offline = 0x5a;
+ vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
+ break;
+ case 6:
+ /* Yield until scheduler delay exceeds target */
+ rundelay = get_run_delay() + MIN_STEAL_TIME;
+ do {
+ sched_yield();
+ } while (get_run_delay() < rundelay);
+ break;
+ }
break;
+ }
case UCALL_DONE:
goto done;
default:
@@ -162,6 +288,33 @@ int main(int argc, char *argv[])
TEST_ASSERT(ti2->version && !(ti2->version & 1),
"Bad time_info version %x", ti->version);
+ if (do_runstate_tests) {
+ /*
+ * Fetch runstate and check sanity. Strictly speaking in the
+ * general case we might not expect the numbers to be identical
+ * but in this case we know we aren't running the vCPU any more.
+ */
+ struct kvm_xen_vcpu_attr rst = {
+ .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA,
+ };
+ vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst);
+
+ TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch");
+ TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time,
+ "State entry time mismatch");
+ TEST_ASSERT(rs->time[RUNSTATE_running] == rst.u.runstate.time_running,
+ "Running time mismatch");
+ TEST_ASSERT(rs->time[RUNSTATE_runnable] == rst.u.runstate.time_runnable,
+ "Runnable time mismatch");
+ TEST_ASSERT(rs->time[RUNSTATE_blocked] == rst.u.runstate.time_blocked,
+ "Blocked time mismatch");
+ TEST_ASSERT(rs->time[RUNSTATE_offline] == rst.u.runstate.time_offline,
+ "Offline time mismatch");
+
+ TEST_ASSERT(rs->state_entry_time == rs->time[0] +
+ rs->time[1] + rs->time[2] + rs->time[3],
+ "runstate times don't add up");
+ }
kvm_vm_free(vm);
return 0;
}
diff --git a/tools/testing/selftests/mount_setattr/.gitignore b/tools/testing/selftests/mount_setattr/.gitignore
new file mode 100644
index 000000000000..5f74d8488472
--- /dev/null
+++ b/tools/testing/selftests/mount_setattr/.gitignore
@@ -0,0 +1 @@
+mount_setattr_test
diff --git a/tools/testing/selftests/mount_setattr/Makefile b/tools/testing/selftests/mount_setattr/Makefile
new file mode 100644
index 000000000000..2250f7dcb81e
--- /dev/null
+++ b/tools/testing/selftests/mount_setattr/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for mount selftests.
+CFLAGS = -g -I../../../../usr/include/ -Wall -O2 -pthread
+
+TEST_GEN_FILES += mount_setattr_test
+
+include ../lib.mk
diff --git a/tools/testing/selftests/mount_setattr/config b/tools/testing/selftests/mount_setattr/config
new file mode 100644
index 000000000000..416bd53ce982
--- /dev/null
+++ b/tools/testing/selftests/mount_setattr/config
@@ -0,0 +1 @@
+CONFIG_USER_NS=y
diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
new file mode 100644
index 000000000000..4e94e566e040
--- /dev/null
+++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
@@ -0,0 +1,1424 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <errno.h>
+#include <pthread.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/mount.h>
+#include <sys/wait.h>
+#include <sys/vfs.h>
+#include <sys/statvfs.h>
+#include <sys/sysinfo.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <stdbool.h>
+#include <stdarg.h>
+
+#include "../kselftest_harness.h"
+
+#ifndef CLONE_NEWNS
+#define CLONE_NEWNS 0x00020000
+#endif
+
+#ifndef CLONE_NEWUSER
+#define CLONE_NEWUSER 0x10000000
+#endif
+
+#ifndef MS_REC
+#define MS_REC 16384
+#endif
+
+#ifndef MS_RELATIME
+#define MS_RELATIME (1 << 21)
+#endif
+
+#ifndef MS_STRICTATIME
+#define MS_STRICTATIME (1 << 24)
+#endif
+
+#ifndef MOUNT_ATTR_RDONLY
+#define MOUNT_ATTR_RDONLY 0x00000001
+#endif
+
+#ifndef MOUNT_ATTR_NOSUID
+#define MOUNT_ATTR_NOSUID 0x00000002
+#endif
+
+#ifndef MOUNT_ATTR_NOEXEC
+#define MOUNT_ATTR_NOEXEC 0x00000008
+#endif
+
+#ifndef MOUNT_ATTR_NODIRATIME
+#define MOUNT_ATTR_NODIRATIME 0x00000080
+#endif
+
+#ifndef MOUNT_ATTR__ATIME
+#define MOUNT_ATTR__ATIME 0x00000070
+#endif
+
+#ifndef MOUNT_ATTR_RELATIME
+#define MOUNT_ATTR_RELATIME 0x00000000
+#endif
+
+#ifndef MOUNT_ATTR_NOATIME
+#define MOUNT_ATTR_NOATIME 0x00000010
+#endif
+
+#ifndef MOUNT_ATTR_STRICTATIME
+#define MOUNT_ATTR_STRICTATIME 0x00000020
+#endif
+
+#ifndef AT_RECURSIVE
+#define AT_RECURSIVE 0x8000
+#endif
+
+#ifndef MS_SHARED
+#define MS_SHARED (1 << 20)
+#endif
+
+#define DEFAULT_THREADS 4
+#define ptr_to_int(p) ((int)((intptr_t)(p)))
+#define int_to_ptr(u) ((void *)((intptr_t)(u)))
+
+#ifndef __NR_mount_setattr
+ #if defined __alpha__
+ #define __NR_mount_setattr 552
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_mount_setattr (442 + 4000)
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_mount_setattr (442 + 6000)
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_mount_setattr (442 + 5000)
+ #endif
+ #elif defined __ia64__
+ #define __NR_mount_setattr (442 + 1024)
+ #else
+ #define __NR_mount_setattr 442
+ #endif
+
+struct mount_attr {
+ __u64 attr_set;
+ __u64 attr_clr;
+ __u64 propagation;
+ __u64 userns_fd;
+};
+#endif
+
+#ifndef __NR_open_tree
+ #if defined __alpha__
+ #define __NR_open_tree 538
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_open_tree 4428
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_open_tree 6428
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_open_tree 5428
+ #endif
+ #elif defined __ia64__
+ #define __NR_open_tree (428 + 1024)
+ #else
+ #define __NR_open_tree 428
+ #endif
+#endif
+
+#ifndef MOUNT_ATTR_IDMAP
+#define MOUNT_ATTR_IDMAP 0x00100000
+#endif
+
+static inline int sys_mount_setattr(int dfd, const char *path, unsigned int flags,
+ struct mount_attr *attr, size_t size)
+{
+ return syscall(__NR_mount_setattr, dfd, path, flags, attr, size);
+}
+
+#ifndef OPEN_TREE_CLONE
+#define OPEN_TREE_CLONE 1
+#endif
+
+#ifndef OPEN_TREE_CLOEXEC
+#define OPEN_TREE_CLOEXEC O_CLOEXEC
+#endif
+
+#ifndef AT_RECURSIVE
+#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
+#endif
+
+static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
+{
+ return syscall(__NR_open_tree, dfd, filename, flags);
+}
+
+static ssize_t write_nointr(int fd, const void *buf, size_t count)
+{
+ ssize_t ret;
+
+ do {
+ ret = write(fd, buf, count);
+ } while (ret < 0 && errno == EINTR);
+
+ return ret;
+}
+
+static int write_file(const char *path, const void *buf, size_t count)
+{
+ int fd;
+ ssize_t ret;
+
+ fd = open(path, O_WRONLY | O_CLOEXEC | O_NOCTTY | O_NOFOLLOW);
+ if (fd < 0)
+ return -1;
+
+ ret = write_nointr(fd, buf, count);
+ close(fd);
+ if (ret < 0 || (size_t)ret != count)
+ return -1;
+
+ return 0;
+}
+
+static int create_and_enter_userns(void)
+{
+ uid_t uid;
+ gid_t gid;
+ char map[100];
+
+ uid = getuid();
+ gid = getgid();
+
+ if (unshare(CLONE_NEWUSER))
+ return -1;
+
+ if (write_file("/proc/self/setgroups", "deny", sizeof("deny") - 1) &&
+ errno != ENOENT)
+ return -1;
+
+ snprintf(map, sizeof(map), "0 %d 1", uid);
+ if (write_file("/proc/self/uid_map", map, strlen(map)))
+ return -1;
+
+
+ snprintf(map, sizeof(map), "0 %d 1", gid);
+ if (write_file("/proc/self/gid_map", map, strlen(map)))
+ return -1;
+
+ if (setgid(0))
+ return -1;
+
+ if (setuid(0))
+ return -1;
+
+ return 0;
+}
+
+static int prepare_unpriv_mountns(void)
+{
+ if (create_and_enter_userns())
+ return -1;
+
+ if (unshare(CLONE_NEWNS))
+ return -1;
+
+ if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0))
+ return -1;
+
+ return 0;
+}
+
+static int read_mnt_flags(const char *path)
+{
+ int ret;
+ struct statvfs stat;
+ unsigned int mnt_flags;
+
+ ret = statvfs(path, &stat);
+ if (ret != 0)
+ return -EINVAL;
+
+ if (stat.f_flag &
+ ~(ST_RDONLY | ST_NOSUID | ST_NODEV | ST_NOEXEC | ST_NOATIME |
+ ST_NODIRATIME | ST_RELATIME | ST_SYNCHRONOUS | ST_MANDLOCK))
+ return -EINVAL;
+
+ mnt_flags = 0;
+ if (stat.f_flag & ST_RDONLY)
+ mnt_flags |= MS_RDONLY;
+ if (stat.f_flag & ST_NOSUID)
+ mnt_flags |= MS_NOSUID;
+ if (stat.f_flag & ST_NODEV)
+ mnt_flags |= MS_NODEV;
+ if (stat.f_flag & ST_NOEXEC)
+ mnt_flags |= MS_NOEXEC;
+ if (stat.f_flag & ST_NOATIME)
+ mnt_flags |= MS_NOATIME;
+ if (stat.f_flag & ST_NODIRATIME)
+ mnt_flags |= MS_NODIRATIME;
+ if (stat.f_flag & ST_RELATIME)
+ mnt_flags |= MS_RELATIME;
+ if (stat.f_flag & ST_SYNCHRONOUS)
+ mnt_flags |= MS_SYNCHRONOUS;
+ if (stat.f_flag & ST_MANDLOCK)
+ mnt_flags |= ST_MANDLOCK;
+
+ return mnt_flags;
+}
+
+static char *get_field(char *src, int nfields)
+{
+ int i;
+ char *p = src;
+
+ for (i = 0; i < nfields; i++) {
+ while (*p && *p != ' ' && *p != '\t')
+ p++;
+
+ if (!*p)
+ break;
+
+ p++;
+ }
+
+ return p;
+}
+
+static void null_endofword(char *word)
+{
+ while (*word && *word != ' ' && *word != '\t')
+ word++;
+ *word = '\0';
+}
+
+static bool is_shared_mount(const char *path)
+{
+ size_t len = 0;
+ char *line = NULL;
+ FILE *f = NULL;
+
+ f = fopen("/proc/self/mountinfo", "re");
+ if (!f)
+ return false;
+
+ while (getline(&line, &len, f) != -1) {
+ char *opts, *target;
+
+ target = get_field(line, 4);
+ if (!target)
+ continue;
+
+ opts = get_field(target, 2);
+ if (!opts)
+ continue;
+
+ null_endofword(target);
+
+ if (strcmp(target, path) != 0)
+ continue;
+
+ null_endofword(opts);
+ if (strstr(opts, "shared:"))
+ return true;
+ }
+
+ free(line);
+ fclose(f);
+
+ return false;
+}
+
+static void *mount_setattr_thread(void *data)
+{
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID,
+ .attr_clr = 0,
+ .propagation = MS_SHARED,
+ };
+
+ if (sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)))
+ pthread_exit(int_to_ptr(-1));
+
+ pthread_exit(int_to_ptr(0));
+}
+
+/* Attempt to de-conflict with the selftests tree. */
+#ifndef SKIP
+#define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__)
+#endif
+
+static bool mount_setattr_supported(void)
+{
+ int ret;
+
+ ret = sys_mount_setattr(-EBADF, "", AT_EMPTY_PATH, NULL, 0);
+ if (ret < 0 && errno == ENOSYS)
+ return false;
+
+ return true;
+}
+
+FIXTURE(mount_setattr) {
+};
+
+FIXTURE_SETUP(mount_setattr)
+{
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_EQ(prepare_unpriv_mountns(), 0);
+
+ (void)umount2("/mnt", MNT_DETACH);
+ (void)umount2("/tmp", MNT_DETACH);
+
+ ASSERT_EQ(mount("testing", "/tmp", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/tmp/B", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/tmp/B/BB", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B/BB", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/mnt/A", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt/A", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/mnt/A/AA", 0777), 0);
+
+ ASSERT_EQ(mount("/tmp", "/mnt/A/AA", NULL, MS_BIND | MS_REC, NULL), 0);
+
+ ASSERT_EQ(mkdir("/mnt/B", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt/B", "ramfs",
+ MS_NOATIME | MS_NODEV | MS_NOSUID, 0), 0);
+
+ ASSERT_EQ(mkdir("/mnt/B/BB", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B/BB", "devpts",
+ MS_RELATIME | MS_NOEXEC | MS_RDONLY, 0), 0);
+}
+
+FIXTURE_TEARDOWN(mount_setattr)
+{
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ (void)umount2("/mnt/A", MNT_DETACH);
+ (void)umount2("/tmp", MNT_DETACH);
+}
+
+TEST_F(mount_setattr, invalid_attributes)
+{
+ struct mount_attr invalid_attr = {
+ .attr_set = (1U << 31),
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr)), 0);
+
+ invalid_attr.attr_set = 0;
+ invalid_attr.attr_clr = (1U << 31);
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr)), 0);
+
+ invalid_attr.attr_clr = 0;
+ invalid_attr.propagation = (1U << 31);
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr)), 0);
+
+ invalid_attr.attr_set = (1U << 31);
+ invalid_attr.attr_clr = (1U << 31);
+ invalid_attr.propagation = (1U << 31);
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr)), 0);
+
+ ASSERT_NE(sys_mount_setattr(-1, "mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr)), 0);
+}
+
+TEST_F(mount_setattr, extensibility)
+{
+ unsigned int old_flags = 0, new_flags = 0, expected_flags = 0;
+ char *s = "dummy";
+ struct mount_attr invalid_attr = {};
+ struct mount_attr_large {
+ struct mount_attr attr1;
+ struct mount_attr attr2;
+ struct mount_attr attr3;
+ } large_attr = {};
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, NULL,
+ sizeof(invalid_attr)), 0);
+ ASSERT_EQ(errno, EFAULT);
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, (void *)s,
+ sizeof(invalid_attr)), 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr, 0), 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr) / 2), 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &invalid_attr,
+ sizeof(invalid_attr) / 2), 0);
+ ASSERT_EQ(errno, EINVAL);
+
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE,
+ (void *)&large_attr, sizeof(large_attr)), 0);
+
+ large_attr.attr3.attr_set = MOUNT_ATTR_RDONLY;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE,
+ (void *)&large_attr, sizeof(large_attr)), 0);
+
+ large_attr.attr3.attr_set = 0;
+ large_attr.attr1.attr_set = MOUNT_ATTR_RDONLY;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE,
+ (void *)&large_attr, sizeof(large_attr)), 0);
+
+ expected_flags = old_flags;
+ expected_flags |= MS_RDONLY;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+}
+
+TEST_F(mount_setattr, basic)
+{
+ unsigned int old_flags = 0, new_flags = 0, expected_flags = 0;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOEXEC | MOUNT_ATTR_RELATIME,
+ .attr_clr = MOUNT_ATTR__ATIME,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", 0, &attr, sizeof(attr)), 0);
+
+ expected_flags = old_flags;
+ expected_flags |= MS_RDONLY;
+ expected_flags |= MS_NOEXEC;
+ expected_flags &= ~MS_NOATIME;
+ expected_flags |= MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, old_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, old_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, old_flags);
+}
+
+TEST_F(mount_setattr, basic_recursive)
+{
+ int fd;
+ unsigned int old_flags = 0, new_flags = 0, expected_flags = 0;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOEXEC | MOUNT_ATTR_RELATIME,
+ .attr_clr = MOUNT_ATTR__ATIME,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags = old_flags;
+ expected_flags |= MS_RDONLY;
+ expected_flags |= MS_NOEXEC;
+ expected_flags &= ~MS_NOATIME;
+ expected_flags |= MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ attr.attr_clr = MOUNT_ATTR_RDONLY;
+ attr.propagation = MS_SHARED;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags &= ~MS_RDONLY;
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B/BB"), true);
+
+ fd = open("/mnt/A/AA/B/b", O_RDWR | O_CLOEXEC | O_CREAT | O_EXCL, 0777);
+ ASSERT_GE(fd, 0);
+
+ /*
+ * We're holding a fd open for writing so this needs to fail somewhere
+ * in the middle and the mount options need to be unchanged.
+ */
+ attr.attr_set = MOUNT_ATTR_RDONLY;
+ ASSERT_LT(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B/BB"), true);
+
+ EXPECT_EQ(close(fd), 0);
+}
+
+TEST_F(mount_setattr, mount_has_writers)
+{
+ int fd, dfd;
+ unsigned int old_flags = 0, new_flags = 0;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOEXEC | MOUNT_ATTR_RELATIME,
+ .attr_clr = MOUNT_ATTR__ATIME,
+ .propagation = MS_SHARED,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ fd = open("/mnt/A/AA/B/b", O_RDWR | O_CLOEXEC | O_CREAT | O_EXCL, 0777);
+ ASSERT_GE(fd, 0);
+
+ /*
+ * We're holding a fd open to a mount somwhere in the middle so this
+ * needs to fail somewhere in the middle. After this the mount options
+ * need to be unchanged.
+ */
+ ASSERT_LT(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, old_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A"), false);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, old_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA"), false);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, old_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B"), false);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, old_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B/BB"), false);
+
+ dfd = open("/mnt/A/AA/B", O_DIRECTORY | O_CLOEXEC);
+ ASSERT_GE(dfd, 0);
+ EXPECT_EQ(fsync(dfd), 0);
+ EXPECT_EQ(close(dfd), 0);
+
+ EXPECT_EQ(fsync(fd), 0);
+ EXPECT_EQ(close(fd), 0);
+
+ /* All writers are gone so this should succeed. */
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+}
+
+TEST_F(mount_setattr, mixed_mount_options)
+{
+ unsigned int old_flags1 = 0, old_flags2 = 0, new_flags = 0, expected_flags = 0;
+ struct mount_attr attr = {
+ .attr_clr = MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME,
+ .attr_set = MOUNT_ATTR_RELATIME,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags1 = read_mnt_flags("/mnt/B");
+ ASSERT_GT(old_flags1, 0);
+
+ old_flags2 = read_mnt_flags("/mnt/B/BB");
+ ASSERT_GT(old_flags2, 0);
+
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/B", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags = old_flags2;
+ expected_flags &= ~(MS_RDONLY | MS_NOEXEC | MS_NOATIME | MS_NOSUID);
+ expected_flags |= MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ expected_flags = old_flags2;
+ expected_flags &= ~(MS_RDONLY | MS_NOEXEC | MS_NOATIME | MS_NOSUID);
+ expected_flags |= MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+}
+
+TEST_F(mount_setattr, time_changes)
+{
+ unsigned int old_flags = 0, new_flags = 0, expected_flags = 0;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_NODIRATIME | MOUNT_ATTR_NOATIME,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ attr.attr_set = MOUNT_ATTR_STRICTATIME;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ attr.attr_set = MOUNT_ATTR_STRICTATIME | MOUNT_ATTR_NOATIME;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ attr.attr_set = MOUNT_ATTR_STRICTATIME | MOUNT_ATTR_NOATIME;
+ attr.attr_clr = MOUNT_ATTR__ATIME;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ attr.attr_set = 0;
+ attr.attr_clr = MOUNT_ATTR_STRICTATIME;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ attr.attr_clr = MOUNT_ATTR_NOATIME;
+ ASSERT_NE(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ attr.attr_set = MOUNT_ATTR_NODIRATIME | MOUNT_ATTR_NOATIME;
+ attr.attr_clr = MOUNT_ATTR__ATIME;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags = old_flags;
+ expected_flags |= MS_NOATIME;
+ expected_flags |= MS_NODIRATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ attr.attr_set &= ~MOUNT_ATTR_NOATIME;
+ attr.attr_set |= MOUNT_ATTR_RELATIME;
+ attr.attr_clr |= MOUNT_ATTR__ATIME;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags &= ~MS_NOATIME;
+ expected_flags |= MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ attr.attr_set &= ~MOUNT_ATTR_RELATIME;
+ attr.attr_set |= MOUNT_ATTR_STRICTATIME;
+ attr.attr_clr |= MOUNT_ATTR__ATIME;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags &= ~MS_RELATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ attr.attr_set &= ~MOUNT_ATTR_STRICTATIME;
+ attr.attr_set |= MOUNT_ATTR_NOATIME;
+ attr.attr_clr |= MOUNT_ATTR__ATIME;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags |= MS_NOATIME;
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ memset(&attr, 0, sizeof(attr));
+ attr.attr_clr = MOUNT_ATTR_NODIRATIME;
+ ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0);
+
+ expected_flags &= ~MS_NODIRATIME;
+
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+}
+
+TEST_F(mount_setattr, multi_threaded)
+{
+ int i, j, nthreads, ret = 0;
+ unsigned int old_flags = 0, new_flags = 0, expected_flags = 0;
+ pthread_attr_t pattr;
+ pthread_t threads[DEFAULT_THREADS];
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ old_flags = read_mnt_flags("/mnt/A");
+ ASSERT_GT(old_flags, 0);
+
+ /* Try to change mount options from multiple threads. */
+ nthreads = get_nprocs_conf();
+ if (nthreads > DEFAULT_THREADS)
+ nthreads = DEFAULT_THREADS;
+
+ pthread_attr_init(&pattr);
+ for (i = 0; i < nthreads; i++)
+ ASSERT_EQ(pthread_create(&threads[i], &pattr, mount_setattr_thread, NULL), 0);
+
+ for (j = 0; j < i; j++) {
+ void *retptr = NULL;
+
+ EXPECT_EQ(pthread_join(threads[j], &retptr), 0);
+
+ ret += ptr_to_int(retptr);
+ EXPECT_EQ(ret, 0);
+ }
+ pthread_attr_destroy(&pattr);
+
+ ASSERT_EQ(ret, 0);
+
+ expected_flags = old_flags;
+ expected_flags |= MS_RDONLY;
+ expected_flags |= MS_NOSUID;
+ new_flags = read_mnt_flags("/mnt/A");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B"), true);
+
+ new_flags = read_mnt_flags("/mnt/A/AA/B/BB");
+ ASSERT_EQ(new_flags, expected_flags);
+
+ ASSERT_EQ(is_shared_mount("/mnt/A/AA/B/BB"), true);
+}
+
+TEST_F(mount_setattr, wrong_user_namespace)
+{
+ int ret;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ EXPECT_EQ(create_and_enter_userns(), 0);
+ ret = sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr));
+ ASSERT_LT(ret, 0);
+ ASSERT_EQ(errno, EPERM);
+}
+
+TEST_F(mount_setattr, wrong_mount_namespace)
+{
+ int fd, ret;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_RDONLY,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ fd = open("/mnt/A", O_DIRECTORY | O_CLOEXEC);
+ ASSERT_GE(fd, 0);
+
+ ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+
+ ret = sys_mount_setattr(fd, "", AT_EMPTY_PATH | AT_RECURSIVE, &attr, sizeof(attr));
+ ASSERT_LT(ret, 0);
+ ASSERT_EQ(errno, EINVAL);
+}
+
+FIXTURE(mount_setattr_idmapped) {
+};
+
+FIXTURE_SETUP(mount_setattr_idmapped)
+{
+ int img_fd = -EBADF;
+
+ ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+
+ ASSERT_EQ(mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0), 0);
+
+ (void)umount2("/mnt", MNT_DETACH);
+ (void)umount2("/tmp", MNT_DETACH);
+
+ ASSERT_EQ(mount("testing", "/tmp", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/tmp/B", 0777), 0);
+ ASSERT_EQ(mknodat(-EBADF, "/tmp/B/b", S_IFREG | 0644, 0), 0);
+ ASSERT_EQ(chown("/tmp/B/b", 0, 0), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/tmp/B/BB", 0777), 0);
+ ASSERT_EQ(mknodat(-EBADF, "/tmp/B/BB/b", S_IFREG | 0644, 0), 0);
+ ASSERT_EQ(chown("/tmp/B/BB/b", 0, 0), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B/BB", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/mnt/A", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt/A", "tmpfs", MS_NOATIME | MS_NODEV,
+ "size=100000,mode=700"), 0);
+
+ ASSERT_EQ(mkdir("/mnt/A/AA", 0777), 0);
+
+ ASSERT_EQ(mount("/tmp", "/mnt/A/AA", NULL, MS_BIND | MS_REC, NULL), 0);
+
+ ASSERT_EQ(mkdir("/mnt/B", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/mnt/B", "ramfs",
+ MS_NOATIME | MS_NODEV | MS_NOSUID, 0), 0);
+
+ ASSERT_EQ(mkdir("/mnt/B/BB", 0777), 0);
+
+ ASSERT_EQ(mount("testing", "/tmp/B/BB", "devpts",
+ MS_RELATIME | MS_NOEXEC | MS_RDONLY, 0), 0);
+
+ ASSERT_EQ(mkdir("/mnt/C", 0777), 0);
+ ASSERT_EQ(mkdir("/mnt/D", 0777), 0);
+ img_fd = openat(-EBADF, "/mnt/C/ext4.img", O_CREAT | O_WRONLY, 0600);
+ ASSERT_GE(img_fd, 0);
+ ASSERT_EQ(ftruncate(img_fd, 1024 * 2048), 0);
+ ASSERT_EQ(system("mkfs.ext4 -q /mnt/C/ext4.img"), 0);
+ ASSERT_EQ(system("mount -o loop -t ext4 /mnt/C/ext4.img /mnt/D/"), 0);
+ ASSERT_EQ(close(img_fd), 0);
+}
+
+FIXTURE_TEARDOWN(mount_setattr_idmapped)
+{
+ (void)umount2("/mnt/A", MNT_DETACH);
+ (void)umount2("/tmp", MNT_DETACH);
+}
+
+/**
+ * Validate that negative fd values are rejected.
+ */
+TEST_F(mount_setattr_idmapped, invalid_fd_negative)
+{
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ .userns_fd = -EBADF,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_NE(sys_mount_setattr(-1, "/", 0, &attr, sizeof(attr)), 0) {
+ TH_LOG("failure: created idmapped mount with negative fd");
+ }
+}
+
+/**
+ * Validate that excessively large fd values are rejected.
+ */
+TEST_F(mount_setattr_idmapped, invalid_fd_large)
+{
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ .userns_fd = INT64_MAX,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_NE(sys_mount_setattr(-1, "/", 0, &attr, sizeof(attr)), 0) {
+ TH_LOG("failure: created idmapped mount with too large fd value");
+ }
+}
+
+/**
+ * Validate that closed fd values are rejected.
+ */
+TEST_F(mount_setattr_idmapped, invalid_fd_closed)
+{
+ int fd;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+ ASSERT_GE(fd, 0);
+ ASSERT_GE(close(fd), 0);
+
+ attr.userns_fd = fd;
+ ASSERT_NE(sys_mount_setattr(-1, "/", 0, &attr, sizeof(attr)), 0) {
+ TH_LOG("failure: created idmapped mount with closed fd");
+ }
+}
+
+/**
+ * Validate that the initial user namespace is rejected.
+ */
+TEST_F(mount_setattr_idmapped, invalid_fd_initial_userns)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC | OPEN_TREE_CLONE);
+ ASSERT_GE(open_tree_fd, 0);
+
+ attr.userns_fd = open("/proc/1/ns/user", O_RDONLY | O_CLOEXEC);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(errno, EPERM);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+static int map_ids(pid_t pid, unsigned long nsid, unsigned long hostid,
+ unsigned long range)
+{
+ char map[100], procfile[256];
+
+ snprintf(procfile, sizeof(procfile), "/proc/%d/uid_map", pid);
+ snprintf(map, sizeof(map), "%lu %lu %lu", nsid, hostid, range);
+ if (write_file(procfile, map, strlen(map)))
+ return -1;
+
+
+ snprintf(procfile, sizeof(procfile), "/proc/%d/gid_map", pid);
+ snprintf(map, sizeof(map), "%lu %lu %lu", nsid, hostid, range);
+ if (write_file(procfile, map, strlen(map)))
+ return -1;
+
+ return 0;
+}
+
+#define __STACK_SIZE (8 * 1024 * 1024)
+static pid_t do_clone(int (*fn)(void *), void *arg, int flags)
+{
+ void *stack;
+
+ stack = malloc(__STACK_SIZE);
+ if (!stack)
+ return -ENOMEM;
+
+#ifdef __ia64__
+ return __clone2(fn, stack, __STACK_SIZE, flags | SIGCHLD, arg, NULL);
+#else
+ return clone(fn, stack + __STACK_SIZE, flags | SIGCHLD, arg, NULL);
+#endif
+}
+
+static int get_userns_fd_cb(void *data)
+{
+ return kill(getpid(), SIGSTOP);
+}
+
+static int wait_for_pid(pid_t pid)
+{
+ int status, ret;
+
+again:
+ ret = waitpid(pid, &status, 0);
+ if (ret == -1) {
+ if (errno == EINTR)
+ goto again;
+
+ return -1;
+ }
+
+ if (!WIFEXITED(status))
+ return -1;
+
+ return WEXITSTATUS(status);
+}
+
+static int get_userns_fd(unsigned long nsid, unsigned long hostid, unsigned long range)
+{
+ int ret;
+ pid_t pid;
+ char path[256];
+
+ pid = do_clone(get_userns_fd_cb, NULL, CLONE_NEWUSER);
+ if (pid < 0)
+ return -errno;
+
+ ret = map_ids(pid, nsid, hostid, range);
+ if (ret < 0)
+ return ret;
+
+ snprintf(path, sizeof(path), "/proc/%d/ns/user", pid);
+ ret = open(path, O_RDONLY | O_CLOEXEC);
+ kill(pid, SIGKILL);
+ wait_for_pid(pid);
+ return ret;
+}
+
+/**
+ * Validate that an attached mount in our mount namespace can be idmapped.
+ * (The kernel enforces that the mount's mount namespace and the caller's mount
+ * namespace match.)
+ */
+TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC);
+ ASSERT_GE(open_tree_fd, 0);
+
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_EQ(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+/**
+ * Validate that idmapping a mount is rejected if the mount's mount namespace
+ * and our mount namespace don't match.
+ * (The kernel enforces that the mount's mount namespace and the caller's mount
+ * namespace match.)
+ */
+TEST_F(mount_setattr_idmapped, attached_mount_outside_current_mount_namespace)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC);
+ ASSERT_GE(open_tree_fd, 0);
+
+ ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr,
+ sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+/**
+ * Validate that an attached mount in our mount namespace can be idmapped.
+ */
+TEST_F(mount_setattr_idmapped, detached_mount_inside_current_mount_namespace)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC |
+ OPEN_TREE_CLONE);
+ ASSERT_GE(open_tree_fd, 0);
+
+ /* Changing mount properties on a detached mount. */
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_EQ(sys_mount_setattr(open_tree_fd, "",
+ AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+/**
+ * Validate that a detached mount not in our mount namespace can be idmapped.
+ */
+TEST_F(mount_setattr_idmapped, detached_mount_outside_current_mount_namespace)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC |
+ OPEN_TREE_CLONE);
+ ASSERT_GE(open_tree_fd, 0);
+
+ ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+
+ /* Changing mount properties on a detached mount. */
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_EQ(sys_mount_setattr(open_tree_fd, "",
+ AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+/**
+ * Validate that currently changing the idmapping of an idmapped mount fails.
+ */
+TEST_F(mount_setattr_idmapped, change_idmapping)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/D",
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC |
+ OPEN_TREE_CLONE);
+ ASSERT_GE(open_tree_fd, 0);
+
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_EQ(sys_mount_setattr(open_tree_fd, "",
+ AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+
+ /* Change idmapping on a detached mount that is already idmapped. */
+ attr.userns_fd = get_userns_fd(0, 20000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+}
+
+static bool expected_uid_gid(int dfd, const char *path, int flags,
+ uid_t expected_uid, gid_t expected_gid)
+{
+ int ret;
+ struct stat st;
+
+ ret = fstatat(dfd, path, &st, flags);
+ if (ret < 0)
+ return false;
+
+ return st.st_uid == expected_uid && st.st_gid == expected_gid;
+}
+
+TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid)
+{
+ int open_tree_fd = -EBADF;
+ struct mount_attr attr = {
+ .attr_set = MOUNT_ATTR_IDMAP,
+ };
+
+ if (!mount_setattr_supported())
+ SKIP(return, "mount_setattr syscall not supported");
+
+ ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/b", 0, 0, 0), 0);
+ ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/BB/b", 0, 0, 0), 0);
+
+ open_tree_fd = sys_open_tree(-EBADF, "/mnt/A",
+ AT_RECURSIVE |
+ AT_EMPTY_PATH |
+ AT_NO_AUTOMOUNT |
+ AT_SYMLINK_NOFOLLOW |
+ OPEN_TREE_CLOEXEC |
+ OPEN_TREE_CLONE);
+ ASSERT_GE(open_tree_fd, 0);
+
+ attr.userns_fd = get_userns_fd(0, 10000, 10000);
+ ASSERT_GE(attr.userns_fd, 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_EQ(close(attr.userns_fd), 0);
+ ASSERT_EQ(close(open_tree_fd), 0);
+
+ ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/b", 0, 0, 0), 0);
+ ASSERT_EQ(expected_uid_gid(-EBADF, "/tmp/B/BB/b", 0, 0, 0), 0);
+ ASSERT_EQ(expected_uid_gid(open_tree_fd, "B/b", 0, 0, 0), 0);
+ ASSERT_EQ(expected_uid_gid(open_tree_fd, "B/BB/b", 0, 0, 0), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 74c69b75f6f5..7ed7cd95e58f 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -39,7 +39,7 @@ ip0() { pretty 0 "ip $*"; ip -n $netns0 "$@"; }
ip1() { pretty 1 "ip $*"; ip -n $netns1 "$@"; }
ip2() { pretty 2 "ip $*"; ip -n $netns2 "$@"; }
sleep() { read -t "$1" -N 1 || true; }
-waitiperf() { pretty "${1//*-}" "wait for iperf:5201 pid $2"; while [[ $(ss -N "$1" -tlpH 'sport = 5201') != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; }
+waitiperf() { pretty "${1//*-}" "wait for iperf:${3:-5201} pid $2"; while [[ $(ss -N "$1" -tlpH "sport = ${3:-5201}") != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; }
waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; }
waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; }
@@ -141,6 +141,19 @@ tests() {
n2 iperf3 -s -1 -B fd00::2 &
waitiperf $netns2 $!
n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2
+
+ # TCP over IPv4, in parallel
+ for max in 4 5 50; do
+ local pids=( )
+ for ((i=0; i < max; ++i)) do
+ n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 &
+ pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i ))
+ done
+ for ((i=0; i < max; ++i)) do
+ n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 &
+ done
+ wait "${pids[@]}"
+ done
}
[[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}"
generated by cgit (git 2.34.1) at 2025-10-10 00:33:40 +0000