summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/bpf/bpftool/net.c1
-rw-r--r--tools/bpf/resolve_btfids/main.c17
-rw-r--r--tools/testing/selftests/bpf/Makefile3
-rw-r--r--tools/testing/selftests/bpf/progs/bprm_opts.c2
-rw-r--r--tools/testing/selftests/bpf/test_maps.c48
-rw-r--r--tools/testing/selftests/bpf/xdpxceiver.c4
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh2
-rw-r--r--tools/testing/selftests/kvm/Makefile2
-rw-r--r--tools/testing/selftests/kvm/demand_paging_test.c118
-rw-r--r--tools/testing/selftests/kvm/dirty_log_perf_test.c145
-rw-r--r--tools/testing/selftests/kvm/dirty_log_test.c125
-rw-r--r--tools/testing/selftests/kvm/include/guest_modes.h21
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h9
-rw-r--r--tools/testing/selftests/kvm/include/perf_test_util.h167
-rw-r--r--tools/testing/selftests/kvm/lib/guest_modes.c70
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c9
-rw-r--r--tools/testing/selftests/kvm/lib/perf_test_util.c134
-rwxr-xr-xtools/testing/selftests/net/fib_nexthops.sh2
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh71
-rwxr-xr-xtools/testing/selftests/net/udpgro.sh34
-rw-r--r--tools/testing/selftests/netfilter/Makefile3
-rwxr-xr-xtools/testing/selftests/netfilter/ipip-conntrack-mtu.sh206
-rw-r--r--tools/testing/selftests/wireguard/qemu/debug.config1
23 files changed, 736 insertions, 458 deletions
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 3fae61ef6339..ff3aa0cf3997 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -11,7 +11,6 @@
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
#include <net/if.h>
-#include <linux/if.h>
#include <linux/rtnetlink.h>
#include <linux/socket.h>
#include <linux/tc_act/tc_bpf.h>
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index e3ea569ee125..7409d7860aa6 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -139,6 +139,8 @@ int eprintf(int level, int var, const char *fmt, ...)
#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
#define pr_err(fmt, ...) \
eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+ eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
static bool is_btf_id(const char *name)
{
@@ -472,7 +474,7 @@ static int symbols_resolve(struct object *obj)
int nr_funcs = obj->nr_funcs;
int err, type_id;
struct btf *btf;
- __u32 nr;
+ __u32 nr_types;
btf = btf__parse(obj->btf ?: obj->path, NULL);
err = libbpf_get_error(btf);
@@ -483,12 +485,12 @@ static int symbols_resolve(struct object *obj)
}
err = -1;
- nr = btf__get_nr_types(btf);
+ nr_types = btf__get_nr_types(btf);
/*
* Iterate all the BTF types and search for collected symbol IDs.
*/
- for (type_id = 1; type_id <= nr; type_id++) {
+ for (type_id = 1; type_id <= nr_types; type_id++) {
const struct btf_type *type;
struct rb_root *root;
struct btf_id *id;
@@ -526,8 +528,13 @@ static int symbols_resolve(struct object *obj)
id = btf_id__find(root, str);
if (id) {
- id->id = type_id;
- (*nr)--;
+ if (id->id) {
+ pr_info("WARN: multiple IDs found for '%s': %d, %d - using %d\n",
+ str, id->id, type_id, id->id);
+ } else {
+ id->id = type_id;
+ (*nr)--;
+ }
}
}
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 8c33e999319a..c51df6b91bef 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -121,6 +121,9 @@ VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \
/sys/kernel/btf/vmlinux \
/boot/vmlinux-$(shell uname -r)
VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+ifeq ($(VMLINUX_BTF),)
+$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
+endif
# Define simple and short `make test_progs`, `make test_sysctl`, etc targets
# to build individual tests.
diff --git a/tools/testing/selftests/bpf/progs/bprm_opts.c b/tools/testing/selftests/bpf/progs/bprm_opts.c
index 5bfef2887e70..418d9c6d4952 100644
--- a/tools/testing/selftests/bpf/progs/bprm_opts.c
+++ b/tools/testing/selftests/bpf/progs/bprm_opts.c
@@ -4,7 +4,7 @@
* Copyright 2020 Google LLC.
*/
-#include "vmlinux.h"
+#include <linux/bpf.h>
#include <errno.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 0ad3e6305ff0..51adc42b2b40 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1312,22 +1312,58 @@ static void test_map_stress(void)
#define DO_UPDATE 1
#define DO_DELETE 0
+#define MAP_RETRIES 20
+
+static int map_update_retriable(int map_fd, const void *key, const void *value,
+ int flags, int attempts)
+{
+ while (bpf_map_update_elem(map_fd, key, value, flags)) {
+ if (!attempts || (errno != EAGAIN && errno != EBUSY))
+ return -errno;
+
+ usleep(1);
+ attempts--;
+ }
+
+ return 0;
+}
+
+static int map_delete_retriable(int map_fd, const void *key, int attempts)
+{
+ while (bpf_map_delete_elem(map_fd, key)) {
+ if (!attempts || (errno != EAGAIN && errno != EBUSY))
+ return -errno;
+
+ usleep(1);
+ attempts--;
+ }
+
+ return 0;
+}
+
static void test_update_delete(unsigned int fn, void *data)
{
int do_update = ((int *)data)[1];
int fd = ((int *)data)[0];
- int i, key, value;
+ int i, key, value, err;
for (i = fn; i < MAP_SIZE; i += TASKS) {
key = value = i;
if (do_update) {
- assert(bpf_map_update_elem(fd, &key, &value,
- BPF_NOEXIST) == 0);
- assert(bpf_map_update_elem(fd, &key, &value,
- BPF_EXIST) == 0);
+ err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES);
+ if (err)
+ printf("error %d %d\n", err, errno);
+ assert(err == 0);
+ err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES);
+ if (err)
+ printf("error %d %d\n", err, errno);
+ assert(err == 0);
} else {
- assert(bpf_map_delete_elem(fd, &key) == 0);
+ err = map_delete_retriable(fd, &key, MAP_RETRIES);
+ if (err)
+ printf("error %d %d\n", err, errno);
+ assert(err == 0);
}
}
}
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 014dedaa4dd2..1e722ee76b1f 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -715,7 +715,7 @@ static void worker_pkt_dump(void)
int payload = *((uint32_t *)(pkt_buf[iter]->payload + PKT_HDR_SIZE));
if (payload == EOT) {
- ksft_print_msg("End-of-tranmission frame received\n");
+ ksft_print_msg("End-of-transmission frame received\n");
fprintf(stdout, "---------------------------------------\n");
break;
}
@@ -747,7 +747,7 @@ static void worker_pkt_validate(void)
}
if (payloadseqnum == EOT) {
- ksft_print_msg("End-of-tranmission frame received: PASS\n");
+ ksft_print_msg("End-of-transmission frame received: PASS\n");
sigvar = 1;
break;
}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
index 4d900bc1f76c..5c7700212f75 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
@@ -230,7 +230,7 @@ switch_create()
__mlnx_qos -i $swp4 --pfc=0,1,0,0,0,0,0,0 >/dev/null
# PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which
# is (-2*MTU) about 80K of delay provision.
- __mlnx_qos -i $swp3 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null
+ __mlnx_qos -i $swp4 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null
# bridges
# -------
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index c7ca4faba272..fe41c6a0fa67 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -33,7 +33,7 @@ ifeq ($(ARCH),s390)
UNAME_M := s390x
endif
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
+LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 3d96a7bfaff3..cdad1eca72f7 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -7,23 +7,20 @@
* Copyright (C) 2019, Google, Inc.
*/
-#define _GNU_SOURCE /* for program_invocation_name */
+#define _GNU_SOURCE /* for pipe2 */
#include <stdio.h>
#include <stdlib.h>
-#include <sys/syscall.h>
-#include <unistd.h>
-#include <asm/unistd.h>
#include <time.h>
#include <poll.h>
#include <pthread.h>
-#include <linux/bitmap.h>
-#include <linux/bitops.h>
#include <linux/userfaultfd.h>
+#include <sys/syscall.h>
-#include "perf_test_util.h"
-#include "processor.h"
+#include "kvm_util.h"
#include "test_util.h"
+#include "perf_test_util.h"
+#include "guest_modes.h"
#ifdef __NR_userfaultfd
@@ -39,12 +36,14 @@
#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
#endif
+static int nr_vcpus = 1;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
static char *guest_data_prototype;
static void *vcpu_worker(void *data)
{
int ret;
- struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+ struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
int vcpu_id = vcpu_args->vcpu_id;
struct kvm_vm *vm = perf_test_args.vm;
struct kvm_run *run;
@@ -248,9 +247,14 @@ static int setup_demand_paging(struct kvm_vm *vm,
return 0;
}
-static void run_test(enum vm_guest_mode mode, bool use_uffd,
- useconds_t uffd_delay)
+struct test_params {
+ bool use_uffd;
+ useconds_t uffd_delay;
+};
+
+static void run_test(enum vm_guest_mode mode, void *arg)
{
+ struct test_params *p = arg;
pthread_t *vcpu_threads;
pthread_t *uffd_handler_threads = NULL;
struct uffd_handler_args *uffd_args = NULL;
@@ -261,7 +265,7 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
int vcpu_id;
int r;
- vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+ vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size);
perf_test_args.wr_fract = 1;
@@ -273,9 +277,9 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
TEST_ASSERT(vcpu_threads, "Memory allocation failed");
- add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+ perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
- if (use_uffd) {
+ if (p->use_uffd) {
uffd_handler_threads =
malloc(nr_vcpus * sizeof(*uffd_handler_threads));
TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
@@ -308,7 +312,7 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
r = setup_demand_paging(vm,
&uffd_handler_threads[vcpu_id],
pipefds[vcpu_id * 2],
- uffd_delay, &uffd_args[vcpu_id],
+ p->uffd_delay, &uffd_args[vcpu_id],
vcpu_hva, guest_percpu_mem_size);
if (r < 0)
exit(-r);
@@ -339,7 +343,7 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
pr_info("All vCPU threads joined\n");
- if (use_uffd) {
+ if (p->use_uffd) {
char c;
/* Tell the user fault fd handler threads to quit */
@@ -357,43 +361,23 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd,
perf_test_args.vcpu_args[0].pages * nr_vcpus /
((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
- ucall_uninit(vm);
- kvm_vm_free(vm);
+ perf_test_destroy_vm(vm);
free(guest_data_prototype);
free(vcpu_threads);
- if (use_uffd) {
+ if (p->use_uffd) {
free(uffd_handler_threads);
free(uffd_args);
free(pipefds);
}
}
-struct guest_mode {
- bool supported;
- bool enabled;
-};
-static struct guest_mode guest_modes[NUM_VM_MODES];
-
-#define guest_mode_init(mode, supported, enabled) ({ \
- guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
-})
-
static void help(char *name)
{
- int i;
-
puts("");
printf("usage: %s [-h] [-m mode] [-u] [-d uffd_delay_usec]\n"
" [-b memory] [-v vcpus]\n", name);
- printf(" -m: specify the guest mode ID to test\n"
- " (default: test all supported modes)\n"
- " This option may be used multiple times.\n"
- " Guest mode IDs:\n");
- for (i = 0; i < NUM_VM_MODES; ++i) {
- printf(" %d: %s%s\n", i, vm_guest_mode_string(i),
- guest_modes[i].supported ? " (supported)" : "");
- }
+ guest_modes_help();
printf(" -u: use User Fault FD to handle vCPU page\n"
" faults.\n");
printf(" -d: add a delay in usec to the User Fault\n"
@@ -410,53 +394,22 @@ static void help(char *name)
int main(int argc, char *argv[])
{
int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
- bool mode_selected = false;
- unsigned int mode;
- int opt, i;
- bool use_uffd = false;
- useconds_t uffd_delay = 0;
-
-#ifdef __x86_64__
- guest_mode_init(VM_MODE_PXXV48_4K, true, true);
-#endif
-#ifdef __aarch64__
- guest_mode_init(VM_MODE_P40V48_4K, true, true);
- guest_mode_init(VM_MODE_P40V48_64K, true, true);
- {
- unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
-
- if (limit >= 52)
- guest_mode_init(VM_MODE_P52V48_64K, true, true);
- if (limit >= 48) {
- guest_mode_init(VM_MODE_P48V48_4K, true, true);
- guest_mode_init(VM_MODE_P48V48_64K, true, true);
- }
- }
-#endif
-#ifdef __s390x__
- guest_mode_init(VM_MODE_P40V48_4K, true, true);
-#endif
+ struct test_params p = {};
+ int opt;
+
+ guest_modes_append_default();
while ((opt = getopt(argc, argv, "hm:ud:b:v:")) != -1) {
switch (opt) {
case 'm':
- if (!mode_selected) {
- for (i = 0; i < NUM_VM_MODES; ++i)
- guest_modes[i].enabled = false;
- mode_selected = true;
- }
- mode = strtoul(optarg, NULL, 10);
- TEST_ASSERT(mode < NUM_VM_MODES,
- "Guest mode ID %d too big", mode);
- guest_modes[mode].enabled = true;
+ guest_modes_cmdline(optarg);
break;
case 'u':
- use_uffd = true;
+ p.use_uffd = true;
break;
case 'd':
- uffd_delay = strtoul(optarg, NULL, 0);
- TEST_ASSERT(uffd_delay >= 0,
- "A negative UFFD delay is not supported.");
+ p.uffd_delay = strtoul(optarg, NULL, 0);
+ TEST_ASSERT(p.uffd_delay >= 0, "A negative UFFD delay is not supported.");
break;
case 'b':
guest_percpu_mem_size = parse_size(optarg);
@@ -473,14 +426,7 @@ int main(int argc, char *argv[])
}
}
- for (i = 0; i < NUM_VM_MODES; ++i) {
- if (!guest_modes[i].enabled)
- continue;
- TEST_ASSERT(guest_modes[i].supported,
- "Guest mode ID %d (%s) not supported.",
- i, vm_guest_mode_string(i));
- run_test(i, use_uffd, uffd_delay);
- }
+ for_each_guest_mode(run_test, &p);
return 0;
}
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 9c6a7be31e03..2283a0ec74a9 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -8,29 +8,28 @@
* Copyright (C) 2020, Google, Inc.
*/
-#define _GNU_SOURCE /* for program_invocation_name */
-
#include <stdio.h>
#include <stdlib.h>
-#include <unistd.h>
#include <time.h>
#include <pthread.h>
#include <linux/bitmap.h>
-#include <linux/bitops.h>
#include "kvm_util.h"
-#include "perf_test_util.h"
-#include "processor.h"
#include "test_util.h"
+#include "perf_test_util.h"
+#include "guest_modes.h"
/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
#define TEST_HOST_LOOP_N 2UL
+static int nr_vcpus = 1;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+
/* Host variables */
static u64 dirty_log_manual_caps;
static bool host_quit;
static uint64_t iteration;
-static uint64_t vcpu_last_completed_iteration[MAX_VCPUS];
+static uint64_t vcpu_last_completed_iteration[KVM_MAX_VCPUS];
static void *vcpu_worker(void *data)
{
@@ -42,7 +41,7 @@ static void *vcpu_worker(void *data)
struct timespec ts_diff;
struct timespec total = (struct timespec){0};
struct timespec avg;
- struct vcpu_args *vcpu_args = (struct vcpu_args *)data;
+ struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
int vcpu_id = vcpu_args->vcpu_id;
vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
@@ -89,9 +88,15 @@ static void *vcpu_worker(void *data)
return NULL;
}
-static void run_test(enum vm_guest_mode mode, unsigned long iterations,
- uint64_t phys_offset, int wr_fract)
+struct test_params {
+ unsigned long iterations;
+ uint64_t phys_offset;
+ int wr_fract;
+};
+
+static void run_test(enum vm_guest_mode mode, void *arg)
{
+ struct test_params *p = arg;
pthread_t *vcpu_threads;
struct kvm_vm *vm;
unsigned long *bmap;
@@ -106,9 +111,9 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
struct kvm_enable_cap cap = {};
struct timespec clear_dirty_log_total = (struct timespec){0};
- vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size);
+ vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size);
- perf_test_args.wr_fract = wr_fract;
+ perf_test_args.wr_fract = p->wr_fract;
guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
@@ -124,7 +129,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
TEST_ASSERT(vcpu_threads, "Memory allocation failed");
- add_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
+ perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size);
sync_global_to_guest(vm, perf_test_args);
@@ -150,13 +155,13 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
/* Enable dirty logging */
clock_gettime(CLOCK_MONOTONIC, &start);
- vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX,
+ vm_mem_region_set_flags(vm, PERF_TEST_MEM_SLOT_INDEX,
KVM_MEM_LOG_DIRTY_PAGES);
ts_diff = timespec_diff_now(start);
pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
ts_diff.tv_sec, ts_diff.tv_nsec);
- while (iteration < iterations) {
+ while (iteration < p->iterations) {
/*
* Incrementing the iteration number will start the vCPUs
* dirtying memory again.
@@ -177,7 +182,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
iteration, ts_diff.tv_sec, ts_diff.tv_nsec);
clock_gettime(CLOCK_MONOTONIC, &start);
- kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+ kvm_vm_get_dirty_log(vm, PERF_TEST_MEM_SLOT_INDEX, bmap);
ts_diff = timespec_diff_now(start);
get_dirty_log_total = timespec_add(get_dirty_log_total,
@@ -187,7 +192,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
if (dirty_log_manual_caps) {
clock_gettime(CLOCK_MONOTONIC, &start);
- kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
+ kvm_vm_clear_dirty_log(vm, PERF_TEST_MEM_SLOT_INDEX, bmap, 0,
host_num_pages);
ts_diff = timespec_diff_now(start);
@@ -205,43 +210,30 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
/* Disable dirty logging */
clock_gettime(CLOCK_MONOTONIC, &start);
- vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0);
+ vm_mem_region_set_flags(vm, PERF_TEST_MEM_SLOT_INDEX, 0);
ts_diff = timespec_diff_now(start);
pr_info("Disabling dirty logging time: %ld.%.9lds\n",
ts_diff.tv_sec, ts_diff.tv_nsec);
- avg = timespec_div(get_dirty_log_total, iterations);
+ avg = timespec_div(get_dirty_log_total, p->iterations);
pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
- iterations, get_dirty_log_total.tv_sec,
+ p->iterations, get_dirty_log_total.tv_sec,
get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
if (dirty_log_manual_caps) {
- avg = timespec_div(clear_dirty_log_total, iterations);
+ avg = timespec_div(clear_dirty_log_total, p->iterations);
pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
- iterations, clear_dirty_log_total.tv_sec,
+ p->iterations, clear_dirty_log_total.tv_sec,
clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec);
}
free(bmap);
free(vcpu_threads);
- ucall_uninit(vm);
- kvm_vm_free(vm);
+ perf_test_destroy_vm(vm);
}
-struct guest_mode {
- bool supported;
- bool enabled;
-};
-static struct guest_mode guest_modes[NUM_VM_MODES];
-
-#define guest_mode_init(mode, supported, enabled) ({ \
- guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
-})
-
static void help(char *name)
{
- int i;
-
puts("");
printf("usage: %s [-h] [-i iterations] [-p offset] "
"[-m mode] [-b vcpu bytes] [-v vcpus]\n", name);
@@ -250,14 +242,7 @@ static void help(char *name)
TEST_HOST_LOOP_N);
printf(" -p: specify guest physical test memory offset\n"
" Warning: a low offset can conflict with the loaded test code.\n");
- printf(" -m: specify the guest mode ID to test "
- "(default: test all supported modes)\n"
- " This option may be used multiple times.\n"
- " Guest mode IDs:\n");
- for (i = 0; i < NUM_VM_MODES; ++i) {
- printf(" %d: %s%s\n", i, vm_guest_mode_string(i),
- guest_modes[i].supported ? " (supported)" : "");
- }
+ guest_modes_help();
printf(" -b: specify the size of the memory region which should be\n"
" dirtied by each vCPU. e.g. 10M or 3G.\n"
" (default: 1G)\n");
@@ -272,74 +257,43 @@ static void help(char *name)
int main(int argc, char *argv[])
{
- unsigned long iterations = TEST_HOST_LOOP_N;
- bool mode_selected = false;
- uint64_t phys_offset = 0;
- unsigned int mode;
- int opt, i;
- int wr_fract = 1;
+ int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+ struct test_params p = {
+ .iterations = TEST_HOST_LOOP_N,
+ .wr_fract = 1,
+ };
+ int opt;
dirty_log_manual_caps =
kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
KVM_DIRTY_LOG_INITIALLY_SET);
-#ifdef __x86_64__
- guest_mode_init(VM_MODE_PXXV48_4K, true, true);
-#endif
-#ifdef __aarch64__
- guest_mode_init(VM_MODE_P40V48_4K, true, true);
- guest_mode_init(VM_MODE_P40V48_64K, true, true);
-
- {
- unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
-
- if (limit >= 52)
- guest_mode_init(VM_MODE_P52V48_64K, true, true);
- if (limit >= 48) {
- guest_mode_init(VM_MODE_P48V48_4K, true, true);
- guest_mode_init(VM_MODE_P48V48_64K, true, true);
- }
- }
-#endif
-#ifdef __s390x__
- guest_mode_init(VM_MODE_P40V48_4K, true, true);
-#endif
+ guest_modes_append_default();
while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) {
switch (opt) {
case 'i':
- iterations = strtol(optarg, NULL, 10);
+ p.iterations = strtol(optarg, NULL, 10);
break;
case 'p':
- phys_offset = strtoull(optarg, NULL, 0);
+ p.phys_offset = strtoull(optarg, NULL, 0);
break;
case 'm':
- if (!mode_selected) {
- for (i = 0; i < NUM_VM_MODES; ++i)
- guest_modes[i].enabled = false;
- mode_selected = true;
- }
- mode = strtoul(optarg, NULL, 10);
- TEST_ASSERT(mode < NUM_VM_MODES,
- "Guest mode ID %d too big", mode);
- guest_modes[mode].enabled = true;
+ guest_modes_cmdline(optarg);
break;
case 'b':
guest_percpu_mem_size = parse_size(optarg);
break;
case 'f':
- wr_fract = atoi(optarg);
- TEST_ASSERT(wr_fract >= 1,
+ p.wr_fract = atoi(optarg);
+ TEST_ASSERT(p.wr_fract >= 1,
"Write fraction cannot be less than one");
break;
case 'v':
nr_vcpus = atoi(optarg);
- TEST_ASSERT(nr_vcpus > 0,
- "Must have a positive number of vCPUs");
- TEST_ASSERT(nr_vcpus <= MAX_VCPUS,
- "This test does not currently support\n"
- "more than %d vCPUs.", MAX_VCPUS);
+ TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
+ "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
break;
case 'h':
default:
@@ -348,18 +302,11 @@ int main(int argc, char *argv[])
}
}
- TEST_ASSERT(iterations >= 2, "The test should have at least two iterations");
+ TEST_ASSERT(p.iterations >= 2, "The test should have at least two iterations");
- pr_info("Test iterations: %"PRIu64"\n", iterations);
+ pr_info("Test iterations: %"PRIu64"\n", p.iterations);
- for (i = 0; i < NUM_VM_MODES; ++i) {
- if (!guest_modes[i].enabled)
- continue;
- TEST_ASSERT(guest_modes[i].supported,
- "Guest mode ID %d (%s) not supported.",
- i, vm_guest_mode_string(i));
- run_test(i, iterations, phys_offset, wr_fract);
- }
+ for_each_guest_mode(run_test, &p);
return 0;
}
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 471baecb7772..bb2752d78fe3 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -9,8 +9,6 @@
#include <stdio.h>
#include <stdlib.h>
-#include <unistd.h>
-#include <time.h>
#include <pthread.h>
#include <semaphore.h>
#include <sys/types.h>
@@ -20,8 +18,9 @@
#include <linux/bitops.h>
#include <asm/barrier.h>
-#include "test_util.h"
#include "kvm_util.h"
+#include "test_util.h"
+#include "guest_modes.h"
#include "processor.h"
#define VCPU_ID 1
@@ -673,9 +672,15 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
#define DIRTY_MEM_BITS 30 /* 1G */
#define PAGE_SHIFT_4K 12
-static void run_test(enum vm_guest_mode mode, unsigned long iterations,
- unsigned long interval, uint64_t phys_offset)
+struct test_params {
+ unsigned long iterations;
+ unsigned long interval;
+ uint64_t phys_offset;
+};
+
+static void run_test(enum vm_guest_mode mode, void *arg)
{
+ struct test_params *p = arg;
struct kvm_vm *vm;
unsigned long *bmap;
@@ -709,12 +714,12 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
host_page_size = getpagesize();
host_num_pages = vm_num_host_pages(mode, guest_num_pages);
- if (!phys_offset) {
+ if (!p->phys_offset) {
guest_test_phys_mem = (vm_get_max_gfn(vm) -
guest_num_pages) * guest_page_size;
guest_test_phys_mem &= ~(host_page_size - 1);
} else {
- guest_test_phys_mem = phys_offset;
+ guest_test_phys_mem = p->phys_offset;
}
#ifdef __s390x__
@@ -758,9 +763,9 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
- while (iteration < iterations) {
+ while (iteration < p->iterations) {
/* Give the vcpu thread some time to dirty some pages */
- usleep(interval * 1000);
+ usleep(p->interval * 1000);
log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
bmap, host_num_pages);
vm_dirty_log_verify(mode, bmap);
@@ -783,20 +788,8 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
kvm_vm_free(vm);
}
-struct guest_mode {
- bool supported;
- bool enabled;
-};
-static struct guest_mode guest_modes[NUM_VM_MODES];
-
-#define guest_mode_init(mode, supported, enabled) ({ \
- guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
-})
-
static void help(char *name)
{
- int i;
-
puts("");
printf("usage: %s [-h] [-i iterations] [-I interval] "
"[-p offset] [-m mode]\n", name);
@@ -813,51 +806,23 @@ static void help(char *name)
printf(" -M: specify the host logging mode "
"(default: run all log modes). Supported modes: \n\t");
log_modes_dump();
- printf(" -m: specify the guest mode ID to test "
- "(default: test all supported modes)\n"
- " This option may be used multiple times.\n"
- " Guest mode IDs:\n");
- for (i = 0; i < NUM_VM_MODES; ++i) {
- printf(" %d: %s%s\n", i, vm_guest_mode_string(i),
- guest_modes[i].supported ? " (supported)" : "");
- }
+ guest_modes_help();
puts("");
exit(0);
}
int main(int argc, char *argv[])
{
- unsigned long iterations = TEST_HOST_LOOP_N;
- unsigned long interval = TEST_HOST_LOOP_INTERVAL;
- bool mode_selected = false;
- uint64_t phys_offset = 0;
- unsigned int mode;
- int opt, i, j;
+ struct test_params p = {
+ .iterations = TEST_HOST_LOOP_N,
+ .interval = TEST_HOST_LOOP_INTERVAL,
+ };
+ int opt, i;
sem_init(&dirty_ring_vcpu_stop, 0, 0);
sem_init(&dirty_ring_vcpu_cont, 0, 0);
-#ifdef __x86_64__
- guest_mode_init(VM_MODE_PXXV48_4K, true, true);
-#endif
-#ifdef __aarch64__
- guest_mode_init(VM_MODE_P40V48_4K, true, true);
- guest_mode_init(VM_MODE_P40V48_64K, true, true);
-
- {
- unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
-
- if (limit >= 52)
- guest_mode_init(VM_MODE_P52V48_64K, true, true);
- if (limit >= 48) {
- guest_mode_init(VM_MODE_P48V48_4K, true, true);
- guest_mode_init(VM_MODE_P48V48_64K, true, true);
- }
- }
-#endif
-#ifdef __s390x__
- guest_mode_init(VM_MODE_P40V48_4K, true, true);
-#endif
+ guest_modes_append_default();
while ((opt = getopt(argc, argv, "c:hi:I:p:m:M:")) != -1) {
switch (opt) {
@@ -865,24 +830,16 @@ int main(int argc, char *argv[])
test_dirty_ring_count = strtol(optarg, NULL, 10);
break;
case 'i':
- iterations = strtol(optarg, NULL, 10);
+ p.iterations = strtol(optarg, NULL, 10);
break;
case 'I':
- interval = strtol(optarg, NULL, 10);
+ p.interval = strtol(optarg, NULL, 10);
break;
case 'p':
- phys_offset = strtoull(optarg, NULL, 0);
+ p.phys_offset = strtoull(optarg, NULL, 0);
break;
case 'm':
- if (!mode_selected) {
- for (i = 0; i < NUM_VM_MODES; ++i)
- guest_modes[i].enabled = false;
- mode_selected = true;
- }
- mode = strtoul(optarg, NULL, 10);
- TEST_ASSERT(mode < NUM_VM_MODES,
- "Guest mode ID %d too big", mode);
- guest_modes[mode].enabled = true;
+ guest_modes_cmdline(optarg);
break;
case 'M':
if (!strcmp(optarg, "all")) {
@@ -911,32 +868,24 @@ int main(int argc, char *argv[])
}
}
- TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
- TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+ TEST_ASSERT(p.iterations > 2, "Iterations must be greater than two");
+ TEST_ASSERT(p.interval > 0, "Interval must be greater than zero");
pr_info("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
- iterations, interval);
+ p.iterations, p.interval);
srandom(time(0));
- for (i = 0; i < NUM_VM_MODES; ++i) {
- if (!guest_modes[i].enabled)
- continue;
- TEST_ASSERT(guest_modes[i].supported,
- "Guest mode ID %d (%s) not supported.",
- i, vm_guest_mode_string(i));
- if (host_log_mode_option == LOG_MODE_ALL) {
- /* Run each log mode */
- for (j = 0; j < LOG_MODE_NUM; j++) {
- pr_info("Testing Log Mode '%s'\n",
- log_modes[j].name);
- host_log_mode = j;
- run_test(i, iterations, interval, phys_offset);
- }
- } else {
- host_log_mode = host_log_mode_option;
- run_test(i, iterations, interval, phys_offset);
+ if (host_log_mode_option == LOG_MODE_ALL) {
+ /* Run each log mode */
+ for (i = 0; i < LOG_MODE_NUM; i++) {
+ pr_info("Testing Log Mode '%s'\n", log_modes[i].name);
+ host_log_mode = i;
+ for_each_guest_mode(run_test, &p);
}
+ } else {
+ host_log_mode = host_log_mode_option;
+ for_each_guest_mode(run_test, &p);
}
return 0;
diff --git a/tools/testing/selftests/kvm/include/guest_modes.h b/tools/testing/selftests/kvm/include/guest_modes.h
new file mode 100644
index 000000000000..b691df33e64e
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/guest_modes.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include "kvm_util.h"
+
+struct guest_mode {
+ bool supported;
+ bool enabled;
+};
+
+extern struct guest_mode guest_modes[NUM_VM_MODES];
+
+#define guest_mode_append(mode, supported, enabled) ({ \
+ guest_modes[mode] = (struct guest_mode){ supported, enabled }; \
+})
+
+void guest_modes_append_default(void);
+void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg);
+void guest_modes_help(void);
+void guest_modes_cmdline(const char *arg);
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index dfa9d369e8fc..5cbb861525ed 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -16,6 +16,7 @@
#include "sparsebit.h"
+#define KVM_MAX_VCPUS 512
/*
* Callers of kvm_util only have an incomplete/opaque description of the
@@ -70,6 +71,14 @@ enum vm_guest_mode {
#define vm_guest_mode_string(m) vm_guest_mode_string[m]
extern const char * const vm_guest_mode_string[];
+struct vm_guest_mode_params {
+ unsigned int pa_bits;
+ unsigned int va_bits;
+ unsigned int page_size;
+ unsigned int page_shift;
+};
+extern const struct vm_guest_mode_params vm_guest_mode_params[];
+
enum vm_mem_backing_src_type {
VM_MEM_SRC_ANONYMOUS,
VM_MEM_SRC_ANONYMOUS_THP,
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 239421e4f6b8..b1188823c31b 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -9,38 +9,15 @@
#define SELFTEST_KVM_PERF_TEST_UTIL_H
#include "kvm_util.h"
-#include "processor.h"
-
-#define MAX_VCPUS 512
-
-#define PAGE_SHIFT_4K 12
-#define PTES_PER_4K_PT 512
-
-#define TEST_MEM_SLOT_INDEX 1
/* Default guest test virtual memory offset */
#define DEFAULT_GUEST_TEST_MEM 0xc0000000
#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-static uint64_t guest_test_phys_mem;
-
-/*
- * Guest virtual memory offset of the testing memory slot.
- * Must not conflict with identity mapped test code.
- */
-static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
-static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
-
-/* Number of VCPUs for the test */
-static int nr_vcpus = 1;
+#define PERF_TEST_MEM_SLOT_INDEX 1
-struct vcpu_args {
+struct perf_test_vcpu_args {
uint64_t gva;
uint64_t pages;
@@ -54,141 +31,21 @@ struct perf_test_args {
uint64_t guest_page_size;
int wr_fract;
- struct vcpu_args vcpu_args[MAX_VCPUS];
+ struct perf_test_vcpu_args vcpu_args[KVM_MAX_VCPUS];
};
-static struct perf_test_args perf_test_args;
+extern struct perf_test_args perf_test_args;
/*
- * Continuously write to the first 8 bytes of each page in the
- * specified region.
+ * Guest physical memory offset of the testing memory slot.
+ * This will be set to the topmost valid physical address minus
+ * the test memory size.
*/
-static void guest_code(uint32_t vcpu_id)
-{
- struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
- uint64_t gva;
- uint64_t pages;
- int i;
-
- /* Make sure vCPU args data structure is not corrupt. */
- GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
-
- gva = vcpu_args->gva;
- pages = vcpu_args->pages;
-
- while (true) {
- for (i = 0; i < pages; i++) {
- uint64_t addr = gva + (i * perf_test_args.guest_page_size);
-
- if (i % perf_test_args.wr_fract == 0)
- *(uint64_t *)addr = 0x0123456789ABCDEF;
- else
- READ_ONCE(*(uint64_t *)addr);
- }
-
- GUEST_SYNC(1);
- }
-}
-
-static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
- uint64_t vcpu_memory_bytes)
-{
- struct kvm_vm *vm;
- uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
- uint64_t guest_num_pages;
-
- /* Account for a few pages per-vCPU for stacks */
- pages += DEFAULT_STACK_PGS * vcpus;
-
- /*
- * Reserve twice the ammount of memory needed to map the test region and
- * the page table / stacks region, at 4k, for page tables. Do the
- * calculation with 4K page size: the smallest of all archs. (e.g., 64K
- * page size guest will need even less memory for page tables).
- */
- pages += (2 * pages) / PTES_PER_4K_PT;
- pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
- PTES_PER_4K_PT;
- pages = vm_adjust_num_guest_pages(mode, pages);
-
- pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
-
- vm = vm_create(mode, pages, O_RDWR);
- kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
-#ifdef __x86_64__
- vm_create_irqchip(vm);
-#endif
-
- perf_test_args.vm = vm;
- perf_test_args.guest_page_size = vm_get_page_size(vm);
- perf_test_args.host_page_size = getpagesize();
-
- TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
- "Guest memory size is not guest page size aligned.");
-
- guest_num_pages = (vcpus * vcpu_memory_bytes) /
- perf_test_args.guest_page_size;
- guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
-
- /*
- * If there should be more memory in the guest test region than there
- * can be pages in the guest, it will definitely cause problems.
- */
- TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
- "Requested more guest memory than address space allows.\n"
- " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
- guest_num_pages, vm_get_max_gfn(vm), vcpus,
- vcpu_memory_bytes);
-
- TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
- "Guest memory size is not host page size aligned.");
-
- guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
- perf_test_args.guest_page_size;
- guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
-
-#ifdef __s390x__
- /* Align to 1M (segment size) */
- guest_test_phys_mem &= ~((1 << 20) - 1);
-#endif
-
- pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
-
- /* Add an extra memory slot for testing */
- vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
- guest_test_phys_mem,
- TEST_MEM_SLOT_INDEX,
- guest_num_pages, 0);
-
- /* Do mapping for the demand paging memory slot */
- virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
-
- ucall_init(vm, NULL);
-
- return vm;
-}
-
-static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
-{
- vm_paddr_t vcpu_gpa;
- struct vcpu_args *vcpu_args;
- int vcpu_id;
-
- for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
- vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
-
- vm_vcpu_add_default(vm, vcpu_id, guest_code);
-
- vcpu_args->vcpu_id = vcpu_id;
- vcpu_args->gva = guest_test_virt_mem +
- (vcpu_id * vcpu_memory_bytes);
- vcpu_args->pages = vcpu_memory_bytes /
- perf_test_args.guest_page_size;
+extern uint64_t guest_test_phys_mem;
- vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
- pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
- vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
- }
-}
+struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
+ uint64_t vcpu_memory_bytes);
+void perf_test_destroy_vm(struct kvm_vm *vm);
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes);
#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
new file mode 100644
index 000000000000..25bff307c71f
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include "guest_modes.h"
+
+struct guest_mode guest_modes[NUM_VM_MODES];
+
+void guest_modes_append_default(void)
+{
+ guest_mode_append(VM_MODE_DEFAULT, true, true);
+
+#ifdef __aarch64__
+ guest_mode_append(VM_MODE_P40V48_64K, true, true);
+ {
+ unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+ if (limit >= 52)
+ guest_mode_append(VM_MODE_P52V48_64K, true, true);
+ if (limit >= 48) {
+ guest_mode_append(VM_MODE_P48V48_4K, true, true);
+ guest_mode_append(VM_MODE_P48V48_64K, true, true);
+ }
+ }
+#endif
+}
+
+void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)
+{
+ int i;
+
+ for (i = 0; i < NUM_VM_MODES; ++i) {
+ if (!guest_modes[i].enabled)
+ continue;
+ TEST_ASSERT(guest_modes[i].supported,
+ "Guest mode ID %d (%s) not supported.",
+ i, vm_guest_mode_string(i));
+ func(i, arg);
+ }
+}
+
+void guest_modes_help(void)
+{
+ int i;
+
+ printf(" -m: specify the guest mode ID to test\n"
+ " (default: test all supported modes)\n"
+ " This option may be used multiple times.\n"
+ " Guest mode IDs:\n");
+ for (i = 0; i < NUM_VM_MODES; ++i) {
+ printf(" %d: %s%s\n", i, vm_guest_mode_string(i),
+ guest_modes[i].supported ? " (supported)" : "");
+ }
+}
+
+void guest_modes_cmdline(const char *arg)
+{
+ static bool mode_selected;
+ unsigned int mode;
+ int i;
+
+ if (!mode_selected) {
+ for (i = 0; i < NUM_VM_MODES; ++i)
+ guest_modes[i].enabled = false;
+ mode_selected = true;
+ }
+
+ mode = strtoul(optarg, NULL, 10);
+ TEST_ASSERT(mode < NUM_VM_MODES, "Guest mode ID %d too big", mode);
+ guest_modes[mode].enabled = true;
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 88ef7067f1e6..fa5a90e6c6f0 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -153,14 +153,7 @@ const char * const vm_guest_mode_string[] = {
_Static_assert(sizeof(vm_guest_mode_string)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
-struct vm_guest_mode_params {
- unsigned int pa_bits;
- unsigned int va_bits;
- unsigned int page_size;
- unsigned int page_shift;
-};
-
-static const struct vm_guest_mode_params vm_guest_mode_params[] = {
+const struct vm_guest_mode_params vm_guest_mode_params[] = {
{ 52, 48, 0x1000, 12 },
{ 52, 48, 0x10000, 16 },
{ 48, 48, 0x1000, 12 },
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
new file mode 100644
index 000000000000..9be1944c2d1c
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#include "kvm_util.h"
+#include "perf_test_util.h"
+#include "processor.h"
+
+struct perf_test_args perf_test_args;
+
+uint64_t guest_test_phys_mem;
+
+/*
+ * Guest virtual memory offset of the testing memory slot.
+ * Must not conflict with identity mapped test code.
+ */
+static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
+
+/*
+ * Continuously write to the first 8 bytes of each page in the
+ * specified region.
+ */
+static void guest_code(uint32_t vcpu_id)
+{
+ struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+ uint64_t gva;
+ uint64_t pages;
+ int i;
+
+ /* Make sure vCPU args data structure is not corrupt. */
+ GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
+
+ gva = vcpu_args->gva;
+ pages = vcpu_args->pages;
+
+ while (true) {
+ for (i = 0; i < pages; i++) {
+ uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+
+ if (i % perf_test_args.wr_fract == 0)
+ *(uint64_t *)addr = 0x0123456789ABCDEF;
+ else
+ READ_ONCE(*(uint64_t *)addr);
+ }
+
+ GUEST_SYNC(1);
+ }
+}
+
+struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
+ uint64_t vcpu_memory_bytes)
+{
+ struct kvm_vm *vm;
+ uint64_t guest_num_pages;
+
+ pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
+ perf_test_args.host_page_size = getpagesize();
+ perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
+
+ guest_num_pages = vm_adjust_num_guest_pages(mode,
+ (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size);
+
+ TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+ "Guest memory size is not host page size aligned.");
+ TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+ "Guest memory size is not guest page size aligned.");
+
+ vm = vm_create_with_vcpus(mode, vcpus,
+ (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
+ 0, guest_code, NULL);
+
+ perf_test_args.vm = vm;
+
+ /*
+ * If there should be more memory in the guest test region than there
+ * can be pages in the guest, it will definitely cause problems.
+ */
+ TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+ "Requested more guest memory than address space allows.\n"
+ " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+ guest_num_pages, vm_get_max_gfn(vm), vcpus,
+ vcpu_memory_bytes);
+
+ guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+ perf_test_args.guest_page_size;
+ guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+#ifdef __s390x__
+ /* Align to 1M (segment size) */
+ guest_test_phys_mem &= ~((1 << 20) - 1);
+#endif
+ pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+
+ /* Add an extra memory slot for testing */
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ guest_test_phys_mem,
+ PERF_TEST_MEM_SLOT_INDEX,
+ guest_num_pages, 0);
+
+ /* Do mapping for the demand paging memory slot */
+ virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+
+ ucall_init(vm, NULL);
+
+ return vm;
+}
+
+void perf_test_destroy_vm(struct kvm_vm *vm)
+{
+ ucall_uninit(vm);
+ kvm_vm_free(vm);
+}
+
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
+{
+ vm_paddr_t vcpu_gpa;
+ struct perf_test_vcpu_args *vcpu_args;
+ int vcpu_id;
+
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+ vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+
+ vcpu_args->vcpu_id = vcpu_id;
+ vcpu_args->gva = guest_test_virt_mem +
+ (vcpu_id * vcpu_memory_bytes);
+ vcpu_args->pages = vcpu_memory_bytes /
+ perf_test_args.guest_page_size;
+
+ vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
+ pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+ vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+ }
+}
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index eb693a3b7b4a..4c7d33618437 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -869,7 +869,7 @@ ipv6_torture()
pid3=$!
ip netns exec me ping -f 2001:db8:101::2 >/dev/null 2>&1 &
pid4=$!
- ip netns exec me mausezahn veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
+ ip netns exec me mausezahn -6 veth1 -B 2001:db8:101::2 -A 2001:db8:91::1 -c 0 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1 &
pid5=$!
sleep 300
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 464e31eabc73..64cd2e23c568 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -162,7 +162,15 @@
# - list_flush_ipv6_exception
# Using the same topology as in pmtu_ipv6, create exceptions, and check
# they are shown when listing exception caches, gone after flushing them
-
+#
+# - pmtu_ipv4_route_change
+# Use the same topology as in pmtu_ipv4, but issue a route replacement
+# command and delete the corresponding device afterward. This tests for
+# proper cleanup of the PMTU exceptions by the route replacement path.
+# Device unregistration should complete successfully
+#
+# - pmtu_ipv6_route_change
+# Same as above but with IPv6
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
@@ -224,7 +232,9 @@ tests="
cleanup_ipv4_exception ipv4: cleanup of cached exceptions 1
cleanup_ipv6_exception ipv6: cleanup of cached exceptions 1
list_flush_ipv4_exception ipv4: list and flush cached exceptions 1
- list_flush_ipv6_exception ipv6: list and flush cached exceptions 1"
+ list_flush_ipv6_exception ipv6: list and flush cached exceptions 1
+ pmtu_ipv4_route_change ipv4: PMTU exception w/route replace 1
+ pmtu_ipv6_route_change ipv6: PMTU exception w/route replace 1"
NS_A="ns-A"
NS_B="ns-B"
@@ -1782,6 +1792,63 @@ test_list_flush_ipv6_exception() {
return ${fail}
}
+test_pmtu_ipvX_route_change() {
+ family=${1}
+
+ setup namespaces routing || return 2
+ trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
+ "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \
+ "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \
+ "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2
+
+ if [ ${family} -eq 4 ]; then
+ ping=ping
+ dst1="${prefix4}.${b_r1}.1"
+ dst2="${prefix4}.${b_r2}.1"
+ gw="${prefix4}.${a_r1}.2"
+ else
+ ping=${ping6}
+ dst1="${prefix6}:${b_r1}::1"
+ dst2="${prefix6}:${b_r2}::1"
+ gw="${prefix6}:${a_r1}::2"
+ fi
+
+ # Set up initial MTU values
+ mtu "${ns_a}" veth_A-R1 2000
+ mtu "${ns_r1}" veth_R1-A 2000
+ mtu "${ns_r1}" veth_R1-B 1400
+ mtu "${ns_b}" veth_B-R1 1400
+
+ mtu "${ns_a}" veth_A-R2 2000
+ mtu "${ns_r2}" veth_R2-A 2000
+ mtu "${ns_r2}" veth_R2-B 1500
+ mtu "${ns_b}" veth_B-R2 1500
+
+ # Create route exceptions
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1}
+ run_cmd ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2}
+
+ # Check that exceptions have been created with the correct PMTU
+ pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+ check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
+ pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+ check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
+
+ # Replace the route from A to R1
+ run_cmd ${ns_a} ip route change default via ${gw}
+
+ # Delete the device in A
+ run_cmd ${ns_a} ip link del "veth_A-R1"
+}
+
+test_pmtu_ipv4_route_change() {
+ test_pmtu_ipvX_route_change 4
+}
+
+test_pmtu_ipv6_route_change() {
+ test_pmtu_ipvX_route_change 6
+}
+
usage() {
echo
echo "$0 [OPTIONS] [TEST]..."
diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index ac2a30be9b32..f8a19f548ae9 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -5,6 +5,14 @@
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+# set global exit status, but never reset nonzero one.
+check_err()
+{
+ if [ $ret -eq 0 ]; then
+ ret=$1
+ fi
+}
+
cleanup() {
local -r jobs="$(jobs -p)"
local -r ns="$(ip netns list|grep $PEER_NS)"
@@ -44,7 +52,9 @@ run_one() {
# Hack: let bg programs complete the startup
sleep 0.1
./udpgso_bench_tx ${tx_args}
+ ret=$?
wait $(jobs -p)
+ return $ret
}
run_test() {
@@ -87,8 +97,10 @@ run_one_nat() {
sleep 0.1
./udpgso_bench_tx ${tx_args}
+ ret=$?
kill -INT $pid
wait $(jobs -p)
+ return $ret
}
run_one_2sock() {
@@ -110,7 +122,9 @@ run_one_2sock() {
sleep 0.1
# first UDP GSO socket should be closed at this point
./udpgso_bench_tx ${tx_args}
+ ret=$?
wait $(jobs -p)
+ return $ret
}
run_nat_test() {
@@ -131,36 +145,54 @@ run_all() {
local -r core_args="-l 4"
local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+ ret=0
echo "ipv4"
run_test "no GRO" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400"
+ check_err $?
# explicitly check we are not receiving UDP_SEGMENT cmsg (-S -1)
# when GRO does not take place
run_test "no GRO chk cmsg" "${ipv4_args} -M 10 -s 1400" "-4 -n 10 -l 1400 -S -1"
+ check_err $?
# the GSO packets are aggregated because:
# * veth schedule napi after each xmit
# * segmentation happens in BH context, veth napi poll is delayed after
# the transmission of the last segment
run_test "GRO" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720"
+ check_err $?
run_test "GRO chk cmsg" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+ check_err $?
run_test "GRO with custom segment size" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720"
+ check_err $?
run_test "GRO with custom segment size cmsg" "${ipv4_args} -M 1 -s 14720 -S 500 " "-4 -n 1 -l 14720 -S 500"
+ check_err $?
run_nat_test "bad GRO lookup" "${ipv4_args} -M 1 -s 14720 -S 0" "-n 10 -l 1472"
+ check_err $?
run_2sock_test "multiple GRO socks" "${ipv4_args} -M 1 -s 14720 -S 0 " "-4 -n 1 -l 14720 -S 1472"
+ check_err $?
echo "ipv6"
run_test "no GRO" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400"
+ check_err $?
run_test "no GRO chk cmsg" "${ipv6_args} -M 10 -s 1400" "-n 10 -l 1400 -S -1"
+ check_err $?
run_test "GRO" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520"
+ check_err $?
run_test "GRO chk cmsg" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 1 -l 14520 -S 1452"
+ check_err $?
run_test "GRO with custom segment size" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520"
+ check_err $?
run_test "GRO with custom segment size cmsg" "${ipv6_args} -M 1 -s 14520 -S 500" "-n 1 -l 14520 -S 500"
+ check_err $?
run_nat_test "bad GRO lookup" "${ipv6_args} -M 1 -s 14520 -S 0" "-n 10 -l 1452"
+ check_err $?
run_2sock_test "multiple GRO socks" "${ipv6_args} -M 1 -s 14520 -S 0 " "-n 1 -l 14520 -S 1452"
+ check_err $?
+ return $ret
}
if [ ! -f ../bpf/xdp_dummy.o ]; then
@@ -180,3 +212,5 @@ elif [[ $1 == "__subprocess_2sock" ]]; then
shift
run_one_2sock $@
fi
+
+exit $?
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index a374e10ef506..3006a8e5b41a 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -4,7 +4,8 @@
TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
nft_concat_range.sh nft_conntrack_helper.sh \
- nft_queue.sh nft_meta.sh
+ nft_queue.sh nft_meta.sh \
+ ipip-conntrack-mtu.sh
LDLIBS = -lmnl
TEST_GEN_FILES = nf-queue
diff --git a/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh b/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh
new file mode 100755
index 000000000000..4a6f5c3b3215
--- /dev/null
+++ b/tools/testing/selftests/netfilter/ipip-conntrack-mtu.sh
@@ -0,0 +1,206 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# Conntrack needs to reassemble fragments in order to have complete
+# packets for rule matching. Reassembly can lead to packet loss.
+
+# Consider the following setup:
+# +--------+ +---------+ +--------+
+# |Router A|-------|Wanrouter|-------|Router B|
+# | |.IPIP..| |..IPIP.| |
+# +--------+ +---------+ +--------+
+# / mtu 1400 \
+# / \
+#+--------+ +--------+
+#|Client A| |Client B|
+#| | | |
+#+--------+ +--------+
+
+# Router A and Router B use IPIP tunnel interfaces to tunnel traffic
+# between Client A and Client B over WAN. Wanrouter has MTU 1400 set
+# on its interfaces.
+
+rnd=$(mktemp -u XXXXXXXX)
+rx=$(mktemp)
+
+r_a="ns-ra-$rnd"
+r_b="ns-rb-$rnd"
+r_w="ns-rw-$rnd"
+c_a="ns-ca-$rnd"
+c_b="ns-cb-$rnd"
+
+checktool (){
+ if ! $1 > /dev/null 2>&1; then
+ echo "SKIP: Could not $2"
+ exit $ksft_skip
+ fi
+}
+
+checktool "iptables --version" "run test without iptables"
+checktool "ip -Version" "run test without ip tool"
+checktool "which nc" "run test without nc (netcat)"
+checktool "ip netns add ${r_a}" "create net namespace"
+
+for n in ${r_b} ${r_w} ${c_a} ${c_b};do
+ ip netns add ${n}
+done
+
+cleanup() {
+ for n in ${r_a} ${r_b} ${r_w} ${c_a} ${c_b};do
+ ip netns del ${n}
+ done
+ rm -f ${rx}
+}
+
+trap cleanup EXIT
+
+test_path() {
+ msg="$1"
+
+ ip netns exec ${c_b} nc -n -w 3 -q 3 -u -l -p 5000 > ${rx} < /dev/null &
+
+ sleep 1
+ for i in 1 2 3; do
+ head -c1400 /dev/zero | tr "\000" "a" | ip netns exec ${c_a} nc -n -w 1 -u 192.168.20.2 5000
+ done
+
+ wait
+
+ bytes=$(wc -c < ${rx})
+
+ if [ $bytes -eq 1400 ];then
+ echo "OK: PMTU $msg connection tracking"
+ else
+ echo "FAIL: PMTU $msg connection tracking: got $bytes, expected 1400"
+ exit 1
+ fi
+}
+
+# Detailed setup for Router A
+# ---------------------------
+# Interfaces:
+# eth0: 10.2.2.1/24
+# eth1: 192.168.10.1/24
+# ipip0: No IP address, local 10.2.2.1 remote 10.4.4.1
+# Routes:
+# 192.168.20.0/24 dev ipip0 (192.168.20.0/24 is subnet of Client B)
+# 10.4.4.1 via 10.2.2.254 (Router B via Wanrouter)
+# No iptables rules at all.
+
+ip link add veth0 netns ${r_a} type veth peer name veth0 netns ${r_w}
+ip link add veth1 netns ${r_a} type veth peer name veth0 netns ${c_a}
+
+l_addr="10.2.2.1"
+r_addr="10.4.4.1"
+ip netns exec ${r_a} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip
+
+for dev in lo veth0 veth1 ipip0; do
+ ip -net ${r_a} link set $dev up
+done
+
+ip -net ${r_a} addr add 10.2.2.1/24 dev veth0
+ip -net ${r_a} addr add 192.168.10.1/24 dev veth1
+
+ip -net ${r_a} route add 192.168.20.0/24 dev ipip0
+ip -net ${r_a} route add 10.4.4.0/24 via 10.2.2.254
+
+ip netns exec ${r_a} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Detailed setup for Router B
+# ---------------------------
+# Interfaces:
+# eth0: 10.4.4.1/24
+# eth1: 192.168.20.1/24
+# ipip0: No IP address, local 10.4.4.1 remote 10.2.2.1
+# Routes:
+# 192.168.10.0/24 dev ipip0 (192.168.10.0/24 is subnet of Client A)
+# 10.2.2.1 via 10.4.4.254 (Router A via Wanrouter)
+# No iptables rules at all.
+
+ip link add veth0 netns ${r_b} type veth peer name veth1 netns ${r_w}
+ip link add veth1 netns ${r_b} type veth peer name veth0 netns ${c_b}
+
+l_addr="10.4.4.1"
+r_addr="10.2.2.1"
+
+ip netns exec ${r_b} ip link add ipip0 type ipip local ${l_addr} remote ${r_addr} mode ipip || exit $ksft_skip
+
+for dev in lo veth0 veth1 ipip0; do
+ ip -net ${r_b} link set $dev up
+done
+
+ip -net ${r_b} addr add 10.4.4.1/24 dev veth0
+ip -net ${r_b} addr add 192.168.20.1/24 dev veth1
+
+ip -net ${r_b} route add 192.168.10.0/24 dev ipip0
+ip -net ${r_b} route add 10.2.2.0/24 via 10.4.4.254
+ip netns exec ${r_b} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Client A
+ip -net ${c_a} addr add 192.168.10.2/24 dev veth0
+ip -net ${c_a} link set dev lo up
+ip -net ${c_a} link set dev veth0 up
+ip -net ${c_a} route add default via 192.168.10.1
+
+# Client A
+ip -net ${c_b} addr add 192.168.20.2/24 dev veth0
+ip -net ${c_b} link set dev veth0 up
+ip -net ${c_b} link set dev lo up
+ip -net ${c_b} route add default via 192.168.20.1
+
+# Wan
+ip -net ${r_w} addr add 10.2.2.254/24 dev veth0
+ip -net ${r_w} addr add 10.4.4.254/24 dev veth1
+
+ip -net ${r_w} link set dev lo up
+ip -net ${r_w} link set dev veth0 up mtu 1400
+ip -net ${r_w} link set dev veth1 up mtu 1400
+
+ip -net ${r_a} link set dev veth0 mtu 1400
+ip -net ${r_b} link set dev veth0 mtu 1400
+
+ip netns exec ${r_w} sysctl -q net.ipv4.conf.all.forwarding=1 > /dev/null
+
+# Path MTU discovery
+# ------------------
+# Running tracepath from Client A to Client B shows PMTU discovery is working
+# as expected:
+#
+# clienta:~# tracepath 192.168.20.2
+# 1?: [LOCALHOST] pmtu 1500
+# 1: 192.168.10.1 0.867ms
+# 1: 192.168.10.1 0.302ms
+# 2: 192.168.10.1 0.312ms pmtu 1480
+# 2: no reply
+# 3: 192.168.10.1 0.510ms pmtu 1380
+# 3: 192.168.20.2 2.320ms reached
+# Resume: pmtu 1380 hops 3 back 3
+
+# ip netns exec ${c_a} traceroute --mtu 192.168.20.2
+
+# Router A has learned PMTU (1400) to Router B from Wanrouter.
+# Client A has learned PMTU (1400 - IPIP overhead = 1380) to Client B
+# from Router A.
+
+#Send large UDP packet
+#---------------------
+#Now we send a 1400 bytes UDP packet from Client A to Client B:
+
+# clienta:~# head -c1400 /dev/zero | tr "\000" "a" | nc -u 192.168.20.2 5000
+test_path "without"
+
+# The IPv4 stack on Client A already knows the PMTU to Client B, so the
+# UDP packet is sent as two fragments (1380 + 20). Router A forwards the
+# fragments between eth1 and ipip0. The fragments fit into the tunnel and
+# reach their destination.
+
+#When sending the large UDP packet again, Router A now reassembles the
+#fragments before routing the packet over ipip0. The resulting IPIP
+#packet is too big (1400) for the tunnel PMTU (1380) to Router B, it is
+#dropped on Router A before sending.
+
+ip netns exec ${r_a} iptables -A FORWARD -m conntrack --ctstate NEW
+test_path "with"
diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config
index b50c2085c1ac..fe07d97df9fa 100644
--- a/tools/testing/selftests/wireguard/qemu/debug.config
+++ b/tools/testing/selftests/wireguard/qemu/debug.config
@@ -1,5 +1,4 @@
CONFIG_LOCALVERSION="-debug"
-CONFIG_ENABLE_MUST_CHECK=y
CONFIG_FRAME_POINTER=y
CONFIG_STACK_VALIDATION=y
CONFIG_DEBUG_KERNEL=y