diff options
Diffstat (limited to 'tools/testing/selftests/net')
51 files changed, 3916 insertions, 98 deletions
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index c6dd2a335cf4..47c293c2962f 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -34,6 +34,7 @@ reuseport_bpf_numa reuseport_dualstack rxtimestamp sctp_hello +scm_inq scm_pidfd scm_rights sk_bind_sendto_listen diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 332f387615d7..b31a71f2b372 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -41,6 +41,7 @@ TEST_PROGS += netns-name.sh TEST_PROGS += link_netns.py TEST_PROGS += nl_netdev.py TEST_PROGS += rtnetlink.py +TEST_PROGS += rtnetlink_notification.sh TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh @@ -62,6 +63,7 @@ TEST_PROGS += ip_local_port_range.sh TEST_PROGS += rps_default_mask.sh TEST_PROGS += big_tcp.sh TEST_PROGS += netns-sysctl.sh +TEST_PROGS += netdev-l2addr.sh TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh xfrm_policy_add_speed.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any @@ -99,6 +101,7 @@ TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh +TEST_PROGS += test_neigh.sh TEST_PROGS += fdb_flush.sh fdb_notify.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh @@ -112,6 +115,8 @@ TEST_PROGS += skf_net_off.sh TEST_GEN_FILES += skf_net_off TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh +TEST_PROGS += broadcast_pmtu.sh +TEST_PROGS += ipv6_force_forwarding.sh # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := busy_poller netlink-dumps diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 50584479540b..a4b61c6d0290 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,4 +1,4 @@ CFLAGS += $(KHDR_INCLUDES) -TEST_GEN_PROGS := diag_uid msg_oob scm_pidfd scm_rights unix_connect +TEST_GEN_PROGS := diag_uid msg_oob scm_inq scm_pidfd scm_rights unix_connect include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/scm_inq.c b/tools/testing/selftests/net/af_unix/scm_inq.c new file mode 100644 index 000000000000..9d22561e7b8f --- /dev/null +++ b/tools/testing/selftests/net/af_unix/scm_inq.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2025 Google LLC */ + +#include <linux/sockios.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/types.h> + +#include "../../kselftest_harness.h" + +#define NR_CHUNKS 100 +#define MSG_LEN 256 + +struct scm_inq { + struct cmsghdr cmsghdr; + int inq; +}; + +FIXTURE(scm_inq) +{ + int fd[2]; +}; + +FIXTURE_VARIANT(scm_inq) +{ + int type; +}; + +FIXTURE_VARIANT_ADD(scm_inq, stream) +{ + .type = SOCK_STREAM, +}; + +FIXTURE_VARIANT_ADD(scm_inq, dgram) +{ + .type = SOCK_DGRAM, +}; + +FIXTURE_VARIANT_ADD(scm_inq, seqpacket) +{ + .type = SOCK_SEQPACKET, +}; + +FIXTURE_SETUP(scm_inq) +{ + int err; + + err = socketpair(AF_UNIX, variant->type | SOCK_NONBLOCK, 0, self->fd); + ASSERT_EQ(0, err); +} + +FIXTURE_TEARDOWN(scm_inq) +{ + close(self->fd[0]); + close(self->fd[1]); +} + +static void send_chunks(struct __test_metadata *_metadata, + FIXTURE_DATA(scm_inq) *self) +{ + char buf[MSG_LEN] = {}; + int i, ret; + + for (i = 0; i < NR_CHUNKS; i++) { + ret = send(self->fd[0], buf, sizeof(buf), 0); + ASSERT_EQ(sizeof(buf), ret); + } +} + +static void recv_chunks(struct __test_metadata *_metadata, + FIXTURE_DATA(scm_inq) *self) +{ + struct msghdr msg = {}; + struct iovec iov = {}; + struct scm_inq cmsg; + char buf[MSG_LEN]; + int i, ret; + int inq; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = &cmsg; + msg.msg_controllen = CMSG_SPACE(sizeof(cmsg.inq)); + + iov.iov_base = buf; + iov.iov_len = sizeof(buf); + + for (i = 0; i < NR_CHUNKS; i++) { + memset(buf, 0, sizeof(buf)); + memset(&cmsg, 0, sizeof(cmsg)); + + ret = recvmsg(self->fd[1], &msg, 0); + ASSERT_EQ(MSG_LEN, ret); + ASSERT_NE(NULL, CMSG_FIRSTHDR(&msg)); + ASSERT_EQ(CMSG_LEN(sizeof(cmsg.inq)), cmsg.cmsghdr.cmsg_len); + ASSERT_EQ(SOL_SOCKET, cmsg.cmsghdr.cmsg_level); + ASSERT_EQ(SCM_INQ, cmsg.cmsghdr.cmsg_type); + + ret = ioctl(self->fd[1], SIOCINQ, &inq); + ASSERT_EQ(0, ret); + ASSERT_EQ(cmsg.inq, inq); + } +} + +TEST_F(scm_inq, basic) +{ + int err, inq; + + err = setsockopt(self->fd[1], SOL_SOCKET, SO_INQ, &(int){1}, sizeof(int)); + if (variant->type != SOCK_STREAM) { + ASSERT_EQ(-ENOPROTOOPT, -errno); + return; + } + + ASSERT_EQ(0, err); + + err = ioctl(self->fd[1], SIOCINQ, &inq); + ASSERT_EQ(0, err); + ASSERT_EQ(0, inq); + + send_chunks(_metadata, self); + recv_chunks(_metadata, self); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/bench/Makefile b/tools/testing/selftests/net/bench/Makefile new file mode 100644 index 000000000000..2546c45e42f7 --- /dev/null +++ b/tools/testing/selftests/net/bench/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +TEST_GEN_MODS_DIR := page_pool + +TEST_PROGS += test_bench_page_pool.sh + +include ../../lib.mk diff --git a/tools/testing/selftests/net/bench/page_pool/Makefile b/tools/testing/selftests/net/bench/page_pool/Makefile new file mode 100644 index 000000000000..0549a16ba275 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/Makefile @@ -0,0 +1,17 @@ +BENCH_PAGE_POOL_SIMPLE_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= /lib/modules/$(shell uname -r)/build + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +obj-m += bench_page_pool.o +bench_page_pool-y += bench_page_pool_simple.o time_bench.o + +all: + +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) clean diff --git a/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c new file mode 100644 index 000000000000..cb6468adbda4 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c @@ -0,0 +1,267 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Benchmark module for page_pool. + * + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/interrupt.h> +#include <linux/limits.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <net/page_pool/helpers.h> + +#include "time_bench.h" + +static int verbose = 1; +#define MY_POOL_SIZE 1024 + +/* Makes tests selectable. Useful for perf-record to analyze a single test. + * Hint: Bash shells support writing binary number like: $((2#101010) + * + * # modprobe bench_page_pool_simple run_flags=$((2#100)) + */ +static unsigned long run_flags = 0xFFFFFFFF; +module_param(run_flags, ulong, 0); +MODULE_PARM_DESC(run_flags, "Limit which bench test that runs"); + +/* Count the bit number from the enum */ +enum benchmark_bit { + bit_run_bench_baseline, + bit_run_bench_no_softirq01, + bit_run_bench_no_softirq02, + bit_run_bench_no_softirq03, +}; + +#define bit(b) (1 << (b)) +#define enabled(b) ((run_flags & (bit(b)))) + +/* notice time_bench is limited to U32_MAX nr loops */ +static unsigned long loops = 10000000; +module_param(loops, ulong, 0); +MODULE_PARM_DESC(loops, "Specify loops bench will run"); + +/* Timing at the nanosec level, we need to know the overhead + * introduced by the for loop itself + */ +static int time_bench_for_loop(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + int i; + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + } + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +static int time_bench_atomic_inc(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + atomic_t cnt; + int i; + + atomic_set(&cnt, 0); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + atomic_inc(&cnt); + barrier(); /* avoid compiler to optimize this loop */ + } + loops_cnt = atomic_read(&cnt); + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +/* The ptr_ping in page_pool uses a spinlock. We need to know the minimum + * overhead of taking+releasing a spinlock, to know the cycles that can be saved + * by e.g. amortizing this via bulking. + */ +static int time_bench_lock(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + spinlock_t lock; + int i; + + spin_lock_init(&lock); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + spin_lock(&lock); + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + spin_unlock(&lock); + } + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +/* Helper for filling some page's into ptr_ring */ +static void pp_fill_ptr_ring(struct page_pool *pp, int elems) +{ + /* GFP_ATOMIC needed when under run softirq */ + gfp_t gfp_mask = GFP_ATOMIC; + struct page **array; + int i; + + array = kcalloc(elems, sizeof(struct page *), gfp_mask); + + for (i = 0; i < elems; i++) + array[i] = page_pool_alloc_pages(pp, gfp_mask); + for (i = 0; i < elems; i++) + page_pool_put_page(pp, array[i], -1, false); + + kfree(array); +} + +enum test_type { type_fast_path, type_ptr_ring, type_page_allocator }; + +/* Depends on compile optimizing this function */ +static int time_bench_page_pool(struct time_bench_record *rec, void *data, + enum test_type type, const char *func) +{ + uint64_t loops_cnt = 0; + gfp_t gfp_mask = GFP_ATOMIC; /* GFP_ATOMIC is not really needed */ + int i, err; + + struct page_pool *pp; + struct page *page; + + struct page_pool_params pp_params = { + .order = 0, + .flags = 0, + .pool_size = MY_POOL_SIZE, + .nid = NUMA_NO_NODE, + .dev = NULL, /* Only use for DMA mapping */ + .dma_dir = DMA_BIDIRECTIONAL, + }; + + pp = page_pool_create(&pp_params); + if (IS_ERR(pp)) { + err = PTR_ERR(pp); + pr_warn("%s: Error(%d) creating page_pool\n", func, err); + goto out; + } + pp_fill_ptr_ring(pp, 64); + + if (in_serving_softirq()) + pr_warn("%s(): in_serving_softirq fast-path\n", func); + else + pr_warn("%s(): Cannot use page_pool fast-path\n", func); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + /* Common fast-path alloc that depend on in_serving_softirq() */ + page = page_pool_alloc_pages(pp, gfp_mask); + if (!page) + break; + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + + /* The benchmarks purpose it to test different return paths. + * Compiler should inline optimize other function calls out + */ + if (type == type_fast_path) { + /* Fast-path recycling e.g. XDP_DROP use-case */ + page_pool_recycle_direct(pp, page); + + } else if (type == type_ptr_ring) { + /* Normal return path */ + page_pool_put_page(pp, page, -1, false); + + } else if (type == type_page_allocator) { + /* Test if not pages are recycled, but instead + * returned back into systems page allocator + */ + get_page(page); /* cause no-recycling */ + page_pool_put_page(pp, page, -1, false); + put_page(page); + } else { + BUILD_BUG(); + } + } + time_bench_stop(rec, loops_cnt); +out: + page_pool_destroy(pp); + return loops_cnt; +} + +static int time_bench_page_pool01_fast_path(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_fast_path, __func__); +} + +static int time_bench_page_pool02_ptr_ring(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_ptr_ring, __func__); +} + +static int time_bench_page_pool03_slow(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_page_allocator, __func__); +} + +static int run_benchmark_tests(void) +{ + uint32_t nr_loops = loops; + + /* Baseline tests */ + if (enabled(bit_run_bench_baseline)) { + time_bench_loop(nr_loops * 10, 0, "for_loop", NULL, + time_bench_for_loop); + time_bench_loop(nr_loops * 10, 0, "atomic_inc", NULL, + time_bench_atomic_inc); + time_bench_loop(nr_loops, 0, "lock", NULL, time_bench_lock); + } + + /* This test cannot activate correct code path, due to no-softirq ctx */ + if (enabled(bit_run_bench_no_softirq01)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool01", NULL, + time_bench_page_pool01_fast_path); + if (enabled(bit_run_bench_no_softirq02)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool02", NULL, + time_bench_page_pool02_ptr_ring); + if (enabled(bit_run_bench_no_softirq03)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool03", NULL, + time_bench_page_pool03_slow); + + return 0; +} + +static int __init bench_page_pool_simple_module_init(void) +{ + if (verbose) + pr_info("Loaded\n"); + + if (loops > U32_MAX) { + pr_err("Module param loops(%lu) exceeded U32_MAX(%u)\n", loops, + U32_MAX); + return -ECHRNG; + } + + run_benchmark_tests(); + + return 0; +} +module_init(bench_page_pool_simple_module_init); + +static void __exit bench_page_pool_simple_module_exit(void) +{ + if (verbose) + pr_info("Unloaded\n"); +} +module_exit(bench_page_pool_simple_module_exit); + +MODULE_DESCRIPTION("Benchmark of page_pool simple cases"); +MODULE_AUTHOR("Jesper Dangaard Brouer <netoptimizer@brouer.com>"); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.c b/tools/testing/selftests/net/bench/page_pool/time_bench.c new file mode 100644 index 000000000000..073bb36ec5f2 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/time_bench.c @@ -0,0 +1,394 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Benchmarking code execution time inside the kernel + * + * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/time.h> + +#include <linux/perf_event.h> /* perf_event_create_kernel_counter() */ + +/* For concurrency testing */ +#include <linux/completion.h> +#include <linux/sched.h> +#include <linux/workqueue.h> +#include <linux/kthread.h> + +#include "time_bench.h" + +static int verbose = 1; + +/** TSC (Time-Stamp Counter) based ** + * See: linux/time_bench.h + * tsc_start_clock() and tsc_stop_clock() + */ + +/** Wall-clock based ** + */ + +/** PMU (Performance Monitor Unit) based ** + */ +#define PERF_FORMAT \ + (PERF_FORMAT_GROUP | PERF_FORMAT_ID | PERF_FORMAT_TOTAL_TIME_ENABLED | \ + PERF_FORMAT_TOTAL_TIME_RUNNING) + +struct raw_perf_event { + uint64_t config; /* event */ + uint64_t config1; /* umask */ + struct perf_event *save; + char *desc; +}; + +/* if HT is enable a maximum of 4 events (5 if one is instructions + * retired can be specified, if HT is disabled a maximum of 8 (9 if + * one is instructions retired) can be specified. + * + * From Table 19-1. Architectural Performance Events + * Architectures Software Developer’s Manual Volume 3: System Programming + * Guide + */ +struct raw_perf_event perf_events[] = { + { 0x3c, 0x00, NULL, "Unhalted CPU Cycles" }, + { 0xc0, 0x00, NULL, "Instruction Retired" } +}; + +#define NUM_EVTS (ARRAY_SIZE(perf_events)) + +/* WARNING: PMU config is currently broken! + */ +bool time_bench_PMU_config(bool enable) +{ + int i; + struct perf_event_attr perf_conf; + struct perf_event *perf_event; + int cpu; + + preempt_disable(); + cpu = smp_processor_id(); + pr_info("DEBUG: cpu:%d\n", cpu); + preempt_enable(); + + memset(&perf_conf, 0, sizeof(struct perf_event_attr)); + perf_conf.type = PERF_TYPE_RAW; + perf_conf.size = sizeof(struct perf_event_attr); + perf_conf.read_format = PERF_FORMAT; + perf_conf.pinned = 1; + perf_conf.exclude_user = 1; /* No userspace events */ + perf_conf.exclude_kernel = 0; /* Only kernel events */ + + for (i = 0; i < NUM_EVTS; i++) { + perf_conf.disabled = enable; + //perf_conf.disabled = (i == 0) ? 1 : 0; + perf_conf.config = perf_events[i].config; + perf_conf.config1 = perf_events[i].config1; + if (verbose) + pr_info("%s() enable PMU counter: %s\n", + __func__, perf_events[i].desc); + perf_event = perf_event_create_kernel_counter(&perf_conf, cpu, + NULL /* task */, + NULL /* overflow_handler*/, + NULL /* context */); + if (perf_event) { + perf_events[i].save = perf_event; + pr_info("%s():DEBUG perf_event success\n", __func__); + + perf_event_enable(perf_event); + } else { + pr_info("%s():DEBUG perf_event is NULL\n", __func__); + } + } + + return true; +} + +/** Generic functions ** + */ + +/* Calculate stats, store results in record */ +bool time_bench_calc_stats(struct time_bench_record *rec) +{ +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ + uint64_t ns_per_call_tmp_rem = 0; + uint32_t ns_per_call_remainder = 0; + uint64_t pmc_ipc_tmp_rem = 0; + uint32_t pmc_ipc_remainder = 0; + uint32_t pmc_ipc_div = 0; + uint32_t invoked_cnt_precision = 0; + uint32_t invoked_cnt = 0; /* 32-bit due to div_u64_rem() */ + + if (rec->flags & TIME_BENCH_LOOP) { + if (rec->invoked_cnt < 1000) { + pr_err("ERR: need more(>1000) loops(%llu) for timing\n", + rec->invoked_cnt); + return false; + } + if (rec->invoked_cnt > ((1ULL << 32) - 1)) { + /* div_u64_rem() can only support div with 32bit*/ + pr_err("ERR: Invoke cnt(%llu) too big overflow 32bit\n", + rec->invoked_cnt); + return false; + } + invoked_cnt = (uint32_t)rec->invoked_cnt; + } + + /* TSC (Time-Stamp Counter) records */ + if (rec->flags & TIME_BENCH_TSC) { + rec->tsc_interval = rec->tsc_stop - rec->tsc_start; + if (rec->tsc_interval == 0) { + pr_err("ABORT: timing took ZERO TSC time\n"); + return false; + } + /* Calculate stats */ + if (rec->flags & TIME_BENCH_LOOP) + rec->tsc_cycles = rec->tsc_interval / invoked_cnt; + else + rec->tsc_cycles = rec->tsc_interval; + } + + /* Wall-clock time calc */ + if (rec->flags & TIME_BENCH_WALLCLOCK) { + rec->time_start = rec->ts_start.tv_nsec + + (NANOSEC_PER_SEC * rec->ts_start.tv_sec); + rec->time_stop = rec->ts_stop.tv_nsec + + (NANOSEC_PER_SEC * rec->ts_stop.tv_sec); + rec->time_interval = rec->time_stop - rec->time_start; + if (rec->time_interval == 0) { + pr_err("ABORT: timing took ZERO wallclock time\n"); + return false; + } + /* Calculate stats */ + /*** Division in kernel it tricky ***/ + /* Orig: time_sec = (time_interval / NANOSEC_PER_SEC); */ + /* remainder only correct because NANOSEC_PER_SEC is 10^9 */ + rec->time_sec = div_u64_rem(rec->time_interval, NANOSEC_PER_SEC, + &rec->time_sec_remainder); + //TODO: use existing struct timespec records instead of div? + + if (rec->flags & TIME_BENCH_LOOP) { + /*** Division in kernel it tricky ***/ + /* Orig: ns = ((double)time_interval / invoked_cnt); */ + /* First get quotient */ + rec->ns_per_call_quotient = + div_u64_rem(rec->time_interval, invoked_cnt, + &ns_per_call_remainder); + /* Now get decimals .xxx precision (incorrect roundup)*/ + ns_per_call_tmp_rem = ns_per_call_remainder; + invoked_cnt_precision = invoked_cnt / 1000; + if (invoked_cnt_precision > 0) { + rec->ns_per_call_decimal = + div_u64_rem(ns_per_call_tmp_rem, + invoked_cnt_precision, + &ns_per_call_remainder); + } + } + } + + /* Performance Monitor Unit (PMU) counters */ + if (rec->flags & TIME_BENCH_PMU) { + //FIXME: Overflow handling??? + rec->pmc_inst = rec->pmc_inst_stop - rec->pmc_inst_start; + rec->pmc_clk = rec->pmc_clk_stop - rec->pmc_clk_start; + + /* Calc Instruction Per Cycle (IPC) */ + /* First get quotient */ + rec->pmc_ipc_quotient = div_u64_rem(rec->pmc_inst, rec->pmc_clk, + &pmc_ipc_remainder); + /* Now get decimals .xxx precision (incorrect roundup)*/ + pmc_ipc_tmp_rem = pmc_ipc_remainder; + pmc_ipc_div = rec->pmc_clk / 1000; + if (pmc_ipc_div > 0) { + rec->pmc_ipc_decimal = div_u64_rem(pmc_ipc_tmp_rem, + pmc_ipc_div, + &pmc_ipc_remainder); + } + } + + return true; +} + +/* Generic function for invoking a loop function and calculating + * execution time stats. The function being called/timed is assumed + * to perform a tight loop, and update the timing record struct. + */ +bool time_bench_loop(uint32_t loops, int step, char *txt, void *data, + int (*func)(struct time_bench_record *record, void *data)) +{ + struct time_bench_record rec; + + /* Setup record */ + memset(&rec, 0, sizeof(rec)); /* zero func might not update all */ + rec.version_abi = 1; + rec.loops = loops; + rec.step = step; + rec.flags = (TIME_BENCH_LOOP | TIME_BENCH_TSC | TIME_BENCH_WALLCLOCK); + + /*** Loop function being timed ***/ + if (!func(&rec, data)) { + pr_err("ABORT: function being timed failed\n"); + return false; + } + + if (rec.invoked_cnt < loops) + pr_warn("WARNING: Invoke count(%llu) smaller than loops(%d)\n", + rec.invoked_cnt, loops); + + /* Calculate stats */ + time_bench_calc_stats(&rec); + + pr_info("Type:%s Per elem: %llu cycles(tsc) %llu.%03llu ns (step:%d) - (measurement period time:%llu.%09u sec time_interval:%llu) - (invoke count:%llu tsc_interval:%llu)\n", + txt, rec.tsc_cycles, rec.ns_per_call_quotient, + rec.ns_per_call_decimal, rec.step, rec.time_sec, + rec.time_sec_remainder, rec.time_interval, rec.invoked_cnt, + rec.tsc_interval); + if (rec.flags & TIME_BENCH_PMU) + pr_info("Type:%s PMU inst/clock%llu/%llu = %llu.%03llu IPC (inst per cycle)\n", + txt, rec.pmc_inst, rec.pmc_clk, rec.pmc_ipc_quotient, + rec.pmc_ipc_decimal); + return true; +} + +/* Function getting invoked by kthread */ +static int invoke_test_on_cpu_func(void *private) +{ + struct time_bench_cpu *cpu = private; + struct time_bench_sync *sync = cpu->sync; + cpumask_t newmask = CPU_MASK_NONE; + void *data = cpu->data; + + /* Restrict CPU */ + cpumask_set_cpu(cpu->rec.cpu, &newmask); + set_cpus_allowed_ptr(current, &newmask); + + /* Synchronize start of concurrency test */ + atomic_inc(&sync->nr_tests_running); + wait_for_completion(&sync->start_event); + + /* Start benchmark function */ + if (!cpu->bench_func(&cpu->rec, data)) { + pr_err("ERROR: function being timed failed on CPU:%d(%d)\n", + cpu->rec.cpu, smp_processor_id()); + } else { + if (verbose) + pr_info("SUCCESS: ran on CPU:%d(%d)\n", cpu->rec.cpu, + smp_processor_id()); + } + cpu->did_bench_run = true; + + /* End test */ + atomic_dec(&sync->nr_tests_running); + /* Wait for kthread_stop() telling us to stop */ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void time_bench_print_stats_cpumask(const char *desc, + struct time_bench_cpu *cpu_tasks, + const struct cpumask *mask) +{ + uint64_t average = 0; + int cpu; + int step = 0; + struct sum { + uint64_t tsc_cycles; + int records; + } sum = { 0 }; + + /* Get stats */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + struct time_bench_record *rec = &c->rec; + + /* Calculate stats */ + time_bench_calc_stats(rec); + + pr_info("Type:%s CPU(%d) %llu cycles(tsc) %llu.%03llu ns (step:%d) - (measurement period time:%llu.%09u sec time_interval:%llu) - (invoke count:%llu tsc_interval:%llu)\n", + desc, cpu, rec->tsc_cycles, rec->ns_per_call_quotient, + rec->ns_per_call_decimal, rec->step, rec->time_sec, + rec->time_sec_remainder, rec->time_interval, + rec->invoked_cnt, rec->tsc_interval); + + /* Collect average */ + sum.records++; + sum.tsc_cycles += rec->tsc_cycles; + step = rec->step; + } + + if (sum.records) /* avoid div-by-zero */ + average = sum.tsc_cycles / sum.records; + pr_info("Sum Type:%s Average: %llu cycles(tsc) CPUs:%d step:%d\n", desc, + average, sum.records, step); +} + +void time_bench_run_concurrent(uint32_t loops, int step, void *data, + const struct cpumask *mask, /* Support masking outsome CPUs*/ + struct time_bench_sync *sync, + struct time_bench_cpu *cpu_tasks, + int (*func)(struct time_bench_record *record, void *data)) +{ + int cpu, running = 0; + + if (verbose) // DEBUG + pr_warn("%s() Started on CPU:%d\n", __func__, + smp_processor_id()); + + /* Reset sync conditions */ + atomic_set(&sync->nr_tests_running, 0); + init_completion(&sync->start_event); + + /* Spawn off jobs on all CPUs */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + + running++; + c->sync = sync; /* Send sync variable along */ + c->data = data; /* Send opaque along */ + + /* Init benchmark record */ + memset(&c->rec, 0, sizeof(struct time_bench_record)); + c->rec.version_abi = 1; + c->rec.loops = loops; + c->rec.step = step; + c->rec.flags = (TIME_BENCH_LOOP | TIME_BENCH_TSC | + TIME_BENCH_WALLCLOCK); + c->rec.cpu = cpu; + c->bench_func = func; + c->task = kthread_run(invoke_test_on_cpu_func, c, + "time_bench%d", cpu); + if (IS_ERR(c->task)) { + pr_err("%s(): Failed to start test func\n", __func__); + return; /* Argh, what about cleanup?! */ + } + } + + /* Wait until all processes are running */ + while (atomic_read(&sync->nr_tests_running) < running) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + /* Kick off all CPU concurrently on completion event */ + complete_all(&sync->start_event); + + /* Wait for CPUs to finish */ + while (atomic_read(&sync->nr_tests_running)) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + + /* Stop the kthreads */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + + kthread_stop(c->task); + } + + if (verbose) // DEBUG - happens often, finish on another CPU + pr_warn("%s() Finished on CPU:%d\n", __func__, + smp_processor_id()); +} diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.h b/tools/testing/selftests/net/bench/page_pool/time_bench.h new file mode 100644 index 000000000000..e113fcf341dc --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/time_bench.h @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Benchmarking code execution time inside the kernel + * + * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer + * for licensing details see kernel-base/COPYING + */ +#ifndef _LINUX_TIME_BENCH_H +#define _LINUX_TIME_BENCH_H + +/* Main structure used for recording a benchmark run */ +struct time_bench_record { + uint32_t version_abi; + uint32_t loops; /* Requested loop invocations */ + uint32_t step; /* option for e.g. bulk invocations */ + + uint32_t flags; /* Measurements types enabled */ +#define TIME_BENCH_LOOP BIT(0) +#define TIME_BENCH_TSC BIT(1) +#define TIME_BENCH_WALLCLOCK BIT(2) +#define TIME_BENCH_PMU BIT(3) + + uint32_t cpu; /* Used when embedded in time_bench_cpu */ + + /* Records */ + uint64_t invoked_cnt; /* Returned actual invocations */ + uint64_t tsc_start; + uint64_t tsc_stop; + struct timespec64 ts_start; + struct timespec64 ts_stop; + /* PMU counters for instruction and cycles + * instructions counter including pipelined instructions + */ + uint64_t pmc_inst_start; + uint64_t pmc_inst_stop; + /* CPU unhalted clock counter */ + uint64_t pmc_clk_start; + uint64_t pmc_clk_stop; + + /* Result records */ + uint64_t tsc_interval; + uint64_t time_start, time_stop, time_interval; /* in nanosec */ + uint64_t pmc_inst, pmc_clk; + + /* Derived result records */ + uint64_t tsc_cycles; // +decimal? + uint64_t ns_per_call_quotient, ns_per_call_decimal; + uint64_t time_sec; + uint32_t time_sec_remainder; + uint64_t pmc_ipc_quotient, pmc_ipc_decimal; /* inst per cycle */ +}; + +/* For synchronizing parallel CPUs to run concurrently */ +struct time_bench_sync { + atomic_t nr_tests_running; + struct completion start_event; +}; + +/* Keep track of CPUs executing our bench function. + * + * Embed a time_bench_record for storing info per cpu + */ +struct time_bench_cpu { + struct time_bench_record rec; + struct time_bench_sync *sync; /* back ptr */ + struct task_struct *task; + /* "data" opaque could have been placed in time_bench_sync, + * but to avoid any false sharing, place it per CPU + */ + void *data; + /* Support masking outsome CPUs, mark if it ran */ + bool did_bench_run; + /* int cpu; // note CPU stored in time_bench_record */ + int (*bench_func)(struct time_bench_record *record, void *data); +}; + +/* + * Below TSC assembler code is not compatible with other archs, and + * can also fail on guests if cpu-flags are not correct. + * + * The way TSC reading is used, many iterations, does not require as + * high accuracy as described below (in Intel Doc #324264). + * + * Considering changing to use get_cycles() (#include <asm/timex.h>). + */ + +/** TSC (Time-Stamp Counter) based ** + * Recommend reading, to understand details of reading TSC accurately: + * Intel Doc #324264, "How to Benchmark Code Execution Times on Intel" + * + * Consider getting exclusive ownership of CPU by using: + * unsigned long flags; + * preempt_disable(); + * raw_local_irq_save(flags); + * _your_code_ + * raw_local_irq_restore(flags); + * preempt_enable(); + * + * Clobbered registers: "%rax", "%rbx", "%rcx", "%rdx" + * RDTSC only change "%rax" and "%rdx" but + * CPUID clears the high 32-bits of all (rax/rbx/rcx/rdx) + */ +static __always_inline uint64_t tsc_start_clock(void) +{ + /* See: Intel Doc #324264 */ + unsigned int hi, lo; + + asm volatile("CPUID\n\t" + "RDTSC\n\t" + "mov %%edx, %0\n\t" + "mov %%eax, %1\n\t" + : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx"); + //FIXME: on 32bit use clobbered %eax + %edx + return ((uint64_t)lo) | (((uint64_t)hi) << 32); +} + +static __always_inline uint64_t tsc_stop_clock(void) +{ + /* See: Intel Doc #324264 */ + unsigned int hi, lo; + + asm volatile("RDTSCP\n\t" + "mov %%edx, %0\n\t" + "mov %%eax, %1\n\t" + "CPUID\n\t" + : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx"); + return ((uint64_t)lo) | (((uint64_t)hi) << 32); +} + +/** Wall-clock based ** + * + * use: getnstimeofday() + * getnstimeofday(&rec->ts_start); + * getnstimeofday(&rec->ts_stop); + * + * API changed see: Documentation/core-api/timekeeping.rst + * https://www.kernel.org/doc/html/latest/core-api/timekeeping.html#c.getnstimeofday + * + * We should instead use: ktime_get_real_ts64() is a direct + * replacement, but consider using monotonic time (ktime_get_ts64()) + * and/or a ktime_t based interface (ktime_get()/ktime_get_real()). + */ + +/** PMU (Performance Monitor Unit) based ** + * + * Needed for calculating: Instructions Per Cycle (IPC) + * - The IPC number tell how efficient the CPU pipelining were + */ +//lookup: perf_event_create_kernel_counter() + +bool time_bench_PMU_config(bool enable); + +/* Raw reading via rdpmc() using fixed counters + * + * From: https://github.com/andikleen/simple-pmu + */ +enum { + FIXED_SELECT = (1U << 30), /* == 0x40000000 */ + FIXED_INST_RETIRED_ANY = 0, + FIXED_CPU_CLK_UNHALTED_CORE = 1, + FIXED_CPU_CLK_UNHALTED_REF = 2, +}; + +static __always_inline unsigned int long long p_rdpmc(unsigned int in) +{ + unsigned int d, a; + + asm volatile("rdpmc" : "=d"(d), "=a"(a) : "c"(in) : "memory"); + return ((unsigned long long)d << 32) | a; +} + +/* These PMU counter needs to be enabled, but I don't have the + * configure code implemented. My current hack is running: + * sudo perf stat -e cycles:k -e instructions:k insmod lib/ring_queue_test.ko + */ +/* Reading all pipelined instruction */ +static __always_inline unsigned long long pmc_inst(void) +{ + return p_rdpmc(FIXED_SELECT | FIXED_INST_RETIRED_ANY); +} + +/* Reading CPU clock cycles */ +static __always_inline unsigned long long pmc_clk(void) +{ + return p_rdpmc(FIXED_SELECT | FIXED_CPU_CLK_UNHALTED_CORE); +} + +/* Raw reading via MSR rdmsr() is likely wrong + * FIXME: How can I know which raw MSR registers are conf for what? + */ +#define MSR_IA32_PCM0 0x400000C1 /* PERFCTR0 */ +#define MSR_IA32_PCM1 0x400000C2 /* PERFCTR1 */ +#define MSR_IA32_PCM2 0x400000C3 +static inline uint64_t msr_inst(unsigned long long *msr_result) +{ + return rdmsrq_safe(MSR_IA32_PCM0, msr_result); +} + +/** Generic functions ** + */ +bool time_bench_loop(uint32_t loops, int step, char *txt, void *data, + int (*func)(struct time_bench_record *rec, void *data)); +bool time_bench_calc_stats(struct time_bench_record *rec); + +void time_bench_run_concurrent(uint32_t loops, int step, void *data, + const struct cpumask *mask, /* Support masking outsome CPUs*/ + struct time_bench_sync *sync, struct time_bench_cpu *cpu_tasks, + int (*func)(struct time_bench_record *record, void *data)); +void time_bench_print_stats_cpumask(const char *desc, + struct time_bench_cpu *cpu_tasks, + const struct cpumask *mask); + +//FIXME: use rec->flags to select measurement, should be MACRO +static __always_inline void time_bench_start(struct time_bench_record *rec) +{ + //getnstimeofday(&rec->ts_start); + ktime_get_real_ts64(&rec->ts_start); + if (rec->flags & TIME_BENCH_PMU) { + rec->pmc_inst_start = pmc_inst(); + rec->pmc_clk_start = pmc_clk(); + } + rec->tsc_start = tsc_start_clock(); +} + +static __always_inline void time_bench_stop(struct time_bench_record *rec, + uint64_t invoked_cnt) +{ + rec->tsc_stop = tsc_stop_clock(); + if (rec->flags & TIME_BENCH_PMU) { + rec->pmc_inst_stop = pmc_inst(); + rec->pmc_clk_stop = pmc_clk(); + } + //getnstimeofday(&rec->ts_stop); + ktime_get_real_ts64(&rec->ts_stop); + rec->invoked_cnt = invoked_cnt; +} + +#endif /* _LINUX_TIME_BENCH_H */ diff --git a/tools/testing/selftests/net/bench/test_bench_page_pool.sh b/tools/testing/selftests/net/bench/test_bench_page_pool.sh new file mode 100755 index 000000000000..7b8b18cfedce --- /dev/null +++ b/tools/testing/selftests/net/bench/test_bench_page_pool.sh @@ -0,0 +1,32 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# + +set -e + +DRIVER="./page_pool/bench_page_pool.ko" +result="" + +function run_test() +{ + rmmod "bench_page_pool.ko" || true + insmod $DRIVER > /dev/null 2>&1 + result=$(dmesg | tail -10) + echo "$result" + + echo + echo "Fast path results:" + echo "${result}" | grep -o -E "no-softirq-page_pool01 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns" + + echo + echo "ptr_ring results:" + echo "${result}" | grep -o -E "no-softirq-page_pool02 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns" + + echo + echo "slow path results:" + echo "${result}" | grep -o -E "no-softirq-page_pool03 Per elem: ([0-9]+) cycles\(tsc\) ([0-9]+\.[0-9]+) ns" +} + +run_test + +exit 0 diff --git a/tools/testing/selftests/net/broadcast_pmtu.sh b/tools/testing/selftests/net/broadcast_pmtu.sh new file mode 100755 index 000000000000..726eb5d25839 --- /dev/null +++ b/tools/testing/selftests/net/broadcast_pmtu.sh @@ -0,0 +1,47 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Ensures broadcast route MTU is respected + +CLIENT_NS=$(mktemp -u client-XXXXXXXX) +CLIENT_IP4="192.168.0.1/24" +CLIENT_BROADCAST_ADDRESS="192.168.0.255" + +SERVER_NS=$(mktemp -u server-XXXXXXXX) +SERVER_IP4="192.168.0.2/24" + +setup() { + ip netns add "${CLIENT_NS}" + ip netns add "${SERVER_NS}" + + ip -net "${SERVER_NS}" link add link1 type veth peer name link0 netns "${CLIENT_NS}" + + ip -net "${CLIENT_NS}" link set link0 up + ip -net "${CLIENT_NS}" link set link0 mtu 9000 + ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}" dev link0 + + ip -net "${SERVER_NS}" link set link1 up + ip -net "${SERVER_NS}" link set link1 mtu 1500 + ip -net "${SERVER_NS}" addr add "${SERVER_IP4}" dev link1 + + read -r -a CLIENT_BROADCAST_ENTRY <<< "$(ip -net "${CLIENT_NS}" route show table local type broadcast)" + ip -net "${CLIENT_NS}" route del "${CLIENT_BROADCAST_ENTRY[@]}" + ip -net "${CLIENT_NS}" route add "${CLIENT_BROADCAST_ENTRY[@]}" mtu 1500 + + ip net exec "${SERVER_NS}" sysctl -wq net.ipv4.icmp_echo_ignore_broadcasts=0 +} + +cleanup() { + ip -net "${SERVER_NS}" link del link1 + ip netns del "${CLIENT_NS}" + ip netns del "${SERVER_NS}" +} + +trap cleanup EXIT + +setup && + echo "Testing for broadcast route MTU" && + ip net exec "${CLIENT_NS}" ping -f -M want -q -c 1 -s 8000 -w 1 -b "${CLIENT_BROADCAST_ADDRESS}" > /dev/null 2>&1 + +exit $? + diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 3cfef5153823..c24417d0047b 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -30,16 +30,25 @@ CONFIG_NET_FOU=y CONFIG_NET_FOU_IP_TUNNELS=y CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NF_CONNTRACK=m CONFIG_IPV6_MROUTE=y CONFIG_IPV6_SIT=y CONFIG_NF_NAT=m CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_IPTABLES_LEGACY=m CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_IPTABLES_LEGACY=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_FILTER=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_RAW=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_NAT=m CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IPV6_GRE=m CONFIG_IPV6_SEG6_LWTUNNEL=y @@ -57,6 +66,8 @@ CONFIG_NF_TABLES_IPV6=y CONFIG_NF_TABLES_IPV4=y CONFIG_NFT_NAT=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m +CONFIG_NETFILTER_XT_TARGET_HL=m +CONFIG_NETFILTER_XT_NAT=m CONFIG_NET_ACT_CSUM=m CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_GACT=m diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 00bde7b6f39e..d7bb2e80e88c 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -102,6 +102,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \ vxlan_bridge_1d_port_8472.sh \ vxlan_bridge_1d.sh \ vxlan_bridge_1q_ipv6.sh \ + vxlan_bridge_1q_mc_ul.sh \ vxlan_bridge_1q_port_8472_ipv6.sh \ vxlan_bridge_1q_port_8472.sh \ vxlan_bridge_1q.sh \ diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 508f3c700d71..890b3374dacd 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -37,6 +37,7 @@ declare -A NETIFS=( : "${TEAMD:=teamd}" : "${MCD:=smcrouted}" : "${MC_CLI:=smcroutectl}" +: "${MCD_TABLE_NAME:=selftests}" # Constants for netdevice bring-up: # Default time in seconds to wait for an interface to come up before giving up @@ -141,6 +142,20 @@ check_tc_version() fi } +check_tc_erspan_support() +{ + local dev=$1; shift + + tc filter add dev $dev ingress pref 1 handle 1 flower \ + erspan_opts 1:0:0:0 &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: iproute2 too old; tc is missing erspan support" + return $ksft_skip + fi + tc filter del dev $dev ingress pref 1 handle 1 flower \ + erspan_opts 1:0:0:0 &> /dev/null +} + # Old versions of tc don't understand "mpls_uc" check_tc_mpls_support() { @@ -525,9 +540,9 @@ setup_wait_dev_with_timeout() return 1 } -setup_wait() +setup_wait_n() { - local num_netifs=${1:-$NUM_NETIFS} + local num_netifs=$1; shift local i for ((i = 1; i <= num_netifs; ++i)); do @@ -538,6 +553,11 @@ setup_wait() sleep $WAIT_TIME } +setup_wait() +{ + setup_wait_n "$NUM_NETIFS" +} + wait_for_dev() { local dev=$1; shift @@ -1757,6 +1777,51 @@ mc_send() msend -g $groups -I $if_name -c 1 > /dev/null 2>&1 } +adf_mcd_start() +{ + local ifs=("$@") + + local table_name="$MCD_TABLE_NAME" + local smcroutedir + local pid + local if + local i + + check_command "$MCD" || return 1 + check_command "$MC_CLI" || return 1 + + smcroutedir=$(mktemp -d) + defer rm -rf "$smcroutedir" + + for ((i = 1; i <= NUM_NETIFS; ++i)); do + echo "phyint ${NETIFS[p$i]} enable" >> \ + "$smcroutedir/$table_name.conf" + done + + for if in "${ifs[@]}"; do + if ! ip_link_has_flag "$if" MULTICAST; then + ip link set dev "$if" multicast on + defer ip link set dev "$if" multicast off + fi + + echo "phyint $if enable" >> \ + "$smcroutedir/$table_name.conf" + done + + "$MCD" -N -I "$table_name" -f "$smcroutedir/$table_name.conf" \ + -P "$smcroutedir/$table_name.pid" + busywait "$BUSYWAIT_TIMEOUT" test -e "$smcroutedir/$table_name.pid" + pid=$(cat "$smcroutedir/$table_name.pid") + defer kill_process "$pid" +} + +mc_cli() +{ + local table_name="$MCD_TABLE_NAME" + + "$MC_CLI" -I "$table_name" "$@" +} + start_ip_monitor() { local mtype=$1; shift diff --git a/tools/testing/selftests/net/forwarding/router_multicast.sh b/tools/testing/selftests/net/forwarding/router_multicast.sh index 5a58b1ec8aef..83e52abdbc2e 100755 --- a/tools/testing/selftests/net/forwarding/router_multicast.sh +++ b/tools/testing/selftests/net/forwarding/router_multicast.sh @@ -33,10 +33,6 @@ NUM_NETIFS=6 source lib.sh source tc_common.sh -require_command $MCD -require_command $MC_CLI -table_name=selftests - h1_create() { simple_if_init $h1 198.51.100.2/28 2001:db8:1::2/64 @@ -149,25 +145,6 @@ router_destroy() ip link set dev $rp1 down } -start_mcd() -{ - SMCROUTEDIR="$(mktemp -d)" - - for ((i = 1; i <= $NUM_NETIFS; ++i)); do - echo "phyint ${NETIFS[p$i]} enable" >> \ - $SMCROUTEDIR/$table_name.conf - done - - $MCD -N -I $table_name -f $SMCROUTEDIR/$table_name.conf \ - -P $SMCROUTEDIR/$table_name.pid -} - -kill_mcd() -{ - pkill $MCD - rm -rf $SMCROUTEDIR -} - setup_prepare() { h1=${NETIFS[p1]} @@ -179,7 +156,7 @@ setup_prepare() rp3=${NETIFS[p5]} h3=${NETIFS[p6]} - start_mcd + adf_mcd_start || exit "$EXIT_STATUS" vrf_prepare @@ -206,7 +183,7 @@ cleanup() vrf_cleanup - kill_mcd + defer_scopes_cleanup } create_mcast_sg() @@ -214,9 +191,9 @@ create_mcast_sg() local if_name=$1; shift local s_addr=$1; shift local mcast=$1; shift - local dest_ifs=${@} + local dest_ifs=("${@}") - $MC_CLI -I $table_name add $if_name $s_addr $mcast $dest_ifs + mc_cli add "$if_name" "$s_addr" "$mcast" "${dest_ifs[@]}" } delete_mcast_sg() @@ -224,9 +201,9 @@ delete_mcast_sg() local if_name=$1; shift local s_addr=$1; shift local mcast=$1; shift - local dest_ifs=${@} + local dest_ifs=("${@}") - $MC_CLI -I $table_name remove $if_name $s_addr $mcast $dest_ifs + mc_cli remove "$if_name" "$s_addr" "$mcast" "${dest_ifs[@]}" } mcast_v4() diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index b1daad19b01e..b58909a93112 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -6,7 +6,7 @@ ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \ match_ip_tos_test match_indev_test match_ip_ttl_test match_mpls_label_test \ match_mpls_tc_test match_mpls_bos_test match_mpls_ttl_test \ - match_mpls_lse_test" + match_mpls_lse_test match_erspan_opts_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -676,6 +676,56 @@ match_mpls_lse_test() log_test "mpls lse match ($tcflags)" } +match_erspan_opts_test() +{ + RET=0 + + check_tc_erspan_support $h2 || return 0 + + # h1 erspan setup + tunnel_create erspan1 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1001 \ + tos C ttl 64 erspan_ver 1 erspan 6789 # ERSPAN Type II + tunnel_create erspan2 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1002 \ + tos C ttl 64 erspan_ver 2 erspan_dir egress erspan_hwid 63 \ + # ERSPAN Type III + ip link set dev erspan1 master v$h1 + ip link set dev erspan2 master v$h1 + # h2 erspan setup + ip link add ep-ex type erspan ttl 64 external # To collect tunnel info + ip link set ep-ex up + ip link set dev ep-ex master v$h2 + tc qdisc add dev ep-ex clsact + + # ERSPAN Type II [decap direction] + tc filter add dev ep-ex ingress protocol ip handle 101 flower \ + $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \ + enc_key_id 1001 erspan_opts 1:6789:0:0 \ + action drop + # ERSPAN Type III [decap direction] + tc filter add dev ep-ex ingress protocol ip handle 102 flower \ + $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \ + enc_key_id 1002 erspan_opts 2:0:1:63 action drop + + ep1mac=$(mac_get erspan1) + $MZ erspan1 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q + tc_check_packets "dev ep-ex ingress" 101 1 + check_err $? "ERSPAN Type II" + + ep2mac=$(mac_get erspan2) + $MZ erspan2 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q + tc_check_packets "dev ep-ex ingress" 102 1 + check_err $? "ERSPAN Type III" + + # h2 erspan cleanup + tc qdisc del dev ep-ex clsact + tunnel_destroy ep-ex + # h1 erspan cleanup + tunnel_destroy erspan2 # ERSPAN Type III + tunnel_destroy erspan1 # ERSPAN Type II + + log_test "erspan_opts match ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh new file mode 100755 index 000000000000..462db0b603e7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q_mc_ul.sh @@ -0,0 +1,771 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------------------------+ +# | + $h1.10 + $h1.20 | +# | | 192.0.2.1/28 | 2001:db8:1::1/64 | +# | \________ ________/ | +# | \ / | +# | + $h1 H1 (vrf) | +# +-----------|-----------------------------+ +# | +# +-----------|----------------------------------------------------------------+ +# | +---------|--------------------------------------+ SWITCH (main vrf) | +# | | + $swp1 BR1 (802.1q) | | +# | | vid 10 20 | | +# | | | | +# | | + vx10 (vxlan) + vx20 (vxlan) | + lo10 (dummy) | +# | | local 192.0.2.100 local 2001:db8:4::1 | 192.0.2.100/28 | +# | | group 233.252.0.1 group ff0e::1:2:3 | 2001:db8:4::1/64 | +# | | id 1000 id 2000 | | +# | | vid 10 pvid untagged vid 20 pvid untagged | | +# | +------------------------------------------------+ | +# | | +# | + $swp2 $swp3 + | +# | | 192.0.2.33/28 192.0.2.65/28 | | +# | | 2001:db8:2::1/64 2001:db8:3::1/64 | | +# | | | | +# +---|--------------------------------------------------------------------|---+ +# | | +# +---|--------------------------------+ +--------------------------------|---+ +# | | H2 (vrf) | | H3 (vrf) | | +# | +-|----------------------------+ | | +-----------------------------|-+ | +# | | + $h2 BR2 (802.1d) | | | | BR3 (802.1d) $h3 + | | +# | | | | | | | | +# | | + v1$h2 (veth) | | | | v1$h3 (veth) + | | +# | +-|----------------------------+ | | +-----------------------------|-+ | +# | | | | | | +# +---|--------------------------------+ +--------------------------------|---+ +# | | +# +---|--------------------------------+ +--------------------------------|---+ +# | + v2$h2 (veth) NS2 (netns) | | NS3 (netns) v2$h3 (veth) + | +# | 192.0.2.34/28 | | 192.0.2.66/28 | +# | 2001:db8:2::2/64 | | 2001:db8:3::2/64 | +# | | | | +# | +--------------------------------+ | | +--------------------------------+ | +# | | BR1 (802.1q) | | | | BR1 (802.1q) | | +# | | + vx10 (vxlan) | | | | + vx10 (vxlan) | | +# | | local 192.0.2.34 | | | | local 192.0.2.50 | | +# | | group 233.252.0.1 dev v2$h2 | | | | group 233.252.0.1 dev v2$h3 | | +# | | id 1000 dstport $VXPORT | | | | id 1000 dstport $VXPORT | | +# | | vid 10 pvid untagged | | | | vid 10 pvid untagged | | +# | | | | | | | | +# | | + vx20 (vxlan) | | | | + vx20 (vxlan) | | +# | | local 2001:db8:2::2 | | | | local 2001:db8:3::2 | | +# | | group ff0e::1:2:3 dev v2$h2 | | | | group ff0e::1:2:3 dev v2$h3 | | +# | | id 2000 dstport $VXPORT | | | | id 2000 dstport $VXPORT | | +# | | vid 20 pvid untagged | | | | vid 20 pvid untagged | | +# | | | | | | | | +# | | + w1 (veth) | | | | + w1 (veth) | | +# | | | vid 10 20 | | | | | vid 10 20 | | +# | +--|-----------------------------+ | | +--|-----------------------------+ | +# | | | | | | +# | +--|-----------------------------+ | | +--|-----------------------------+ | +# | | + w2 (veth) VW2 (vrf) | | | | + w2 (veth) VW2 (vrf) | | +# | | |\ | | | | |\ | | +# | | | + w2.10 | | | | | + w2.10 | | +# | | | 192.0.2.3/28 | | | | | 192.0.2.4/28 | | +# | | | | | | | | | | +# | | + w2.20 | | | | + w2.20 | | +# | | 2001:db8:1::3/64 | | | | 2001:db8:1::4/64 | | +# | +--------------------------------+ | | +--------------------------------+ | +# +------------------------------------+ +------------------------------------+ +# +#shellcheck disable=SC2317 # SC doesn't see our uses of functions. + +: "${VXPORT:=4789}" +export VXPORT + +: "${GROUP4:=233.252.0.1}" +export GROUP4 + +: "${GROUP6:=ff0e::1:2:3}" +export GROUP6 + +: "${IPMR:=lo10}" + +ALL_TESTS=" + ipv4_nomcroute + ipv4_mcroute + ipv4_mcroute_changelink + ipv4_mcroute_starg + ipv4_mcroute_noroute + ipv4_mcroute_fdb + ipv4_mcroute_fdb_oif0 + ipv4_mcroute_fdb_oif0_sep + + ipv6_nomcroute + ipv6_mcroute + ipv6_mcroute_changelink + ipv6_mcroute_starg + ipv6_mcroute_noroute + ipv6_mcroute_fdb + ipv6_mcroute_fdb_oif0 + + ipv4_nomcroute_rx + ipv4_mcroute_rx + ipv4_mcroute_starg_rx + ipv4_mcroute_fdb_oif0_sep_rx + ipv4_mcroute_fdb_sep_rx + + ipv6_nomcroute_rx + ipv6_mcroute_rx + ipv6_mcroute_starg_rx + ipv6_mcroute_fdb_sep_rx +" + +NUM_NETIFS=6 +source lib.sh + +h1_create() +{ + simple_if_init "$h1" + defer simple_if_fini "$h1" + + ip_link_add "$h1.10" master "v$h1" link "$h1" type vlan id 10 + ip_link_set_up "$h1.10" + ip_addr_add "$h1.10" 192.0.2.1/28 + + ip_link_add "$h1.20" master "v$h1" link "$h1" type vlan id 20 + ip_link_set_up "$h1.20" + ip_addr_add "$h1.20" 2001:db8:1::1/64 +} + +install_capture() +{ + local dev=$1; shift + + tc qdisc add dev "$dev" clsact + defer tc qdisc del dev "$dev" clsact + + tc filter add dev "$dev" ingress proto ip pref 104 \ + flower skip_hw ip_proto udp dst_port "$VXPORT" \ + action pass + defer tc filter del dev "$dev" ingress proto ip pref 104 + + tc filter add dev "$dev" ingress proto ipv6 pref 106 \ + flower skip_hw ip_proto udp dst_port "$VXPORT" \ + action pass + defer tc filter del dev "$dev" ingress proto ipv6 pref 106 +} + +h2_create() +{ + # $h2 + ip_link_set_up "$h2" + + # H2 + vrf_create "v$h2" + defer vrf_destroy "v$h2" + + ip_link_set_up "v$h2" + + # br2 + ip_link_add br2 type bridge vlan_filtering 0 mcast_snooping 0 + ip_link_set_master br2 "v$h2" + ip_link_set_up br2 + + # $h2 + ip_link_set_master "$h2" br2 + install_capture "$h2" + + # v1$h2 + ip_link_set_up "v1$h2" + ip_link_set_master "v1$h2" br2 +} + +h3_create() +{ + # $h3 + ip_link_set_up "$h3" + + # H3 + vrf_create "v$h3" + defer vrf_destroy "v$h3" + + ip_link_set_up "v$h3" + + # br3 + ip_link_add br3 type bridge vlan_filtering 0 mcast_snooping 0 + ip_link_set_master br3 "v$h3" + ip_link_set_up br3 + + # $h3 + ip_link_set_master "$h3" br3 + install_capture "$h3" + + # v1$h3 + ip_link_set_up "v1$h3" + ip_link_set_master "v1$h3" br3 +} + +switch_create() +{ + local swp1_mac + + # br1 + swp1_mac=$(mac_get "$swp1") + ip_link_add br1 type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 0 + ip_link_set_addr br1 "$swp1_mac" + ip_link_set_up br1 + + # A dummy to force the IPv6 OIF=0 test to install a suitable MC route on + # $IPMR to be deterministic. Also used for the IPv6 RX!=TX ping test. + ip_link_add "X$IPMR" up type dummy + + # IPMR + ip_link_add "$IPMR" up type dummy + ip_addr_add "$IPMR" 192.0.2.100/28 + ip_addr_add "$IPMR" 2001:db8:4::1/64 + + # $swp1 + ip_link_set_up "$swp1" + ip_link_set_master "$swp1" br1 + bridge_vlan_add vid 10 dev "$swp1" + bridge_vlan_add vid 20 dev "$swp1" + + # $swp2 + ip_link_set_up "$swp2" + ip_addr_add "$swp2" 192.0.2.33/28 + ip_addr_add "$swp2" 2001:db8:2::1/64 + + # $swp3 + ip_link_set_up "$swp3" + ip_addr_add "$swp3" 192.0.2.65/28 + ip_addr_add "$swp3" 2001:db8:3::1/64 +} + +vx_create() +{ + local name=$1; shift + local vid=$1; shift + + ip_link_add "$name" up type vxlan dstport "$VXPORT" \ + nolearning noudpcsum tos inherit ttl 16 \ + "$@" + ip_link_set_master "$name" br1 + bridge_vlan_add vid "$vid" dev "$name" pvid untagged +} +export -f vx_create + +vx_wait() +{ + # Wait for all the ARP, IGMP etc. noise to settle down so that the + # tunnel is clear for measurements. + sleep 10 +} + +vx10_create() +{ + vx_create vx10 10 id 1000 "$@" +} +export -f vx10_create + +vx20_create() +{ + vx_create vx20 20 id 2000 "$@" +} +export -f vx20_create + +vx10_create_wait() +{ + vx10_create "$@" + vx_wait +} + +vx20_create_wait() +{ + vx20_create "$@" + vx_wait +} + +ns_init_common() +{ + local ns=$1; shift + local if_in=$1; shift + local ipv4_in=$1; shift + local ipv6_in=$1; shift + local ipv4_host=$1; shift + local ipv6_host=$1; shift + + # v2$h2 / v2$h3 + ip_link_set_up "$if_in" + ip_addr_add "$if_in" "$ipv4_in" + ip_addr_add "$if_in" "$ipv6_in" + + # br1 + ip_link_add br1 type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 0 + ip_link_set_up br1 + + # vx10, vx20 + vx10_create local "${ipv4_in%/*}" group "$GROUP4" dev "$if_in" + vx20_create local "${ipv6_in%/*}" group "$GROUP6" dev "$if_in" + + # w1 + ip_link_add w1 type veth peer name w2 + ip_link_set_master w1 br1 + ip_link_set_up w1 + bridge_vlan_add vid 10 dev w1 + bridge_vlan_add vid 20 dev w1 + + # w2 + simple_if_init w2 + defer simple_if_fini w2 + + # w2.10 + ip_link_add w2.10 master vw2 link w2 type vlan id 10 + ip_link_set_up w2.10 + ip_addr_add w2.10 "$ipv4_host" + + # w2.20 + ip_link_add w2.20 master vw2 link w2 type vlan id 20 + ip_link_set_up w2.20 + ip_addr_add w2.20 "$ipv6_host" +} +export -f ns_init_common + +ns2_create() +{ + # NS2 + ip netns add ns2 + defer ip netns del ns2 + + # v2$h2 + ip link set dev "v2$h2" netns ns2 + defer ip -n ns2 link set dev "v2$h2" netns 1 + + in_ns ns2 \ + ns_init_common ns2 "v2$h2" \ + 192.0.2.34/28 2001:db8:2::2/64 \ + 192.0.2.3/28 2001:db8:1::3/64 +} + +ns3_create() +{ + # NS3 + ip netns add ns3 + defer ip netns del ns3 + + # v2$h3 + ip link set dev "v2$h3" netns ns3 + defer ip -n ns3 link set dev "v2$h3" netns 1 + + ip -n ns3 link set dev "v2$h3" up + + in_ns ns3 \ + ns_init_common ns3 "v2$h3" \ + 192.0.2.66/28 2001:db8:3::2/64 \ + 192.0.2.4/28 2001:db8:1::4/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + defer vrf_cleanup + + forwarding_enable + defer forwarding_restore + + ip_link_add "v1$h2" type veth peer name "v2$h2" + ip_link_add "v1$h3" type veth peer name "v2$h3" + + h1_create + h2_create + h3_create + switch_create + ns2_create + ns3_create +} + +adf_install_broken_sg() +{ + adf_mcd_start "$IPMR" || exit "$EXIT_STATUS" + + mc_cli add "$swp2" 192.0.2.100 "$GROUP4" "$swp1" "$swp3" + defer mc_cli remove "$swp2" 192.0.2.100 "$GROUP4" "$swp1" "$swp3" + + mc_cli add "$swp2" 2001:db8:4::1 "$GROUP6" "$swp1" "$swp3" + defer mc_cli remove "$swp2" 2001:db8:4::1 "$GROUP6" "$swp1" "$swp3" +} + +adf_install_rx() +{ + mc_cli add "$swp2" 0.0.0.0 "$GROUP4" "$IPMR" + defer mc_cli remove "$swp2" 0.0.0.0 "$GROUP4" lo10 + + mc_cli add "$swp3" 0.0.0.0 "$GROUP4" "$IPMR" + defer mc_cli remove "$swp3" 0.0.0.0 "$GROUP4" lo10 + + mc_cli add "$swp2" :: "$GROUP6" "$IPMR" + defer mc_cli remove "$swp2" :: "$GROUP6" lo10 + + mc_cli add "$swp3" :: "$GROUP6" "$IPMR" + defer mc_cli remove "$swp3" :: "$GROUP6" lo10 +} + +adf_install_sg() +{ + adf_mcd_start "$IPMR" || exit "$EXIT_STATUS" + + mc_cli add "$IPMR" 192.0.2.100 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" 192.0.2.33 "$GROUP4" "$swp2" "$swp3" + + mc_cli add "$IPMR" 2001:db8:4::1 "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" 2001:db8:4::1 "$GROUP6" "$swp2" "$swp3" + + adf_install_rx +} + +adf_install_sg_sep() +{ + adf_mcd_start lo || exit "$EXIT_STATUS" + + mc_cli add lo 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove lo 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + + mc_cli add lo 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove lo 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" +} + +adf_install_sg_sep_rx() +{ + local lo=$1; shift + + adf_mcd_start "$IPMR" "$lo" || exit "$EXIT_STATUS" + + mc_cli add "$lo" 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove "$lo" 192.0.2.120 "$GROUP4" "$swp2" "$swp3" + + mc_cli add "$lo" 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove "$lo" 2001:db8:5::1 "$GROUP6" "$swp2" "$swp3" + + adf_install_rx +} + +adf_install_starg() +{ + adf_mcd_start "$IPMR" || exit "$EXIT_STATUS" + + mc_cli add "$IPMR" 0.0.0.0 "$GROUP4" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" 0.0.0.0 "$GROUP4" "$swp2" "$swp3" + + mc_cli add "$IPMR" :: "$GROUP6" "$swp2" "$swp3" + defer mc_cli remove "$IPMR" :: "$GROUP6" "$swp2" "$swp3" + + adf_install_rx +} + +do_packets_v4() +{ + local mac + + mac=$(mac_get "$h2") + "$MZ" "$h1" -Q 10 -c 10 -d 100msec -p 64 -a own -b "$mac" \ + -A 192.0.2.1 -B 192.0.2.2 -t udp sp=1234,dp=2345 -q +} + +do_packets_v6() +{ + local mac + + mac=$(mac_get "$h2") + "$MZ" -6 "$h1" -Q 20 -c 10 -d 100msec -p 64 -a own -b "$mac" \ + -A 2001:db8:1::1 -B 2001:db8:1::2 -t udp sp=1234,dp=2345 -q +} + +do_test() +{ + local ipv=$1; shift + local expect_h2=$1; shift + local expect_h3=$1; shift + local what=$1; shift + + local pref=$((100 + ipv)) + local t0_h2 + local t0_h3 + local t1_h2 + local t1_h3 + local d_h2 + local d_h3 + + RET=0 + + t0_h2=$(tc_rule_stats_get "$h2" "$pref" ingress) + t0_h3=$(tc_rule_stats_get "$h3" "$pref" ingress) + + "do_packets_v$ipv" + sleep 1 + + t1_h2=$(tc_rule_stats_get "$h2" "$pref" ingress) + t1_h3=$(tc_rule_stats_get "$h3" "$pref" ingress) + + d_h2=$((t1_h2 - t0_h2)) + d_h3=$((t1_h3 - t0_h3)) + + ((d_h2 == expect_h2)) + check_err $? "Expected $expect_h2 packets on H2, got $d_h2" + + ((d_h3 == expect_h3)) + check_err $? "Expected $expect_h3 packets on H3, got $d_h3" + + log_test "VXLAN MC flood $what" +} + +ipv4_do_test_rx() +{ + local h3_should_fail=$1; shift + local what=$1; shift + + RET=0 + + ping_do "$h1.10" 192.0.2.3 + check_err $? "H2 should respond" + + ping_do "$h1.10" 192.0.2.4 + check_err_fail "$h3_should_fail" $? "H3 responds" + + log_test "VXLAN MC flood $what" +} + +ipv6_do_test_rx() +{ + local h3_should_fail=$1; shift + local what=$1; shift + + RET=0 + + ping6_do "$h1.20" 2001:db8:1::3 + check_err $? "H2 should respond" + + ping6_do "$h1.20" 2001:db8:1::4 + check_err_fail "$h3_should_fail" $? "H3 responds" + + log_test "VXLAN MC flood $what" +} + +ipv4_nomcroute() +{ + # Install a misleading (S,G) rule to attempt to trick the system into + # pushing the packets elsewhere. + adf_install_broken_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$swp2" + do_test 4 10 0 "IPv4 nomcroute" +} + +ipv6_nomcroute() +{ + # Like for IPv4, install a misleading (S,G). + adf_install_broken_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$swp2" + do_test 6 10 0 "IPv6 nomcroute" +} + +ipv4_nomcroute_rx() +{ + vx10_create local 192.0.2.100 group "$GROUP4" dev "$swp2" + ipv4_do_test_rx 1 "IPv4 nomcroute ping" +} + +ipv6_nomcroute_rx() +{ + vx20_create local 2001:db8:4::1 group "$GROUP6" dev "$swp2" + ipv6_do_test_rx 1 "IPv6 nomcroute ping" +} + +ipv4_mcroute() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + do_test 4 10 10 "IPv4 mcroute" +} + +ipv6_mcroute() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + do_test 6 10 10 "IPv6 mcroute" +} + +ipv4_mcroute_rx() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + ipv4_do_test_rx 0 "IPv4 mcroute ping" +} + +ipv6_mcroute_rx() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + ipv6_do_test_rx 0 "IPv6 mcroute ping" +} + +ipv4_mcroute_changelink() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" + ip link set dev vx10 type vxlan mcroute + sleep 1 + do_test 4 10 10 "IPv4 mcroute changelink" +} + +ipv6_mcroute_changelink() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + ip link set dev vx20 type vxlan mcroute + sleep 1 + do_test 6 10 10 "IPv6 mcroute changelink" +} + +ipv4_mcroute_starg() +{ + adf_install_starg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + do_test 4 10 10 "IPv4 mcroute (*,G)" +} + +ipv6_mcroute_starg() +{ + adf_install_starg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + do_test 6 10 10 "IPv6 mcroute (*,G)" +} + +ipv4_mcroute_starg_rx() +{ + adf_install_starg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + ipv4_do_test_rx 0 "IPv4 mcroute (*,G) ping" +} + +ipv6_mcroute_starg_rx() +{ + adf_install_starg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + ipv6_do_test_rx 0 "IPv6 mcroute (*,G) ping" +} + +ipv4_mcroute_noroute() +{ + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + do_test 4 0 0 "IPv4 mcroute, no route" +} + +ipv6_mcroute_noroute() +{ + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + do_test 6 0 0 "IPv6 mcroute, no route" +} + +ipv4_mcroute_fdb() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 dev "$IPMR" mcroute + bridge fdb add dev vx10 \ + 00:00:00:00:00:00 self static dst "$GROUP4" via "$IPMR" + do_test 4 10 10 "IPv4 mcroute FDB" +} + +ipv6_mcroute_fdb() +{ + adf_install_sg + vx20_create_wait local 2001:db8:4::1 dev "$IPMR" mcroute + bridge -6 fdb add dev vx20 \ + 00:00:00:00:00:00 self static dst "$GROUP6" via "$IPMR" + do_test 6 10 10 "IPv6 mcroute FDB" +} + +# Use FDB to configure VXLAN in a way where oif=0 for purposes of FIB lookup. +ipv4_mcroute_fdb_oif0() +{ + adf_install_sg + vx10_create_wait local 192.0.2.100 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" + do_test 4 10 10 "IPv4 mcroute oif=0" +} + +ipv6_mcroute_fdb_oif0() +{ + # The IPv6 tunnel lookup does not fall back to selection by source + # address. Instead it just does a FIB match, and that would find one of + # the several ff00::/8 multicast routes -- each device has one. In order + # to reliably force the $IPMR device, add a /128 route for the + # destination group address. + ip -6 route add table local multicast "$GROUP6/128" dev "$IPMR" + defer ip -6 route del table local multicast "$GROUP6/128" dev "$IPMR" + + adf_install_sg + vx20_create_wait local 2001:db8:4::1 group "$GROUP6" dev "$IPMR" mcroute + bridge -6 fdb del dev vx20 00:00:00:00:00:00 + bridge -6 fdb add dev vx20 00:00:00:00:00:00 self static dst "$GROUP6" + do_test 6 10 10 "IPv6 mcroute oif=0" +} + +# In oif=0 test as above, have FIB lookup resolve to loopback instead of IPMR. +# This doesn't work with IPv6 -- a MC route on lo would be marked as RTF_REJECT. +ipv4_mcroute_fdb_oif0_sep() +{ + adf_install_sg_sep + + ip_addr_add lo 192.0.2.120/28 + vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" + do_test 4 10 10 "IPv4 mcroute TX!=RX oif=0" +} + +ipv4_mcroute_fdb_oif0_sep_rx() +{ + adf_install_sg_sep_rx lo + + ip_addr_add lo 192.0.2.120/28 + vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" + ipv4_do_test_rx 0 "IPv4 mcroute TX!=RX oif=0 ping" +} + +ipv4_mcroute_fdb_sep_rx() +{ + adf_install_sg_sep_rx lo + + ip_addr_add lo 192.0.2.120/28 + vx10_create_wait local 192.0.2.120 group "$GROUP4" dev "$IPMR" mcroute + bridge fdb del dev vx10 00:00:00:00:00:00 + bridge fdb add \ + dev vx10 00:00:00:00:00:00 self static dst "$GROUP4" via lo + ipv4_do_test_rx 0 "IPv4 mcroute TX!=RX ping" +} + +ipv6_mcroute_fdb_sep_rx() +{ + adf_install_sg_sep_rx "X$IPMR" + + ip_addr_add "X$IPMR" 2001:db8:5::1/64 + vx20_create_wait local 2001:db8:5::1 group "$GROUP6" dev "$IPMR" mcroute + bridge -6 fdb del dev vx20 00:00:00:00:00:00 + bridge -6 fdb add dev vx20 00:00:00:00:00:00 \ + self static dst "$GROUP6" via "X$IPMR" + ipv6_do_test_rx 0 "IPv6 mcroute TX!=RX ping" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/ipv6_force_forwarding.sh b/tools/testing/selftests/net/ipv6_force_forwarding.sh new file mode 100755 index 000000000000..bf0243366caa --- /dev/null +++ b/tools/testing/selftests/net/ipv6_force_forwarding.sh @@ -0,0 +1,105 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test IPv6 force_forwarding interface property +# +# This test verifies that the force_forwarding property works correctly: +# - When global forwarding is disabled, packets are not forwarded normally +# - When force_forwarding is enabled on an interface, packets are forwarded +# regardless of the global forwarding setting + +source lib.sh + +cleanup() { + cleanup_ns $ns1 $ns2 $ns3 +} + +trap cleanup EXIT + +setup_test() { + # Create three namespaces: sender, router, receiver + setup_ns ns1 ns2 ns3 + + # Create veth pairs: ns1 <-> ns2 <-> ns3 + ip link add name veth12 type veth peer name veth21 + ip link add name veth23 type veth peer name veth32 + + # Move interfaces to namespaces + ip link set veth12 netns $ns1 + ip link set veth21 netns $ns2 + ip link set veth23 netns $ns2 + ip link set veth32 netns $ns3 + + # Configure interfaces + ip -n $ns1 addr add 2001:db8:1::1/64 dev veth12 nodad + ip -n $ns2 addr add 2001:db8:1::2/64 dev veth21 nodad + ip -n $ns2 addr add 2001:db8:2::1/64 dev veth23 nodad + ip -n $ns3 addr add 2001:db8:2::2/64 dev veth32 nodad + + # Bring up interfaces + ip -n $ns1 link set veth12 up + ip -n $ns2 link set veth21 up + ip -n $ns2 link set veth23 up + ip -n $ns3 link set veth32 up + + # Add routes + ip -n $ns1 route add 2001:db8:2::/64 via 2001:db8:1::2 + ip -n $ns3 route add 2001:db8:1::/64 via 2001:db8:2::1 + + # Disable global forwarding + ip netns exec $ns2 sysctl -qw net.ipv6.conf.all.forwarding=0 +} + +test_force_forwarding() { + local ret=0 + + echo "TEST: force_forwarding functionality" + + # Check if force_forwarding sysctl exists + if ! ip netns exec $ns2 test -f /proc/sys/net/ipv6/conf/veth21/force_forwarding; then + echo "SKIP: force_forwarding not available" + return $ksft_skip + fi + + # Test 1: Without force_forwarding, ping should fail + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth21.force_forwarding=0 + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth23.force_forwarding=0 + + if ip netns exec $ns1 ping -6 -c 1 -W 2 2001:db8:2::2 &>/dev/null; then + echo "FAIL: ping succeeded when forwarding disabled" + ret=1 + else + echo "PASS: forwarding disabled correctly" + fi + + # Test 2: With force_forwarding enabled, ping should succeed + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth21.force_forwarding=1 + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth23.force_forwarding=1 + + if ip netns exec $ns1 ping -6 -c 1 -W 2 2001:db8:2::2 &>/dev/null; then + echo "PASS: force_forwarding enabled forwarding" + else + echo "FAIL: ping failed with force_forwarding enabled" + ret=1 + fi + + return $ret +} + +echo "IPv6 force_forwarding test" +echo "==========================" + +setup_test +test_force_forwarding +ret=$? + +if [ $ret -eq 0 ]; then + echo "OK" + exit 0 +elif [ $ret -eq $ksft_skip ]; then + echo "SKIP" + exit $ksft_skip +else + echo "FAIL" + exit 1 +fi diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 86a216e9aca8..c7add0dc4c60 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -240,6 +240,29 @@ create_netdevsim() { echo nsim$id } +create_netdevsim_port() { + local nsim_id="$1" + local ns="$2" + local port_id="$3" + local perm_addr="$4" + local orig_dev + local new_dev + local nsim_path + + nsim_path="/sys/bus/netdevsim/devices/netdevsim$nsim_id" + + echo "$port_id $perm_addr" | ip netns exec "$ns" tee "$nsim_path"/new_port > /dev/null || return 1 + + orig_dev=$(ip netns exec "$ns" find "$nsim_path"/net/ -maxdepth 1 -name 'e*' | tail -n 1) + orig_dev=$(basename "$orig_dev") + new_dev="nsim${nsim_id}p$port_id" + + ip -netns "$ns" link set dev "$orig_dev" name "$new_dev" + ip -netns "$ns" link set dev "$new_dev" up + + echo "$new_dev" +} + # Remove netdevsim with given id. cleanup_netdevsim() { local id="$1" @@ -547,13 +570,19 @@ ip_link_set_addr() defer ip link set dev "$name" address "$old_addr" } -ip_link_is_up() +ip_link_has_flag() { local name=$1; shift + local flag=$1; shift local state=$(ip -j link show "$name" | - jq -r '(.[].flags[] | select(. == "UP")) // "DOWN"') - [[ $state == "UP" ]] + jq --arg flag "$flag" 'any(.[].flags.[]; . == $flag)') + [[ $state == true ]] +} + +ip_link_is_up() +{ + ip_link_has_flag "$1" UP } ip_link_set_up() diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 8697bd27dc30..02be28dcc089 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -6,4 +6,4 @@ from .netns import NetNS, NetNSEnter from .nsim import * from .utils import * from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily -from .ynl import NetshaperFamily +from .ynl import NetshaperFamily, DevlinkFamily diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 61287c203b6e..8e35ed12ed9e 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -32,6 +32,7 @@ class KsftTerminate(KeyboardInterrupt): def ksft_pr(*objs, **kwargs): + kwargs["flush"] = True print("#", *objs, **kwargs) @@ -139,7 +140,7 @@ def ktap_result(ok, cnt=1, case="", comment=""): res += "." + str(case.__name__) if comment: res += " # " + comment - print(res) + print(res, flush=True) def ksft_flush_defer(): @@ -227,8 +228,8 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0} - print("TAP version 13") - print("1.." + str(len(cases))) + print("TAP version 13", flush=True) + print("1.." + str(len(cases)), flush=True) global KSFT_RESULT cnt = 0 diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index 34470d65d871..f395c90fb0f1 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -175,6 +175,10 @@ def tool(name, args, json=None, ns=None, host=None): return cmd_obj +def bpftool(args, json=None, ns=None, host=None): + return tool('bpftool', args, json=json, ns=ns, host=host) + + def ip(args, json=None, ns=None, host=None): if ns: args = f'-netns {ns} ' + args @@ -185,6 +189,41 @@ def ethtool(args, json=None, ns=None, host=None): return tool('ethtool', args, json=json, ns=ns, host=host) +def bpftrace(expr, json=None, ns=None, host=None, timeout=None): + """ + Run bpftrace and return map data (if json=True). + The output of bpftrace is inconvenient, so the helper converts + to a dict indexed by map name, e.g.: + { + "@": { ... }, + "@map2": { ... }, + } + """ + cmd_arr = ['bpftrace'] + # Throw in --quiet if json, otherwise the output has two objects + if json: + cmd_arr += ['-f', 'json', '-q'] + if timeout: + expr += ' interval:s:' + str(timeout) + ' { exit(); }' + cmd_arr += ['-e', expr] + cmd_obj = cmd(cmd_arr, ns=ns, host=host, shell=False) + if json: + # bpftrace prints objects as lines + ret = {} + for l in cmd_obj.stdout.split('\n'): + if not l.strip(): + continue + one = _json.loads(l) + if one.get('type') != 'map': + continue + for k, v in one["data"].items(): + if k.startswith('@'): + k = k.lstrip('@') + ret[k] = v + return ret + return cmd_obj + + def rand_port(type=socket.SOCK_STREAM): """ Get a random unprivileged port. diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py index 6329ae805abf..2b3a61ea3bfa 100644 --- a/tools/testing/selftests/net/lib/py/ynl.py +++ b/tools/testing/selftests/net/lib/py/ynl.py @@ -56,3 +56,8 @@ class NetshaperFamily(YnlFamily): def __init__(self, recv_size=0): super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(), schema='', recv_size=recv_size) + +class DevlinkFamily(YnlFamily): + def __init__(self, recv_size=0): + super().__init__((SPEC_PATH / Path('devlink.yaml')).as_posix(), + schema='', recv_size=recv_size) diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c new file mode 100644 index 000000000000..521ba38f2ddd --- /dev/null +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -0,0 +1,621 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/udp.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +#define MAX_ADJST_OFFSET 256 +#define MAX_PAYLOAD_LEN 5000 +#define MAX_HDR_LEN 64 + +enum { + XDP_MODE = 0, + XDP_PORT = 1, + XDP_ADJST_OFFSET = 2, + XDP_ADJST_TAG = 3, +} xdp_map_setup_keys; + +enum { + XDP_MODE_PASS = 0, + XDP_MODE_DROP = 1, + XDP_MODE_TX = 2, + XDP_MODE_TAIL_ADJST = 3, + XDP_MODE_HEAD_ADJST = 4, +} xdp_map_modes; + +enum { + STATS_RX = 0, + STATS_PASS = 1, + STATS_DROP = 2, + STATS_TX = 3, + STATS_ABORT = 4, +} xdp_stats; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + __type(value, __s32); +} map_xdp_setup SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + __type(value, __u64); +} map_xdp_stats SEC(".maps"); + +static __u32 min(__u32 a, __u32 b) +{ + return a < b ? a : b; +} + +static void record_stats(struct xdp_md *ctx, __u32 stat_type) +{ + __u64 *count; + + count = bpf_map_lookup_elem(&map_xdp_stats, &stat_type); + + if (count) + __sync_fetch_and_add(count, 1); +} + +static struct udphdr *filter_udphdr(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + + if (data + sizeof(*eth) > data_end) + return NULL; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + + if (iph + 1 > (struct iphdr *)data_end || + iph->protocol != IPPROTO_UDP) + return NULL; + + udph = (void *)eth + sizeof(*iph) + sizeof(*eth); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + + if (ipv6h + 1 > (struct ipv6hdr *)data_end || + ipv6h->nexthdr != IPPROTO_UDP) + return NULL; + + udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth); + } else { + return NULL; + } + + if (udph + 1 > (struct udphdr *)data_end) + return NULL; + + if (udph->dest != bpf_htons(port)) + return NULL; + + record_stats(ctx, STATS_RX); + + return udph; +} + +static int xdp_mode_pass(struct xdp_md *ctx, __u16 port) +{ + struct udphdr *udph = NULL; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + record_stats(ctx, STATS_PASS); + + return XDP_PASS; +} + +static int xdp_mode_drop_handler(struct xdp_md *ctx, __u16 port) +{ + struct udphdr *udph = NULL; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + record_stats(ctx, STATS_DROP); + + return XDP_DROP; +} + +static void swap_machdr(void *data) +{ + struct ethhdr *eth = data; + __u8 tmp_mac[ETH_ALEN]; + + __builtin_memcpy(tmp_mac, eth->h_source, ETH_ALEN); + __builtin_memcpy(eth->h_source, eth->h_dest, ETH_ALEN); + __builtin_memcpy(eth->h_dest, tmp_mac, ETH_ALEN); +} + +static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + + if (data + sizeof(*eth) > data_end) + return XDP_PASS; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + __be32 tmp_ip = iph->saddr; + + if (iph + 1 > (struct iphdr *)data_end || + iph->protocol != IPPROTO_UDP) + return XDP_PASS; + + udph = data + sizeof(*iph) + sizeof(*eth); + + if (udph + 1 > (struct udphdr *)data_end) + return XDP_PASS; + if (udph->dest != bpf_htons(port)) + return XDP_PASS; + + record_stats(ctx, STATS_RX); + swap_machdr((void *)eth); + + iph->saddr = iph->daddr; + iph->daddr = tmp_ip; + + record_stats(ctx, STATS_TX); + + return XDP_TX; + + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + struct in6_addr tmp_ipv6; + + if (ipv6h + 1 > (struct ipv6hdr *)data_end || + ipv6h->nexthdr != IPPROTO_UDP) + return XDP_PASS; + + udph = data + sizeof(*ipv6h) + sizeof(*eth); + + if (udph + 1 > (struct udphdr *)data_end) + return XDP_PASS; + if (udph->dest != bpf_htons(port)) + return XDP_PASS; + + record_stats(ctx, STATS_RX); + swap_machdr((void *)eth); + + __builtin_memcpy(&tmp_ipv6, &ipv6h->saddr, sizeof(tmp_ipv6)); + __builtin_memcpy(&ipv6h->saddr, &ipv6h->daddr, + sizeof(tmp_ipv6)); + __builtin_memcpy(&ipv6h->daddr, &tmp_ipv6, sizeof(tmp_ipv6)); + + record_stats(ctx, STATS_TX); + + return XDP_TX; + } + + return XDP_PASS; +} + +static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + __u32 len, len_new; + + if (data + sizeof(*eth) > data_end) + return NULL; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + __u16 total_len; + + if (iph + 1 > (struct iphdr *)data_end) + return NULL; + + iph->tot_len = bpf_htons(bpf_ntohs(iph->tot_len) + offset); + + udph = (void *)eth + sizeof(*iph) + sizeof(*eth); + if (!udph || udph + 1 > (struct udphdr *)data_end) + return NULL; + + len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + __u16 payload_len; + + if (ipv6h + 1 > (struct ipv6hdr *)data_end) + return NULL; + + udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth); + if (!udph || udph + 1 > (struct udphdr *)data_end) + return NULL; + + *udp_csum = ~((__u32)udph->check); + + len = ipv6h->payload_len; + len_new = bpf_htons(bpf_ntohs(len) + offset); + ipv6h->payload_len = len_new; + + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + + len = udph->len; + len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + } else { + return NULL; + } + + udph->len = len_new; + + return udph; +} + +static __u16 csum_fold_helper(__u32 csum) +{ + return ~((csum & 0xffff) + (csum >> 16)) ? : 0xffff; +} + +static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, + __u32 hdr_len) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + __u32 buff_pos, udp_csum = 0; + struct udphdr *udph = NULL; + __u32 buff_len; + + udph = update_pkt(ctx, 0 - offset, &udp_csum); + if (!udph) + return -1; + + buff_len = bpf_xdp_get_buff_len(ctx); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + /* Make sure we have enough data to avoid eating the header */ + if (buff_len - offset < hdr_len) + return -1; + + buff_pos = buff_len - offset; + if (bpf_xdp_load_bytes(ctx, buff_pos, tmp_buff, offset) < 0) + return -1; + + udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (bpf_xdp_adjust_tail(ctx, 0 - offset) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_tail_grow_data(struct xdp_md *ctx, __u16 offset) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + __u32 buff_pos, udp_csum = 0; + __u32 buff_len, hdr_len, key; + struct udphdr *udph; + __s32 *val; + __u8 tag; + + /* Proceed to update the packet headers before attempting to adjuste + * the tail. Once the tail is adjusted we lose access to the offset + * amount of data at the end of the packet which is crucial to update + * the checksum. + * Since any failure beyond this would abort the packet, we should + * not worry about passing a packet up the stack with wrong headers + */ + udph = update_pkt(ctx, offset, &udp_csum); + if (!udph) + return -1; + + key = XDP_ADJST_TAG; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return -1; + + tag = (__u8)(*val); + + for (int i = 0; i < MAX_ADJST_OFFSET; i++) + __builtin_memcpy(&tmp_buff[i], &tag, 1); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + udp_csum = bpf_csum_diff(0, 0, (__be32 *)tmp_buff, offset, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + buff_len = bpf_xdp_get_buff_len(ctx); + + if (bpf_xdp_adjust_tail(ctx, offset) < 0) { + bpf_printk("Failed to adjust tail\n"); + return -1; + } + + if (bpf_xdp_store_bytes(ctx, buff_len, tmp_buff, offset) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port) +{ + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + __s32 *adjust_offset, *val; + __u32 key, hdr_len; + void *offset_ptr; + __u8 tag; + int ret; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + hdr_len = (void *)udph - data + sizeof(struct udphdr); + key = XDP_ADJST_OFFSET; + adjust_offset = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!adjust_offset) + return XDP_PASS; + + if (*adjust_offset < 0) + ret = xdp_adjst_tail_shrnk_data(ctx, + (__u16)(0 - *adjust_offset), + hdr_len); + else + ret = xdp_adjst_tail_grow_data(ctx, (__u16)(*adjust_offset)); + if (ret) + goto abort_pkt; + + record_stats(ctx, STATS_PASS); + return XDP_PASS; + +abort_pkt: + record_stats(ctx, STATS_ABORT); + return XDP_ABORTED; +} + +static int xdp_adjst_head_shrnk_data(struct xdp_md *ctx, __u64 hdr_len, + __u32 offset) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + struct udphdr *udph; + void *offset_ptr; + __u32 udp_csum = 0; + + /* Update the length information in the IP and UDP headers before + * adjusting the headroom. This simplifies accessing the relevant + * fields in the IP and UDP headers for fragmented packets. Any + * failure beyond this point will result in the packet being aborted, + * so we don't need to worry about incorrect length information for + * passed packets. + */ + udph = update_pkt(ctx, (__s16)(0 - offset), &udp_csum); + if (!udph) + return -1; + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + if (bpf_xdp_load_bytes(ctx, hdr_len, tmp_buff, offset) < 0) + return -1; + + udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); + + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (bpf_xdp_load_bytes(ctx, 0, tmp_buff, MAX_ADJST_OFFSET) < 0) + return -1; + + if (bpf_xdp_adjust_head(ctx, offset) < 0) + return -1; + + if (offset > MAX_ADJST_OFFSET) + return -1; + + if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) + return -1; + + /* Added here to handle clang complain about negative value */ + hdr_len = hdr_len & 0xff; + + if (hdr_len == 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, 0, tmp_buff, hdr_len) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_head_grow_data(struct xdp_md *ctx, __u64 hdr_len, + __u32 offset) +{ + char hdr_buff[MAX_HDR_LEN]; + char data_buff[MAX_ADJST_OFFSET]; + void *offset_ptr; + __s32 *val; + __u32 key; + __u8 tag; + __u32 udp_csum = 0; + struct udphdr *udph; + + udph = update_pkt(ctx, (__s16)(offset), &udp_csum); + if (!udph) + return -1; + + key = XDP_ADJST_TAG; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return -1; + + tag = (__u8)(*val); + for (int i = 0; i < MAX_ADJST_OFFSET; i++) + __builtin_memcpy(&data_buff[i], &tag, 1); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + udp_csum = bpf_csum_diff(0, 0, (__be32 *)data_buff, offset, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) + return -1; + + /* Added here to handle clang complain about negative value */ + hdr_len = hdr_len & 0xff; + + if (hdr_len == 0) + return -1; + + if (bpf_xdp_load_bytes(ctx, 0, hdr_buff, hdr_len) < 0) + return -1; + + if (offset > MAX_ADJST_OFFSET) + return -1; + + if (bpf_xdp_adjust_head(ctx, 0 - offset) < 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, 0, hdr_buff, hdr_len) < 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, hdr_len, data_buff, offset) < 0) + return -1; + + return 0; +} + +static int xdp_head_adjst(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph_ptr = NULL; + __u32 key, size, hdr_len; + __s32 *val; + int res; + + /* Filter packets based on UDP port */ + udph_ptr = filter_udphdr(ctx, port); + if (!udph_ptr) + return XDP_PASS; + + hdr_len = (void *)udph_ptr - data + sizeof(struct udphdr); + + key = XDP_ADJST_OFFSET; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return XDP_PASS; + + switch (*val) { + case -16: + case 16: + size = 16; + break; + case -32: + case 32: + size = 32; + break; + case -64: + case 64: + size = 64; + break; + case -128: + case 128: + size = 128; + break; + case -256: + case 256: + size = 256; + break; + default: + bpf_printk("Invalid adjustment offset: %d\n", *val); + goto abort; + } + + if (*val < 0) + res = xdp_adjst_head_grow_data(ctx, hdr_len, size); + else + res = xdp_adjst_head_shrnk_data(ctx, hdr_len, size); + + if (res) + goto abort; + + record_stats(ctx, STATS_PASS); + return XDP_PASS; + +abort: + record_stats(ctx, STATS_ABORT); + return XDP_ABORTED; +} + +static int xdp_prog_common(struct xdp_md *ctx) +{ + __u32 key, *port; + __s32 *mode; + + key = XDP_MODE; + mode = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!mode) + return XDP_PASS; + + key = XDP_PORT; + port = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!port) + return XDP_PASS; + + switch (*mode) { + case XDP_MODE_PASS: + return xdp_mode_pass(ctx, (__u16)(*port)); + case XDP_MODE_DROP: + return xdp_mode_drop_handler(ctx, (__u16)(*port)); + case XDP_MODE_TX: + return xdp_mode_tx_handler(ctx, (__u16)(*port)); + case XDP_MODE_TAIL_ADJST: + return xdp_adjst_tail(ctx, (__u16)(*port)); + case XDP_MODE_HEAD_ADJST: + return xdp_head_adjst(ctx, (__u16)(*port)); + } + + /* Default action is to simple pass */ + return XDP_PASS; +} + +SEC("xdp") +int xdp_prog(struct xdp_md *ctx) +{ + return xdp_prog_common(ctx); +} + +SEC("xdp.frags") +int xdp_prog_frags(struct xdp_md *ctx) +{ + return xdp_prog_common(ctx); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 4f80014cae49..968d440c03fe 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -13,6 +13,7 @@ CONFIG_NETFILTER_NETLINK=m CONFIG_NF_TABLES=m CONFIG_NFT_COMPAT=m CONFIG_NETFILTER_XTABLES=m +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NETFILTER_XT_MATCH_BPF=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m @@ -25,6 +26,7 @@ CONFIG_IP_MULTIPLE_TABLES=y CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP6_NF_TARGET_REJECT=m CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IP6_NF_FILTER=m CONFIG_NET_ACT_CSUM=m diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c index 7ea5fb28c93d..1d5d3c4e7e87 100644 --- a/tools/testing/selftests/net/msg_zerocopy.c +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -77,6 +77,7 @@ static int cfg_cork; static bool cfg_cork_mixed; static int cfg_cpu = -1; /* default: pin to last cpu */ +static int cfg_expect_zerocopy = -1; static int cfg_family = PF_UNSPEC; static int cfg_ifindex = 1; static int cfg_payload_len; @@ -92,9 +93,9 @@ static socklen_t cfg_alen; static struct sockaddr_storage cfg_dst_addr; static struct sockaddr_storage cfg_src_addr; +static int exitcode; static char payload[IP_MAXPACKET]; static long packets, bytes, completions, expected_completions; -static int zerocopied = -1; static uint32_t next_completion; static uint32_t sends_since_notify; @@ -444,11 +445,13 @@ static bool do_recv_completion(int fd, int domain) next_completion = hi + 1; zerocopy = !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED); - if (zerocopied == -1) - zerocopied = zerocopy; - else if (zerocopied != zerocopy) { - fprintf(stderr, "serr: inconsistent\n"); - zerocopied = zerocopy; + if (cfg_expect_zerocopy != -1 && + cfg_expect_zerocopy != zerocopy) { + fprintf(stderr, "serr: ee_code: %u != expected %u\n", + zerocopy, cfg_expect_zerocopy); + exitcode = 1; + /* suppress repeated messages */ + cfg_expect_zerocopy = zerocopy; } if (cfg_verbose >= 2) @@ -571,7 +574,7 @@ static void do_tx(int domain, int type, int protocol) fprintf(stderr, "tx=%lu (%lu MB) txc=%lu zc=%c\n", packets, bytes >> 20, completions, - zerocopied == 1 ? 'y' : 'n'); + cfg_zerocopy && cfg_expect_zerocopy == 1 ? 'y' : 'n'); } static int do_setup_rx(int domain, int type, int protocol) @@ -715,7 +718,7 @@ static void parse_opts(int argc, char **argv) cfg_payload_len = max_payload_len; - while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vz")) != -1) { + while ((c = getopt(argc, argv, "46c:C:D:i:l:mp:rs:S:t:vzZ:")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -770,6 +773,9 @@ static void parse_opts(int argc, char **argv) case 'z': cfg_zerocopy = true; break; + case 'Z': + cfg_expect_zerocopy = !!atoi(optarg); + break; } } @@ -817,5 +823,5 @@ int main(int argc, char **argv) else error(1, 0, "unknown cfg_test %s", cfg_test); - return 0; + return exitcode; } diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh index 89c22f5320e0..28178a38a4e7 100755 --- a/tools/testing/selftests/net/msg_zerocopy.sh +++ b/tools/testing/selftests/net/msg_zerocopy.sh @@ -6,6 +6,7 @@ set -e readonly DEV="veth0" +readonly DUMMY_DEV="dummy0" readonly DEV_MTU=65535 readonly BIN="./msg_zerocopy" @@ -14,21 +15,25 @@ readonly NSPREFIX="ns-${RAND}" readonly NS1="${NSPREFIX}1" readonly NS2="${NSPREFIX}2" -readonly SADDR4='192.168.1.1' -readonly DADDR4='192.168.1.2' -readonly SADDR6='fd::1' -readonly DADDR6='fd::2' +readonly LPREFIX4='192.168.1' +readonly RPREFIX4='192.168.2' +readonly LPREFIX6='fd' +readonly RPREFIX6='fc' + readonly path_sysctl_mem="net.core.optmem_max" # No arguments: automated test if [[ "$#" -eq "0" ]]; then - $0 4 tcp -t 1 - $0 6 tcp -t 1 - $0 4 udp -t 1 - $0 6 udp -t 1 - echo "OK. All tests passed" - exit 0 + ret=0 + + $0 4 tcp -t 1 || ret=1 + $0 6 tcp -t 1 || ret=1 + $0 4 udp -t 1 || ret=1 + $0 6 udp -t 1 || ret=1 + + [[ "$ret" == "0" ]] && echo "OK. All tests passed" + exit $ret fi # Argument parsing @@ -45,11 +50,18 @@ readonly EXTRA_ARGS="$@" # Argument parsing: configure addresses if [[ "${IP}" == "4" ]]; then - readonly SADDR="${SADDR4}" - readonly DADDR="${DADDR4}" + readonly SADDR="${LPREFIX4}.1" + readonly DADDR="${LPREFIX4}.2" + readonly DUMMY_ADDR="${RPREFIX4}.1" + readonly DADDR_TXONLY="${RPREFIX4}.2" + readonly MASK="24" elif [[ "${IP}" == "6" ]]; then - readonly SADDR="${SADDR6}" - readonly DADDR="${DADDR6}" + readonly SADDR="${LPREFIX6}::1" + readonly DADDR="${LPREFIX6}::2" + readonly DUMMY_ADDR="${RPREFIX6}::1" + readonly DADDR_TXONLY="${RPREFIX6}::2" + readonly MASK="64" + readonly NODAD="nodad" else echo "Invalid IP version ${IP}" exit 1 @@ -89,33 +101,61 @@ ip netns exec "${NS2}" sysctl -w -q "${path_sysctl_mem}=1000000" ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \ peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}" +ip link add "${DUMMY_DEV}" mtu "${DEV_MTU}" netns "${NS2}" type dummy + # Bring the devices up ip -netns "${NS1}" link set "${DEV}" up ip -netns "${NS2}" link set "${DEV}" up +ip -netns "${NS2}" link set "${DUMMY_DEV}" up # Set fixed MAC addresses on the devices ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02 ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06 # Add fixed IP addresses to the devices -ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}" -ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}" -ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad -ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad +ip -netns "${NS1}" addr add "${SADDR}/${MASK}" dev "${DEV}" ${NODAD} +ip -netns "${NS2}" addr add "${DADDR}/${MASK}" dev "${DEV}" ${NODAD} +ip -netns "${NS2}" addr add "${DUMMY_ADDR}/${MASK}" dev "${DUMMY_DEV}" ${NODAD} + +ip -netns "${NS1}" route add default via "${DADDR}" dev "${DEV}" +ip -netns "${NS2}" route add default via "${DADDR_TXONLY}" dev "${DUMMY_DEV}" + +ip netns exec "${NS2}" sysctl -wq net.ipv4.ip_forward=1 +ip netns exec "${NS2}" sysctl -wq net.ipv6.conf.all.forwarding=1 # Optionally disable sg or csum offload to test edge cases # ip netns exec "${NS1}" ethtool -K "${DEV}" sg off +ret=0 + do_test() { local readonly ARGS="$1" - echo "ipv${IP} ${TXMODE} ${ARGS}" - ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" & + # tx-rx test + # packets queued to a local socket are copied, + # sender notification has SO_EE_CODE_ZEROCOPY_COPIED. + + echo -e "\nipv${IP} ${TXMODE} ${ARGS} tx-rx\n" + ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 \ + -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" & sleep 0.2 - ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" + ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 \ + -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" -Z 0 || ret=1 wait + + # next test is unconnected tx to dummy0, cannot exercise with tcp + [[ "${TXMODE}" == "tcp" ]] && return + + # tx-only test: send out dummy0 + # packets leaving the host are not copied, + # sender notification does not have SO_EE_CODE_ZEROCOPY_COPIED. + + echo -e "\nipv${IP} ${TXMODE} ${ARGS} tx-only\n" + ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 \ + -S "${SADDR}" -D "${DADDR_TXONLY}" ${ARGS} "${TXMODE}" -Z 1 || ret=1 } do_test "${EXTRA_ARGS}" do_test "-z ${EXTRA_ARGS}" -echo ok + +[[ "$ret" == "0" ]] && echo "OK" diff --git a/tools/testing/selftests/net/netdev-l2addr.sh b/tools/testing/selftests/net/netdev-l2addr.sh new file mode 100755 index 000000000000..18509da293e5 --- /dev/null +++ b/tools/testing/selftests/net/netdev-l2addr.sh @@ -0,0 +1,59 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh +set -o pipefail + +NSIM_ADDR=2025 +TEST_ADDR="d0:be:d0:be:d0:00" + +RET_CODE=0 + +cleanup() { + cleanup_netdevsim "$NSIM_ADDR" + cleanup_ns "$NS" +} + +trap cleanup EXIT + +fail() { + echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2 + RET_CODE=1 +} + +get_addr() +{ + local type="$1" + local dev="$2" + local ns="$3" + + ip -j -n "$ns" link show dev "$dev" | jq -er ".[0].$type" +} + +setup_ns NS + +nsim=$(create_netdevsim $NSIM_ADDR "$NS") + +get_addr address "$nsim" "$NS" >/dev/null || fail "Couldn't get ether addr" +get_addr broadcast "$nsim" "$NS" >/dev/null || fail "Couldn't get brd addr" +get_addr permaddr "$nsim" "$NS" >/dev/null && fail "Found perm_addr without setting it" + +ip -n "$NS" link set dev "$nsim" address "$TEST_ADDR" +ip -n "$NS" link set dev "$nsim" brd "$TEST_ADDR" + +[[ "$(get_addr address "$nsim" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't set ether addr" +[[ "$(get_addr broadcast "$nsim" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't set brd addr" + +if create_netdevsim_port "$NSIM_ADDR" "$NS" 2 "FF:FF:FF:FF:FF:FF" 2>/dev/null; then + fail "Created netdevsim with broadcast permaddr" +fi + +nsim_port=$(create_netdevsim_port "$NSIM_ADDR" "$NS" 2 "$TEST_ADDR") + +get_addr address "$nsim_port" "$NS" >/dev/null || fail "Couldn't get ether addr" +get_addr broadcast "$nsim_port" "$NS" >/dev/null || fail "Couldn't get brd addr" +[[ "$(get_addr permaddr "$nsim_port" "$NS")" == "$TEST_ADDR" ]] || fail "Couldn't get permaddr" + +cleanup_netdevsim "$NSIM_ADDR" "$NS" + +exit $RET_CODE diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config index 363646f4fefe..79d5b33966ba 100644 --- a/tools/testing/selftests/net/netfilter/config +++ b/tools/testing/selftests/net/netfilter/config @@ -1,6 +1,8 @@ CONFIG_AUDIT=y CONFIG_BPF_SYSCALL=y CONFIG_BRIDGE=m +CONFIG_NETFILTER_XTABLES_LEGACY=y +CONFIG_BRIDGE_NF_EBTABLES_LEGACY=m CONFIG_BRIDGE_EBT_BROUTE=m CONFIG_BRIDGE_EBT_IP=m CONFIG_BRIDGE_EBT_REDIRECT=m @@ -14,7 +16,10 @@ CONFIG_INET_ESP=m CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP6_NF_MATCH_RPFILTER=m CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_IPTABLES_LEGACY=m CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_IPTABLES_LEGACY=m +CONFIG_IP_NF_NAT=m CONFIG_IP_NF_FILTER=m CONFIG_IP6_NF_FILTER=m CONFIG_IP_NF_RAW=m @@ -92,4 +97,4 @@ CONFIG_XFRM_STATISTICS=y CONFIG_NET_PKTGEN=m CONFIG_TUN=m CONFIG_INET_DIAG=m -CONFIG_SCTP_DIAG=m +CONFIG_INET_SCTP_DIAG=m diff --git a/tools/testing/selftests/net/netfilter/ipvs.sh b/tools/testing/selftests/net/netfilter/ipvs.sh index 6af2ea3ad6b8..9c9d5b38ab71 100755 --- a/tools/testing/selftests/net/netfilter/ipvs.sh +++ b/tools/testing/selftests/net/netfilter/ipvs.sh @@ -151,7 +151,7 @@ test_nat() { test_tun() { ip netns exec "${ns0}" ip route add "${vip_v4}" via "${gip_v4}" dev br0 - ip netns exec "${ns1}" modprobe -q ipip + modprobe -q ipip ip netns exec "${ns1}" ip link set tunl0 up ip netns exec "${ns1}" sysctl -qw net.ipv4.ip_forward=0 ip netns exec "${ns1}" sysctl -qw net.ipv4.conf.all.send_redirects=0 @@ -160,10 +160,10 @@ test_tun() { ip netns exec "${ns1}" ipvsadm -a -i -t "${vip_v4}:${port}" -r ${rip_v4}:${port} ip netns exec "${ns1}" ip addr add ${vip_v4}/32 dev lo:1 - ip netns exec "${ns2}" modprobe -q ipip ip netns exec "${ns2}" ip link set tunl0 up ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_ignore=1 ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.arp_announce=2 + ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.tunl0.rp_filter=0 ip netns exec "${ns2}" ip addr add "${vip_v4}/32" dev lo:1 test_service diff --git a/tools/testing/selftests/net/netfilter/nft_interface_stress.sh b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh index 5ff7be9daeee..c0fffaa6dbd9 100755 --- a/tools/testing/selftests/net/netfilter/nft_interface_stress.sh +++ b/tools/testing/selftests/net/netfilter/nft_interface_stress.sh @@ -10,6 +10,8 @@ source lib.sh checktool "nft --version" "run test without nft tool" checktool "iperf3 --version" "run test without iperf3 tool" +read kernel_tainted < /proc/sys/kernel/tainted + # how many seconds to torture the kernel? # default to 80% of max run time but don't exceed 48s TEST_RUNTIME=$((${kselftest_timeout:-60} * 8 / 10)) @@ -135,7 +137,8 @@ else wait fi -[[ $(</proc/sys/kernel/tainted) -eq 0 ]] || { + +[[ $kernel_tainted -eq 0 && $(</proc/sys/kernel/tainted) -ne 0 ]] && { echo "FAIL: Kernel is tainted!" exit $ksft_fail } diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index cd8a58097448..1f5227f3d64d 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -385,7 +385,7 @@ static int get_bind_to_device(int sd, char *name, size_t len) name[0] = '\0'; rc = getsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, name, &optlen); if (rc < 0) - log_err_errno("setsockopt(SO_BINDTODEVICE)"); + log_err_errno("getsockopt(SO_BINDTODEVICE)"); return rc; } @@ -535,7 +535,7 @@ static int set_freebind(int sd, int version) break; case AF_INET6: if (setsockopt(sd, SOL_IPV6, IPV6_FREEBIND, &one, sizeof(one))) { - log_err_errno("setsockopt(IPV6_FREEBIND"); + log_err_errno("setsockopt(IPV6_FREEBIND)"); rc = -1; } break; @@ -812,7 +812,7 @@ static int convert_addr(struct sock_args *args, const char *_str, sep++; if (str_to_uint(sep, 1, pfx_len_max, &args->prefix_len) != 0) { - fprintf(stderr, "Invalid port\n"); + fprintf(stderr, "Invalid prefix length\n"); return 1; } } else { @@ -1272,7 +1272,7 @@ static int msg_loop(int client, int sd, void *addr, socklen_t alen, } } - nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1; + nfds = interactive ? MAX(fileno(stdin), sd) + 1 : sd + 1; while (1) { FD_ZERO(&rfds); FD_SET(sd, &rfds); @@ -1492,7 +1492,7 @@ static int lsock_init(struct sock_args *args) sd = socket(args->version, args->type, args->protocol); if (sd < 0) { log_err_errno("Error opening socket"); - return -1; + return -1; } if (set_reuseaddr(sd) != 0) @@ -1912,7 +1912,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) * waiting to be told when to continue */ if (read(fd, &buf, sizeof(buf)) <= 0) { - log_err_errno("Failed to read IPC status from status"); + log_err_errno("Failed to read IPC status from pipe"); return 1; } if (!buf) { diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py index beaee5e4e2aa..5c66421ab8aa 100755 --- a/tools/testing/selftests/net/nl_netdev.py +++ b/tools/testing/selftests/net/nl_netdev.py @@ -2,8 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 import time +from os import system from lib.py import ksft_run, ksft_exit, ksft_pr -from lib.py import ksft_eq, ksft_ge, ksft_busy_wait +from lib.py import ksft_eq, ksft_ge, ksft_ne, ksft_busy_wait from lib.py import NetdevFamily, NetdevSimDev, ip @@ -34,6 +35,128 @@ def napi_list_check(nf) -> None: ksft_eq(len(napis), 100, comment=f"queue count after reset queue {q} mode {i}") +def napi_set_threaded(nf) -> None: + """ + Test that verifies various cases of napi threaded + set and unset at napi and device level. + """ + with NetdevSimDev(queue_count=2) as nsimdev: + nsim = nsimdev.nsims[0] + + ip(f"link set dev {nsim.ifname} up") + + napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True) + ksft_eq(len(napis), 2) + + napi0_id = napis[0]['id'] + napi1_id = napis[1]['id'] + + # set napi threaded and verify + nf.napi_set({'id': napi0_id, 'threaded': "enabled"}) + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "enabled") + ksft_ne(napi0.get('pid'), None) + + # check it is not set for napi1 + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "disabled") + ksft_eq(napi1.get('pid'), None) + + ip(f"link set dev {nsim.ifname} down") + ip(f"link set dev {nsim.ifname} up") + + # verify if napi threaded is still set + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "enabled") + ksft_ne(napi0.get('pid'), None) + + # check it is still not set for napi1 + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "disabled") + ksft_eq(napi1.get('pid'), None) + + # unset napi threaded and verify + nf.napi_set({'id': napi0_id, 'threaded': "disabled"}) + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "disabled") + ksft_eq(napi0.get('pid'), None) + + # set threaded at device level + system(f"echo 1 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is set for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "enabled") + ksft_ne(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "enabled") + ksft_ne(napi1.get('pid'), None) + + # unset threaded at device level + system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is unset for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "disabled") + ksft_eq(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "disabled") + ksft_eq(napi1.get('pid'), None) + + # set napi threaded for napi0 + nf.napi_set({'id': napi0_id, 'threaded': 1}) + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "enabled") + ksft_ne(napi0.get('pid'), None) + + # unset threaded at device level + system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is unset for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "disabled") + ksft_eq(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "disabled") + ksft_eq(napi1.get('pid'), None) + +def dev_set_threaded(nf) -> None: + """ + Test that verifies various cases of napi threaded + set and unset at device level using sysfs. + """ + with NetdevSimDev(queue_count=2) as nsimdev: + nsim = nsimdev.nsims[0] + + ip(f"link set dev {nsim.ifname} up") + + napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True) + ksft_eq(len(napis), 2) + + napi0_id = napis[0]['id'] + napi1_id = napis[1]['id'] + + # set threaded + system(f"echo 1 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is set for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "enabled") + ksft_ne(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "enabled") + ksft_ne(napi1.get('pid'), None) + + # unset threaded + system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded") + + # check napi threaded is unset for both napis + napi0 = nf.napi_get({'id': napi0_id}) + ksft_eq(napi0['threaded'], "disabled") + ksft_eq(napi0.get('pid'), None) + napi1 = nf.napi_get({'id': napi1_id}) + ksft_eq(napi1['threaded'], "disabled") + ksft_eq(napi1.get('pid'), None) def nsim_rxq_reset_down(nf) -> None: """ @@ -122,7 +245,7 @@ def page_pool_check(nf) -> None: def main() -> None: nf = NetdevFamily() ksft_run([empty_check, lo_check, page_pool_check, napi_list_check, - nsim_rxq_reset_down], + dev_set_threaded, napi_set_threaded, nsim_rxq_reset_down], args=(nf, )) ksft_exit() diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index ef8b25a606d8..c5b01e1bd4c7 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -39,11 +39,15 @@ if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then # xfail tests that are known flaky with dbg config, not fixable. # still run them for coverage (and expect 100% pass without dbg). declare -ar xfail_list=( + "tcp_blocking_blocking-connect.pkt" + "tcp_blocking_blocking-read.pkt" "tcp_eor_no-coalesce-retrans.pkt" "tcp_fast_recovery_prr-ss.*.pkt" + "tcp_sack_sack-route-refresh-ip-tos.pkt" "tcp_slow_start_slow-start-after-win-update.pkt" "tcp_timestamping.*.pkt" "tcp_user_timeout_user-timeout-probe.pkt" + "tcp_zerocopy_cl.*.pkt" "tcp_zerocopy_epoll_.*.pkt" "tcp_tcp_info_tcp-info-.*-limited.pkt" ) diff --git a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt index 914eabab367a..657e42ca65b5 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_blocking_blocking-read.pkt @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Test for blocking read. + --tolerance_usecs=10000 +--mss=1000 `./defaults.sh` diff --git a/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt b/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt new file mode 100644 index 000000000000..c790d0af635e --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_dsack_mult.pkt @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +// Test various DSACK (RFC 2883) behaviors. + +--mss=1000 + +`./defaults.sh` + + + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8> + +.1 < . 1:1(0) ack 1 win 1024 + +0 accept(3, ..., ...) = 4 + +// First SACK range. + +0 < P. 1001:2001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop, nop, sack 1001:2001> + +// Check SACK coalescing (contiguous sequence). + +0 < P. 2001:3001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 1001:3001> + +// Check we have two SACK ranges for non contiguous sequences. + +0 < P. 4001:5001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 4001:5001 1001:3001> + +// Three ranges. + +0 < P. 7001:8001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 1 <nop,nop,sack 7001:8001 4001:5001 1001:3001> + +// DSACK (1001:3001) + SACK (6001:7001) + +0 < P. 1:6001(6000) ack 1 win 1024 + +0 > . 1:1(0) ack 6001 <nop,nop,sack 1001:3001 7001:8001> + +// DSACK (7001:8001) + +0 < P. 6001:8001(2000) ack 1 win 1024 + +0 > . 1:1(0) ack 8001 <nop,nop,sack 7001:8001> + +// DSACK for an older segment. + +0 < P. 1:1001(1000) ack 1 win 1024 + +0 > . 1:1(0) ack 8001 <nop,nop,sack 1:1001> diff --git a/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt index df49c67645ac..e13f0eee9795 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Test TCP_INQ and TCP_CM_INQ on the client side. + +--mss=1000 + `./defaults.sh ` diff --git a/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt b/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt index 04a5e2590c62..14dd5f813d50 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Test TCP_INQ and TCP_CM_INQ on the server side. + +--mss=1000 + `./defaults.sh ` diff --git a/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt b/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt new file mode 100644 index 000000000000..7e6bc5fb0c8d --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_ooo_rcv_mss.pkt @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh +sysctl -q net.ipv4.tcp_rmem="4096 131072 $((32*1024*1024))"` + + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < . 2001:11001(9000) ack 1 win 257 + +0 > . 1:1(0) ack 1 win 81 <nop,nop,sack 2001:11001> + +// check that ooo packet properly updates tcpi_rcv_mss + +0 %{ assert tcpi_rcv_mss == 1000, tcpi_rcv_mss }% + + +0 < . 11001:21001(10000) ack 1 win 257 + +0 > . 1:1(0) ack 1 win 81 <nop,nop,sack 2001:21001> + diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt new file mode 100644 index 000000000000..3848b419e68c --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh` + + 0 `nstat -n` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [10000], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 0> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < P. 1:4001(4000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + +// packet in sequence : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW + +0 < P. 4001:54001(50000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + +// ooo packet. : SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE / LINUX_MIB_BEYOND_WINDOW + +1 < P. 5001:55001(50000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + +// SKB_DROP_REASON_TCP_INVALID_SEQUENCE / LINUX_MIB_BEYOND_WINDOW + +0 < P. 70001:80001(10000) ack 1 win 257 + +0 > . 1:1(0) ack 4001 win 5000 + + +0 read(4, ..., 100000) = 4000 + +// If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd + +0 < P. 4001:54001(50000) ack 1 win 257 + +0 > . 1:1(0) ack 54001 win 0 + +// Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times. ++0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "` diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt new file mode 100644 index 000000000000..f575c0ff89da --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 + +--mss=1000 + +`./defaults.sh` + + 0 `nstat -n` + +// Establish a connection. + +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> + +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0> + +.1 < . 1:1(0) ack 1 win 257 + + +0 accept(3, ..., ...) = 4 + + +0 < P. 1:20001(20000) ack 1 win 257 + +.04 > . 1:1(0) ack 20001 win 18000 + + +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0 + +0 < P. 20001:80001(60000) ack 1 win 257 + +0 > . 1:1(0) ack 20001 win 18000 + + +0 read(4, ..., 20000) = 20000 +// A too big packet is accepted if the receive queue is empty + +0 < P. 20001:80001(60000) ack 1 win 257 + +0 > . 1:1(0) ack 80001 win 0 + diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 2e8243a65b50..d6c00efeb664 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -21,6 +21,7 @@ ALL_TESTS=" kci_test_vrf kci_test_encap kci_test_macsec + kci_test_macsec_vlan kci_test_ipsec kci_test_ipsec_offload kci_test_fdb_get @@ -30,6 +31,7 @@ ALL_TESTS=" kci_test_address_proto kci_test_enslave_bonding kci_test_mngtmpaddr + kci_test_operstate " devdummy="test-dummy0" @@ -291,6 +293,17 @@ kci_test_route_get() end_test "PASS: route get" } +check_addr_not_exist() +{ + dev=$1 + addr=$2 + if ip addr show dev $dev | grep -q $addr; then + return 1 + else + return 0 + fi +} + kci_test_addrlft() { for i in $(seq 10 100) ;do @@ -298,9 +311,8 @@ kci_test_addrlft() run_cmd ip addr add 10.23.11.$i/32 dev "$devdummy" preferred_lft $lft valid_lft $((lft+1)) done - sleep 5 - run_cmd_grep_fail "10.23.11." ip addr show dev "$devdummy" - if [ $? -eq 0 ]; then + slowwait 5 check_addr_not_exist "$devdummy" "10.23.11." + if [ $? -eq 1 ]; then check_err 1 end_test "FAIL: preferred_lft addresses remaining" return @@ -561,6 +573,41 @@ kci_test_macsec() end_test "PASS: macsec" } +# Test __dev_set_rx_mode call from dev_uc_add under addr_list_lock spinlock. +# Make sure __dev_set_promiscuity is not grabbing (sleeping) netdev instance +# lock. +# https://lore.kernel.org/netdev/2aff4342b0f5b1539c02ffd8df4c7e58dd9746e7.camel@nvidia.com/ +kci_test_macsec_vlan() +{ + msname="test_macsec1" + vlanname="test_vlan1" + local ret=0 + run_cmd_grep "^Usage: ip macsec" ip macsec help + if [ $? -ne 0 ]; then + end_test "SKIP: macsec: iproute2 too old" + return $ksft_skip + fi + run_cmd ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on + if [ $ret -ne 0 ];then + end_test "FAIL: can't add macsec interface, skipping test" + return 1 + fi + + run_cmd ip link set dev "$msname" up + ip link add link "$msname" name "$vlanname" type vlan id 1 + ip link set dev "$vlanname" address 00:11:22:33:44:88 + ip link set dev "$vlanname" up + run_cmd ip link del dev "$vlanname" + run_cmd ip link del dev "$msname" + + if [ $ret -ne 0 ];then + end_test "FAIL: macsec_vlan" + return 1 + fi + + end_test "PASS: macsec_vlan" +} + #------------------------------------------------------------------- # Example commands # ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \ @@ -673,6 +720,11 @@ kci_test_ipsec_offload() sysfsf=$sysfsd/ipsec sysfsnet=/sys/bus/netdevsim/devices/netdevsim0/net/ probed=false + esp4_offload_probed_default=false + + if lsmod | grep -q esp4_offload; then + esp4_offload_probed_default=true + fi if ! mount | grep -q debugfs; then mount -t debugfs none /sys/kernel/debug/ &> /dev/null @@ -766,6 +818,7 @@ EOF fi # clean up any leftovers + ! "$esp4_offload_probed_default" && lsmod | grep -q esp4_offload && rmmod esp4_offload echo 0 > /sys/bus/netdevsim/del_device $probed && rmmod netdevsim @@ -1334,6 +1387,39 @@ kci_test_mngtmpaddr() return $ret } +kci_test_operstate() +{ + local ret=0 + + # Check that it is possible to set operational state during device + # creation and that it is preserved when the administrative state of + # the device is toggled. + run_cmd ip link add name vx0 up state up type vxlan id 10010 dstport 4789 + run_cmd_grep "state UP" ip link show dev vx0 + run_cmd ip link set dev vx0 down + run_cmd_grep "state DOWN" ip link show dev vx0 + run_cmd ip link set dev vx0 up + run_cmd_grep "state UP" ip link show dev vx0 + + run_cmd ip link del dev vx0 + + # Check that it is possible to set the operational state of the device + # after creation. + run_cmd ip link add name vx0 up type vxlan id 10010 dstport 4789 + run_cmd_grep "state UNKNOWN" ip link show dev vx0 + run_cmd ip link set dev vx0 state up + run_cmd_grep "state UP" ip link show dev vx0 + + run_cmd ip link del dev vx0 + + if [ "$ret" -ne 0 ]; then + end_test "FAIL: operstate" + return 1 + fi + + end_test "PASS: operstate" +} + kci_test_rtnl() { local current_test diff --git a/tools/testing/selftests/net/rtnetlink_notification.sh b/tools/testing/selftests/net/rtnetlink_notification.sh new file mode 100755 index 000000000000..3f9780232bd6 --- /dev/null +++ b/tools/testing/selftests/net/rtnetlink_notification.sh @@ -0,0 +1,112 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking rtnetlink notification callpaths, and get as much +# coverage as possible. +# +# set -e + +ALL_TESTS=" + kci_test_mcast_addr_notification + kci_test_anycast_addr_notification +" + +source lib.sh +test_dev="test-dummy1" + +kci_test_mcast_addr_notification() +{ + RET=0 + local tmpfile + local monitor_pid + local match_result + + tmpfile=$(mktemp) + defer rm "$tmpfile" + + ip monitor maddr > $tmpfile & + monitor_pid=$! + defer kill_process "$monitor_pid" + + sleep 1 + + if [ ! -e "/proc/$monitor_pid" ]; then + RET=$ksft_skip + log_test "mcast addr notification: iproute2 too old" + return $RET + fi + + ip link add name "$test_dev" type dummy + check_err $? "failed to add dummy interface" + ip link set "$test_dev" up + check_err $? "failed to set dummy interface up" + ip link del dev "$test_dev" + check_err $? "Failed to delete dummy interface" + sleep 1 + + # There should be 4 line matches as follows. + # 13: test-dummy1 inet6 mcast ff02::1 scope global + # 13: test-dummy1 inet mcast 224.0.0.1 scope global + # Deleted 13: test-dummy1 inet mcast 224.0.0.1 scope global + # Deleted 13: test-dummy1 inet6 mcast ff02::1 scope global + match_result=$(grep -cE "$test_dev.*(224.0.0.1|ff02::1)" "$tmpfile") + if [ "$match_result" -ne 4 ]; then + RET=$ksft_fail + fi + log_test "mcast addr notification: Expected 4 matches, got $match_result" + return $RET +} + +kci_test_anycast_addr_notification() +{ + RET=0 + local tmpfile + local monitor_pid + local match_result + + tmpfile=$(mktemp) + defer rm "$tmpfile" + + ip monitor acaddress > "$tmpfile" & + monitor_pid=$! + defer kill_process "$monitor_pid" + sleep 1 + + if [ ! -e "/proc/$monitor_pid" ]; then + RET=$ksft_skip + log_test "anycast addr notification: iproute2 too old" + return "$RET" + fi + + ip link add name "$test_dev" type dummy + check_err $? "failed to add dummy interface" + ip link set "$test_dev" up + check_err $? "failed to set dummy interface up" + sysctl -qw net.ipv6.conf."$test_dev".forwarding=1 + ip link del dev "$test_dev" + check_err $? "Failed to delete dummy interface" + sleep 1 + + # There should be 2 line matches as follows. + # 9: dummy2 inet6 any fe80:: scope global + # Deleted 9: dummy2 inet6 any fe80:: scope global + match_result=$(grep -cE "$test_dev.*(fe80::)" "$tmpfile") + if [ "$match_result" -ne 2 ]; then + RET=$ksft_fail + fi + log_test "anycast addr notification: Expected 2 matches, got $match_result" + return "$RET" +} + +#check for needed privileges +if [ "$(id -u)" -ne 0 ];then + RET=$ksft_skip + log_test "need root privileges" + exit $RET +fi + +require_command ip + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh index ba730655a7bf..4bc135e5c22c 100755 --- a/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_next_csid_l3vpn_test.sh @@ -594,7 +594,7 @@ setup_rt_local_sids() dev "${DUMMY_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh index 4b86040c58c6..34b781a2ae74 100755 --- a/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_end_x_next_csid_l3vpn_test.sh @@ -72,6 +72,9 @@ # Every fcf0:0:x:y::/64 network interconnects the SRv6 routers rt-x with rt-y in # the selftest network. # +# In addition, every router interface connecting rt-x to rt-y is assigned an +# IPv6 link-local address fe80::x:y/64. +# # Local SID/C-SID table # ===================== # @@ -521,6 +524,9 @@ setup_rt_networking() ip -netns "${nsname}" addr \ add "${net_prefix}::${rt}/64" dev "${devname}" nodad + ip -netns "${nsname}" addr \ + add "fe80::${rt}:${neigh}/64" dev "${devname}" nodad + ip -netns "${nsname}" link set "${devname}" up done @@ -609,6 +615,27 @@ set_end_x_nextcsid() nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}" } +set_end_x_ll_nextcsid() +{ + local rt="$1" + local adj="$2" + + eval nsname=\${$(get_rtname "${rt}")} + lcnode_func_prefix="$(build_lcnode_func_prefix "${rt}")" + nh6_ll_addr="fe80::${adj}:${rt}" + oifname="veth-rt-${rt}-${adj}" + + # enabled NEXT-C-SID SRv6 End.X behavior via an IPv6 link-local nexthop + # address (note that "dev" is the dummy dum0 device chosen for the sake + # of simplicity). + ip -netns "${nsname}" -6 route \ + replace "${lcnode_func_prefix}" \ + table "${LOCALSID_TABLE_ID}" \ + encap seg6local action End.X nh6 "${nh6_ll_addr}" \ + oif "${oifname}" flavors next-csid lblen "${LCBLOCK_BLEN}" \ + nflen "${LCNODEFUNC_BLEN}" dev "${DUMMY_DEVNAME}" +} + set_underlay_sids_reachability() { local rt="$1" @@ -654,7 +681,7 @@ setup_rt_local_sids() set_underlay_sids_reachability "${rt}" "${rt_neighs}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ @@ -1016,6 +1043,27 @@ host_vpn_tests() check_and_log_hs_ipv4_connectivity 1 2 check_and_log_hs_ipv4_connectivity 2 1 + + # Setup the adjacencies in the SRv6 aware routers using IPv6 link-local + # addresses. + # - rt-3 SRv6 End.X adjacency with rt-4 + # - rt-4 SRv6 End.X adjacency with rt-1 + set_end_x_ll_nextcsid 3 4 + set_end_x_ll_nextcsid 4 1 + + log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv6), link-local" + + check_and_log_hs_ipv6_connectivity 1 2 + check_and_log_hs_ipv6_connectivity 2 1 + + log_section "SRv6 VPN connectivity test hosts (h1 <-> h2, IPv4), link-local" + + check_and_log_hs_ipv4_connectivity 1 2 + check_and_log_hs_ipv4_connectivity 2 1 + + # Restore the previous adjacencies. + set_end_x_nextcsid 3 4 + set_end_x_nextcsid 4 1 } __nextcsid_end_x_behavior_test() diff --git a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh index 3efce1718c5f..6a68c7eff1dc 100755 --- a/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hencap_red_l3vpn_test.sh @@ -395,7 +395,7 @@ setup_rt_local_sids() dev "${VRF_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behavior instaces are grouped together in the 'localsid' + # Endpoint behavior instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule \ add to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh index cabc70538ffe..0979b5316fdf 100755 --- a/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh +++ b/tools/testing/selftests/net/srv6_hl2encap_red_l2vpn_test.sh @@ -343,7 +343,7 @@ setup_rt_local_sids() encap seg6local action End dev "${DUMMY_DEVNAME}" # all SIDs for VPNs start with a common locator. Routes and SRv6 - # Endpoint behaviors instaces are grouped together in the 'localsid' + # Endpoint behaviors instances are grouped together in the 'localsid' # table. ip -netns "${nsname}" -6 rule add \ to "${VPN_LOCATOR_SERVICE}::/16" \ diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c index f00245263b20..6478da6a71c3 100644 --- a/tools/testing/selftests/net/tcp_ao/seq-ext.c +++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Check that after SEQ number wrap-around: * 1. SEQ-extension has upper bytes set - * 2. TCP conneciton is alive and no TCPAOBad segments + * 2. TCP connection is alive and no TCPAOBad segments * In order to test (2), the test doesn't just adjust seq number for a queue * on a connected socket, but migrates it to another sk+port number, so * that there won't be any delayed packets that will fail to verify diff --git a/tools/testing/selftests/net/test_neigh.sh b/tools/testing/selftests/net/test_neigh.sh new file mode 100755 index 000000000000..388056472b5b --- /dev/null +++ b/tools/testing/selftests/net/test_neigh.sh @@ -0,0 +1,366 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh +TESTS=" + extern_valid_ipv4 + extern_valid_ipv6 +" +VERBOSE=0 + +################################################################################ +# Utilities + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: $cmd" + stderr= + fi + + out=$(eval "$cmd" "$stderr") + rc=$? + if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +################################################################################ +# Setup + +setup() +{ + set -e + + setup_ns ns1 ns2 + + ip -n "$ns1" link add veth0 type veth peer name veth1 netns "$ns2" + ip -n "$ns1" link set dev veth0 up + ip -n "$ns2" link set dev veth1 up + + ip -n "$ns1" address add 192.0.2.1/24 dev veth0 + ip -n "$ns1" address add 2001:db8:1::1/64 dev veth0 nodad + ip -n "$ns2" address add 192.0.2.2/24 dev veth1 + ip -n "$ns2" address add 2001:db8:1::2/64 dev veth1 nodad + + ip netns exec "$ns1" sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + ip netns exec "$ns2" sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 + + sleep 5 + + set +e +} + +exit_cleanup_all() +{ + cleanup_all_ns + exit "${EXIT_STATUS}" +} + +################################################################################ +# Tests + +extern_valid_common() +{ + local af_str=$1; shift + local ip_addr=$1; shift + local tbl_name=$1; shift + local subnet=$1; shift + local mac + + mac=$(ip -n "$ns2" -j link show dev veth1 | jq -r '.[]["address"]') + + RET=0 + + # Check that simple addition works. + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "No \"extern_valid\" flag after addition" + + log_test "$af_str \"extern_valid\" flag: Add entry" + + RET=0 + + # Check that an entry cannot be added with "extern_valid" flag and an + # invalid state. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr nud none dev veth0 extern_valid" + check_fail $? "Managed to add an entry with \"extern_valid\" flag and an invalid state" + + log_test "$af_str \"extern_valid\" flag: Add with an invalid state" + + RET=0 + + # Check that entry cannot be added with both "extern_valid" flag and + # "use" / "managed" flag. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + check_fail $? "Managed to add an entry with \"extern_valid\" flag and \"use\" flag" + + log_test "$af_str \"extern_valid\" flag: Add with \"use\" flag" + + RET=0 + + # Check that "extern_valid" flag can be toggled using replace. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Did not manage to set \"extern_valid\" flag with replace" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_fail $? "Did not manage to clear \"extern_valid\" flag with replace" + + log_test "$af_str \"extern_valid\" flag: Replace entry" + + RET=0 + + # Check that an existing "extern_valid" entry can be marked as + # "managed". + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid managed" + check_err $? "Did not manage to add \"managed\" flag to an existing \"extern_valid\" entry" + + log_test "$af_str \"extern_valid\" flag: Replace entry with \"managed\" flag" + + RET=0 + + # Check that entry cannot be replaced with "extern_valid" flag and an + # invalid state. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr nud none dev veth0 extern_valid" + check_fail $? "Managed to replace an entry with \"extern_valid\" flag and an invalid state" + + log_test "$af_str \"extern_valid\" flag: Replace with an invalid state" + + RET=0 + + # Check that an "extern_valid" entry is flushed when the interface is + # put administratively down. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 link set dev veth0 down" + run_cmd "ip -n $ns1 link set dev veth0 up" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0" + check_fail $? "\"extern_valid\" entry not flushed upon interface down" + + log_test "$af_str \"extern_valid\" flag: Interface down" + + RET=0 + + # Check that an "extern_valid" entry is not flushed when the interface + # loses its carrier. + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns2 link set dev veth1 down" + run_cmd "ip -n $ns2 link set dev veth1 up" + run_cmd "sleep 2" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0" + check_err $? "\"extern_valid\" entry flushed upon carrier down" + + log_test "$af_str \"extern_valid\" flag: Carrier down" + + RET=0 + + # Check that when entry transitions to "reachable" state it maintains + # the "extern_valid" flag. Wait "delay_probe" seconds for ARP request / + # NS to be sent. + local delay_probe + + delay_probe=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["delay_probe"]') + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + run_cmd "sleep $((delay_probe / 1000 + 2))" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"REACHABLE\"" + check_err $? "Entry did not transition to \"reachable\" state" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry did not maintain \"extern_valid\" flag after transition to \"reachable\" state" + + log_test "$af_str \"extern_valid\" flag: Transition to \"reachable\" state" + + RET=0 + + # Drop all packets, trigger resolution and check that entry goes back + # to "stale" state instead of "failed". + local mcast_reprobes + local retrans_time + local ucast_probes + local app_probes + local probes + local delay + + run_cmd "ip -n $ns1 neigh flush dev veth0" + run_cmd "tc -n $ns2 qdisc add dev veth1 clsact" + run_cmd "tc -n $ns2 filter add dev veth1 ingress proto all matchall action drop" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh replace $ip_addr lladdr $mac nud stale dev veth0 extern_valid use" + retrans_time=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["retrans"]') + ucast_probes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["ucast_probes"]') + app_probes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["app_probes"]') + mcast_reprobes=$(ip -n "$ns1" -j ntable show dev veth0 name "$tbl_name" | jq '.[]["mcast_reprobes"]') + delay=$((delay_probe + (ucast_probes + app_probes + mcast_reprobes) * retrans_time)) + run_cmd "sleep $((delay / 1000 + 2))" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"STALE\"" + check_err $? "Entry did not return to \"stale\" state" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry did not maintain \"extern_valid\" flag after returning to \"stale\" state" + probes=$(ip -n "$ns1" -j -s neigh get "$ip_addr" dev veth0 | jq '.[]["probes"]') + if [[ $probes -eq 0 ]]; then + check_err 1 "No probes were sent" + fi + + log_test "$af_str \"extern_valid\" flag: Transition back to \"stale\" state" + + run_cmd "tc -n $ns2 qdisc del dev veth1 clsact" + + RET=0 + + # Forced garbage collection runs whenever the number of entries is + # larger than "thresh3" and deletes stale entries that have not been + # updated in the last 5 seconds. + # + # Check that an "extern_valid" entry survives a forced garbage + # collection. Add an entry, wait 5 seconds and add more entries than + # "thresh3" so that forced garbage collection will run. + # + # Note that the garbage collection thresholds are global resources and + # that changes in the initial namespace affect all the namespaces. + local forced_gc_runs_t0 + local forced_gc_runs_t1 + local orig_thresh1 + local orig_thresh2 + local orig_thresh3 + + run_cmd "ip -n $ns1 neigh flush dev veth0" + orig_thresh1=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["thresh1"]') + orig_thresh2=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh2")) | .["thresh2"]') + orig_thresh3=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh3")) | .["thresh3"]') + run_cmd "ip ntable change name $tbl_name thresh3 10 thresh2 9 thresh1 8" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh add ${subnet}3 lladdr $mac nud stale dev veth0" + run_cmd "sleep 5" + forced_gc_runs_t0=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("forced_gc_runs")) | .["forced_gc_runs"]') + for i in {1..20}; do + run_cmd "ip -n $ns1 neigh add ${subnet}$((i + 4)) nud none dev veth0" + done + forced_gc_runs_t1=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("forced_gc_runs")) | .["forced_gc_runs"]') + if [[ $forced_gc_runs_t1 -eq $forced_gc_runs_t0 ]]; then + check_err 1 "Forced garbage collection did not run" + fi + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry with \"extern_valid\" flag did not survive forced garbage collection" + run_cmd "ip -n $ns1 neigh get ${subnet}3 dev veth0" + check_fail $? "Entry without \"extern_valid\" flag survived forced garbage collection" + + log_test "$af_str \"extern_valid\" flag: Forced garbage collection" + + run_cmd "ip ntable change name $tbl_name thresh3 $orig_thresh3 thresh2 $orig_thresh2 thresh1 $orig_thresh1" + + RET=0 + + # Periodic garbage collection runs every "base_reachable"/2 seconds and + # if the number of entries is larger than "thresh1", then it deletes + # stale entries that have not been used in the last "gc_stale" seconds. + # + # Check that an "extern_valid" entry survives a periodic garbage + # collection. Add an "extern_valid" entry, add more than "thresh1" + # regular entries, wait "base_reachable" (longer than "gc_stale") + # seconds and check that the "extern_valid" entry was not deleted. + # + # Note that the garbage collection thresholds and "base_reachable" are + # global resources and that changes in the initial namespace affect all + # the namespaces. + local periodic_gc_runs_t0 + local periodic_gc_runs_t1 + local orig_base_reachable + local orig_gc_stale + + run_cmd "ip -n $ns1 neigh flush dev veth0" + orig_thresh1=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["thresh1"]') + orig_base_reachable=$(ip -j ntable show name "$tbl_name" | jq '.[] | select(has("thresh1")) | .["base_reachable"]') + run_cmd "ip ntable change name $tbl_name thresh1 10 base_reachable 10000" + orig_gc_stale=$(ip -n "$ns1" -j ntable show name "$tbl_name" dev veth0 | jq '.[]["gc_stale"]') + run_cmd "ip -n $ns1 ntable change name $tbl_name dev veth0 gc_stale 5000" + # Wait orig_base_reachable/2 for the new interval to take effect. + run_cmd "sleep $(((orig_base_reachable / 1000) / 2 + 2))" + run_cmd "ip -n $ns1 neigh add $ip_addr lladdr $mac nud stale dev veth0 extern_valid" + run_cmd "ip -n $ns1 neigh add ${subnet}3 lladdr $mac nud stale dev veth0" + for i in {1..20}; do + run_cmd "ip -n $ns1 neigh add ${subnet}$((i + 4)) nud none dev veth0" + done + periodic_gc_runs_t0=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("periodic_gc_runs")) | .["periodic_gc_runs"]') + run_cmd "sleep 10" + periodic_gc_runs_t1=$(ip -j -s ntable show name "$tbl_name" | jq '.[] | select(has("periodic_gc_runs")) | .["periodic_gc_runs"]') + [[ $periodic_gc_runs_t1 -ne $periodic_gc_runs_t0 ]] + check_err $? "Periodic garbage collection did not run" + run_cmd "ip -n $ns1 neigh get $ip_addr dev veth0 | grep \"extern_valid\"" + check_err $? "Entry with \"extern_valid\" flag did not survive periodic garbage collection" + run_cmd "ip -n $ns1 neigh get ${subnet}3 dev veth0" + check_fail $? "Entry without \"extern_valid\" flag survived periodic garbage collection" + + log_test "$af_str \"extern_valid\" flag: Periodic garbage collection" + + run_cmd "ip -n $ns1 ntable change name $tbl_name dev veth0 gc_stale $orig_gc_stale" + run_cmd "ip ntable change name $tbl_name thresh1 $orig_thresh1 base_reachable $orig_base_reachable" +} + +extern_valid_ipv4() +{ + extern_valid_common "IPv4" 192.0.2.2 "arp_cache" 192.0.2. +} + +extern_valid_ipv6() +{ + extern_valid_common "IPv6" 2001:db8:1::2 "ndisc_cache" 2001:db8:1:: +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -v Verbose mode (show commands and output) +EOF +} + +################################################################################ +# Main + +while getopts ":t:pvh" opt; do + case $opt in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$((VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +require_command jq + +if ! ip neigh help 2>&1 | grep -q "extern_valid"; then + echo "SKIP: iproute2 ip too old, missing \"extern_valid\" support" + exit "$ksft_skip" +fi + +trap exit_cleanup_all EXIT + +for t in $TESTS +do + setup; $t; cleanup_all_ns; +done diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh index 6127a78ee988..8deacc565afa 100755 --- a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh +++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh @@ -146,18 +146,17 @@ run_cmd() } check_hv_connectivity() { - ip netns exec $hv_1 ping -c 1 -W 1 $1 &>/dev/null - sleep 1 - ip netns exec $hv_1 ping -c 1 -W 1 $2 &>/dev/null + slowwait 5 ip netns exec $hv_1 ping -c 1 -W 1 $1 &>/dev/null + slowwait 5 ip netns exec $hv_1 ping -c 1 -W 1 $2 &>/dev/null return $? } check_vm_connectivity() { - run_cmd "ip netns exec $vm_11 ping -c 1 -W 1 10.0.10.12" + slowwait 5 run_cmd "ip netns exec $vm_11 ping -c 1 -W 1 10.0.10.12" log_test $? 0 "VM connectivity over $1 (ipv4 default rdst)" - run_cmd "ip netns exec $vm_21 ping -c 1 -W 1 10.0.10.22" + slowwait 5 run_cmd "ip netns exec $vm_21 ping -c 1 -W 1 10.0.10.22" log_test $? 0 "VM connectivity over $1 (ipv6 default rdst)" } diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh index e9c2f71da207..ce34cb2e6e0b 100755 --- a/tools/testing/selftests/net/vrf_route_leaking.sh +++ b/tools/testing/selftests/net/vrf_route_leaking.sh @@ -275,7 +275,7 @@ setup_sym() # Wait for ip config to settle - sleep 2 + slowwait 5 ip netns exec $h1 "${ping6}" -c1 -w1 ${H2_N2_IP6} >/dev/null 2>&1 } setup_asym() @@ -370,7 +370,7 @@ setup_asym() ip -netns $r2 -6 addr add dev eth1 ${R2_N2_IP6}/64 nodad # Wait for ip config to settle - sleep 2 + slowwait 5 ip netns exec $h1 "${ping6}" -c1 -w1 ${H2_N2_IP6} >/dev/null 2>&1 } check_connectivity() |