From 9c2a2a45136de428b73907195a4a99eb78dc3aca Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Mon, 18 Nov 2024 22:03:42 +0100 Subject: selftest/bpf: Add test for af_vsock poll() Verify that vsock's poll() notices when sk_psock::ingress_msg isn't empty. Signed-off-by: Michal Luczaj Acked-by: Stefano Garzarella Link: https://lore.kernel.org/r/20241118-vsock-bpf-poll-close-v1-2-f1b9669cacdc@rbox.co Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend --- .../selftests/bpf/prog_tests/sockmap_basic.c | 46 ++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index a2041f8e32eb..6a9aab2d051a 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -937,6 +937,50 @@ out: test_sockmap_pass_prog__destroy(skel); } +static void test_sockmap_skb_verdict_vsock_poll(void) +{ + struct test_sockmap_pass_prog *skel; + int err, map, conn, peer; + struct bpf_program *prog; + struct bpf_link *link; + char buf = 'x'; + int zero = 0; + + skel = test_sockmap_pass_prog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + if (create_pair(AF_VSOCK, SOCK_STREAM, &conn, &peer)) + goto destroy; + + prog = skel->progs.prog_skb_verdict; + map = bpf_map__fd(skel->maps.sock_map_rx); + link = bpf_program__attach_sockmap(prog, map); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap")) + goto close; + + err = bpf_map_update_elem(map, &zero, &conn, BPF_ANY); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + goto detach; + + if (xsend(peer, &buf, 1, 0) != 1) + goto detach; + + err = poll_read(conn, IO_TIMEOUT_SEC); + if (!ASSERT_OK(err, "poll")) + goto detach; + + if (xrecv_nonblock(conn, &buf, 1, 0) != 1) + FAIL("xrecv_nonblock"); +detach: + bpf_link__detach(link); +close: + xclose(conn); + xclose(peer); +destroy: + test_sockmap_pass_prog__destroy(skel); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -997,4 +1041,6 @@ void test_sockmap_basic(void) test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKMAP); if (test__start_subtest("sockhash sk_msg attach sockhash helpers with link")) test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKHASH); + if (test__start_subtest("sockmap skb_verdict vsock poll")) + test_sockmap_skb_verdict_vsock_poll(); } -- cgit v1.3.1 From 515745445e92500e8916ffe29cc4893ad97517b8 Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Mon, 18 Nov 2024 22:03:44 +0100 Subject: selftest/bpf: Add test for vsock removal from sockmap on close() Make sure the proto::close callback gets invoked on vsock release. Signed-off-by: Michal Luczaj Acked-by: Stefano Garzarella Link: https://lore.kernel.org/r/20241118-vsock-bpf-poll-close-v1-4-f1b9669cacdc@rbox.co Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend --- .../selftests/bpf/prog_tests/sockmap_basic.c | 31 ++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 6a9aab2d051a..fdff0652d7ef 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -108,6 +108,35 @@ out: close(s); } +static void test_sockmap_vsock_delete_on_close(void) +{ + int err, c, p, map; + const int zero = 0; + + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair(AF_VSOCK)")) + return; + + map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), + sizeof(int), 1, NULL); + if (!ASSERT_GE(map, 0, "bpf_map_create")) { + close(c); + goto out; + } + + err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); + close(c); + if (!ASSERT_OK(err, "bpf_map_update")) + goto out; + + err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + ASSERT_OK(err, "after close(), bpf_map_update"); + +out: + close(p); + close(map); +} + static void test_skmsg_helpers(enum bpf_map_type map_type) { struct test_skmsg_load_helpers *skel; @@ -987,6 +1016,8 @@ void test_sockmap_basic(void) test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP); if (test__start_subtest("sockhash create_update_free")) test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH); + if (test__start_subtest("sockmap vsock delete on close")) + test_sockmap_vsock_delete_on_close(); if (test__start_subtest("sockmap sk_msg load helpers")) test_skmsg_helpers(BPF_MAP_TYPE_SOCKMAP); if (test__start_subtest("sockhash sk_msg load helpers")) -- cgit v1.3.1 From 6b64128a74ebcacc5a0de5a74834e3b9f47a354c Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 19 Nov 2024 17:18:19 +0100 Subject: selftests/bpf: Check for PREEMPTION instead of PREEMPT CONFIG_PREEMPT is a preemtion model the so called "Low-Latency Desktop". A different preemption model is PREEMPT_RT the so called "Real-Time". Both implement preemption in kernel and set CONFIG_PREEMPTION. There is also the so called "LAZY PREEMPT" which the "Scheduler controlled preemption model". Here we have also preemption in the kernel the rules are slightly different. Therefore the testsuite should not check for CONFIG_PREEMPT (as one model) but for CONFIG_PREEMPTION to figure out if preemption in the kernel is possible. Signed-off-by: Sebastian Andrzej Siewior Link: https://lore.kernel.org/r/20241119161819.qvEcs-n_@linutronix.de Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/map_tests/task_storage_map.c | 4 ++-- tools/testing/selftests/bpf/prog_tests/task_local_storage.c | 2 +- tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c | 4 ++-- tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c | 4 ++-- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/map_tests/task_storage_map.c b/tools/testing/selftests/bpf/map_tests/task_storage_map.c index 62971dbf2996..a4121d2248ac 100644 --- a/tools/testing/selftests/bpf/map_tests/task_storage_map.c +++ b/tools/testing/selftests/bpf/map_tests/task_storage_map.c @@ -78,8 +78,8 @@ void test_task_storage_map_stress_lookup(void) CHECK(err, "open_and_load", "error %d\n", err); /* Only for a fully preemptible kernel */ - if (!skel->kconfig->CONFIG_PREEMPT) { - printf("%s SKIP (no CONFIG_PREEMPT)\n", __func__); + if (!skel->kconfig->CONFIG_PREEMPTION) { + printf("%s SKIP (no CONFIG_PREEMPTION)\n", __func__); read_bpf_task_storage_busy__destroy(skel); skips++; return; diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c index 60f474d965a9..42e822ea352f 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c @@ -197,7 +197,7 @@ static void test_nodeadlock(void) /* Unnecessary recursion and deadlock detection are reproducible * in the preemptible kernel. */ - if (!skel->kconfig->CONFIG_PREEMPT) { + if (!skel->kconfig->CONFIG_PREEMPTION) { test__skip(); goto done; } diff --git a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c index 76556e0b42b2..69da05bb6c63 100644 --- a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c +++ b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c @@ -4,7 +4,7 @@ #include #include -extern bool CONFIG_PREEMPT __kconfig __weak; +extern bool CONFIG_PREEMPTION __kconfig __weak; extern const int bpf_task_storage_busy __ksym; char _license[] SEC("license") = "GPL"; @@ -24,7 +24,7 @@ int BPF_PROG(read_bpf_task_storage_busy) { int *value; - if (!CONFIG_PREEMPT) + if (!CONFIG_PREEMPTION) return 0; if (bpf_get_current_pid_tgid() >> 32 != pid) diff --git a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c index ea2dbb80f7b3..986829aaf73a 100644 --- a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c +++ b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c @@ -10,7 +10,7 @@ char _license[] SEC("license") = "GPL"; #define EBUSY 16 #endif -extern bool CONFIG_PREEMPT __kconfig __weak; +extern bool CONFIG_PREEMPTION __kconfig __weak; int nr_get_errs = 0; int nr_del_errs = 0; @@ -29,7 +29,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type, int ret, zero = 0; int *value; - if (!CONFIG_PREEMPT) + if (!CONFIG_PREEMPTION) return 0; task = bpf_get_current_task_btf(); -- cgit v1.3.1 From 3448ad23b34e43a2526bd0f9e1221e8de876adec Mon Sep 17 00:00:00 2001 From: Zijian Zhang Date: Wed, 16 Oct 2024 23:48:37 +0000 Subject: selftests/bpf: Add apply_bytes test to test_txmsg_redir_wait_sndmem in test_sockmap Add this to more comprehensively test the socket memory accounting logic in the __SK_REDIRECT and __SK_DROP cases of tcp_bpf_sendmsg. We don't have test when apply_bytes are not zero in test_txmsg_redir_wait_sndmem. test_send_large has opt->rate=2, it will invoke sendmsg two times. Specifically, the first sendmsg will trigger the case where the ret value of tcp_bpf_sendmsg_redir is less than 0; while the second sendmsg happens after the 3 seconds timeout, and it will trigger __SK_DROP because socket c2 has been removed from the sockmap/hash. Signed-off-by: Zijian Zhang Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20241016234838.3167769-2-zijianzhang@bytedance.com --- tools/testing/selftests/bpf/test_sockmap.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index e5c7ecbe57e3..fd2da2234cc9 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1579,8 +1579,12 @@ static void test_txmsg_redir(int cgrp, struct sockmap_options *opt) static void test_txmsg_redir_wait_sndmem(int cgrp, struct sockmap_options *opt) { - txmsg_redir = 1; opt->tx_wait_mem = true; + txmsg_redir = 1; + test_send_large(opt, cgrp); + + txmsg_redir = 1; + txmsg_apply = 4097; test_send_large(opt, cgrp); opt->tx_wait_mem = false; } -- cgit v1.3.1 From 12659d28615d606b36e382f4de2dd05550d202af Mon Sep 17 00:00:00 2001 From: Tao Lyu Date: Mon, 2 Dec 2024 16:02:37 -0800 Subject: bpf: Ensure reg is PTR_TO_STACK in process_iter_arg Currently, KF_ARG_PTR_TO_ITER handling missed checking the reg->type and ensuring it is PTR_TO_STACK. Instead of enforcing this in the caller of process_iter_arg, move the check into it instead so that all callers will gain the check by default. This is similar to process_dynptr_func. An existing selftest in verifier_bits_iter.c fails due to this change, but it's because it was passing a NULL pointer into iter_next helper and getting an error further down the checks, but probably meant to pass an uninitialized iterator on the stack (as is done in the subsequent test below it). We will gain coverage for non-PTR_TO_STACK arguments in later patches hence just change the declaration to zero-ed stack object. Fixes: 06accc8779c1 ("bpf: add support for open-coded iterator loops") Suggested-by: Andrii Nakryiko Signed-off-by: Tao Lyu [ Kartikeya: move check into process_iter_arg, rewrite commit log ] Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20241203000238.3602922-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 5 +++++ tools/testing/selftests/bpf/progs/verifier_bits_iter.c | 4 ++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'tools/testing') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1c4ebb326785..358a3566bb60 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8189,6 +8189,11 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id const struct btf_type *t; int spi, err, i, nr_slots, btf_id; + if (reg->type != PTR_TO_STACK) { + verbose(env, "arg#%d expected pointer to an iterator on stack\n", regno - 1); + return -EINVAL; + } + /* For iter_{new,next,destroy} functions, btf_check_iter_kfuncs() * ensures struct convention, so we wouldn't need to do any BTF * validation here. But given iter state can be passed as a parameter diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c index 7c881bca9af5..a7a6ae6c162f 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -35,9 +35,9 @@ __description("uninitialized iter in ->next()") __failure __msg("expected an initialized iter_bits as arg #1") int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) { - struct bpf_iter_bits *it = NULL; + struct bpf_iter_bits it = {}; - bpf_iter_bits_next(it); + bpf_iter_bits_next(&it); return 0; } -- cgit v1.3.1 From 7f71197001e35f46aca97204986edf9301f8dd09 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 2 Dec 2024 16:02:38 -0800 Subject: selftests/bpf: Add tests for iter arg check Add selftests to cover argument type check for iterator kfuncs, and cover all three kinds (new, next, destroy). Without the fix in the previous patch, the selftest would not cause a verifier error. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20241203000238.3602922-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/progs/iters.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index ef70b88bccb2..7c969c127573 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -1486,4 +1486,30 @@ int iter_subprog_check_stacksafe(const void *ctx) return 0; } +struct bpf_iter_num global_it; + +SEC("raw_tp") +__failure __msg("arg#0 expected pointer to an iterator on stack") +int iter_new_bad_arg(const void *ctx) +{ + bpf_iter_num_new(&global_it, 0, 1); + return 0; +} + +SEC("raw_tp") +__failure __msg("arg#0 expected pointer to an iterator on stack") +int iter_next_bad_arg(const void *ctx) +{ + bpf_iter_num_next(&global_it); + return 0; +} + +SEC("raw_tp") +__failure __msg("arg#0 expected pointer to an iterator on stack") +int iter_destroy_bad_arg(const void *ctx) +{ + bpf_iter_num_destroy(&global_it); + return 0; +} + char _license[] SEC("license") = "GPL"; -- cgit v1.3.1 From bd74e238ae6944b462f57ce8752440a011ba4530 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 2 Dec 2024 16:22:35 -0800 Subject: bpf: Zero index arg error string for dynptr and iter Andrii spotted that process_dynptr_func's rejection of incorrect argument register type will print an error string where argument numbers are not zero-indexed, unlike elsewhere in the verifier. Fix this by subtracting 1 from regno. The same scenario exists for iterator messages. Fix selftest error strings that match on the exact argument number while we're at it to ensure clean bisection. Suggested-by: Andrii Nakryiko Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20241203002235.3776418-1-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 12 ++++++------ tools/testing/selftests/bpf/progs/dynptr_fail.c | 22 +++++++++++----------- .../selftests/bpf/progs/iters_state_safety.c | 14 +++++++------- .../selftests/bpf/progs/iters_testmod_seq.c | 4 ++-- .../selftests/bpf/progs/test_kfunc_dynptr_param.c | 2 +- .../selftests/bpf/progs/verifier_bits_iter.c | 4 ++-- 6 files changed, 29 insertions(+), 29 deletions(-) (limited to 'tools/testing') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 358a3566bb60..2fd35465d650 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8071,7 +8071,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) { verbose(env, "arg#%d expected pointer to stack or const struct bpf_dynptr\n", - regno); + regno - 1); return -EINVAL; } @@ -8125,7 +8125,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn if (!is_dynptr_reg_valid_init(env, reg)) { verbose(env, "Expected an initialized dynptr as arg #%d\n", - regno); + regno - 1); return -EINVAL; } @@ -8133,7 +8133,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn if (!is_dynptr_type_expected(env, reg, arg_type & ~MEM_RDONLY)) { verbose(env, "Expected a dynptr of type %s as arg #%d\n", - dynptr_type_str(arg_to_dynptr_type(arg_type)), regno); + dynptr_type_str(arg_to_dynptr_type(arg_type)), regno - 1); return -EINVAL; } @@ -8202,7 +8202,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id */ btf_id = btf_check_iter_arg(meta->btf, meta->func_proto, regno - 1); if (btf_id < 0) { - verbose(env, "expected valid iter pointer as arg #%d\n", regno); + verbose(env, "expected valid iter pointer as arg #%d\n", regno - 1); return -EINVAL; } t = btf_type_by_id(meta->btf, btf_id); @@ -8212,7 +8212,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id /* bpf_iter__new() expects pointer to uninit iter state */ if (!is_iter_reg_valid_uninit(env, reg, nr_slots)) { verbose(env, "expected uninitialized iter_%s as arg #%d\n", - iter_type_str(meta->btf, btf_id), regno); + iter_type_str(meta->btf, btf_id), regno - 1); return -EINVAL; } @@ -8236,7 +8236,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id break; case -EINVAL: verbose(env, "expected an initialized iter_%s as arg #%d\n", - iter_type_str(meta->btf, btf_id), regno); + iter_type_str(meta->btf, btf_id), regno - 1); return err; case -EPROTO: verbose(env, "expected an RCU CS when using %s\n", meta->func_name); diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index 8f36c9de7591..dfd817d0348c 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -149,7 +149,7 @@ int ringbuf_release_uninit_dynptr(void *ctx) /* A dynptr can't be used after it has been invalidated */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int use_after_invalid(void *ctx) { struct bpf_dynptr ptr; @@ -428,7 +428,7 @@ int invalid_helper2(void *ctx) /* A bpf_dynptr is invalidated if it's been written into */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int invalid_write1(void *ctx) { struct bpf_dynptr ptr; @@ -1407,7 +1407,7 @@ int invalid_slice_rdwr_rdonly(struct __sk_buff *skb) /* bpf_dynptr_adjust can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_adjust_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1420,7 +1420,7 @@ int dynptr_adjust_invalid(void *ctx) /* bpf_dynptr_is_null can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_is_null_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1433,7 +1433,7 @@ int dynptr_is_null_invalid(void *ctx) /* bpf_dynptr_is_rdonly can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_is_rdonly_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1446,7 +1446,7 @@ int dynptr_is_rdonly_invalid(void *ctx) /* bpf_dynptr_size can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_size_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1459,7 +1459,7 @@ int dynptr_size_invalid(void *ctx) /* Only initialized dynptrs can be cloned */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int clone_invalid1(void *ctx) { struct bpf_dynptr ptr1 = {}; @@ -1493,7 +1493,7 @@ int clone_invalid2(struct xdp_md *xdp) /* Invalidating a dynptr should invalidate its clones */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int clone_invalidate1(void *ctx) { struct bpf_dynptr clone; @@ -1514,7 +1514,7 @@ int clone_invalidate1(void *ctx) /* Invalidating a dynptr should invalidate its parent */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int clone_invalidate2(void *ctx) { struct bpf_dynptr ptr; @@ -1535,7 +1535,7 @@ int clone_invalidate2(void *ctx) /* Invalidating a dynptr should invalidate its siblings */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int clone_invalidate3(void *ctx) { struct bpf_dynptr ptr; @@ -1723,7 +1723,7 @@ __noinline long global_call_bpf_dynptr(const struct bpf_dynptr *dynptr) } SEC("?raw_tp") -__failure __msg("arg#1 expected pointer to stack or const struct bpf_dynptr") +__failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr") int test_dynptr_reg_type(void *ctx) { struct task_struct *current = NULL; diff --git a/tools/testing/selftests/bpf/progs/iters_state_safety.c b/tools/testing/selftests/bpf/progs/iters_state_safety.c index d47e59aba6de..f41257eadbb2 100644 --- a/tools/testing/selftests/bpf/progs/iters_state_safety.c +++ b/tools/testing/selftests/bpf/progs/iters_state_safety.c @@ -73,7 +73,7 @@ int create_and_forget_to_destroy_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int destroy_without_creating_fail(void *ctx) { /* init with zeros to stop verifier complaining about uninit stack */ @@ -91,7 +91,7 @@ int destroy_without_creating_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int compromise_iter_w_direct_write_fail(void *ctx) { struct bpf_iter_num iter; @@ -143,7 +143,7 @@ int compromise_iter_w_direct_write_and_skip_destroy_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int compromise_iter_w_helper_write_fail(void *ctx) { struct bpf_iter_num iter; @@ -230,7 +230,7 @@ int valid_stack_reuse(void *ctx) } SEC("?raw_tp") -__failure __msg("expected uninitialized iter_num as arg #1") +__failure __msg("expected uninitialized iter_num as arg #0") int double_create_fail(void *ctx) { struct bpf_iter_num iter; @@ -258,7 +258,7 @@ int double_create_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int double_destroy_fail(void *ctx) { struct bpf_iter_num iter; @@ -284,7 +284,7 @@ int double_destroy_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int next_without_new_fail(void *ctx) { struct bpf_iter_num iter; @@ -305,7 +305,7 @@ int next_without_new_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int next_after_destroy_fail(void *ctx) { struct bpf_iter_num iter; diff --git a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c index 4a176e6aede8..6543d5b6e0a9 100644 --- a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c +++ b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c @@ -79,7 +79,7 @@ int testmod_seq_truncated(const void *ctx) SEC("?raw_tp") __failure -__msg("expected an initialized iter_testmod_seq as arg #2") +__msg("expected an initialized iter_testmod_seq as arg #1") int testmod_seq_getter_before_bad(const void *ctx) { struct bpf_iter_testmod_seq it; @@ -89,7 +89,7 @@ int testmod_seq_getter_before_bad(const void *ctx) SEC("?raw_tp") __failure -__msg("expected an initialized iter_testmod_seq as arg #2") +__msg("expected an initialized iter_testmod_seq as arg #1") int testmod_seq_getter_after_bad(const void *ctx) { struct bpf_iter_testmod_seq it; diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c index e68667aec6a6..cd4d752bd089 100644 --- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c @@ -45,7 +45,7 @@ int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size) } SEC("?lsm.s/bpf") -__failure __msg("arg#1 expected pointer to stack or const struct bpf_dynptr") +__failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr") int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size) { unsigned long val = 0; diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c index a7a6ae6c162f..8bcddadfc4da 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -32,7 +32,7 @@ int BPF_PROG(no_destroy, struct bpf_iter_meta *meta, struct cgroup *cgrp) SEC("iter/cgroup") __description("uninitialized iter in ->next()") -__failure __msg("expected an initialized iter_bits as arg #1") +__failure __msg("expected an initialized iter_bits as arg #0") int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) { struct bpf_iter_bits it = {}; @@ -43,7 +43,7 @@ int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) SEC("iter/cgroup") __description("uninitialized iter in ->destroy()") -__failure __msg("expected an initialized iter_bits as arg #1") +__failure __msg("expected an initialized iter_bits as arg #0") int BPF_PROG(destroy_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) { struct bpf_iter_bits it = {}; -- cgit v1.3.1 From adfdd9c68566120debc622712888c4d084539081 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Tue, 3 Dec 2024 20:47:55 -0800 Subject: selftests/bpf: Introduce __caps_unpriv annotation for tests Add a __caps_unpriv annotation so that tests requiring specific capabilities while dropping the rest can conveniently specify them during selftest declaration instead of munging with capabilities at runtime from the testing binary. While at it, let us convert test_verifier_mtu to use this new support instead. Since we do not want to include linux/capability.h, we only defined the four main capabilities BPF subsystem deals with in bpf_misc.h for use in tests. If the user passes a CAP_SYS_NICE or anything else that's not defined in the header, capability parsing code will return a warning. Also reject strtol returning 0. CAP_CHOWN = 0 but we'll never need to use it, and strtol doesn't errno on failed conversion. Fail the test in such a case. The original diff for this idea is available at link [0]. [0]: https://lore.kernel.org/bpf/a1e48f5d9ae133e19adc6adf27e19d585e06bab4.camel@gmail.com Signed-off-by: Eduard Zingerman [ Kartikeya: rebase on bpf-next, add warn to parse_caps, convert test_verifier_mtu ] Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20241204044757.1483141-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/prog_tests/verifier.c | 19 +--------- tools/testing/selftests/bpf/progs/bpf_misc.h | 12 ++++++ tools/testing/selftests/bpf/progs/verifier_mtu.c | 4 +- tools/testing/selftests/bpf/test_loader.c | 46 +++++++++++++++++++++++ 4 files changed, 62 insertions(+), 19 deletions(-) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index d9f65adb456b..3ee40ee9413a 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -225,24 +225,7 @@ void test_verifier_xdp(void) { RUN(verifier_xdp); } void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); } void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); } void test_verifier_lsm(void) { RUN(verifier_lsm); } - -void test_verifier_mtu(void) -{ - __u64 caps = 0; - int ret; - - /* In case CAP_BPF and CAP_PERFMON is not set */ - ret = cap_enable_effective(1ULL << CAP_BPF | 1ULL << CAP_NET_ADMIN, &caps); - if (!ASSERT_OK(ret, "set_cap_bpf_cap_net_admin")) - return; - ret = cap_disable_effective(1ULL << CAP_SYS_ADMIN | 1ULL << CAP_PERFMON, NULL); - if (!ASSERT_OK(ret, "disable_cap_sys_admin")) - goto restore_cap; - RUN(verifier_mtu); -restore_cap: - if (caps) - cap_enable_effective(caps, NULL); -} +void test_verifier_mtu(void) { RUN(verifier_mtu); } static int init_test_val_map(struct bpf_object *obj, char *map_name) { diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index eccaf955e394..f45f4352feeb 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -5,6 +5,10 @@ #define XSTR(s) STR(s) #define STR(s) #s +/* Expand a macro and then stringize the expansion */ +#define QUOTE(str) #str +#define EXPAND_QUOTE(str) QUOTE(str) + /* This set of attributes controls behavior of the * test_loader.c:test_loader__run_subtests(). * @@ -106,6 +110,7 @@ * __arch_* Specify on which architecture the test case should be tested. * Several __arch_* annotations could be specified at once. * When test case is not run on current arch it is marked as skipped. + * __caps_unpriv Specify the capabilities that should be set when running the test. */ #define __msg(msg) __attribute__((btf_decl_tag("comment:test_expect_msg=" XSTR(__COUNTER__) "=" msg))) #define __xlated(msg) __attribute__((btf_decl_tag("comment:test_expect_xlated=" XSTR(__COUNTER__) "=" msg))) @@ -129,6 +134,13 @@ #define __arch_x86_64 __arch("X86_64") #define __arch_arm64 __arch("ARM64") #define __arch_riscv64 __arch("RISCV64") +#define __caps_unpriv(caps) __attribute__((btf_decl_tag("comment:test_caps_unpriv=" EXPAND_QUOTE(caps)))) + +/* Define common capabilities tested using __caps_unpriv */ +#define CAP_NET_ADMIN 12 +#define CAP_SYS_ADMIN 21 +#define CAP_PERFMON 38 +#define CAP_BPF 39 /* Convenience macro for use with 'asm volatile' blocks */ #define __naked __attribute__((naked)) diff --git a/tools/testing/selftests/bpf/progs/verifier_mtu.c b/tools/testing/selftests/bpf/progs/verifier_mtu.c index 70c7600a26a0..4ccf1ebc42d1 100644 --- a/tools/testing/selftests/bpf/progs/verifier_mtu.c +++ b/tools/testing/selftests/bpf/progs/verifier_mtu.c @@ -6,7 +6,9 @@ SEC("tc/ingress") __description("uninit/mtu: write rejected") -__failure __msg("invalid indirect read from stack") +__success +__caps_unpriv(CAP_BPF|CAP_NET_ADMIN) +__failure_unpriv __msg_unpriv("invalid indirect read from stack") int tc_uninit_mtu(struct __sk_buff *ctx) { __u32 mtu; diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index 3e9b009580d4..53b06647cf57 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -36,6 +36,7 @@ #define TEST_TAG_ARCH "comment:test_arch=" #define TEST_TAG_JITED_PFX "comment:test_jited=" #define TEST_TAG_JITED_PFX_UNPRIV "comment:test_jited_unpriv=" +#define TEST_TAG_CAPS_UNPRIV "comment:test_caps_unpriv=" /* Warning: duplicated in bpf_misc.h */ #define POINTER_VALUE 0xcafe4all @@ -74,6 +75,7 @@ struct test_subspec { struct expected_msgs jited; int retval; bool execute; + __u64 caps; }; struct test_spec { @@ -276,6 +278,37 @@ static int parse_int(const char *str, int *val, const char *name) return 0; } +static int parse_caps(const char *str, __u64 *val, const char *name) +{ + int cap_flag = 0; + char *token = NULL, *saveptr = NULL; + + char *str_cpy = strdup(str); + if (str_cpy == NULL) { + PRINT_FAIL("Memory allocation failed\n"); + return -EINVAL; + } + + token = strtok_r(str_cpy, "|", &saveptr); + while (token != NULL) { + errno = 0; + if (!strncmp("CAP_", token, sizeof("CAP_") - 1)) { + PRINT_FAIL("define %s constant in bpf_misc.h, failed to parse caps\n", token); + return -EINVAL; + } + cap_flag = strtol(token, NULL, 10); + if (!cap_flag || errno) { + PRINT_FAIL("failed to parse caps %s\n", name); + return -EINVAL; + } + *val |= (1ULL << cap_flag); + token = strtok_r(NULL, "|", &saveptr); + } + + free(str_cpy); + return 0; +} + static int parse_retval(const char *str, int *val, const char *name) { struct { @@ -541,6 +574,12 @@ static int parse_test_spec(struct test_loader *tester, jit_on_next_line = true; } else if (str_has_pfx(s, TEST_BTF_PATH)) { spec->btf_custom_path = s + sizeof(TEST_BTF_PATH) - 1; + } else if (str_has_pfx(s, TEST_TAG_CAPS_UNPRIV)) { + val = s + sizeof(TEST_TAG_CAPS_UNPRIV) - 1; + err = parse_caps(val, &spec->unpriv.caps, "test caps"); + if (err) + goto cleanup; + spec->mode_mask |= UNPRIV; } } @@ -917,6 +956,13 @@ void run_subtest(struct test_loader *tester, test__end_subtest(); return; } + if (subspec->caps) { + err = cap_enable_effective(subspec->caps, NULL); + if (err) { + PRINT_FAIL("failed to set capabilities: %i, %s\n", err, strerror(err)); + goto subtest_cleanup; + } + } } /* Implicitly reset to NULL if next test case doesn't specify */ -- cgit v1.3.1 From f513c3635078fc184af66b1af9e4f2b2d19b7d79 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 3 Dec 2024 20:47:56 -0800 Subject: selftests/bpf: Add test for reading from STACK_INVALID slots Ensure that when CAP_PERFMON is dropped, and the verifier sees allow_ptr_leaks as false, we are not permitted to read from a STACK_INVALID slot. Without the fix, the test will report unexpected success in loading. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20241204044757.1483141-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- .../testing/selftests/bpf/progs/verifier_spill_fill.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index 671d9f415dbf..bab6d789ba00 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -1244,4 +1244,22 @@ __naked void old_stack_misc_vs_cur_ctx_ptr(void) : __clobber_all); } +SEC("socket") +__description("stack_noperfmon: reject read of invalid slots") +__success +__caps_unpriv(CAP_BPF) +__failure_unpriv __msg_unpriv("invalid read from stack off -8+1 size 8") +__naked void stack_noperfmon_reject_invalid_read(void) +{ + asm volatile (" \ + r2 = 1; \ + r6 = r10; \ + r6 += -8; \ + *(u8 *)(r6 + 0) = r2; \ + r2 = *(u64 *)(r6 + 0); \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + char _license[] SEC("license") = "GPL"; -- cgit v1.3.1 From 19b6dbc006ecc1f2c8d7fa2d5afbfb7e7eba7920 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 3 Dec 2024 20:47:57 -0800 Subject: selftests/bpf: Add test for narrow spill into 64-bit spilled scalar Add a test case to verify that without CAP_PERFMON, the test now succeeds instead of failing due to a verification error. Acked-by: Eduard Zingerman Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20241204044757.1483141-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/progs/verifier_spill_fill.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index bab6d789ba00..1e5a511e8494 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -1262,4 +1262,21 @@ __naked void stack_noperfmon_reject_invalid_read(void) " ::: __clobber_all); } +SEC("socket") +__description("stack_noperfmon: narrow spill onto 64-bit scalar spilled slots") +__success +__caps_unpriv(CAP_BPF) +__success_unpriv +__naked void stack_noperfmon_spill_32bit_onto_64bit_slot(void) +{ + asm volatile(" \ + r0 = 0; \ + *(u64 *)(r10 - 8) = r0; \ + *(u32 *)(r10 - 8) = r0; \ + exit; \ +" : + : + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; -- cgit v1.3.1 From 3e18f5f1e5a152a51dbb6c234e2a0421aec11e31 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 6 Dec 2024 19:06:21 +0800 Subject: selftests/bpf: Move test_lpm_map.c to map_tests Move test_lpm_map.c to map_tests/ to include LPM trie test cases in regular test_maps run. Most code remains unchanged, including the use of assert(). Only reduce n_lookups from 64K to 512, which decreases test_lpm_map runtime from 37s to 0.7s. Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20241206110622.1161752-9-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/.gitignore | 1 - tools/testing/selftests/bpf/Makefile | 2 +- .../bpf/map_tests/lpm_trie_map_basic_ops.c | 793 ++++++++++++++++++++ tools/testing/selftests/bpf/test_lpm_map.c | 797 --------------------- 4 files changed, 794 insertions(+), 799 deletions(-) create mode 100644 tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c delete mode 100644 tools/testing/selftests/bpf/test_lpm_map.c (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index c2a1842c3d8b..e9c377001f93 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -5,7 +5,6 @@ bpf-syscall* test_verifier test_maps test_lru_map -test_lpm_map test_tag FEATURE-DUMP.libbpf FEATURE-DUMP.selftests diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 6ad3b1ba1920..7eeb3cbe18c7 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -83,7 +83,7 @@ CLANG_CPUV4 := 1 endif # Order correspond to 'make run_tests' order -TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ +TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_progs \ test_sockmap \ test_tcpnotify_user test_sysctl \ test_progs-no_alu32 diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c new file mode 100644 index 000000000000..f375c89d78a4 --- /dev/null +++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c @@ -0,0 +1,793 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Randomized tests for eBPF longest-prefix-match maps + * + * This program runs randomized tests against the lpm-bpf-map. It implements a + * "Trivial Longest Prefix Match" (tlpm) based on simple, linear, singly linked + * lists. The implementation should be pretty straightforward. + * + * Based on tlpm, this inserts randomized data into bpf-lpm-maps and verifies + * the trie-based bpf-map implementation behaves the same way as tlpm. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "bpf_util.h" + +struct tlpm_node { + struct tlpm_node *next; + size_t n_bits; + uint8_t key[]; +}; + +static struct tlpm_node *tlpm_match(struct tlpm_node *list, + const uint8_t *key, + size_t n_bits); + +static struct tlpm_node *tlpm_add(struct tlpm_node *list, + const uint8_t *key, + size_t n_bits) +{ + struct tlpm_node *node; + size_t n; + + n = (n_bits + 7) / 8; + + /* 'overwrite' an equivalent entry if one already exists */ + node = tlpm_match(list, key, n_bits); + if (node && node->n_bits == n_bits) { + memcpy(node->key, key, n); + return list; + } + + /* add new entry with @key/@n_bits to @list and return new head */ + + node = malloc(sizeof(*node) + n); + assert(node); + + node->next = list; + node->n_bits = n_bits; + memcpy(node->key, key, n); + + return node; +} + +static void tlpm_clear(struct tlpm_node *list) +{ + struct tlpm_node *node; + + /* free all entries in @list */ + + while ((node = list)) { + list = list->next; + free(node); + } +} + +static struct tlpm_node *tlpm_match(struct tlpm_node *list, + const uint8_t *key, + size_t n_bits) +{ + struct tlpm_node *best = NULL; + size_t i; + + /* Perform longest prefix-match on @key/@n_bits. That is, iterate all + * entries and match each prefix against @key. Remember the "best" + * entry we find (i.e., the longest prefix that matches) and return it + * to the caller when done. + */ + + for ( ; list; list = list->next) { + for (i = 0; i < n_bits && i < list->n_bits; ++i) { + if ((key[i / 8] & (1 << (7 - i % 8))) != + (list->key[i / 8] & (1 << (7 - i % 8)))) + break; + } + + if (i >= list->n_bits) { + if (!best || i > best->n_bits) + best = list; + } + } + + return best; +} + +static struct tlpm_node *tlpm_delete(struct tlpm_node *list, + const uint8_t *key, + size_t n_bits) +{ + struct tlpm_node *best = tlpm_match(list, key, n_bits); + struct tlpm_node *node; + + if (!best || best->n_bits != n_bits) + return list; + + if (best == list) { + node = best->next; + free(best); + return node; + } + + for (node = list; node; node = node->next) { + if (node->next == best) { + node->next = best->next; + free(best); + return list; + } + } + /* should never get here */ + assert(0); + return list; +} + +static void test_lpm_basic(void) +{ + struct tlpm_node *list = NULL, *t1, *t2; + + /* very basic, static tests to verify tlpm works as expected */ + + assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8)); + + t1 = list = tlpm_add(list, (uint8_t[]){ 0xff }, 8); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8)); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16)); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0x00 }, 16)); + assert(!tlpm_match(list, (uint8_t[]){ 0x7f }, 8)); + assert(!tlpm_match(list, (uint8_t[]){ 0xfe }, 8)); + assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 7)); + + t2 = list = tlpm_add(list, (uint8_t[]){ 0xff, 0xff }, 16); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8)); + assert(t2 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16)); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 15)); + assert(!tlpm_match(list, (uint8_t[]){ 0x7f, 0xff }, 16)); + + list = tlpm_delete(list, (uint8_t[]){ 0xff, 0xff }, 16); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8)); + assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16)); + + list = tlpm_delete(list, (uint8_t[]){ 0xff }, 8); + assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8)); + + tlpm_clear(list); +} + +static void test_lpm_order(void) +{ + struct tlpm_node *t1, *t2, *l1 = NULL, *l2 = NULL; + size_t i, j; + + /* Verify the tlpm implementation works correctly regardless of the + * order of entries. Insert a random set of entries into @l1, and copy + * the same data in reverse order into @l2. Then verify a lookup of + * random keys will yield the same result in both sets. + */ + + for (i = 0; i < (1 << 12); ++i) + l1 = tlpm_add(l1, (uint8_t[]){ + rand() % 0xff, + rand() % 0xff, + }, rand() % 16 + 1); + + for (t1 = l1; t1; t1 = t1->next) + l2 = tlpm_add(l2, t1->key, t1->n_bits); + + for (i = 0; i < (1 << 8); ++i) { + uint8_t key[] = { rand() % 0xff, rand() % 0xff }; + + t1 = tlpm_match(l1, key, 16); + t2 = tlpm_match(l2, key, 16); + + assert(!t1 == !t2); + if (t1) { + assert(t1->n_bits == t2->n_bits); + for (j = 0; j < t1->n_bits; ++j) + assert((t1->key[j / 8] & (1 << (7 - j % 8))) == + (t2->key[j / 8] & (1 << (7 - j % 8)))); + } + } + + tlpm_clear(l1); + tlpm_clear(l2); +} + +static void test_lpm_map(int keysize) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); + volatile size_t n_matches, n_matches_after_delete; + size_t i, j, n_nodes, n_lookups; + struct tlpm_node *t, *list = NULL; + struct bpf_lpm_trie_key_u8 *key; + uint8_t *data, *value; + int r, map; + + /* Compare behavior of tlpm vs. bpf-lpm. Create a randomized set of + * prefixes and insert it into both tlpm and bpf-lpm. Then run some + * randomized lookups and verify both maps return the same result. + */ + + n_matches = 0; + n_matches_after_delete = 0; + n_nodes = 1 << 8; + n_lookups = 1 << 9; + + data = alloca(keysize); + memset(data, 0, keysize); + + value = alloca(keysize + 1); + memset(value, 0, keysize + 1); + + key = alloca(sizeof(*key) + keysize); + memset(key, 0, sizeof(*key) + keysize); + + map = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, + sizeof(*key) + keysize, + keysize + 1, + 4096, + &opts); + assert(map >= 0); + + for (i = 0; i < n_nodes; ++i) { + for (j = 0; j < keysize; ++j) + value[j] = rand() & 0xff; + value[keysize] = rand() % (8 * keysize + 1); + + list = tlpm_add(list, value, value[keysize]); + + key->prefixlen = value[keysize]; + memcpy(key->data, value, keysize); + r = bpf_map_update_elem(map, key, value, 0); + assert(!r); + } + + for (i = 0; i < n_lookups; ++i) { + for (j = 0; j < keysize; ++j) + data[j] = rand() & 0xff; + + t = tlpm_match(list, data, 8 * keysize); + + key->prefixlen = 8 * keysize; + memcpy(key->data, data, keysize); + r = bpf_map_lookup_elem(map, key, value); + assert(!r || errno == ENOENT); + assert(!t == !!r); + + if (t) { + ++n_matches; + assert(t->n_bits == value[keysize]); + for (j = 0; j < t->n_bits; ++j) + assert((t->key[j / 8] & (1 << (7 - j % 8))) == + (value[j / 8] & (1 << (7 - j % 8)))); + } + } + + /* Remove the first half of the elements in the tlpm and the + * corresponding nodes from the bpf-lpm. Then run the same + * large number of random lookups in both and make sure they match. + * Note: we need to count the number of nodes actually inserted + * since there may have been duplicates. + */ + for (i = 0, t = list; t; i++, t = t->next) + ; + for (j = 0; j < i / 2; ++j) { + key->prefixlen = list->n_bits; + memcpy(key->data, list->key, keysize); + r = bpf_map_delete_elem(map, key); + assert(!r); + list = tlpm_delete(list, list->key, list->n_bits); + assert(list); + } + for (i = 0; i < n_lookups; ++i) { + for (j = 0; j < keysize; ++j) + data[j] = rand() & 0xff; + + t = tlpm_match(list, data, 8 * keysize); + + key->prefixlen = 8 * keysize; + memcpy(key->data, data, keysize); + r = bpf_map_lookup_elem(map, key, value); + assert(!r || errno == ENOENT); + assert(!t == !!r); + + if (t) { + ++n_matches_after_delete; + assert(t->n_bits == value[keysize]); + for (j = 0; j < t->n_bits; ++j) + assert((t->key[j / 8] & (1 << (7 - j % 8))) == + (value[j / 8] & (1 << (7 - j % 8)))); + } + } + + close(map); + tlpm_clear(list); + + /* With 255 random nodes in the map, we are pretty likely to match + * something on every lookup. For statistics, use this: + * + * printf(" nodes: %zu\n" + * " lookups: %zu\n" + * " matches: %zu\n" + * "matches(delete): %zu\n", + * n_nodes, n_lookups, n_matches, n_matches_after_delete); + */ +} + +/* Test the implementation with some 'real world' examples */ + +static void test_lpm_ipaddr(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); + struct bpf_lpm_trie_key_u8 *key_ipv4; + struct bpf_lpm_trie_key_u8 *key_ipv6; + size_t key_size_ipv4; + size_t key_size_ipv6; + int map_fd_ipv4; + int map_fd_ipv6; + __u64 value; + + key_size_ipv4 = sizeof(*key_ipv4) + sizeof(__u32); + key_size_ipv6 = sizeof(*key_ipv6) + sizeof(__u32) * 4; + key_ipv4 = alloca(key_size_ipv4); + key_ipv6 = alloca(key_size_ipv6); + + map_fd_ipv4 = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, + key_size_ipv4, sizeof(value), + 100, &opts); + assert(map_fd_ipv4 >= 0); + + map_fd_ipv6 = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, + key_size_ipv6, sizeof(value), + 100, &opts); + assert(map_fd_ipv6 >= 0); + + /* Fill data some IPv4 and IPv6 address ranges */ + value = 1; + key_ipv4->prefixlen = 16; + inet_pton(AF_INET, "192.168.0.0", key_ipv4->data); + assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); + + value = 2; + key_ipv4->prefixlen = 24; + inet_pton(AF_INET, "192.168.0.0", key_ipv4->data); + assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); + + value = 3; + key_ipv4->prefixlen = 24; + inet_pton(AF_INET, "192.168.128.0", key_ipv4->data); + assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); + + value = 5; + key_ipv4->prefixlen = 24; + inet_pton(AF_INET, "192.168.1.0", key_ipv4->data); + assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); + + value = 4; + key_ipv4->prefixlen = 23; + inet_pton(AF_INET, "192.168.0.0", key_ipv4->data); + assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); + + value = 0xdeadbeef; + key_ipv6->prefixlen = 64; + inet_pton(AF_INET6, "2a00:1450:4001:814::200e", key_ipv6->data); + assert(bpf_map_update_elem(map_fd_ipv6, key_ipv6, &value, 0) == 0); + + /* Set tprefixlen to maximum for lookups */ + key_ipv4->prefixlen = 32; + key_ipv6->prefixlen = 128; + + /* Test some lookups that should come back with a value */ + inet_pton(AF_INET, "192.168.128.23", key_ipv4->data); + assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0); + assert(value == 3); + + inet_pton(AF_INET, "192.168.0.1", key_ipv4->data); + assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0); + assert(value == 2); + + inet_pton(AF_INET6, "2a00:1450:4001:814::", key_ipv6->data); + assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0); + assert(value == 0xdeadbeef); + + inet_pton(AF_INET6, "2a00:1450:4001:814::1", key_ipv6->data); + assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0); + assert(value == 0xdeadbeef); + + /* Test some lookups that should not match any entry */ + inet_pton(AF_INET, "10.0.0.1", key_ipv4->data); + assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -ENOENT); + + inet_pton(AF_INET, "11.11.11.11", key_ipv4->data); + assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -ENOENT); + + inet_pton(AF_INET6, "2a00:ffff::", key_ipv6->data); + assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == -ENOENT); + + close(map_fd_ipv4); + close(map_fd_ipv6); +} + +static void test_lpm_delete(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); + struct bpf_lpm_trie_key_u8 *key; + size_t key_size; + int map_fd; + __u64 value; + + key_size = sizeof(*key) + sizeof(__u32); + key = alloca(key_size); + + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, + key_size, sizeof(value), + 100, &opts); + assert(map_fd >= 0); + + /* Add nodes: + * 192.168.0.0/16 (1) + * 192.168.0.0/24 (2) + * 192.168.128.0/24 (3) + * 192.168.1.0/24 (4) + * + * (1) + * / \ + * (IM) (3) + * / \ + * (2) (4) + */ + value = 1; + key->prefixlen = 16; + inet_pton(AF_INET, "192.168.0.0", key->data); + assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); + + value = 2; + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.0.0", key->data); + assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); + + value = 3; + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.128.0", key->data); + assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); + + value = 4; + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.1.0", key->data); + assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); + + /* remove non-existent node */ + key->prefixlen = 32; + inet_pton(AF_INET, "10.0.0.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == -ENOENT); + + key->prefixlen = 30; // unused prefix so far + inet_pton(AF_INET, "192.255.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == -ENOENT); + + key->prefixlen = 16; // same prefix as the root node + inet_pton(AF_INET, "192.255.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == -ENOENT); + + /* assert initial lookup */ + key->prefixlen = 32; + inet_pton(AF_INET, "192.168.0.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); + assert(value == 2); + + /* remove leaf node */ + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == 0); + + key->prefixlen = 32; + inet_pton(AF_INET, "192.168.0.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); + assert(value == 1); + + /* remove leaf (and intermediary) node */ + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.1.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == 0); + + key->prefixlen = 32; + inet_pton(AF_INET, "192.168.1.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); + assert(value == 1); + + /* remove root node */ + key->prefixlen = 16; + inet_pton(AF_INET, "192.168.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == 0); + + key->prefixlen = 32; + inet_pton(AF_INET, "192.168.128.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); + assert(value == 3); + + /* remove last node */ + key->prefixlen = 24; + inet_pton(AF_INET, "192.168.128.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == 0); + + key->prefixlen = 32; + inet_pton(AF_INET, "192.168.128.1", key->data); + assert(bpf_map_lookup_elem(map_fd, key, &value) == -ENOENT); + + close(map_fd); +} + +static void test_lpm_get_next_key(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); + struct bpf_lpm_trie_key_u8 *key_p, *next_key_p; + size_t key_size; + __u32 value = 0; + int map_fd; + + key_size = sizeof(*key_p) + sizeof(__u32); + key_p = alloca(key_size); + next_key_p = alloca(key_size); + + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, sizeof(value), 100, &opts); + assert(map_fd >= 0); + + /* empty tree. get_next_key should return ENOENT */ + assert(bpf_map_get_next_key(map_fd, NULL, key_p) == -ENOENT); + + /* get and verify the first key, get the second one should fail. */ + key_p->prefixlen = 16; + inet_pton(AF_INET, "192.168.0.0", key_p->data); + assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0); + + memset(key_p, 0, key_size); + assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); + assert(key_p->prefixlen == 16 && key_p->data[0] == 192 && + key_p->data[1] == 168); + + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -ENOENT); + + /* no exact matching key should get the first one in post order. */ + key_p->prefixlen = 8; + assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); + assert(key_p->prefixlen == 16 && key_p->data[0] == 192 && + key_p->data[1] == 168); + + /* add one more element (total two) */ + key_p->prefixlen = 24; + inet_pton(AF_INET, "192.168.128.0", key_p->data); + assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0); + + memset(key_p, 0, key_size); + assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); + assert(key_p->prefixlen == 24 && key_p->data[0] == 192 && + key_p->data[1] == 168 && key_p->data[2] == 128); + + memset(next_key_p, 0, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168); + + memcpy(key_p, next_key_p, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -ENOENT); + + /* Add one more element (total three) */ + key_p->prefixlen = 24; + inet_pton(AF_INET, "192.168.0.0", key_p->data); + assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0); + + memset(key_p, 0, key_size); + assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); + assert(key_p->prefixlen == 24 && key_p->data[0] == 192 && + key_p->data[1] == 168 && key_p->data[2] == 0); + + memset(next_key_p, 0, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168 && next_key_p->data[2] == 128); + + memcpy(key_p, next_key_p, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168); + + memcpy(key_p, next_key_p, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -ENOENT); + + /* Add one more element (total four) */ + key_p->prefixlen = 24; + inet_pton(AF_INET, "192.168.1.0", key_p->data); + assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0); + + memset(key_p, 0, key_size); + assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); + assert(key_p->prefixlen == 24 && key_p->data[0] == 192 && + key_p->data[1] == 168 && key_p->data[2] == 0); + + memset(next_key_p, 0, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168 && next_key_p->data[2] == 1); + + memcpy(key_p, next_key_p, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168 && next_key_p->data[2] == 128); + + memcpy(key_p, next_key_p, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168); + + memcpy(key_p, next_key_p, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -ENOENT); + + /* Add one more element (total five) */ + key_p->prefixlen = 28; + inet_pton(AF_INET, "192.168.1.128", key_p->data); + assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0); + + memset(key_p, 0, key_size); + assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); + assert(key_p->prefixlen == 24 && key_p->data[0] == 192 && + key_p->data[1] == 168 && key_p->data[2] == 0); + + memset(next_key_p, 0, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 28 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168 && next_key_p->data[2] == 1 && + next_key_p->data[3] == 128); + + memcpy(key_p, next_key_p, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168 && next_key_p->data[2] == 1); + + memcpy(key_p, next_key_p, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168 && next_key_p->data[2] == 128); + + memcpy(key_p, next_key_p, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168); + + memcpy(key_p, next_key_p, key_size); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -ENOENT); + + /* no exact matching key should return the first one in post order */ + key_p->prefixlen = 22; + inet_pton(AF_INET, "192.168.1.0", key_p->data); + assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); + assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && + next_key_p->data[1] == 168 && next_key_p->data[2] == 0); + + close(map_fd); +} + +#define MAX_TEST_KEYS 4 +struct lpm_mt_test_info { + int cmd; /* 0: update, 1: delete, 2: lookup, 3: get_next_key */ + int iter; + int map_fd; + struct { + __u32 prefixlen; + __u32 data; + } key[MAX_TEST_KEYS]; +}; + +static void *lpm_test_command(void *arg) +{ + int i, j, ret, iter, key_size; + struct lpm_mt_test_info *info = arg; + struct bpf_lpm_trie_key_u8 *key_p; + + key_size = sizeof(*key_p) + sizeof(__u32); + key_p = alloca(key_size); + for (iter = 0; iter < info->iter; iter++) + for (i = 0; i < MAX_TEST_KEYS; i++) { + /* first half of iterations in forward order, + * and second half in backward order. + */ + j = (iter < (info->iter / 2)) ? i : MAX_TEST_KEYS - i - 1; + key_p->prefixlen = info->key[j].prefixlen; + memcpy(key_p->data, &info->key[j].data, sizeof(__u32)); + if (info->cmd == 0) { + __u32 value = j; + /* update must succeed */ + assert(bpf_map_update_elem(info->map_fd, key_p, &value, 0) == 0); + } else if (info->cmd == 1) { + ret = bpf_map_delete_elem(info->map_fd, key_p); + assert(ret == 0 || errno == ENOENT); + } else if (info->cmd == 2) { + __u32 value; + ret = bpf_map_lookup_elem(info->map_fd, key_p, &value); + assert(ret == 0 || errno == ENOENT); + } else { + struct bpf_lpm_trie_key_u8 *next_key_p = alloca(key_size); + ret = bpf_map_get_next_key(info->map_fd, key_p, next_key_p); + assert(ret == 0 || errno == ENOENT || errno == ENOMEM); + } + } + + // Pass successful exit info back to the main thread + pthread_exit((void *)info); +} + +static void setup_lpm_mt_test_info(struct lpm_mt_test_info *info, int map_fd) +{ + info->iter = 2000; + info->map_fd = map_fd; + info->key[0].prefixlen = 16; + inet_pton(AF_INET, "192.168.0.0", &info->key[0].data); + info->key[1].prefixlen = 24; + inet_pton(AF_INET, "192.168.0.0", &info->key[1].data); + info->key[2].prefixlen = 24; + inet_pton(AF_INET, "192.168.128.0", &info->key[2].data); + info->key[3].prefixlen = 24; + inet_pton(AF_INET, "192.168.1.0", &info->key[3].data); +} + +static void test_lpm_multi_thread(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); + struct lpm_mt_test_info info[4]; + size_t key_size, value_size; + pthread_t thread_id[4]; + int i, map_fd; + void *ret; + + /* create a trie */ + value_size = sizeof(__u32); + key_size = sizeof(struct bpf_lpm_trie_key_hdr) + value_size; + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, value_size, 100, &opts); + + /* create 4 threads to test update, delete, lookup and get_next_key */ + setup_lpm_mt_test_info(&info[0], map_fd); + for (i = 0; i < 4; i++) { + if (i != 0) + memcpy(&info[i], &info[0], sizeof(info[i])); + info[i].cmd = i; + assert(pthread_create(&thread_id[i], NULL, &lpm_test_command, &info[i]) == 0); + } + + for (i = 0; i < 4; i++) + assert(pthread_join(thread_id[i], &ret) == 0 && ret == (void *)&info[i]); + + close(map_fd); +} + +void test_lpm_trie_map_basic_ops(void) +{ + int i; + + /* we want predictable, pseudo random tests */ + srand(0xf00ba1); + + test_lpm_basic(); + test_lpm_order(); + + /* Test with 8, 16, 24, 32, ... 128 bit prefix length */ + for (i = 1; i <= 16; ++i) + test_lpm_map(i); + + test_lpm_ipaddr(); + test_lpm_delete(); + test_lpm_get_next_key(); + test_lpm_multi_thread(); + + printf("%s: PASS\n", __func__); +} diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c deleted file mode 100644 index d98c72dc563e..000000000000 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ /dev/null @@ -1,797 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Randomized tests for eBPF longest-prefix-match maps - * - * This program runs randomized tests against the lpm-bpf-map. It implements a - * "Trivial Longest Prefix Match" (tlpm) based on simple, linear, singly linked - * lists. The implementation should be pretty straightforward. - * - * Based on tlpm, this inserts randomized data into bpf-lpm-maps and verifies - * the trie-based bpf-map implementation behaves the same way as tlpm. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -#include "bpf_util.h" - -struct tlpm_node { - struct tlpm_node *next; - size_t n_bits; - uint8_t key[]; -}; - -static struct tlpm_node *tlpm_match(struct tlpm_node *list, - const uint8_t *key, - size_t n_bits); - -static struct tlpm_node *tlpm_add(struct tlpm_node *list, - const uint8_t *key, - size_t n_bits) -{ - struct tlpm_node *node; - size_t n; - - n = (n_bits + 7) / 8; - - /* 'overwrite' an equivalent entry if one already exists */ - node = tlpm_match(list, key, n_bits); - if (node && node->n_bits == n_bits) { - memcpy(node->key, key, n); - return list; - } - - /* add new entry with @key/@n_bits to @list and return new head */ - - node = malloc(sizeof(*node) + n); - assert(node); - - node->next = list; - node->n_bits = n_bits; - memcpy(node->key, key, n); - - return node; -} - -static void tlpm_clear(struct tlpm_node *list) -{ - struct tlpm_node *node; - - /* free all entries in @list */ - - while ((node = list)) { - list = list->next; - free(node); - } -} - -static struct tlpm_node *tlpm_match(struct tlpm_node *list, - const uint8_t *key, - size_t n_bits) -{ - struct tlpm_node *best = NULL; - size_t i; - - /* Perform longest prefix-match on @key/@n_bits. That is, iterate all - * entries and match each prefix against @key. Remember the "best" - * entry we find (i.e., the longest prefix that matches) and return it - * to the caller when done. - */ - - for ( ; list; list = list->next) { - for (i = 0; i < n_bits && i < list->n_bits; ++i) { - if ((key[i / 8] & (1 << (7 - i % 8))) != - (list->key[i / 8] & (1 << (7 - i % 8)))) - break; - } - - if (i >= list->n_bits) { - if (!best || i > best->n_bits) - best = list; - } - } - - return best; -} - -static struct tlpm_node *tlpm_delete(struct tlpm_node *list, - const uint8_t *key, - size_t n_bits) -{ - struct tlpm_node *best = tlpm_match(list, key, n_bits); - struct tlpm_node *node; - - if (!best || best->n_bits != n_bits) - return list; - - if (best == list) { - node = best->next; - free(best); - return node; - } - - for (node = list; node; node = node->next) { - if (node->next == best) { - node->next = best->next; - free(best); - return list; - } - } - /* should never get here */ - assert(0); - return list; -} - -static void test_lpm_basic(void) -{ - struct tlpm_node *list = NULL, *t1, *t2; - - /* very basic, static tests to verify tlpm works as expected */ - - assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8)); - - t1 = list = tlpm_add(list, (uint8_t[]){ 0xff }, 8); - assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8)); - assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16)); - assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0x00 }, 16)); - assert(!tlpm_match(list, (uint8_t[]){ 0x7f }, 8)); - assert(!tlpm_match(list, (uint8_t[]){ 0xfe }, 8)); - assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 7)); - - t2 = list = tlpm_add(list, (uint8_t[]){ 0xff, 0xff }, 16); - assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8)); - assert(t2 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16)); - assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 15)); - assert(!tlpm_match(list, (uint8_t[]){ 0x7f, 0xff }, 16)); - - list = tlpm_delete(list, (uint8_t[]){ 0xff, 0xff }, 16); - assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8)); - assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16)); - - list = tlpm_delete(list, (uint8_t[]){ 0xff }, 8); - assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8)); - - tlpm_clear(list); -} - -static void test_lpm_order(void) -{ - struct tlpm_node *t1, *t2, *l1 = NULL, *l2 = NULL; - size_t i, j; - - /* Verify the tlpm implementation works correctly regardless of the - * order of entries. Insert a random set of entries into @l1, and copy - * the same data in reverse order into @l2. Then verify a lookup of - * random keys will yield the same result in both sets. - */ - - for (i = 0; i < (1 << 12); ++i) - l1 = tlpm_add(l1, (uint8_t[]){ - rand() % 0xff, - rand() % 0xff, - }, rand() % 16 + 1); - - for (t1 = l1; t1; t1 = t1->next) - l2 = tlpm_add(l2, t1->key, t1->n_bits); - - for (i = 0; i < (1 << 8); ++i) { - uint8_t key[] = { rand() % 0xff, rand() % 0xff }; - - t1 = tlpm_match(l1, key, 16); - t2 = tlpm_match(l2, key, 16); - - assert(!t1 == !t2); - if (t1) { - assert(t1->n_bits == t2->n_bits); - for (j = 0; j < t1->n_bits; ++j) - assert((t1->key[j / 8] & (1 << (7 - j % 8))) == - (t2->key[j / 8] & (1 << (7 - j % 8)))); - } - } - - tlpm_clear(l1); - tlpm_clear(l2); -} - -static void test_lpm_map(int keysize) -{ - LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); - volatile size_t n_matches, n_matches_after_delete; - size_t i, j, n_nodes, n_lookups; - struct tlpm_node *t, *list = NULL; - struct bpf_lpm_trie_key_u8 *key; - uint8_t *data, *value; - int r, map; - - /* Compare behavior of tlpm vs. bpf-lpm. Create a randomized set of - * prefixes and insert it into both tlpm and bpf-lpm. Then run some - * randomized lookups and verify both maps return the same result. - */ - - n_matches = 0; - n_matches_after_delete = 0; - n_nodes = 1 << 8; - n_lookups = 1 << 16; - - data = alloca(keysize); - memset(data, 0, keysize); - - value = alloca(keysize + 1); - memset(value, 0, keysize + 1); - - key = alloca(sizeof(*key) + keysize); - memset(key, 0, sizeof(*key) + keysize); - - map = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, - sizeof(*key) + keysize, - keysize + 1, - 4096, - &opts); - assert(map >= 0); - - for (i = 0; i < n_nodes; ++i) { - for (j = 0; j < keysize; ++j) - value[j] = rand() & 0xff; - value[keysize] = rand() % (8 * keysize + 1); - - list = tlpm_add(list, value, value[keysize]); - - key->prefixlen = value[keysize]; - memcpy(key->data, value, keysize); - r = bpf_map_update_elem(map, key, value, 0); - assert(!r); - } - - for (i = 0; i < n_lookups; ++i) { - for (j = 0; j < keysize; ++j) - data[j] = rand() & 0xff; - - t = tlpm_match(list, data, 8 * keysize); - - key->prefixlen = 8 * keysize; - memcpy(key->data, data, keysize); - r = bpf_map_lookup_elem(map, key, value); - assert(!r || errno == ENOENT); - assert(!t == !!r); - - if (t) { - ++n_matches; - assert(t->n_bits == value[keysize]); - for (j = 0; j < t->n_bits; ++j) - assert((t->key[j / 8] & (1 << (7 - j % 8))) == - (value[j / 8] & (1 << (7 - j % 8)))); - } - } - - /* Remove the first half of the elements in the tlpm and the - * corresponding nodes from the bpf-lpm. Then run the same - * large number of random lookups in both and make sure they match. - * Note: we need to count the number of nodes actually inserted - * since there may have been duplicates. - */ - for (i = 0, t = list; t; i++, t = t->next) - ; - for (j = 0; j < i / 2; ++j) { - key->prefixlen = list->n_bits; - memcpy(key->data, list->key, keysize); - r = bpf_map_delete_elem(map, key); - assert(!r); - list = tlpm_delete(list, list->key, list->n_bits); - assert(list); - } - for (i = 0; i < n_lookups; ++i) { - for (j = 0; j < keysize; ++j) - data[j] = rand() & 0xff; - - t = tlpm_match(list, data, 8 * keysize); - - key->prefixlen = 8 * keysize; - memcpy(key->data, data, keysize); - r = bpf_map_lookup_elem(map, key, value); - assert(!r || errno == ENOENT); - assert(!t == !!r); - - if (t) { - ++n_matches_after_delete; - assert(t->n_bits == value[keysize]); - for (j = 0; j < t->n_bits; ++j) - assert((t->key[j / 8] & (1 << (7 - j % 8))) == - (value[j / 8] & (1 << (7 - j % 8)))); - } - } - - close(map); - tlpm_clear(list); - - /* With 255 random nodes in the map, we are pretty likely to match - * something on every lookup. For statistics, use this: - * - * printf(" nodes: %zu\n" - * " lookups: %zu\n" - * " matches: %zu\n" - * "matches(delete): %zu\n", - * n_nodes, n_lookups, n_matches, n_matches_after_delete); - */ -} - -/* Test the implementation with some 'real world' examples */ - -static void test_lpm_ipaddr(void) -{ - LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); - struct bpf_lpm_trie_key_u8 *key_ipv4; - struct bpf_lpm_trie_key_u8 *key_ipv6; - size_t key_size_ipv4; - size_t key_size_ipv6; - int map_fd_ipv4; - int map_fd_ipv6; - __u64 value; - - key_size_ipv4 = sizeof(*key_ipv4) + sizeof(__u32); - key_size_ipv6 = sizeof(*key_ipv6) + sizeof(__u32) * 4; - key_ipv4 = alloca(key_size_ipv4); - key_ipv6 = alloca(key_size_ipv6); - - map_fd_ipv4 = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, - key_size_ipv4, sizeof(value), - 100, &opts); - assert(map_fd_ipv4 >= 0); - - map_fd_ipv6 = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, - key_size_ipv6, sizeof(value), - 100, &opts); - assert(map_fd_ipv6 >= 0); - - /* Fill data some IPv4 and IPv6 address ranges */ - value = 1; - key_ipv4->prefixlen = 16; - inet_pton(AF_INET, "192.168.0.0", key_ipv4->data); - assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); - - value = 2; - key_ipv4->prefixlen = 24; - inet_pton(AF_INET, "192.168.0.0", key_ipv4->data); - assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); - - value = 3; - key_ipv4->prefixlen = 24; - inet_pton(AF_INET, "192.168.128.0", key_ipv4->data); - assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); - - value = 5; - key_ipv4->prefixlen = 24; - inet_pton(AF_INET, "192.168.1.0", key_ipv4->data); - assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); - - value = 4; - key_ipv4->prefixlen = 23; - inet_pton(AF_INET, "192.168.0.0", key_ipv4->data); - assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0); - - value = 0xdeadbeef; - key_ipv6->prefixlen = 64; - inet_pton(AF_INET6, "2a00:1450:4001:814::200e", key_ipv6->data); - assert(bpf_map_update_elem(map_fd_ipv6, key_ipv6, &value, 0) == 0); - - /* Set tprefixlen to maximum for lookups */ - key_ipv4->prefixlen = 32; - key_ipv6->prefixlen = 128; - - /* Test some lookups that should come back with a value */ - inet_pton(AF_INET, "192.168.128.23", key_ipv4->data); - assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0); - assert(value == 3); - - inet_pton(AF_INET, "192.168.0.1", key_ipv4->data); - assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0); - assert(value == 2); - - inet_pton(AF_INET6, "2a00:1450:4001:814::", key_ipv6->data); - assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0); - assert(value == 0xdeadbeef); - - inet_pton(AF_INET6, "2a00:1450:4001:814::1", key_ipv6->data); - assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0); - assert(value == 0xdeadbeef); - - /* Test some lookups that should not match any entry */ - inet_pton(AF_INET, "10.0.0.1", key_ipv4->data); - assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -ENOENT); - - inet_pton(AF_INET, "11.11.11.11", key_ipv4->data); - assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -ENOENT); - - inet_pton(AF_INET6, "2a00:ffff::", key_ipv6->data); - assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == -ENOENT); - - close(map_fd_ipv4); - close(map_fd_ipv6); -} - -static void test_lpm_delete(void) -{ - LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); - struct bpf_lpm_trie_key_u8 *key; - size_t key_size; - int map_fd; - __u64 value; - - key_size = sizeof(*key) + sizeof(__u32); - key = alloca(key_size); - - map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, - key_size, sizeof(value), - 100, &opts); - assert(map_fd >= 0); - - /* Add nodes: - * 192.168.0.0/16 (1) - * 192.168.0.0/24 (2) - * 192.168.128.0/24 (3) - * 192.168.1.0/24 (4) - * - * (1) - * / \ - * (IM) (3) - * / \ - * (2) (4) - */ - value = 1; - key->prefixlen = 16; - inet_pton(AF_INET, "192.168.0.0", key->data); - assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); - - value = 2; - key->prefixlen = 24; - inet_pton(AF_INET, "192.168.0.0", key->data); - assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); - - value = 3; - key->prefixlen = 24; - inet_pton(AF_INET, "192.168.128.0", key->data); - assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); - - value = 4; - key->prefixlen = 24; - inet_pton(AF_INET, "192.168.1.0", key->data); - assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0); - - /* remove non-existent node */ - key->prefixlen = 32; - inet_pton(AF_INET, "10.0.0.1", key->data); - assert(bpf_map_lookup_elem(map_fd, key, &value) == -ENOENT); - - key->prefixlen = 30; // unused prefix so far - inet_pton(AF_INET, "192.255.0.0", key->data); - assert(bpf_map_delete_elem(map_fd, key) == -ENOENT); - - key->prefixlen = 16; // same prefix as the root node - inet_pton(AF_INET, "192.255.0.0", key->data); - assert(bpf_map_delete_elem(map_fd, key) == -ENOENT); - - /* assert initial lookup */ - key->prefixlen = 32; - inet_pton(AF_INET, "192.168.0.1", key->data); - assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); - assert(value == 2); - - /* remove leaf node */ - key->prefixlen = 24; - inet_pton(AF_INET, "192.168.0.0", key->data); - assert(bpf_map_delete_elem(map_fd, key) == 0); - - key->prefixlen = 32; - inet_pton(AF_INET, "192.168.0.1", key->data); - assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); - assert(value == 1); - - /* remove leaf (and intermediary) node */ - key->prefixlen = 24; - inet_pton(AF_INET, "192.168.1.0", key->data); - assert(bpf_map_delete_elem(map_fd, key) == 0); - - key->prefixlen = 32; - inet_pton(AF_INET, "192.168.1.1", key->data); - assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); - assert(value == 1); - - /* remove root node */ - key->prefixlen = 16; - inet_pton(AF_INET, "192.168.0.0", key->data); - assert(bpf_map_delete_elem(map_fd, key) == 0); - - key->prefixlen = 32; - inet_pton(AF_INET, "192.168.128.1", key->data); - assert(bpf_map_lookup_elem(map_fd, key, &value) == 0); - assert(value == 3); - - /* remove last node */ - key->prefixlen = 24; - inet_pton(AF_INET, "192.168.128.0", key->data); - assert(bpf_map_delete_elem(map_fd, key) == 0); - - key->prefixlen = 32; - inet_pton(AF_INET, "192.168.128.1", key->data); - assert(bpf_map_lookup_elem(map_fd, key, &value) == -ENOENT); - - close(map_fd); -} - -static void test_lpm_get_next_key(void) -{ - LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); - struct bpf_lpm_trie_key_u8 *key_p, *next_key_p; - size_t key_size; - __u32 value = 0; - int map_fd; - - key_size = sizeof(*key_p) + sizeof(__u32); - key_p = alloca(key_size); - next_key_p = alloca(key_size); - - map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, sizeof(value), 100, &opts); - assert(map_fd >= 0); - - /* empty tree. get_next_key should return ENOENT */ - assert(bpf_map_get_next_key(map_fd, NULL, key_p) == -ENOENT); - - /* get and verify the first key, get the second one should fail. */ - key_p->prefixlen = 16; - inet_pton(AF_INET, "192.168.0.0", key_p->data); - assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0); - - memset(key_p, 0, key_size); - assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); - assert(key_p->prefixlen == 16 && key_p->data[0] == 192 && - key_p->data[1] == 168); - - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -ENOENT); - - /* no exact matching key should get the first one in post order. */ - key_p->prefixlen = 8; - assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); - assert(key_p->prefixlen == 16 && key_p->data[0] == 192 && - key_p->data[1] == 168); - - /* add one more element (total two) */ - key_p->prefixlen = 24; - inet_pton(AF_INET, "192.168.128.0", key_p->data); - assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0); - - memset(key_p, 0, key_size); - assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); - assert(key_p->prefixlen == 24 && key_p->data[0] == 192 && - key_p->data[1] == 168 && key_p->data[2] == 128); - - memset(next_key_p, 0, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168); - - memcpy(key_p, next_key_p, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -ENOENT); - - /* Add one more element (total three) */ - key_p->prefixlen = 24; - inet_pton(AF_INET, "192.168.0.0", key_p->data); - assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0); - - memset(key_p, 0, key_size); - assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); - assert(key_p->prefixlen == 24 && key_p->data[0] == 192 && - key_p->data[1] == 168 && key_p->data[2] == 0); - - memset(next_key_p, 0, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168 && next_key_p->data[2] == 128); - - memcpy(key_p, next_key_p, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168); - - memcpy(key_p, next_key_p, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -ENOENT); - - /* Add one more element (total four) */ - key_p->prefixlen = 24; - inet_pton(AF_INET, "192.168.1.0", key_p->data); - assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0); - - memset(key_p, 0, key_size); - assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); - assert(key_p->prefixlen == 24 && key_p->data[0] == 192 && - key_p->data[1] == 168 && key_p->data[2] == 0); - - memset(next_key_p, 0, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168 && next_key_p->data[2] == 1); - - memcpy(key_p, next_key_p, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168 && next_key_p->data[2] == 128); - - memcpy(key_p, next_key_p, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168); - - memcpy(key_p, next_key_p, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -ENOENT); - - /* Add one more element (total five) */ - key_p->prefixlen = 28; - inet_pton(AF_INET, "192.168.1.128", key_p->data); - assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0); - - memset(key_p, 0, key_size); - assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0); - assert(key_p->prefixlen == 24 && key_p->data[0] == 192 && - key_p->data[1] == 168 && key_p->data[2] == 0); - - memset(next_key_p, 0, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 28 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168 && next_key_p->data[2] == 1 && - next_key_p->data[3] == 128); - - memcpy(key_p, next_key_p, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168 && next_key_p->data[2] == 1); - - memcpy(key_p, next_key_p, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168 && next_key_p->data[2] == 128); - - memcpy(key_p, next_key_p, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168); - - memcpy(key_p, next_key_p, key_size); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -ENOENT); - - /* no exact matching key should return the first one in post order */ - key_p->prefixlen = 22; - inet_pton(AF_INET, "192.168.1.0", key_p->data); - assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0); - assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 && - next_key_p->data[1] == 168 && next_key_p->data[2] == 0); - - close(map_fd); -} - -#define MAX_TEST_KEYS 4 -struct lpm_mt_test_info { - int cmd; /* 0: update, 1: delete, 2: lookup, 3: get_next_key */ - int iter; - int map_fd; - struct { - __u32 prefixlen; - __u32 data; - } key[MAX_TEST_KEYS]; -}; - -static void *lpm_test_command(void *arg) -{ - int i, j, ret, iter, key_size; - struct lpm_mt_test_info *info = arg; - struct bpf_lpm_trie_key_u8 *key_p; - - key_size = sizeof(*key_p) + sizeof(__u32); - key_p = alloca(key_size); - for (iter = 0; iter < info->iter; iter++) - for (i = 0; i < MAX_TEST_KEYS; i++) { - /* first half of iterations in forward order, - * and second half in backward order. - */ - j = (iter < (info->iter / 2)) ? i : MAX_TEST_KEYS - i - 1; - key_p->prefixlen = info->key[j].prefixlen; - memcpy(key_p->data, &info->key[j].data, sizeof(__u32)); - if (info->cmd == 0) { - __u32 value = j; - /* update must succeed */ - assert(bpf_map_update_elem(info->map_fd, key_p, &value, 0) == 0); - } else if (info->cmd == 1) { - ret = bpf_map_delete_elem(info->map_fd, key_p); - assert(ret == 0 || errno == ENOENT); - } else if (info->cmd == 2) { - __u32 value; - ret = bpf_map_lookup_elem(info->map_fd, key_p, &value); - assert(ret == 0 || errno == ENOENT); - } else { - struct bpf_lpm_trie_key_u8 *next_key_p = alloca(key_size); - ret = bpf_map_get_next_key(info->map_fd, key_p, next_key_p); - assert(ret == 0 || errno == ENOENT || errno == ENOMEM); - } - } - - // Pass successful exit info back to the main thread - pthread_exit((void *)info); -} - -static void setup_lpm_mt_test_info(struct lpm_mt_test_info *info, int map_fd) -{ - info->iter = 2000; - info->map_fd = map_fd; - info->key[0].prefixlen = 16; - inet_pton(AF_INET, "192.168.0.0", &info->key[0].data); - info->key[1].prefixlen = 24; - inet_pton(AF_INET, "192.168.0.0", &info->key[1].data); - info->key[2].prefixlen = 24; - inet_pton(AF_INET, "192.168.128.0", &info->key[2].data); - info->key[3].prefixlen = 24; - inet_pton(AF_INET, "192.168.1.0", &info->key[3].data); -} - -static void test_lpm_multi_thread(void) -{ - LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); - struct lpm_mt_test_info info[4]; - size_t key_size, value_size; - pthread_t thread_id[4]; - int i, map_fd; - void *ret; - - /* create a trie */ - value_size = sizeof(__u32); - key_size = sizeof(struct bpf_lpm_trie_key_hdr) + value_size; - map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, value_size, 100, &opts); - - /* create 4 threads to test update, delete, lookup and get_next_key */ - setup_lpm_mt_test_info(&info[0], map_fd); - for (i = 0; i < 4; i++) { - if (i != 0) - memcpy(&info[i], &info[0], sizeof(info[i])); - info[i].cmd = i; - assert(pthread_create(&thread_id[i], NULL, &lpm_test_command, &info[i]) == 0); - } - - for (i = 0; i < 4; i++) - assert(pthread_join(thread_id[i], &ret) == 0 && ret == (void *)&info[i]); - - close(map_fd); -} - -int main(void) -{ - int i; - - /* we want predictable, pseudo random tests */ - srand(0xf00ba1); - - /* Use libbpf 1.0 API mode */ - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - - test_lpm_basic(); - test_lpm_order(); - - /* Test with 8, 16, 24, 32, ... 128 bit prefix length */ - for (i = 1; i <= 16; ++i) - test_lpm_map(i); - - test_lpm_ipaddr(); - test_lpm_delete(); - test_lpm_get_next_key(); - test_lpm_multi_thread(); - - printf("test_lpm: OK\n"); - return 0; -} -- cgit v1.3.1 From 04d4ce91b0bed4120e0c5fadc5291cebaa9c2a06 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 6 Dec 2024 19:06:22 +0800 Subject: selftests/bpf: Add more test cases for LPM trie Add more test cases for LPM trie in test_maps: 1) test_lpm_trie_update_flags It constructs various use cases for BPF_EXIST and BPF_NOEXIST and check whether the return value of update operation is expected. 2) test_lpm_trie_update_full_maps It tests the update operations on a full LPM trie map. Adding new node will fail and overwriting the value of existed node will succeed. 3) test_lpm_trie_iterate_strs and test_lpm_trie_iterate_ints There two test cases test whether the iteration through get_next_key is sorted and expected. These two test cases delete the minimal key after each iteration and check whether next iteration returns the second minimal key. The only difference between these two test cases is the former one saves strings in the LPM trie and the latter saves integers. Without the fix of get_next_key, these two cases will fail as shown below: test_lpm_trie_iterate_strs(1091):FAIL:iterate #2 got abc exp abS test_lpm_trie_iterate_ints(1142):FAIL:iterate #1 got 0x2 exp 0x1 Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20241206110622.1161752-10-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- .../bpf/map_tests/lpm_trie_map_basic_ops.c | 395 +++++++++++++++++++++ 1 file changed, 395 insertions(+) (limited to 'tools/testing') diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c index f375c89d78a4..d32e4edac930 100644 --- a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c +++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c @@ -20,10 +20,12 @@ #include #include #include +#include #include #include #include +#include #include "bpf_util.h" @@ -33,6 +35,22 @@ struct tlpm_node { uint8_t key[]; }; +struct lpm_trie_bytes_key { + union { + struct bpf_lpm_trie_key_hdr hdr; + __u32 prefixlen; + }; + unsigned char data[8]; +}; + +struct lpm_trie_int_key { + union { + struct bpf_lpm_trie_key_hdr hdr; + __u32 prefixlen; + }; + unsigned int data; +}; + static struct tlpm_node *tlpm_match(struct tlpm_node *list, const uint8_t *key, size_t n_bits); @@ -770,6 +788,378 @@ static void test_lpm_multi_thread(void) close(map_fd); } +static int lpm_trie_create(unsigned int key_size, unsigned int value_size, unsigned int max_entries) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int fd; + + opts.map_flags = BPF_F_NO_PREALLOC; + fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie", key_size, value_size, max_entries, + &opts); + CHECK(fd < 0, "bpf_map_create", "error %d\n", errno); + + return fd; +} + +static void test_lpm_trie_update_flags(void) +{ + struct lpm_trie_int_key key; + unsigned int value, got; + int fd, err; + + fd = lpm_trie_create(sizeof(key), sizeof(value), 3); + + /* invalid flags (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 0; + err = bpf_map_update_elem(fd, &key, &value, BPF_F_LOCK); + CHECK(err != -EINVAL, "invalid update flag", "error %d\n", err); + + /* invalid flags (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 0; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST | BPF_EXIST); + CHECK(err != -EINVAL, "invalid update flag", "error %d\n", err); + + /* overwrite an empty qp-trie (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err != -ENOENT, "overwrite empty qp-trie", "error %d\n", err); + + /* add a new node */ + key.prefixlen = 16; + key.data = 0; + value = 1; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add the same node as new node (Error) */ + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err != -EEXIST, "add new elem again", "error %d\n", err); + + /* overwrite the existed node */ + value = 4; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* overwrite the node */ + value = 1; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err, "update elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* overwrite a non-existent node which is the prefix of the first + * node (Error). + */ + key.prefixlen = 8; + key.data = 0; + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err != -ENOENT, "overwrite nonexistent elem", "error %d\n", err); + + /* add a new node which is the prefix of the first node */ + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup key", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add another new node which will be the sibling of the first node */ + key.prefixlen = 9; + key.data = htobe32(1 << 23); + value = 5; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup key", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* overwrite the third node */ + value = 3; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup key", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* delete the second node to make it an intermediate node */ + key.prefixlen = 8; + key.data = 0; + err = bpf_map_delete_elem(fd, &key); + CHECK(err, "del elem", "error %d\n", err); + + /* overwrite the intermediate node (Error) */ + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err != -ENOENT, "overwrite nonexistent elem", "error %d\n", err); + + close(fd); +} + +static void test_lpm_trie_update_full_map(void) +{ + struct lpm_trie_int_key key; + int value, got; + int fd, err; + + fd = lpm_trie_create(sizeof(key), sizeof(value), 3); + + /* add a new node */ + key.prefixlen = 16; + key.data = 0; + value = 0; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add new node */ + key.prefixlen = 8; + key.data = 0; + value = 1; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* add new node */ + key.prefixlen = 9; + key.data = htobe32(1 << 23); + value = 2; + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add new elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* try to add more node (Error) */ + key.prefixlen = 32; + key.data = 0; + value = 3; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err != -ENOSPC, "add to full trie", "error %d\n", err); + + /* update the value of an existed node with BPF_EXIST */ + key.prefixlen = 16; + key.data = 0; + value = 4; + err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + /* update the value of an existed node with BPF_ANY */ + key.prefixlen = 9; + key.data = htobe32(1 << 23); + value = 5; + err = bpf_map_update_elem(fd, &key, &value, BPF_ANY); + CHECK(err, "overwrite elem", "error %d\n", err); + got = 0; + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "error %d\n", err); + CHECK(got != value, "check value", "got %d exp %d\n", got, value); + + close(fd); +} + +static int cmp_str(const void *a, const void *b) +{ + const char *str_a = *(const char **)a, *str_b = *(const char **)b; + + return strcmp(str_a, str_b); +} + +/* Save strings in LPM trie. The trailing '\0' for each string will be + * accounted in the prefixlen. The strings returned during the iteration + * should be sorted as expected. + */ +static void test_lpm_trie_iterate_strs(void) +{ + static const char * const keys[] = { + "ab", "abO", "abc", "abo", "abS", "abcd", + }; + const char *sorted_keys[ARRAY_SIZE(keys)]; + struct lpm_trie_bytes_key key, next_key; + unsigned int value, got, i, j, len; + struct lpm_trie_bytes_key *cur; + int fd, err; + + fd = lpm_trie_create(sizeof(key), sizeof(value), ARRAY_SIZE(keys)); + + for (i = 0; i < ARRAY_SIZE(keys); i++) { + unsigned int flags; + + /* add i-th element */ + flags = i % 2 ? BPF_NOEXIST : 0; + len = strlen(keys[i]); + /* include the trailing '\0' */ + key.prefixlen = (len + 1) * 8; + memset(key.data, 0, sizeof(key.data)); + memcpy(key.data, keys[i], len); + value = i + 100; + err = bpf_map_update_elem(fd, &key, &value, flags); + CHECK(err, "add elem", "#%u error %d\n", i, err); + + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "#%u error %d\n", i, err); + CHECK(got != value, "lookup elem", "#%u expect %u got %u\n", i, value, got); + + /* re-add i-th element (Error) */ + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err != -EEXIST, "re-add elem", "#%u error %d\n", i, err); + + /* Overwrite i-th element */ + flags = i % 2 ? 0 : BPF_EXIST; + value = i; + err = bpf_map_update_elem(fd, &key, &value, flags); + CHECK(err, "update elem", "error %d\n", err); + + /* Lookup #[0~i] elements */ + for (j = 0; j <= i; j++) { + len = strlen(keys[j]); + key.prefixlen = (len + 1) * 8; + memset(key.data, 0, sizeof(key.data)); + memcpy(key.data, keys[j], len); + err = bpf_map_lookup_elem(fd, &key, &got); + CHECK(err, "lookup elem", "#%u/%u error %d\n", i, j, err); + CHECK(got != j, "lookup elem", "#%u/%u expect %u got %u\n", + i, j, value, got); + } + } + + /* Add element to a full qp-trie (Error) */ + key.prefixlen = sizeof(key.data) * 8; + memset(key.data, 0, sizeof(key.data)); + value = 0; + err = bpf_map_update_elem(fd, &key, &value, 0); + CHECK(err != -ENOSPC, "add to full qp-trie", "error %d\n", err); + + /* Iterate sorted elements: no deletion */ + memcpy(sorted_keys, keys, sizeof(keys)); + qsort(sorted_keys, ARRAY_SIZE(sorted_keys), sizeof(sorted_keys[0]), cmp_str); + cur = NULL; + for (i = 0; i < ARRAY_SIZE(sorted_keys); i++) { + len = strlen(sorted_keys[i]); + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err, "iterate", "#%u error %d\n", i, err); + CHECK(next_key.prefixlen != (len + 1) * 8, "iterate", + "#%u invalid len %u expect %u\n", + i, next_key.prefixlen, (len + 1) * 8); + CHECK(memcmp(sorted_keys[i], next_key.data, len + 1), "iterate", + "#%u got %.*s exp %.*s\n", i, len, next_key.data, len, sorted_keys[i]); + + cur = &next_key; + } + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err != -ENOENT, "more element", "error %d\n", err); + + /* Iterate sorted elements: delete the found key after each iteration */ + cur = NULL; + for (i = 0; i < ARRAY_SIZE(sorted_keys); i++) { + len = strlen(sorted_keys[i]); + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err, "iterate", "#%u error %d\n", i, err); + CHECK(next_key.prefixlen != (len + 1) * 8, "iterate", + "#%u invalid len %u expect %u\n", + i, next_key.prefixlen, (len + 1) * 8); + CHECK(memcmp(sorted_keys[i], next_key.data, len + 1), "iterate", + "#%u got %.*s exp %.*s\n", i, len, next_key.data, len, sorted_keys[i]); + + cur = &next_key; + + err = bpf_map_delete_elem(fd, cur); + CHECK(err, "delete", "#%u error %d\n", i, err); + } + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err != -ENOENT, "non-empty qp-trie", "error %d\n", err); + + close(fd); +} + +/* Use the fixed prefixlen (32) and save integers in LPM trie. The iteration of + * LPM trie will return these integers in big-endian order, therefore, convert + * these integers to big-endian before update. After each iteration, delete the + * found key (the smallest integer) and expect the next iteration will return + * the second smallest number. + */ +static void test_lpm_trie_iterate_ints(void) +{ + struct lpm_trie_int_key key, next_key; + unsigned int i, max_entries; + struct lpm_trie_int_key *cur; + unsigned int *data_set; + int fd, err; + bool value; + + max_entries = 4096; + data_set = calloc(max_entries, sizeof(*data_set)); + CHECK(!data_set, "malloc", "no mem\n"); + for (i = 0; i < max_entries; i++) + data_set[i] = i; + + fd = lpm_trie_create(sizeof(key), sizeof(value), max_entries); + value = true; + for (i = 0; i < max_entries; i++) { + key.prefixlen = 32; + key.data = htobe32(data_set[i]); + + err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST); + CHECK(err, "add elem", "#%u error %d\n", i, err); + } + + cur = NULL; + for (i = 0; i < max_entries; i++) { + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err, "iterate", "#%u error %d\n", i, err); + CHECK(next_key.prefixlen != 32, "iterate", "#%u invalid len %u\n", + i, next_key.prefixlen); + CHECK(be32toh(next_key.data) != data_set[i], "iterate", "#%u got 0x%x exp 0x%x\n", + i, be32toh(next_key.data), data_set[i]); + cur = &next_key; + + /* + * Delete the minimal key, the next call of bpf_get_next_key() + * will return the second minimal key. + */ + err = bpf_map_delete_elem(fd, &next_key); + CHECK(err, "del elem", "#%u elem error %d\n", i, err); + } + err = bpf_map_get_next_key(fd, cur, &next_key); + CHECK(err != -ENOENT, "more element", "error %d\n", err); + + err = bpf_map_get_next_key(fd, NULL, &next_key); + CHECK(err != -ENOENT, "no-empty qp-trie", "error %d\n", err); + + free(data_set); + + close(fd); +} + void test_lpm_trie_map_basic_ops(void) { int i; @@ -789,5 +1179,10 @@ void test_lpm_trie_map_basic_ops(void) test_lpm_get_next_key(); test_lpm_multi_thread(); + test_lpm_trie_update_flags(); + test_lpm_trie_update_full_map(); + test_lpm_trie_iterate_strs(); + test_lpm_trie_iterate_ints(); + printf("%s: PASS\n", __func__); } -- cgit v1.3.1