diff options
Diffstat (limited to 'tools/testing/selftests/bpf')
248 files changed, 14538 insertions, 1174 deletions
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 3d8378972d26..be1ee7ba7ce0 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -44,3 +44,4 @@ xdp_redirect_multi xdp_synproxy xdp_hw_metadata xdp_features +verification_cert.h diff --git a/tools/testing/selftests/bpf/DENYLIST b/tools/testing/selftests/bpf/DENYLIST index 1789a61d0a9b..f748f2c33b22 100644 --- a/tools/testing/selftests/bpf/DENYLIST +++ b/tools/testing/selftests/bpf/DENYLIST @@ -1,6 +1,5 @@ # TEMPORARY # Alphabetical order -dynptr/test_probe_read_user_str_dynptr # disabled until https://patchwork.kernel.org/project/linux-mm/patch/20250422131449.57177-1-mykyta.yatsenko5@gmail.com/ makes it into the bpf-next get_stack_raw_tp # spams with kernel warnings until next bpf -> bpf-next merge stacktrace_build_id stacktrace_build_id_nmi diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64 deleted file mode 100644 index 12e99c0277a8..000000000000 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ /dev/null @@ -1 +0,0 @@ -tracing_struct/struct_many_args # struct_many_args:FAIL:tracing_struct_many_args__attach unexpected error: -524 diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index 3ebd77206f98..a17baf8c6fd7 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -2,4 +2,3 @@ # Alphabetical order get_stack_raw_tp # user_stack corrupted user stack (no backchain userspace) stacktrace_build_id # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2 (?) -verifier_iterating_callbacks diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 910d8d6402ef..f00587d4ede6 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -109,6 +109,7 @@ TEST_PROGS := test_kmod.sh \ test_xdping.sh \ test_bpftool_build.sh \ test_bpftool.sh \ + test_bpftool_map.sh \ test_bpftool_metadata.sh \ test_doc_build.sh \ test_xsk.sh \ @@ -119,7 +120,7 @@ TEST_PROGS_EXTENDED := \ test_bpftool.py TEST_KMODS := bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ - bpf_test_modorder_y.ko + bpf_test_modorder_y.ko bpf_test_rqspinlock.ko TEST_KMOD_TARGETS = $(addprefix $(OUTPUT)/,$(TEST_KMODS)) # Compile but not part of 'make run_tests' @@ -136,7 +137,7 @@ TEST_GEN_PROGS_EXTENDED = \ xdping \ xskxceiver -TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi +TEST_GEN_FILES += $(TEST_KMODS) liburandom_read.so urandom_read sign-file uprobe_multi ifneq ($(V),1) submake_extras := feature_display=0 @@ -397,7 +398,7 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers endif -# vmlinux.h is first dumped to a temprorary file and then compared to +# vmlinux.h is first dumped to a temporary file and then compared to # the previous version. This helps to avoid unnecessary re-builds of # $(TRUNNER_BPF_OBJS) $(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR) @@ -495,15 +496,16 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ test_subskeleton.skel.h test_subskeleton_lib.skel.h \ test_usdt.skel.h -LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c \ - trace_printk.c trace_vprintk.c map_ptr_kern.c \ +LSKELS := fexit_sleep.c trace_printk.c trace_vprintk.c map_ptr_kern.c \ core_kern.c core_kern_overflow.c test_ringbuf.c \ test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c +LSKELS_SIGNED := fentry_test.c fexit_test.c atomics.c + # Generate both light skeleton and libbpf skeleton for these LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test.c \ kfunc_call_test_subprog.c -SKEL_BLACKLIST += $$(LSKELS) +SKEL_BLACKLIST += $$(LSKELS) $$(LSKELS_SIGNED) test_static_linked.skel.h-deps := test_static_linked1.bpf.o test_static_linked2.bpf.o linked_funcs.skel.h-deps := linked_funcs1.bpf.o linked_funcs2.bpf.o @@ -534,6 +536,7 @@ HEADERS_FOR_BPF_OBJS := $(wildcard $(BPFDIR)/*.bpf.h) \ # $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, bpf_gcc, etc) define DEFINE_TEST_RUNNER +LSKEL_SIGN := -S -k $(PRIVATE_KEY) -i $(VERIFICATION_CERT) TRUNNER_OUTPUT := $(OUTPUT)$(if $2,/)$2 TRUNNER_BINARY := $1$(if $2,-)$2 TRUNNER_TEST_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.test.o, \ @@ -549,6 +552,7 @@ TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \ $$(TRUNNER_BPF_SRCS))) TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS) $$(LSKELS_EXTRA)) TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS)) +TRUNNER_BPF_LSKELS_SIGNED := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS_SIGNED)) TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS) # Evaluate rules now with extra TRUNNER_XXX variables above already defined @@ -603,6 +607,15 @@ $(TRUNNER_BPF_LSKELS): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT) $(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.llinked3.o) name $$(notdir $$(<:.bpf.o=_lskel)) > $$@ $(Q)rm -f $$(<:.o=.llinked1.o) $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o) +$(TRUNNER_BPF_LSKELS_SIGNED): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT) + $$(call msg,GEN-SKEL,$(TRUNNER_BINARY) (signed),$$@) + $(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked1.o) $$< + $(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked2.o) $$(<:.o=.llinked1.o) + $(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked3.o) $$(<:.o=.llinked2.o) + $(Q)diff $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o) + $(Q)$$(BPFTOOL) gen skeleton $(LSKEL_SIGN) $$(<:.o=.llinked3.o) name $$(notdir $$(<:.bpf.o=_lskel)) > $$@ + $(Q)rm -f $$(<:.o=.llinked1.o) $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o) + $(LINKED_BPF_OBJS): %: $(TRUNNER_OUTPUT)/% # .SECONDEXPANSION here allows to correctly expand %-deps variables as prerequisites @@ -652,6 +665,7 @@ $(TRUNNER_TEST_OBJS:.o=.d): $(TRUNNER_OUTPUT)/%.test.d: \ $(TRUNNER_EXTRA_HDRS) \ $(TRUNNER_BPF_SKELS) \ $(TRUNNER_BPF_LSKELS) \ + $(TRUNNER_BPF_LSKELS_SIGNED) \ $(TRUNNER_BPF_SKELS_LINKED) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) @@ -666,6 +680,7 @@ $(foreach N,$(patsubst $(TRUNNER_OUTPUT)/%.o,%,$(TRUNNER_EXTRA_OBJS)), \ $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ %.c \ $(TRUNNER_EXTRA_HDRS) \ + $(VERIFY_SIG_HDR) \ $(TRUNNER_TESTS_HDR) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) $$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@) @@ -696,6 +711,18 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ endef +VERIFY_SIG_SETUP := $(CURDIR)/verify_sig_setup.sh +VERIFY_SIG_HDR := verification_cert.h +VERIFICATION_CERT := $(BUILD_DIR)/signing_key.der +PRIVATE_KEY := $(BUILD_DIR)/signing_key.pem + +$(VERIFICATION_CERT) $(PRIVATE_KEY): $(VERIFY_SIG_SETUP) + $(Q)mkdir -p $(BUILD_DIR) + $(Q)$(VERIFY_SIG_SETUP) genkey $(BUILD_DIR) + +$(VERIFY_SIG_HDR): $(VERIFICATION_CERT) + $(Q)xxd -i -n test_progs_verification_cert $< > $@ + # Define test_progs test runner. TRUNNER_TESTS_DIR := prog_tests TRUNNER_BPF_PROGS_DIR := progs @@ -715,6 +742,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c \ disasm.c \ disasm_helpers.c \ json_writer.c \ + $(VERIFY_SIG_HDR) \ flow_dissector_load.h \ ip_check_defrag_frags.h TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \ @@ -724,7 +752,7 @@ TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \ $(OUTPUT)/uprobe_multi \ $(TEST_KMOD_TARGETS) \ ima_setup.sh \ - verify_sig_setup.sh \ + $(VERIFY_SIG_SETUP) \ $(wildcard progs/btf_dump_test_case_*.c) \ $(wildcard progs/*.bpf.o) TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE @@ -815,6 +843,7 @@ $(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h $(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h $(OUTPUT)/bench_bpf_crypto.o: $(OUTPUT)/crypto_bench.skel.h $(OUTPUT)/bench_sockmap.o: $(OUTPUT)/bench_sockmap_prog.skel.h +$(OUTPUT)/bench_lpm_trie_map.o: $(OUTPUT)/lpm_trie_bench.skel.h $(OUTPUT)/lpm_trie_map.skel.h $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o \ @@ -836,10 +865,16 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \ $(OUTPUT)/bench_htab_mem.o \ $(OUTPUT)/bench_bpf_crypto.o \ $(OUTPUT)/bench_sockmap.o \ + $(OUTPUT)/bench_lpm_trie_map.o \ # $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@ +# This works around GCC warning about snprintf truncating strings like: +# +# char a[PATH_MAX], b[PATH_MAX]; +# snprintf(a, "%s/foo", b); // triggers -Wformat-truncation +$(OUTPUT)/veristat.o: CFLAGS += -Wno-format-truncation $(OUTPUT)/veristat.o: $(BPFOBJ) $(OUTPUT)/veristat: $(OUTPUT)/veristat.o $(call msg,BINARY,,$@) diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index ddd73d06a1eb..bd29bb2e6cb5 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -284,6 +284,7 @@ extern struct argp bench_htab_mem_argp; extern struct argp bench_trigger_batch_argp; extern struct argp bench_crypto_argp; extern struct argp bench_sockmap_argp; +extern struct argp bench_lpm_trie_map_argp; static const struct argp_child bench_parsers[] = { { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 }, @@ -299,6 +300,7 @@ static const struct argp_child bench_parsers[] = { { &bench_trigger_batch_argp, 0, "BPF triggering benchmark", 0 }, { &bench_crypto_argp, 0, "bpf crypto benchmark", 0 }, { &bench_sockmap_argp, 0, "bpf sockmap benchmark", 0 }, + { &bench_lpm_trie_map_argp, 0, "LPM trie map benchmark", 0 }, {}, }; @@ -499,7 +501,7 @@ extern const struct bench bench_rename_rawtp; extern const struct bench bench_rename_fentry; extern const struct bench bench_rename_fexit; -/* pure counting benchmarks to establish theoretical lmits */ +/* pure counting benchmarks to establish theoretical limits */ extern const struct bench bench_trig_usermode_count; extern const struct bench bench_trig_syscall_count; extern const struct bench bench_trig_kernel_count; @@ -510,6 +512,8 @@ extern const struct bench bench_trig_kretprobe; extern const struct bench bench_trig_kprobe_multi; extern const struct bench bench_trig_kretprobe_multi; extern const struct bench bench_trig_fentry; +extern const struct bench bench_trig_kprobe_multi_all; +extern const struct bench bench_trig_kretprobe_multi_all; extern const struct bench bench_trig_fexit; extern const struct bench bench_trig_fmodret; extern const struct bench bench_trig_tp; @@ -558,6 +562,13 @@ extern const struct bench bench_htab_mem; extern const struct bench bench_crypto_encrypt; extern const struct bench bench_crypto_decrypt; extern const struct bench bench_sockmap; +extern const struct bench bench_lpm_trie_noop; +extern const struct bench bench_lpm_trie_baseline; +extern const struct bench bench_lpm_trie_lookup; +extern const struct bench bench_lpm_trie_insert; +extern const struct bench bench_lpm_trie_update; +extern const struct bench bench_lpm_trie_delete; +extern const struct bench bench_lpm_trie_free; static const struct bench *benchs[] = { &bench_count_global, @@ -578,6 +589,8 @@ static const struct bench *benchs[] = { &bench_trig_kprobe_multi, &bench_trig_kretprobe_multi, &bench_trig_fentry, + &bench_trig_kprobe_multi_all, + &bench_trig_kretprobe_multi_all, &bench_trig_fexit, &bench_trig_fmodret, &bench_trig_tp, @@ -625,6 +638,13 @@ static const struct bench *benchs[] = { &bench_crypto_encrypt, &bench_crypto_decrypt, &bench_sockmap, + &bench_lpm_trie_noop, + &bench_lpm_trie_baseline, + &bench_lpm_trie_lookup, + &bench_lpm_trie_insert, + &bench_lpm_trie_update, + &bench_lpm_trie_delete, + &bench_lpm_trie_free, }; static void find_benchmark(void) diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h index 005c401b3e22..bea323820ffb 100644 --- a/tools/testing/selftests/bpf/bench.h +++ b/tools/testing/selftests/bpf/bench.h @@ -46,6 +46,7 @@ struct bench_res { unsigned long gp_ns; unsigned long gp_ct; unsigned int stime; + unsigned long duration_ns; }; struct bench { diff --git a/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c new file mode 100644 index 000000000000..246f6cb3387d --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c @@ -0,0 +1,555 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Cloudflare */ + +/* + * All of these benchmarks operate on tries with keys in the range + * [0, args.nr_entries), i.e. there are no gaps or partially filled + * branches of the trie for any key < args.nr_entries. + * + * This gives an idea of worst-case behaviour. + */ + +#include <argp.h> +#include <linux/time64.h> +#include <linux/if_ether.h> +#include "lpm_trie_bench.skel.h" +#include "lpm_trie_map.skel.h" +#include "bench.h" +#include "testing_helpers.h" +#include "progs/lpm_trie.h" + +static struct ctx { + struct lpm_trie_bench *bench; +} ctx; + +static struct { + __u32 nr_entries; + __u32 prefixlen; + bool random; +} args = { + .nr_entries = 0, + .prefixlen = 32, + .random = false, +}; + +enum { + ARG_NR_ENTRIES = 9000, + ARG_PREFIX_LEN, + ARG_RANDOM, +}; + +static const struct argp_option opts[] = { + { "nr_entries", ARG_NR_ENTRIES, "NR_ENTRIES", 0, + "Number of unique entries in the LPM trie" }, + { "prefix_len", ARG_PREFIX_LEN, "PREFIX_LEN", 0, + "Number of prefix bits to use in the LPM trie" }, + { "random", ARG_RANDOM, NULL, 0, "Access random keys during op" }, + {}, +}; + +static error_t lpm_parse_arg(int key, char *arg, struct argp_state *state) +{ + long ret; + + switch (key) { + case ARG_NR_ENTRIES: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > UINT_MAX) { + fprintf(stderr, "Invalid nr_entries count."); + argp_usage(state); + } + args.nr_entries = ret; + break; + case ARG_PREFIX_LEN: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > UINT_MAX) { + fprintf(stderr, "Invalid prefix_len value."); + argp_usage(state); + } + args.prefixlen = ret; + break; + case ARG_RANDOM: + args.random = true; + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +const struct argp bench_lpm_trie_map_argp = { + .options = opts, + .parser = lpm_parse_arg, +}; + +static void validate_common(void) +{ + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer\n"); + exit(1); + } + + if (args.nr_entries == 0) { + fprintf(stderr, "Missing --nr_entries parameter\n"); + exit(1); + } + + if ((1UL << args.prefixlen) < args.nr_entries) { + fprintf(stderr, "prefix_len value too small for nr_entries\n"); + exit(1); + } +} + +static void lpm_insert_validate(void) +{ + validate_common(); + + if (env.producer_cnt != 1) { + fprintf(stderr, "lpm-trie-insert requires a single producer\n"); + exit(1); + } + + if (args.random) { + fprintf(stderr, "lpm-trie-insert does not support --random\n"); + exit(1); + } +} + +static void lpm_delete_validate(void) +{ + validate_common(); + + if (env.producer_cnt != 1) { + fprintf(stderr, "lpm-trie-delete requires a single producer\n"); + exit(1); + } + + if (args.random) { + fprintf(stderr, "lpm-trie-delete does not support --random\n"); + exit(1); + } +} + +static void lpm_free_validate(void) +{ + validate_common(); + + if (env.producer_cnt != 1) { + fprintf(stderr, "lpm-trie-free requires a single producer\n"); + exit(1); + } + + if (args.random) { + fprintf(stderr, "lpm-trie-free does not support --random\n"); + exit(1); + } +} + +static struct trie_key *keys; +static __u32 *vals; + +static void fill_map(int map_fd) +{ + int err; + + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + err = bpf_map_update_batch(map_fd, keys, vals, &args.nr_entries, &opts); + if (err) { + fprintf(stderr, "failed to batch update keys to map: %d\n", + -err); + exit(1); + } +} + +static void empty_map(int map_fd) +{ + int err; + + DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, + .elem_flags = 0, + .flags = 0, + ); + + err = bpf_map_delete_batch(map_fd, keys, &args.nr_entries, &opts); + if (err) { + fprintf(stderr, "failed to batch delete keys for map: %d\n", + -err); + exit(1); + } +} + +static void attach_prog(void) +{ + int i; + + ctx.bench = lpm_trie_bench__open_and_load(); + if (!ctx.bench) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + ctx.bench->bss->nr_entries = args.nr_entries; + ctx.bench->bss->prefixlen = args.prefixlen; + ctx.bench->bss->random = args.random; + + if (lpm_trie_bench__attach(ctx.bench)) { + fprintf(stderr, "failed to attach skeleton\n"); + exit(1); + } + + keys = calloc(args.nr_entries, sizeof(*keys)); + vals = calloc(args.nr_entries, sizeof(*vals)); + + for (i = 0; i < args.nr_entries; i++) { + struct trie_key *k = &keys[i]; + __u32 *v = &vals[i]; + + k->prefixlen = args.prefixlen; + k->data = i; + *v = 1; + } +} + +static void attach_prog_and_fill_map(void) +{ + int fd; + + attach_prog(); + + fd = bpf_map__fd(ctx.bench->maps.trie_map); + fill_map(fd); +} + +static void lpm_noop_setup(void) +{ + attach_prog(); + ctx.bench->bss->op = LPM_OP_NOOP; +} + +static void lpm_baseline_setup(void) +{ + attach_prog(); + ctx.bench->bss->op = LPM_OP_BASELINE; +} + +static void lpm_lookup_setup(void) +{ + attach_prog_and_fill_map(); + ctx.bench->bss->op = LPM_OP_LOOKUP; +} + +static void lpm_insert_setup(void) +{ + attach_prog(); + ctx.bench->bss->op = LPM_OP_INSERT; +} + +static void lpm_update_setup(void) +{ + attach_prog_and_fill_map(); + ctx.bench->bss->op = LPM_OP_UPDATE; +} + +static void lpm_delete_setup(void) +{ + attach_prog_and_fill_map(); + ctx.bench->bss->op = LPM_OP_DELETE; +} + +static void lpm_free_setup(void) +{ + attach_prog(); + ctx.bench->bss->op = LPM_OP_FREE; +} + +static void lpm_measure(struct bench_res *res) +{ + res->hits = atomic_swap(&ctx.bench->bss->hits, 0); + res->duration_ns = atomic_swap(&ctx.bench->bss->duration_ns, 0); +} + +static void bench_reinit_map(void) +{ + int fd = bpf_map__fd(ctx.bench->maps.trie_map); + + switch (ctx.bench->bss->op) { + case LPM_OP_INSERT: + /* trie_map needs to be emptied */ + empty_map(fd); + break; + case LPM_OP_DELETE: + /* trie_map needs to be refilled */ + fill_map(fd); + break; + default: + fprintf(stderr, "Unexpected REINIT return code for op %d\n", + ctx.bench->bss->op); + exit(1); + } +} + +/* For NOOP, BASELINE, LOOKUP, INSERT, UPDATE, and DELETE */ +static void *lpm_producer(void *unused __always_unused) +{ + int err; + char in[ETH_HLEN]; /* unused */ + + LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = in, + .data_size_in = sizeof(in), .repeat = 1, ); + + while (true) { + int fd = bpf_program__fd(ctx.bench->progs.run_bench); + err = bpf_prog_test_run_opts(fd, &opts); + if (err) { + fprintf(stderr, "failed to run BPF prog: %d\n", err); + exit(1); + } + + /* Check for kernel error code */ + if ((int)opts.retval < 0) { + fprintf(stderr, "BPF prog returned error: %d\n", + opts.retval); + exit(1); + } + + switch (opts.retval) { + case LPM_BENCH_SUCCESS: + break; + case LPM_BENCH_REINIT_MAP: + bench_reinit_map(); + break; + default: + fprintf(stderr, "Unexpected BPF prog return code %d for op %d\n", + opts.retval, ctx.bench->bss->op); + exit(1); + } + } + + return NULL; +} + +static void *lpm_free_producer(void *unused __always_unused) +{ + while (true) { + struct lpm_trie_map *skel; + + skel = lpm_trie_map__open_and_load(); + if (!skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + fill_map(bpf_map__fd(skel->maps.trie_free_map)); + lpm_trie_map__destroy(skel); + } + + return NULL; +} + +/* + * The standard bench op_report_*() functions assume measurements are + * taken over a 1-second interval but operations that modify the map + * (INSERT, DELETE, and FREE) cannot run indefinitely without + * "resetting" the map to the initial state. Depending on the size of + * the map, this likely needs to happen before the 1-second timer fires. + * + * Calculate the fraction of a second over which the op measurement was + * taken (to ignore any time spent doing the reset) and report the + * throughput results per second. + */ +static void frac_second_report_progress(int iter, struct bench_res *res, + long delta_ns, double rate_divisor, + char rate) +{ + double hits_per_sec, hits_per_prod; + + hits_per_sec = res->hits / rate_divisor / + (res->duration_ns / (double)NSEC_PER_SEC); + hits_per_prod = hits_per_sec / env.producer_cnt; + + printf("Iter %3d (%7.3lfus): ", iter, + (delta_ns - NSEC_PER_SEC) / 1000.0); + printf("hits %8.3lf%c/s (%7.3lf%c/prod)\n", hits_per_sec, rate, + hits_per_prod, rate); +} + +static void frac_second_report_final(struct bench_res res[], int res_cnt, + double lat_divisor, double rate_divisor, + char rate, const char *unit) +{ + double hits_mean = 0.0, hits_stddev = 0.0; + double latency = 0.0; + int i; + + for (i = 0; i < res_cnt; i++) { + double val = res[i].hits / rate_divisor / + (res[i].duration_ns / (double)NSEC_PER_SEC); + hits_mean += val / (0.0 + res_cnt); + latency += res[i].duration_ns / res[i].hits / (0.0 + res_cnt); + } + + if (res_cnt > 1) { + for (i = 0; i < res_cnt; i++) { + double val = + res[i].hits / rate_divisor / + (res[i].duration_ns / (double)NSEC_PER_SEC); + hits_stddev += (hits_mean - val) * (hits_mean - val) / + (res_cnt - 1.0); + } + + hits_stddev = sqrt(hits_stddev); + } + printf("Summary: throughput %8.3lf \u00B1 %5.3lf %c ops/s (%7.3lf%c ops/prod), ", + hits_mean, hits_stddev, rate, hits_mean / env.producer_cnt, + rate); + printf("latency %8.3lf %s/op\n", + latency / lat_divisor / env.producer_cnt, unit); +} + +static void insert_ops_report_progress(int iter, struct bench_res *res, + long delta_ns) +{ + double rate_divisor = 1000000.0; + char rate = 'M'; + + frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate); +} + +static void delete_ops_report_progress(int iter, struct bench_res *res, + long delta_ns) +{ + double rate_divisor = 1000000.0; + char rate = 'M'; + + frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate); +} + +static void free_ops_report_progress(int iter, struct bench_res *res, + long delta_ns) +{ + double rate_divisor = 1000.0; + char rate = 'K'; + + frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate); +} + +static void insert_ops_report_final(struct bench_res res[], int res_cnt) +{ + double lat_divisor = 1.0; + double rate_divisor = 1000000.0; + const char *unit = "ns"; + char rate = 'M'; + + frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate, + unit); +} + +static void delete_ops_report_final(struct bench_res res[], int res_cnt) +{ + double lat_divisor = 1.0; + double rate_divisor = 1000000.0; + const char *unit = "ns"; + char rate = 'M'; + + frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate, + unit); +} + +static void free_ops_report_final(struct bench_res res[], int res_cnt) +{ + double lat_divisor = 1000000.0; + double rate_divisor = 1000.0; + const char *unit = "ms"; + char rate = 'K'; + + frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate, + unit); +} + +/* noop bench measures harness-overhead */ +const struct bench bench_lpm_trie_noop = { + .name = "lpm-trie-noop", + .argp = &bench_lpm_trie_map_argp, + .validate = validate_common, + .setup = lpm_noop_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +/* baseline overhead for lookup and update */ +const struct bench bench_lpm_trie_baseline = { + .name = "lpm-trie-baseline", + .argp = &bench_lpm_trie_map_argp, + .validate = validate_common, + .setup = lpm_baseline_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +/* measure cost of doing a lookup on existing entries in a full trie */ +const struct bench bench_lpm_trie_lookup = { + .name = "lpm-trie-lookup", + .argp = &bench_lpm_trie_map_argp, + .validate = validate_common, + .setup = lpm_lookup_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +/* measure cost of inserting new entries into an empty trie */ +const struct bench bench_lpm_trie_insert = { + .name = "lpm-trie-insert", + .argp = &bench_lpm_trie_map_argp, + .validate = lpm_insert_validate, + .setup = lpm_insert_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = insert_ops_report_progress, + .report_final = insert_ops_report_final, +}; + +/* measure cost of updating existing entries in a full trie */ +const struct bench bench_lpm_trie_update = { + .name = "lpm-trie-update", + .argp = &bench_lpm_trie_map_argp, + .validate = validate_common, + .setup = lpm_update_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +/* measure cost of deleting existing entries from a full trie */ +const struct bench bench_lpm_trie_delete = { + .name = "lpm-trie-delete", + .argp = &bench_lpm_trie_map_argp, + .validate = lpm_delete_validate, + .setup = lpm_delete_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = delete_ops_report_progress, + .report_final = delete_ops_report_final, +}; + +/* measure cost of freeing a full trie */ +const struct bench bench_lpm_trie_free = { + .name = "lpm-trie-free", + .argp = &bench_lpm_trie_map_argp, + .validate = lpm_free_validate, + .setup = lpm_free_setup, + .producer_thread = lpm_free_producer, + .measure = lpm_measure, + .report_progress = free_ops_report_progress, + .report_final = free_ops_report_final, +}; diff --git a/tools/testing/selftests/bpf/benchs/bench_sockmap.c b/tools/testing/selftests/bpf/benchs/bench_sockmap.c index 8ebf563a67a2..cfc072aa7fff 100644 --- a/tools/testing/selftests/bpf/benchs/bench_sockmap.c +++ b/tools/testing/selftests/bpf/benchs/bench_sockmap.c @@ -10,6 +10,7 @@ #include <argp.h> #include "bench.h" #include "bench_sockmap_prog.skel.h" +#include "bpf_util.h" #define FILE_SIZE (128 * 1024) #define DATA_REPEAT_SIZE 10 @@ -124,8 +125,8 @@ static void bench_sockmap_prog_destroy(void) { int i; - for (i = 0; i < sizeof(ctx.fds); i++) { - if (ctx.fds[0] > 0) + for (i = 0; i < ARRAY_SIZE(ctx.fds); i++) { + if (ctx.fds[i] > 0) close(ctx.fds[i]); } diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 82327657846e..1e2aff007c2a 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -226,6 +226,65 @@ static void trigger_fentry_setup(void) attach_bpf(ctx.skel->progs.bench_trigger_fentry); } +static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + char **syms = NULL; + size_t cnt = 0; + + /* Some recursive functions will be skipped in + * bpf_get_ksyms -> skip_entry, as they can introduce sufficient + * overhead. However, it's difficut to skip all the recursive + * functions for a debug kernel. + * + * So, don't run the kprobe-multi-all and kretprobe-multi-all on + * a debug kernel. + */ + if (bpf_get_ksyms(&syms, &cnt, true)) { + fprintf(stderr, "failed to get ksyms\n"); + exit(1); + } + + opts.syms = (const char **) syms; + opts.cnt = cnt; + opts.retprobe = kretprobe; + /* attach empty to all the kernel functions except bpf_get_numa_node_id. */ + if (!bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts)) { + fprintf(stderr, "failed to attach bpf_program__attach_kprobe_multi_opts to all\n"); + exit(1); + } +} + +static void trigger_kprobe_multi_all_setup(void) +{ + struct bpf_program *prog, *empty; + + setup_ctx(); + empty = ctx.skel->progs.bench_kprobe_multi_empty; + prog = ctx.skel->progs.bench_trigger_kprobe_multi; + bpf_program__set_autoload(empty, true); + bpf_program__set_autoload(prog, true); + load_ctx(); + + attach_ksyms_all(empty, false); + attach_bpf(prog); +} + +static void trigger_kretprobe_multi_all_setup(void) +{ + struct bpf_program *prog, *empty; + + setup_ctx(); + empty = ctx.skel->progs.bench_kretprobe_multi_empty; + prog = ctx.skel->progs.bench_trigger_kretprobe_multi; + bpf_program__set_autoload(empty, true); + bpf_program__set_autoload(prog, true); + load_ctx(); + + attach_ksyms_all(empty, true); + attach_bpf(prog); +} + static void trigger_fexit_setup(void) { setup_ctx(); @@ -512,6 +571,8 @@ BENCH_TRIG_KERNEL(kretprobe, "kretprobe"); BENCH_TRIG_KERNEL(kprobe_multi, "kprobe-multi"); BENCH_TRIG_KERNEL(kretprobe_multi, "kretprobe-multi"); BENCH_TRIG_KERNEL(fentry, "fentry"); +BENCH_TRIG_KERNEL(kprobe_multi_all, "kprobe-multi-all"); +BENCH_TRIG_KERNEL(kretprobe_multi_all, "kretprobe-multi-all"); BENCH_TRIG_KERNEL(fexit, "fexit"); BENCH_TRIG_KERNEL(fmodret, "fmodret"); BENCH_TRIG_KERNEL(tp, "tp"); diff --git a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh index a690f5a68b6b..f7573708a0c3 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh @@ -6,8 +6,8 @@ def_tests=( \ usermode-count kernel-count syscall-count \ fentry fexit fmodret \ rawtp tp \ - kprobe kprobe-multi \ - kretprobe kretprobe-multi \ + kprobe kprobe-multi kprobe-multi-all \ + kretprobe kretprobe-multi kretprobe-multi-all \ ) tests=("$@") diff --git a/tools/testing/selftests/bpf/bpf_arena_common.h b/tools/testing/selftests/bpf/bpf_arena_common.h index 68a51dcc0669..16f8ce832004 100644 --- a/tools/testing/selftests/bpf/bpf_arena_common.h +++ b/tools/testing/selftests/bpf/bpf_arena_common.h @@ -46,8 +46,11 @@ void __arena* bpf_arena_alloc_pages(void *map, void __arena *addr, __u32 page_cnt, int node_id, __u64 flags) __ksym __weak; +int bpf_arena_reserve_pages(void *map, void __arena *addr, __u32 page_cnt) __ksym __weak; void bpf_arena_free_pages(void *map, void __arena *ptr, __u32 page_cnt) __ksym __weak; +#define arena_base(map) ((void __arena *)((struct bpf_arena *)(map))->user_vm_start) + #else /* when compiled as user space code */ #define __arena diff --git a/tools/testing/selftests/bpf/bpf_atomic.h b/tools/testing/selftests/bpf/bpf_atomic.h index a9674e544322..c550e5711967 100644 --- a/tools/testing/selftests/bpf/bpf_atomic.h +++ b/tools/testing/selftests/bpf/bpf_atomic.h @@ -61,7 +61,7 @@ extern bool CONFIG_X86_64 __kconfig __weak; #define smp_mb() \ ({ \ - unsigned long __val; \ + volatile unsigned long __val; \ __sync_fetch_and_add(&__val, 0); \ }) diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 5e512a1d09d1..2cd9165c7348 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -219,7 +219,7 @@ extern void bpf_put_file(struct file *file) __ksym; * including the NULL termination character, stored in the supplied * buffer. On error, a negative integer is returned. */ -extern int bpf_path_d_path(struct path *path, char *buf, size_t buf__sz) __ksym; +extern int bpf_path_d_path(const struct path *path, char *buf, size_t buf__sz) __ksym; /* This macro must be used to mark the exception callback corresponding to the * main program. For example: @@ -596,4 +596,61 @@ extern int bpf_iter_dmabuf_new(struct bpf_iter_dmabuf *it) __weak __ksym; extern struct dma_buf *bpf_iter_dmabuf_next(struct bpf_iter_dmabuf *it) __weak __ksym; extern void bpf_iter_dmabuf_destroy(struct bpf_iter_dmabuf *it) __weak __ksym; +extern int bpf_cgroup_read_xattr(struct cgroup *cgroup, const char *name__str, + struct bpf_dynptr *value_p) __weak __ksym; + +#define PREEMPT_BITS 8 +#define SOFTIRQ_BITS 8 +#define HARDIRQ_BITS 4 +#define NMI_BITS 4 + +#define PREEMPT_SHIFT 0 +#define SOFTIRQ_SHIFT (PREEMPT_SHIFT + PREEMPT_BITS) +#define HARDIRQ_SHIFT (SOFTIRQ_SHIFT + SOFTIRQ_BITS) +#define NMI_SHIFT (HARDIRQ_SHIFT + HARDIRQ_BITS) + +#define __IRQ_MASK(x) ((1UL << (x))-1) + +#define SOFTIRQ_MASK (__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) +#define HARDIRQ_MASK (__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT) +#define NMI_MASK (__IRQ_MASK(NMI_BITS) << NMI_SHIFT) + +extern bool CONFIG_PREEMPT_RT __kconfig __weak; +#ifdef bpf_target_x86 +extern const int __preempt_count __ksym; +#endif + +struct task_struct___preempt_rt { + int softirq_disable_cnt; +} __attribute__((preserve_access_index)); + +static inline int get_preempt_count(void) +{ +#if defined(bpf_target_x86) + return *(int *) bpf_this_cpu_ptr(&__preempt_count); +#elif defined(bpf_target_arm64) + return bpf_get_current_task_btf()->thread_info.preempt.count; +#endif + return 0; +} + +/* Description + * Report whether it is in interrupt context. Only works on the following archs: + * * x86 + * * arm64 + */ +static inline int bpf_in_interrupt(void) +{ + struct task_struct___preempt_rt *tsk; + int pcnt; + + pcnt = get_preempt_count(); + if (!CONFIG_PREEMPT_RT) + return pcnt & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_MASK); + + tsk = (void *) bpf_get_current_task_btf(); + return (pcnt & (NMI_MASK | HARDIRQ_MASK)) | + (tsk->softirq_disable_cnt & SOFTIRQ_MASK); +} + #endif diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index 8215c9b3115e..794d44d19c88 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -19,6 +19,9 @@ extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags, extern int bpf_dynptr_from_xdp(struct xdp_md *xdp, __u64 flags, struct bpf_dynptr *ptr__uninit) __ksym __weak; +extern int bpf_dynptr_from_skb_meta(struct __sk_buff *skb, __u64 flags, + struct bpf_dynptr *ptr__uninit) __ksym __weak; + /* Description * Obtain a read-only pointer to the dynptr's data * Returns @@ -69,7 +72,7 @@ extern int bpf_get_file_xattr(struct file *file, const char *name, struct bpf_dynptr *value_ptr) __ksym; extern int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *digest_ptr) __ksym; -extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym; +extern struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym; extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; extern void bpf_key_put(struct bpf_key *key) __ksym; extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr, diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 5f6963a320d7..4bc2d25f33e1 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -67,6 +67,9 @@ static inline void bpf_strlcpy(char *dst, const char *src, size_t sz) #define sys_gettid() syscall(SYS_gettid) #endif +/* and poison usage to ensure it does not creep back in. */ +#pragma GCC poison gettid + #ifndef ENOTSUPP #define ENOTSUPP 524 #endif diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index e4535451322e..20cede4db3ce 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -4,6 +4,7 @@ #include <sys/mount.h> #include <sys/stat.h> #include <sys/types.h> +#include <sys/xattr.h> #include <linux/limits.h> #include <stdio.h> #include <stdlib.h> @@ -319,6 +320,26 @@ int join_parent_cgroup(const char *relative_path) } /** + * set_cgroup_xattr() - Set xattr on a cgroup dir + * @relative_path: The cgroup path, relative to the workdir, to set xattr + * @name: xattr name + * @value: xattr value + * + * This function set xattr on cgroup dir. + * + * On success, it returns 0, otherwise on failure it returns -1. + */ +int set_cgroup_xattr(const char *relative_path, + const char *name, + const char *value) +{ + char cgroup_path[PATH_MAX + 1]; + + format_cgroup_path(cgroup_path, relative_path); + return setxattr(cgroup_path, name, value, strlen(value) + 1, 0); +} + +/** * __cleanup_cgroup_environment() - Delete temporary cgroups * * This is a helper for cleanup_cgroup_environment() that is responsible for @@ -391,6 +412,26 @@ void remove_cgroup(const char *relative_path) log_err("rmdiring cgroup %s .. %s", relative_path, cgroup_path); } +/* + * remove_cgroup_pid() - Remove a cgroup setup by process identified by PID + * @relative_path: The cgroup path, relative to the workdir, to remove + * @pid: PID to be used to find cgroup_path + * + * This function expects a cgroup to already be created, relative to the cgroup + * work dir. It also expects the cgroup doesn't have any children or live + * processes and it removes the cgroup. + * + * On failure, it will print an error to stderr. + */ +void remove_cgroup_pid(const char *relative_path, int pid) +{ + char cgroup_path[PATH_MAX + 1]; + + format_cgroup_path_pid(cgroup_path, relative_path, pid); + if (rmdir(cgroup_path)) + log_err("rmdiring cgroup %s .. %s", relative_path, cgroup_path); +} + /** * create_and_get_cgroup() - Create a cgroup, relative to workdir, and get the FD * @relative_path: The cgroup path, relative to the workdir, to join diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index 502845160d88..3857304be874 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -19,6 +19,7 @@ int cgroup_setup_and_join(const char *relative_path); int get_root_cgroup(void); int create_and_get_cgroup(const char *relative_path); void remove_cgroup(const char *relative_path); +void remove_cgroup_pid(const char *relative_path, int pid); unsigned long long get_cgroup_id(const char *relative_path); int get_cgroup1_hierarchy_id(const char *subsys_name); @@ -26,6 +27,10 @@ int join_cgroup(const char *relative_path); int join_root_cgroup(void); int join_parent_cgroup(const char *relative_path); +int set_cgroup_xattr(const char *relative_path, + const char *name, + const char *value); + int setup_cgroup_environment(void); void cleanup_cgroup_environment(void); diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index f74e1ea0ad3b..70b28c1e653e 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -61,6 +61,7 @@ CONFIG_MPLS_IPTUNNEL=y CONFIG_MPLS_ROUTING=y CONFIG_MPTCP=y CONFIG_NET_ACT_GACT=y +CONFIG_NET_ACT_MIRRED=y CONFIG_NET_ACT_SKBMOD=y CONFIG_NET_CLS=y CONFIG_NET_CLS_ACT=y @@ -97,6 +98,9 @@ CONFIG_NF_TABLES_NETDEV=y CONFIG_NF_TABLES_IPV4=y CONFIG_NF_TABLES_IPV6=y CONFIG_NETFILTER_INGRESS=y +CONFIG_IP_NF_IPTABLES_LEGACY=y +CONFIG_IP6_NF_IPTABLES_LEGACY=y +CONFIG_NETFILTER_XTABLES_LEGACY=y CONFIG_NF_FLOW_TABLE=y CONFIG_NF_FLOW_TABLE_INET=y CONFIG_NETFILTER_NETLINK=y @@ -105,6 +109,7 @@ CONFIG_IP_NF_IPTABLES=y CONFIG_IP6_NF_IPTABLES=y CONFIG_IP6_NF_FILTER=y CONFIG_NF_NAT=y +CONFIG_PACKET=y CONFIG_RC_CORE=y CONFIG_SECURITY=y CONFIG_SECURITYFS=y diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64 index e1495a4bbc99..7efad36ceb26 100644 --- a/tools/testing/selftests/bpf/config.aarch64 +++ b/tools/testing/selftests/bpf/config.aarch64 @@ -31,10 +31,7 @@ CONFIG_COMPAT=y CONFIG_CPUSETS=y CONFIG_CRASH_DUMP=y CONFIG_CRYPTO_USER_API_RNG=y -CONFIG_CRYPTO_USER_API_SKCIPHER=y CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_INFO_BTF=y -CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_INFO_REDUCED=n CONFIG_DEBUG_LIST=y CONFIG_DEBUG_LOCKDEP=y @@ -46,7 +43,6 @@ CONFIG_DETECT_HUNG_TASK=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_DEVTMPFS=y CONFIG_DRM=y -CONFIG_DUMMY=y CONFIG_EXPERT=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -70,13 +66,11 @@ CONFIG_HZ_100=y CONFIG_IDLE_PAGE_TRACKING=y CONFIG_IKHEADERS=y CONFIG_INET6_ESP=y -CONFIG_INET_ESP=y CONFIG_INET=y CONFIG_INPUT_EVDEV=y CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MULTICAST=y CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_NF_IPTABLES=y CONFIG_IPV6_SEG6_LWTUNNEL=y CONFIG_IPVLAN=y CONFIG_JUMP_LABEL=y @@ -97,22 +91,18 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_NAMESPACES=y CONFIG_NET_ACT_BPF=y -CONFIG_NET_ACT_GACT=y CONFIG_NETDEVICES=y CONFIG_NETFILTER_XT_MATCH_BPF=y CONFIG_NETFILTER_XT_TARGET_MARK=y CONFIG_NET_KEY=y -CONFIG_NET_SCH_FQ=y CONFIG_NET_VRF=y CONFIG_NET=y -CONFIG_NF_TABLES=y CONFIG_NLMON=y CONFIG_NO_HZ_IDLE=y CONFIG_NR_CPUS=256 CONFIG_NUMA=y CONFIG_OVERLAY_FS=y CONFIG_PACKET_DIAG=y -CONFIG_PACKET=y CONFIG_PANIC_ON_OOPS=y CONFIG_PARTITION_ADVANCED=y CONFIG_PCI_HOST_GENERIC=y @@ -149,7 +139,6 @@ CONFIG_TASK_XACCT=y CONFIG_TCG_TIS=y CONFIG_TCG_TPM=y CONFIG_TCP_CONG_ADVANCED=y -CONFIG_TCP_CONG_DCTCP=y CONFIG_TLS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS=y @@ -161,6 +150,5 @@ CONFIG_UPROBES=y CONFIG_USER_NS=y CONFIG_VETH=y CONFIG_VLAN_8021Q=y -CONFIG_VSOCKETS=y CONFIG_VSOCKETS_LOOPBACK=y CONFIG_XFRM_USER=y diff --git a/tools/testing/selftests/bpf/config.ppc64el b/tools/testing/selftests/bpf/config.ppc64el new file mode 100644 index 000000000000..b53afb5e0b71 --- /dev/null +++ b/tools/testing/selftests/bpf/config.ppc64el @@ -0,0 +1,92 @@ +CONFIG_ALTIVEC=y +CONFIG_AUDIT=y +CONFIG_BLK_CGROUP=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BONDING=y +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_BPF_PRELOAD_UMD=y +CONFIG_BPF_PRELOAD=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_HUGETLB=y +CONFIG_CGROUP_NET_CLASSID=y +CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_SCHED=y +CONFIG_CGROUPS=y +CONFIG_CMDLINE_BOOL=y +CONFIG_CMDLINE="console=hvc0 wg.success=hvc1 panic_on_warn=1" +CONFIG_CPU_LITTLE_ENDIAN=y +CONFIG_CPUSETS=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DEBUG_FS=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_DEVTMPFS=y +CONFIG_EXPERT=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_FS=y +CONFIG_FRAME_POINTER=y +CONFIG_FRAME_WARN=1280 +CONFIG_HARDLOCKUP_DETECTOR=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_HUGETLBFS=y +CONFIG_HVC_CONSOLE=y +CONFIG_INET=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IPV6_SEG6_LWTUNNEL=y +CONFIG_JUMP_LABEL=y +CONFIG_KALLSYMS_ALL=y +CONFIG_KPROBES=y +CONFIG_MEMCG=y +CONFIG_NAMESPACES=y +CONFIG_NET_ACT_BPF=y +CONFIG_NETDEVICES=y +CONFIG_NETFILTER_XT_MATCH_BPF=y +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_NET_VRF=y +CONFIG_NET=y +CONFIG_NO_HZ_IDLE=y +CONFIG_NONPORTABLE=y +CONFIG_NR_CPUS=256 +CONFIG_PANIC_ON_OOPS=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_PCI_HOST_GENERIC=y +CONFIG_PCI=y +CONFIG_POSIX_MQUEUE=y +CONFIG_PPC64=y +CONFIG_PPC_OF_BOOT_TRAMPOLINE=y +CONFIG_PPC_PSERIES=y +CONFIG_PPC_RADIX_MMU=y +CONFIG_PRINTK_TIME=y +CONFIG_PROC_KCORE=y +CONFIG_PROFILING=y +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_RT_GROUP_SCHED=y +CONFIG_SECTION_MISMATCH_WARN_ONLY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_SMP=y +CONFIG_SOC_VIRT=y +CONFIG_SYSVIPC=y +CONFIG_TCP_CONG_ADVANCED=y +CONFIG_THREAD_SHIFT=14 +CONFIG_TLS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_TMPFS=y +CONFIG_TUN=y +CONFIG_UNIX=y +CONFIG_UPROBES=y +CONFIG_USER_NS=y +CONFIG_VETH=y +CONFIG_VLAN_8021Q=y +CONFIG_VSOCKETS_LOOPBACK=y +CONFIG_VSX=y +CONFIG_XFRM_USER=y diff --git a/tools/testing/selftests/bpf/config.riscv64 b/tools/testing/selftests/bpf/config.riscv64 index bb7043a80e1a..7bee24a79a71 100644 --- a/tools/testing/selftests/bpf/config.riscv64 +++ b/tools/testing/selftests/bpf/config.riscv64 @@ -48,7 +48,6 @@ CONFIG_NET_VRF=y CONFIG_NONPORTABLE=y CONFIG_NO_HZ_IDLE=y CONFIG_NR_CPUS=256 -CONFIG_PACKET=y CONFIG_PANIC_ON_OOPS=y CONFIG_PARTITION_ADVANCED=y CONFIG_PCI=y diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x index 26c3bc2ce11d..db61878148e4 100644 --- a/tools/testing/selftests/bpf/config.s390x +++ b/tools/testing/selftests/bpf/config.s390x @@ -22,10 +22,7 @@ CONFIG_CHECKPOINT_RESTORE=y CONFIG_CPUSETS=y CONFIG_CRASH_DUMP=y CONFIG_CRYPTO_USER_API_RNG=y -CONFIG_CRYPTO_USER_API_SKCIPHER=y CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_INFO_BTF=y -CONFIG_DEBUG_INFO_DWARF4=y CONFIG_DEBUG_LIST=y CONFIG_DEBUG_LOCKDEP=y CONFIG_DEBUG_NOTIFIERS=y @@ -56,11 +53,9 @@ CONFIG_IDLE_PAGE_TRACKING=y CONFIG_IKHEADERS=y CONFIG_INET6_ESP=y CONFIG_INET=y -CONFIG_INET_ESP=y CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MULTICAST=y CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_NF_IPTABLES=y CONFIG_IPV6_SEG6_LWTUNNEL=y CONFIG_IPVLAN=y CONFIG_JUMP_LABEL=y @@ -83,18 +78,14 @@ CONFIG_MEMORY_HOTREMOVE=y CONFIG_NAMESPACES=y CONFIG_NET=y CONFIG_NET_ACT_BPF=y -CONFIG_NET_ACT_GACT=y CONFIG_NET_KEY=y -CONFIG_NET_SCH_FQ=y CONFIG_NET_VRF=y CONFIG_NETDEVICES=y CONFIG_NETFILTER_XT_MATCH_BPF=y CONFIG_NETFILTER_XT_TARGET_MARK=y -CONFIG_NF_TABLES=y CONFIG_NO_HZ_IDLE=y CONFIG_NR_CPUS=256 CONFIG_NUMA=y -CONFIG_PACKET=y CONFIG_PANIC_ON_OOPS=y CONFIG_PARTITION_ADVANCED=y CONFIG_PCI=y @@ -119,7 +110,6 @@ CONFIG_TASK_IO_ACCOUNTING=y CONFIG_TASK_XACCT=y CONFIG_TASKSTATS=y CONFIG_TCP_CONG_ADVANCED=y -CONFIG_TCP_CONG_DCTCP=y CONFIG_TLS=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y @@ -131,6 +121,5 @@ CONFIG_UPROBES=y CONFIG_USER_NS=y CONFIG_VETH=y CONFIG_VLAN_8021Q=y -CONFIG_VSOCKETS=y CONFIG_VSOCKETS_LOOPBACK=y CONFIG_XFRM_USER=y diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64 index 5e713ef7caa3..42ad817b00ae 100644 --- a/tools/testing/selftests/bpf/config.x86_64 +++ b/tools/testing/selftests/bpf/config.x86_64 @@ -44,7 +44,6 @@ CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_XXHASH=y CONFIG_DCB=y CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEFAULT_FQ_CODEL=y @@ -104,12 +103,10 @@ CONFIG_HZ_1000=y CONFIG_INET=y CONFIG_INPUT_EVDEV=y CONFIG_INTEL_POWERCLAMP=y -CONFIG_IP6_NF_IPTABLES=y CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MROUTE=y CONFIG_IP_MULTICAST=y CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_NF_IPTABLES=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y CONFIG_IP_ROUTE_MULTIPATH=y @@ -162,7 +159,6 @@ CONFIG_NUMA=y CONFIG_NUMA_BALANCING=y CONFIG_NVMEM=y CONFIG_OSF_PARTITION=y -CONFIG_PACKET=y CONFIG_PANIC_ON_OOPS=y CONFIG_PARTITION_ADVANCED=y CONFIG_PCI=y @@ -220,7 +216,6 @@ CONFIG_VALIDATE_FS_PARSER=y CONFIG_VETH=y CONFIG_VIRT_DRIVERS=y CONFIG_VLAN_8021Q=y -CONFIG_VSOCKETS=y CONFIG_VSOCKETS_LOOPBACK=y CONFIG_X86_ACPI_CPUFREQ=y CONFIG_X86_CPUID=y diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 72b5c174ab3b..cdf7b6641444 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -457,7 +457,7 @@ int append_tid(char *str, size_t sz) if (end + 8 > sz) return -1; - sprintf(&str[end], "%07d", gettid()); + sprintf(&str[end], "%07ld", sys_gettid()); str[end + 7] = '\0'; return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index 1d53a8561ee2..24c509ce4e5b 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -42,11 +42,11 @@ static struct bpf_align_test tests[] = { .matches = { {0, "R1", "ctx()"}, {0, "R10", "fp0"}, - {0, "R3_w", "2"}, - {1, "R3_w", "4"}, - {2, "R3_w", "8"}, - {3, "R3_w", "16"}, - {4, "R3_w", "32"}, + {0, "R3", "2"}, + {1, "R3", "4"}, + {2, "R3", "8"}, + {3, "R3", "16"}, + {4, "R3", "32"}, }, }, { @@ -70,17 +70,17 @@ static struct bpf_align_test tests[] = { .matches = { {0, "R1", "ctx()"}, {0, "R10", "fp0"}, - {0, "R3_w", "1"}, - {1, "R3_w", "2"}, - {2, "R3_w", "4"}, - {3, "R3_w", "8"}, - {4, "R3_w", "16"}, - {5, "R3_w", "1"}, - {6, "R4_w", "32"}, - {7, "R4_w", "16"}, - {8, "R4_w", "8"}, - {9, "R4_w", "4"}, - {10, "R4_w", "2"}, + {0, "R3", "1"}, + {1, "R3", "2"}, + {2, "R3", "4"}, + {3, "R3", "8"}, + {4, "R3", "16"}, + {5, "R3", "1"}, + {6, "R4", "32"}, + {7, "R4", "16"}, + {8, "R4", "8"}, + {9, "R4", "4"}, + {10, "R4", "2"}, }, }, { @@ -99,12 +99,12 @@ static struct bpf_align_test tests[] = { .matches = { {0, "R1", "ctx()"}, {0, "R10", "fp0"}, - {0, "R3_w", "4"}, - {1, "R3_w", "8"}, - {2, "R3_w", "10"}, - {3, "R4_w", "8"}, - {4, "R4_w", "12"}, - {5, "R4_w", "14"}, + {0, "R3", "4"}, + {1, "R3", "8"}, + {2, "R3", "10"}, + {3, "R4", "8"}, + {4, "R4", "12"}, + {5, "R4", "14"}, }, }, { @@ -121,10 +121,10 @@ static struct bpf_align_test tests[] = { .matches = { {0, "R1", "ctx()"}, {0, "R10", "fp0"}, - {0, "R3_w", "7"}, - {1, "R3_w", "7"}, - {2, "R3_w", "14"}, - {3, "R3_w", "56"}, + {0, "R3", "7"}, + {1, "R3", "7"}, + {2, "R3", "14"}, + {3, "R3", "56"}, }, }, @@ -162,19 +162,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {6, "R0_w", "pkt(off=8,r=8)"}, - {6, "R3_w", "var_off=(0x0; 0xff)"}, - {7, "R3_w", "var_off=(0x0; 0x1fe)"}, - {8, "R3_w", "var_off=(0x0; 0x3fc)"}, - {9, "R3_w", "var_off=(0x0; 0x7f8)"}, - {10, "R3_w", "var_off=(0x0; 0xff0)"}, - {12, "R3_w", "pkt_end()"}, - {17, "R4_w", "var_off=(0x0; 0xff)"}, - {18, "R4_w", "var_off=(0x0; 0x1fe0)"}, - {19, "R4_w", "var_off=(0x0; 0xff0)"}, - {20, "R4_w", "var_off=(0x0; 0x7f8)"}, - {21, "R4_w", "var_off=(0x0; 0x3fc)"}, - {22, "R4_w", "var_off=(0x0; 0x1fe)"}, + {6, "R0", "pkt(off=8,r=8)"}, + {6, "R3", "var_off=(0x0; 0xff)"}, + {7, "R3", "var_off=(0x0; 0x1fe)"}, + {8, "R3", "var_off=(0x0; 0x3fc)"}, + {9, "R3", "var_off=(0x0; 0x7f8)"}, + {10, "R3", "var_off=(0x0; 0xff0)"}, + {12, "R3", "pkt_end()"}, + {17, "R4", "var_off=(0x0; 0xff)"}, + {18, "R4", "var_off=(0x0; 0x1fe0)"}, + {19, "R4", "var_off=(0x0; 0xff0)"}, + {20, "R4", "var_off=(0x0; 0x7f8)"}, + {21, "R4", "var_off=(0x0; 0x3fc)"}, + {22, "R4", "var_off=(0x0; 0x1fe)"}, }, }, { @@ -195,16 +195,16 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {6, "R3_w", "var_off=(0x0; 0xff)"}, - {7, "R4_w", "var_off=(0x0; 0xff)"}, - {8, "R4_w", "var_off=(0x0; 0xff)"}, - {9, "R4_w", "var_off=(0x0; 0xff)"}, - {10, "R4_w", "var_off=(0x0; 0x1fe)"}, - {11, "R4_w", "var_off=(0x0; 0xff)"}, - {12, "R4_w", "var_off=(0x0; 0x3fc)"}, - {13, "R4_w", "var_off=(0x0; 0xff)"}, - {14, "R4_w", "var_off=(0x0; 0x7f8)"}, - {15, "R4_w", "var_off=(0x0; 0xff0)"}, + {6, "R3", "var_off=(0x0; 0xff)"}, + {7, "R4", "var_off=(0x0; 0xff)"}, + {8, "R4", "var_off=(0x0; 0xff)"}, + {9, "R4", "var_off=(0x0; 0xff)"}, + {10, "R4", "var_off=(0x0; 0x1fe)"}, + {11, "R4", "var_off=(0x0; 0xff)"}, + {12, "R4", "var_off=(0x0; 0x3fc)"}, + {13, "R4", "var_off=(0x0; 0xff)"}, + {14, "R4", "var_off=(0x0; 0x7f8)"}, + {15, "R4", "var_off=(0x0; 0xff0)"}, }, }, { @@ -235,14 +235,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {2, "R5_w", "pkt(r=0)"}, - {4, "R5_w", "pkt(off=14,r=0)"}, - {5, "R4_w", "pkt(off=14,r=0)"}, + {2, "R5", "pkt(r=0)"}, + {4, "R5", "pkt(off=14,r=0)"}, + {5, "R4", "pkt(off=14,r=0)"}, {9, "R2", "pkt(r=18)"}, {10, "R5", "pkt(off=14,r=18)"}, - {10, "R4_w", "var_off=(0x0; 0xff)"}, - {13, "R4_w", "var_off=(0x0; 0xffff)"}, - {14, "R4_w", "var_off=(0x0; 0xffff)"}, + {10, "R4", "var_off=(0x0; 0xff)"}, + {13, "R4", "var_off=(0x0; 0xffff)"}, + {14, "R4", "var_off=(0x0; 0xffff)"}, }, }, { @@ -299,12 +299,12 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w", "pkt(r=8)"}, - {7, "R6_w", "var_off=(0x0; 0x3fc)"}, + {6, "R2", "pkt(r=8)"}, + {7, "R6", "var_off=(0x0; 0x3fc)"}, /* Offset is added to packet pointer R5, resulting in * known fixed offset, and variable offset from R6. */ - {11, "R5_w", "pkt(id=1,off=14,"}, + {11, "R5", "pkt(id=1,off=14,"}, /* At the time the word size load is performed from R5, * it's total offset is NET_IP_ALIGN + reg->off (0) + * reg->aux_off (14) which is 16. Then the variable @@ -320,12 +320,12 @@ static struct bpf_align_test tests[] = { * instruction to validate R5 state. We also check * that R4 is what it should be in such case. */ - {18, "R4_w", "var_off=(0x0; 0x3fc)"}, - {18, "R5_w", "var_off=(0x0; 0x3fc)"}, + {18, "R4", "var_off=(0x0; 0x3fc)"}, + {18, "R5", "var_off=(0x0; 0x3fc)"}, /* Constant offset is added to R5, resulting in * reg->off of 14. */ - {19, "R5_w", "pkt(id=2,off=14,"}, + {19, "R5", "pkt(id=2,off=14,"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off * (14) which is 16. Then the variable offset is 4-byte @@ -337,21 +337,21 @@ static struct bpf_align_test tests[] = { /* Constant offset is added to R5 packet pointer, * resulting in reg->off value of 14. */ - {26, "R5_w", "pkt(off=14,r=8)"}, + {26, "R5", "pkt(off=14,r=8)"}, /* Variable offset is added to R5, resulting in a * variable offset of (4n). See comment for insn #18 * for R4 = R5 trick. */ - {28, "R4_w", "var_off=(0x0; 0x3fc)"}, - {28, "R5_w", "var_off=(0x0; 0x3fc)"}, + {28, "R4", "var_off=(0x0; 0x3fc)"}, + {28, "R5", "var_off=(0x0; 0x3fc)"}, /* Constant is added to R5 again, setting reg->off to 18. */ - {29, "R5_w", "pkt(id=3,off=18,"}, + {29, "R5", "pkt(id=3,off=18,"}, /* And once more we add a variable; resulting var_off * is still (4n), fixed offset is not changed. * Also, we create a new reg->id. */ - {31, "R4_w", "var_off=(0x0; 0x7fc)"}, - {31, "R5_w", "var_off=(0x0; 0x7fc)"}, + {31, "R4", "var_off=(0x0; 0x7fc)"}, + {31, "R5", "var_off=(0x0; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (18) * which is 20. Then the variable offset is (4n), so @@ -397,12 +397,12 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w", "pkt(r=8)"}, - {7, "R6_w", "var_off=(0x0; 0x3fc)"}, + {6, "R2", "pkt(r=8)"}, + {7, "R6", "var_off=(0x0; 0x3fc)"}, /* Adding 14 makes R6 be (4n+2) */ - {8, "R6_w", "var_off=(0x2; 0x7fc)"}, + {8, "R6", "var_off=(0x2; 0x7fc)"}, /* Packet pointer has (4n+2) offset */ - {11, "R5_w", "var_off=(0x2; 0x7fc)"}, + {11, "R5", "var_off=(0x2; 0x7fc)"}, {12, "R4", "var_off=(0x2; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) @@ -414,11 +414,11 @@ static struct bpf_align_test tests[] = { /* Newly read value in R6 was shifted left by 2, so has * known alignment of 4. */ - {17, "R6_w", "var_off=(0x0; 0x3fc)"}, + {17, "R6", "var_off=(0x0; 0x3fc)"}, /* Added (4n) to packet pointer's (4n+2) var_off, giving * another (4n+2). */ - {19, "R5_w", "var_off=(0x2; 0xffc)"}, + {19, "R5", "var_off=(0x2; 0xffc)"}, {20, "R4", "var_off=(0x2; 0xffc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) @@ -459,18 +459,18 @@ static struct bpf_align_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .matches = { - {3, "R5_w", "pkt_end()"}, + {3, "R5", "pkt_end()"}, /* (ptr - ptr) << 2 == unknown, (4n) */ - {5, "R5_w", "var_off=(0x0; 0xfffffffffffffffc)"}, + {5, "R5", "var_off=(0x0; 0xfffffffffffffffc)"}, /* (4n) + 14 == (4n+2). We blow our bounds, because * the add could overflow. */ - {6, "R5_w", "var_off=(0x2; 0xfffffffffffffffc)"}, + {6, "R5", "var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ {9, "R5", "var_off=(0x2; 0x7ffffffffffffffc)"}, /* packet pointer + nonnegative (4n+2) */ - {11, "R6_w", "var_off=(0x2; 0x7ffffffffffffffc)"}, - {12, "R4_w", "var_off=(0x2; 0x7ffffffffffffffc)"}, + {11, "R6", "var_off=(0x2; 0x7ffffffffffffffc)"}, + {12, "R4", "var_off=(0x2; 0x7ffffffffffffffc)"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -478,7 +478,7 @@ static struct bpf_align_test tests[] = { * So we did not get a 'range' on R6, and the access * attempt will fail. */ - {15, "R6_w", "var_off=(0x2; 0x7ffffffffffffffc)"}, + {15, "R6", "var_off=(0x2; 0x7ffffffffffffffc)"}, } }, { @@ -513,12 +513,12 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w", "pkt(r=8)"}, - {8, "R6_w", "var_off=(0x0; 0x3fc)"}, + {6, "R2", "pkt(r=8)"}, + {8, "R6", "var_off=(0x0; 0x3fc)"}, /* Adding 14 makes R6 be (4n+2) */ - {9, "R6_w", "var_off=(0x2; 0x7fc)"}, + {9, "R6", "var_off=(0x2; 0x7fc)"}, /* New unknown value in R7 is (4n) */ - {10, "R7_w", "var_off=(0x0; 0x3fc)"}, + {10, "R7", "var_off=(0x0; 0x3fc)"}, /* Subtracting it from R6 blows our unsigned bounds */ {11, "R6", "var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>= 0 */ @@ -566,16 +566,16 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w", "pkt(r=8)"}, - {9, "R6_w", "var_off=(0x0; 0x3c)"}, + {6, "R2", "pkt(r=8)"}, + {9, "R6", "var_off=(0x0; 0x3c)"}, /* Adding 14 makes R6 be (4n+2) */ - {10, "R6_w", "var_off=(0x2; 0x7c)"}, + {10, "R6", "var_off=(0x2; 0x7c)"}, /* Subtracting from packet pointer overflows ubounds */ - {13, "R5_w", "var_off=(0xffffffffffffff82; 0x7c)"}, + {13, "R5", "var_off=(0xffffffffffffff82; 0x7c)"}, /* New unknown value in R7 is (4n), >= 76 */ - {14, "R7_w", "var_off=(0x0; 0x7fc)"}, + {14, "R7", "var_off=(0x0; 0x7fc)"}, /* Adding it to packet pointer gives nice bounds again */ - {16, "R5_w", "var_off=(0x2; 0x7fc)"}, + {16, "R5", "var_off=(0x2; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so diff --git a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c index 0223fce4db2b..693fd86fbde6 100644 --- a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c @@ -40,8 +40,13 @@ static void *spin_lock_thread(void *arg) err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run err"); + + if (topts.retval == -EOPNOTSUPP) + goto end; + ASSERT_EQ((int)topts.retval, 0, "test_run retval"); +end: pthread_exit(arg); } @@ -63,6 +68,7 @@ static void test_arena_spin_lock_size(int size) skel = arena_spin_lock__open_and_load(); if (!ASSERT_OK_PTR(skel, "arena_spin_lock__open_and_load")) return; + if (skel->data->test_skip == 2) { test__skip(); goto end; @@ -86,6 +92,13 @@ static void test_arena_spin_lock_size(int size) goto end_barrier; } + if (skel->data->test_skip == 3) { + printf("%s:SKIP: CONFIG_NR_CPUS exceed the maximum supported by arena spinlock\n", + __func__); + test__skip(); + goto end_barrier; + } + ASSERT_EQ(skel->bss->counter, repeat * nthreads, "check counter value"); end_barrier: diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c index 13e101f370a1..92b5f378bfb8 100644 --- a/tools/testing/selftests/bpf/prog_tests/atomics.c +++ b/tools/testing/selftests/bpf/prog_tests/atomics.c @@ -165,11 +165,17 @@ static void test_xchg(struct atomics_lskel *skel) void test_atomics(void) { struct atomics_lskel *skel; + int err; - skel = atomics_lskel__open_and_load(); - if (!ASSERT_OK_PTR(skel, "atomics skeleton load")) + skel = atomics_lskel__open(); + if (!ASSERT_OK_PTR(skel, "atomics skeleton open")) return; + skel->keyring_id = KEY_SPEC_SESSION_KEYRING; + err = atomics_lskel__load(skel); + if (!ASSERT_OK(err, "atomics skeleton load")) + goto cleanup; + if (skel->data->skip_tests) { printf("%s:SKIP:no ENABLE_ATOMICS_TESTS (missing Clang BPF atomics support)", __func__); diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index cabc51c2ca6b..9e77e5da7097 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -3,6 +3,7 @@ #include "test_attach_kprobe_sleepable.skel.h" #include "test_attach_probe_manual.skel.h" #include "test_attach_probe.skel.h" +#include "kprobe_write_ctx.skel.h" /* this is how USDT semaphore is actually defined, except volatile modifier */ volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes"))); @@ -201,6 +202,31 @@ cleanup: test_attach_probe_manual__destroy(skel); } +#ifdef __x86_64__ +/* attach kprobe/kretprobe long event name testings */ +static void test_attach_kprobe_write_ctx(void) +{ + struct kprobe_write_ctx *skel = NULL; + struct bpf_link *link = NULL; + + skel = kprobe_write_ctx__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kprobe_write_ctx__open_and_load")) + return; + + link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_write_ctx, + "bpf_fentry_test1", NULL); + if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_opts")) + bpf_link__destroy(link); + + kprobe_write_ctx__destroy(skel); +} +#else +static void test_attach_kprobe_write_ctx(void) +{ + test__skip(); +} +#endif + static void test_attach_probe_auto(struct test_attach_probe *skel) { struct bpf_link *uprobe_err_link; @@ -406,6 +432,8 @@ void test_attach_probe(void) test_attach_uprobe_long_event_name(); if (test__start_subtest("kprobe-long_name")) test_attach_kprobe_long_event_name(); + if (test__start_subtest("kprobe-write-ctx")) + test_attach_kprobe_write_ctx(); cleanup: test_attach_probe__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c index 67557cda2208..42b49870e520 100644 --- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c @@ -13,7 +13,7 @@ static void test_fail_cases(void) { LIBBPF_OPTS(bpf_map_create_opts, opts); - __u32 value; + __u32 value = 0; int fd, err; /* Invalid key size */ diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 6befa870434b..75f4dff7d042 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -450,8 +450,7 @@ static void pe_subtest(struct test_bpf_cookie *skel) attr.size = sizeof(attr); attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; - attr.freq = 1; - attr.sample_freq = 10000; + attr.sample_period = 100000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (!ASSERT_GE(pfd, 0, "perf_fd")) goto cleanup; @@ -489,10 +488,28 @@ cleanup: bpf_link__destroy(link); } +static int verify_tracing_link_info(int fd, u64 cookie) +{ + struct bpf_link_info info; + int err; + u32 len = sizeof(info); + + err = bpf_link_get_info_by_fd(fd, &info, &len); + if (!ASSERT_OK(err, "get_link_info")) + return -1; + + if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_TRACING, "link_type")) + return -1; + + ASSERT_EQ(info.tracing.cookie, cookie, "tracing_cookie"); + + return 0; +} + static void tracing_subtest(struct test_bpf_cookie *skel) { __u64 cookie; - int prog_fd; + int prog_fd, err; int fentry_fd = -1, fexit_fd = -1, fmod_ret_fd = -1; LIBBPF_OPTS(bpf_test_run_opts, opts); LIBBPF_OPTS(bpf_link_create_opts, link_opts); @@ -507,6 +524,10 @@ static void tracing_subtest(struct test_bpf_cookie *skel) if (!ASSERT_GE(fentry_fd, 0, "fentry.link_create")) goto cleanup; + err = verify_tracing_link_info(fentry_fd, cookie); + if (!ASSERT_OK(err, "verify_tracing_link_info")) + goto cleanup; + cookie = 0x20000000000000L; prog_fd = bpf_program__fd(skel->progs.fexit_test1); link_opts.tracing.cookie = cookie; @@ -635,10 +656,29 @@ cleanup: bpf_link__destroy(link); } +static int verify_raw_tp_link_info(int fd, u64 cookie) +{ + struct bpf_link_info info; + int err; + u32 len = sizeof(info); + + memset(&info, 0, sizeof(info)); + err = bpf_link_get_info_by_fd(fd, &info, &len); + if (!ASSERT_OK(err, "get_link_info")) + return -1; + + if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_RAW_TRACEPOINT, "link_type")) + return -1; + + ASSERT_EQ(info.raw_tracepoint.cookie, cookie, "raw_tp_cookie"); + + return 0; +} + static void raw_tp_subtest(struct test_bpf_cookie *skel) { __u64 cookie; - int prog_fd, link_fd = -1; + int err, prog_fd, link_fd = -1; struct bpf_link *link = NULL; LIBBPF_OPTS(bpf_raw_tp_opts, raw_tp_opts); LIBBPF_OPTS(bpf_raw_tracepoint_opts, opts); @@ -656,6 +696,11 @@ static void raw_tp_subtest(struct test_bpf_cookie *skel) goto cleanup; usleep(1); /* trigger */ + + err = verify_raw_tp_link_info(link_fd, cookie); + if (!ASSERT_OK(err, "verify_raw_tp_link_info")) + goto cleanup; + close(link_fd); /* detach */ link_fd = -1; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index add4a18c33bd..5225d69bf79b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -323,7 +323,7 @@ static void test_task_pidfd(void) static void test_task_sleepable(void) { struct bpf_iter_tasks *skel; - int pid, status, err, data_pipe[2], finish_pipe[2], c; + int pid, status, err, data_pipe[2], finish_pipe[2], c = 0; char *test_data = NULL; char *test_data_long = NULL; char *data[2]; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c index fe2c502e5089..ecc3d47919ad 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c @@ -78,7 +78,7 @@ static int test_setup_uffd(void *fault_addr) } uffd_register.range.start = (unsigned long)fault_addr; - uffd_register.range.len = 4096; + uffd_register.range.len = getpagesize(); uffd_register.mode = UFFDIO_REGISTER_MODE_MISSING; if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) { close(uffd); diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index c0a776feec23..10cba526d3e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -63,7 +63,7 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t) /* tests with t->known_ptr_sz have no "long" or "unsigned long" type, * so it's impossible to determine correct pointer size; but if they - * do, it should be 8 regardless of host architecture, becaues BPF + * do, it should be 8 regardless of host architecture, because BPF * target is always 64-bit */ if (!t->known_ptr_sz) { @@ -879,6 +879,122 @@ static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d, "static int bpf_cgrp_storage_busy = (int)2", 2); } +struct btf_dump_string_ctx { + struct btf *btf; + struct btf_dump *d; + char *str; + struct btf_dump_type_data_opts *opts; + int array_id; +}; + +static int btf_dump_one_string(struct btf_dump_string_ctx *ctx, + char *ptr, size_t ptr_sz, + const char *expected_val) +{ + size_t type_sz; + int ret; + + ctx->str[0] = '\0'; + type_sz = btf__resolve_size(ctx->btf, ctx->array_id); + ret = btf_dump__dump_type_data(ctx->d, ctx->array_id, ptr, ptr_sz, ctx->opts); + if (type_sz <= ptr_sz) { + if (!ASSERT_EQ(ret, type_sz, "failed/unexpected type_sz")) + return -EINVAL; + } + if (!ASSERT_STREQ(ctx->str, expected_val, "ensure expected/actual match")) + return -EFAULT; + return 0; +} + +static void btf_dump_strings(struct btf_dump_string_ctx *ctx) +{ + struct btf_dump_type_data_opts *opts = ctx->opts; + + opts->emit_strings = true; + + opts->compact = true; + opts->emit_zeroes = false; + + opts->skip_names = false; + btf_dump_one_string(ctx, "foo", 4, "(char[4])\"foo\""); + + opts->skip_names = true; + btf_dump_one_string(ctx, "foo", 4, "\"foo\""); + + /* This should have no effect. */ + opts->emit_zeroes = false; + btf_dump_one_string(ctx, "foo", 4, "\"foo\""); + + /* This should have no effect. */ + opts->compact = false; + btf_dump_one_string(ctx, "foo", 4, "\"foo\""); + + /* Non-printable characters come out as hex. */ + btf_dump_one_string(ctx, "fo\xff", 4, "\"fo\\xff\""); + btf_dump_one_string(ctx, "fo\x7", 4, "\"fo\\x07\""); + + /* + * Strings that are too long for the specified type ("char[4]") + * should fall back to the current behavior. + */ + opts->compact = true; + btf_dump_one_string(ctx, "abcde", 6, "['a','b','c','d',]"); + + /* + * Strings that are too short for the specified type ("char[4]") + * should work normally. + */ + btf_dump_one_string(ctx, "ab", 3, "\"ab\""); + + /* Non-NUL-terminated arrays don't get printed as strings. */ + char food[4] = { 'f', 'o', 'o', 'd' }; + char bye[3] = { 'b', 'y', 'e' }; + + btf_dump_one_string(ctx, food, 4, "['f','o','o','d',]"); + btf_dump_one_string(ctx, bye, 3, "['b','y','e',]"); + + /* The embedded NUL should terminate the string. */ + char embed[4] = { 'f', 'o', '\0', 'd' }; + + btf_dump_one_string(ctx, embed, 4, "\"fo\""); +} + +static void test_btf_dump_string_data(void) +{ + struct test_ctx t = {}; + char str[STRSIZE]; + struct btf_dump *d; + DECLARE_LIBBPF_OPTS(btf_dump_type_data_opts, opts); + struct btf_dump_string_ctx ctx; + int char_id, int_id, array_id; + + if (test_ctx__init(&t)) + return; + + d = btf_dump__new(t.btf, btf_dump_snprintf, str, NULL); + if (!ASSERT_OK_PTR(d, "could not create BTF dump")) + return; + + /* Generate BTF for a four-element char array. */ + char_id = btf__add_int(t.btf, "char", 1, BTF_INT_CHAR); + ASSERT_EQ(char_id, 1, "char_id"); + int_id = btf__add_int(t.btf, "int", 4, BTF_INT_SIGNED); + ASSERT_EQ(int_id, 2, "int_id"); + array_id = btf__add_array(t.btf, int_id, char_id, 4); + ASSERT_EQ(array_id, 3, "array_id"); + + ctx.btf = t.btf; + ctx.d = d; + ctx.str = str; + ctx.opts = &opts; + ctx.array_id = array_id; + + btf_dump_strings(&ctx); + + btf_dump__free(d); + test_ctx__free(&t); +} + static void test_btf_datasec(struct btf *btf, struct btf_dump *d, char *str, const char *name, const char *expected_val, void *data, size_t data_sz) @@ -970,6 +1086,8 @@ void test_btf_dump() { test_btf_dump_struct_data(btf, d, str); if (test__start_subtest("btf_dump: var_data")) test_btf_dump_var_data(btf, d, str); + if (test__start_subtest("btf_dump: string_data")) + test_btf_dump_string_data(); btf_dump__free(d); btf__free(btf); diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c new file mode 100644 index 000000000000..bb60704a3ef9 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c @@ -0,0 +1,617 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include "cgroup_helpers.h" +#include "cgroup_mprog.skel.h" + +static void assert_mprog_count(int cg, int atype, int expected) +{ + __u32 count = 0, attach_flags = 0; + int err; + + err = bpf_prog_query(cg, atype, 0, &attach_flags, + NULL, &count); + ASSERT_EQ(count, expected, "count"); + ASSERT_EQ(err, 0, "prog_query"); +} + +static void test_prog_attach_detach(int atype) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; + struct cgroup_mprog *skel; + __u32 prog_ids[10]; + int cg, err; + + cg = test__join_cgroup("/prog_attach_detach"); + if (!ASSERT_GE(cg, 0, "join_cgroup /prog_attach_detach")) + return; + + skel = cgroup_mprog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.getsockopt_1); + fd2 = bpf_program__fd(skel->progs.getsockopt_2); + fd3 = bpf_program__fd(skel->progs.getsockopt_3); + fd4 = bpf_program__fd(skel->progs.getsockopt_4); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + id4 = id_from_prog_fd(fd4); + + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER, + .expected_revision = 1, + ); + + /* ordering: [fd1] */ + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(cg, atype, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE, + .expected_revision = 2, + ); + + /* ordering: [fd2, fd1] */ + err = bpf_prog_attach_opts(fd2, cg, atype, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup1; + + assert_mprog_count(cg, atype, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER, + .relative_fd = fd2, + .expected_revision = 3, + ); + + /* ordering: [fd2, fd3, fd1] */ + err = bpf_prog_attach_opts(fd3, cg, atype, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup2; + + assert_mprog_count(cg, atype, 3); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI, + .expected_revision = 4, + ); + + /* ordering: [fd2, fd3, fd1, fd4] */ + err = bpf_prog_attach_opts(fd4, cg, atype, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup3; + + assert_mprog_count(cg, atype, 4); + + /* retrieve optq.prog_cnt */ + err = bpf_prog_query_opts(cg, atype, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + /* optq.prog_cnt will be used in below query */ + memset(prog_ids, 0, sizeof(prog_ids)); + optq.prog_ids = prog_ids; + err = bpf_prog_query_opts(cg, atype, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id1, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(optq.link_ids, NULL, "link_ids"); + +cleanup4: + optd.expected_revision = 5; + err = bpf_prog_detach_opts(fd4, cg, atype, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(cg, atype, 3); + +cleanup3: + LIBBPF_OPTS_RESET(optd); + err = bpf_prog_detach_opts(fd3, cg, atype, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(cg, atype, 2); + + /* Check revision after two detach operations */ + err = bpf_prog_query_opts(cg, atype, &optq); + ASSERT_OK(err, "prog_query"); + ASSERT_EQ(optq.revision, 7, "revision"); + +cleanup2: + err = bpf_prog_detach_opts(fd2, cg, atype, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(cg, atype, 1); + +cleanup1: + err = bpf_prog_detach_opts(fd1, cg, atype, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(cg, atype, 0); + +cleanup: + cgroup_mprog__destroy(skel); + close(cg); +} + +static void test_link_attach_detach(int atype) +{ + LIBBPF_OPTS(bpf_cgroup_opts, opta); + LIBBPF_OPTS(bpf_cgroup_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + struct bpf_link *link1, *link2, *link3, *link4; + __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; + struct cgroup_mprog *skel; + __u32 prog_ids[10]; + int cg, err; + + cg = test__join_cgroup("/link_attach_detach"); + if (!ASSERT_GE(cg, 0, "join_cgroup /link_attach_detach")) + return; + + skel = cgroup_mprog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.getsockopt_1); + fd2 = bpf_program__fd(skel->progs.getsockopt_2); + fd3 = bpf_program__fd(skel->progs.getsockopt_3); + fd4 = bpf_program__fd(skel->progs.getsockopt_4); + + id1 = id_from_prog_fd(fd1); + id2 = id_from_prog_fd(fd2); + id3 = id_from_prog_fd(fd3); + id4 = id_from_prog_fd(fd4); + + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .expected_revision = 1, + ); + + /* ordering: [fd1] */ + link1 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_1, cg, &opta); + if (!ASSERT_OK_PTR(link1, "link_attach")) + goto cleanup; + + assert_mprog_count(cg, atype, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE | BPF_F_LINK, + .relative_id = id_from_link_fd(bpf_link__fd(link1)), + .expected_revision = 2, + ); + + /* ordering: [fd2, fd1] */ + link2 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_2, cg, &opta); + if (!ASSERT_OK_PTR(link2, "link_attach")) + goto cleanup1; + + assert_mprog_count(cg, atype, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER | BPF_F_LINK, + .relative_fd = bpf_link__fd(link2), + .expected_revision = 3, + ); + + /* ordering: [fd2, fd3, fd1] */ + link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta); + if (!ASSERT_OK_PTR(link3, "link_attach")) + goto cleanup2; + + assert_mprog_count(cg, atype, 3); + + LIBBPF_OPTS_RESET(opta, + .expected_revision = 4, + ); + + /* ordering: [fd2, fd3, fd1, fd4] */ + link4 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_4, cg, &opta); + if (!ASSERT_OK_PTR(link4, "link_attach")) + goto cleanup3; + + assert_mprog_count(cg, atype, 4); + + /* retrieve optq.prog_cnt */ + err = bpf_prog_query_opts(cg, atype, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + /* optq.prog_cnt will be used in below query */ + memset(prog_ids, 0, sizeof(prog_ids)); + optq.prog_ids = prog_ids; + err = bpf_prog_query_opts(cg, atype, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(optq.count, 4, "count"); + ASSERT_EQ(optq.revision, 5, "revision"); + ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], id1, "prog_ids[2]"); + ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]"); + ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(optq.link_ids, NULL, "link_ids"); + +cleanup4: + bpf_link__destroy(link4); + assert_mprog_count(cg, atype, 3); + +cleanup3: + bpf_link__destroy(link3); + assert_mprog_count(cg, atype, 2); + + /* Check revision after two detach operations */ + err = bpf_prog_query_opts(cg, atype, &optq); + ASSERT_OK(err, "prog_query"); + ASSERT_EQ(optq.revision, 7, "revision"); + +cleanup2: + bpf_link__destroy(link2); + assert_mprog_count(cg, atype, 1); + +cleanup1: + bpf_link__destroy(link1); + assert_mprog_count(cg, atype, 0); + +cleanup: + cgroup_mprog__destroy(skel); + close(cg); +} + +static void test_preorder_prog_attach_detach(int atype) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + __u32 fd1, fd2, fd3, fd4; + struct cgroup_mprog *skel; + int cg, err; + + cg = test__join_cgroup("/preorder_prog_attach_detach"); + if (!ASSERT_GE(cg, 0, "join_cgroup /preorder_prog_attach_detach")) + return; + + skel = cgroup_mprog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.getsockopt_1); + fd2 = bpf_program__fd(skel->progs.getsockopt_2); + fd3 = bpf_program__fd(skel->progs.getsockopt_3); + fd4 = bpf_program__fd(skel->progs.getsockopt_4); + + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI, + .expected_revision = 1, + ); + + /* ordering: [fd1] */ + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count(cg, atype, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER, + .expected_revision = 2, + ); + + /* ordering: [fd1, fd2] */ + err = bpf_prog_attach_opts(fd2, cg, atype, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup1; + + assert_mprog_count(cg, atype, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER, + .relative_fd = fd2, + .expected_revision = 3, + ); + + err = bpf_prog_attach_opts(fd3, cg, atype, &opta); + if (!ASSERT_EQ(err, -EINVAL, "prog_attach")) + goto cleanup2; + + assert_mprog_count(cg, atype, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER | BPF_F_PREORDER, + .relative_fd = fd2, + .expected_revision = 3, + ); + + /* ordering: [fd1, fd2, fd3] */ + err = bpf_prog_attach_opts(fd3, cg, atype, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup2; + + assert_mprog_count(cg, atype, 3); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI, + .expected_revision = 4, + ); + + /* ordering: [fd2, fd3, fd1, fd4] */ + err = bpf_prog_attach_opts(fd4, cg, atype, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup3; + + assert_mprog_count(cg, atype, 4); + + err = bpf_prog_detach_opts(fd4, cg, atype, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(cg, atype, 3); + +cleanup3: + err = bpf_prog_detach_opts(fd3, cg, atype, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(cg, atype, 2); + +cleanup2: + err = bpf_prog_detach_opts(fd2, cg, atype, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(cg, atype, 1); + +cleanup1: + err = bpf_prog_detach_opts(fd1, cg, atype, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count(cg, atype, 0); + +cleanup: + cgroup_mprog__destroy(skel); + close(cg); +} + +static void test_preorder_link_attach_detach(int atype) +{ + LIBBPF_OPTS(bpf_cgroup_opts, opta); + struct bpf_link *link1, *link2, *link3, *link4; + struct cgroup_mprog *skel; + __u32 fd2; + int cg; + + cg = test__join_cgroup("/preorder_link_attach_detach"); + if (!ASSERT_GE(cg, 0, "join_cgroup /preorder_link_attach_detach")) + return; + + skel = cgroup_mprog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd2 = bpf_program__fd(skel->progs.getsockopt_2); + + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .expected_revision = 1, + ); + + /* ordering: [fd1] */ + link1 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_1, cg, &opta); + if (!ASSERT_OK_PTR(link1, "link_attach")) + goto cleanup; + + assert_mprog_count(cg, atype, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_PREORDER, + .expected_revision = 2, + ); + + /* ordering: [fd1, fd2] */ + link2 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_2, cg, &opta); + if (!ASSERT_OK_PTR(link2, "link_attach")) + goto cleanup1; + + assert_mprog_count(cg, atype, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER, + .relative_fd = fd2, + .expected_revision = 3, + ); + + link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta); + if (!ASSERT_ERR_PTR(link3, "link_attach")) + goto cleanup2; + + assert_mprog_count(cg, atype, 2); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_AFTER | BPF_F_PREORDER | BPF_F_LINK, + .relative_fd = bpf_link__fd(link2), + .expected_revision = 3, + ); + + /* ordering: [fd1, fd2, fd3] */ + link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta); + if (!ASSERT_OK_PTR(link3, "link_attach")) + goto cleanup2; + + assert_mprog_count(cg, atype, 3); + + LIBBPF_OPTS_RESET(opta, + .expected_revision = 4, + ); + + /* ordering: [fd2, fd3, fd1, fd4] */ + link4 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_4, cg, &opta); + if (!ASSERT_OK_PTR(link4, "prog_attach")) + goto cleanup3; + + assert_mprog_count(cg, atype, 4); + + bpf_link__destroy(link4); + assert_mprog_count(cg, atype, 3); + +cleanup3: + bpf_link__destroy(link3); + assert_mprog_count(cg, atype, 2); + +cleanup2: + bpf_link__destroy(link2); + assert_mprog_count(cg, atype, 1); + +cleanup1: + bpf_link__destroy(link1); + assert_mprog_count(cg, atype, 0); + +cleanup: + cgroup_mprog__destroy(skel); + close(cg); +} + +static void test_invalid_attach_detach(int atype) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + __u32 fd1, fd2, id2; + struct cgroup_mprog *skel; + int cg, err; + + cg = test__join_cgroup("/invalid_attach_detach"); + if (!ASSERT_GE(cg, 0, "join_cgroup /invalid_attach_detach")) + return; + + skel = cgroup_mprog__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.getsockopt_1); + fd2 = bpf_program__fd(skel->progs.getsockopt_2); + + id2 = id_from_prog_fd(fd2); + + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER, + .relative_id = id2, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + ASSERT_EQ(err, -EINVAL, "prog_attach"); + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_ID, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + ASSERT_EQ(err, -ENOENT, "prog_attach"); + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER | BPF_F_ID, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + ASSERT_EQ(err, -ENOENT, "prog_attach"); + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER, + .relative_id = id2, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + ASSERT_EQ(err, -EINVAL, "prog_attach"); + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_LINK, + .relative_id = id2, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + ASSERT_EQ(err, -EINVAL, "prog_attach"); + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI, + .relative_id = id2, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + ASSERT_EQ(err, -EINVAL, "prog_attach"); + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE, + .relative_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + ASSERT_EQ(err, -ENOENT, "prog_attach"); + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER, + .relative_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + ASSERT_EQ(err, -ENOENT, "prog_attach"); + assert_mprog_count(cg, atype, 0); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + assert_mprog_count(cg, atype, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + ASSERT_EQ(err, -EINVAL, "prog_attach"); + assert_mprog_count(cg, atype, 1); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE | BPF_F_AFTER, + .replace_prog_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd1, cg, atype, &opta); + ASSERT_EQ(err, -EINVAL, "prog_attach"); + assert_mprog_count(cg, atype, 1); +cleanup: + cgroup_mprog__destroy(skel); + close(cg); +} + +void test_cgroup_mprog_opts(void) +{ + if (test__start_subtest("prog_attach_detach")) + test_prog_attach_detach(BPF_CGROUP_GETSOCKOPT); + if (test__start_subtest("link_attach_detach")) + test_link_attach_detach(BPF_CGROUP_GETSOCKOPT); + if (test__start_subtest("preorder_prog_attach_detach")) + test_preorder_prog_attach_detach(BPF_CGROUP_GETSOCKOPT); + if (test__start_subtest("preorder_link_attach_detach")) + test_preorder_link_attach_detach(BPF_CGROUP_GETSOCKOPT); + if (test__start_subtest("invalid_attach_detach")) + test_invalid_attach_detach(BPF_CGROUP_GETSOCKOPT); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c new file mode 100644 index 000000000000..a36d2e968bc5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include "cgroup_helpers.h" +#include "cgroup_preorder.skel.h" + +static int run_getsockopt_test(int cg_parent, int sock_fd, bool has_relative_fd) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opts); + enum bpf_attach_type prog_p_atype, prog_p2_atype; + int prog_p_fd, prog_p2_fd; + struct cgroup_preorder *skel = NULL; + struct bpf_program *prog; + __u8 *result, buf; + socklen_t optlen = 1; + int err = 0; + + skel = cgroup_preorder__open_and_load(); + if (!ASSERT_OK_PTR(skel, "cgroup_preorder__open_and_load")) + return 0; + + LIBBPF_OPTS_RESET(opts); + opts.flags = BPF_F_ALLOW_MULTI; + prog = skel->progs.parent; + prog_p_fd = bpf_program__fd(prog); + prog_p_atype = bpf_program__expected_attach_type(prog); + err = bpf_prog_attach_opts(prog_p_fd, cg_parent, prog_p_atype, &opts); + if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent")) + goto close_skel; + + opts.flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE; + if (has_relative_fd) + opts.relative_fd = prog_p_fd; + prog = skel->progs.parent_2; + prog_p2_fd = bpf_program__fd(prog); + prog_p2_atype = bpf_program__expected_attach_type(prog); + err = bpf_prog_attach_opts(prog_p2_fd, cg_parent, prog_p2_atype, &opts); + if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent_2")) + goto detach_parent; + + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (!ASSERT_OK(err, "getsockopt")) + goto detach_parent_2; + + result = skel->bss->result; + ASSERT_TRUE(result[0] == 4 && result[1] == 3, "result values"); + +detach_parent_2: + ASSERT_OK(bpf_prog_detach2(prog_p2_fd, cg_parent, prog_p2_atype), + "bpf_prog_detach2-parent_2"); +detach_parent: + ASSERT_OK(bpf_prog_detach2(prog_p_fd, cg_parent, prog_p_atype), + "bpf_prog_detach2-parent"); +close_skel: + cgroup_preorder__destroy(skel); + return err; +} + +void test_cgroup_mprog_ordering(void) +{ + int cg_parent = -1, sock_fd = -1; + + cg_parent = test__join_cgroup("/parent"); + if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent")) + goto out; + + sock_fd = socket(AF_INET, SOCK_STREAM, 0); + if (!ASSERT_GE(sock_fd, 0, "socket")) + goto out; + + ASSERT_OK(run_getsockopt_test(cg_parent, sock_fd, false), "getsockopt_test_1"); + ASSERT_OK(run_getsockopt_test(cg_parent, sock_fd, true), "getsockopt_test_2"); + +out: + close(sock_fd); + close(cg_parent); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c b/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c new file mode 100644 index 000000000000..5ad904e9d15d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <errno.h> +#include <fcntl.h> +#include <sys/stat.h> +#include <string.h> +#include <unistd.h> +#include <sys/socket.h> +#include <test_progs.h> +#include "cgroup_helpers.h" + +#include "read_cgroupfs_xattr.skel.h" +#include "cgroup_read_xattr.skel.h" + +#define CGROUP_FS_PARENT "foo/" +#define CGROUP_FS_CHILD CGROUP_FS_PARENT "bar/" +#define TMP_FILE "/tmp/selftests_cgroup_xattr" + +static const char xattr_value_a[] = "bpf_selftest_value_a"; +static const char xattr_value_b[] = "bpf_selftest_value_b"; +static const char xattr_name[] = "user.bpf_test"; + +static void test_read_cgroup_xattr(void) +{ + int tmp_fd, parent_cgroup_fd = -1, child_cgroup_fd = -1; + struct read_cgroupfs_xattr *skel = NULL; + + parent_cgroup_fd = test__join_cgroup(CGROUP_FS_PARENT); + if (!ASSERT_OK_FD(parent_cgroup_fd, "create parent cgroup")) + return; + if (!ASSERT_OK(set_cgroup_xattr(CGROUP_FS_PARENT, xattr_name, xattr_value_a), + "set parent xattr")) + goto out; + + child_cgroup_fd = test__join_cgroup(CGROUP_FS_CHILD); + if (!ASSERT_OK_FD(child_cgroup_fd, "create child cgroup")) + goto out; + if (!ASSERT_OK(set_cgroup_xattr(CGROUP_FS_CHILD, xattr_name, xattr_value_b), + "set child xattr")) + goto out; + + skel = read_cgroupfs_xattr__open_and_load(); + if (!ASSERT_OK_PTR(skel, "read_cgroupfs_xattr__open_and_load")) + goto out; + + skel->bss->target_pid = sys_gettid(); + + if (!ASSERT_OK(read_cgroupfs_xattr__attach(skel), "read_cgroupfs_xattr__attach")) + goto out; + + tmp_fd = open(TMP_FILE, O_RDONLY | O_CREAT); + ASSERT_OK_FD(tmp_fd, "open tmp file"); + close(tmp_fd); + + ASSERT_TRUE(skel->bss->found_value_a, "found_value_a"); + ASSERT_TRUE(skel->bss->found_value_b, "found_value_b"); + +out: + close(child_cgroup_fd); + close(parent_cgroup_fd); + read_cgroupfs_xattr__destroy(skel); + unlink(TMP_FILE); +} + +void test_cgroup_xattr(void) +{ + RUN_TESTS(cgroup_read_xattr); + + if (test__start_subtest("read_cgroupfs_xattr")) + test_read_cgroup_xattr(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c index adda85f97058..4b42fbc96efc 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c +++ b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c @@ -4,6 +4,8 @@ #define _GNU_SOURCE #include <cgroup_helpers.h> #include <test_progs.h> +#include <sched.h> +#include <sys/wait.h> #include "cgrp_kfunc_failure.skel.h" #include "cgrp_kfunc_success.skel.h" @@ -87,6 +89,72 @@ static const char * const success_tests[] = { "test_cgrp_from_id", }; +static void test_cgrp_from_id_ns(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + struct cgrp_kfunc_success *skel; + struct bpf_program *prog; + int pid, pipe_fd[2]; + + skel = open_load_cgrp_kfunc_skel(); + if (!ASSERT_OK_PTR(skel, "open_load_skel")) + return; + + if (!ASSERT_OK(skel->bss->err, "pre_mkdir_err")) + goto cleanup; + + prog = skel->progs.test_cgrp_from_id_ns; + + if (!ASSERT_OK(pipe(pipe_fd), "pipe")) + goto cleanup; + + pid = fork(); + if (!ASSERT_GE(pid, 0, "fork result")) { + close(pipe_fd[0]); + close(pipe_fd[1]); + goto cleanup; + } + + if (pid == 0) { + int ret = 0; + + close(pipe_fd[0]); + + if (!ASSERT_GE(cgroup_setup_and_join("cgrp_from_id_ns"), 0, "join cgroup")) + exit(1); + + if (!ASSERT_OK(unshare(CLONE_NEWCGROUP), "unshare cgns")) + exit(1); + + ret = bpf_prog_test_run_opts(bpf_program__fd(prog), &opts); + if (!ASSERT_OK(ret, "test run ret")) + exit(1); + + if (!ASSERT_OK(opts.retval, "test run retval")) + exit(1); + + if (!ASSERT_EQ(write(pipe_fd[1], &ret, sizeof(ret)), sizeof(ret), "write pipe")) + exit(1); + + exit(0); + } else { + int res; + + close(pipe_fd[1]); + + ASSERT_EQ(read(pipe_fd[0], &res, sizeof(res)), sizeof(res), "read res"); + ASSERT_EQ(waitpid(pid, NULL, 0), pid, "wait on child"); + + remove_cgroup_pid("cgrp_from_id_ns", pid); + + ASSERT_OK(res, "result from run"); + } + + close(pipe_fd[0]); +cleanup: + cgrp_kfunc_success__destroy(skel); +} + void test_cgrp_kfunc(void) { int i, err; @@ -102,6 +170,9 @@ void test_cgrp_kfunc(void) run_success_test(success_tests[i]); } + if (test__start_subtest("test_cgrp_from_id_ns")) + test_cgrp_from_id_ns(); + RUN_TESTS(cgrp_kfunc_failure); cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index 62e7ec775f24..b9f86cb91e81 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -21,9 +21,19 @@ static struct { {"test_dynptr_data", SETUP_SYSCALL_SLEEP}, {"test_dynptr_copy", SETUP_SYSCALL_SLEEP}, {"test_dynptr_copy_xdp", SETUP_XDP_PROG}, + {"test_dynptr_memset_zero", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_memset_notzero", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_memset_zero_offset", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_memset_zero_adjusted", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_memset_overflow", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_memset_overflow_offset", SETUP_SYSCALL_SLEEP}, + {"test_dynptr_memset_readonly", SETUP_SKB_PROG}, + {"test_dynptr_memset_xdp_chunks", SETUP_XDP_PROG}, {"test_ringbuf", SETUP_SYSCALL_SLEEP}, {"test_skb_readonly", SETUP_SKB_PROG}, {"test_dynptr_skb_data", SETUP_SKB_PROG}, + {"test_dynptr_skb_meta_data", SETUP_SKB_PROG}, + {"test_dynptr_skb_meta_flags", SETUP_SKB_PROG}, {"test_adjust", SETUP_SYSCALL_SLEEP}, {"test_adjust_err", SETUP_SYSCALL_SLEEP}, {"test_zero_size_dynptr", SETUP_SYSCALL_SLEEP}, @@ -43,6 +53,8 @@ static struct { {"test_copy_from_user_task_str_dynptr", SETUP_SYSCALL_SLEEP}, }; +#define PAGE_SIZE_64K 65536 + static void verify_success(const char *prog_name, enum test_setup_type setup_type) { char user_data[384] = {[0 ... 382] = 'a', '\0'}; @@ -138,14 +150,18 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ } case SETUP_XDP_PROG: { - char data[5000]; + char data[90000]; int err, prog_fd; LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = sizeof(data), .repeat = 1, ); + if (getpagesize() == PAGE_SIZE_64K) + opts.data_size_in = sizeof(data); + else + opts.data_size_in = 5000; + prog_fd = bpf_program__fd(prog); err = bpf_prog_test_run_opts(prog_fd, &opts); diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c index 9add890c2d37..c534b4d5f9da 100644 --- a/tools/testing/selftests/bpf/prog_tests/fd_array.c +++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c @@ -293,7 +293,7 @@ static int get_btf_id_by_fd(int btf_fd, __u32 *id) * 1) Create a new btf, it's referenced only by a file descriptor, so refcnt=1 * 2) Load a BPF prog with fd_array[0] = btf_fd; now btf's refcnt=2 * 3) Close the btf_fd, now refcnt=1 - * Wait and check that BTF stil exists. + * Wait and check that BTF still exists. */ static void check_fd_array_cnt__referenced_btfs(void) { @@ -312,7 +312,7 @@ static void check_fd_array_cnt__referenced_btfs(void) /* btf should still exist when original file descriptor is closed */ err = get_btf_id_by_fd(extra_fds[0], &btf_id); - if (!ASSERT_GE(err, 0, "get_btf_id_by_fd")) + if (!ASSERT_EQ(err, 0, "get_btf_id_by_fd")) goto cleanup; Close(extra_fds[0]); diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 130f5b82d2e6..5ef1804e44df 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -12,13 +12,24 @@ void test_fentry_fexit(void) int err, prog_fd, i; LIBBPF_OPTS(bpf_test_run_opts, topts); - fentry_skel = fentry_test_lskel__open_and_load(); + fentry_skel = fentry_test_lskel__open(); if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) goto close_prog; - fexit_skel = fexit_test_lskel__open_and_load(); + + fentry_skel->keyring_id = KEY_SPEC_SESSION_KEYRING; + err = fentry_test_lskel__load(fentry_skel); + if (!ASSERT_OK(err, "fentry_skel_load")) + goto close_prog; + + fexit_skel = fexit_test_lskel__open(); if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) goto close_prog; + fexit_skel->keyring_id = KEY_SPEC_SESSION_KEYRING; + err = fexit_test_lskel__load(fexit_skel); + if (!ASSERT_OK(err, "fexit_skel_load")) + goto close_prog; + err = fentry_test_lskel__attach(fentry_skel); if (!ASSERT_OK(err, "fentry_attach")) goto close_prog; diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index aee1bc77a17f..ec882328eb59 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -43,8 +43,13 @@ static void fentry_test(void) struct fentry_test_lskel *fentry_skel = NULL; int err; - fentry_skel = fentry_test_lskel__open_and_load(); - if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) + fentry_skel = fentry_test_lskel__open(); + if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_open")) + goto cleanup; + + fentry_skel->keyring_id = KEY_SPEC_SESSION_KEYRING; + err = fentry_test_lskel__load(fentry_skel); + if (!ASSERT_OK(err, "fentry_skel_load")) goto cleanup; err = fentry_test_common(fentry_skel); diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c b/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c deleted file mode 100644 index 568d3aa48a78..000000000000 --- a/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c +++ /dev/null @@ -1,9 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <test_progs.h> -#include "fexit_noreturns.skel.h" - -void test_fexit_noreturns(void) -{ - RUN_TESTS(fexit_noreturns); -} diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index 1c13007e37dd..94eed753560c 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -43,8 +43,13 @@ static void fexit_test(void) struct fexit_test_lskel *fexit_skel = NULL; int err; - fexit_skel = fexit_test_lskel__open_and_load(); - if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) + fexit_skel = fexit_test_lskel__open(); + if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_open")) + goto cleanup; + + fexit_skel->keyring_id = KEY_SPEC_SESSION_KEYRING; + err = fexit_test_lskel__load(fexit_skel); + if (!ASSERT_OK(err, "fexit_skel_load")) goto cleanup; err = fexit_test_common(fexit_skel); diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c index b7b77a6b2979..0de8facca4c5 100644 --- a/tools/testing/selftests/bpf/prog_tests/free_timer.c +++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c @@ -124,6 +124,10 @@ void test_free_timer(void) int err; skel = free_timer__open_and_load(); + if (!skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(skel, "open_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/kernel_flag.c b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c index a133354ac9bc..97b00c7efe94 100644 --- a/tools/testing/selftests/bpf/prog_tests/kernel_flag.c +++ b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c @@ -16,7 +16,7 @@ void test_kernel_flag(void) if (!ASSERT_OK_PTR(lsm_skel, "lsm_skel")) return; - lsm_skel->bss->monitored_tid = gettid(); + lsm_skel->bss->monitored_tid = sys_gettid(); ret = test_kernel_flag__attach(lsm_skel); if (!ASSERT_OK(ret, "test_kernel_flag__attach")) diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index e19ef509ebf8..6cfaa978bc9a 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -7,6 +7,7 @@ #include "kprobe_multi_session.skel.h" #include "kprobe_multi_session_cookie.skel.h" #include "kprobe_multi_verifier.skel.h" +#include "kprobe_write_ctx.skel.h" #include "bpf/libbpf_internal.h" #include "bpf/hashmap.h" @@ -422,220 +423,6 @@ static void test_unique_match(void) kprobe_multi__destroy(skel); } -static size_t symbol_hash(long key, void *ctx __maybe_unused) -{ - return str_hash((const char *) key); -} - -static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused) -{ - return strcmp((const char *) key1, (const char *) key2) == 0; -} - -static bool is_invalid_entry(char *buf, bool kernel) -{ - if (kernel && strchr(buf, '[')) - return true; - if (!kernel && !strchr(buf, '[')) - return true; - return false; -} - -static bool skip_entry(char *name) -{ - /* - * We attach to almost all kernel functions and some of them - * will cause 'suspicious RCU usage' when fprobe is attached - * to them. Filter out the current culprits - arch_cpu_idle - * default_idle and rcu_* functions. - */ - if (!strcmp(name, "arch_cpu_idle")) - return true; - if (!strcmp(name, "default_idle")) - return true; - if (!strncmp(name, "rcu_", 4)) - return true; - if (!strcmp(name, "bpf_dispatcher_xdp_func")) - return true; - if (!strncmp(name, "__ftrace_invalid_address__", - sizeof("__ftrace_invalid_address__") - 1)) - return true; - return false; -} - -/* Do comparision by ignoring '.llvm.<hash>' suffixes. */ -static int compare_name(const char *name1, const char *name2) -{ - const char *res1, *res2; - int len1, len2; - - res1 = strstr(name1, ".llvm."); - res2 = strstr(name2, ".llvm."); - len1 = res1 ? res1 - name1 : strlen(name1); - len2 = res2 ? res2 - name2 : strlen(name2); - - if (len1 == len2) - return strncmp(name1, name2, len1); - if (len1 < len2) - return strncmp(name1, name2, len1) <= 0 ? -1 : 1; - return strncmp(name1, name2, len2) >= 0 ? 1 : -1; -} - -static int load_kallsyms_compare(const void *p1, const void *p2) -{ - return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name); -} - -static int search_kallsyms_compare(const void *p1, const struct ksym *p2) -{ - return compare_name(p1, p2->name); -} - -static int get_syms(char ***symsp, size_t *cntp, bool kernel) -{ - size_t cap = 0, cnt = 0; - char *name = NULL, *ksym_name, **syms = NULL; - struct hashmap *map; - struct ksyms *ksyms; - struct ksym *ks; - char buf[256]; - FILE *f; - int err = 0; - - ksyms = load_kallsyms_custom_local(load_kallsyms_compare); - if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_custom_local")) - return -EINVAL; - - /* - * The available_filter_functions contains many duplicates, - * but other than that all symbols are usable in kprobe multi - * interface. - * Filtering out duplicates by using hashmap__add, which won't - * add existing entry. - */ - - if (access("/sys/kernel/tracing/trace", F_OK) == 0) - f = fopen("/sys/kernel/tracing/available_filter_functions", "r"); - else - f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r"); - - if (!f) - return -EINVAL; - - map = hashmap__new(symbol_hash, symbol_equal, NULL); - if (IS_ERR(map)) { - err = libbpf_get_error(map); - goto error; - } - - while (fgets(buf, sizeof(buf), f)) { - if (is_invalid_entry(buf, kernel)) - continue; - - free(name); - if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1) - continue; - if (skip_entry(name)) - continue; - - ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare); - if (!ks) { - err = -EINVAL; - goto error; - } - - ksym_name = ks->name; - err = hashmap__add(map, ksym_name, 0); - if (err == -EEXIST) { - err = 0; - continue; - } - if (err) - goto error; - - err = libbpf_ensure_mem((void **) &syms, &cap, - sizeof(*syms), cnt + 1); - if (err) - goto error; - - syms[cnt++] = ksym_name; - } - - *symsp = syms; - *cntp = cnt; - -error: - free(name); - fclose(f); - hashmap__free(map); - if (err) - free(syms); - return err; -} - -static int get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel) -{ - unsigned long *addr, *addrs, *tmp_addrs; - int err = 0, max_cnt, inc_cnt; - char *name = NULL; - size_t cnt = 0; - char buf[256]; - FILE *f; - - if (access("/sys/kernel/tracing/trace", F_OK) == 0) - f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r"); - else - f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r"); - - if (!f) - return -ENOENT; - - /* In my local setup, the number of entries is 50k+ so Let us initially - * allocate space to hold 64k entries. If 64k is not enough, incrementally - * increase 1k each time. - */ - max_cnt = 65536; - inc_cnt = 1024; - addrs = malloc(max_cnt * sizeof(long)); - if (addrs == NULL) { - err = -ENOMEM; - goto error; - } - - while (fgets(buf, sizeof(buf), f)) { - if (is_invalid_entry(buf, kernel)) - continue; - - free(name); - if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2) - continue; - if (skip_entry(name)) - continue; - - if (cnt == max_cnt) { - max_cnt += inc_cnt; - tmp_addrs = realloc(addrs, max_cnt); - if (!tmp_addrs) { - err = -ENOMEM; - goto error; - } - addrs = tmp_addrs; - } - - addrs[cnt++] = (unsigned long)addr; - } - - *addrsp = addrs; - *cntp = cnt; - -error: - free(name); - fclose(f); - if (err) - free(addrs); - return err; -} - static void do_bench_test(struct kprobe_multi_empty *skel, struct bpf_kprobe_multi_opts *opts) { long attach_start_ns, attach_end_ns; @@ -670,7 +457,7 @@ static void test_kprobe_multi_bench_attach(bool kernel) char **syms = NULL; size_t cnt = 0; - if (!ASSERT_OK(get_syms(&syms, &cnt, kernel), "get_syms")) + if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms")) return; skel = kprobe_multi_empty__open_and_load(); @@ -696,13 +483,13 @@ static void test_kprobe_multi_bench_attach_addr(bool kernel) size_t cnt = 0; int err; - err = get_addrs(&addrs, &cnt, kernel); + err = bpf_get_addrs(&addrs, &cnt, kernel); if (err == -ENOENT) { test__skip(); return; } - if (!ASSERT_OK(err, "get_addrs")) + if (!ASSERT_OK(err, "bpf_get_addrs")) return; skel = kprobe_multi_empty__open_and_load(); @@ -753,6 +540,30 @@ cleanup: kprobe_multi_override__destroy(skel); } +#ifdef __x86_64__ +static void test_attach_write_ctx(void) +{ + struct kprobe_write_ctx *skel = NULL; + struct bpf_link *link = NULL; + + skel = kprobe_write_ctx__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kprobe_write_ctx__open_and_load")) + return; + + link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_multi_write_ctx, + "bpf_fentry_test1", NULL); + if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_opts")) + bpf_link__destroy(link); + + kprobe_write_ctx__destroy(skel); +} +#else +static void test_attach_write_ctx(void) +{ + test__skip(); +} +#endif + void serial_test_kprobe_multi_bench_attach(void) { if (test__start_subtest("kernel")) @@ -792,5 +603,7 @@ void test_kprobe_multi_test(void) test_session_cookie_skel_api(); if (test__start_subtest("unique_match")) test_unique_match(); + if (test__start_subtest("attach_write_ctx")) + test_attach_write_ctx(); RUN_TESTS(kprobe_multi_verifier); } diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c index 5266c7022863..14c5a7ef0e87 100644 --- a/tools/testing/selftests/bpf/prog_tests/linked_list.c +++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c @@ -72,7 +72,7 @@ static struct { { "new_null_ret", "R0 invalid mem access 'ptr_or_null_'" }, { "obj_new_acq", "Unreleased reference id=" }, { "use_after_drop", "invalid mem access 'scalar'" }, - { "ptr_walk_scalar", "type=scalar expected=percpu_ptr_" }, + { "ptr_walk_scalar", "type=rdonly_untrusted_mem expected=percpu_ptr_" }, { "direct_read_lock", "direct access to bpf_spin_lock is disallowed" }, { "direct_write_lock", "direct access to bpf_spin_lock is disallowed" }, { "direct_read_head", "direct access to bpf_list_head is disallowed" }, diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c index 169ce689b97c..d6f14a232002 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_buf.c +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -7,6 +7,10 @@ #include "test_log_buf.skel.h" #include "bpf_util.h" +#if !defined(__clang__) +#pragma GCC diagnostic ignored "-Wmaybe-uninitialized" +#endif + static size_t libbpf_log_pos; static char libbpf_log_buf[1024 * 1024]; static bool libbpf_log_error; diff --git a/tools/testing/selftests/bpf/prog_tests/map_excl.c b/tools/testing/selftests/bpf/prog_tests/map_excl.c new file mode 100644 index 000000000000..6bdc6d6de0da --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_excl.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025 Google LLC. */ +#define _GNU_SOURCE +#include <unistd.h> +#include <sys/syscall.h> +#include <test_progs.h> +#include <bpf/btf.h> + +#include "map_excl.skel.h" + +static void test_map_excl_allowed(void) +{ + struct map_excl *skel = map_excl__open(); + int err; + + err = bpf_map__set_exclusive_program(skel->maps.excl_map, skel->progs.should_have_access); + if (!ASSERT_OK(err, "bpf_map__set_exclusive_program")) + goto out; + + bpf_program__set_autoload(skel->progs.should_have_access, true); + bpf_program__set_autoload(skel->progs.should_not_have_access, false); + + err = map_excl__load(skel); + ASSERT_OK(err, "map_excl__load"); +out: + map_excl__destroy(skel); +} + +static void test_map_excl_denied(void) +{ + struct map_excl *skel = map_excl__open(); + int err; + + err = bpf_map__set_exclusive_program(skel->maps.excl_map, skel->progs.should_have_access); + if (!ASSERT_OK(err, "bpf_map__make_exclusive")) + goto out; + + bpf_program__set_autoload(skel->progs.should_have_access, false); + bpf_program__set_autoload(skel->progs.should_not_have_access, true); + + err = map_excl__load(skel); + ASSERT_EQ(err, -EACCES, "exclusive map access not denied\n"); +out: + map_excl__destroy(skel); + +} + +void test_map_excl(void) +{ + if (test__start_subtest("map_excl_allowed")) + test_map_excl_allowed(); + if (test__start_subtest("map_excl_denied")) + test_map_excl_denied(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c b/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c new file mode 100644 index 000000000000..40d4f687bd9c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <test_progs.h> +#include "mem_rdonly_untrusted.skel.h" + +void test_mem_rdonly_untrusted(void) +{ + RUN_TESTS(mem_rdonly_untrusted); +} diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c index 6d391d95f96e..70fa7ae93173 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c @@ -90,7 +90,7 @@ void test_module_attach(void) test_module_attach__detach(skel); - /* attach fentry/fexit and make sure it get's module reference */ + /* attach fentry/fexit and make sure it gets module reference */ link = bpf_program__attach(skel->progs.handle_fentry); if (!ASSERT_OK_PTR(link, "attach_fentry")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c b/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c new file mode 100644 index 000000000000..9ae49b587f3e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <test_progs.h> + + +#include "test_pinning_devmap.skel.h" + +void test_pinning_devmap_reuse(void) +{ + const char *pinpath1 = "/sys/fs/bpf/pinmap1"; + const char *pinpath2 = "/sys/fs/bpf/pinmap2"; + struct test_pinning_devmap *skel1 = NULL, *skel2 = NULL; + int err; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + + /* load the object a first time */ + skel1 = test_pinning_devmap__open_and_load(); + if (!ASSERT_OK_PTR(skel1, "skel_load1")) + goto out; + + /* load the object a second time, re-using the pinned map */ + skel2 = test_pinning_devmap__open_and_load(); + if (!ASSERT_OK_PTR(skel2, "skel_load2")) + goto out; + + /* we can close the reference safely without + * the map's refcount falling to 0 + */ + test_pinning_devmap__destroy(skel1); + skel1 = NULL; + + /* now, swap the pins */ + err = renameat2(0, pinpath1, 0, pinpath2, RENAME_EXCHANGE); + if (!ASSERT_OK(err, "swap pins")) + goto out; + + /* load the object again, this time the re-use should fail */ + skel1 = test_pinning_devmap__open_and_load(); + if (!ASSERT_ERR_PTR(skel1, "skel_load3")) + goto out; + +out: + unlink(pinpath1); + unlink(pinpath2); + test_pinning_devmap__destroy(skel1); + test_pinning_devmap__destroy(skel2); +} diff --git a/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c b/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c index 14f2796076e0..7607cfc2408c 100644 --- a/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c +++ b/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c @@ -54,3 +54,128 @@ void test_prog_tests_framework(void) return; clear_test_state(state); } + +static void dummy_emit(const char *buf, bool force) {} + +void test_prog_tests_framework_expected_msgs(void) +{ + struct expected_msgs msgs; + int i, j, error_cnt; + const struct { + const char *name; + const char *log; + const char *expected; + struct expect_msg *pats; + } cases[] = { + { + .name = "simple-ok", + .log = "aaabbbccc", + .pats = (struct expect_msg[]) { + { .substr = "aaa" }, + { .substr = "ccc" }, + {} + } + }, + { + .name = "simple-fail", + .log = "aaabbbddd", + .expected = "MATCHED SUBSTR: 'aaa'\n" + "EXPECTED SUBSTR: 'ccc'\n", + .pats = (struct expect_msg[]) { + { .substr = "aaa" }, + { .substr = "ccc" }, + {} + } + }, + { + .name = "negative-ok-mid", + .log = "aaabbbccc", + .pats = (struct expect_msg[]) { + { .substr = "aaa" }, + { .substr = "foo", .negative = true }, + { .substr = "bar", .negative = true }, + { .substr = "ccc" }, + {} + } + }, + { + .name = "negative-ok-tail", + .log = "aaabbbccc", + .pats = (struct expect_msg[]) { + { .substr = "aaa" }, + { .substr = "foo", .negative = true }, + {} + } + }, + { + .name = "negative-ok-head", + .log = "aaabbbccc", + .pats = (struct expect_msg[]) { + { .substr = "foo", .negative = true }, + { .substr = "ccc" }, + {} + } + }, + { + .name = "negative-fail-head", + .log = "aaabbbccc", + .expected = "UNEXPECTED SUBSTR: 'aaa'\n", + .pats = (struct expect_msg[]) { + { .substr = "aaa", .negative = true }, + { .substr = "bbb" }, + {} + } + }, + { + .name = "negative-fail-tail", + .log = "aaabbbccc", + .expected = "UNEXPECTED SUBSTR: 'ccc'\n", + .pats = (struct expect_msg[]) { + { .substr = "bbb" }, + { .substr = "ccc", .negative = true }, + {} + } + }, + { + .name = "negative-fail-mid-1", + .log = "aaabbbccc", + .expected = "UNEXPECTED SUBSTR: 'bbb'\n", + .pats = (struct expect_msg[]) { + { .substr = "aaa" }, + { .substr = "bbb", .negative = true }, + { .substr = "ccc" }, + {} + } + }, + { + .name = "negative-fail-mid-2", + .log = "aaabbb222ccc", + .expected = "UNEXPECTED SUBSTR: '222'\n", + .pats = (struct expect_msg[]) { + { .substr = "aaa" }, + { .substr = "222", .negative = true }, + { .substr = "bbb", .negative = true }, + { .substr = "ccc" }, + {} + } + } + }; + + for (i = 0; i < ARRAY_SIZE(cases); i++) { + if (test__start_subtest(cases[i].name)) { + error_cnt = env.subtest_state->error_cnt; + msgs.patterns = cases[i].pats; + msgs.cnt = 0; + for (j = 0; cases[i].pats[j].substr; j++) + msgs.cnt++; + validate_msgs(cases[i].log, &msgs, dummy_emit); + fflush(stderr); + env.subtest_state->error_cnt = error_cnt; + if (cases[i].expected) + ASSERT_HAS_SUBSTR(env.subtest_state->log_buf, cases[i].expected, "expected output"); + else + ASSERT_STREQ(env.subtest_state->log_buf, "", "expected no output"); + test__end_subtest(); + } + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c index 39d42271cc46..d93a0c7b1786 100644 --- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c +++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c @@ -465,6 +465,20 @@ static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, return range_improve(x_t, x, x_swap); } + if (!t_is_32(x_t) && !t_is_32(y_t) && x_t != y_t) { + if (x_t == S64 && x.a > x.b) { + if (x.b < y.a && x.a <= y.b) + return range(x_t, x.a, y.b); + if (x.a > y.b && x.b >= y.a) + return range(x_t, y.a, x.b); + } else if (x_t == U64 && y.a > y.b) { + if (y.b < x.a && y.a <= x.b) + return range(x_t, y.a, x.b); + if (y.a > x.b && y.b >= x.a) + return range(x_t, x.a, y.b); + } + } + /* otherwise, plain range cast and intersection works */ return range_improve(x_t, x, y_cast); } @@ -609,7 +623,7 @@ static void range_cond(enum num_t t, struct range x, struct range y, *newx = range(t, x.a, x.b); *newy = range(t, y.a + 1, y.b); } else if (x.a == x.b && x.b == y.b) { - /* X is a constant matching rigth side of Y */ + /* X is a constant matching right side of Y */ *newx = range(t, x.a, x.b); *newy = range(t, y.a, y.b - 1); } else if (y.a == y.b && x.a == y.a) { @@ -617,7 +631,7 @@ static void range_cond(enum num_t t, struct range x, struct range y, *newx = range(t, x.a + 1, x.b); *newy = range(t, y.a, y.b); } else if (y.a == y.b && x.b == y.b) { - /* Y is a constant matching rigth side of X */ + /* Y is a constant matching right side of X */ *newx = range(t, x.a, x.b - 1); *newy = range(t, y.a, y.b); } else { diff --git a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c index 0703e987df89..8c6c2043a432 100644 --- a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c @@ -99,3 +99,19 @@ end: res_spin_lock__destroy(skel); return; } + +void serial_test_res_spin_lock_stress(void) +{ + if (libbpf_num_possible_cpus() < 3) { + test__skip(); + return; + } + + ASSERT_OK(load_module("bpf_test_rqspinlock.ko", false), "load module AA"); + sleep(5); + unload_module("bpf_test_rqspinlock", false); + + ASSERT_OK(load_module_params("bpf_test_rqspinlock.ko", "test_ab=1", false), "load module ABBA"); + sleep(5); + unload_module("bpf_test_rqspinlock", false); +} diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index da430df45aa4..d1e4cb28a72c 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -97,7 +97,7 @@ static void ringbuf_write_subtest(void) if (!ASSERT_OK_PTR(skel, "skel_open")) return; - skel->maps.ringbuf.max_entries = 0x4000; + skel->maps.ringbuf.max_entries = 0x40000; err = test_ringbuf_write_lskel__load(skel); if (!ASSERT_OK(err, "skel_load")) @@ -108,7 +108,7 @@ static void ringbuf_write_subtest(void) mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0); if (!ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos")) goto cleanup; - *mmap_ptr = 0x3000; + *mmap_ptr = 0x30000; ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw"); skel->bss->pid = getpid(); diff --git a/tools/testing/selftests/bpf/prog_tests/sha256.c b/tools/testing/selftests/bpf/prog_tests/sha256.c new file mode 100644 index 000000000000..604a0b1423d5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sha256.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright 2025 Google LLC */ + +#include <test_progs.h> +#include "bpf/libbpf_internal.h" + +#define MAX_LEN 4096 + +/* Test libbpf_sha256() for all lengths from 0 to MAX_LEN inclusively. */ +void test_sha256(void) +{ + /* + * The correctness of this value was verified by running this test with + * libbpf_sha256() replaced by OpenSSL's SHA256(). + */ + static const __u8 expected_digest_of_digests[SHA256_DIGEST_LENGTH] = { + 0x62, 0x30, 0x0e, 0x1d, 0xea, 0x7f, 0xc4, 0x74, + 0xfd, 0x8e, 0x64, 0x0b, 0xd8, 0x5f, 0xea, 0x04, + 0xf3, 0xef, 0x77, 0x42, 0xc2, 0x01, 0xb8, 0x90, + 0x6e, 0x19, 0x91, 0x1b, 0xca, 0xb3, 0x28, 0x42, + }; + __u64 seed = 0; + __u8 *data = NULL, *digests = NULL; + __u8 digest_of_digests[SHA256_DIGEST_LENGTH]; + size_t i; + + data = malloc(MAX_LEN); + if (!ASSERT_OK_PTR(data, "malloc")) + goto out; + digests = malloc((MAX_LEN + 1) * SHA256_DIGEST_LENGTH); + if (!ASSERT_OK_PTR(digests, "malloc")) + goto out; + + /* Generate MAX_LEN bytes of "random" data deterministically. */ + for (i = 0; i < MAX_LEN; i++) { + seed = (seed * 25214903917 + 11) & ((1ULL << 48) - 1); + data[i] = (__u8)(seed >> 16); + } + + /* Calculate a digest for each length 0 through MAX_LEN inclusively. */ + for (i = 0; i <= MAX_LEN; i++) + libbpf_sha256(data, i, &digests[i * SHA256_DIGEST_LENGTH]); + + /* Calculate and verify the digest of all the digests. */ + libbpf_sha256(digests, (MAX_LEN + 1) * SHA256_DIGEST_LENGTH, + digest_of_digests); + ASSERT_MEMEQ(digest_of_digests, expected_digest_of_digests, + SHA256_DIGEST_LENGTH, "digest_of_digests"); +out: + free(data); + free(digests); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c index a4517bee34d5..27781df8f2fb 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c @@ -1,11 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2024 Meta +#include <poll.h> #include <test_progs.h> #include "network_helpers.h" #include "sock_iter_batch.skel.h" #define TEST_NS "sock_iter_batch_netns" +#define TEST_CHILD_NS "sock_iter_batch_child_netns" static const int init_batch_size = 16; static const int nr_soreuse = 4; @@ -118,6 +120,45 @@ done: return nth_sock_idx; } +static void destroy(int fd) +{ + struct sock_iter_batch *skel = NULL; + __u64 cookie = socket_cookie(fd); + struct bpf_link *link = NULL; + int iter_fd = -1; + int nread; + __u64 out; + + skel = sock_iter_batch__open(); + if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open")) + goto done; + + skel->rodata->destroy_cookie = cookie; + + if (!ASSERT_OK(sock_iter_batch__load(skel), "sock_iter_batch__load")) + goto done; + + link = bpf_program__attach_iter(skel->progs.iter_tcp_destroy, NULL); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter")) + goto done; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create")) + goto done; + + /* Delete matching socket. */ + nread = read(iter_fd, &out, sizeof(out)); + ASSERT_GE(nread, 0, "nread"); + if (nread) + ASSERT_EQ(out, cookie, "cookie matches"); +done: + if (iter_fd >= 0) + close(iter_fd); + bpf_link__destroy(link); + sock_iter_batch__destroy(skel); + close(fd); +} + static int get_seen_count(int fd, struct sock_count counts[], int n) { __u64 cookie = socket_cookie(fd); @@ -152,8 +193,71 @@ static void check_n_were_seen_once(int *fds, int fds_len, int n, ASSERT_EQ(seen_once, n, "seen_once"); } +static int accept_from_one(struct pollfd *server_poll_fds, + int server_poll_fds_len) +{ + static const int poll_timeout_ms = 5000; /* 5s */ + int ret; + int i; + + ret = poll(server_poll_fds, server_poll_fds_len, poll_timeout_ms); + if (!ASSERT_EQ(ret, 1, "poll")) + return -1; + + for (i = 0; i < server_poll_fds_len; i++) + if (server_poll_fds[i].revents & POLLIN) + return accept(server_poll_fds[i].fd, NULL, NULL); + + return -1; +} + +static int *connect_to_server(int family, int sock_type, const char *addr, + __u16 port, int nr_connects, int *server_fds, + int server_fds_len) +{ + struct pollfd *server_poll_fds = NULL; + int *established_socks = NULL; + int i; + + server_poll_fds = calloc(server_fds_len, sizeof(*server_poll_fds)); + if (!ASSERT_OK_PTR(server_poll_fds, "server_poll_fds")) + return NULL; + + for (i = 0; i < server_fds_len; i++) { + server_poll_fds[i].fd = server_fds[i]; + server_poll_fds[i].events = POLLIN; + } + + i = 0; + + established_socks = malloc(sizeof(*established_socks) * nr_connects*2); + if (!ASSERT_OK_PTR(established_socks, "established_socks")) + goto error; + + while (nr_connects--) { + established_socks[i] = connect_to_addr_str(family, sock_type, + addr, port, NULL); + if (!ASSERT_OK_FD(established_socks[i], "connect_to_addr_str")) + goto error; + i++; + established_socks[i] = accept_from_one(server_poll_fds, + server_fds_len); + if (!ASSERT_OK_FD(established_socks[i], "accept_from_one")) + goto error; + i++; + } + + free(server_poll_fds); + return established_socks; +error: + free_fds(established_socks, i); + free(server_poll_fds); + return NULL; +} + static void remove_seen(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { int close_idx; @@ -182,8 +286,46 @@ static void remove_seen(int family, int sock_type, const char *addr, __u16 port, counts_len); } +static void remove_seen_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int close_idx; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Leave one established socket. */ + read_n(iter_fd, established_socks_len - 1, counts, counts_len); + + /* Close a socket we've already seen to remove it from the bucket. */ + close_idx = get_nth_socket(established_socks, established_socks_len, + link, listen_socks_len + 1); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + destroy(established_socks[close_idx]); + established_socks[close_idx] = -1; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure the last socket wasn't skipped and that there were no + * repeats. + */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); +} + static void remove_unseen(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -214,8 +356,54 @@ static void remove_unseen(int family, int sock_type, const char *addr, counts_len); } +static void remove_unseen_established(int family, int sock_type, + const char *addr, __u16 port, + int *listen_socks, int listen_socks_len, + int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int close_idx; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established socket. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Make sure we saw one established socks. */ + check_n_were_seen_once(established_socks, established_socks_len, 1, + counts, counts_len); + + /* Close what would be the next socket in the bucket to exercise the + * condition where we need to skip past the first cookie we remembered. + */ + close_idx = get_nth_socket(established_socks, established_socks_len, + link, listen_socks_len + 1); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + + destroy(established_socks[close_idx]); + established_socks[close_idx] = -1; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure the remaining sockets were seen exactly once and that we + * didn't repeat the socket that was already seen. + */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); +} + static void remove_all(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -242,8 +430,57 @@ static void remove_all(int family, int sock_type, const char *addr, ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n"); } +static void remove_all_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int *close_idx = NULL; + int i; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established socket. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Make sure we saw one established socks. */ + check_n_were_seen_once(established_socks, established_socks_len, 1, + counts, counts_len); + + /* Close all remaining sockets to exhaust the list of saved cookies and + * exit without putting any sockets into the batch on the next read. + */ + close_idx = malloc(sizeof(int) * (established_socks_len - 1)); + if (!ASSERT_OK_PTR(close_idx, "close_idx malloc")) + return; + for (i = 0; i < established_socks_len - 1; i++) { + close_idx[i] = get_nth_socket(established_socks, + established_socks_len, link, + listen_socks_len + i); + if (!ASSERT_GE(close_idx[i], 0, "close_idx")) + return; + } + + for (i = 0; i < established_socks_len - 1; i++) { + destroy(established_socks[close_idx[i]]); + established_socks[close_idx[i]] = -1; + } + + /* Make sure there are no more sockets returned */ + ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n"); + free(close_idx); +} + static void add_some(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { int *new_socks = NULL; @@ -271,8 +508,52 @@ done: free_fds(new_socks, socks_len); } +static void add_some_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, + int counts_len, struct bpf_link *link, + int iter_fd) +{ + int *new_socks = NULL; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established_socks_len - 1 sockets. */ + read_n(iter_fd, established_socks_len - 1, counts, counts_len); + + /* Make sure we saw established_socks_len - 1 sockets exactly once. */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); + + /* Double the number of established sockets in the bucket. */ + new_socks = connect_to_server(family, sock_type, addr, port, + established_socks_len / 2, listen_socks, + listen_socks_len); + if (!ASSERT_OK_PTR(new_socks, "connect_to_server")) + goto done; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure each of the original sockets was seen exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len, counts, counts_len); +done: + free_fds(new_socks, established_socks_len); +} + static void force_realloc(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -299,11 +580,32 @@ done: free_fds(new_socks, socks_len); } +static void force_realloc_established(int family, int sock_type, + const char *addr, __u16 port, + int *listen_socks, int listen_socks_len, + int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + /* Iterate through all sockets to trigger a realloc. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure each socket was seen exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len, counts, counts_len); +} + struct test_case { void (*test)(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd); const char *description; + int ehash_buckets; + int connections; int init_socks; int max_socks; int sock_type; @@ -358,18 +660,140 @@ static struct test_case resume_tests[] = { .family = AF_INET6, .test = force_realloc, }, + { + .description = "tcp: resume after removing a seen socket (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_seen, + }, + { + .description = "tcp: resume after removing one unseen socket (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_unseen, + }, + { + .description = "tcp: resume after removing all unseen sockets (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_all, + }, + { + .description = "tcp: resume after adding a few sockets (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + /* Use AF_INET so that new sockets are added to the head of the + * bucket's list. + */ + .family = AF_INET, + .test = add_some, + }, + { + .description = "tcp: force a realloc to occur (listening)", + .init_socks = init_batch_size, + .max_socks = init_batch_size * 2, + .sock_type = SOCK_STREAM, + /* Use AF_INET6 so that new sockets are added to the tail of the + * bucket's list, needing to be added to the next batch to force + * a realloc. + */ + .family = AF_INET6, + .test = force_realloc, + }, + { + .description = "tcp: resume after removing a seen socket (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_seen_established, + }, + { + .description = "tcp: resume after removing one unseen socket (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_unseen_established, + }, + { + .description = "tcp: resume after removing all unseen sockets (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_all_established, + }, + { + .description = "tcp: resume after adding a few sockets (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = add_some_established, + }, + { + .description = "tcp: force a realloc to occur (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + /* Bucket size will need to double when going from listening to + * established sockets. + */ + .connections = init_batch_size, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse + (init_batch_size * 2), + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = force_realloc_established, + }, }; static void do_resume_test(struct test_case *tc) { struct sock_iter_batch *skel = NULL; + struct sock_count *counts = NULL; static const __u16 port = 10001; + struct nstoken *nstoken = NULL; struct bpf_link *link = NULL; - struct sock_count *counts; + int *established_fds = NULL; int err, iter_fd = -1; const char *addr; int *fds = NULL; - int local_port; + + if (tc->ehash_buckets) { + SYS_NOFAIL("ip netns del " TEST_CHILD_NS); + SYS(done, "sysctl -wq net.ipv4.tcp_child_ehash_entries=%d", + tc->ehash_buckets); + SYS(done, "ip netns add %s", TEST_CHILD_NS); + SYS(done, "ip -net %s link set dev lo up", TEST_CHILD_NS); + nstoken = open_netns(TEST_CHILD_NS); + if (!ASSERT_OK_PTR(nstoken, "open_child_netns")) + goto done; + } counts = calloc(tc->max_socks, sizeof(*counts)); if (!ASSERT_OK_PTR(counts, "counts")) @@ -384,11 +808,18 @@ static void do_resume_test(struct test_case *tc) tc->init_socks); if (!ASSERT_OK_PTR(fds, "start_reuseport_server")) goto done; - local_port = get_socket_local_port(*fds); - if (!ASSERT_GE(local_port, 0, "get_socket_local_port")) - goto done; - skel->rodata->ports[0] = ntohs(local_port); + if (tc->connections) { + established_fds = connect_to_server(tc->family, tc->sock_type, + addr, port, + tc->connections, fds, + tc->init_socks); + if (!ASSERT_OK_PTR(established_fds, "connect_to_server")) + goto done; + } + skel->rodata->ports[0] = 0; + skel->rodata->ports[1] = 0; skel->rodata->sf = tc->family; + skel->rodata->ss = 0; err = sock_iter_batch__load(skel); if (!ASSERT_OK(err, "sock_iter_batch__load")) @@ -406,10 +837,15 @@ static void do_resume_test(struct test_case *tc) goto done; tc->test(tc->family, tc->sock_type, addr, port, fds, tc->init_socks, - counts, tc->max_socks, link, iter_fd); + established_fds, tc->connections*2, counts, tc->max_socks, + link, iter_fd); done: + close_netns(nstoken); + SYS_NOFAIL("ip netns del " TEST_CHILD_NS); + SYS_NOFAIL("sysctl -w net.ipv4.tcp_child_ehash_entries=0"); free(counts); free_fds(fds, tc->init_socks); + free_fds(established_fds, tc->connections*2); if (iter_fd >= 0) close(iter_fd); bpf_link__destroy(link); @@ -454,6 +890,8 @@ static void do_test(int sock_type, bool onebyone) skel->rodata->ports[i] = ntohs(local_port); } skel->rodata->sf = AF_INET6; + if (sock_type == SOCK_STREAM) + skel->rodata->ss = TCP_LISTEN; err = sock_iter_batch__load(skel); if (!ASSERT_OK(err, "sock_iter_batch__load")) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index b6c471da5c28..b87e7f39e15a 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -314,6 +314,95 @@ out: test_sockmap_ktls__destroy(skel); } +static void test_sockmap_ktls_tx_pop(int family, int sotype) +{ + char msg[37] = "0123456789abcdefghijklmnopqrstuvwxyz\0"; + int c = 0, p = 0, one = 1, sent, recvd; + struct test_sockmap_ktls *skel; + int prog_fd, map_fd; + char rcv[50] = {0}; + int err; + int i, m, r; + + skel = test_sockmap_ktls__open_and_load(); + if (!ASSERT_TRUE(skel, "open ktls skel")) + return; + + err = create_pair(family, sotype, &c, &p); + if (!ASSERT_OK(err, "create_pair()")) + goto out; + + prog_fd = bpf_program__fd(skel->progs.prog_sk_policy); + map_fd = bpf_map__fd(skel->maps.sock_map); + + err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_MSG_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach sk msg")) + goto out; + + err = bpf_map_update_elem(map_fd, &one, &c, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(c)")) + goto out; + + err = init_ktls_pairs(c, p); + if (!ASSERT_OK(err, "init_ktls_pairs(c, p)")) + goto out; + + struct { + int pop_start; + int pop_len; + } pop_policy[] = { + /* trim the start */ + {0, 2}, + {0, 10}, + {1, 2}, + {1, 10}, + /* trim the end */ + {35, 2}, + /* New entries should be added before this line */ + {-1, -1}, + }; + + i = 0; + while (pop_policy[i].pop_start >= 0) { + skel->bss->pop_start = pop_policy[i].pop_start; + skel->bss->pop_end = pop_policy[i].pop_len; + + sent = send(c, msg, sizeof(msg), 0); + if (!ASSERT_EQ(sent, sizeof(msg), "send(msg)")) + goto out; + + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1); + if (!ASSERT_EQ(recvd, sizeof(msg) - pop_policy[i].pop_len, "pop len mismatch")) + goto out; + + /* verify the data + * msg: 0123456789a bcdefghij klmnopqrstuvwxyz + * | | + * popped data + */ + for (m = 0, r = 0; m < sizeof(msg);) { + /* skip checking the data that has been popped */ + if (m >= pop_policy[i].pop_start && + m <= pop_policy[i].pop_start + pop_policy[i].pop_len - 1) { + m++; + continue; + } + + if (!ASSERT_EQ(msg[m], rcv[r], "data mismatch")) + goto out; + m++; + r++; + } + i++; + } +out: + if (c) + close(c); + if (p) + close(p); + test_sockmap_ktls__destroy(skel); +} + static void run_tests(int family, enum bpf_map_type map_type) { int map; @@ -338,6 +427,8 @@ static void run_ktls_test(int family, int sotype) test_sockmap_ktls_tx_cork(family, sotype, true); if (test__start_subtest("tls tx egress with no buf")) test_sockmap_ktls_tx_no_buf(family, sotype, true); + if (test__start_subtest("tls tx with pop")) + test_sockmap_ktls_tx_pop(family, sotype); } void test_sockmap_ktls(void) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 1d98eee7a2c3..f1bdccc7e4e7 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -924,6 +924,8 @@ static void redir_partial(int family, int sotype, int sock_map, int parser_map) goto close; n = xsend(c1, buf, sizeof(buf), 0); + if (n == -1) + goto close; if (n < sizeof(buf)) FAIL("incomplete write"); diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c index e3ea5dc2f697..254fbfeab06a 100644 --- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c @@ -13,22 +13,22 @@ static struct { const char *err_msg; } spin_lock_fail_tests[] = { { "lock_id_kptr_preserve", - "5: (bf) r1 = r0 ; R0_w=ptr_foo(id=2,ref_obj_id=2) " - "R1_w=ptr_foo(id=2,ref_obj_id=2) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n" + "5: (bf) r1 = r0 ; R0=ptr_foo(id=2,ref_obj_id=2) " + "R1=ptr_foo(id=2,ref_obj_id=2) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n" "R1 type=ptr_ expected=percpu_ptr_" }, { "lock_id_global_zero", - "; R1_w=map_value(map=.data.A,ks=4,vs=4)\n2: (85) call bpf_this_cpu_ptr#154\n" + "; R1=map_value(map=.data.A,ks=4,vs=4)\n2: (85) call bpf_this_cpu_ptr#154\n" "R1 type=map_value expected=percpu_ptr_" }, { "lock_id_mapval_preserve", "[0-9]\\+: (bf) r1 = r0 ;" - " R0_w=map_value(id=1,map=array_map,ks=4,vs=8)" - " R1_w=map_value(id=1,map=array_map,ks=4,vs=8)\n" + " R0=map_value(id=1,map=array_map,ks=4,vs=8)" + " R1=map_value(id=1,map=array_map,ks=4,vs=8)\n" "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n" "R1 type=map_value expected=percpu_ptr_" }, { "lock_id_innermapval_preserve", "[0-9]\\+: (bf) r1 = r0 ;" " R0=map_value(id=2,ks=4,vs=8)" - " R1_w=map_value(id=2,ks=4,vs=8)\n" + " R1=map_value(id=2,ks=4,vs=8)\n" "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n" "R1 type=map_value expected=percpu_ptr_" }, { "lock_id_mismatch_kptr_kptr", "bpf_spin_unlock of different lock" }, diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c index b7ba5cd47d96..271b5cc9fc01 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c @@ -39,7 +39,7 @@ retry: bpf_map_update_elem(control_map_fd, &key, &val, 0); /* for every element in stackid_hmap, we can find a corresponding one - * in stackmap, and vise versa. + * in stackmap, and vice versa. */ err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c index 0832fd787457..b277dddd5af7 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c @@ -66,7 +66,7 @@ retry: bpf_map_update_elem(control_map_fd, &key, &val, 0); /* for every element in stackid_hmap, we can find a corresponding one - * in stackmap, and vise versa. + * in stackmap, and vice versa. */ err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c index df59e4ae2951..c23b97414813 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c @@ -1,46 +1,27 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include "stacktrace_map.skel.h" void test_stacktrace_map(void) { + struct stacktrace_map *skel; int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; - const char *prog_name = "oncpu"; - int err, prog_fd, stack_trace_len; - const char *file = "./test_stacktrace_map.bpf.o"; - __u32 key, val, duration = 0; - struct bpf_program *prog; - struct bpf_object *obj; - struct bpf_link *link; + int err, stack_trace_len; + __u32 key, val, stack_id, duration = 0; + __u64 stack[PERF_MAX_STACK_DEPTH]; - err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); - if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno)) + skel = stacktrace_map__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) return; - prog = bpf_object__find_program_by_name(obj, prog_name); - if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name)) - goto close_prog; - - link = bpf_program__attach_tracepoint(prog, "sched", "sched_switch"); - if (!ASSERT_OK_PTR(link, "attach_tp")) - goto close_prog; - - /* find map fds */ - control_map_fd = bpf_find_map(__func__, obj, "control_map"); - if (CHECK_FAIL(control_map_fd < 0)) - goto disable_pmu; - - stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap"); - if (CHECK_FAIL(stackid_hmap_fd < 0)) - goto disable_pmu; - - stackmap_fd = bpf_find_map(__func__, obj, "stackmap"); - if (CHECK_FAIL(stackmap_fd < 0)) - goto disable_pmu; - - stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); - if (CHECK_FAIL(stack_amap_fd < 0)) - goto disable_pmu; + control_map_fd = bpf_map__fd(skel->maps.control_map); + stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap); + stackmap_fd = bpf_map__fd(skel->maps.stackmap); + stack_amap_fd = bpf_map__fd(skel->maps.stack_amap); + err = stacktrace_map__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto out; /* give some time for bpf program run */ sleep(1); @@ -50,26 +31,32 @@ void test_stacktrace_map(void) bpf_map_update_elem(control_map_fd, &key, &val, 0); /* for every element in stackid_hmap, we can find a corresponding one - * in stackmap, and vise versa. + * in stackmap, and vice versa. */ err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto out; err = compare_map_keys(stackmap_fd, stackid_hmap_fd); if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap", "err %d errno %d\n", err, errno)) - goto disable_pmu; + goto out; stack_trace_len = PERF_MAX_STACK_DEPTH * sizeof(__u64); err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); if (CHECK(err, "compare_stack_ips stackmap vs. stack_amap", "err %d errno %d\n", err, errno)) - goto disable_pmu; - -disable_pmu: - bpf_link__destroy(link); -close_prog: - bpf_object__close(obj); + goto out; + + stack_id = skel->bss->stack_id; + err = bpf_map_lookup_and_delete_elem(stackmap_fd, &stack_id, stack); + if (!ASSERT_OK(err, "lookup and delete target stack_id")) + goto out; + + err = bpf_map_lookup_elem(stackmap_fd, &stack_id, stack); + if (!ASSERT_EQ(err, -ENOENT, "lookup deleted stack_id")) + goto out; +out: + stacktrace_map__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c index c6ef06f55cdb..e985d51d3d47 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c @@ -5,7 +5,7 @@ void test_stacktrace_map_raw_tp(void) { const char *prog_name = "oncpu"; int control_map_fd, stackid_hmap_fd, stackmap_fd; - const char *file = "./test_stacktrace_map.bpf.o"; + const char *file = "./stacktrace_map.bpf.o"; __u32 key, val, duration = 0; int err, prog_fd; struct bpf_program *prog; @@ -46,7 +46,7 @@ void test_stacktrace_map_raw_tp(void) bpf_map_update_elem(control_map_fd, &key, &val, 0); /* for every element in stackid_hmap, we can find a corresponding one - * in stackmap, and vise versa. + * in stackmap, and vice versa. */ err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap", diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c index 1932b1e0685c..dc2ccf6a14d1 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c @@ -40,7 +40,7 @@ void test_stacktrace_map_skip(void) skel->bss->control = 1; /* for every element in stackid_hmap, we can find a corresponding one - * in stackmap, and vise versa. + * in stackmap, and vice versa. */ err = compare_map_keys(stackid_hmap_fd, stackmap_fd); if (!ASSERT_OK(err, "compare_map_keys stackid_hmap vs. stackmap")) diff --git a/tools/testing/selftests/bpf/prog_tests/stream.c b/tools/testing/selftests/bpf/prog_tests/stream.c new file mode 100644 index 000000000000..c3cce5c292bd --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/stream.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include <sys/mman.h> + +#include "stream.skel.h" +#include "stream_fail.skel.h" + +void test_stream_failure(void) +{ + RUN_TESTS(stream_fail); +} + +void test_stream_success(void) +{ + RUN_TESTS(stream); + return; +} + +void test_stream_syscall(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts); + struct stream *skel; + int ret, prog_fd; + char buf[64]; + + skel = stream__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stream__open_and_load")) + return; + + prog_fd = bpf_program__fd(skel->progs.stream_syscall); + ret = bpf_prog_test_run_opts(prog_fd, &opts); + ASSERT_OK(ret, "ret"); + ASSERT_OK(opts.retval, "retval"); + + ASSERT_LT(bpf_prog_stream_read(0, BPF_STREAM_STDOUT, buf, sizeof(buf), &ropts), 0, "error"); + ret = -errno; + ASSERT_EQ(ret, -EINVAL, "bad prog_fd"); + + ASSERT_LT(bpf_prog_stream_read(prog_fd, 0, buf, sizeof(buf), &ropts), 0, "error"); + ret = -errno; + ASSERT_EQ(ret, -ENOENT, "bad stream id"); + + ASSERT_LT(bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, NULL, sizeof(buf), NULL), 0, "error"); + ret = -errno; + ASSERT_EQ(ret, -EFAULT, "bad stream buf"); + + ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, buf, 2, NULL); + ASSERT_EQ(ret, 2, "bytes"); + ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, buf, 2, NULL); + ASSERT_EQ(ret, 1, "bytes"); + ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, buf, 1, &ropts); + ASSERT_EQ(ret, 0, "no bytes stdout"); + ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDERR, buf, 1, &ropts); + ASSERT_EQ(ret, 0, "no bytes stderr"); + + stream__destroy(skel); +} + +static void test_address(struct bpf_program *prog, unsigned long *fault_addr_p) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts); + int ret, prog_fd; + char fault_addr[64]; + char buf[1024]; + + prog_fd = bpf_program__fd(prog); + + ret = bpf_prog_test_run_opts(prog_fd, &opts); + ASSERT_OK(ret, "ret"); + ASSERT_OK(opts.retval, "retval"); + + sprintf(fault_addr, "0x%lx", *fault_addr_p); + + ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDERR, buf, sizeof(buf), &ropts); + ASSERT_GT(ret, 0, "stream read"); + ASSERT_LE(ret, 1023, "len for buf"); + buf[ret] = '\0'; + + if (!ASSERT_HAS_SUBSTR(buf, fault_addr, "fault_addr")) { + fprintf(stderr, "Output from stream:\n%s\n", buf); + fprintf(stderr, "Fault Addr: %s\n", fault_addr); + } +} + +void test_stream_arena_fault_address(void) +{ + struct stream *skel; + +#if !defined(__x86_64__) && !defined(__aarch64__) + printf("%s:SKIP: arena fault reporting not supported\n", __func__); + test__skip(); + return; +#endif + + skel = stream__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stream__open_and_load")) + return; + + if (test__start_subtest("read_fault")) + test_address(skel->progs.stream_arena_read_fault, &skel->bss->fault_addr); + if (test__start_subtest("write_fault")) + test_address(skel->progs.stream_arena_write_fault, &skel->bss->fault_addr); + + stream__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c new file mode 100644 index 000000000000..4d66fad3c8bd --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025 Red Hat, Inc.*/ +#include <test_progs.h> +#include "string_kfuncs_success.skel.h" +#include "string_kfuncs_failure1.skel.h" +#include "string_kfuncs_failure2.skel.h" +#include <sys/mman.h> + +static const char * const test_cases[] = { + "strcmp", + "strcasecmp", + "strchr", + "strchrnul", + "strnchr", + "strrchr", + "strlen", + "strnlen", + "strspn_str", + "strspn_accept", + "strcspn_str", + "strcspn_reject", + "strstr", + "strnstr", +}; + +void run_too_long_tests(void) +{ + struct string_kfuncs_failure2 *skel; + struct bpf_program *prog; + char test_name[256]; + int err, i; + + skel = string_kfuncs_failure2__open_and_load(); + if (!ASSERT_OK_PTR(skel, "string_kfuncs_failure2__open_and_load")) + return; + + memset(skel->bss->long_str, 'a', sizeof(skel->bss->long_str)); + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + sprintf(test_name, "test_%s_too_long", test_cases[i]); + if (!test__start_subtest(test_name)) + continue; + + prog = bpf_object__find_program_by_name(skel->obj, test_name); + if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) + goto cleanup; + + LIBBPF_OPTS(bpf_test_run_opts, topts); + err = bpf_prog_test_run_opts(bpf_program__fd(prog), &topts); + if (!ASSERT_OK(err, "bpf_prog_test_run")) + goto cleanup; + + ASSERT_EQ(topts.retval, -E2BIG, "reading too long string fails with -E2BIG"); + } + +cleanup: + string_kfuncs_failure2__destroy(skel); +} + +void test_string_kfuncs(void) +{ + RUN_TESTS(string_kfuncs_success); + RUN_TESTS(string_kfuncs_failure1); + + run_too_long_tests(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index 66a900327f91..0ab36503c3b2 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -1195,7 +1195,7 @@ static void test_tailcall_hierarchy_count(const char *which, bool test_fentry, bool test_fexit, bool test_fentry_entry) { - int err, map_fd, prog_fd, main_data_fd, fentry_data_fd, fexit_data_fd, i, val; + int err, map_fd, prog_fd, main_data_fd, fentry_data_fd = 0, fexit_data_fd = 0, i, val; struct bpf_object *obj = NULL, *fentry_obj = NULL, *fexit_obj = NULL; struct bpf_link *fentry_link = NULL, *fexit_link = NULL; struct bpf_program *prog, *fentry_prog; diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_data.h b/tools/testing/selftests/bpf/prog_tests/task_local_data.h new file mode 100644 index 000000000000..2de38776a2d4 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/task_local_data.h @@ -0,0 +1,386 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __TASK_LOCAL_DATA_H +#define __TASK_LOCAL_DATA_H + +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <stdatomic.h> +#include <stddef.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/syscall.h> +#include <sys/types.h> + +#ifdef TLD_FREE_DATA_ON_THREAD_EXIT +#include <pthread.h> +#endif + +#include <bpf/bpf.h> + +/* + * OPTIONS + * + * Define the option before including the header + * + * TLD_FREE_DATA_ON_THREAD_EXIT - Frees memory on thread exit automatically + * + * Thread-specific memory for storing TLD is allocated lazily on the first call to + * tld_get_data(). The thread that calls it must also call tld_free() on thread exit + * to prevent memory leak. Pthread will be included if the option is defined. A pthread + * key will be registered with a destructor that calls tld_free(). + * + * + * TLD_DYN_DATA_SIZE - The maximum size of memory allocated for TLDs created dynamically + * (default: 64 bytes) + * + * A TLD can be defined statically using TLD_DEFINE_KEY() or created on the fly using + * tld_create_key(). As the total size of TLDs created with tld_create_key() cannot be + * possibly known statically, a memory area of size TLD_DYN_DATA_SIZE will be allocated + * for these TLDs. This additional memory is allocated for every thread that calls + * tld_get_data() even if no tld_create_key are actually called, so be mindful of + * potential memory wastage. Use TLD_DEFINE_KEY() whenever possible as just enough memory + * will be allocated for TLDs created with it. + * + * + * TLD_NAME_LEN - The maximum length of the name of a TLD (default: 62) + * + * Setting TLD_NAME_LEN will affect the maximum number of TLDs a process can store, + * TLD_MAX_DATA_CNT. + * + * + * TLD_DATA_USE_ALIGNED_ALLOC - Always use aligned_alloc() instead of malloc() + * + * When allocating the memory for storing TLDs, we need to make sure there is a memory + * region of the X bytes within a page. This is due to the limit posed by UPTR: memory + * pinned to the kernel cannot exceed a page nor can it cross the page boundary. The + * library normally calls malloc(2*X) given X bytes of total TLDs, and only uses + * aligned_alloc(PAGE_SIZE, X) when X >= PAGE_SIZE / 2. This is to reduce memory wastage + * as not all memory allocator can use the exact amount of memory requested to fulfill + * aligned_alloc(). For example, some may round the size up to the alignment. Enable the + * option to always use aligned_alloc() if the implementation has low memory overhead. + */ + +#define TLD_PAGE_SIZE getpagesize() +#define TLD_PAGE_MASK (~(TLD_PAGE_SIZE - 1)) + +#define TLD_ROUND_MASK(x, y) ((__typeof__(x))((y) - 1)) +#define TLD_ROUND_UP(x, y) ((((x) - 1) | TLD_ROUND_MASK(x, y)) + 1) + +#define TLD_READ_ONCE(x) (*(volatile typeof(x) *)&(x)) + +#ifndef TLD_DYN_DATA_SIZE +#define TLD_DYN_DATA_SIZE 64 +#endif + +#define TLD_MAX_DATA_CNT (TLD_PAGE_SIZE / sizeof(struct tld_metadata) - 1) + +#ifndef TLD_NAME_LEN +#define TLD_NAME_LEN 62 +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +typedef struct { + __s16 off; +} tld_key_t; + +struct tld_metadata { + char name[TLD_NAME_LEN]; + _Atomic __u16 size; +}; + +struct tld_meta_u { + _Atomic __u8 cnt; + __u16 size; + struct tld_metadata metadata[]; +}; + +struct tld_data_u { + __u64 start; /* offset of tld_data_u->data in a page */ + char data[]; +}; + +struct tld_map_value { + void *data; + struct tld_meta_u *meta; +}; + +struct tld_meta_u * _Atomic tld_meta_p __attribute__((weak)); +__thread struct tld_data_u *tld_data_p __attribute__((weak)); +__thread void *tld_data_alloc_p __attribute__((weak)); + +#ifdef TLD_FREE_DATA_ON_THREAD_EXIT +pthread_key_t tld_pthread_key __attribute__((weak)); + +static void tld_free(void); + +static void __tld_thread_exit_handler(void *unused) +{ + tld_free(); +} +#endif + +static int __tld_init_meta_p(void) +{ + struct tld_meta_u *meta, *uninit = NULL; + int err = 0; + + meta = (struct tld_meta_u *)aligned_alloc(TLD_PAGE_SIZE, TLD_PAGE_SIZE); + if (!meta) { + err = -ENOMEM; + goto out; + } + + memset(meta, 0, TLD_PAGE_SIZE); + meta->size = TLD_DYN_DATA_SIZE; + + if (!atomic_compare_exchange_strong(&tld_meta_p, &uninit, meta)) { + free(meta); + goto out; + } + +#ifdef TLD_FREE_DATA_ON_THREAD_EXIT + pthread_key_create(&tld_pthread_key, __tld_thread_exit_handler); +#endif +out: + return err; +} + +static int __tld_init_data_p(int map_fd) +{ + bool use_aligned_alloc = false; + struct tld_map_value map_val; + struct tld_data_u *data; + void *data_alloc = NULL; + int err, tid_fd = -1; + + tid_fd = syscall(SYS_pidfd_open, sys_gettid(), O_EXCL); + if (tid_fd < 0) { + err = -errno; + goto out; + } + +#ifdef TLD_DATA_USE_ALIGNED_ALLOC + use_aligned_alloc = true; +#endif + + /* + * tld_meta_p->size = TLD_DYN_DATA_SIZE + + * total size of TLDs defined via TLD_DEFINE_KEY() + */ + data_alloc = (use_aligned_alloc || tld_meta_p->size * 2 >= TLD_PAGE_SIZE) ? + aligned_alloc(TLD_PAGE_SIZE, tld_meta_p->size) : + malloc(tld_meta_p->size * 2); + if (!data_alloc) { + err = -ENOMEM; + goto out; + } + + /* + * Always pass a page-aligned address to UPTR since the size of tld_map_value::data + * is a page in BTF. If data_alloc spans across two pages, use the page that contains large + * enough memory. + */ + if (TLD_PAGE_SIZE - (~TLD_PAGE_MASK & (intptr_t)data_alloc) >= tld_meta_p->size) { + map_val.data = (void *)(TLD_PAGE_MASK & (intptr_t)data_alloc); + data = data_alloc; + data->start = (~TLD_PAGE_MASK & (intptr_t)data_alloc) + + offsetof(struct tld_data_u, data); + } else { + map_val.data = (void *)(TLD_ROUND_UP((intptr_t)data_alloc, TLD_PAGE_SIZE)); + data = (void *)(TLD_ROUND_UP((intptr_t)data_alloc, TLD_PAGE_SIZE)); + data->start = offsetof(struct tld_data_u, data); + } + map_val.meta = TLD_READ_ONCE(tld_meta_p); + + err = bpf_map_update_elem(map_fd, &tid_fd, &map_val, 0); + if (err) { + free(data_alloc); + goto out; + } + + tld_data_p = data; + tld_data_alloc_p = data_alloc; +#ifdef TLD_FREE_DATA_ON_THREAD_EXIT + pthread_setspecific(tld_pthread_key, (void *)1); +#endif +out: + if (tid_fd >= 0) + close(tid_fd); + return err; +} + +static tld_key_t __tld_create_key(const char *name, size_t size, bool dyn_data) +{ + int err, i, sz, off = 0; + __u8 cnt; + + if (!TLD_READ_ONCE(tld_meta_p)) { + err = __tld_init_meta_p(); + if (err) + return (tld_key_t){err}; + } + + for (i = 0; i < TLD_MAX_DATA_CNT; i++) { +retry: + cnt = atomic_load(&tld_meta_p->cnt); + if (i < cnt) { + /* A metadata is not ready until size is updated with a non-zero value */ + while (!(sz = atomic_load(&tld_meta_p->metadata[i].size))) + sched_yield(); + + if (!strncmp(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN)) + return (tld_key_t){-EEXIST}; + + off += TLD_ROUND_UP(sz, 8); + continue; + } + + /* + * TLD_DEFINE_KEY() is given memory upto a page while at most + * TLD_DYN_DATA_SIZE is allocated for tld_create_key() + */ + if (dyn_data) { + if (off + TLD_ROUND_UP(size, 8) > tld_meta_p->size) + return (tld_key_t){-E2BIG}; + } else { + if (off + TLD_ROUND_UP(size, 8) > TLD_PAGE_SIZE - sizeof(struct tld_data_u)) + return (tld_key_t){-E2BIG}; + tld_meta_p->size += TLD_ROUND_UP(size, 8); + } + + /* + * Only one tld_create_key() can increase the current cnt by one and + * takes the latest available slot. Other threads will check again if a new + * TLD can still be added, and then compete for the new slot after the + * succeeding thread update the size. + */ + if (!atomic_compare_exchange_strong(&tld_meta_p->cnt, &cnt, cnt + 1)) + goto retry; + + strncpy(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN); + atomic_store(&tld_meta_p->metadata[i].size, size); + return (tld_key_t){(__s16)off}; + } + + return (tld_key_t){-ENOSPC}; +} + +/** + * TLD_DEFINE_KEY() - Define a TLD and a global variable key associated with the TLD. + * + * @name: The name of the TLD + * @size: The size of the TLD + * @key: The variable name of the key. Cannot exceed TLD_NAME_LEN + * + * The macro can only be used in file scope. + * + * A global variable key of opaque type, tld_key_t, will be declared and initialized before + * main() starts. Use tld_key_is_err() or tld_key_err_or_zero() later to check if the key + * creation succeeded. Pass the key to tld_get_data() to get a pointer to the TLD. + * bpf programs can also fetch the same key by name. + * + * The total size of TLDs created using TLD_DEFINE_KEY() cannot exceed a page. Just + * enough memory will be allocated for each thread on the first call to tld_get_data(). + */ +#define TLD_DEFINE_KEY(key, name, size) \ +tld_key_t key; \ + \ +__attribute__((constructor)) \ +void __tld_define_key_##key(void) \ +{ \ + key = __tld_create_key(name, size, false); \ +} + +/** + * tld_create_key() - Create a TLD and return a key associated with the TLD. + * + * @name: The name the TLD + * @size: The size of the TLD + * + * Return an opaque object key. Use tld_key_is_err() or tld_key_err_or_zero() to check + * if the key creation succeeded. Pass the key to tld_get_data() to get a pointer to + * locate the TLD. bpf programs can also fetch the same key by name. + * + * Use tld_create_key() only when a TLD needs to be created dynamically (e.g., @name is + * not known statically or a TLD needs to be created conditionally) + * + * An additional TLD_DYN_DATA_SIZE bytes are allocated per-thread to accommodate TLDs + * created dynamically with tld_create_key(). Since only a user page is pinned to the + * kernel, when TLDs created with TLD_DEFINE_KEY() uses more than TLD_PAGE_SIZE - + * TLD_DYN_DATA_SIZE, the buffer size will be limited to the rest of the page. + */ +__attribute__((unused)) +static tld_key_t tld_create_key(const char *name, size_t size) +{ + return __tld_create_key(name, size, true); +} + +__attribute__((unused)) +static inline bool tld_key_is_err(tld_key_t key) +{ + return key.off < 0; +} + +__attribute__((unused)) +static inline int tld_key_err_or_zero(tld_key_t key) +{ + return tld_key_is_err(key) ? key.off : 0; +} + +/** + * tld_get_data() - Get a pointer to the TLD associated with the given key of the + * calling thread. + * + * @map_fd: A file descriptor of tld_data_map, the underlying BPF task local storage map + * of task local data. + * @key: A key object created by TLD_DEFINE_KEY() or tld_create_key(). + * + * Return a pointer to the TLD if the key is valid; NULL if not enough memory for TLD + * for this thread, or the key is invalid. The returned pointer is guaranteed to be 8-byte + * aligned. + * + * Threads that call tld_get_data() must call tld_free() on exit to prevent + * memory leak if TLD_FREE_DATA_ON_THREAD_EXIT is not defined. + */ +__attribute__((unused)) +static void *tld_get_data(int map_fd, tld_key_t key) +{ + if (!TLD_READ_ONCE(tld_meta_p)) + return NULL; + + /* tld_data_p is allocated on the first invocation of tld_get_data() */ + if (!tld_data_p && __tld_init_data_p(map_fd)) + return NULL; + + return tld_data_p->data + key.off; +} + +/** + * tld_free() - Free task local data memory of the calling thread + * + * For the calling thread, all pointers to TLDs acquired before will become invalid. + * + * Users must call tld_free() on thread exit to prevent memory leak. Alternatively, + * define TLD_FREE_DATA_ON_THREAD_EXIT and a thread exit handler will be registered + * to free the memory automatically. + */ +__attribute__((unused)) +static void tld_free(void) +{ + if (tld_data_alloc_p) { + free(tld_data_alloc_p); + tld_data_alloc_p = NULL; + tld_data_p = NULL; + } +} + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* __TASK_LOCAL_DATA_H */ diff --git a/tools/testing/selftests/bpf/prog_tests/task_work_stress.c b/tools/testing/selftests/bpf/prog_tests/task_work_stress.c new file mode 100644 index 000000000000..450d17d91a56 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/task_work_stress.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include <string.h> +#include <stdio.h> +#include "task_work_stress.skel.h" +#include <linux/bpf.h> +#include <linux/perf_event.h> +#include <sys/syscall.h> +#include <time.h> +#include <stdlib.h> +#include <stdatomic.h> + +struct test_data { + int prog_fd; + atomic_int exit; +}; + +void *runner(void *test_data) +{ + struct test_data *td = test_data; + int err = 0; + LIBBPF_OPTS(bpf_test_run_opts, opts); + + while (!err && !atomic_load(&td->exit)) + err = bpf_prog_test_run_opts(td->prog_fd, &opts); + + return NULL; +} + +static int get_env_int(const char *str, int def) +{ + const char *s = getenv(str); + char *end; + int retval; + + if (!s || !*s) + return def; + errno = 0; + retval = strtol(s, &end, 10); + if (errno || *end || retval < 0) + return def; + return retval; +} + +static void task_work_run(bool enable_delete) +{ + struct task_work_stress *skel; + struct bpf_program *scheduler, *deleter; + int nthreads = 16; + int test_time_s = get_env_int("BPF_TASK_WORK_TEST_TIME", 1); + pthread_t tid[nthreads], tid_del; + bool started[nthreads], started_del = false; + struct test_data td_sched = { .exit = 0 }, td_del = { .exit = 1 }; + int i, err; + + skel = task_work_stress__open(); + if (!ASSERT_OK_PTR(skel, "task_work__open")) + return; + + scheduler = bpf_object__find_program_by_name(skel->obj, "schedule_task_work"); + bpf_program__set_autoload(scheduler, true); + + deleter = bpf_object__find_program_by_name(skel->obj, "delete_task_work"); + bpf_program__set_autoload(deleter, true); + + err = task_work_stress__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + for (i = 0; i < nthreads; ++i) + started[i] = false; + + td_sched.prog_fd = bpf_program__fd(scheduler); + for (i = 0; i < nthreads; ++i) { + if (pthread_create(&tid[i], NULL, runner, &td_sched) != 0) { + fprintf(stderr, "could not start thread"); + goto cancel; + } + started[i] = true; + } + + if (enable_delete) + atomic_store(&td_del.exit, 0); + + td_del.prog_fd = bpf_program__fd(deleter); + if (pthread_create(&tid_del, NULL, runner, &td_del) != 0) { + fprintf(stderr, "could not start thread"); + goto cancel; + } + started_del = true; + + /* Run stress test for some time */ + sleep(test_time_s); + +cancel: + atomic_store(&td_sched.exit, 1); + atomic_store(&td_del.exit, 1); + for (i = 0; i < nthreads; ++i) { + if (started[i]) + pthread_join(tid[i], NULL); + } + + if (started_del) + pthread_join(tid_del, NULL); + + ASSERT_GT(skel->bss->callback_scheduled, 0, "work scheduled"); + /* Some scheduling attempts should have failed due to contention */ + ASSERT_GT(skel->bss->schedule_error, 0, "schedule error"); + + if (enable_delete) { + /* If delete thread is enabled, it has cancelled some callbacks */ + ASSERT_GT(skel->bss->delete_success, 0, "delete success"); + ASSERT_LT(skel->bss->callback_success, skel->bss->callback_scheduled, "callbacks"); + } else { + /* Without delete thread number of scheduled callbacks is the same as fired */ + ASSERT_EQ(skel->bss->callback_success, skel->bss->callback_scheduled, "callbacks"); + } + +cleanup: + task_work_stress__destroy(skel); +} + +void test_task_work_stress(void) +{ + if (test__start_subtest("no_delete")) + task_work_run(false); + if (test__start_subtest("with_delete")) + task_work_run(true); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h index 924d0e25320c..d52a62af77bf 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h @@ -8,34 +8,6 @@ # define loopback 1 #endif -static inline __u32 id_from_prog_fd(int fd) -{ - struct bpf_prog_info prog_info = {}; - __u32 prog_info_len = sizeof(prog_info); - int err; - - err = bpf_obj_get_info_by_fd(fd, &prog_info, &prog_info_len); - if (!ASSERT_OK(err, "id_from_prog_fd")) - return 0; - - ASSERT_NEQ(prog_info.id, 0, "prog_info.id"); - return prog_info.id; -} - -static inline __u32 id_from_link_fd(int fd) -{ - struct bpf_link_info link_info = {}; - __u32 link_info_len = sizeof(link_info); - int err; - - err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len); - if (!ASSERT_OK(err, "id_from_link_fd")) - return 0; - - ASSERT_NEQ(link_info.id, 0, "link_info.id"); - return link_info.id; -} - static inline __u32 ifindex_from_link_fd(int fd) { struct bpf_link_info link_info = {}; diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c new file mode 100644 index 000000000000..fd8762ba4b67 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "struct_ops_id_ops_mapping1.skel.h" +#include "struct_ops_id_ops_mapping2.skel.h" + +static void test_st_ops_id_ops_mapping(void) +{ + struct struct_ops_id_ops_mapping1 *skel1 = NULL; + struct struct_ops_id_ops_mapping2 *skel2 = NULL; + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + int err, pid, prog1_fd, prog2_fd; + + skel1 = struct_ops_id_ops_mapping1__open_and_load(); + if (!ASSERT_OK_PTR(skel1, "struct_ops_id_ops_mapping1__open")) + goto out; + + skel2 = struct_ops_id_ops_mapping2__open_and_load(); + if (!ASSERT_OK_PTR(skel2, "struct_ops_id_ops_mapping2__open")) + goto out; + + err = bpf_map_get_info_by_fd(bpf_map__fd(skel1->maps.st_ops_map), + &info, &len); + if (!ASSERT_OK(err, "bpf_map_get_info_by_fd")) + goto out; + + skel1->bss->st_ops_id = info.id; + + err = bpf_map_get_info_by_fd(bpf_map__fd(skel2->maps.st_ops_map), + &info, &len); + if (!ASSERT_OK(err, "bpf_map_get_info_by_fd")) + goto out; + + skel2->bss->st_ops_id = info.id; + + err = struct_ops_id_ops_mapping1__attach(skel1); + if (!ASSERT_OK(err, "struct_ops_id_ops_mapping1__attach")) + goto out; + + err = struct_ops_id_ops_mapping2__attach(skel2); + if (!ASSERT_OK(err, "struct_ops_id_ops_mapping2__attach")) + goto out; + + /* run tracing prog that calls .test_1 and checks return */ + pid = getpid(); + skel1->bss->test_pid = pid; + skel2->bss->test_pid = pid; + sys_gettid(); + skel1->bss->test_pid = 0; + skel2->bss->test_pid = 0; + + /* run syscall_prog that calls .test_1 and checks return */ + prog1_fd = bpf_program__fd(skel1->progs.syscall_prog); + err = bpf_prog_test_run_opts(prog1_fd, NULL); + ASSERT_OK(err, "bpf_prog_test_run_opts"); + + prog2_fd = bpf_program__fd(skel2->progs.syscall_prog); + err = bpf_prog_test_run_opts(prog2_fd, NULL); + ASSERT_OK(err, "bpf_prog_test_run_opts"); + + ASSERT_EQ(skel1->bss->test_err, 0, "skel1->bss->test_err"); + ASSERT_EQ(skel2->bss->test_err, 0, "skel2->bss->test_err"); + +out: + struct_ops_id_ops_mapping1__destroy(skel1); + struct_ops_id_ops_mapping2__destroy(skel2); +} + +void test_struct_ops_id_ops_mapping(void) +{ + if (test__start_subtest("st_ops_id_ops_mapping")) + test_st_ops_id_ops_mapping(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c b/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c new file mode 100644 index 000000000000..9fd6306b455c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c @@ -0,0 +1,297 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <pthread.h> +#include <bpf/btf.h> +#include <test_progs.h> + +#define TLD_FREE_DATA_ON_THREAD_EXIT +#define TLD_DYN_DATA_SIZE 4096 +#include "task_local_data.h" + +struct test_tld_struct { + __u64 a; + __u64 b; + __u64 c; + __u64 d; +}; + +#include "test_task_local_data.skel.h" + +TLD_DEFINE_KEY(value0_key, "value0", sizeof(int)); + +/* + * Reset task local data between subtests by clearing metadata other + * than the statically defined value0. This is safe as subtests run + * sequentially. Users of task local data library should not touch + * library internal. + */ +static void reset_tld(void) +{ + if (TLD_READ_ONCE(tld_meta_p)) { + /* Remove TLDs created by tld_create_key() */ + tld_meta_p->cnt = 1; + tld_meta_p->size = TLD_DYN_DATA_SIZE; + memset(&tld_meta_p->metadata[1], 0, + (TLD_MAX_DATA_CNT - 1) * sizeof(struct tld_metadata)); + } +} + +/* Serialize access to bpf program's global variables */ +static pthread_mutex_t global_mutex; + +static tld_key_t *tld_keys; + +#define TEST_BASIC_THREAD_NUM 32 + +void *test_task_local_data_basic_thread(void *arg) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + struct test_task_local_data *skel = (struct test_task_local_data *)arg; + int fd, err, tid, *value0, *value1; + struct test_tld_struct *value2; + + fd = bpf_map__fd(skel->maps.tld_data_map); + + value0 = tld_get_data(fd, value0_key); + if (!ASSERT_OK_PTR(value0, "tld_get_data")) + goto out; + + value1 = tld_get_data(fd, tld_keys[1]); + if (!ASSERT_OK_PTR(value1, "tld_get_data")) + goto out; + + value2 = tld_get_data(fd, tld_keys[2]); + if (!ASSERT_OK_PTR(value2, "tld_get_data")) + goto out; + + tid = sys_gettid(); + + *value0 = tid + 0; + *value1 = tid + 1; + value2->a = tid + 2; + value2->b = tid + 3; + value2->c = tid + 4; + value2->d = tid + 5; + + pthread_mutex_lock(&global_mutex); + /* Run task_main that read task local data and save to global variables */ + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts); + ASSERT_OK(err, "run task_main"); + ASSERT_OK(opts.retval, "task_main retval"); + + ASSERT_EQ(skel->bss->test_value0, tid + 0, "tld_get_data value0"); + ASSERT_EQ(skel->bss->test_value1, tid + 1, "tld_get_data value1"); + ASSERT_EQ(skel->bss->test_value2.a, tid + 2, "tld_get_data value2.a"); + ASSERT_EQ(skel->bss->test_value2.b, tid + 3, "tld_get_data value2.b"); + ASSERT_EQ(skel->bss->test_value2.c, tid + 4, "tld_get_data value2.c"); + ASSERT_EQ(skel->bss->test_value2.d, tid + 5, "tld_get_data value2.d"); + pthread_mutex_unlock(&global_mutex); + + /* Make sure valueX are indeed local to threads */ + ASSERT_EQ(*value0, tid + 0, "value0"); + ASSERT_EQ(*value1, tid + 1, "value1"); + ASSERT_EQ(value2->a, tid + 2, "value2.a"); + ASSERT_EQ(value2->b, tid + 3, "value2.b"); + ASSERT_EQ(value2->c, tid + 4, "value2.c"); + ASSERT_EQ(value2->d, tid + 5, "value2.d"); + + *value0 = tid + 5; + *value1 = tid + 4; + value2->a = tid + 3; + value2->b = tid + 2; + value2->c = tid + 1; + value2->d = tid + 0; + + /* Run task_main again */ + pthread_mutex_lock(&global_mutex); + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts); + ASSERT_OK(err, "run task_main"); + ASSERT_OK(opts.retval, "task_main retval"); + + ASSERT_EQ(skel->bss->test_value0, tid + 5, "tld_get_data value0"); + ASSERT_EQ(skel->bss->test_value1, tid + 4, "tld_get_data value1"); + ASSERT_EQ(skel->bss->test_value2.a, tid + 3, "tld_get_data value2.a"); + ASSERT_EQ(skel->bss->test_value2.b, tid + 2, "tld_get_data value2.b"); + ASSERT_EQ(skel->bss->test_value2.c, tid + 1, "tld_get_data value2.c"); + ASSERT_EQ(skel->bss->test_value2.d, tid + 0, "tld_get_data value2.d"); + pthread_mutex_unlock(&global_mutex); + +out: + pthread_exit(NULL); +} + +static void test_task_local_data_basic(void) +{ + struct test_task_local_data *skel; + pthread_t thread[TEST_BASIC_THREAD_NUM]; + char dummy_key_name[TLD_NAME_LEN]; + tld_key_t key; + int i, err; + + reset_tld(); + + ASSERT_OK(pthread_mutex_init(&global_mutex, NULL), "pthread_mutex_init"); + + skel = test_task_local_data__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + tld_keys = calloc(TLD_MAX_DATA_CNT, sizeof(tld_key_t)); + if (!ASSERT_OK_PTR(tld_keys, "calloc tld_keys")) + goto out; + + ASSERT_FALSE(tld_key_is_err(value0_key), "TLD_DEFINE_KEY"); + tld_keys[1] = tld_create_key("value1", sizeof(int)); + ASSERT_FALSE(tld_key_is_err(tld_keys[1]), "tld_create_key"); + tld_keys[2] = tld_create_key("value2", sizeof(struct test_tld_struct)); + ASSERT_FALSE(tld_key_is_err(tld_keys[2]), "tld_create_key"); + + /* + * Shouldn't be able to store data exceed a page. Create a TLD just big + * enough to exceed a page. TLDs already created are int value0, int + * value1, and struct test_tld_struct value2. + */ + key = tld_create_key("value_not_exist", + TLD_PAGE_SIZE - 2 * sizeof(int) - sizeof(struct test_tld_struct) + 1); + ASSERT_EQ(tld_key_err_or_zero(key), -E2BIG, "tld_create_key"); + + key = tld_create_key("value2", sizeof(struct test_tld_struct)); + ASSERT_EQ(tld_key_err_or_zero(key), -EEXIST, "tld_create_key"); + + /* Shouldn't be able to create the (TLD_MAX_DATA_CNT+1)-th TLD */ + for (i = 3; i < TLD_MAX_DATA_CNT; i++) { + snprintf(dummy_key_name, TLD_NAME_LEN, "dummy_value%d", i); + tld_keys[i] = tld_create_key(dummy_key_name, sizeof(int)); + ASSERT_FALSE(tld_key_is_err(tld_keys[i]), "tld_create_key"); + } + key = tld_create_key("value_not_exist", sizeof(struct test_tld_struct)); + ASSERT_EQ(tld_key_err_or_zero(key), -ENOSPC, "tld_create_key"); + + /* Access TLDs from multiple threads and check if they are thread-specific */ + for (i = 0; i < TEST_BASIC_THREAD_NUM; i++) { + err = pthread_create(&thread[i], NULL, test_task_local_data_basic_thread, skel); + if (!ASSERT_OK(err, "pthread_create")) + goto out; + } + +out: + for (i = 0; i < TEST_BASIC_THREAD_NUM; i++) + pthread_join(thread[i], NULL); + + if (tld_keys) { + free(tld_keys); + tld_keys = NULL; + } + tld_free(); + test_task_local_data__destroy(skel); +} + +#define TEST_RACE_THREAD_NUM (TLD_MAX_DATA_CNT - 3) + +void *test_task_local_data_race_thread(void *arg) +{ + int err = 0, id = (intptr_t)arg; + char key_name[32]; + tld_key_t key; + + key = tld_create_key("value_not_exist", TLD_PAGE_SIZE + 1); + if (tld_key_err_or_zero(key) != -E2BIG) { + err = 1; + goto out; + } + + /* Only one thread will succeed in creating value1 */ + key = tld_create_key("value1", sizeof(int)); + if (!tld_key_is_err(key)) + tld_keys[1] = key; + + /* Only one thread will succeed in creating value2 */ + key = tld_create_key("value2", sizeof(struct test_tld_struct)); + if (!tld_key_is_err(key)) + tld_keys[2] = key; + + snprintf(key_name, 32, "thread_%d", id); + tld_keys[id] = tld_create_key(key_name, sizeof(int)); + if (tld_key_is_err(tld_keys[id])) + err = 2; +out: + return (void *)(intptr_t)err; +} + +static void test_task_local_data_race(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + pthread_t thread[TEST_RACE_THREAD_NUM]; + struct test_task_local_data *skel; + int fd, i, j, err, *data; + void *ret = NULL; + + skel = test_task_local_data__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + tld_keys = calloc(TLD_MAX_DATA_CNT, sizeof(tld_key_t)); + if (!ASSERT_OK_PTR(tld_keys, "calloc tld_keys")) + goto out; + + fd = bpf_map__fd(skel->maps.tld_data_map); + + ASSERT_FALSE(tld_key_is_err(value0_key), "TLD_DEFINE_KEY"); + tld_keys[0] = value0_key; + + for (j = 0; j < 100; j++) { + reset_tld(); + + for (i = 0; i < TEST_RACE_THREAD_NUM; i++) { + /* + * Try to make tld_create_key() race with each other. Call + * tld_create_key(), both valid and invalid, from different threads. + */ + err = pthread_create(&thread[i], NULL, test_task_local_data_race_thread, + (void *)(intptr_t)(i + 3)); + if (CHECK_FAIL(err)) + break; + } + + /* Wait for all tld_create_key() to return */ + for (i = 0; i < TEST_RACE_THREAD_NUM; i++) { + pthread_join(thread[i], &ret); + if (CHECK_FAIL(ret)) + break; + } + + /* Write a unique number to each TLD */ + for (i = 0; i < TLD_MAX_DATA_CNT; i++) { + data = tld_get_data(fd, tld_keys[i]); + if (CHECK_FAIL(!data)) + break; + *data = i; + } + + /* Read TLDs and check the value to see if any address collides with another */ + for (i = 0; i < TLD_MAX_DATA_CNT; i++) { + data = tld_get_data(fd, tld_keys[i]); + if (CHECK_FAIL(*data != i)) + break; + } + + /* Run task_main to make sure no invalid TLDs are added */ + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts); + ASSERT_OK(err, "run task_main"); + ASSERT_OK(opts.retval, "task_main retval"); + } +out: + if (tld_keys) { + free(tld_keys); + tld_keys = NULL; + } + tld_free(); + test_task_local_data__destroy(skel); +} + +void test_task_local_data(void) +{ + if (test__start_subtest("task_local_data_basic")) + test_task_local_data_basic(); + if (test__start_subtest("task_local_data_race")) + test_task_local_data_race(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_task_work.c b/tools/testing/selftests/bpf/prog_tests/test_task_work.c new file mode 100644 index 000000000000..774b31a5f6ca --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_task_work.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include <string.h> +#include <stdio.h> +#include "task_work.skel.h" +#include "task_work_fail.skel.h" +#include <linux/bpf.h> +#include <linux/perf_event.h> +#include <sys/syscall.h> +#include <time.h> + +static int perf_event_open(__u32 type, __u64 config, int pid) +{ + struct perf_event_attr attr = { + .type = type, + .config = config, + .size = sizeof(struct perf_event_attr), + .sample_period = 100000, + }; + + return syscall(__NR_perf_event_open, &attr, pid, -1, -1, 0); +} + +struct elem { + char data[128]; + struct bpf_task_work tw; +}; + +static int verify_map(struct bpf_map *map, const char *expected_data) +{ + int err; + struct elem value; + int processed_values = 0; + int k, sz; + + sz = bpf_map__max_entries(map); + for (k = 0; k < sz; ++k) { + err = bpf_map__lookup_elem(map, &k, sizeof(int), &value, sizeof(struct elem), 0); + if (err) + continue; + if (!ASSERT_EQ(strcmp(expected_data, value.data), 0, "map data")) { + fprintf(stderr, "expected '%s', found '%s' in %s map", expected_data, + value.data, bpf_map__name(map)); + return 2; + } + processed_values++; + } + + return processed_values == 0; +} + +static void task_work_run(const char *prog_name, const char *map_name) +{ + struct task_work *skel; + struct bpf_program *prog; + struct bpf_map *map; + struct bpf_link *link = NULL; + int err, pe_fd = -1, pid, status, pipefd[2]; + char user_string[] = "hello world"; + + if (!ASSERT_NEQ(pipe(pipefd), -1, "pipe")) + return; + + pid = fork(); + if (pid == 0) { + __u64 num = 1; + int i; + char buf; + + close(pipefd[1]); + read(pipefd[0], &buf, sizeof(buf)); + close(pipefd[0]); + + for (i = 0; i < 10000; ++i) + num *= time(0) % 7; + (void)num; + exit(0); + } + if (!ASSERT_GT(pid, 0, "fork() failed")) { + close(pipefd[0]); + close(pipefd[1]); + return; + } + + skel = task_work__open(); + if (!ASSERT_OK_PTR(skel, "task_work__open")) + return; + + bpf_object__for_each_program(prog, skel->obj) { + bpf_program__set_autoload(prog, false); + } + + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!ASSERT_OK_PTR(prog, "prog_name")) + goto cleanup; + bpf_program__set_autoload(prog, true); + skel->bss->user_ptr = (char *)user_string; + + err = task_work__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pe_fd = perf_event_open(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES, pid); + if (pe_fd == -1 && (errno == ENOENT || errno == EOPNOTSUPP)) { + printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__); + test__skip(); + goto cleanup; + } + if (!ASSERT_NEQ(pe_fd, -1, "pe_fd")) { + fprintf(stderr, "perf_event_open errno: %d, pid: %d\n", errno, pid); + goto cleanup; + } + + link = bpf_program__attach_perf_event(prog, pe_fd); + if (!ASSERT_OK_PTR(link, "attach_perf_event")) + goto cleanup; + + /* perf event fd ownership is passed to bpf_link */ + pe_fd = -1; + close(pipefd[0]); + write(pipefd[1], user_string, 1); + close(pipefd[1]); + /* Wait to collect some samples */ + waitpid(pid, &status, 0); + pid = 0; + map = bpf_object__find_map_by_name(skel->obj, map_name); + if (!ASSERT_OK_PTR(map, "find map_name")) + goto cleanup; + if (!ASSERT_OK(verify_map(map, user_string), "verify map")) + goto cleanup; +cleanup: + if (pe_fd >= 0) + close(pe_fd); + bpf_link__destroy(link); + task_work__destroy(skel); + if (pid > 0) { + close(pipefd[0]); + write(pipefd[1], user_string, 1); + close(pipefd[1]); + waitpid(pid, &status, 0); + } +} + +void test_task_work(void) +{ + if (test__start_subtest("test_task_work_hash_map")) + task_work_run("oncpu_hash_map", "hmap"); + + if (test__start_subtest("test_task_work_array_map")) + task_work_run("oncpu_array_map", "arrmap"); + + if (test__start_subtest("test_task_work_lru_map")) + task_work_run("oncpu_lru_map", "lrumap"); + + RUN_TESTS(task_work_fail); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c index 47b56c258f3f..b38c16b4247f 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_veristat.c +++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c @@ -60,29 +60,41 @@ static void test_set_global_vars_succeeds(void) " -G \"var_s8 = -128\" "\ " -G \"var_u8 = 255\" "\ " -G \"var_ea = EA2\" "\ - " -G \"var_eb = EB2\" "\ - " -G \"var_ec = EC2\" "\ + " -G \"var_eb = EB2\" "\ + " -G \"var_ec=EC2\" "\ " -G \"var_b = 1\" "\ - " -G \"struct1.struct2.u.var_u8 = 170\" "\ + " -G \"struct1[2].struct2[1][2].u.var_u8[2]=170\" "\ " -G \"union1.struct3.var_u8_l = 0xaa\" "\ " -G \"union1.struct3.var_u8_h = 0xaa\" "\ - "-vl2 > %s", fix->veristat, fix->tmpfile); + " -G \"arr[3]= 171\" " \ + " -G \"arr[EA2] =172\" " \ + " -G \"enum_arr[EC2]=EA3\" " \ + " -G \"three_d[31][7][EA2]=173\"" \ + " -G \"struct1[2].struct2[1][2].u.mat[5][3]=174\" " \ + " -G \"struct11 [ 7 ] [ 5 ] .struct2[0][1].u.mat[3][0] = 175\" " \ + " -vl2 > %s", fix->veristat, fix->tmpfile); read(fix->fd, fix->output, fix->sz); - __CHECK_STR("_w=0xf000000000000001 ", "var_s64 = 0xf000000000000001"); - __CHECK_STR("_w=0xfedcba9876543210 ", "var_u64 = 0xfedcba9876543210"); - __CHECK_STR("_w=0x80000000 ", "var_s32 = -0x80000000"); - __CHECK_STR("_w=0x76543210 ", "var_u32 = 0x76543210"); - __CHECK_STR("_w=0x8000 ", "var_s16 = -32768"); - __CHECK_STR("_w=0xecec ", "var_u16 = 60652"); - __CHECK_STR("_w=128 ", "var_s8 = -128"); - __CHECK_STR("_w=255 ", "var_u8 = 255"); - __CHECK_STR("_w=11 ", "var_ea = EA2"); - __CHECK_STR("_w=12 ", "var_eb = EB2"); - __CHECK_STR("_w=13 ", "var_ec = EC2"); - __CHECK_STR("_w=1 ", "var_b = 1"); - __CHECK_STR("_w=170 ", "struct1.struct2.u.var_u8 = 170"); - __CHECK_STR("_w=0xaaaa ", "union1.var_u16 = 0xaaaa"); + __CHECK_STR("=0xf000000000000001 ", "var_s64 = 0xf000000000000001"); + __CHECK_STR("=0xfedcba9876543210 ", "var_u64 = 0xfedcba9876543210"); + __CHECK_STR("=0x80000000 ", "var_s32 = -0x80000000"); + __CHECK_STR("=0x76543210 ", "var_u32 = 0x76543210"); + __CHECK_STR("=0x8000 ", "var_s16 = -32768"); + __CHECK_STR("=0xecec ", "var_u16 = 60652"); + __CHECK_STR("=128 ", "var_s8 = -128"); + __CHECK_STR("=255 ", "var_u8 = 255"); + __CHECK_STR("=11 ", "var_ea = EA2"); + __CHECK_STR("=12 ", "var_eb = EB2"); + __CHECK_STR("=13 ", "var_ec = EC2"); + __CHECK_STR("=1 ", "var_b = 1"); + __CHECK_STR("=170 ", "struct1[2].struct2[1][2].u.var_u8[2]=170"); + __CHECK_STR("=0xaaaa ", "union1.var_u16 = 0xaaaa"); + __CHECK_STR("=171 ", "arr[3]= 171"); + __CHECK_STR("=172 ", "arr[EA2] =172"); + __CHECK_STR("=10 ", "enum_arr[EC2]=EA3"); + __CHECK_STR("=173 ", "matrix[31][7][11]=173"); + __CHECK_STR("=174 ", "struct1[2].struct2[1][2].u.mat[5][3]=174"); + __CHECK_STR("=175 ", "struct11[7][5].struct2[0][1].u.mat[3][0]=175"); out: teardown_fixture(fix); @@ -105,8 +117,8 @@ static void test_set_global_vars_from_file_succeeds(void) SYS(out, "%s set_global_vars.bpf.o -G \"@%s\" -vl2 > %s", fix->veristat, input_file, fix->tmpfile); read(fix->fd, fix->output, fix->sz); - __CHECK_STR("_w=0x8000 ", "var_s16 = -32768"); - __CHECK_STR("_w=0xecec ", "var_u16 = 60652"); + __CHECK_STR("=0x8000 ", "var_s16 = -32768"); + __CHECK_STR("=0xecec ", "var_u16 = 60652"); out: close(fd); @@ -129,6 +141,95 @@ out: teardown_fixture(fix); } +static void test_unsupported_ptr_array_type(void) +{ + struct fixture *fix = init_fixture(); + + SYS_FAIL(out, + "%s set_global_vars.bpf.o -G \"ptr_arr[0] = 0\" -vl2 2> %s", + fix->veristat, fix->tmpfile); + + read(fix->fd, fix->output, fix->sz); + __CHECK_STR("Can't set ptr_arr[0]. Only ints and enums are supported", "ptr_arr"); + +out: + teardown_fixture(fix); +} + +static void test_array_out_of_bounds(void) +{ + struct fixture *fix = init_fixture(); + + SYS_FAIL(out, + "%s set_global_vars.bpf.o -G \"arr[99] = 0\" -vl2 2> %s", + fix->veristat, fix->tmpfile); + + read(fix->fd, fix->output, fix->sz); + __CHECK_STR("Array index 99 is out of bounds", "arr[99]"); + +out: + teardown_fixture(fix); +} + +static void test_array_index_not_found(void) +{ + struct fixture *fix = init_fixture(); + + SYS_FAIL(out, + "%s set_global_vars.bpf.o -G \"arr[EG2] = 0\" -vl2 2> %s", + fix->veristat, fix->tmpfile); + + read(fix->fd, fix->output, fix->sz); + __CHECK_STR("Can't resolve enum value EG2", "arr[EG2]"); + +out: + teardown_fixture(fix); +} + +static void test_array_index_for_non_array(void) +{ + struct fixture *fix = init_fixture(); + + SYS_FAIL(out, + "%s set_global_vars.bpf.o -G \"var_b[0] = 1\" -vl2 2> %s", + fix->veristat, fix->tmpfile); + + pread(fix->fd, fix->output, fix->sz, 0); + __CHECK_STR("Array index is not expected for var_b", "var_b[0] = 1"); + + SYS_FAIL(out, + "%s set_global_vars.bpf.o -G \"union1.struct3[0].var_u8_l=1\" -vl2 2> %s", + fix->veristat, fix->tmpfile); + + pread(fix->fd, fix->output, fix->sz, 0); + __CHECK_STR("Array index is not expected for struct3", "union1.struct3[0].var_u8_l=1"); + +out: + teardown_fixture(fix); +} + +static void test_no_array_index_for_array(void) +{ + struct fixture *fix = init_fixture(); + + SYS_FAIL(out, + "%s set_global_vars.bpf.o -G \"arr = 1\" -vl2 2> %s", + fix->veristat, fix->tmpfile); + + pread(fix->fd, fix->output, fix->sz, 0); + __CHECK_STR("Can't set arr. Only ints and enums are supported", "arr = 1"); + + SYS_FAIL(out, + "%s set_global_vars.bpf.o -G \"struct1[0].struct2.u.var_u8[2]=1\" -vl2 2> %s", + fix->veristat, fix->tmpfile); + + pread(fix->fd, fix->output, fix->sz, 0); + __CHECK_STR("Can't resolve field u for non-composite type", "struct1[0].struct2.u.var_u8[2]=1"); + +out: + teardown_fixture(fix); +} + void test_veristat(void) { if (test__start_subtest("set_global_vars_succeeds")) @@ -139,6 +240,22 @@ void test_veristat(void) if (test__start_subtest("set_global_vars_from_file_succeeds")) test_set_global_vars_from_file_succeeds(); + + if (test__start_subtest("test_unsupported_ptr_array_type")) + test_unsupported_ptr_array_type(); + + if (test__start_subtest("test_array_out_of_bounds")) + test_array_out_of_bounds(); + + if (test__start_subtest("test_array_index_not_found")) + test_array_index_not_found(); + + if (test__start_subtest("test_array_index_for_non_array")) + test_array_index_for_non_array(); + + if (test__start_subtest("test_no_array_index_for_array")) + test_no_array_index_for_array(); + } #undef __CHECK_STR diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index d66687f1ee6a..34f9ccce2602 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -3,6 +3,7 @@ #include <test_progs.h> #include "timer.skel.h" #include "timer_failure.skel.h" +#include "timer_interrupt.skel.h" #define NUM_THR 8 @@ -86,6 +87,10 @@ void serial_test_timer(void) int err; timer_skel = timer__open_and_load(); + if (!timer_skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load")) return; @@ -95,3 +100,36 @@ void serial_test_timer(void) RUN_TESTS(timer_failure); } + +void test_timer_interrupt(void) +{ + struct timer_interrupt *skel = NULL; + int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, opts); + + skel = timer_interrupt__open_and_load(); + if (!skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } + if (!ASSERT_OK_PTR(skel, "timer_interrupt__open_and_load")) + return; + + err = timer_interrupt__attach(skel); + if (!ASSERT_OK(err, "timer_interrupt__attach")) + goto out; + + prog_fd = bpf_program__fd(skel->progs.test_timer_interrupt); + err = bpf_prog_test_run_opts(prog_fd, &opts); + if (!ASSERT_OK(err, "bpf_prog_test_run_opts")) + goto out; + + usleep(50); + + ASSERT_EQ(skel->bss->in_interrupt, 0, "in_interrupt"); + if (skel->bss->preempt_count) + ASSERT_NEQ(skel->bss->in_interrupt_cb, 0, "in_interrupt_cb"); + +out: + timer_interrupt__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c index f74b82305da8..b841597c8a3a 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_crash.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c @@ -12,6 +12,10 @@ static void test_timer_crash_mode(int mode) struct timer_crash *skel; skel = timer_crash__open_and_load(); + if (!skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load")) return; skel->bss->pid = getpid(); diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c index 1a2f99596916..eb303fa1e09a 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c @@ -59,6 +59,10 @@ void test_timer_lockup(void) } skel = timer_lockup__open_and_load(); + if (!skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c index 9ff7843909e7..c930c7d7105b 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c @@ -65,6 +65,10 @@ void serial_test_timer_mim(void) goto cleanup; timer_skel = timer_mim__open_and_load(); + if (!timer_skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c index f9392df23f8a..b81dde283052 100644 --- a/tools/testing/selftests/bpf/prog_tests/token.c +++ b/tools/testing/selftests/bpf/prog_tests/token.c @@ -115,7 +115,7 @@ static int create_bpffs_fd(void) static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts) { - int mnt_fd, err; + int err; /* set up token delegation mount options */ err = set_delegate_mask(fs_fd, "delegate_cmds", opts->cmds, opts->cmds_str); @@ -136,12 +136,7 @@ static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts) if (err < 0) return -errno; - /* create O_PATH fd for detached mount */ - mnt_fd = sys_fsmount(fs_fd, 0, 0); - if (err < 0) - return -errno; - - return mnt_fd; + return 0; } /* send FD over Unix domain (AF_UNIX) socket */ @@ -287,6 +282,7 @@ static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callba { int mnt_fd = -1, fs_fd = -1, err = 0, bpffs_fd = -1, token_fd = -1; struct token_lsm *lsm_skel = NULL; + char one; /* load and attach LSM "policy" before we go into unpriv userns */ lsm_skel = token_lsm__open_and_load(); @@ -333,13 +329,19 @@ static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callba err = sendfd(sock_fd, fs_fd); if (!ASSERT_OK(err, "send_fs_fd")) goto cleanup; - zclose(fs_fd); + + /* wait that the parent reads the fd, does the fsconfig() calls + * and send us a signal that it is done + */ + err = read(sock_fd, &one, sizeof(one)); + if (!ASSERT_GE(err, 0, "read_one")) + goto cleanup; /* avoid mucking around with mount namespaces and mounting at - * well-known path, just get detach-mounted BPF FS fd back from parent + * well-known path, just create O_PATH fd for detached mount */ - err = recvfd(sock_fd, &mnt_fd); - if (!ASSERT_OK(err, "recv_mnt_fd")) + mnt_fd = sys_fsmount(fs_fd, 0, 0); + if (!ASSERT_OK_FD(mnt_fd, "mnt_fd")) goto cleanup; /* try to fspick() BPF FS and try to add some delegation options */ @@ -429,24 +431,24 @@ again: static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd) { - int fs_fd = -1, mnt_fd = -1, token_fd = -1, err; + int fs_fd = -1, token_fd = -1, err; + char one = 1; err = recvfd(sock_fd, &fs_fd); if (!ASSERT_OK(err, "recv_bpffs_fd")) goto cleanup; - mnt_fd = materialize_bpffs_fd(fs_fd, bpffs_opts); - if (!ASSERT_GE(mnt_fd, 0, "materialize_bpffs_fd")) { + err = materialize_bpffs_fd(fs_fd, bpffs_opts); + if (!ASSERT_GE(err, 0, "materialize_bpffs_fd")) { err = -EINVAL; goto cleanup; } - zclose(fs_fd); - /* pass BPF FS context object to parent */ - err = sendfd(sock_fd, mnt_fd); - if (!ASSERT_OK(err, "send_mnt_fd")) + /* notify the child that we did the fsconfig() calls and it can proceed. */ + err = write(sock_fd, &one, sizeof(one)); + if (!ASSERT_EQ(err, sizeof(one), "send_one")) goto cleanup; - zclose(mnt_fd); + zclose(fs_fd); /* receive BPF token FD back from child for some extra tests */ err = recvfd(sock_fd, &token_fd); @@ -459,7 +461,6 @@ static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd) cleanup: zclose(sock_fd); zclose(fs_fd); - zclose(mnt_fd); zclose(token_fd); if (child_pid > 0) @@ -1046,6 +1047,41 @@ err_out: #define bit(n) (1ULL << (n)) +static int userns_bpf_token_info(int mnt_fd, struct token_lsm *lsm_skel) +{ + int err, token_fd = -1; + struct bpf_token_info info; + u32 len = sizeof(struct bpf_token_info); + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + memset(&info, 0, len); + err = bpf_obj_get_info_by_fd(token_fd, &info, &len); + if (!ASSERT_ERR(err, "bpf_obj_get_token_info")) + goto cleanup; + if (!ASSERT_EQ(info.allowed_cmds, bit(BPF_MAP_CREATE), "token_info_cmds_map_create")) { + err = -EINVAL; + goto cleanup; + } + if (!ASSERT_EQ(info.allowed_progs, bit(BPF_PROG_TYPE_XDP), "token_info_progs_xdp")) { + err = -EINVAL; + goto cleanup; + } + + /* The BPF_PROG_TYPE_EXT is not set in token */ + if (ASSERT_EQ(info.allowed_progs, bit(BPF_PROG_TYPE_EXT), "token_info_progs_ext")) + err = -EINVAL; + +cleanup: + zclose(token_fd); + return err; +} + void test_token(void) { if (test__start_subtest("map_token")) { @@ -1149,4 +1185,13 @@ void test_token(void) subtest_userns(&opts, userns_obj_priv_implicit_token_envvar); } + if (test__start_subtest("bpf_token_info")) { + struct bpffs_opts opts = { + .cmds = bit(BPF_MAP_CREATE), + .progs = bit(BPF_PROG_TYPE_XDP), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_bpf_token_info); + } } diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_failure.c b/tools/testing/selftests/bpf/prog_tests/tracing_failure.c index a222df765bc3..10e231965589 100644 --- a/tools/testing/selftests/bpf/prog_tests/tracing_failure.c +++ b/tools/testing/selftests/bpf/prog_tests/tracing_failure.c @@ -28,10 +28,62 @@ out: tracing_failure__destroy(skel); } +static void test_tracing_fail_prog(const char *prog_name, const char *exp_msg) +{ + struct tracing_failure *skel; + struct bpf_program *prog; + char log_buf[256]; + int err; + + skel = tracing_failure__open(); + if (!ASSERT_OK_PTR(skel, "tracing_failure__open")) + return; + + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name")) + goto out; + + bpf_program__set_autoload(prog, true); + bpf_program__set_log_buf(prog, log_buf, sizeof(log_buf)); + + err = tracing_failure__load(skel); + if (!ASSERT_ERR(err, "tracing_failure__load")) + goto out; + + ASSERT_HAS_SUBSTR(log_buf, exp_msg, "log_buf"); +out: + tracing_failure__destroy(skel); +} + +static void test_tracing_deny(void) +{ + int btf_id; + + /* __rcu_read_lock depends on CONFIG_PREEMPT_RCU */ + btf_id = libbpf_find_vmlinux_btf_id("__rcu_read_lock", BPF_TRACE_FENTRY); + if (btf_id <= 0) { + test__skip(); + return; + } + + test_tracing_fail_prog("tracing_deny", + "Attaching tracing programs to function '__rcu_read_lock' is rejected."); +} + +static void test_fexit_noreturns(void) +{ + test_tracing_fail_prog("fexit_noreturns", + "Attaching fexit/fmod_ret to __noreturn function 'do_exit' is rejected."); +} + void test_tracing_failure(void) { if (test__start_subtest("bpf_spin_lock")) test_bpf_spin_lock(true); if (test__start_subtest("bpf_spin_unlock")) test_bpf_spin_lock(false); + if (test__start_subtest("tracing_deny")) + test_tracing_deny(); + if (test__start_subtest("fexit_noreturns")) + test_fexit_noreturns(); } diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c index 19e68d4b3532..6f8c0bfb0415 100644 --- a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c +++ b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c @@ -112,10 +112,39 @@ destroy_skel: tracing_struct_many_args__destroy(skel); } +static void test_union_args(void) +{ + struct tracing_struct *skel; + int err; + + skel = tracing_struct__open_and_load(); + if (!ASSERT_OK_PTR(skel, "tracing_struct__open_and_load")) + return; + + err = tracing_struct__attach(skel); + if (!ASSERT_OK(err, "tracing_struct__attach")) + goto out; + + ASSERT_OK(trigger_module_test_read(256), "trigger_read"); + + ASSERT_EQ(skel->bss->ut1_a_a, 1, "ut1:a.arg.a"); + ASSERT_EQ(skel->bss->ut1_b, 4, "ut1:b"); + ASSERT_EQ(skel->bss->ut1_c, 5, "ut1:c"); + + ASSERT_EQ(skel->bss->ut2_a, 6, "ut2:a"); + ASSERT_EQ(skel->bss->ut2_b_a, 2, "ut2:b.arg.a"); + ASSERT_EQ(skel->bss->ut2_b_b, 3, "ut2:b.arg.b"); + +out: + tracing_struct__destroy(skel); +} + void test_tracing_struct(void) { if (test__start_subtest("struct_args")) test_struct_args(); if (test__start_subtest("struct_many_args")) test_struct_many_args(); + if (test__start_subtest("union_args")) + test_union_args(); } diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe.c b/tools/testing/selftests/bpf/prog_tests/uprobe.c index cf3e0e7a64fa..86404476c1da 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe.c @@ -2,6 +2,7 @@ /* Copyright (c) 2023 Hengqi Chen */ #include <test_progs.h> +#include <asm/ptrace.h> #include "test_uprobe.skel.h" static FILE *urand_spawn(int *pid) @@ -33,7 +34,7 @@ static int urand_trigger(FILE **urand_pipe) return exit_code; } -void test_uprobe(void) +static void test_uprobe_attach(void) { LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts); struct test_uprobe *skel; @@ -93,3 +94,156 @@ cleanup: pclose(urand_pipe); test_uprobe__destroy(skel); } + +#ifdef __x86_64__ +__naked __maybe_unused unsigned long uprobe_regs_change_trigger(void) +{ + asm volatile ( + "ret\n" + ); +} + +static __naked void uprobe_regs_change(struct pt_regs *before, struct pt_regs *after) +{ + asm volatile ( + "movq %r11, 48(%rdi)\n" + "movq %r10, 56(%rdi)\n" + "movq %r9, 64(%rdi)\n" + "movq %r8, 72(%rdi)\n" + "movq %rax, 80(%rdi)\n" + "movq %rcx, 88(%rdi)\n" + "movq %rdx, 96(%rdi)\n" + "movq %rsi, 104(%rdi)\n" + "movq %rdi, 112(%rdi)\n" + + /* save 2nd argument */ + "pushq %rsi\n" + "call uprobe_regs_change_trigger\n" + + /* save return value and load 2nd argument pointer to rax */ + "pushq %rax\n" + "movq 8(%rsp), %rax\n" + + "movq %r11, 48(%rax)\n" + "movq %r10, 56(%rax)\n" + "movq %r9, 64(%rax)\n" + "movq %r8, 72(%rax)\n" + "movq %rcx, 88(%rax)\n" + "movq %rdx, 96(%rax)\n" + "movq %rsi, 104(%rax)\n" + "movq %rdi, 112(%rax)\n" + + /* restore return value and 2nd argument */ + "pop %rax\n" + "pop %rsi\n" + + "movq %rax, 80(%rsi)\n" + "ret\n" + ); +} + +static void regs_common(void) +{ + struct pt_regs before = {}, after = {}, expected = { + .rax = 0xc0ffe, + .rcx = 0xbad, + .rdx = 0xdead, + .r8 = 0x8, + .r9 = 0x9, + .r10 = 0x10, + .r11 = 0x11, + .rdi = 0x12, + .rsi = 0x13, + }; + LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts); + struct test_uprobe *skel; + + skel = test_uprobe__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + skel->bss->my_pid = getpid(); + skel->bss->regs = expected; + + uprobe_opts.func_name = "uprobe_regs_change_trigger"; + skel->links.test_regs_change = bpf_program__attach_uprobe_opts(skel->progs.test_regs_change, + -1, + "/proc/self/exe", + 0 /* offset */, + &uprobe_opts); + if (!ASSERT_OK_PTR(skel->links.test_regs_change, "bpf_program__attach_uprobe_opts")) + goto cleanup; + + uprobe_regs_change(&before, &after); + + ASSERT_EQ(after.rax, expected.rax, "ax"); + ASSERT_EQ(after.rcx, expected.rcx, "cx"); + ASSERT_EQ(after.rdx, expected.rdx, "dx"); + ASSERT_EQ(after.r8, expected.r8, "r8"); + ASSERT_EQ(after.r9, expected.r9, "r9"); + ASSERT_EQ(after.r10, expected.r10, "r10"); + ASSERT_EQ(after.r11, expected.r11, "r11"); + ASSERT_EQ(after.rdi, expected.rdi, "rdi"); + ASSERT_EQ(after.rsi, expected.rsi, "rsi"); + +cleanup: + test_uprobe__destroy(skel); +} + +static noinline unsigned long uprobe_regs_change_ip_1(void) +{ + return 0xc0ffee; +} + +static noinline unsigned long uprobe_regs_change_ip_2(void) +{ + return 0xdeadbeef; +} + +static void regs_ip(void) +{ + LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts); + struct test_uprobe *skel; + unsigned long ret; + + skel = test_uprobe__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + skel->bss->my_pid = getpid(); + skel->bss->ip = (unsigned long) uprobe_regs_change_ip_2; + + uprobe_opts.func_name = "uprobe_regs_change_ip_1"; + skel->links.test_regs_change_ip = bpf_program__attach_uprobe_opts( + skel->progs.test_regs_change_ip, + -1, + "/proc/self/exe", + 0 /* offset */, + &uprobe_opts); + if (!ASSERT_OK_PTR(skel->links.test_regs_change_ip, "bpf_program__attach_uprobe_opts")) + goto cleanup; + + ret = uprobe_regs_change_ip_1(); + ASSERT_EQ(ret, 0xdeadbeef, "ret"); + +cleanup: + test_uprobe__destroy(skel); +} + +static void test_uprobe_regs_change(void) +{ + if (test__start_subtest("regs_change_common")) + regs_common(); + if (test__start_subtest("regs_change_ip")) + regs_ip(); +} +#else +static void test_uprobe_regs_change(void) { } +#endif + +void test_uprobe(void) +{ + if (test__start_subtest("attach")) + test_uprobe_attach(); + test_uprobe_regs_change(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c index c397336fe1ed..955a37751b52 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c @@ -8,22 +8,31 @@ #include <asm/ptrace.h> #include <linux/compiler.h> #include <linux/stringify.h> +#include <linux/kernel.h> #include <sys/wait.h> #include <sys/syscall.h> #include <sys/prctl.h> #include <asm/prctl.h> #include "uprobe_syscall.skel.h" #include "uprobe_syscall_executed.skel.h" +#include "bpf/libbpf_internal.h" -__naked unsigned long uretprobe_regs_trigger(void) +#define USDT_NOP .byte 0x0f, 0x1f, 0x44, 0x00, 0x00 +#include "usdt.h" + +#pragma GCC diagnostic ignored "-Wattributes" + +__attribute__((aligned(16))) +__nocf_check __weak __naked unsigned long uprobe_regs_trigger(void) { asm volatile ( + ".byte 0x0f, 0x1f, 0x44, 0x00, 0x00\n" /* nop5 */ "movq $0xdeadbeef, %rax\n" "ret\n" ); } -__naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after) +__naked void uprobe_regs(struct pt_regs *before, struct pt_regs *after) { asm volatile ( "movq %r15, 0(%rdi)\n" @@ -44,15 +53,17 @@ __naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after) "movq $0, 120(%rdi)\n" /* orig_rax */ "movq $0, 128(%rdi)\n" /* rip */ "movq $0, 136(%rdi)\n" /* cs */ + "pushq %rax\n" "pushf\n" "pop %rax\n" "movq %rax, 144(%rdi)\n" /* eflags */ + "pop %rax\n" "movq %rsp, 152(%rdi)\n" /* rsp */ "movq $0, 160(%rdi)\n" /* ss */ /* save 2nd argument */ "pushq %rsi\n" - "call uretprobe_regs_trigger\n" + "call uprobe_regs_trigger\n" /* save return value and load 2nd argument pointer to rax */ "pushq %rax\n" @@ -92,25 +103,37 @@ __naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after) ); } -static void test_uretprobe_regs_equal(void) +static void test_uprobe_regs_equal(bool retprobe) { + LIBBPF_OPTS(bpf_uprobe_opts, opts, + .retprobe = retprobe, + ); struct uprobe_syscall *skel = NULL; struct pt_regs before = {}, after = {}; unsigned long *pb = (unsigned long *) &before; unsigned long *pa = (unsigned long *) &after; unsigned long *pp; + unsigned long offset; unsigned int i, cnt; - int err; + + offset = get_uprobe_offset(&uprobe_regs_trigger); + if (!ASSERT_GE(offset, 0, "get_uprobe_offset")) + return; skel = uprobe_syscall__open_and_load(); if (!ASSERT_OK_PTR(skel, "uprobe_syscall__open_and_load")) goto cleanup; - err = uprobe_syscall__attach(skel); - if (!ASSERT_OK(err, "uprobe_syscall__attach")) + skel->links.probe = bpf_program__attach_uprobe_opts(skel->progs.probe, + 0, "/proc/self/exe", offset, &opts); + if (!ASSERT_OK_PTR(skel->links.probe, "bpf_program__attach_uprobe_opts")) goto cleanup; - uretprobe_regs(&before, &after); + /* make sure uprobe gets optimized */ + if (!retprobe) + uprobe_regs_trigger(); + + uprobe_regs(&before, &after); pp = (unsigned long *) &skel->bss->regs; cnt = sizeof(before)/sizeof(*pb); @@ -119,7 +142,7 @@ static void test_uretprobe_regs_equal(void) unsigned int offset = i * sizeof(unsigned long); /* - * Check register before and after uretprobe_regs_trigger call + * Check register before and after uprobe_regs_trigger call * that triggers the uretprobe. */ switch (offset) { @@ -133,7 +156,7 @@ static void test_uretprobe_regs_equal(void) /* * Check register seen from bpf program and register after - * uretprobe_regs_trigger call + * uprobe_regs_trigger call (with rax exception, check below). */ switch (offset) { /* @@ -146,6 +169,15 @@ static void test_uretprobe_regs_equal(void) case offsetof(struct pt_regs, rsp): case offsetof(struct pt_regs, ss): break; + /* + * uprobe does not see return value in rax, it needs to see the + * original (before) rax value + */ + case offsetof(struct pt_regs, rax): + if (!retprobe) { + ASSERT_EQ(pp[i], pb[i], "uprobe rax prog-before value check"); + break; + } default: if (!ASSERT_EQ(pp[i], pa[i], "register prog-after value check")) fprintf(stdout, "failed register offset %u\n", offset); @@ -175,7 +207,7 @@ static int write_bpf_testmod_uprobe(unsigned long offset) return ret != n ? (int) ret : 0; } -static void test_uretprobe_regs_change(void) +static void test_regs_change(void) { struct pt_regs before = {}, after = {}; unsigned long *pb = (unsigned long *) &before; @@ -183,13 +215,16 @@ static void test_uretprobe_regs_change(void) unsigned long cnt = sizeof(before)/sizeof(*pb); unsigned int i, err, offset; - offset = get_uprobe_offset(uretprobe_regs_trigger); + offset = get_uprobe_offset(uprobe_regs_trigger); err = write_bpf_testmod_uprobe(offset); if (!ASSERT_OK(err, "register_uprobe")) return; - uretprobe_regs(&before, &after); + /* make sure uprobe gets optimized */ + uprobe_regs_trigger(); + + uprobe_regs(&before, &after); err = write_bpf_testmod_uprobe(0); if (!ASSERT_OK(err, "unregister_uprobe")) @@ -251,7 +286,8 @@ static void test_uretprobe_syscall_call(void) .retprobe = true, ); struct uprobe_syscall_executed *skel; - int pid, status, err, go[2], c; + int pid, status, err, go[2], c = 0; + struct bpf_link *link; if (!ASSERT_OK(pipe(go), "pipe")) return; @@ -277,11 +313,14 @@ static void test_uretprobe_syscall_call(void) _exit(0); } - skel->links.test = bpf_program__attach_uprobe_multi(skel->progs.test, pid, - "/proc/self/exe", - "uretprobe_syscall_call", &opts); - if (!ASSERT_OK_PTR(skel->links.test, "bpf_program__attach_uprobe_multi")) + skel->bss->pid = pid; + + link = bpf_program__attach_uprobe_multi(skel->progs.test_uretprobe_multi, + pid, "/proc/self/exe", + "uretprobe_syscall_call", &opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi")) goto cleanup; + skel->links.test_uretprobe_multi = link; /* kick the child */ write(go[1], &c, 1); @@ -301,6 +340,256 @@ cleanup: close(go[0]); } +#define TRAMP "[uprobes-trampoline]" + +__attribute__((aligned(16))) +__nocf_check __weak __naked void uprobe_test(void) +{ + asm volatile (" \n" + ".byte 0x0f, 0x1f, 0x44, 0x00, 0x00 \n" + "ret \n" + ); +} + +__attribute__((aligned(16))) +__nocf_check __weak void usdt_test(void) +{ + USDT(optimized_uprobe, usdt); +} + +static int find_uprobes_trampoline(void *tramp_addr) +{ + void *start, *end; + char line[128]; + int ret = -1; + FILE *maps; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) { + fprintf(stderr, "cannot open maps\n"); + return -1; + } + + while (fgets(line, sizeof(line), maps)) { + int m = -1; + + /* We care only about private r-x mappings. */ + if (sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n", &start, &end, &m) != 2) + continue; + if (m < 0) + continue; + if (!strncmp(&line[m], TRAMP, sizeof(TRAMP)-1) && (start == tramp_addr)) { + ret = 0; + break; + } + } + + fclose(maps); + return ret; +} + +static unsigned char nop5[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 }; + +static void *find_nop5(void *fn) +{ + int i; + + for (i = 0; i < 10; i++) { + if (!memcmp(nop5, fn + i, 5)) + return fn + i; + } + return NULL; +} + +typedef void (__attribute__((nocf_check)) *trigger_t)(void); + +static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigger, + void *addr, int executed) +{ + struct __arch_relative_insn { + __u8 op; + __s32 raddr; + } __packed *call; + void *tramp = NULL; + + /* Uprobe gets optimized after first trigger, so let's press twice. */ + trigger(); + trigger(); + + /* Make sure bpf program got executed.. */ + ASSERT_EQ(skel->bss->executed, executed, "executed"); + + /* .. and check the trampoline is as expected. */ + call = (struct __arch_relative_insn *) addr; + tramp = (void *) (call + 1) + call->raddr; + ASSERT_EQ(call->op, 0xe8, "call"); + ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline"); + + return tramp; +} + +static void check_detach(void *addr, void *tramp) +{ + /* [uprobes_trampoline] stays after detach */ + ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline"); + ASSERT_OK(memcmp(addr, nop5, 5), "nop5"); +} + +static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link, + trigger_t trigger, void *addr, int executed) +{ + void *tramp; + + tramp = check_attach(skel, trigger, addr, executed); + bpf_link__destroy(link); + check_detach(addr, tramp); +} + +static void test_uprobe_legacy(void) +{ + struct uprobe_syscall_executed *skel = NULL; + LIBBPF_OPTS(bpf_uprobe_opts, opts, + .retprobe = true, + ); + struct bpf_link *link; + unsigned long offset; + + offset = get_uprobe_offset(&uprobe_test); + if (!ASSERT_GE(offset, 0, "get_uprobe_offset")) + goto cleanup; + + /* uprobe */ + skel = uprobe_syscall_executed__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load")) + return; + + skel->bss->pid = getpid(); + + link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe, + 0, "/proc/self/exe", offset, NULL); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts")) + goto cleanup; + + check(skel, link, uprobe_test, uprobe_test, 2); + + /* uretprobe */ + skel->bss->executed = 0; + + link = bpf_program__attach_uprobe_opts(skel->progs.test_uretprobe, + 0, "/proc/self/exe", offset, &opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts")) + goto cleanup; + + check(skel, link, uprobe_test, uprobe_test, 2); + +cleanup: + uprobe_syscall_executed__destroy(skel); +} + +static void test_uprobe_multi(void) +{ + struct uprobe_syscall_executed *skel = NULL; + LIBBPF_OPTS(bpf_uprobe_multi_opts, opts); + struct bpf_link *link; + unsigned long offset; + + offset = get_uprobe_offset(&uprobe_test); + if (!ASSERT_GE(offset, 0, "get_uprobe_offset")) + goto cleanup; + + opts.offsets = &offset; + opts.cnt = 1; + + skel = uprobe_syscall_executed__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load")) + return; + + skel->bss->pid = getpid(); + + /* uprobe.multi */ + link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi, + 0, "/proc/self/exe", NULL, &opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi")) + goto cleanup; + + check(skel, link, uprobe_test, uprobe_test, 2); + + /* uretprobe.multi */ + skel->bss->executed = 0; + opts.retprobe = true; + link = bpf_program__attach_uprobe_multi(skel->progs.test_uretprobe_multi, + 0, "/proc/self/exe", NULL, &opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi")) + goto cleanup; + + check(skel, link, uprobe_test, uprobe_test, 2); + +cleanup: + uprobe_syscall_executed__destroy(skel); +} + +static void test_uprobe_session(void) +{ + struct uprobe_syscall_executed *skel = NULL; + LIBBPF_OPTS(bpf_uprobe_multi_opts, opts, + .session = true, + ); + struct bpf_link *link; + unsigned long offset; + + offset = get_uprobe_offset(&uprobe_test); + if (!ASSERT_GE(offset, 0, "get_uprobe_offset")) + goto cleanup; + + opts.offsets = &offset; + opts.cnt = 1; + + skel = uprobe_syscall_executed__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load")) + return; + + skel->bss->pid = getpid(); + + link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_session, + 0, "/proc/self/exe", NULL, &opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi")) + goto cleanup; + + check(skel, link, uprobe_test, uprobe_test, 4); + +cleanup: + uprobe_syscall_executed__destroy(skel); +} + +static void test_uprobe_usdt(void) +{ + struct uprobe_syscall_executed *skel; + struct bpf_link *link; + void *addr; + + errno = 0; + addr = find_nop5(usdt_test); + if (!ASSERT_OK_PTR(addr, "find_nop5")) + return; + + skel = uprobe_syscall_executed__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load")) + return; + + skel->bss->pid = getpid(); + + link = bpf_program__attach_usdt(skel->progs.test_usdt, + -1 /* all PIDs */, "/proc/self/exe", + "optimized_uprobe", "usdt", NULL); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt")) + goto cleanup; + + check(skel, link, usdt_test, addr, 2); + +cleanup: + uprobe_syscall_executed__destroy(skel); +} + /* * Borrowed from tools/testing/selftests/x86/test_shadow_stack.c. * @@ -343,43 +632,172 @@ static void test_uretprobe_shadow_stack(void) return; } - /* Run all of the uretprobe tests. */ - test_uretprobe_regs_equal(); - test_uretprobe_regs_change(); + /* Run all the tests with shadow stack in place. */ + + test_uprobe_regs_equal(false); + test_uprobe_regs_equal(true); test_uretprobe_syscall_call(); + test_uprobe_legacy(); + test_uprobe_multi(); + test_uprobe_session(); + test_uprobe_usdt(); + + test_regs_change(); + ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK); } -#else -static void test_uretprobe_regs_equal(void) + +static volatile bool race_stop; + +static USDT_DEFINE_SEMA(race); + +static void *worker_trigger(void *arg) { - test__skip(); + unsigned long rounds = 0; + + while (!race_stop) { + uprobe_test(); + rounds++; + } + + printf("tid %ld trigger rounds: %lu\n", sys_gettid(), rounds); + return NULL; } -static void test_uretprobe_regs_change(void) +static void *worker_attach(void *arg) { - test__skip(); + LIBBPF_OPTS(bpf_uprobe_opts, opts); + struct uprobe_syscall_executed *skel; + unsigned long rounds = 0, offset; + const char *sema[2] = { + __stringify(USDT_SEMA(race)), + NULL, + }; + unsigned long *ref; + int err; + + offset = get_uprobe_offset(&uprobe_test); + if (!ASSERT_GE(offset, 0, "get_uprobe_offset")) + return NULL; + + err = elf_resolve_syms_offsets("/proc/self/exe", 1, (const char **) &sema, &ref, STT_OBJECT); + if (!ASSERT_OK(err, "elf_resolve_syms_offsets_sema")) + return NULL; + + opts.ref_ctr_offset = *ref; + + skel = uprobe_syscall_executed__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load")) + return NULL; + + skel->bss->pid = getpid(); + + while (!race_stop) { + skel->links.test_uprobe = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe, + 0, "/proc/self/exe", offset, &opts); + if (!ASSERT_OK_PTR(skel->links.test_uprobe, "bpf_program__attach_uprobe_opts")) + break; + + bpf_link__destroy(skel->links.test_uprobe); + skel->links.test_uprobe = NULL; + rounds++; + } + + printf("tid %ld attach rounds: %lu hits: %d\n", sys_gettid(), rounds, skel->bss->executed); + uprobe_syscall_executed__destroy(skel); + free(ref); + return NULL; } -static void test_uretprobe_syscall_call(void) +static useconds_t race_msec(void) { - test__skip(); + char *env; + + env = getenv("BPF_SELFTESTS_UPROBE_SYSCALL_RACE_MSEC"); + if (env) + return atoi(env); + + /* default duration is 500ms */ + return 500; } -static void test_uretprobe_shadow_stack(void) +static void test_uprobe_race(void) { - test__skip(); + int err, i, nr_threads; + pthread_t *threads; + + nr_threads = libbpf_num_possible_cpus(); + if (!ASSERT_GT(nr_threads, 0, "libbpf_num_possible_cpus")) + return; + nr_threads = max(2, nr_threads); + + threads = alloca(sizeof(*threads) * nr_threads); + if (!ASSERT_OK_PTR(threads, "malloc")) + return; + + for (i = 0; i < nr_threads; i++) { + err = pthread_create(&threads[i], NULL, i % 2 ? worker_trigger : worker_attach, + NULL); + if (!ASSERT_OK(err, "pthread_create")) + goto cleanup; + } + + usleep(race_msec() * 1000); + +cleanup: + race_stop = true; + for (nr_threads = i, i = 0; i < nr_threads; i++) + pthread_join(threads[i], NULL); + + ASSERT_FALSE(USDT_SEMA_IS_ACTIVE(race), "race_semaphore"); } + +#ifndef __NR_uprobe +#define __NR_uprobe 336 #endif -void test_uprobe_syscall(void) +static void test_uprobe_error(void) +{ + long err = syscall(__NR_uprobe); + + ASSERT_EQ(err, -1, "error"); + ASSERT_EQ(errno, ENXIO, "errno"); +} + +static void __test_uprobe_syscall(void) { if (test__start_subtest("uretprobe_regs_equal")) - test_uretprobe_regs_equal(); - if (test__start_subtest("uretprobe_regs_change")) - test_uretprobe_regs_change(); + test_uprobe_regs_equal(true); if (test__start_subtest("uretprobe_syscall_call")) test_uretprobe_syscall_call(); if (test__start_subtest("uretprobe_shadow_stack")) test_uretprobe_shadow_stack(); + if (test__start_subtest("uprobe_legacy")) + test_uprobe_legacy(); + if (test__start_subtest("uprobe_multi")) + test_uprobe_multi(); + if (test__start_subtest("uprobe_session")) + test_uprobe_session(); + if (test__start_subtest("uprobe_usdt")) + test_uprobe_usdt(); + if (test__start_subtest("uprobe_race")) + test_uprobe_race(); + if (test__start_subtest("uprobe_error")) + test_uprobe_error(); + if (test__start_subtest("uprobe_regs_equal")) + test_uprobe_regs_equal(false); + if (test__start_subtest("regs_change")) + test_regs_change(); +} +#else +static void __test_uprobe_syscall(void) +{ + test__skip(); +} +#endif + +void test_uprobe_syscall(void) +{ + __test_uprobe_syscall(); } diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c index 495d66414b57..f4be5269fa90 100644 --- a/tools/testing/selftests/bpf/prog_tests/usdt.c +++ b/tools/testing/selftests/bpf/prog_tests/usdt.c @@ -40,12 +40,79 @@ static void __always_inline trigger_func(int x) { } } -static void subtest_basic_usdt(void) +#if defined(__x86_64__) || defined(__i386__) +/* + * SIB (Scale-Index-Base) addressing format: "size@(base_reg, index_reg, scale)" + * - 'size' is the size in bytes of the array element, and its sign indicates + * whether the type is signed (negative) or unsigned (positive). + * - 'base_reg' is the register holding the base address, normally rdx or edx + * - 'index_reg' is the register holding the index, normally rax or eax + * - 'scale' is the scaling factor (typically 1, 2, 4, or 8), which matches the + * size of the element type. + * + * For example, for an array of 'short' (signed 2-byte elements), the SIB spec would be: + * - size: -2 (negative because 'short' is signed) + * - scale: 2 (since sizeof(short) == 2) + * + * The resulting SIB format: "-2@(%%rdx,%%rax,2)" for x86_64, "-2@(%%edx,%%eax,2)" for i386 + */ +static volatile short array[] = {-1, -2, -3, -4}; + +#if defined(__x86_64__) +#define USDT_SIB_ARG_SPEC -2@(%%rdx,%%rax,2) +#else +#define USDT_SIB_ARG_SPEC -2@(%%edx,%%eax,2) +#endif + +unsigned short test_usdt_sib_semaphore SEC(".probes"); + +static void trigger_sib_spec(void) +{ + /* + * Force SIB addressing with inline assembly. + * + * You must compile with -std=gnu99 or -std=c99 to use the + * STAP_PROBE_ASM macro. + * + * The STAP_PROBE_ASM macro generates a quoted string that gets + * inserted between the surrounding assembly instructions. In this + * case, USDT_SIB_ARG_SPEC is embedded directly into the instruction + * stream, creating a probe point between the asm statement boundaries. + * It works fine with gcc/clang. + * + * Register constraints: + * - "d"(array): Binds the 'array' variable to %rdx or %edx register + * - "a"(0): Binds the constant 0 to %rax or %eax register + * These ensure that when USDT_SIB_ARG_SPEC references %%rdx(%edx) and + * %%rax(%eax), they contain the expected values for SIB addressing. + * + * The "memory" clobber prevents the compiler from reordering memory + * accesses around the probe point, ensuring that the probe behavior + * is predictable and consistent. + */ + asm volatile( + STAP_PROBE_ASM(test, usdt_sib, USDT_SIB_ARG_SPEC) + : + : "d"(array), "a"(0) + : "memory" + ); +} +#endif + +static void subtest_basic_usdt(bool optimized) { LIBBPF_OPTS(bpf_usdt_opts, opts); struct test_usdt *skel; struct test_usdt__bss *bss; - int err, i; + int err, i, called; + const __u64 expected_cookie = 0xcafedeadbeeffeed; + +#define TRIGGER(x) ({ \ + trigger_func(x); \ + if (optimized) \ + trigger_func(x); \ + optimized ? 2 : 1; \ + }) skel = test_usdt__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -59,20 +126,29 @@ static void subtest_basic_usdt(void) goto cleanup; /* usdt0 won't be auto-attached */ - opts.usdt_cookie = 0xcafedeadbeeffeed; + opts.usdt_cookie = expected_cookie; skel->links.usdt0 = bpf_program__attach_usdt(skel->progs.usdt0, 0 /*self*/, "/proc/self/exe", "test", "usdt0", &opts); if (!ASSERT_OK_PTR(skel->links.usdt0, "usdt0_link")) goto cleanup; - trigger_func(1); +#if defined(__x86_64__) || defined(__i386__) + opts.usdt_cookie = expected_cookie; + skel->links.usdt_sib = bpf_program__attach_usdt(skel->progs.usdt_sib, + 0 /*self*/, "/proc/self/exe", + "test", "usdt_sib", &opts); + if (!ASSERT_OK_PTR(skel->links.usdt_sib, "usdt_sib_link")) + goto cleanup; +#endif + + called = TRIGGER(1); - ASSERT_EQ(bss->usdt0_called, 1, "usdt0_called"); - ASSERT_EQ(bss->usdt3_called, 1, "usdt3_called"); - ASSERT_EQ(bss->usdt12_called, 1, "usdt12_called"); + ASSERT_EQ(bss->usdt0_called, called, "usdt0_called"); + ASSERT_EQ(bss->usdt3_called, called, "usdt3_called"); + ASSERT_EQ(bss->usdt12_called, called, "usdt12_called"); - ASSERT_EQ(bss->usdt0_cookie, 0xcafedeadbeeffeed, "usdt0_cookie"); + ASSERT_EQ(bss->usdt0_cookie, expected_cookie, "usdt0_cookie"); ASSERT_EQ(bss->usdt0_arg_cnt, 0, "usdt0_arg_cnt"); ASSERT_EQ(bss->usdt0_arg_ret, -ENOENT, "usdt0_arg_ret"); ASSERT_EQ(bss->usdt0_arg_size, -ENOENT, "usdt0_arg_size"); @@ -119,11 +195,11 @@ static void subtest_basic_usdt(void) * bpf_program__attach_usdt() handles this properly and attaches to * all possible places of USDT invocation. */ - trigger_func(2); + called += TRIGGER(2); - ASSERT_EQ(bss->usdt0_called, 2, "usdt0_called"); - ASSERT_EQ(bss->usdt3_called, 2, "usdt3_called"); - ASSERT_EQ(bss->usdt12_called, 2, "usdt12_called"); + ASSERT_EQ(bss->usdt0_called, called, "usdt0_called"); + ASSERT_EQ(bss->usdt3_called, called, "usdt3_called"); + ASSERT_EQ(bss->usdt12_called, called, "usdt12_called"); /* only check values that depend on trigger_func()'s input value */ ASSERT_EQ(bss->usdt3_args[0], 2, "usdt3_arg1"); @@ -142,9 +218,9 @@ static void subtest_basic_usdt(void) if (!ASSERT_OK_PTR(skel->links.usdt3, "usdt3_reattach")) goto cleanup; - trigger_func(3); + called += TRIGGER(3); - ASSERT_EQ(bss->usdt3_called, 3, "usdt3_called"); + ASSERT_EQ(bss->usdt3_called, called, "usdt3_called"); /* this time usdt3 has custom cookie */ ASSERT_EQ(bss->usdt3_cookie, 0xBADC00C51E, "usdt3_cookie"); ASSERT_EQ(bss->usdt3_arg_cnt, 3, "usdt3_arg_cnt"); @@ -156,8 +232,19 @@ static void subtest_basic_usdt(void) ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2"); ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3"); +#if defined(__x86_64__) || defined(__i386__) + trigger_sib_spec(); + ASSERT_EQ(bss->usdt_sib_called, 1, "usdt_sib_called"); + ASSERT_EQ(bss->usdt_sib_cookie, expected_cookie, "usdt_sib_cookie"); + ASSERT_EQ(bss->usdt_sib_arg_cnt, 1, "usdt_sib_arg_cnt"); + ASSERT_EQ(bss->usdt_sib_arg, nums[0], "usdt_sib_arg"); + ASSERT_EQ(bss->usdt_sib_arg_ret, 0, "usdt_sib_arg_ret"); + ASSERT_EQ(bss->usdt_sib_arg_size, sizeof(nums[0]), "usdt_sib_arg_size"); +#endif + cleanup: test_usdt__destroy(skel); +#undef TRIGGER } unsigned short test_usdt_100_semaphore SEC(".probes"); @@ -270,8 +357,16 @@ static void subtest_multispec_usdt(void) */ trigger_300_usdts(); - /* we'll reuse usdt_100 BPF program for usdt_300 test */ bpf_link__destroy(skel->links.usdt_100); + + bss->usdt_100_called = 0; + bss->usdt_100_sum = 0; + + /* If built with arm64/clang, there will be much less number of specs + * for usdt_300 call sites. + */ +#if !defined(__aarch64__) || !defined(__clang__) + /* we'll reuse usdt_100 BPF program for usdt_300 test */ skel->links.usdt_100 = bpf_program__attach_usdt(skel->progs.usdt_100, -1, "/proc/self/exe", "test", "usdt_300", NULL); err = -errno; @@ -282,13 +377,11 @@ static void subtest_multispec_usdt(void) /* let's check that there are no "dangling" BPF programs attached due * to partial success of the above test:usdt_300 attachment */ - bss->usdt_100_called = 0; - bss->usdt_100_sum = 0; - f300(777); /* this is 301st instance of usdt_300 */ ASSERT_EQ(bss->usdt_100_called, 0, "usdt_301_called"); ASSERT_EQ(bss->usdt_100_sum, 0, "usdt_301_sum"); +#endif /* This time we have USDT with 400 inlined invocations, but arg specs * should be the same across all sites, so libbpf will only need to @@ -419,7 +512,11 @@ cleanup: void test_usdt(void) { if (test__start_subtest("basic")) - subtest_basic_usdt(); + subtest_basic_usdt(false); +#ifdef __x86_64__ + if (test__start_subtest("basic_optimized")) + subtest_basic_usdt(true); +#endif if (test__start_subtest("multispec")) subtest_multispec_usdt(); if (test__start_subtest("urand_auto_attach")) diff --git a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c index d424e7ecbd12..9fd3ae987321 100644 --- a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c @@ -21,8 +21,7 @@ #include "../progs/test_user_ringbuf.h" static const long c_sample_size = sizeof(struct sample) + BPF_RINGBUF_HDR_SZ; -static const long c_ringbuf_size = 1 << 12; /* 1 small page */ -static const long c_max_entries = c_ringbuf_size / c_sample_size; +static long c_ringbuf_size, c_max_entries; static void drain_current_samples(void) { @@ -424,7 +423,9 @@ static void test_user_ringbuf_loop(void) uint32_t remaining_samples = total_samples; int err; - BUILD_BUG_ON(total_samples <= c_max_entries); + if (!ASSERT_LT(c_max_entries, total_samples, "compare_c_max_entries")) + return; + err = load_skel_create_user_ringbuf(&skel, &ringbuf); if (err) return; @@ -686,6 +687,9 @@ void test_user_ringbuf(void) { int i; + c_ringbuf_size = getpagesize(); /* 1 page */ + c_max_entries = c_ringbuf_size / c_sample_size; + for (i = 0; i < ARRAY_SIZE(success_tests); i++) { if (!test__start_subtest(success_tests[i].test_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index c9da06741104..28e81161e6fc 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -46,6 +46,7 @@ #include "verifier_ldsx.skel.h" #include "verifier_leak_ptr.skel.h" #include "verifier_linked_scalars.skel.h" +#include "verifier_live_stack.skel.h" #include "verifier_load_acquire.skel.h" #include "verifier_loops1.skel.h" #include "verifier_lwt.skel.h" @@ -59,6 +60,7 @@ #include "verifier_meta_access.skel.h" #include "verifier_movsx.skel.h" #include "verifier_mtu.skel.h" +#include "verifier_mul.skel.h" #include "verifier_netfilter_ctx.skel.h" #include "verifier_netfilter_retcode.skel.h" #include "verifier_bpf_fastcall.skel.h" @@ -85,6 +87,7 @@ #include "verifier_store_release.skel.h" #include "verifier_subprog_precision.skel.h" #include "verifier_subreg.skel.h" +#include "verifier_tailcall.skel.h" #include "verifier_tailcall_jit.skel.h" #include "verifier_typedef.skel.h" #include "verifier_uninit.skel.h" @@ -182,6 +185,7 @@ void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); } void test_verifier_ldsx(void) { RUN(verifier_ldsx); } void test_verifier_leak_ptr(void) { RUN(verifier_leak_ptr); } void test_verifier_linked_scalars(void) { RUN(verifier_linked_scalars); } +void test_verifier_live_stack(void) { RUN(verifier_live_stack); } void test_verifier_loops1(void) { RUN(verifier_loops1); } void test_verifier_lwt(void) { RUN(verifier_lwt); } void test_verifier_map_in_map(void) { RUN(verifier_map_in_map); } @@ -193,6 +197,7 @@ void test_verifier_may_goto_1(void) { RUN(verifier_may_goto_1); } void test_verifier_may_goto_2(void) { RUN(verifier_may_goto_2); } void test_verifier_meta_access(void) { RUN(verifier_meta_access); } void test_verifier_movsx(void) { RUN(verifier_movsx); } +void test_verifier_mul(void) { RUN(verifier_mul); } void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); } void test_verifier_netfilter_retcode(void) { RUN(verifier_netfilter_retcode); } void test_verifier_bpf_fastcall(void) { RUN(verifier_bpf_fastcall); } @@ -219,6 +224,7 @@ void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } void test_verifier_store_release(void) { RUN(verifier_store_release); } void test_verifier_subprog_precision(void) { RUN(verifier_subprog_precision); } void test_verifier_subreg(void) { RUN(verifier_subreg); } +void test_verifier_tailcall(void) { RUN(verifier_tailcall); } void test_verifier_tailcall_jit(void) { RUN(verifier_tailcall_jit); } void test_verifier_typedef(void) { RUN(verifier_typedef); } void test_verifier_uninit(void) { RUN(verifier_uninit); } diff --git a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c index ab0f02faa80c..4d69d9d55e17 100644 --- a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c @@ -268,7 +268,7 @@ static void test_verify_pkcs7_sig_from_map(void) char *tmp_dir; struct test_verify_pkcs7_sig *skel = NULL; struct bpf_map *map; - struct data data; + struct data data = {}; int ret, zero = 0; /* Trigger creation of session keyring. */ diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index b2b2d85dbb1b..43264347e7d7 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -37,21 +37,26 @@ static void test_xdp_adjust_tail_shrink(void) bpf_object__close(obj); } -static void test_xdp_adjust_tail_grow(void) +static void test_xdp_adjust_tail_grow(bool is_64k_pagesize) { const char *file = "./test_xdp_adjust_tail_grow.bpf.o"; struct bpf_object *obj; - char buf[4096]; /* avoid segfault: large buf to hold grow results */ + char buf[8192]; /* avoid segfault: large buf to hold grow results */ __u32 expect_sz; int err, prog_fd; LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &pkt_v4, - .data_size_in = sizeof(pkt_v4), .data_out = buf, .data_size_out = sizeof(buf), .repeat = 1, ); + /* topts.data_size_in as a special signal to bpf prog */ + if (is_64k_pagesize) + topts.data_size_in = sizeof(pkt_v4) - 1; + else + topts.data_size_in = sizeof(pkt_v4); + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (!ASSERT_OK(err, "test_xdp_adjust_tail_grow")) return; @@ -208,7 +213,7 @@ out: bpf_object__close(obj); } -static void test_xdp_adjust_frags_tail_grow(void) +static void test_xdp_adjust_frags_tail_grow_4k(void) { const char *file = "./test_xdp_adjust_tail_grow.bpf.o"; __u32 exp_size; @@ -246,14 +251,20 @@ static void test_xdp_adjust_frags_tail_grow(void) ASSERT_EQ(topts.retval, XDP_TX, "9Kb+10b retval"); ASSERT_EQ(topts.data_size_out, exp_size, "9Kb+10b size"); - for (i = 0; i < 9000; i++) - ASSERT_EQ(buf[i], 1, "9Kb+10b-old"); + for (i = 0; i < 9000; i++) { + if (buf[i] != 1) + ASSERT_EQ(buf[i], 1, "9Kb+10b-old"); + } - for (i = 9000; i < 9010; i++) - ASSERT_EQ(buf[i], 0, "9Kb+10b-new"); + for (i = 9000; i < 9010; i++) { + if (buf[i] != 0) + ASSERT_EQ(buf[i], 0, "9Kb+10b-new"); + } - for (i = 9010; i < 16384; i++) - ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched"); + for (i = 9010; i < 16384; i++) { + if (buf[i] != 1) + ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched"); + } /* Test a too large grow */ memset(buf, 1, 16384); @@ -273,16 +284,93 @@ out: bpf_object__close(obj); } +static void test_xdp_adjust_frags_tail_grow_64k(void) +{ + const char *file = "./test_xdp_adjust_tail_grow.bpf.o"; + __u32 exp_size; + struct bpf_program *prog; + struct bpf_object *obj; + int err, i, prog_fd; + __u8 *buf; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + goto out; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(262144); + if (!ASSERT_OK_PTR(buf, "alloc buf 256Kb")) + goto out; + + /* Test case add 10 bytes to last frag */ + memset(buf, 1, 262144); + exp_size = 90000 + 10; + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 90000; + topts.data_size_out = 262144; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "90Kb+10b"); + ASSERT_EQ(topts.retval, XDP_TX, "90Kb+10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "90Kb+10b size"); + + for (i = 0; i < 90000; i++) { + if (buf[i] != 1) + ASSERT_EQ(buf[i], 1, "90Kb+10b-old"); + } + + for (i = 90000; i < 90010; i++) { + if (buf[i] != 0) + ASSERT_EQ(buf[i], 0, "90Kb+10b-new"); + } + + for (i = 90010; i < 262144; i++) { + if (buf[i] != 1) + ASSERT_EQ(buf[i], 1, "90Kb+10b-untouched"); + } + + /* Test a too large grow */ + memset(buf, 1, 262144); + exp_size = 90001; + + topts.data_in = topts.data_out = buf; + topts.data_size_in = 90001; + topts.data_size_out = 262144; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "90Kb+10b"); + ASSERT_EQ(topts.retval, XDP_DROP, "90Kb+10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "90Kb+10b size"); + + free(buf); +out: + bpf_object__close(obj); +} + void test_xdp_adjust_tail(void) { + int page_size = getpagesize(); + if (test__start_subtest("xdp_adjust_tail_shrink")) test_xdp_adjust_tail_shrink(); if (test__start_subtest("xdp_adjust_tail_grow")) - test_xdp_adjust_tail_grow(); + test_xdp_adjust_tail_grow(page_size == 65536); if (test__start_subtest("xdp_adjust_tail_grow2")) test_xdp_adjust_tail_grow2(); if (test__start_subtest("xdp_adjust_frags_tail_shrink")) test_xdp_adjust_frags_tail_shrink(); - if (test__start_subtest("xdp_adjust_frags_tail_grow")) - test_xdp_adjust_frags_tail_grow(); + if (test__start_subtest("xdp_adjust_frags_tail_grow")) { + if (page_size == 65536) + test_xdp_adjust_frags_tail_grow_64k(); + else + test_xdp_adjust_frags_tail_grow_4k(); + } } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index b9d9f0a502ce..178292d1251a 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -9,6 +9,7 @@ #define TX_NETNS "xdp_context_tx" #define RX_NETNS "xdp_context_rx" #define TAP_NAME "tap0" +#define DUMMY_NAME "dum0" #define TAP_NETNS "xdp_context_tuntap" #define TEST_PAYLOAD_LEN 32 @@ -96,9 +97,7 @@ void test_xdp_context_test_run(void) /* Meta data must be 255 bytes or smaller */ test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0); - /* Total size of data must match data_end - data_meta */ - test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), - sizeof(data) - 1, 0, 0, 0); + /* Total size of data must be data_end - data_meta or larger */ test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), sizeof(data) + 1, 0, 0, 0); @@ -156,15 +155,30 @@ err: return -1; } -static void assert_test_result(struct test_xdp_meta *skel) +static int write_test_packet(int tap_fd) +{ + __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN]; + int n; + + /* The ethernet header doesn't need to be valid for this test */ + memset(packet, 0, sizeof(struct ethhdr)); + memcpy(packet + sizeof(struct ethhdr), test_payload, TEST_PAYLOAD_LEN); + + n = write(tap_fd, packet, sizeof(packet)); + if (!ASSERT_EQ(n, sizeof(packet), "write packet")) + return -1; + + return 0; +} + +static void assert_test_result(const struct bpf_map *result_map) { int err; __u32 map_key = 0; __u8 map_value[TEST_PAYLOAD_LEN]; - err = bpf_map__lookup_elem(skel->maps.test_result, &map_key, - sizeof(map_key), &map_value, - TEST_PAYLOAD_LEN, BPF_ANY); + err = bpf_map__lookup_elem(result_map, &map_key, sizeof(map_key), + &map_value, TEST_PAYLOAD_LEN, BPF_ANY); if (!ASSERT_OK(err, "lookup test_result")) return; @@ -172,6 +186,18 @@ static void assert_test_result(struct test_xdp_meta *skel) "test_result map contains test payload"); } +static bool clear_test_result(struct bpf_map *result_map) +{ + const __u8 v[sizeof(test_payload)] = {}; + const __u32 k = 0; + int err; + + err = bpf_map__update_elem(result_map, &k, sizeof(k), v, sizeof(v), BPF_ANY); + ASSERT_OK(err, "update test_result"); + + return err == 0; +} + void test_xdp_context_veth(void) { LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); @@ -248,7 +274,7 @@ void test_xdp_context_veth(void) if (!ASSERT_OK(ret, "send_test_packet")) goto close; - assert_test_result(skel); + assert_test_result(skel->maps.test_result); close: close_netns(nstoken); @@ -257,17 +283,21 @@ close: netns_free(tx_ns); } -void test_xdp_context_tuntap(void) +static void test_tuntap(struct bpf_program *xdp_prog, + struct bpf_program *tc_prio_1_prog, + struct bpf_program *tc_prio_2_prog, + struct bpf_map *result_map) { LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); struct netns_obj *ns = NULL; - struct test_xdp_meta *skel = NULL; - __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN]; int tap_fd = -1; int tap_ifindex; int ret; + if (!clear_test_result(result_map)) + return; + ns = netns_new(TAP_NETNS, true); if (!ASSERT_OK_PTR(ns, "create and open ns")) return; @@ -278,10 +308,6 @@ void test_xdp_context_tuntap(void) SYS(close, "ip link set dev " TAP_NAME " up"); - skel = test_xdp_meta__open_and_load(); - if (!ASSERT_OK_PTR(skel, "open and load skeleton")) - goto close; - tap_ifindex = if_nametoindex(TAP_NAME); if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex")) goto close; @@ -291,33 +317,175 @@ void test_xdp_context_tuntap(void) if (!ASSERT_OK(ret, "bpf_tc_hook_create")) goto close; - tc_opts.prog_fd = bpf_program__fd(skel->progs.ing_cls); + tc_opts.prog_fd = bpf_program__fd(tc_prio_1_prog); ret = bpf_tc_attach(&tc_hook, &tc_opts); if (!ASSERT_OK(ret, "bpf_tc_attach")) goto close; - ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(skel->progs.ing_xdp), + if (tc_prio_2_prog) { + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 2, + .prog_fd = bpf_program__fd(tc_prio_2_prog)); + + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto close; + } + + ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(xdp_prog), 0, NULL); if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) goto close; - /* The ethernet header is not relevant for this test and doesn't need to - * be meaningful. - */ - struct ethhdr eth = { 0 }; + ret = write_test_packet(tap_fd); + if (!ASSERT_OK(ret, "write_test_packet")) + goto close; - memcpy(packet, ð, sizeof(eth)); - memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN); + assert_test_result(result_map); + +close: + if (tap_fd >= 0) + close(tap_fd); + netns_free(ns); +} + +/* Write a packet to a tap dev and copy it to ingress of a dummy dev */ +static void test_tuntap_mirred(struct bpf_program *xdp_prog, + struct bpf_program *tc_prog, + bool *test_pass) +{ + LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); + LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); + struct netns_obj *ns = NULL; + int dummy_ifindex; + int tap_fd = -1; + int tap_ifindex; + int ret; + + *test_pass = false; + + ns = netns_new(TAP_NETNS, true); + if (!ASSERT_OK_PTR(ns, "netns_new")) + return; - ret = write(tap_fd, packet, sizeof(packet)); - if (!ASSERT_EQ(ret, sizeof(packet), "write packet")) + /* Setup dummy interface */ + SYS(close, "ip link add name " DUMMY_NAME " type dummy"); + SYS(close, "ip link set dev " DUMMY_NAME " up"); + + dummy_ifindex = if_nametoindex(DUMMY_NAME); + if (!ASSERT_GE(dummy_ifindex, 0, "if_nametoindex")) goto close; - assert_test_result(skel); + tc_hook.ifindex = dummy_ifindex; + ret = bpf_tc_hook_create(&tc_hook); + if (!ASSERT_OK(ret, "bpf_tc_hook_create")) + goto close; + + tc_opts.prog_fd = bpf_program__fd(tc_prog); + ret = bpf_tc_attach(&tc_hook, &tc_opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + goto close; + + /* Setup TAP interface */ + tap_fd = open_tuntap(TAP_NAME, true); + if (!ASSERT_GE(tap_fd, 0, "open_tuntap")) + goto close; + + SYS(close, "ip link set dev " TAP_NAME " up"); + + tap_ifindex = if_nametoindex(TAP_NAME); + if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex")) + goto close; + + ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(xdp_prog), 0, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) + goto close; + + /* Copy all packets received from TAP to dummy ingress */ + SYS(close, "tc qdisc add dev " TAP_NAME " clsact"); + SYS(close, "tc filter add dev " TAP_NAME " ingress " + "protocol all matchall " + "action mirred ingress mirror dev " DUMMY_NAME); + + /* Receive a packet on TAP */ + ret = write_test_packet(tap_fd); + if (!ASSERT_OK(ret, "write_test_packet")) + goto close; + + ASSERT_TRUE(*test_pass, "test_pass"); close: if (tap_fd >= 0) close(tap_fd); - test_xdp_meta__destroy(skel); netns_free(ns); } + +void test_xdp_context_tuntap(void) +{ + struct test_xdp_meta *skel = NULL; + + skel = test_xdp_meta__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open and load skeleton")) + return; + + if (test__start_subtest("data_meta")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.ing_cls, + NULL, /* tc prio 2 */ + skel->maps.test_result); + if (test__start_subtest("dynptr_read")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.ing_cls_dynptr_read, + NULL, /* tc prio 2 */ + skel->maps.test_result); + if (test__start_subtest("dynptr_slice")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.ing_cls_dynptr_slice, + NULL, /* tc prio 2 */ + skel->maps.test_result); + if (test__start_subtest("dynptr_write")) + test_tuntap(skel->progs.ing_xdp_zalloc_meta, + skel->progs.ing_cls_dynptr_write, + skel->progs.ing_cls_dynptr_read, + skel->maps.test_result); + if (test__start_subtest("dynptr_slice_rdwr")) + test_tuntap(skel->progs.ing_xdp_zalloc_meta, + skel->progs.ing_cls_dynptr_slice_rdwr, + skel->progs.ing_cls_dynptr_slice, + skel->maps.test_result); + if (test__start_subtest("dynptr_offset")) + test_tuntap(skel->progs.ing_xdp_zalloc_meta, + skel->progs.ing_cls_dynptr_offset_wr, + skel->progs.ing_cls_dynptr_offset_rd, + skel->maps.test_result); + if (test__start_subtest("dynptr_offset_oob")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.ing_cls_dynptr_offset_oob, + skel->progs.ing_cls, + skel->maps.test_result); + if (test__start_subtest("clone_data_meta_empty_on_data_write")) + test_tuntap_mirred(skel->progs.ing_xdp, + skel->progs.clone_data_meta_empty_on_data_write, + &skel->bss->test_pass); + if (test__start_subtest("clone_data_meta_empty_on_meta_write")) + test_tuntap_mirred(skel->progs.ing_xdp, + skel->progs.clone_data_meta_empty_on_meta_write, + &skel->bss->test_pass); + if (test__start_subtest("clone_dynptr_empty_on_data_slice_write")) + test_tuntap_mirred(skel->progs.ing_xdp, + skel->progs.clone_dynptr_empty_on_data_slice_write, + &skel->bss->test_pass); + if (test__start_subtest("clone_dynptr_empty_on_meta_slice_write")) + test_tuntap_mirred(skel->progs.ing_xdp, + skel->progs.clone_dynptr_empty_on_meta_slice_write, + &skel->bss->test_pass); + if (test__start_subtest("clone_dynptr_rdonly_before_data_dynptr_write")) + test_tuntap_mirred(skel->progs.ing_xdp, + skel->progs.clone_dynptr_rdonly_before_data_dynptr_write, + &skel->bss->test_pass); + if (test__start_subtest("clone_dynptr_rdonly_before_meta_dynptr_write")) + test_tuntap_mirred(skel->progs.ing_xdp, + skel->progs.clone_dynptr_rdonly_before_meta_dynptr_write, + &skel->bss->test_pass); + + test_xdp_meta__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index 461ab18705d5..a8ab05216c38 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -7,6 +7,7 @@ #include <test_progs.h> #include "test_xdp_devmap_helpers.skel.h" +#include "test_xdp_devmap_tailcall.skel.h" #include "test_xdp_with_devmap_frags_helpers.skel.h" #include "test_xdp_with_devmap_helpers.skel.h" @@ -107,6 +108,29 @@ static void test_neg_xdp_devmap_helpers(void) } } +static void test_xdp_devmap_tailcall(enum bpf_attach_type prog_dev, + enum bpf_attach_type prog_tail, + bool expect_reject) +{ + struct test_xdp_devmap_tailcall *skel; + int err; + + skel = test_xdp_devmap_tailcall__open(); + if (!ASSERT_OK_PTR(skel, "test_xdp_devmap_tailcall__open")) + return; + + bpf_program__set_expected_attach_type(skel->progs.xdp_devmap, prog_dev); + bpf_program__set_expected_attach_type(skel->progs.xdp_entry, prog_tail); + + err = test_xdp_devmap_tailcall__load(skel); + if (expect_reject) + ASSERT_ERR(err, "test_xdp_devmap_tailcall__load"); + else + ASSERT_OK(err, "test_xdp_devmap_tailcall__load"); + + test_xdp_devmap_tailcall__destroy(skel); +} + static void test_xdp_with_devmap_frags_helpers(void) { struct test_xdp_with_devmap_frags_helpers *skel; @@ -238,8 +262,13 @@ void serial_test_xdp_devmap_attach(void) if (test__start_subtest("DEVMAP with frags programs in entries")) test_xdp_with_devmap_frags_helpers(); - if (test__start_subtest("Verifier check of DEVMAP programs")) + if (test__start_subtest("Verifier check of DEVMAP programs")) { test_neg_xdp_devmap_helpers(); + test_xdp_devmap_tailcall(BPF_XDP_DEVMAP, BPF_XDP_DEVMAP, false); + test_xdp_devmap_tailcall(0, 0, true); + test_xdp_devmap_tailcall(BPF_XDP_DEVMAP, 0, true); + test_xdp_devmap_tailcall(0, BPF_XDP_DEVMAP, true); + } if (test__start_subtest("DEVMAP with programs in entries on veth")) test_xdp_with_devmap_helpers_veth(); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index 7dac044664ac..dd34b0cc4b4e 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -66,16 +66,25 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int fd) #else #define MAX_PKT_SIZE 3408 #endif + +#define PAGE_SIZE_4K 4096 +#define PAGE_SIZE_64K 65536 + static void test_max_pkt_size(int fd) { - char data[MAX_PKT_SIZE + 1] = {}; + char data[PAGE_SIZE_64K + 1] = {}; int err; DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = MAX_PKT_SIZE, .flags = BPF_F_TEST_XDP_LIVE_FRAMES, .repeat = 1, ); + + if (getpagesize() == PAGE_SIZE_64K) + opts.data_size_in = MAX_PKT_SIZE + PAGE_SIZE_64K - PAGE_SIZE_4K; + else + opts.data_size_in = MAX_PKT_SIZE; + err = bpf_prog_test_run_opts(fd, &opts); ASSERT_OK(err, "prog_run_max_size"); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c b/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c new file mode 100644 index 000000000000..efa350d04ec5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include <network_helpers.h> +#include "test_xdp_pull_data.skel.h" + +#define PULL_MAX (1 << 31) +#define PULL_PLUS_ONE (1 << 30) + +#define XDP_PACKET_HEADROOM 256 + +/* Find headroom and tailroom occupied by struct xdp_frame and struct + * skb_shared_info so that we can calculate the maximum pull lengths for + * test cases. They might not be the real size of the structures due to + * cache alignment. + */ +static int find_xdp_sizes(struct test_xdp_pull_data *skel, int frame_sz) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct xdp_md ctx = {}; + int prog_fd, err; + __u8 *buf; + + buf = calloc(frame_sz, sizeof(__u8)); + if (!ASSERT_OK_PTR(buf, "calloc buf")) + return -ENOMEM; + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = frame_sz; + topts.data_size_out = frame_sz; + /* Pass a data_end larger than the linear space available to make sure + * bpf_prog_test_run_xdp() will fill the linear data area so that + * xdp_find_sizes can infer the size of struct skb_shared_info + */ + ctx.data_end = frame_sz; + topts.ctx_in = &ctx; + topts.ctx_out = &ctx; + topts.ctx_size_in = sizeof(ctx); + topts.ctx_size_out = sizeof(ctx); + + prog_fd = bpf_program__fd(skel->progs.xdp_find_sizes); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "bpf_prog_test_run_opts"); + + free(buf); + + return err; +} + +/* xdp_pull_data_prog will directly read a marker 0xbb stored at buf[1024] + * so caller expecting XDP_PASS should always pass pull_len no less than 1024 + */ +static void run_test(struct test_xdp_pull_data *skel, int retval, + int frame_sz, int buff_len, int meta_len, int data_len, + int pull_len) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct xdp_md ctx = {}; + int prog_fd, err; + __u8 *buf; + + buf = calloc(buff_len, sizeof(__u8)); + if (!ASSERT_OK_PTR(buf, "calloc buf")) + return; + + buf[meta_len + 1023] = 0xaa; + buf[meta_len + 1024] = 0xbb; + buf[meta_len + 1025] = 0xcc; + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = buff_len; + topts.data_size_out = buff_len; + ctx.data = meta_len; + ctx.data_end = meta_len + data_len; + topts.ctx_in = &ctx; + topts.ctx_out = &ctx; + topts.ctx_size_in = sizeof(ctx); + topts.ctx_size_out = sizeof(ctx); + + skel->bss->data_len = data_len; + if (pull_len & PULL_MAX) { + int headroom = XDP_PACKET_HEADROOM - meta_len - skel->bss->xdpf_sz; + int tailroom = frame_sz - XDP_PACKET_HEADROOM - + data_len - skel->bss->sinfo_sz; + + pull_len = pull_len & PULL_PLUS_ONE ? 1 : 0; + pull_len += headroom + tailroom + data_len; + } + skel->bss->pull_len = pull_len; + + prog_fd = bpf_program__fd(skel->progs.xdp_pull_data_prog); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "bpf_prog_test_run_opts"); + ASSERT_EQ(topts.retval, retval, "xdp_pull_data_prog retval"); + + if (retval == XDP_DROP) + goto out; + + ASSERT_EQ(ctx.data_end, meta_len + pull_len, "linear data size"); + ASSERT_EQ(topts.data_size_out, buff_len, "linear + non-linear data size"); + /* Make sure data around xdp->data_end was not messed up by + * bpf_xdp_pull_data() + */ + ASSERT_EQ(buf[meta_len + 1023], 0xaa, "data[1023]"); + ASSERT_EQ(buf[meta_len + 1024], 0xbb, "data[1024]"); + ASSERT_EQ(buf[meta_len + 1025], 0xcc, "data[1025]"); +out: + free(buf); +} + +static void test_xdp_pull_data_basic(void) +{ + u32 pg_sz, max_meta_len, max_data_len; + struct test_xdp_pull_data *skel; + + skel = test_xdp_pull_data__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_pull_data__open_and_load")) + return; + + pg_sz = sysconf(_SC_PAGE_SIZE); + + if (find_xdp_sizes(skel, pg_sz)) + goto out; + + max_meta_len = XDP_PACKET_HEADROOM - skel->bss->xdpf_sz; + max_data_len = pg_sz - XDP_PACKET_HEADROOM - skel->bss->sinfo_sz; + + /* linear xdp pkt, pull 0 byte */ + run_test(skel, XDP_PASS, pg_sz, 2048, 0, 2048, 2048); + + /* multi-buf pkt, pull results in linear xdp pkt */ + run_test(skel, XDP_PASS, pg_sz, 2048, 0, 1024, 2048); + + /* multi-buf pkt, pull 1 byte to linear data area */ + run_test(skel, XDP_PASS, pg_sz, 9000, 0, 1024, 1025); + + /* multi-buf pkt, pull 0 byte to linear data area */ + run_test(skel, XDP_PASS, pg_sz, 9000, 0, 1025, 1025); + + /* multi-buf pkt, empty linear data area, pull requires memmove */ + run_test(skel, XDP_PASS, pg_sz, 9000, 0, 0, PULL_MAX); + + /* multi-buf pkt, no headroom */ + run_test(skel, XDP_PASS, pg_sz, 9000, max_meta_len, 1024, PULL_MAX); + + /* multi-buf pkt, no tailroom, pull requires memmove */ + run_test(skel, XDP_PASS, pg_sz, 9000, 0, max_data_len, PULL_MAX); + + /* Test cases with invalid pull length */ + + /* linear xdp pkt, pull more than total data len */ + run_test(skel, XDP_DROP, pg_sz, 2048, 0, 2048, 2049); + + /* multi-buf pkt with no space left in linear data area */ + run_test(skel, XDP_DROP, pg_sz, 9000, max_meta_len, max_data_len, + PULL_MAX | PULL_PLUS_ONE); + + /* multi-buf pkt, empty linear data area */ + run_test(skel, XDP_DROP, pg_sz, 9000, 0, 0, PULL_MAX | PULL_PLUS_ONE); + + /* multi-buf pkt, no headroom */ + run_test(skel, XDP_DROP, pg_sz, 9000, max_meta_len, 1024, + PULL_MAX | PULL_PLUS_ONE); + + /* multi-buf pkt, no tailroom */ + run_test(skel, XDP_DROP, pg_sz, 9000, 0, max_data_len, + PULL_MAX | PULL_PLUS_ONE); + +out: + test_xdp_pull_data__destroy(skel); +} + +void test_xdp_pull_data(void) +{ + if (test__start_subtest("xdp_pull_data")) + test_xdp_pull_data_basic(); +} diff --git a/tools/testing/selftests/bpf/progs/arena_atomics.c b/tools/testing/selftests/bpf/progs/arena_atomics.c index a52feff98112..d1841aac94a2 100644 --- a/tools/testing/selftests/bpf/progs/arena_atomics.c +++ b/tools/testing/selftests/bpf/progs/arena_atomics.c @@ -28,7 +28,8 @@ bool skip_all_tests = true; #if defined(ENABLE_ATOMICS_TESTS) && \ defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \ - (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) + (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) bool skip_lacq_srel_tests __attribute((__section__(".data"))) = false; #else bool skip_lacq_srel_tests = true; @@ -314,7 +315,8 @@ int load_acquire(const void *ctx) { #if defined(ENABLE_ATOMICS_TESTS) && \ defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \ - (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) + (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) #define LOAD_ACQUIRE_ARENA(SIZEOP, SIZE, SRC, DST) \ { asm volatile ( \ @@ -365,7 +367,8 @@ int store_release(const void *ctx) { #if defined(ENABLE_ATOMICS_TESTS) && \ defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \ - (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) + (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) #define STORE_RELEASE_ARENA(SIZEOP, DST, VAL) \ { asm volatile ( \ diff --git a/tools/testing/selftests/bpf/progs/arena_spin_lock.c b/tools/testing/selftests/bpf/progs/arena_spin_lock.c index c4500c37f85e..086b57a426cf 100644 --- a/tools/testing/selftests/bpf/progs/arena_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/arena_spin_lock.c @@ -37,8 +37,11 @@ int prog(void *ctx) #if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST) unsigned long flags; - if ((ret = arena_spin_lock_irqsave(&lock, flags))) + if ((ret = arena_spin_lock_irqsave(&lock, flags))) { + if (ret == -EOPNOTSUPP) + test_skip = 3; return ret; + } if (counter != limit) counter++; bpf_repeat(cs_count); diff --git a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h index d67466c1ff77..f90531cf3ee5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h +++ b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h @@ -302,7 +302,7 @@ int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val * barriers. */ if (val & _Q_LOCKED_MASK) - smp_cond_load_acquire_label(&lock->locked, !VAL, release_err); + (void)smp_cond_load_acquire_label(&lock->locked, !VAL, release_err); /* * take ownership and clear the pending bit. @@ -380,7 +380,7 @@ queue: /* Link @node into the waitqueue. */ WRITE_ONCE(prev->next, node); - arch_mcs_spin_lock_contended_label(&node->locked, release_node_err); + (void)arch_mcs_spin_lock_contended_label(&node->locked, release_node_err); /* * While waiting for the MCS lock, the next pointer may have diff --git a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c index 1654a530aa3d..4e51785e7606 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c @@ -101,7 +101,7 @@ static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, tp->snd_cwnd = pkts_in_flight + sndcnt; } -/* Decide wheather to run the increase function of congestion control. */ +/* Decide whether to run the increase function of congestion control. */ static bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) { if (tcp_sk(sk)->reordering > TCP_REORDERING) diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c index 7cd73e75f52a..32c511bcd60b 100644 --- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ -/* WARNING: This implemenation is not necessarily the same +/* WARNING: This implementation is not necessarily the same * as the tcp_dctcp.c. The purpose is mainly for testing * the kernel BPF logic. */ diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_map_elem.c b/tools/testing/selftests/bpf/progs/bpf_iter_map_elem.c new file mode 100644 index 000000000000..2f20485e0de3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_map_elem.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +__u32 value_sum = 0; + +SEC("iter/bpf_map_elem") +int dump_bpf_map_values(struct bpf_iter__bpf_map_elem *ctx) +{ + __u32 value = 0; + + if (ctx->value == (void *)0) + return 0; + + bpf_probe_read_kernel(&value, sizeof(value), ctx->value); + value_sum += value; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c index ffbd4b116d17..23b2aa2604de 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c @@ -64,7 +64,8 @@ int dump_udp4(struct bpf_iter__udp *ctx) 0, 0L, 0, ctx->uid, 0, sock_i_ino(&inet->sk), inet->sk.sk_refcnt.refs.counter, udp_sk, - inet->sk.sk_drops.counter); + udp_sk->drop_counters.drops0.counter + + udp_sk->drop_counters.drops1.counter); return 0; } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c index 47ff7754f4fd..c48b05aa2a4b 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c @@ -72,7 +72,7 @@ int dump_udp6(struct bpf_iter__udp *ctx) 0, 0L, 0, ctx->uid, 0, sock_i_ino(&inet->sk), inet->sk.sk_refcnt.refs.counter, udp_sk, - inet->sk.sk_drops.counter); - + udp_sk->drop_counters.drops0.counter + + udp_sk->drop_counters.drops1.counter); return 0; } diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index 6e208e24ba3b..a7a1a684eed1 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -33,7 +33,20 @@ * e.g. "foo{{[0-9]+}}" matches strings like "foo007". * Extended POSIX regular expression syntax is allowed * inside the brackets. + * __not_msg Message not expected to be found in verifier log. + * If __msg_not is situated between __msg tags + * framework matches __msg tags first, and then + * checks that __msg_not is not present in a portion of + * a log between bracketing __msg tags. + * Same regex syntax as for __msg is supported. * __msg_unpriv Same as __msg but for unprivileged mode. + * __not_msg_unpriv Same as __not_msg but for unprivileged mode. + * + * __stderr Message expected to be found in bpf stderr stream. The + * same regex rules apply like __msg. + * __stderr_unpriv Same as __stderr but for unpriveleged mode. + * __stdout Same as __stderr but for stdout stream. + * __stdout_unpriv Same as __stdout but for unpriveleged mode. * * __xlated Expect a line in a disassembly log after verifier applies rewrites. * Multiple __xlated attributes could be specified. @@ -83,9 +96,11 @@ * expect return value to match passed parameter: * - a decimal number * - a hexadecimal number, when starts from 0x - * - literal INT_MIN - * - literal POINTER_VALUE (see definition below) - * - literal TEST_DATA_LEN (see definition below) + * - a macro which expands to one of the above + * - literal _INT_MIN (expands to INT_MIN) + * In addition, two special macros are defined below: + * - POINTER_VALUE + * - TEST_DATA_LEN * __retval_unpriv Same, but load program in unprivileged mode. * * __description Text to be used instead of a program name for display @@ -113,20 +128,22 @@ * __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 __not_msg(msg) __attribute__((btf_decl_tag("comment:test_expect_not_msg=" XSTR(__COUNTER__) "=" msg))) #define __xlated(msg) __attribute__((btf_decl_tag("comment:test_expect_xlated=" XSTR(__COUNTER__) "=" msg))) #define __jited(msg) __attribute__((btf_decl_tag("comment:test_jited=" XSTR(__COUNTER__) "=" msg))) #define __failure __attribute__((btf_decl_tag("comment:test_expect_failure"))) #define __success __attribute__((btf_decl_tag("comment:test_expect_success"))) #define __description(desc) __attribute__((btf_decl_tag("comment:test_description=" desc))) #define __msg_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_msg_unpriv=" XSTR(__COUNTER__) "=" msg))) +#define __not_msg_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_not_msg_unpriv=" XSTR(__COUNTER__) "=" msg))) #define __xlated_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_xlated_unpriv=" XSTR(__COUNTER__) "=" msg))) #define __jited_unpriv(msg) __attribute__((btf_decl_tag("comment:test_jited=" XSTR(__COUNTER__) "=" msg))) #define __failure_unpriv __attribute__((btf_decl_tag("comment:test_expect_failure_unpriv"))) #define __success_unpriv __attribute__((btf_decl_tag("comment:test_expect_success_unpriv"))) #define __log_level(lvl) __attribute__((btf_decl_tag("comment:test_log_level="#lvl))) #define __flag(flag) __attribute__((btf_decl_tag("comment:test_prog_flags="#flag))) -#define __retval(val) __attribute__((btf_decl_tag("comment:test_retval="#val))) -#define __retval_unpriv(val) __attribute__((btf_decl_tag("comment:test_retval_unpriv="#val))) +#define __retval(val) __attribute__((btf_decl_tag("comment:test_retval="XSTR(val)))) +#define __retval_unpriv(val) __attribute__((btf_decl_tag("comment:test_retval_unpriv="XSTR(val)))) #define __auxiliary __attribute__((btf_decl_tag("comment:test_auxiliary"))) #define __auxiliary_unpriv __attribute__((btf_decl_tag("comment:test_auxiliary_unpriv"))) #define __btf_path(path) __attribute__((btf_decl_tag("comment:test_btf_path=" path))) @@ -134,9 +151,14 @@ #define __arch_x86_64 __arch("X86_64") #define __arch_arm64 __arch("ARM64") #define __arch_riscv64 __arch("RISCV64") +#define __arch_s390x __arch("s390x") #define __caps_unpriv(caps) __attribute__((btf_decl_tag("comment:test_caps_unpriv=" EXPAND_QUOTE(caps)))) #define __load_if_JITed() __attribute__((btf_decl_tag("comment:load_mode=jited"))) #define __load_if_no_JITed() __attribute__((btf_decl_tag("comment:load_mode=no_jited"))) +#define __stderr(msg) __attribute__((btf_decl_tag("comment:test_expect_stderr=" XSTR(__COUNTER__) "=" msg))) +#define __stderr_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_stderr_unpriv=" XSTR(__COUNTER__) "=" msg))) +#define __stdout(msg) __attribute__((btf_decl_tag("comment:test_expect_stdout=" XSTR(__COUNTER__) "=" msg))) +#define __stdout_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_stdout_unpriv=" XSTR(__COUNTER__) "=" msg))) /* Define common capabilities tested using __caps_unpriv */ #define CAP_NET_ADMIN 12 @@ -154,8 +176,12 @@ #define __imm_ptr(name) [name]"r"(&name) #define __imm_insn(name, expr) [name]"i"(*(long *)&(expr)) +#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) + /* Magic constants used with __retval() */ -#define POINTER_VALUE 0xcafe4all +#define POINTER_VALUE 0xbadcafe #define TEST_DATA_LEN 64 #ifndef __used @@ -227,8 +253,17 @@ #if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \ (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ - (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) || \ + (defined(__TARGET_ARCH_powerpc)) #define CAN_USE_LOAD_ACQ_STORE_REL #endif +#if defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) +#define SPEC_V1 +#endif + +#if defined(__TARGET_ARCH_x86) +#define SPEC_V4 +#endif + #endif diff --git a/tools/testing/selftests/bpf/progs/bpf_test_utils.h b/tools/testing/selftests/bpf/progs/bpf_test_utils.h new file mode 100644 index 000000000000..f4e67b492dd2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_test_utils.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BPF_TEST_UTILS_H__ +#define __BPF_TEST_UTILS_H__ + +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +/* Clobber as many native registers and stack slots as possible. */ +static __always_inline void clobber_regs_stack(void) +{ + char tmp_str[] = "123456789"; + unsigned long tmp; + + bpf_strtoul(tmp_str, sizeof(tmp_str), 0, &tmp); + __sink(tmp); +} + +#endif diff --git a/tools/testing/selftests/bpf/progs/cgroup_mprog.c b/tools/testing/selftests/bpf/progs/cgroup_mprog.c new file mode 100644 index 000000000000..6a0ea02c4de2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_mprog.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("cgroup/getsockopt") +int getsockopt_1(struct bpf_sockopt *ctx) +{ + return 1; +} + +SEC("cgroup/getsockopt") +int getsockopt_2(struct bpf_sockopt *ctx) +{ + return 1; +} + +SEC("cgroup/getsockopt") +int getsockopt_3(struct bpf_sockopt *ctx) +{ + return 1; +} + +SEC("cgroup/getsockopt") +int getsockopt_4(struct bpf_sockopt *ctx) +{ + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_read_xattr.c b/tools/testing/selftests/bpf/progs/cgroup_read_xattr.c new file mode 100644 index 000000000000..88e13e17ec9e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_read_xattr.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +char value[16]; + +static __always_inline void read_xattr(struct cgroup *cgroup) +{ + struct bpf_dynptr value_ptr; + + bpf_dynptr_from_mem(value, sizeof(value), 0, &value_ptr); + bpf_cgroup_read_xattr(cgroup, "user.bpf_test", + &value_ptr); +} + +SEC("lsm.s/socket_connect") +__success +int BPF_PROG(trusted_cgroup_ptr_sleepable) +{ + u64 cgrp_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp; + + cgrp = bpf_cgroup_from_id(cgrp_id); + if (!cgrp) + return 0; + + read_xattr(cgrp); + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("lsm/socket_connect") +__success +int BPF_PROG(trusted_cgroup_ptr_non_sleepable) +{ + u64 cgrp_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp; + + cgrp = bpf_cgroup_from_id(cgrp_id); + if (!cgrp) + return 0; + + read_xattr(cgrp); + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("lsm/socket_connect") +__success +int BPF_PROG(use_css_iter_non_sleepable) +{ + u64 cgrp_id = bpf_get_current_cgroup_id(); + struct cgroup_subsys_state *css; + struct cgroup *cgrp; + + cgrp = bpf_cgroup_from_id(cgrp_id); + if (!cgrp) + return 0; + + bpf_for_each(css, css, &cgrp->self, BPF_CGROUP_ITER_ANCESTORS_UP) + read_xattr(css->cgroup); + + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("lsm.s/socket_connect") +__failure __msg("kernel func bpf_iter_css_new requires RCU critical section protection") +int BPF_PROG(use_css_iter_sleepable_missing_rcu_lock) +{ + u64 cgrp_id = bpf_get_current_cgroup_id(); + struct cgroup_subsys_state *css; + struct cgroup *cgrp; + + cgrp = bpf_cgroup_from_id(cgrp_id); + if (!cgrp) + return 0; + + bpf_for_each(css, css, &cgrp->self, BPF_CGROUP_ITER_ANCESTORS_UP) + read_xattr(css->cgroup); + + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("lsm.s/socket_connect") +__success +int BPF_PROG(use_css_iter_sleepable_with_rcu_lock) +{ + u64 cgrp_id = bpf_get_current_cgroup_id(); + struct cgroup_subsys_state *css; + struct cgroup *cgrp; + + bpf_rcu_read_lock(); + cgrp = bpf_cgroup_from_id(cgrp_id); + if (!cgrp) + goto out; + + bpf_for_each(css, css, &cgrp->self, BPF_CGROUP_ITER_ANCESTORS_UP) + read_xattr(css->cgroup); + + bpf_cgroup_release(cgrp); +out: + bpf_rcu_read_unlock(); + return 0; +} + +SEC("lsm/socket_connect") +__success +int BPF_PROG(use_bpf_cgroup_ancestor) +{ + u64 cgrp_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp, *ancestor; + + cgrp = bpf_cgroup_from_id(cgrp_id); + if (!cgrp) + return 0; + + ancestor = bpf_cgroup_ancestor(cgrp, 1); + if (!ancestor) + goto out; + + read_xattr(cgrp); + bpf_cgroup_release(ancestor); +out: + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("cgroup/sendmsg4") +__success +int BPF_PROG(cgroup_skb) +{ + u64 cgrp_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp, *ancestor; + + cgrp = bpf_cgroup_from_id(cgrp_id); + if (!cgrp) + return 0; + + ancestor = bpf_cgroup_ancestor(cgrp, 1); + if (!ancestor) + goto out; + + read_xattr(cgrp); + bpf_cgroup_release(ancestor); +out: + bpf_cgroup_release(cgrp); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c index 5354455a01be..02d8f160ca0e 100644 --- a/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c +++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c @@ -221,3 +221,15 @@ int BPF_PROG(test_cgrp_from_id, struct cgroup *cgrp, const char *path) return 0; } + +SEC("syscall") +int test_cgrp_from_id_ns(void *ctx) +{ + struct cgroup *cg; + + cg = bpf_cgroup_from_id(1); + if (!cg) + return 42; + bpf_cgroup_release(cg); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/compute_live_registers.c b/tools/testing/selftests/bpf/progs/compute_live_registers.c index f3d79aecbf93..6884ab99a421 100644 --- a/tools/testing/selftests/bpf/progs/compute_live_registers.c +++ b/tools/testing/selftests/bpf/progs/compute_live_registers.c @@ -240,6 +240,22 @@ __naked void if2(void) ::: __clobber_all); } +/* Verifier misses that r2 is alive if jset is not handled properly */ +SEC("socket") +__log_level(2) +__msg("2: 012....... (45) if r1 & 0x7 goto pc+1") +__naked void if3_jset_bug(void) +{ + asm volatile ( + "r0 = 1;" + "r2 = 2;" + "if r1 & 0x7 goto +1;" + "exit;" + "r0 = r2;" + "exit;" + ::: __clobber_all); +} + SEC("socket") __log_level(2) __msg("0: .......... (b7) r1 = 0") diff --git a/tools/testing/selftests/bpf/progs/crypto_sanity.c b/tools/testing/selftests/bpf/progs/crypto_sanity.c index 645be6cddf36..dfd8a258f14a 100644 --- a/tools/testing/selftests/bpf/progs/crypto_sanity.c +++ b/tools/testing/selftests/bpf/progs/crypto_sanity.c @@ -14,7 +14,7 @@ unsigned char key[256] = {}; u16 udp_test_port = 7777; u32 authsize, key_len; char algo[128] = {}; -char dst[16] = {}; +char dst[16] = {}, dst_bad[8] = {}; int status; static int skb_dynptr_validate(struct __sk_buff *skb, struct bpf_dynptr *psrc) @@ -59,10 +59,9 @@ int skb_crypto_setup(void *ctx) .authsize = authsize, }; struct bpf_crypto_ctx *cctx; - int err = 0; + int err; status = 0; - if (key_len > 256) { status = -EINVAL; return 0; @@ -70,8 +69,8 @@ int skb_crypto_setup(void *ctx) __builtin_memcpy(¶ms.algo, algo, sizeof(algo)); __builtin_memcpy(¶ms.key, key, sizeof(key)); - cctx = bpf_crypto_ctx_create(¶ms, sizeof(params), &err); + cctx = bpf_crypto_ctx_create(¶ms, sizeof(params), &err); if (!cctx) { status = err; return 0; @@ -80,7 +79,6 @@ int skb_crypto_setup(void *ctx) err = crypto_ctx_insert(cctx); if (err && err != -EEXIST) status = err; - return 0; } @@ -92,6 +90,7 @@ int decrypt_sanity(struct __sk_buff *skb) struct bpf_dynptr psrc, pdst; int err; + status = 0; err = skb_dynptr_validate(skb, &psrc); if (err < 0) { status = err; @@ -110,13 +109,23 @@ int decrypt_sanity(struct __sk_buff *skb) return TC_ACT_SHOT; } - /* dst is a global variable to make testing part easier to check. In real - * production code, a percpu map should be used to store the result. + /* Check also bad case where the dst buffer is smaller than the + * skb's linear section. + */ + bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst); + status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL); + if (!status) + status = -EIO; + if (status != -EINVAL) + goto err; + + /* dst is a global variable to make testing part easier to check. + * In real production code, a percpu map should be used to store + * the result. */ bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst); - status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL); - +err: return TC_ACT_SHOT; } @@ -129,7 +138,6 @@ int encrypt_sanity(struct __sk_buff *skb) int err; status = 0; - err = skb_dynptr_validate(skb, &psrc); if (err < 0) { status = err; @@ -148,13 +156,23 @@ int encrypt_sanity(struct __sk_buff *skb) return TC_ACT_SHOT; } - /* dst is a global variable to make testing part easier to check. In real - * production code, a percpu map should be used to store the result. + /* Check also bad case where the dst buffer is smaller than the + * skb's linear section. + */ + bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst); + status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL); + if (!status) + status = -EIO; + if (status != -EINVAL) + goto err; + + /* dst is a global variable to make testing part easier to check. + * In real production code, a percpu map should be used to store + * the result. */ bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst); - status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL); - +err: return TC_ACT_SHOT; } diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index bd8f15229f5c..dda6a8dada82 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -269,6 +269,26 @@ int data_slice_out_of_bounds_skb(struct __sk_buff *skb) return SK_PASS; } +/* A metadata slice can't be accessed out of bounds */ +SEC("?tc") +__failure __msg("value is outside of the allowed memory range") +int data_slice_out_of_bounds_skb_meta(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + /* this should fail */ + *(md + 1) = 42; + + return SK_PASS; +} + SEC("?raw_tp") __failure __msg("value is outside of the allowed memory range") int data_slice_out_of_bounds_map_value(void *ctx) @@ -1089,6 +1109,26 @@ int skb_invalid_slice_write(struct __sk_buff *skb) return SK_PASS; } +/* bpf_dynptr_slice()s are read-only and cannot be written to */ +SEC("?tc") +__failure __msg("R{{[0-9]+}} cannot write into rdonly_mem") +int skb_meta_invalid_slice_write(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + /* this should fail */ + *md = 42; + + return SK_PASS; +} + /* The read-only data slice is invalidated whenever a helper changes packet data */ SEC("?tc") __failure __msg("invalid mem access 'scalar'") @@ -1192,6 +1232,188 @@ int skb_invalid_data_slice4(struct __sk_buff *skb) return SK_PASS; } +/* Read-only skb data slice is invalidated on write to skb metadata */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int ro_skb_slice_invalid_after_metadata_write(struct __sk_buff *skb) +{ + struct bpf_dynptr data, meta; + __u8 *d; + + bpf_dynptr_from_skb(skb, 0, &data); + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + d = bpf_dynptr_slice(&data, 0, NULL, sizeof(*d)); + if (!d) + return SK_DROP; + + bpf_dynptr_write(&meta, 0, "x", 1, 0); + + /* this should fail */ + val = *d; + + return SK_PASS; +} + +/* Read-write skb data slice is invalidated on write to skb metadata */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int rw_skb_slice_invalid_after_metadata_write(struct __sk_buff *skb) +{ + struct bpf_dynptr data, meta; + __u8 *d; + + bpf_dynptr_from_skb(skb, 0, &data); + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + d = bpf_dynptr_slice_rdwr(&data, 0, NULL, sizeof(*d)); + if (!d) + return SK_DROP; + + bpf_dynptr_write(&meta, 0, "x", 1, 0); + + /* this should fail */ + *d = 42; + + return SK_PASS; +} + +/* Read-only skb metadata slice is invalidated on write to skb data */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int ro_skb_meta_slice_invalid_after_payload_write(struct __sk_buff *skb) +{ + struct bpf_dynptr data, meta; + __u8 *md; + + bpf_dynptr_from_skb(skb, 0, &data); + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + bpf_dynptr_write(&data, 0, "x", 1, 0); + + /* this should fail */ + val = *md; + + return SK_PASS; +} + +/* Read-write skb metadata slice is invalidated on write to skb data slice */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int rw_skb_meta_slice_invalid_after_payload_write(struct __sk_buff *skb) +{ + struct bpf_dynptr data, meta; + __u8 *md; + + bpf_dynptr_from_skb(skb, 0, &data); + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + bpf_dynptr_write(&data, 0, "x", 1, 0); + + /* this should fail */ + *md = 42; + + return SK_PASS; +} + +/* Read-only skb metadata slice is invalidated whenever a helper changes packet data */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int ro_skb_meta_slice_invalid_after_payload_helper(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + val = *md; + + return SK_PASS; +} + +/* Read-write skb metadata slice is invalidated whenever a helper changes packet data */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int rw_skb_meta_slice_invalid_after_payload_helper(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + *md = 42; + + return SK_PASS; +} + +/* Read-only skb metadata slice is invalidated on write to skb metadata */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int ro_skb_meta_slice_invalid_after_metadata_write(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + bpf_dynptr_write(&meta, 0, "x", 1, 0); + + /* this should fail */ + val = *md; + + return SK_PASS; +} + +/* Read-write skb metadata slice is invalidated on write to skb metadata */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int rw_skb_meta_slice_invalid_after_metadata_write(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + + md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + bpf_dynptr_write(&meta, 0, "x", 1, 0); + + /* this should fail */ + *md = 42; + + return SK_PASS; +} + /* The read-only data slice is invalidated whenever a helper changes packet data */ SEC("?xdp") __failure __msg("invalid mem access 'scalar'") @@ -1255,6 +1477,19 @@ int skb_invalid_ctx(void *ctx) return 0; } +/* Only supported prog type can create skb_meta-type dynptrs */ +SEC("?raw_tp") +__failure __msg("calling kernel function bpf_dynptr_from_skb_meta is not allowed") +int skb_meta_invalid_ctx(void *ctx) +{ + struct bpf_dynptr meta; + + /* this should fail */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + + return 0; +} + SEC("fentry/skb_tx_error") __failure __msg("must be referenced or trusted") int BPF_PROG(skb_invalid_ctx_fentry, void *skb) @@ -1665,6 +1900,29 @@ int clone_skb_packet_data(struct __sk_buff *skb) return 0; } +/* A skb clone's metadata slice becomes invalid anytime packet data changes */ +SEC("?tc") +__failure __msg("invalid mem access 'scalar'") +int clone_skb_packet_meta(struct __sk_buff *skb) +{ + struct bpf_dynptr clone, meta; + __u8 *md; + + bpf_dynptr_from_skb_meta(skb, 0, &meta); + bpf_dynptr_clone(&meta, &clone); + md = bpf_dynptr_slice_rdwr(&clone, 0, NULL, sizeof(*md)); + if (!md) + return SK_DROP; + + if (bpf_skb_pull_data(skb, skb->len)) + return SK_DROP; + + /* this should fail */ + *md = 42; + + return 0; +} + /* A xdp clone's data slices should be invalid anytime packet data changes */ SEC("?xdp") __failure __msg("invalid mem access 'scalar'") diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index a0391f9da2d4..127dea342e5a 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -9,6 +9,8 @@ #include "bpf_misc.h" #include "errno.h" +#define PAGE_SIZE_64K 65536 + char _license[] SEC("license") = "GPL"; int pid, err, val; @@ -209,6 +211,61 @@ int test_dynptr_skb_data(struct __sk_buff *skb) return 1; } +SEC("?tc") +int test_dynptr_skb_meta_data(struct __sk_buff *skb) +{ + struct bpf_dynptr meta; + __u8 *md; + int ret; + + err = 1; + ret = bpf_dynptr_from_skb_meta(skb, 0, &meta); + if (ret) + return 1; + + /* This should return NULL. Must use bpf_dynptr_slice API */ + err = 2; + md = bpf_dynptr_data(&meta, 0, sizeof(*md)); + if (md) + return 1; + + err = 0; + return 1; +} + +/* Check that skb metadata dynptr ops don't accept any flags. */ +SEC("?tc") +int test_dynptr_skb_meta_flags(struct __sk_buff *skb) +{ + const __u64 INVALID_FLAGS = ~0ULL; + struct bpf_dynptr meta; + __u8 buf; + int ret; + + err = 1; + ret = bpf_dynptr_from_skb_meta(skb, INVALID_FLAGS, &meta); + if (ret != -EINVAL) + return 1; + + err = 2; + ret = bpf_dynptr_from_skb_meta(skb, 0, &meta); + if (ret) + return 1; + + err = 3; + ret = bpf_dynptr_read(&buf, 0, &meta, 0, INVALID_FLAGS); + if (ret != -EINVAL) + return 1; + + err = 4; + ret = bpf_dynptr_write(&meta, 0, &buf, 0, INVALID_FLAGS); + if (ret != -EINVAL) + return 1; + + err = 0; + return 1; +} + SEC("tp/syscalls/sys_enter_nanosleep") int test_adjust(void *ctx) { @@ -611,11 +668,12 @@ int test_dynptr_copy_xdp(struct xdp_md *xdp) struct bpf_dynptr ptr_buf, ptr_xdp; char data[] = "qwertyuiopasdfghjkl"; char buf[32] = {'\0'}; - __u32 len = sizeof(data); + __u32 len = sizeof(data), xdp_data_size; int i, chunks = 200; /* ptr_xdp is backed by non-contiguous memory */ bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp); + xdp_data_size = bpf_dynptr_size(&ptr_xdp); bpf_ringbuf_reserve_dynptr(&ringbuf, len * chunks, 0, &ptr_buf); /* Destination dynptr is backed by non-contiguous memory */ @@ -673,7 +731,7 @@ int test_dynptr_copy_xdp(struct xdp_md *xdp) goto out; } - if (bpf_dynptr_copy(&ptr_xdp, 2000, &ptr_xdp, 0, len * chunks) != -E2BIG) + if (bpf_dynptr_copy(&ptr_xdp, xdp_data_size - 3000, &ptr_xdp, 0, len * chunks) != -E2BIG) err = 1; out: @@ -681,6 +739,173 @@ out: return XDP_DROP; } +char memset_zero_data[] = "data to be zeroed"; + +SEC("?tp/syscalls/sys_enter_nanosleep") +int test_dynptr_memset_zero(void *ctx) +{ + __u32 data_sz = sizeof(memset_zero_data); + char zeroes[32] = {'\0'}; + struct bpf_dynptr ptr; + + err = bpf_dynptr_from_mem(memset_zero_data, data_sz, 0, &ptr); + err = err ?: bpf_dynptr_memset(&ptr, 0, data_sz, 0); + err = err ?: bpf_memcmp(zeroes, memset_zero_data, data_sz); + + return 0; +} + +#define DYNPTR_MEMSET_VAL 42 + +char memset_notzero_data[] = "data to be overwritten"; + +SEC("?tp/syscalls/sys_enter_nanosleep") +int test_dynptr_memset_notzero(void *ctx) +{ + u32 data_sz = sizeof(memset_notzero_data); + struct bpf_dynptr ptr; + char expected[32]; + + __builtin_memset(expected, DYNPTR_MEMSET_VAL, data_sz); + + err = bpf_dynptr_from_mem(memset_notzero_data, data_sz, 0, &ptr); + err = err ?: bpf_dynptr_memset(&ptr, 0, data_sz, DYNPTR_MEMSET_VAL); + err = err ?: bpf_memcmp(expected, memset_notzero_data, data_sz); + + return 0; +} + +char memset_zero_offset_data[] = "data to be zeroed partially"; + +SEC("?tp/syscalls/sys_enter_nanosleep") +int test_dynptr_memset_zero_offset(void *ctx) +{ + char expected[] = "data to \0\0\0\0eroed partially"; + __u32 data_sz = sizeof(memset_zero_offset_data); + struct bpf_dynptr ptr; + + err = bpf_dynptr_from_mem(memset_zero_offset_data, data_sz, 0, &ptr); + err = err ?: bpf_dynptr_memset(&ptr, 8, 4, 0); + err = err ?: bpf_memcmp(expected, memset_zero_offset_data, data_sz); + + return 0; +} + +char memset_zero_adjusted_data[] = "data to be zeroed partially"; + +SEC("?tp/syscalls/sys_enter_nanosleep") +int test_dynptr_memset_zero_adjusted(void *ctx) +{ + char expected[] = "data\0\0\0\0be zeroed partially"; + __u32 data_sz = sizeof(memset_zero_adjusted_data); + struct bpf_dynptr ptr; + + err = bpf_dynptr_from_mem(memset_zero_adjusted_data, data_sz, 0, &ptr); + err = err ?: bpf_dynptr_adjust(&ptr, 4, 8); + err = err ?: bpf_dynptr_memset(&ptr, 0, bpf_dynptr_size(&ptr), 0); + err = err ?: bpf_memcmp(expected, memset_zero_adjusted_data, data_sz); + + return 0; +} + +char memset_overflow_data[] = "memset overflow data"; + +SEC("?tp/syscalls/sys_enter_nanosleep") +int test_dynptr_memset_overflow(void *ctx) +{ + __u32 data_sz = sizeof(memset_overflow_data); + struct bpf_dynptr ptr; + int ret; + + err = bpf_dynptr_from_mem(memset_overflow_data, data_sz, 0, &ptr); + ret = bpf_dynptr_memset(&ptr, 0, data_sz + 1, 0); + if (ret != -E2BIG) + err = 1; + + return 0; +} + +SEC("?tp/syscalls/sys_enter_nanosleep") +int test_dynptr_memset_overflow_offset(void *ctx) +{ + __u32 data_sz = sizeof(memset_overflow_data); + struct bpf_dynptr ptr; + int ret; + + err = bpf_dynptr_from_mem(memset_overflow_data, data_sz, 0, &ptr); + ret = bpf_dynptr_memset(&ptr, 1, data_sz, 0); + if (ret != -E2BIG) + err = 1; + + return 0; +} + +SEC("?cgroup_skb/egress") +int test_dynptr_memset_readonly(struct __sk_buff *skb) +{ + struct bpf_dynptr ptr; + int ret; + + err = bpf_dynptr_from_skb(skb, 0, &ptr); + + /* cgroup skbs are read only, memset should fail */ + ret = bpf_dynptr_memset(&ptr, 0, bpf_dynptr_size(&ptr), 0); + if (ret != -EINVAL) + err = 1; + + return 0; +} + +#define min_t(type, x, y) ({ \ + type __x = (x); \ + type __y = (y); \ + __x < __y ? __x : __y; }) + +SEC("xdp") +int test_dynptr_memset_xdp_chunks(struct xdp_md *xdp) +{ + u32 data_sz, chunk_sz, offset = 0; + const int max_chunks = 200; + struct bpf_dynptr ptr_xdp; + char expected_buf[32]; + char buf[32]; + int i; + + __builtin_memset(expected_buf, DYNPTR_MEMSET_VAL, sizeof(expected_buf)); + + /* ptr_xdp is backed by non-contiguous memory */ + bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp); + data_sz = bpf_dynptr_size(&ptr_xdp); + + err = bpf_dynptr_memset(&ptr_xdp, 0, data_sz, DYNPTR_MEMSET_VAL); + if (err) { + /* bpf_dynptr_memset() eventually called bpf_xdp_pointer() + * where if data_sz is greater than 0xffff, -EFAULT will be + * returned. For 64K page size, data_sz is greater than + * 64K, so error is expected and let us zero out error and + * return success. + */ + if (data_sz >= PAGE_SIZE_64K) + err = 0; + goto out; + } + + bpf_for(i, 0, max_chunks) { + offset = i * sizeof(buf); + if (offset >= data_sz) + goto out; + chunk_sz = min_t(u32, sizeof(buf), data_sz - offset); + err = bpf_dynptr_read(&buf, chunk_sz, &ptr_xdp, offset, 0); + if (err) + goto out; + err = bpf_memcmp(buf, expected_buf, sizeof(buf)); + if (err) + goto out; + } +out: + return XDP_DROP; +} + void *user_ptr; /* Contains the copy of the data pointed by user_ptr. * Size 384 to make it not fit into a single kernel chunk when copying diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c index 5e0a1ca96d4e..a01c2736890f 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_assert.c +++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c @@ -18,43 +18,43 @@ return *(u64 *)num; \ } -__msg(": R0_w=0xffffffff80000000") +__msg(": R0=0xffffffff80000000") check_assert(s64, ==, eq_int_min, INT_MIN); -__msg(": R0_w=0x7fffffff") +__msg(": R0=0x7fffffff") check_assert(s64, ==, eq_int_max, INT_MAX); -__msg(": R0_w=0") +__msg(": R0=0") check_assert(s64, ==, eq_zero, 0); -__msg(": R0_w=0x8000000000000000 R1_w=0x8000000000000000") +__msg(": R0=0x8000000000000000 R1=0x8000000000000000") check_assert(s64, ==, eq_llong_min, LLONG_MIN); -__msg(": R0_w=0x7fffffffffffffff R1_w=0x7fffffffffffffff") +__msg(": R0=0x7fffffffffffffff R1=0x7fffffffffffffff") check_assert(s64, ==, eq_llong_max, LLONG_MAX); -__msg(": R0_w=scalar(id=1,smax=0x7ffffffe)") +__msg(": R0=scalar(id=1,smax=0x7ffffffe)") check_assert(s64, <, lt_pos, INT_MAX); -__msg(": R0_w=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))") +__msg(": R0=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))") check_assert(s64, <, lt_zero, 0); -__msg(": R0_w=scalar(id=1,smax=0xffffffff7fffffff") +__msg(": R0=scalar(id=1,smax=0xffffffff7fffffff") check_assert(s64, <, lt_neg, INT_MIN); -__msg(": R0_w=scalar(id=1,smax=0x7fffffff)") +__msg(": R0=scalar(id=1,smax=0x7fffffff)") check_assert(s64, <=, le_pos, INT_MAX); -__msg(": R0_w=scalar(id=1,smax=0)") +__msg(": R0=scalar(id=1,smax=0)") check_assert(s64, <=, le_zero, 0); -__msg(": R0_w=scalar(id=1,smax=0xffffffff80000000") +__msg(": R0=scalar(id=1,smax=0xffffffff80000000") check_assert(s64, <=, le_neg, INT_MIN); -__msg(": R0_w=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg(": R0=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >, gt_pos, INT_MAX); -__msg(": R0_w=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg(": R0=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >, gt_zero, 0); -__msg(": R0_w=scalar(id=1,smin=0xffffffff80000001") +__msg(": R0=scalar(id=1,smin=0xffffffff80000001") check_assert(s64, >, gt_neg, INT_MIN); -__msg(": R0_w=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg(": R0=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >=, ge_pos, INT_MAX); -__msg(": R0_w=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") +__msg(": R0=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))") check_assert(s64, >=, ge_zero, 0); -__msg(": R0_w=scalar(id=1,smin=0xffffffff80000000") +__msg(": R0=scalar(id=1,smin=0xffffffff80000000") check_assert(s64, >=, ge_neg, INT_MIN); SEC("?tc") diff --git a/tools/testing/selftests/bpf/progs/fexit_noreturns.c b/tools/testing/selftests/bpf/progs/fexit_noreturns.c deleted file mode 100644 index 54654539f550..000000000000 --- a/tools/testing/selftests/bpf/progs/fexit_noreturns.c +++ /dev/null @@ -1,15 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <linux/bpf.h> -#include <bpf/bpf_helpers.h> -#include <bpf/bpf_tracing.h> -#include "bpf_misc.h" - -char _license[] SEC("license") = "GPL"; - -SEC("fexit/do_exit") -__failure __msg("Attaching fexit/fmod_ret to __noreturn functions is rejected.") -int BPF_PROG(noreturns) -{ - return 0; -} diff --git a/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c b/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c index 544e5ac90461..d09bbd8ae8a8 100644 --- a/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c +++ b/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c @@ -12,7 +12,7 @@ SEC("freplace/connect_v4_prog") int new_connect_v4_prog(struct bpf_sock_addr *ctx) { - // return value thats in invalid range + // return value that's in invalid range return 255; } diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 76adf4a8f2da..7dd92a303bf6 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -1649,4 +1649,281 @@ int clean_live_states(const void *ctx) return 0; } +SEC("?raw_tp") +__flag(BPF_F_TEST_STATE_FREQ) +__failure __msg("misaligned stack access off 0+-31+0 size 8") +__naked int absent_mark_in_the_middle_state(void) +{ + /* This is equivalent to C program below. + * + * r8 = bpf_get_prandom_u32(); + * r6 = -32; + * bpf_iter_num_new(&fp[-8], 0, 10); + * if (unlikely(bpf_get_prandom_u32())) + * r6 = -31; + * while (bpf_iter_num_next(&fp[-8])) { + * if (unlikely(bpf_get_prandom_u32())) + * *(fp + r6) = 7; + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r8 = r0;" + "r7 = 0;" + "r6 = -32;" + "r0 = 0;" + "*(u64 *)(r10 - 16) = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "call %[bpf_get_prandom_u32];" + "if r0 == r8 goto change_r6_%=;" + "loop_%=:" + "call noop;" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 == r8 goto use_r6_%=;" + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + "use_r6_%=:" + "r0 = r10;" + "r0 += r6;" + "r1 = 7;" + "*(u64 *)(r0 + 0) = r1;" + "goto loop_%=;" + "change_r6_%=:" + "r6 = -31;" + "goto loop_%=;" + : + : __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm(bpf_get_prandom_u32) + : __clobber_all + ); +} + +__used __naked +static int noop(void) +{ + asm volatile ( + "r0 = 0;" + "exit;" + ); +} + +SEC("?raw_tp") +__flag(BPF_F_TEST_STATE_FREQ) +__failure __msg("misaligned stack access off 0+-31+0 size 8") +__naked int absent_mark_in_the_middle_state2(void) +{ + /* This is equivalent to C program below. + * + * r8 = bpf_get_prandom_u32(); + * r6 = -32; + * bpf_iter_num_new(&fp[-8], 0, 10); + * if (unlikely(bpf_get_prandom_u32())) { + * r6 = -31; + * jump_into_loop: + * goto +0; + * goto loop; + * } + * if (unlikely(bpf_get_prandom_u32())) + * goto jump_into_loop; + * loop: + * while (bpf_iter_num_next(&fp[-8])) { + * if (unlikely(bpf_get_prandom_u32())) + * *(fp + r6) = 7; + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r8 = r0;" + "r7 = 0;" + "r6 = -32;" + "r0 = 0;" + "*(u64 *)(r10 - 16) = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "call %[bpf_get_prandom_u32];" + "if r0 == r8 goto change_r6_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 == r8 goto jump_into_loop_%=;" + "loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 == r8 goto use_r6_%=;" + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + "use_r6_%=:" + "r0 = r10;" + "r0 += r6;" + "r1 = 7;" + "*(u64 *)(r0 + 0) = r1;" + "goto loop_%=;" + "change_r6_%=:" + "r6 = -31;" + "jump_into_loop_%=: " + "goto +0;" + "goto loop_%=;" + : + : __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm(bpf_get_prandom_u32) + : __clobber_all + ); +} + +SEC("?raw_tp") +__flag(BPF_F_TEST_STATE_FREQ) +__failure __msg("misaligned stack access off 0+-31+0 size 8") +__naked int absent_mark_in_the_middle_state3(void) +{ + /* + * bpf_iter_num_new(&fp[-8], 0, 10) + * loop1(-32, &fp[-8]) + * loop1_wrapper(&fp[-8]) + * bpf_iter_num_destroy(&fp[-8]) + */ + asm volatile ( + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + /* call #1 */ + "r1 = -32;" + "r2 = r10;" + "r2 += -8;" + "call loop1;" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + /* call #2 */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r1 = r10;" + "r1 += -8;" + "call loop1_wrapper;" + /* return */ + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_iter_num_new), + __imm(bpf_iter_num_destroy), + __imm(bpf_get_prandom_u32) + : __clobber_all + ); +} + +__used __naked +static int loop1(void) +{ + /* + * int loop1(num, iter) { + * r6 = num; + * r7 = iter; + * while (bpf_iter_num_next(r7)) { + * if (unlikely(bpf_get_prandom_u32())) + * *(fp + r6) = 7; + * } + * return 0 + * } + */ + asm volatile ( + "r6 = r1;" + "r7 = r2;" + "call %[bpf_get_prandom_u32];" + "r8 = r0;" + "loop_%=:" + "r1 = r7;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 == r8 goto use_r6_%=;" + "goto loop_%=;" + "loop_end_%=:" + "r0 = 0;" + "exit;" + "use_r6_%=:" + "r0 = r10;" + "r0 += r6;" + "r1 = 7;" + "*(u64 *)(r0 + 0) = r1;" + "goto loop_%=;" + : + : __imm(bpf_iter_num_next), + __imm(bpf_get_prandom_u32) + : __clobber_all + ); +} + +__used __naked +static int loop1_wrapper(void) +{ + /* + * int loop1_wrapper(iter) { + * r6 = -32; + * r7 = iter; + * if (unlikely(bpf_get_prandom_u32())) + * r6 = -31; + * loop1(r6, r7); + * return 0; + * } + */ + asm volatile ( + "r6 = -32;" + "r7 = r1;" + "call %[bpf_get_prandom_u32];" + "r8 = r0;" + "call %[bpf_get_prandom_u32];" + "if r0 == r8 goto change_r6_%=;" + "loop_%=:" + "r1 = r6;" + "r2 = r7;" + "call loop1;" + "r0 = 0;" + "exit;" + "change_r6_%=:" + "r6 = -31;" + "goto loop_%=;" + : + : __imm(bpf_iter_num_next), + __imm(bpf_get_prandom_u32) + : __clobber_all + ); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters_state_safety.c b/tools/testing/selftests/bpf/progs/iters_state_safety.c index f41257eadbb2..d273b46dfc7c 100644 --- a/tools/testing/selftests/bpf/progs/iters_state_safety.c +++ b/tools/testing/selftests/bpf/progs/iters_state_safety.c @@ -30,7 +30,7 @@ int force_clang_to_emit_btf_for_externs(void *ctx) SEC("?raw_tp") __success __log_level(2) -__msg("fp-8_w=iter_num(ref_id=1,state=active,depth=0)") +__msg("fp-8=iter_num(ref_id=1,state=active,depth=0)") int create_and_destroy(void *ctx) { struct bpf_iter_num iter; @@ -196,7 +196,7 @@ int leak_iter_from_subprog_fail(void *ctx) SEC("?raw_tp") __success __log_level(2) -__msg("fp-8_w=iter_num(ref_id=1,state=active,depth=0)") +__msg("fp-8=iter_num(ref_id=1,state=active,depth=0)") int valid_stack_reuse(void *ctx) { struct bpf_iter_num iter; @@ -345,7 +345,7 @@ int __naked read_from_iter_slot_fail(void) "r3 = 1000;" "call %[bpf_iter_num_new];" - /* attemp to leak bpf_iter_num state */ + /* attempt to leak bpf_iter_num state */ "r7 = *(u64 *)(r6 + 0);" "r8 = *(u64 *)(r6 + 8);" diff --git a/tools/testing/selftests/bpf/progs/iters_task_failure.c b/tools/testing/selftests/bpf/progs/iters_task_failure.c index 6b1588d70652..fe3663dedbe1 100644 --- a/tools/testing/selftests/bpf/progs/iters_task_failure.c +++ b/tools/testing/selftests/bpf/progs/iters_task_failure.c @@ -15,7 +15,7 @@ void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") -__failure __msg("expected an RCU CS when using bpf_iter_task_next") +__failure __msg("kernel func bpf_iter_task_new requires RCU critical section protection") int BPF_PROG(iter_tasks_without_lock) { struct task_struct *pos; @@ -27,7 +27,7 @@ int BPF_PROG(iter_tasks_without_lock) } SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") -__failure __msg("expected an RCU CS when using bpf_iter_css_next") +__failure __msg("kernel func bpf_iter_css_new requires RCU critical section protection") int BPF_PROG(iter_css_without_lock) { u64 cg_id = bpf_get_current_cgroup_id(); diff --git a/tools/testing/selftests/bpf/progs/iters_testmod.c b/tools/testing/selftests/bpf/progs/iters_testmod.c index 9e4b45201e69..5379e9960ffd 100644 --- a/tools/testing/selftests/bpf/progs/iters_testmod.c +++ b/tools/testing/selftests/bpf/progs/iters_testmod.c @@ -123,3 +123,49 @@ out: bpf_iter_num_destroy(&num_it); return 0; } + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("kernel func bpf_kfunc_ret_rcu_test requires RCU critical section protection") +int iter_ret_rcu_test_protected(const void *ctx) +{ + struct task_struct *p; + + p = bpf_kfunc_ret_rcu_test(); + return p->pid; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("R1 type=rcu_ptr_or_null_ expected=") +int iter_ret_rcu_test_type(const void *ctx) +{ + struct task_struct *p; + + bpf_rcu_read_lock(); + p = bpf_kfunc_ret_rcu_test(); + bpf_this_cpu_ptr(p); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("kernel func bpf_kfunc_ret_rcu_test_nostruct requires RCU critical section protection") +int iter_ret_rcu_test_protected_nostruct(const void *ctx) +{ + void *p; + + p = bpf_kfunc_ret_rcu_test_nostruct(4); + return *(int *)p; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("R1 type=rdonly_rcu_mem_or_null expected=") +int iter_ret_rcu_test_type_nostruct(const void *ctx) +{ + void *p; + + bpf_rcu_read_lock(); + p = bpf_kfunc_ret_rcu_test_nostruct(4); + bpf_this_cpu_ptr(p); + bpf_rcu_read_unlock(); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c index 6543d5b6e0a9..83791348bed5 100644 --- a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c +++ b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c @@ -20,7 +20,7 @@ __s64 res_empty; SEC("raw_tp/sys_enter") __success __log_level(2) -__msg("fp-16_w=iter_testmod_seq(ref_id=1,state=active,depth=0)") +__msg("fp-16=iter_testmod_seq(ref_id=1,state=active,depth=0)") __msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)") __msg("call bpf_iter_testmod_seq_destroy") int testmod_seq_empty(const void *ctx) @@ -38,7 +38,7 @@ __s64 res_full; SEC("raw_tp/sys_enter") __success __log_level(2) -__msg("fp-16_w=iter_testmod_seq(ref_id=1,state=active,depth=0)") +__msg("fp-16=iter_testmod_seq(ref_id=1,state=active,depth=0)") __msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)") __msg("call bpf_iter_testmod_seq_destroy") int testmod_seq_full(const void *ctx) @@ -58,7 +58,7 @@ static volatile int zero = 0; SEC("raw_tp/sys_enter") __success __log_level(2) -__msg("fp-16_w=iter_testmod_seq(ref_id=1,state=active,depth=0)") +__msg("fp-16=iter_testmod_seq(ref_id=1,state=active,depth=0)") __msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)") __msg("call bpf_iter_testmod_seq_destroy") int testmod_seq_truncated(const void *ctx) diff --git a/tools/testing/selftests/bpf/progs/kprobe_write_ctx.c b/tools/testing/selftests/bpf/progs/kprobe_write_ctx.c new file mode 100644 index 000000000000..f77aef0474d3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kprobe_write_ctx.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +#if defined(__TARGET_ARCH_x86) +SEC("kprobe") +int kprobe_write_ctx(struct pt_regs *ctx) +{ + ctx->ax = 0; + return 0; +} + +SEC("kprobe.multi") +int kprobe_multi_write_ctx(struct pt_regs *ctx) +{ + ctx->ax = 0; + return 0; +} +#endif diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c index 6438982b928b..ddd26d1a083f 100644 --- a/tools/testing/selftests/bpf/progs/linked_list_fail.c +++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c @@ -226,8 +226,7 @@ int obj_new_no_composite(void *ctx) SEC("?tc") int obj_new_no_struct(void *ctx) { - - bpf_obj_new(union { int data; unsigned udata; }); + (void)bpf_obj_new(union { int data; unsigned udata; }); return 0; } @@ -252,7 +251,7 @@ int new_null_ret(void *ctx) SEC("?tc") int obj_new_acq(void *ctx) { - bpf_obj_new(struct foo); + (void)bpf_obj_new(struct foo); return 0; } diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c index 50e66772c046..b0fa26fb4760 100644 --- a/tools/testing/selftests/bpf/progs/loop1.c +++ b/tools/testing/selftests/bpf/progs/loop1.c @@ -1,11 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook -#include <linux/sched.h> -#include <linux/ptrace.h> -#include <stdint.h> -#include <stddef.h> -#include <stdbool.h> -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c index 947bb7e988c2..0227409d4b0e 100644 --- a/tools/testing/selftests/bpf/progs/loop2.c +++ b/tools/testing/selftests/bpf/progs/loop2.c @@ -1,11 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook -#include <linux/sched.h> -#include <linux/ptrace.h> -#include <stdint.h> -#include <stddef.h> -#include <stdbool.h> -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c index 717dab14322b..5d1c9a775e6b 100644 --- a/tools/testing/selftests/bpf/progs/loop3.c +++ b/tools/testing/selftests/bpf/progs/loop3.c @@ -1,11 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook -#include <linux/sched.h> -#include <linux/ptrace.h> -#include <stdint.h> -#include <stddef.h> -#include <stdbool.h> -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> diff --git a/tools/testing/selftests/bpf/progs/loop6.c b/tools/testing/selftests/bpf/progs/loop6.c index e4ff97fbcce1..dd36aff4fba3 100644 --- a/tools/testing/selftests/bpf/progs/loop6.c +++ b/tools/testing/selftests/bpf/progs/loop6.c @@ -1,8 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/ptrace.h> -#include <stddef.h> -#include <linux/bpf.h> +#include <vmlinux.h> +#include <bpf/bpf_core_read.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" @@ -26,12 +25,6 @@ char _license[] SEC("license") = "GPL"; #define SG_CHAIN 0x01UL #define SG_END 0x02UL -struct scatterlist { - unsigned long page_link; - unsigned int offset; - unsigned int length; -}; - #define sg_is_chain(sg) ((sg)->page_link & SG_CHAIN) #define sg_is_last(sg) ((sg)->page_link & SG_END) #define sg_chain_ptr(sg) \ @@ -62,7 +55,7 @@ static inline struct scatterlist *get_sgp(struct scatterlist **sgs, int i) return sgp; } -int config = 0; +int run_once = 0; int result = 0; SEC("kprobe/virtqueue_add_sgs") @@ -73,14 +66,14 @@ int BPF_KPROBE(trace_virtqueue_add_sgs, void *unused, struct scatterlist **sgs, __u64 length1 = 0, length2 = 0; unsigned int i, n, len; - if (config != 0) + if (run_once != 0) return 0; for (i = 0; (i < VIRTIO_MAX_SGS) && (i < out_sgs); i++) { __sink(out_sgs); for (n = 0, sgp = get_sgp(sgs, i); sgp && (n < SG_MAX); sgp = __sg_next(sgp)) { - bpf_probe_read_kernel(&len, sizeof(len), &sgp->length); + len = BPF_CORE_READ(sgp, length); length1 += len; n++; } @@ -90,13 +83,13 @@ int BPF_KPROBE(trace_virtqueue_add_sgs, void *unused, struct scatterlist **sgs, __sink(in_sgs); for (n = 0, sgp = get_sgp(sgs, i); sgp && (n < SG_MAX); sgp = __sg_next(sgp)) { - bpf_probe_read_kernel(&len, sizeof(len), &sgp->length); + len = BPF_CORE_READ(sgp, length); length2 += len; n++; } } - config = 1; + run_once = 1; result = length2 - length1; return 0; } diff --git a/tools/testing/selftests/bpf/progs/lpm_trie.h b/tools/testing/selftests/bpf/progs/lpm_trie.h new file mode 100644 index 000000000000..76aa5821807f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lpm_trie.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __PROGS_LPM_TRIE_H +#define __PROGS_LPM_TRIE_H + +struct trie_key { + __u32 prefixlen; + __u32 data; +}; + +/* Benchmark operations */ +enum { + LPM_OP_NOOP = 0, + LPM_OP_BASELINE, + LPM_OP_LOOKUP, + LPM_OP_INSERT, + LPM_OP_UPDATE, + LPM_OP_DELETE, + LPM_OP_FREE +}; + +/* + * Return values from run_bench. + * + * Negative values are also allowed and represent kernel error codes. + */ +#define LPM_BENCH_SUCCESS 0 +#define LPM_BENCH_REINIT_MAP 1 /* Reset trie to initial state for current op */ + +#endif diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_bench.c b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c new file mode 100644 index 000000000000..a0e6ebd5507a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Cloudflare */ + +#include <vmlinux.h> +#include <errno.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" +#include "bpf_atomic.h" +#include "progs/lpm_trie.h" + +#define BPF_OBJ_NAME_LEN 16U +#define MAX_ENTRIES 100000000 +#define NR_LOOPS 10000 + +char _license[] SEC("license") = "GPL"; + +/* Filled by userspace. See fill_map() in bench_lpm_trie_map.c */ +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __type(key, struct trie_key); + __type(value, __u32); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); +} trie_map SEC(".maps"); + +long hits; +long duration_ns; + +/* Configured from userspace */ +__u32 nr_entries; +__u32 prefixlen; +bool random; +__u8 op; + +static __u64 latency_free_start; + +SEC("fentry/bpf_map_free_deferred") +int BPF_PROG(trie_free_entry, struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_map, work); + char name[BPF_OBJ_NAME_LEN]; + u32 map_type; + + map_type = BPF_CORE_READ(map, map_type); + if (map_type != BPF_MAP_TYPE_LPM_TRIE) + return 0; + + /* + * Ideally we'd have access to the map ID but that's already + * freed before we enter trie_free(). + */ + BPF_CORE_READ_STR_INTO(&name, map, name); + if (bpf_strncmp(name, BPF_OBJ_NAME_LEN, "trie_free_map")) + return 0; + + latency_free_start = bpf_ktime_get_ns(); + + return 0; +} + +SEC("fexit/bpf_map_free_deferred") +int BPF_PROG(trie_free_exit, struct work_struct *work) +{ + __u64 val; + + if (!latency_free_start) + return 0; + + val = bpf_ktime_get_ns() - latency_free_start; + latency_free_start = 0; + + __sync_add_and_fetch(&duration_ns, val); + __sync_add_and_fetch(&hits, 1); + + return 0; +} + +static __u32 cur_key; + +static __always_inline void generate_key(struct trie_key *key) +{ + key->prefixlen = prefixlen; + + if (random) + key->data = bpf_get_prandom_u32() % nr_entries; + else + key->data = cur_key++ % nr_entries; +} + +static int noop(__u32 index, __u32 *unused) +{ + return 0; +} + +static int baseline(__u32 index, __u32 *unused) +{ + struct trie_key key; + __u32 blackbox = 0; + + generate_key(&key); + /* Avoid compiler optimizing out the modulo */ + barrier_var(blackbox); + blackbox = READ_ONCE(key.data); + + return 0; +} + +static int lookup(__u32 index, int *retval) +{ + struct trie_key key; + + generate_key(&key); + if (!bpf_map_lookup_elem(&trie_map, &key)) { + *retval = -ENOENT; + return 1; + } + + return 0; +} + +static int insert(__u32 index, int *retval) +{ + struct trie_key key; + u32 val = 1; + int err; + + generate_key(&key); + err = bpf_map_update_elem(&trie_map, &key, &val, BPF_NOEXIST); + if (err) { + *retval = err; + return 1; + } + + /* Is this the last entry? */ + if (key.data == nr_entries - 1) { + /* For atomicity concerns, see the comment in delete() */ + *retval = LPM_BENCH_REINIT_MAP; + return 1; + } + + return 0; +} + +static int update(__u32 index, int *retval) +{ + struct trie_key key; + u32 val = 1; + int err; + + generate_key(&key); + err = bpf_map_update_elem(&trie_map, &key, &val, BPF_EXIST); + if (err) { + *retval = err; + return 1; + } + + return 0; +} + +static int delete(__u32 index, int *retval) +{ + struct trie_key key; + int err; + + generate_key(&key); + err = bpf_map_delete_elem(&trie_map, &key); + if (err) { + *retval = err; + return 1; + } + + /* Do we need to refill the map? */ + if (key.data == nr_entries - 1) { + /* + * Atomicity isn't required because DELETE only supports + * one producer running concurrently. What we need is a + * way to track how many entries have been deleted from + * the trie between consecutive invocations of the BPF + * prog because a single bpf_loop() call might not + * delete all entries, e.g. when NR_LOOPS < nr_entries. + */ + *retval = LPM_BENCH_REINIT_MAP; + return 1; + } + + return 0; +} + +SEC("xdp") +int BPF_PROG(run_bench) +{ + int err = LPM_BENCH_SUCCESS; + u64 start, delta; + int loops; + + start = bpf_ktime_get_ns(); + + switch (op) { + case LPM_OP_NOOP: + loops = bpf_loop(NR_LOOPS, noop, NULL, 0); + break; + case LPM_OP_BASELINE: + loops = bpf_loop(NR_LOOPS, baseline, NULL, 0); + break; + case LPM_OP_LOOKUP: + loops = bpf_loop(NR_LOOPS, lookup, &err, 0); + break; + case LPM_OP_INSERT: + loops = bpf_loop(NR_LOOPS, insert, &err, 0); + break; + case LPM_OP_UPDATE: + loops = bpf_loop(NR_LOOPS, update, &err, 0); + break; + case LPM_OP_DELETE: + loops = bpf_loop(NR_LOOPS, delete, &err, 0); + break; + default: + bpf_printk("invalid benchmark operation\n"); + return -1; + } + + delta = bpf_ktime_get_ns() - start; + + __sync_add_and_fetch(&duration_ns, delta); + __sync_add_and_fetch(&hits, loops); + + return err; +} diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_map.c b/tools/testing/selftests/bpf/progs/lpm_trie_map.c new file mode 100644 index 000000000000..6e60d686b664 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lpm_trie_map.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define MAX_ENTRIES 100000000 + +struct trie_key { + __u32 prefixlen; + __u32 data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __type(key, struct trie_key); + __type(value, __u32); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); +} trie_free_map SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/map_excl.c b/tools/testing/selftests/bpf/progs/map_excl.c new file mode 100644 index 000000000000..d461684728e4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_excl.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025 Google LLC. */ +#include <linux/bpf.h> +#include <time.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1); +} excl_map SEC(".maps"); + +char _license[] SEC("license") = "GPL"; + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int should_have_access(void *ctx) +{ + int key = 0, value = 0xdeadbeef; + + bpf_map_update_elem(&excl_map, &key, &value, 0); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int should_not_have_access(void *ctx) +{ + int key = 0, value = 0xdeadbeef; + + bpf_map_update_elem(&excl_map, &key, &value, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c new file mode 100644 index 000000000000..3b984b6ae7c0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" + +SEC("tp_btf/sys_enter") +__success +__log_level(2) +__msg("r8 = *(u64 *)(r7 +0) ; R7=ptr_nameidata(off={{[0-9]+}}) R8=rdonly_untrusted_mem(sz=0)") +__msg("r9 = *(u8 *)(r8 +0) ; R8=rdonly_untrusted_mem(sz=0) R9=scalar") +int btf_id_to_ptr_mem(void *ctx) +{ + struct task_struct *task; + struct nameidata *idata; + u64 ret, off; + + task = bpf_get_current_task_btf(); + idata = task->nameidata; + off = bpf_core_field_offset(struct nameidata, pathname); + /* + * asm block to have reliable match target for __msg, equivalent of: + * ret = task->nameidata->pathname[0]; + */ + asm volatile ( + "r7 = %[idata];" + "r7 += %[off];" + "r8 = *(u64 *)(r7 + 0);" + "r9 = *(u8 *)(r8 + 0);" + "%[ret] = r9;" + : [ret]"=r"(ret) + : [idata]"r"(idata), + [off]"r"(off) + : "r7", "r8", "r9"); + return ret; +} + +SEC("socket") +__success +__retval(0) +int ldx_is_ok_bad_addr(void *ctx) +{ + char *p; + + if (!bpf_core_enum_value_exists(enum bpf_features, BPF_FEAT_RDONLY_CAST_TO_VOID)) + return 42; + + p = bpf_rdonly_cast(0, 0); + return p[0x7fff]; +} + +SEC("socket") +__success +__retval(1) +int ldx_is_ok_good_addr(void *ctx) +{ + int v, *p; + + v = 1; + p = bpf_rdonly_cast(&v, 0); + return *p; +} + +SEC("socket") +__success +int offset_not_tracked(void *ctx) +{ + int *p, i, s; + + p = bpf_rdonly_cast(0, 0); + s = 0; + bpf_for(i, 0, 1000 * 1000 * 1000) { + p++; + s += *p; + } + return s; +} + +SEC("socket") +__failure +__msg("cannot write into rdonly_untrusted_mem") +int stx_not_ok(void *ctx) +{ + int v, *p; + + v = 1; + p = bpf_rdonly_cast(&v, 0); + *p = 1; + return 0; +} + +SEC("socket") +__failure +__msg("cannot write into rdonly_untrusted_mem") +int atomic_not_ok(void *ctx) +{ + int v, *p; + + v = 1; + p = bpf_rdonly_cast(&v, 0); + __sync_fetch_and_add(p, 1); + return 0; +} + +SEC("socket") +__failure +__msg("cannot write into rdonly_untrusted_mem") +int atomic_rmw_not_ok(void *ctx) +{ + long v, *p; + + v = 1; + p = bpf_rdonly_cast(&v, 0); + return __sync_val_compare_and_swap(p, 0, 42); +} + +SEC("socket") +__failure +__msg("invalid access to memory, mem_size=0 off=0 size=4") +__msg("R1 min value is outside of the allowed memory range") +int kfunc_param_not_ok(void *ctx) +{ + int *p; + + p = bpf_rdonly_cast(0, 0); + bpf_kfunc_trusted_num_test(p); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure +__msg("R1 type=rdonly_untrusted_mem expected=") +int helper_param_not_ok(void *ctx) +{ + char *p; + + p = bpf_rdonly_cast(0, 0); + /* + * Any helper with ARG_CONST_SIZE_OR_ZERO constraint will do, + * the most permissive constraint + */ + bpf_copy_from_user(p, 0, (void *)42); + return 0; +} + +static __noinline u64 *get_some_addr(void) +{ + if (bpf_get_prandom_u32()) + return bpf_rdonly_cast(0, bpf_core_type_id_kernel(struct sock)); + else + return bpf_rdonly_cast(0, 0); +} + +SEC("socket") +__success +__retval(0) +int mixed_mem_type(void *ctx) +{ + u64 *p; + + /* Try to avoid compiler hoisting load to if branches by using __noinline func. */ + p = get_some_addr(); + return *p; +} + +__attribute__((__aligned__(8))) +u8 global[] = { + 0x11, 0x22, 0x33, 0x44, + 0x55, 0x66, 0x77, 0x88, + 0x99 +}; + +__always_inline +static u64 combine(void *p) +{ + u64 acc; + + acc = 0; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + acc |= (*(u64 *)p >> 56) << 24; + acc |= (*(u32 *)p >> 24) << 16; + acc |= (*(u16 *)p >> 8) << 8; + acc |= *(u8 *)p; +#else + acc |= (*(u64 *)p & 0xff) << 24; + acc |= (*(u32 *)p & 0xff) << 16; + acc |= (*(u16 *)p & 0xff) << 8; + acc |= *(u8 *)p; +#endif + return acc; +} + +SEC("socket") +__retval(0x88442211) +int diff_size_access(void *ctx) +{ + return combine(bpf_rdonly_cast(&global, 0)); +} + +SEC("socket") +__retval(0x99553322) +int misaligned_access(void *ctx) +{ + return combine(bpf_rdonly_cast(&global, 0) + 1); +} + +__weak int return_one(void) +{ + return 1; +} + +SEC("socket") +__success +__retval(1) +int null_check(void *ctx) +{ + int *p; + + p = bpf_rdonly_cast(0, 0); + if (p == 0) + /* make this a function call to avoid compiler + * moving r0 assignment before check. + */ + return return_one(); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c index 70302477e326..41389e579578 100644 --- a/tools/testing/selftests/bpf/progs/mptcp_subflow.c +++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c @@ -117,7 +117,7 @@ int _getsockopt_subflow(struct bpf_sockopt *ctx) return 1; msk = bpf_core_cast(sk, struct mptcp_sock); - if (msk->pm.subflows != 1) { + if (msk->pm.extra_subflows != 1) { ctx->retval = -1; return 1; } diff --git a/tools/testing/selftests/bpf/progs/rbtree.c b/tools/testing/selftests/bpf/progs/rbtree.c index a3620c15c136..49fe93d7e059 100644 --- a/tools/testing/selftests/bpf/progs/rbtree.c +++ b/tools/testing/selftests/bpf/progs/rbtree.c @@ -61,19 +61,19 @@ static long __add_three(struct bpf_rb_root *root, struct bpf_spin_lock *lock) } m->key = 1; - bpf_spin_lock(&glock); - bpf_rbtree_add(&groot, &n->node, less); - bpf_rbtree_add(&groot, &m->node, less); - bpf_spin_unlock(&glock); + bpf_spin_lock(lock); + bpf_rbtree_add(root, &n->node, less); + bpf_rbtree_add(root, &m->node, less); + bpf_spin_unlock(lock); n = bpf_obj_new(typeof(*n)); if (!n) return 3; n->key = 3; - bpf_spin_lock(&glock); - bpf_rbtree_add(&groot, &n->node, less); - bpf_spin_unlock(&glock); + bpf_spin_lock(lock); + bpf_rbtree_add(root, &n->node, less); + bpf_spin_unlock(lock); return 0; } diff --git a/tools/testing/selftests/bpf/progs/rbtree_search.c b/tools/testing/selftests/bpf/progs/rbtree_search.c index 098ef970fac1..b05565d1db0d 100644 --- a/tools/testing/selftests/bpf/progs/rbtree_search.c +++ b/tools/testing/selftests/bpf/progs/rbtree_search.c @@ -183,7 +183,7 @@ long test_##op##_spinlock_##dolock(void *ctx) \ } /* - * Use a spearate MSG macro instead of passing to TEST_XXX(..., MSG) + * Use a separate MSG macro instead of passing to TEST_XXX(..., MSG) * to ensure the message itself is not in the bpf prog lineinfo * which the verifier includes in its log. * Otherwise, the test_loader will incorrectly match the prog lineinfo diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c index 43637ee2cdcd..3a868a199349 100644 --- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c +++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c @@ -16,10 +16,11 @@ struct { __type(value, long); } map_a SEC(".maps"); -__u32 user_data, key_serial, target_pid; +__u32 user_data, target_pid; +__s32 key_serial; __u64 flags, task_storage_val, cgroup_id; -struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym; +struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym; void bpf_key_put(struct bpf_key *key) __ksym; void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; diff --git a/tools/testing/selftests/bpf/progs/read_cgroupfs_xattr.c b/tools/testing/selftests/bpf/progs/read_cgroupfs_xattr.c new file mode 100644 index 000000000000..405adbe5e8b0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/read_cgroupfs_xattr.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +pid_t target_pid = 0; + +char xattr_value[64]; +static const char expected_value_a[] = "bpf_selftest_value_a"; +static const char expected_value_b[] = "bpf_selftest_value_b"; +bool found_value_a; +bool found_value_b; + +SEC("lsm.s/file_open") +int BPF_PROG(test_file_open) +{ + u64 cgrp_id = bpf_get_current_cgroup_id(); + struct cgroup_subsys_state *css, *tmp; + struct bpf_dynptr value_ptr; + struct cgroup *cgrp; + + if ((bpf_get_current_pid_tgid() >> 32) != target_pid) + return 0; + + bpf_rcu_read_lock(); + cgrp = bpf_cgroup_from_id(cgrp_id); + if (!cgrp) { + bpf_rcu_read_unlock(); + return 0; + } + + css = &cgrp->self; + bpf_dynptr_from_mem(xattr_value, sizeof(xattr_value), 0, &value_ptr); + bpf_for_each(css, tmp, css, BPF_CGROUP_ITER_ANCESTORS_UP) { + int ret; + + ret = bpf_cgroup_read_xattr(tmp->cgroup, "user.bpf_test", + &value_ptr); + if (ret < 0) + continue; + + if (ret == sizeof(expected_value_a) && + !bpf_strncmp(xattr_value, sizeof(expected_value_a), expected_value_a)) + found_value_a = true; + if (ret == sizeof(expected_value_b) && + !bpf_strncmp(xattr_value, sizeof(expected_value_b), expected_value_b)) + found_value_b = true; + } + + bpf_rcu_read_unlock(); + bpf_cgroup_release(cgrp); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/security_bpf_map.c b/tools/testing/selftests/bpf/progs/security_bpf_map.c new file mode 100644 index 000000000000..7216b3450e96 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/security_bpf_map.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "vmlinux.h" +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +#define EPERM 1 /* Operation not permitted */ + +/* From include/linux/mm.h. */ +#define FMODE_WRITE 0x2 + +struct map; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1); +} prot_status_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 3); +} prot_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 3); +} not_prot_map SEC(".maps"); + +SEC("fmod_ret/security_bpf_map") +int BPF_PROG(fmod_bpf_map, struct bpf_map *map, int fmode) +{ + __u32 key = 0; + __u32 *status_ptr = bpf_map_lookup_elem(&prot_status_map, &key); + + if (!status_ptr || !*status_ptr) + return 0; + + if (map == &prot_map) { + /* Allow read-only access */ + if (fmode & FMODE_WRITE) + return -EPERM; + } + + return 0; +} + +/* + * This program keeps references to maps. This is needed to prevent + * optimizing them out. + */ +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(fentry_dummy1, int a) +{ + __u32 key = 0; + __u32 val1 = a; + __u32 val2 = a + 1; + + bpf_map_update_elem(&prot_map, &key, &val1, BPF_ANY); + bpf_map_update_elem(¬_prot_map, &key, &val2, BPF_ANY); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/set_global_vars.c b/tools/testing/selftests/bpf/progs/set_global_vars.c index 90f5656c3991..ebaef28b2cb3 100644 --- a/tools/testing/selftests/bpf/progs/set_global_vars.c +++ b/tools/testing/selftests/bpf/progs/set_global_vars.c @@ -7,22 +7,30 @@ char _license[] SEC("license") = "GPL"; -enum Enum { EA1 = 0, EA2 = 11 }; +typedef __s32 s32; +typedef s32 i32; +typedef __u8 u8; + +enum Enum { EA1 = 0, EA2 = 11, EA3 = 10 }; enum Enumu64 {EB1 = 0llu, EB2 = 12llu }; enum Enums64 { EC1 = 0ll, EC2 = 13ll }; const volatile __s64 var_s64 = -1; const volatile __u64 var_u64 = 0; -const volatile __s32 var_s32 = -1; +const volatile i32 var_s32 = -1; const volatile __u32 var_u32 = 0; const volatile __s16 var_s16 = -1; const volatile __u16 var_u16 = 0; const volatile __s8 var_s8 = -1; -const volatile __u8 var_u8 = 0; +const volatile u8 var_u8 = 0; const volatile enum Enum var_ea = EA1; const volatile enum Enumu64 var_eb = EB1; const volatile enum Enums64 var_ec = EC1; const volatile bool var_b = false; +const volatile i32 arr[32]; +const volatile enum Enum enum_arr[32]; +const volatile i32 three_d[47][19][17]; +const volatile i32 *ptr_arr[32]; struct Struct { int:16; @@ -35,34 +43,38 @@ struct Struct { volatile struct { const int:1; union { - const volatile __u8 var_u8; + const volatile u8 var_u8[3]; const volatile __s16 filler3; const int:1; + s32 mat[7][5]; } u; }; - } struct2; + } struct2[2][4]; }; const volatile __u32 stru = 0; /* same prefix as below */ -const volatile struct Struct struct1 = {.struct2 = {.u = {.var_u8 = 1}}}; +const volatile struct Struct struct1[3]; +const volatile struct Struct struct11[11][7]; -union Union { - __u16 var_u16; - struct Struct3 { - struct { - __u8 var_u8_l; - }; +struct Struct3 { + struct { + u8 var_u8_l; + }; + struct { struct { - struct { - __u8 var_u8_h; - }; + u8 var_u8_h; }; - } struct3; + }; }; -const volatile union Union union1 = {.var_u16 = -1}; +typedef struct Struct3 Struct3_t; -char arr[4] = {0}; +union Union { + __u16 var_u16; + Struct3_t struct3; +}; + +const volatile union Union union1 = {.var_u16 = -1}; SEC("socket") int test_set_globals(void *ctx) @@ -81,8 +93,14 @@ int test_set_globals(void *ctx) a = var_eb; a = var_ec; a = var_b; - a = struct1.struct2.u.var_u8; + a = struct1[2].struct2[1][2].u.var_u8[2]; a = union1.var_u16; + a = arr[3]; + a = arr[EA2]; + a = enum_arr[EC2]; + a = three_d[31][7][EA2]; + a = struct1[2].struct2[1][2].u.mat[5][3]; + a = struct11[7][5].struct2[0][1].u.mat[3][0]; return a; } diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c index 8f483337e103..77966ded5467 100644 --- a/tools/testing/selftests/bpf/progs/sock_iter_batch.c +++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c @@ -23,6 +23,7 @@ static bool ipv4_addr_loopback(__be32 a) } volatile const unsigned int sf; +volatile const unsigned int ss; volatile const __u16 ports[2]; unsigned int bucket[2]; @@ -42,16 +43,18 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) sock_cookie = bpf_get_socket_cookie(sk); sk = bpf_core_cast(sk, struct sock); if (sk->sk_family != sf || - sk->sk_state != TCP_LISTEN || - sk->sk_family == AF_INET6 ? + (ss && sk->sk_state != ss) || + (sk->sk_family == AF_INET6 ? !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) : - !ipv4_addr_loopback(sk->sk_rcv_saddr)) + !ipv4_addr_loopback(sk->sk_rcv_saddr))) return 0; if (sk->sk_num == ports[0]) idx = 0; else if (sk->sk_num == ports[1]) idx = 1; + else if (!ports[0] && !ports[1]) + idx = 0; else return 0; @@ -67,6 +70,27 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) return 0; } +volatile const __u64 destroy_cookie; + +SEC("iter/tcp") +int iter_tcp_destroy(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = (struct sock_common *)ctx->sk_common; + __u64 sock_cookie; + + if (!sk_common) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk_common); + if (sock_cookie != destroy_cookie) + return 0; + + bpf_sock_destroy(sk_common); + bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie)); + + return 0; +} + #define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk) SEC("iter/udp") @@ -83,15 +107,17 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx) sock_cookie = bpf_get_socket_cookie(sk); sk = bpf_core_cast(sk, struct sock); if (sk->sk_family != sf || - sk->sk_family == AF_INET6 ? + (sk->sk_family == AF_INET6 ? !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) : - !ipv4_addr_loopback(sk->sk_rcv_saddr)) + !ipv4_addr_loopback(sk->sk_rcv_saddr))) return 0; if (sk->sk_num == ports[0]) idx = 0; else if (sk->sk_num == ports[1]) idx = 1; + else if (!ports[0] && !ports[1]) + idx = 0; else return 0; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/stacktrace_map.c index 47568007b668..0c77df05be7f 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/stacktrace_map.c @@ -50,6 +50,7 @@ struct sched_switch_args { int next_prio; }; +__u32 stack_id; SEC("tracepoint/sched/sched_switch") int oncpu(struct sched_switch_args *ctx) { @@ -64,6 +65,7 @@ int oncpu(struct sched_switch_args *ctx) /* The size of stackmap and stackid_hmap should be the same */ key = bpf_get_stackid(ctx, &stackmap, 0); if ((int)key >= 0) { + stack_id = key; bpf_map_update_elem(&stackid_hmap, &key, &val, 0); stack_p = bpf_map_lookup_elem(&stack_amap, &key); if (stack_p) diff --git a/tools/testing/selftests/bpf/progs/stream.c b/tools/testing/selftests/bpf/progs/stream.c new file mode 100644 index 000000000000..4a5bd852f10c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/stream.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" +#include "bpf_arena_common.h" + +struct arr_elem { + struct bpf_res_spin_lock lock; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct arr_elem); +} arrmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARENA); + __uint(map_flags, BPF_F_MMAPABLE); + __uint(max_entries, 1); /* number of pages */ +} arena SEC(".maps"); + +struct elem { + struct bpf_timer timer; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} array SEC(".maps"); + +#define ENOSPC 28 +#define _STR "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" + +int size; +u64 fault_addr; +void *arena_ptr; + +SEC("syscall") +__success __retval(0) +int stream_exhaust(void *ctx) +{ + /* Use global variable for loop convergence. */ + size = 0; + bpf_repeat(BPF_MAX_LOOPS) { + if (bpf_stream_printk(BPF_STDOUT, _STR) == -ENOSPC && size == 99954) + return 0; + size += sizeof(_STR) - 1; + } + return 1; +} + +SEC("syscall") +__arch_x86_64 +__arch_arm64 +__arch_s390x +__success __retval(0) +__stderr("ERROR: Timeout detected for may_goto instruction") +__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}") +__stderr("Call trace:\n" +"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n" +"|[ \t]+[^\n]+\n)*}}") +int stream_cond_break(void *ctx) +{ + while (can_loop) + ; + return 0; +} + +SEC("syscall") +__success __retval(0) +__stderr("ERROR: AA or ABBA deadlock detected for bpf_res_spin_lock") +__stderr("{{Attempted lock = (0x[0-9a-fA-F]+)\n" +"Total held locks = 1\n" +"Held lock\\[ 0\\] = \\1}}") +__stderr("...") +__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}") +__stderr("Call trace:\n" +"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n" +"|[ \t]+[^\n]+\n)*}}") +int stream_deadlock(void *ctx) +{ + struct bpf_res_spin_lock *lock, *nlock; + + lock = bpf_map_lookup_elem(&arrmap, &(int){0}); + if (!lock) + return 1; + nlock = bpf_map_lookup_elem(&arrmap, &(int){0}); + if (!nlock) + return 1; + if (bpf_res_spin_lock(lock)) + return 1; + if (bpf_res_spin_lock(nlock)) { + bpf_res_spin_unlock(lock); + return 0; + } + bpf_res_spin_unlock(nlock); + bpf_res_spin_unlock(lock); + return 1; +} + +SEC("syscall") +__success __retval(0) +int stream_syscall(void *ctx) +{ + bpf_stream_printk(BPF_STDOUT, "foo"); + return 0; +} + +SEC("syscall") +__arch_x86_64 +__arch_arm64 +__success __retval(0) +__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}") +__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}") +__stderr("Call trace:\n" +"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n" +"|[ \t]+[^\n]+\n)*}}") +int stream_arena_write_fault(void *ctx) +{ + struct bpf_arena *ptr = (void *)&arena; + u64 user_vm_start; + + /* Prevent GCC bounds warning: casting &arena to struct bpf_arena * + * triggers bounds checking since the map definition is smaller than struct + * bpf_arena. barrier_var() makes the pointer opaque to GCC, preventing the + * bounds analysis + */ + barrier_var(ptr); + user_vm_start = ptr->user_vm_start; + fault_addr = user_vm_start + 0x7fff; + bpf_addr_space_cast(user_vm_start, 0, 1); + asm volatile ( + "r1 = %0;" + "r2 = 1;" + "*(u32 *)(r1 + 0x7fff) = r2;" + : + : "r" (user_vm_start) + : "r1", "r2" + ); + return 0; +} + +SEC("syscall") +__arch_x86_64 +__arch_arm64 +__success __retval(0) +__stderr("ERROR: Arena READ access at unmapped address 0x{{.*}}") +__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}") +__stderr("Call trace:\n" +"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n" +"|[ \t]+[^\n]+\n)*}}") +int stream_arena_read_fault(void *ctx) +{ + struct bpf_arena *ptr = (void *)&arena; + u64 user_vm_start; + + /* Prevent GCC bounds warning: casting &arena to struct bpf_arena * + * triggers bounds checking since the map definition is smaller than struct + * bpf_arena. barrier_var() makes the pointer opaque to GCC, preventing the + * bounds analysis + */ + barrier_var(ptr); + user_vm_start = ptr->user_vm_start; + fault_addr = user_vm_start + 0x7fff; + bpf_addr_space_cast(user_vm_start, 0, 1); + asm volatile ( + "r1 = %0;" + "r1 = *(u32 *)(r1 + 0x7fff);" + : + : "r" (user_vm_start) + : "r1" + ); + return 0; +} + +static __noinline void subprog(void) +{ + int __arena *addr = (int __arena *)0xdeadbeef; + + arena_ptr = &arena; + *addr = 1; +} + +SEC("syscall") +__arch_x86_64 +__arch_arm64 +__success __retval(0) +__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}") +__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}") +__stderr("Call trace:\n" +"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n" +"|[ \t]+[^\n]+\n)*}}") +int stream_arena_subprog_fault(void *ctx) +{ + subprog(); + return 0; +} + +static __noinline int timer_cb(void *map, int *key, struct bpf_timer *timer) +{ + int __arena *addr = (int __arena *)0xdeadbeef; + + arena_ptr = &arena; + *addr = 1; + return 0; +} + +SEC("syscall") +__arch_x86_64 +__arch_arm64 +__success __retval(0) +__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}") +__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}") +__stderr("Call trace:\n" +"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n" +"|[ \t]+[^\n]+\n)*}}") +int stream_arena_callback_fault(void *ctx) +{ + struct bpf_timer *arr_timer; + + arr_timer = bpf_map_lookup_elem(&array, &(int){0}); + if (!arr_timer) + return 0; + bpf_timer_init(arr_timer, &array, 1); + bpf_timer_set_callback(arr_timer, timer_cb); + bpf_timer_start(arr_timer, 0, 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/stream_fail.c b/tools/testing/selftests/bpf/progs/stream_fail.c new file mode 100644 index 000000000000..b4a0d0cc8ec8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/stream_fail.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +SEC("syscall") +__failure __msg("Possibly NULL pointer passed") +int stream_vprintk_null_arg(void *ctx) +{ + bpf_stream_vprintk(BPF_STDOUT, "", NULL, 0, NULL); + return 0; +} + +SEC("syscall") +__failure __msg("R3 type=scalar expected=") +int stream_vprintk_scalar_arg(void *ctx) +{ + bpf_stream_vprintk(BPF_STDOUT, "", (void *)46, 0, NULL); + return 0; +} + +SEC("syscall") +__failure __msg("arg#1 doesn't point to a const string") +int stream_vprintk_string_arg(void *ctx) +{ + bpf_stream_vprintk(BPF_STDOUT, ctx, NULL, 0, NULL); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c new file mode 100644 index 000000000000..99d72c68f76a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025 Red Hat, Inc.*/ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <linux/limits.h> +#include "bpf_misc.h" +#include "errno.h" + +char *user_ptr = (char *)1; +char *invalid_kern_ptr = (char *)-1; + +/* + * When passing userspace pointers, the error code differs based on arch: + * -ERANGE on arches with non-overlapping address spaces + * -EFAULT on other arches + */ +#if defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_loongarch) || \ + defined(__TARGET_ARCH_powerpc) || defined(__TARGET_ARCH_x86) +#define USER_PTR_ERR -ERANGE +#else +#define USER_PTR_ERR -EFAULT +#endif + +/* + * On s390, __get_kernel_nofault (used in string kfuncs) returns 0 for NULL and + * user_ptr (instead of causing an exception) so the below two groups of tests + * are not applicable. + */ +#ifndef __TARGET_ARCH_s390 + +/* Passing NULL to string kfuncs (treated as a userspace ptr) */ +SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_null1(void *ctx) { return bpf_strcmp(NULL, "hello"); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strcmp_null2(void *ctx) { return bpf_strcmp("hello", NULL); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_null1(void *ctx) { return bpf_strcasecmp(NULL, "HELLO"); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strcasecmp_null2(void *ctx) { return bpf_strcasecmp("HELLO", NULL); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strchr_null(void *ctx) { return bpf_strchr(NULL, 'a'); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strchrnul_null(void *ctx) { return bpf_strchrnul(NULL, 'a'); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strnchr_null(void *ctx) { return bpf_strnchr(NULL, 1, 'a'); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strrchr_null(void *ctx) { return bpf_strrchr(NULL, 'a'); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strlen_null(void *ctx) { return bpf_strlen(NULL); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strnlen_null(void *ctx) { return bpf_strnlen(NULL, 1); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strspn_null1(void *ctx) { return bpf_strspn(NULL, "hello"); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strspn_null2(void *ctx) { return bpf_strspn("hello", NULL); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strcspn_null1(void *ctx) { return bpf_strcspn(NULL, "hello"); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strcspn_null2(void *ctx) { return bpf_strcspn("hello", NULL); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strstr_null1(void *ctx) { return bpf_strstr(NULL, "hello"); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strstr_null2(void *ctx) { return bpf_strstr("hello", NULL); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strnstr_null1(void *ctx) { return bpf_strnstr(NULL, "hello", 1); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strnstr_null2(void *ctx) { return bpf_strnstr("hello", NULL, 1); } + +/* Passing userspace ptr to string kfuncs */ +SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr1(void *ctx) { return bpf_strcmp(user_ptr, "hello"); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr2(void *ctx) { return bpf_strcmp("hello", user_ptr); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_user_ptr1(void *ctx) { return bpf_strcasecmp(user_ptr, "HELLO"); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_user_ptr2(void *ctx) { return bpf_strcasecmp("HELLO", user_ptr); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strchr_user_ptr(void *ctx) { return bpf_strchr(user_ptr, 'a'); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strchrnul_user_ptr(void *ctx) { return bpf_strchrnul(user_ptr, 'a'); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strnchr_user_ptr(void *ctx) { return bpf_strnchr(user_ptr, 1, 'a'); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strrchr_user_ptr(void *ctx) { return bpf_strrchr(user_ptr, 'a'); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strlen_user_ptr(void *ctx) { return bpf_strlen(user_ptr); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strnlen_user_ptr(void *ctx) { return bpf_strnlen(user_ptr, 1); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strspn_user_ptr1(void *ctx) { return bpf_strspn(user_ptr, "hello"); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strspn_user_ptr2(void *ctx) { return bpf_strspn("hello", user_ptr); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcspn_user_ptr1(void *ctx) { return bpf_strcspn(user_ptr, "hello"); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcspn_user_ptr2(void *ctx) { return bpf_strcspn("hello", user_ptr); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strstr_user_ptr1(void *ctx) { return bpf_strstr(user_ptr, "hello"); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strstr_user_ptr2(void *ctx) { return bpf_strstr("hello", user_ptr); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strnstr_user_ptr1(void *ctx) { return bpf_strnstr(user_ptr, "hello", 1); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strnstr_user_ptr2(void *ctx) { return bpf_strnstr("hello", user_ptr, 1); } + +#endif /* __TARGET_ARCH_s390 */ + +/* Passing invalid kernel ptr to string kfuncs should always return -EFAULT */ +SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault1(void *ctx) { return bpf_strcmp(invalid_kern_ptr, "hello"); } +SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault2(void *ctx) { return bpf_strcmp("hello", invalid_kern_ptr); } +SEC("syscall") __retval(-EFAULT) int test_strcasecmp_pagefault1(void *ctx) { return bpf_strcasecmp(invalid_kern_ptr, "HELLO"); } +SEC("syscall") __retval(-EFAULT) int test_strcasecmp_pagefault2(void *ctx) { return bpf_strcasecmp("HELLO", invalid_kern_ptr); } +SEC("syscall") __retval(-EFAULT) int test_strchr_pagefault(void *ctx) { return bpf_strchr(invalid_kern_ptr, 'a'); } +SEC("syscall") __retval(-EFAULT) int test_strchrnul_pagefault(void *ctx) { return bpf_strchrnul(invalid_kern_ptr, 'a'); } +SEC("syscall") __retval(-EFAULT) int test_strnchr_pagefault(void *ctx) { return bpf_strnchr(invalid_kern_ptr, 1, 'a'); } +SEC("syscall") __retval(-EFAULT) int test_strrchr_pagefault(void *ctx) { return bpf_strrchr(invalid_kern_ptr, 'a'); } +SEC("syscall") __retval(-EFAULT) int test_strlen_pagefault(void *ctx) { return bpf_strlen(invalid_kern_ptr); } +SEC("syscall") __retval(-EFAULT) int test_strnlen_pagefault(void *ctx) { return bpf_strnlen(invalid_kern_ptr, 1); } +SEC("syscall") __retval(-EFAULT) int test_strspn_pagefault1(void *ctx) { return bpf_strspn(invalid_kern_ptr, "hello"); } +SEC("syscall") __retval(-EFAULT) int test_strspn_pagefault2(void *ctx) { return bpf_strspn("hello", invalid_kern_ptr); } +SEC("syscall") __retval(-EFAULT) int test_strcspn_pagefault1(void *ctx) { return bpf_strcspn(invalid_kern_ptr, "hello"); } +SEC("syscall") __retval(-EFAULT) int test_strcspn_pagefault2(void *ctx) { return bpf_strcspn("hello", invalid_kern_ptr); } +SEC("syscall") __retval(-EFAULT) int test_strstr_pagefault1(void *ctx) { return bpf_strstr(invalid_kern_ptr, "hello"); } +SEC("syscall") __retval(-EFAULT) int test_strstr_pagefault2(void *ctx) { return bpf_strstr("hello", invalid_kern_ptr); } +SEC("syscall") __retval(-EFAULT) int test_strnstr_pagefault1(void *ctx) { return bpf_strnstr(invalid_kern_ptr, "hello", 1); } +SEC("syscall") __retval(-EFAULT) int test_strnstr_pagefault2(void *ctx) { return bpf_strnstr("hello", invalid_kern_ptr, 1); } + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c new file mode 100644 index 000000000000..e41cc5601994 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025 Red Hat, Inc.*/ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <linux/limits.h> + +char long_str[XATTR_SIZE_MAX + 1]; + +SEC("syscall") int test_strcmp_too_long(void *ctx) { return bpf_strcmp(long_str, long_str); } +SEC("syscall") int test_strcasecmp_too_long(void *ctx) { return bpf_strcasecmp(long_str, long_str); } +SEC("syscall") int test_strchr_too_long(void *ctx) { return bpf_strchr(long_str, 'b'); } +SEC("syscall") int test_strchrnul_too_long(void *ctx) { return bpf_strchrnul(long_str, 'b'); } +SEC("syscall") int test_strnchr_too_long(void *ctx) { return bpf_strnchr(long_str, sizeof(long_str), 'b'); } +SEC("syscall") int test_strrchr_too_long(void *ctx) { return bpf_strrchr(long_str, 'b'); } +SEC("syscall") int test_strlen_too_long(void *ctx) { return bpf_strlen(long_str); } +SEC("syscall") int test_strnlen_too_long(void *ctx) { return bpf_strnlen(long_str, sizeof(long_str)); } +SEC("syscall") int test_strspn_str_too_long(void *ctx) { return bpf_strspn(long_str, "a"); } +SEC("syscall") int test_strspn_accept_too_long(void *ctx) { return bpf_strspn("b", long_str); } +SEC("syscall") int test_strcspn_str_too_long(void *ctx) { return bpf_strcspn(long_str, "b"); } +SEC("syscall") int test_strcspn_reject_too_long(void *ctx) { return bpf_strcspn("b", long_str); } +SEC("syscall") int test_strstr_too_long(void *ctx) { return bpf_strstr(long_str, "hello"); } +SEC("syscall") int test_strnstr_too_long(void *ctx) { return bpf_strnstr(long_str, "hello", sizeof(long_str)); } + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c new file mode 100644 index 000000000000..2e3498e37b9c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025 Red Hat, Inc.*/ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" +#include "errno.h" + +char str[] = "hello world"; + +#define __test(retval) SEC("syscall") __success __retval(retval) + +/* Functional tests */ +__test(0) int test_strcmp_eq(void *ctx) { return bpf_strcmp(str, "hello world"); } +__test(1) int test_strcmp_neq(void *ctx) { return bpf_strcmp(str, "hello"); } +__test(0) int test_strcasecmp_eq1(void *ctx) { return bpf_strcasecmp(str, "hello world"); } +__test(0) int test_strcasecmp_eq2(void *ctx) { return bpf_strcasecmp(str, "HELLO WORLD"); } +__test(0) int test_strcasecmp_eq3(void *ctx) { return bpf_strcasecmp(str, "HELLO world"); } +__test(1) int test_strcasecmp_neq1(void *ctx) { return bpf_strcasecmp(str, "hello"); } +__test(1) int test_strcasecmp_neq2(void *ctx) { return bpf_strcasecmp(str, "HELLO"); } +__test(1) int test_strchr_found(void *ctx) { return bpf_strchr(str, 'e'); } +__test(11) int test_strchr_null(void *ctx) { return bpf_strchr(str, '\0'); } +__test(-ENOENT) int test_strchr_notfound(void *ctx) { return bpf_strchr(str, 'x'); } +__test(1) int test_strchrnul_found(void *ctx) { return bpf_strchrnul(str, 'e'); } +__test(11) int test_strchrnul_notfound(void *ctx) { return bpf_strchrnul(str, 'x'); } +__test(1) int test_strnchr_found(void *ctx) { return bpf_strnchr(str, 5, 'e'); } +__test(11) int test_strnchr_null(void *ctx) { return bpf_strnchr(str, 12, '\0'); } +__test(-ENOENT) int test_strnchr_notfound(void *ctx) { return bpf_strnchr(str, 5, 'w'); } +__test(9) int test_strrchr_found(void *ctx) { return bpf_strrchr(str, 'l'); } +__test(11) int test_strrchr_null(void *ctx) { return bpf_strrchr(str, '\0'); } +__test(-ENOENT) int test_strrchr_notfound(void *ctx) { return bpf_strrchr(str, 'x'); } +__test(11) int test_strlen(void *ctx) { return bpf_strlen(str); } +__test(11) int test_strnlen(void *ctx) { return bpf_strnlen(str, 12); } +__test(5) int test_strspn(void *ctx) { return bpf_strspn(str, "ehlo"); } +__test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); } +__test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); } +__test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); } +__test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); } +__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); } +__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); } +__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); } +__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); } +__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); } +__test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); } + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c new file mode 100644 index 000000000000..ad8bb546c9bf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" + +char _license[] SEC("license") = "GPL"; + +#define bpf_kfunc_multi_st_ops_test_1(args) bpf_kfunc_multi_st_ops_test_1(args, st_ops_id) +int st_ops_id; + +int test_pid; +int test_err; + +#define MAP1_MAGIC 1234 + +SEC("struct_ops") +int BPF_PROG(test_1, struct st_ops_args *args) +{ + return MAP1_MAGIC; +} + +SEC("tp_btf/sys_enter") +int BPF_PROG(sys_enter, struct pt_regs *regs, long id) +{ + struct st_ops_args args = {}; + struct task_struct *task; + int ret; + + task = bpf_get_current_task_btf(); + if (!test_pid || task->pid != test_pid) + return 0; + + ret = bpf_kfunc_multi_st_ops_test_1(&args); + if (ret != MAP1_MAGIC) + test_err++; + + return 0; +} + +SEC("syscall") +int syscall_prog(void *ctx) +{ + struct st_ops_args args = {}; + int ret; + + ret = bpf_kfunc_multi_st_ops_test_1(&args); + if (ret != MAP1_MAGIC) + test_err++; + + return 0; +} + +SEC(".struct_ops.link") +struct bpf_testmod_multi_st_ops st_ops_map = { + .test_1 = (void *)test_1, +}; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c new file mode 100644 index 000000000000..cea1a2f4b62f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" + +char _license[] SEC("license") = "GPL"; + +#define bpf_kfunc_multi_st_ops_test_1(args) bpf_kfunc_multi_st_ops_test_1(args, st_ops_id) +int st_ops_id; + +int test_pid; +int test_err; + +#define MAP2_MAGIC 4567 + +SEC("struct_ops") +int BPF_PROG(test_1, struct st_ops_args *args) +{ + return MAP2_MAGIC; +} + +SEC("tp_btf/sys_enter") +int BPF_PROG(sys_enter, struct pt_regs *regs, long id) +{ + struct st_ops_args args = {}; + struct task_struct *task; + int ret; + + task = bpf_get_current_task_btf(); + if (!test_pid || task->pid != test_pid) + return 0; + + ret = bpf_kfunc_multi_st_ops_test_1(&args); + if (ret != MAP2_MAGIC) + test_err++; + + return 0; +} + +SEC("syscall") +int syscall_prog(void *ctx) +{ + struct st_ops_args args = {}; + int ret; + + ret = bpf_kfunc_multi_st_ops_test_1(&args); + if (ret != MAP2_MAGIC) + test_err++; + + return 0; +} + +SEC(".struct_ops.link") +struct bpf_testmod_multi_st_ops st_ops_map = { + .test_1 = (void *)test_1, +}; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c index 36386b3c23a1..2b98b7710816 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c @@ -9,7 +9,7 @@ void bpf_task_release(struct task_struct *p) __ksym; /* This test struct_ops BPF programs returning referenced kptr. The verifier should * allow a referenced kptr or a NULL pointer to be returned. A referenced kptr to task - * here is acquried automatically as the task argument is tagged with "__ref". + * here is acquired automatically as the task argument is tagged with "__ref". */ SEC("struct_ops/test_return_ref_kptr") struct task_struct *BPF_PROG(kptr_return, int dummy, diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c index 0e4d2ff63ab8..dbe646013811 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c @@ -7,7 +7,7 @@ char _license[] SEC("license") = "GPL"; -#if defined(__TARGET_ARCH_x86) +#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64) bool skip __attribute((__section__(".data"))) = false; #else bool skip = true; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c index 58d5d8dc2235..3d89ad7cbe2a 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c @@ -7,7 +7,7 @@ char _license[] SEC("license") = "GPL"; -#if defined(__TARGET_ARCH_x86) +#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64) bool skip __attribute((__section__(".data"))) = false; #else bool skip = true; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c index 31e58389bb8b..b1f6d7e5a8e5 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c @@ -7,7 +7,7 @@ char _license[] SEC("license") = "GPL"; -#if defined(__TARGET_ARCH_x86) +#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64) bool skip __attribute((__section__(".data"))) = false; #else bool skip = true; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c index 76dcb6089d7f..9c0a65466356 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c @@ -9,7 +9,7 @@ __attribute__((nomerge)) extern void bpf_task_release(struct task_struct *p) __k /* This is a test BPF program that uses struct_ops to access a referenced * kptr argument. This is a test for the verifier to ensure that it - * 1) recongnizes the task as a referenced object (i.e., ref_obj_id > 0), and + * 1) recognizes the task as a referenced object (i.e., ref_obj_id > 0), and * 2) the same reference can be acquired from multiple paths as long as it * has not been released. */ diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c index 327ca395e860..d556b19413d7 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c @@ -2,6 +2,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include "bpf_legacy.h" +#include "bpf_test_utils.h" struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); @@ -24,6 +25,8 @@ int entry(struct __sk_buff *skb) { int ret = 1; + clobber_regs_stack(); + count++; subprog_tail(skb); subprog_tail(skb); diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c index 72fd0d577506..ae94c9c70ab7 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c @@ -2,6 +2,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" +#include "bpf_test_utils.h" int classifier_0(struct __sk_buff *skb); int classifier_1(struct __sk_buff *skb); @@ -60,6 +61,8 @@ int tailcall_bpf2bpf_hierarchy_2(struct __sk_buff *skb) { int ret = 0; + clobber_regs_stack(); + subprog_tail0(skb); subprog_tail1(skb); diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c index a7fb91cb05b7..56b6b0099840 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c @@ -2,6 +2,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" +#include "bpf_test_utils.h" int classifier_0(struct __sk_buff *skb); @@ -53,6 +54,8 @@ int tailcall_bpf2bpf_hierarchy_3(struct __sk_buff *skb) { int ret = 0; + clobber_regs_stack(); + bpf_tail_call_static(skb, &jmp_table0, 0); __sink(ret); diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c index c87f9ca982d3..5261395713cd 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c @@ -4,6 +4,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_test_utils.h" struct { __uint(type, BPF_MAP_TYPE_PROG_ARRAY); @@ -24,6 +25,8 @@ int subprog_tail(void *ctx) SEC("fentry/dummy") int BPF_PROG(fentry, struct sk_buff *skb) { + clobber_regs_stack(); + count++; subprog_tail(ctx); subprog_tail(ctx); diff --git a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h new file mode 100644 index 000000000000..432fff2af844 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h @@ -0,0 +1,237 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __TASK_LOCAL_DATA_BPF_H +#define __TASK_LOCAL_DATA_BPF_H + +/* + * Task local data is a library that facilitates sharing per-task data + * between user space and bpf programs. + * + * + * USAGE + * + * A TLD, an entry of data in task local data, first needs to be created by the + * user space. This is done by calling user space API, TLD_DEFINE_KEY() or + * tld_create_key(), with the name of the TLD and the size. + * + * TLD_DEFINE_KEY(prio, "priority", sizeof(int)); + * + * or + * + * void func_call(...) { + * tld_key_t prio, in_cs; + * + * prio = tld_create_key("priority", sizeof(int)); + * in_cs = tld_create_key("in_critical_section", sizeof(bool)); + * ... + * + * A key associated with the TLD, which has an opaque type tld_key_t, will be + * initialized or returned. It can be used to get a pointer to the TLD in the + * user space by calling tld_get_data(). + * + * In a bpf program, tld_object_init() first needs to be called to initialized a + * tld_object on the stack. Then, TLDs can be accessed by calling tld_get_data(). + * The API will try to fetch the key by the name and use it to locate the data. + * A pointer to the TLD will be returned. It also caches the key in a task local + * storage map, tld_key_map, whose value type, struct tld_keys, must be defined + * by the developer. + * + * struct tld_keys { + * tld_key_t prio; + * tld_key_t in_cs; + * }; + * + * SEC("struct_ops") + * void prog(struct task_struct task, ...) + * { + * struct tld_object tld_obj; + * int err, *p; + * + * err = tld_object_init(task, &tld_obj); + * if (err) + * return; + * + * p = tld_get_data(&tld_obj, prio, "priority", sizeof(int)); + * if (p) + * // do something depending on *p + */ +#include <errno.h> +#include <bpf/bpf_helpers.h> + +#define TLD_ROUND_MASK(x, y) ((__typeof__(x))((y) - 1)) +#define TLD_ROUND_UP(x, y) ((((x) - 1) | TLD_ROUND_MASK(x, y)) + 1) + +#define TLD_MAX_DATA_CNT (__PAGE_SIZE / sizeof(struct tld_metadata) - 1) + +#ifndef TLD_NAME_LEN +#define TLD_NAME_LEN 62 +#endif + +#ifndef TLD_KEY_MAP_CREATE_RETRY +#define TLD_KEY_MAP_CREATE_RETRY 10 +#endif + +typedef struct { + __s16 off; +} tld_key_t; + +struct tld_metadata { + char name[TLD_NAME_LEN]; + __u16 size; +}; + +struct tld_meta_u { + __u8 cnt; + __u16 size; + struct tld_metadata metadata[TLD_MAX_DATA_CNT]; +}; + +struct tld_data_u { + __u64 start; /* offset of tld_data_u->data in a page */ + char data[__PAGE_SIZE - sizeof(__u64)]; +}; + +struct tld_map_value { + struct tld_data_u __uptr *data; + struct tld_meta_u __uptr *meta; +}; + +typedef struct tld_uptr_dummy { + struct tld_data_u data[0]; + struct tld_meta_u meta[0]; +} *tld_uptr_dummy_t; + +struct tld_object { + struct tld_map_value *data_map; + struct tld_keys *key_map; + /* + * Force the compiler to generate the actual definition of tld_meta_u + * and tld_data_u in BTF. Without it, tld_meta_u and u_tld_data will + * be BTF_KIND_FWD. + */ + tld_uptr_dummy_t dummy[0]; +}; + +/* + * Map value of tld_key_map for caching keys. Must be defined by the developer. + * Members should be tld_key_t and passed to the 3rd argument of tld_fetch_key(). + */ +struct tld_keys; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct tld_map_value); +} tld_data_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct tld_keys); +} tld_key_map SEC(".maps"); + +/** + * tld_object_init() - Initialize a tld_object. + * + * @task: The task_struct of the target task + * @tld_obj: A pointer to a tld_object to be initialized + * + * Return 0 on success; -ENODATA if the user space did not initialize task local data + * for the current task through tld_get_data(); -ENOMEM if the creation of tld_key_map + * fails + */ +__attribute__((unused)) +static int tld_object_init(struct task_struct *task, struct tld_object *tld_obj) +{ + int i; + + tld_obj->data_map = bpf_task_storage_get(&tld_data_map, task, 0, 0); + if (!tld_obj->data_map) + return -ENODATA; + + bpf_for(i, 0, TLD_KEY_MAP_CREATE_RETRY) { + tld_obj->key_map = bpf_task_storage_get(&tld_key_map, task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (likely(tld_obj->key_map)) + break; + } + if (!tld_obj->key_map) + return -ENOMEM; + + return 0; +} + +/* + * Return the offset of TLD if @name is found. Otherwise, return the current TLD count + * using the nonpositive range so that the next tld_get_data() can skip fetching key if + * no new TLD is added or start comparing name from the first newly added TLD. + */ +__attribute__((unused)) +static int __tld_fetch_key(struct tld_object *tld_obj, const char *name, int i_start) +{ + struct tld_metadata *metadata; + int i, cnt, start, off = 0; + + if (!tld_obj->data_map || !tld_obj->data_map->data || !tld_obj->data_map->meta) + return 0; + + start = tld_obj->data_map->data->start; + cnt = tld_obj->data_map->meta->cnt; + metadata = tld_obj->data_map->meta->metadata; + + bpf_for(i, 0, cnt) { + if (i >= TLD_MAX_DATA_CNT) + break; + + if (i >= i_start && !bpf_strncmp(metadata[i].name, TLD_NAME_LEN, name)) + return start + off; + + off += TLD_ROUND_UP(metadata[i].size, 8); + } + + return -cnt; +} + +/** + * tld_get_data() - Retrieve a pointer to the TLD associated with the name. + * + * @tld_obj: A pointer to a valid tld_object initialized by tld_object_init() + * @key: The cached key of the TLD in tld_key_map + * @name: The name of the key associated with a TLD + * @size: The size of the TLD. Must be a known constant value + * + * Return a pointer to the TLD associated with @name; NULL if not found or @size is too + * big. @key is used to cache the key if the TLD is found to speed up subsequent calls. + * It should be defined as an member of tld_keys of tld_key_t type by the developer. + */ +#define tld_get_data(tld_obj, key, name, size) \ + ({ \ + void *data = NULL, *_data = (tld_obj)->data_map->data; \ + long off = (tld_obj)->key_map->key.off; \ + int cnt; \ + \ + if (likely(_data)) { \ + if (likely(off > 0)) { \ + barrier_var(off); \ + if (likely(off < __PAGE_SIZE - size)) \ + data = _data + off; \ + } else { \ + cnt = -(off); \ + if (likely((tld_obj)->data_map->meta) && \ + cnt < (tld_obj)->data_map->meta->cnt) { \ + off = __tld_fetch_key(tld_obj, name, cnt); \ + (tld_obj)->key_map->key.off = off; \ + \ + if (likely(off < __PAGE_SIZE - size)) { \ + barrier_var(off); \ + if (off > 0) \ + data = _data + off; \ + } \ + } \ + } \ + } \ + data; \ + }) + +#endif diff --git a/tools/testing/selftests/bpf/progs/task_work.c b/tools/testing/selftests/bpf/progs/task_work.c new file mode 100644 index 000000000000..23217f06a3ec --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_work.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <string.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "errno.h" + +char _license[] SEC("license") = "GPL"; + +const void *user_ptr = NULL; + +struct elem { + char data[128]; + struct bpf_task_work tw; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} hmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} arrmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LRU_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} lrumap SEC(".maps"); + +static int process_work(struct bpf_map *map, void *key, void *value) +{ + struct elem *work = value; + + bpf_copy_from_user_str(work->data, sizeof(work->data), (const void *)user_ptr, 0); + return 0; +} + +int key = 0; + +SEC("perf_event") +int oncpu_hash_map(struct pt_regs *args) +{ + struct elem empty_work = { .data = { 0 } }; + struct elem *work; + struct task_struct *task; + int err; + + task = bpf_get_current_task_btf(); + err = bpf_map_update_elem(&hmap, &key, &empty_work, BPF_NOEXIST); + if (err) + return 0; + work = bpf_map_lookup_elem(&hmap, &key); + if (!work) + return 0; + + bpf_task_work_schedule_resume(task, &work->tw, &hmap, process_work, NULL); + return 0; +} + +SEC("perf_event") +int oncpu_array_map(struct pt_regs *args) +{ + struct elem *work; + struct task_struct *task; + + task = bpf_get_current_task_btf(); + work = bpf_map_lookup_elem(&arrmap, &key); + if (!work) + return 0; + bpf_task_work_schedule_signal(task, &work->tw, &arrmap, process_work, NULL); + return 0; +} + +SEC("perf_event") +int oncpu_lru_map(struct pt_regs *args) +{ + struct elem empty_work = { .data = { 0 } }; + struct elem *work; + struct task_struct *task; + int err; + + task = bpf_get_current_task_btf(); + work = bpf_map_lookup_elem(&lrumap, &key); + if (work) + return 0; + err = bpf_map_update_elem(&lrumap, &key, &empty_work, BPF_NOEXIST); + if (err) + return 0; + work = bpf_map_lookup_elem(&lrumap, &key); + if (!work || work->data[0]) + return 0; + bpf_task_work_schedule_resume(task, &work->tw, &lrumap, process_work, NULL); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/task_work_fail.c b/tools/testing/selftests/bpf/progs/task_work_fail.c new file mode 100644 index 000000000000..77fe8f28facd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_work_fail.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <string.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +const void *user_ptr = NULL; + +struct elem { + char data[128]; + struct bpf_task_work tw; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} hmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} arrmap SEC(".maps"); + +static int process_work(struct bpf_map *map, void *key, void *value) +{ + struct elem *work = value; + + bpf_copy_from_user_str(work->data, sizeof(work->data), (const void *)user_ptr, 0); + return 0; +} + +int key = 0; + +SEC("perf_event") +__failure __msg("doesn't match map pointer in R3") +int mismatch_map(struct pt_regs *args) +{ + struct elem *work; + struct task_struct *task; + + task = bpf_get_current_task_btf(); + work = bpf_map_lookup_elem(&arrmap, &key); + if (!work) + return 0; + bpf_task_work_schedule_resume(task, &work->tw, &hmap, process_work, NULL); + return 0; +} + +SEC("perf_event") +__failure __msg("arg#1 doesn't point to a map value") +int no_map_task_work(struct pt_regs *args) +{ + struct task_struct *task; + struct bpf_task_work tw; + + task = bpf_get_current_task_btf(); + bpf_task_work_schedule_resume(task, &tw, &hmap, process_work, NULL); + return 0; +} + +SEC("perf_event") +__failure __msg("Possibly NULL pointer passed to trusted arg1") +int task_work_null(struct pt_regs *args) +{ + struct task_struct *task; + + task = bpf_get_current_task_btf(); + bpf_task_work_schedule_resume(task, NULL, &hmap, process_work, NULL); + return 0; +} + +SEC("perf_event") +__failure __msg("Possibly NULL pointer passed to trusted arg2") +int map_null(struct pt_regs *args) +{ + struct elem *work; + struct task_struct *task; + + task = bpf_get_current_task_btf(); + work = bpf_map_lookup_elem(&arrmap, &key); + if (!work) + return 0; + bpf_task_work_schedule_resume(task, &work->tw, NULL, process_work, NULL); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/task_work_stress.c b/tools/testing/selftests/bpf/progs/task_work_stress.c new file mode 100644 index 000000000000..90fca06fff56 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/task_work_stress.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <string.h> +#include <stdbool.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +#define ENTRIES 128 + +char _license[] SEC("license") = "GPL"; + +__u64 callback_scheduled = 0; +__u64 callback_success = 0; +__u64 schedule_error = 0; +__u64 delete_success = 0; + +struct elem { + __u32 count; + struct bpf_task_work tw; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, ENTRIES); + __type(key, int); + __type(value, struct elem); +} hmap SEC(".maps"); + +static int process_work(struct bpf_map *map, void *key, void *value) +{ + __sync_fetch_and_add(&callback_success, 1); + return 0; +} + +SEC("syscall") +int schedule_task_work(void *ctx) +{ + struct elem empty_work = {.count = 0}; + struct elem *work; + int key = 0, err; + + key = bpf_ktime_get_ns() % ENTRIES; + work = bpf_map_lookup_elem(&hmap, &key); + if (!work) { + bpf_map_update_elem(&hmap, &key, &empty_work, BPF_NOEXIST); + work = bpf_map_lookup_elem(&hmap, &key); + if (!work) + return 0; + } + err = bpf_task_work_schedule_signal(bpf_get_current_task_btf(), &work->tw, &hmap, + process_work, NULL); + if (err) + __sync_fetch_and_add(&schedule_error, 1); + else + __sync_fetch_and_add(&callback_scheduled, 1); + return 0; +} + +SEC("syscall") +int delete_task_work(void *ctx) +{ + int key = 0, err; + + key = bpf_get_prandom_u32() % ENTRIES; + err = bpf_map_delete_elem(&hmap, &key); + if (!err) + __sync_fetch_and_add(&delete_success, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index f344c6835e84..26a53e54b8fa 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -22,6 +22,7 @@ #include "bpf_compiler.h" #include "test_cls_redirect.h" +#include "bpf_misc.h" #pragma GCC diagnostic ignored "-Waddress-of-packed-member" @@ -31,9 +32,6 @@ #define INLINING __always_inline #endif -#define offsetofend(TYPE, MEMBER) \ - (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) - #define IP_OFFSET_MASK (0x1FFF) #define IP_MF (0x2000) @@ -129,7 +127,7 @@ typedef uint8_t *net_ptr __attribute__((align_value(8))); typedef struct buf { struct __sk_buff *skb; net_ptr head; - /* NB: tail musn't have alignment other than 1, otherwise + /* NB: tail mustn't have alignment other than 1, otherwise * LLVM will go and eliminate code, e.g. when checking packet lengths. */ uint8_t *const tail; diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c index d0f7670351e5..dfd4a2710391 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c @@ -494,7 +494,7 @@ static ret_t get_next_hop(struct bpf_dynptr *dynptr, __u64 *offset, encap_header *offset += sizeof(*next_hop); - /* Skip the remainig next hops (may be zero). */ + /* Skip the remaining next hops (may be zero). */ return skip_next_hops(offset, encap->unigue.hop_count - encap->unigue.next_hop - 1); } diff --git a/tools/testing/selftests/bpf/progs/test_lookup_key.c b/tools/testing/selftests/bpf/progs/test_lookup_key.c index cdbbb12f1491..1f7e1e59b073 100644 --- a/tools/testing/selftests/bpf/progs/test_lookup_key.c +++ b/tools/testing/selftests/bpf/progs/test_lookup_key.c @@ -14,11 +14,11 @@ char _license[] SEC("license") = "GPL"; __u32 monitored_pid; -__u32 key_serial; +__s32 key_serial; __u32 key_id; __u64 flags; -extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym; +extern struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym; extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; extern void bpf_key_put(struct bpf_key *key) __ksym; diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c index abb7344b531f..5edf3cdc213d 100644 --- a/tools/testing/selftests/bpf/progs/test_overhead.c +++ b/tools/testing/selftests/bpf/progs/test_overhead.c @@ -1,9 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ -#include <stdbool.h> -#include <stddef.h> -#include <linux/bpf.h> -#include <linux/ptrace.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> diff --git a/tools/testing/selftests/bpf/progs/test_pinning_devmap.c b/tools/testing/selftests/bpf/progs/test_pinning_devmap.c new file mode 100644 index 000000000000..c855f8f87eff --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_pinning_devmap.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); + __uint(pinning, LIBBPF_PIN_BY_NAME); +} pinmap1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u32); + __uint(pinning, LIBBPF_PIN_BY_NAME); +} pinmap2 SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_write.c b/tools/testing/selftests/bpf/progs/test_ringbuf_write.c index 350513c0e4c9..f063a0013f85 100644 --- a/tools/testing/selftests/bpf/progs/test_ringbuf_write.c +++ b/tools/testing/selftests/bpf/progs/test_ringbuf_write.c @@ -26,11 +26,11 @@ int test_ringbuf_write(void *ctx) if (cur_pid != pid) return 0; - sample1 = bpf_ringbuf_reserve(&ringbuf, 0x3000, 0); + sample1 = bpf_ringbuf_reserve(&ringbuf, 0x30000, 0); if (!sample1) return 0; /* first one can pass */ - sample2 = bpf_ringbuf_reserve(&ringbuf, 0x3000, 0); + sample2 = bpf_ringbuf_reserve(&ringbuf, 0x30000, 0); if (!sample2) { bpf_ringbuf_discard(sample1, 0); __sync_fetch_and_add(&discarded, 1); diff --git a/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c index 8ef6b39335b6..34b30e2603f0 100644 --- a/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c +++ b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c @@ -40,7 +40,7 @@ char digest[MAGIC_SIZE + SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE]; __u32 monitored_pid; char sig[MAX_SIG_SIZE]; __u32 sig_size; -__u32 user_keyring_serial; +__s32 user_keyring_serial; SEC("lsm.s/file_open") int BPF_PROG(test_file_open, struct file *f) diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c index 2796dd8545eb..1c7941a4ad00 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c @@ -1,8 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2024 ByteDance */ -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> +#ifndef PAGE_SIZE +#define PAGE_SIZE __PAGE_SIZE +#endif +#define BPF_SKB_MAX_LEN (PAGE_SIZE << 2) + struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 1); @@ -31,7 +36,7 @@ int prog_skb_verdict(struct __sk_buff *skb) change_tail_ret = bpf_skb_change_tail(skb, skb->len + 1, 0); return SK_PASS; } else if (data[0] == 'E') { /* Error */ - change_tail_ret = bpf_skb_change_tail(skb, 65535, 0); + change_tail_ret = bpf_skb_change_tail(skb, BPF_SKB_MAX_LEN, 0); return SK_PASS; } return SK_PASS; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c index 8bdb9987c0c7..83df4919c224 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c @@ -7,6 +7,8 @@ int cork_byte; int push_start; int push_end; int apply_bytes; +int pop_start; +int pop_end; struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); @@ -22,6 +24,8 @@ int prog_sk_policy(struct sk_msg_md *msg) bpf_msg_cork_bytes(msg, cork_byte); if (push_start > 0 && push_end > 0) bpf_msg_push_data(msg, push_start, push_end, 0); + if (pop_start >= 0 && pop_end > 0) + bpf_msg_pop_data(msg, pop_start, pop_end, 0); return SK_PASS; } diff --git a/tools/testing/selftests/bpf/progs/test_task_local_data.c b/tools/testing/selftests/bpf/progs/test_task_local_data.c new file mode 100644 index 000000000000..fffafc013044 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_task_local_data.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> + +#include "task_local_data.bpf.h" + +struct tld_keys { + tld_key_t value0; + tld_key_t value1; + tld_key_t value2; + tld_key_t value_not_exist; +}; + +struct test_tld_struct { + __u64 a; + __u64 b; + __u64 c; + __u64 d; +}; + +int test_value0; +int test_value1; +struct test_tld_struct test_value2; + +SEC("syscall") +int task_main(void *ctx) +{ + struct tld_object tld_obj; + struct test_tld_struct *struct_p; + struct task_struct *task; + int err, *int_p; + + task = bpf_get_current_task_btf(); + err = tld_object_init(task, &tld_obj); + if (err) + return 1; + + int_p = tld_get_data(&tld_obj, value0, "value0", sizeof(int)); + if (int_p) + test_value0 = *int_p; + else + return 2; + + int_p = tld_get_data(&tld_obj, value1, "value1", sizeof(int)); + if (int_p) + test_value1 = *int_p; + else + return 3; + + struct_p = tld_get_data(&tld_obj, value2, "value2", sizeof(struct test_tld_struct)); + if (struct_p) + test_value2 = *struct_p; + else + return 4; + + int_p = tld_get_data(&tld_obj, value_not_exist, "value_not_exist", sizeof(int)); + if (int_p) + return 5; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c index 28edafe803f0..fcba8299f0bc 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c +++ b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> -#include <linux/if_ether.h> -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/udp.h> -#include <linux/pkt_cls.h> + +#ifndef PAGE_SIZE +#define PAGE_SIZE __PAGE_SIZE +#endif +#define BPF_SKB_MAX_LEN (PAGE_SIZE << 2) long change_tail_ret = 1; @@ -94,7 +94,7 @@ int change_tail(struct __sk_buff *skb) bpf_skb_change_tail(skb, len, 0); return TCX_PASS; } else if (payload[0] == 'E') { /* Error */ - change_tail_ret = bpf_skb_change_tail(skb, 65535, 0); + change_tail_ret = bpf_skb_change_tail(skb, BPF_SKB_MAX_LEN, 0); return TCX_PASS; } else if (payload[0] == 'Z') { /* Zero */ change_tail_ret = bpf_skb_change_tail(skb, 0, 0); diff --git a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c index 5f4e87ee949a..1ecdf4c54de4 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c @@ -14,10 +14,7 @@ #include <bpf/bpf_endian.h> #define BPF_PROG_TEST_TCP_HDR_OPTIONS #include "test_tcp_hdr_options.h" - -#ifndef sizeof_field -#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) -#endif +#include "bpf_misc.h" __u8 test_kind = TCPOPT_EXP; __u16 test_magic = 0xeB9F; diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index 540181c115a8..ef00d38b0a8d 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -23,7 +23,6 @@ struct { struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(max_entries, 2); __type(key, int); __type(value, __u32); } perf_event_map SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/test_uprobe.c b/tools/testing/selftests/bpf/progs/test_uprobe.c index 896c88a4960d..12f4065fca20 100644 --- a/tools/testing/selftests/bpf/progs/test_uprobe.c +++ b/tools/testing/selftests/bpf/progs/test_uprobe.c @@ -59,3 +59,41 @@ int BPF_UPROBE(test4) test4_result = 1; return 0; } + +#if defined(__TARGET_ARCH_x86) +struct pt_regs regs; + +SEC("uprobe") +int BPF_UPROBE(test_regs_change) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + + if (pid != my_pid) + return 0; + + ctx->ax = regs.ax; + ctx->cx = regs.cx; + ctx->dx = regs.dx; + ctx->r8 = regs.r8; + ctx->r9 = regs.r9; + ctx->r10 = regs.r10; + ctx->r11 = regs.r11; + ctx->di = regs.di; + ctx->si = regs.si; + return 0; +} + +unsigned long ip; + +SEC("uprobe") +int BPF_UPROBE(test_regs_change_ip) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + + if (pid != my_pid) + return 0; + + ctx->ip = ip; + return 0; +} +#endif diff --git a/tools/testing/selftests/bpf/progs/test_usdt.c b/tools/testing/selftests/bpf/progs/test_usdt.c index 096488f47fbc..a78c87537b07 100644 --- a/tools/testing/selftests/bpf/progs/test_usdt.c +++ b/tools/testing/selftests/bpf/progs/test_usdt.c @@ -107,4 +107,35 @@ int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5, return 0; } +int usdt_sib_called; +u64 usdt_sib_cookie; +int usdt_sib_arg_cnt; +int usdt_sib_arg_ret; +short usdt_sib_arg; +int usdt_sib_arg_size; + +/* + * usdt_sib is only tested on x86-related architectures, so it requires + * manual attach since auto-attach will panic tests under other architectures + */ +SEC("usdt") +int usdt_sib(struct pt_regs *ctx) +{ + long tmp; + + if (my_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + __sync_fetch_and_add(&usdt_sib_called, 1); + + usdt_sib_cookie = bpf_usdt_cookie(ctx); + usdt_sib_arg_cnt = bpf_usdt_arg_cnt(ctx); + + usdt_sib_arg_ret = bpf_usdt_arg(ctx, 0, &tmp); + usdt_sib_arg = (short)tmp; + usdt_sib_arg_size = bpf_usdt_arg_size(ctx, 0); + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c index e96d09e11115..ff8d755548b9 100644 --- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c @@ -17,7 +17,7 @@ #define MAX_SIG_SIZE 1024 __u32 monitored_pid; -__u32 user_keyring_serial; +__s32 user_keyring_serial; __u64 system_keyring_id; struct data { diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index dc74d8cf9e3f..5904f45cfbc4 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -19,7 +19,9 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) /* Data length determine test case */ if (data_len == 54) { /* sizeof(pkt_v4) */ - offset = 4096; /* test too large offset */ + offset = 4096; /* test too large offset, 4k page size */ + } else if (data_len == 53) { /* sizeof(pkt_v4) - 1 */ + offset = 65536; /* test too large offset, 64k page size */ } else if (data_len == 74) { /* sizeof(pkt_v6) */ offset = 40; } else if (data_len == 64) { @@ -31,6 +33,10 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) offset = 10; } else if (data_len == 9001) { offset = 4096; + } else if (data_len == 90000) { + offset = 10; /* test a small offset, 64k page size */ + } else if (data_len == 90001) { + offset = 65536; /* test too large offset, 64k page size */ } else { return XDP_ABORTED; /* No matching test */ } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_tailcall.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_tailcall.c new file mode 100644 index 000000000000..814e2a980e97 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_tailcall.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +SEC("xdp") +int xdp_devmap(struct xdp_md *ctx) +{ + return ctx->egress_ifindex; +} + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __array(values, int (void *)); +} xdp_map SEC(".maps") = { + .values = { + [0] = (void *)&xdp_devmap, + }, +}; + +SEC("xdp") +int xdp_entry(struct xdp_md *ctx) +{ + bpf_tail_call(ctx, &xdp_map, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index fcf6ca14f2ea..d79cb74b571e 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -1,8 +1,11 @@ +#include <stdbool.h> #include <linux/bpf.h> +#include <linux/errno.h> #include <linux/if_ether.h> #include <linux/pkt_cls.h> #include <bpf/bpf_helpers.h> +#include "bpf_kfuncs.h" #define META_SIZE 32 @@ -23,6 +26,8 @@ struct { __uint(value_size, META_SIZE); } test_result SEC(".maps"); +bool test_pass; + SEC("tc") int ing_cls(struct __sk_buff *ctx) { @@ -40,6 +45,231 @@ int ing_cls(struct __sk_buff *ctx) return TC_ACT_SHOT; } +/* Read from metadata using bpf_dynptr_read helper */ +SEC("tc") +int ing_cls_dynptr_read(struct __sk_buff *ctx) +{ + struct bpf_dynptr meta; + const __u32 zero = 0; + __u8 *dst; + + dst = bpf_map_lookup_elem(&test_result, &zero); + if (!dst) + return TC_ACT_SHOT; + + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + bpf_dynptr_read(dst, META_SIZE, &meta, 0, 0); + + return TC_ACT_SHOT; +} + +/* Write to metadata using bpf_dynptr_write helper */ +SEC("tc") +int ing_cls_dynptr_write(struct __sk_buff *ctx) +{ + struct bpf_dynptr data, meta; + __u8 *src; + + bpf_dynptr_from_skb(ctx, 0, &data); + src = bpf_dynptr_slice(&data, sizeof(struct ethhdr), NULL, META_SIZE); + if (!src) + return TC_ACT_SHOT; + + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + bpf_dynptr_write(&meta, 0, src, META_SIZE, 0); + + return TC_ACT_UNSPEC; /* pass */ +} + +/* Read from metadata using read-only dynptr slice */ +SEC("tc") +int ing_cls_dynptr_slice(struct __sk_buff *ctx) +{ + struct bpf_dynptr meta; + const __u32 zero = 0; + __u8 *dst, *src; + + dst = bpf_map_lookup_elem(&test_result, &zero); + if (!dst) + return TC_ACT_SHOT; + + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + src = bpf_dynptr_slice(&meta, 0, NULL, META_SIZE); + if (!src) + return TC_ACT_SHOT; + + __builtin_memcpy(dst, src, META_SIZE); + + return TC_ACT_SHOT; +} + +/* Write to metadata using writeable dynptr slice */ +SEC("tc") +int ing_cls_dynptr_slice_rdwr(struct __sk_buff *ctx) +{ + struct bpf_dynptr data, meta; + __u8 *src, *dst; + + bpf_dynptr_from_skb(ctx, 0, &data); + src = bpf_dynptr_slice(&data, sizeof(struct ethhdr), NULL, META_SIZE); + if (!src) + return TC_ACT_SHOT; + + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + dst = bpf_dynptr_slice_rdwr(&meta, 0, NULL, META_SIZE); + if (!dst) + return TC_ACT_SHOT; + + __builtin_memcpy(dst, src, META_SIZE); + + return TC_ACT_UNSPEC; /* pass */ +} + +/* Read skb metadata in chunks from various offsets in different ways. */ +SEC("tc") +int ing_cls_dynptr_offset_rd(struct __sk_buff *ctx) +{ + struct bpf_dynptr meta; + const __u32 chunk_len = META_SIZE / 4; + const __u32 zero = 0; + __u8 *dst, *src; + + dst = bpf_map_lookup_elem(&test_result, &zero); + if (!dst) + return TC_ACT_SHOT; + + /* 1. Regular read */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + bpf_dynptr_read(dst, chunk_len, &meta, 0, 0); + dst += chunk_len; + + /* 2. Read from an offset-adjusted dynptr */ + bpf_dynptr_adjust(&meta, chunk_len, bpf_dynptr_size(&meta)); + bpf_dynptr_read(dst, chunk_len, &meta, 0, 0); + dst += chunk_len; + + /* 3. Read at an offset */ + bpf_dynptr_read(dst, chunk_len, &meta, chunk_len, 0); + dst += chunk_len; + + /* 4. Read from a slice starting at an offset */ + src = bpf_dynptr_slice(&meta, 2 * chunk_len, NULL, chunk_len); + if (!src) + return TC_ACT_SHOT; + __builtin_memcpy(dst, src, chunk_len); + + return TC_ACT_SHOT; +} + +/* Write skb metadata in chunks at various offsets in different ways. */ +SEC("tc") +int ing_cls_dynptr_offset_wr(struct __sk_buff *ctx) +{ + const __u32 chunk_len = META_SIZE / 4; + __u8 payload[META_SIZE]; + struct bpf_dynptr meta; + __u8 *dst, *src; + + bpf_skb_load_bytes(ctx, sizeof(struct ethhdr), payload, sizeof(payload)); + src = payload; + + /* 1. Regular write */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + bpf_dynptr_write(&meta, 0, src, chunk_len, 0); + src += chunk_len; + + /* 2. Write to an offset-adjusted dynptr */ + bpf_dynptr_adjust(&meta, chunk_len, bpf_dynptr_size(&meta)); + bpf_dynptr_write(&meta, 0, src, chunk_len, 0); + src += chunk_len; + + /* 3. Write at an offset */ + bpf_dynptr_write(&meta, chunk_len, src, chunk_len, 0); + src += chunk_len; + + /* 4. Write to a slice starting at an offset */ + dst = bpf_dynptr_slice_rdwr(&meta, 2 * chunk_len, NULL, chunk_len); + if (!dst) + return TC_ACT_SHOT; + __builtin_memcpy(dst, src, chunk_len); + + return TC_ACT_UNSPEC; /* pass */ +} + +/* Pass an OOB offset to dynptr read, write, adjust, slice. */ +SEC("tc") +int ing_cls_dynptr_offset_oob(struct __sk_buff *ctx) +{ + struct bpf_dynptr meta; + __u8 md, *p; + int err; + + err = bpf_dynptr_from_skb_meta(ctx, 0, &meta); + if (err) + goto fail; + + /* read offset OOB */ + err = bpf_dynptr_read(&md, sizeof(md), &meta, META_SIZE, 0); + if (err != -E2BIG) + goto fail; + + /* write offset OOB */ + err = bpf_dynptr_write(&meta, META_SIZE, &md, sizeof(md), 0); + if (err != -E2BIG) + goto fail; + + /* adjust end offset OOB */ + err = bpf_dynptr_adjust(&meta, 0, META_SIZE + 1); + if (err != -ERANGE) + goto fail; + + /* adjust start offset OOB */ + err = bpf_dynptr_adjust(&meta, META_SIZE + 1, META_SIZE + 1); + if (err != -ERANGE) + goto fail; + + /* slice offset OOB */ + p = bpf_dynptr_slice(&meta, META_SIZE, NULL, sizeof(*p)); + if (p) + goto fail; + + /* slice rdwr offset OOB */ + p = bpf_dynptr_slice_rdwr(&meta, META_SIZE, NULL, sizeof(*p)); + if (p) + goto fail; + + return TC_ACT_UNSPEC; +fail: + return TC_ACT_SHOT; +} + +/* Reserve and clear space for metadata but don't populate it */ +SEC("xdp") +int ing_xdp_zalloc_meta(struct xdp_md *ctx) +{ + struct ethhdr *eth = ctx_ptr(ctx, data); + __u8 *meta; + int ret; + + /* Drop any non-test packets */ + if (eth + 1 > ctx_ptr(ctx, data_end)) + return XDP_DROP; + if (eth->h_proto != 0) + return XDP_DROP; + + ret = bpf_xdp_adjust_meta(ctx, -META_SIZE); + if (ret < 0) + return XDP_DROP; + + meta = ctx_ptr(ctx, data_meta); + if (meta + META_SIZE > ctx_ptr(ctx, data)) + return XDP_DROP; + + __builtin_memset(meta, 0, META_SIZE); + + return XDP_PASS; +} + SEC("xdp") int ing_xdp(struct xdp_md *ctx) { @@ -73,4 +303,193 @@ int ing_xdp(struct xdp_md *ctx) return XDP_PASS; } +/* + * Check that skb->data_meta..skb->data is empty if prog writes to packet + * _payload_ using packet pointers. Applies only to cloned skbs. + */ +SEC("tc") +int clone_data_meta_empty_on_data_write(struct __sk_buff *ctx) +{ + struct ethhdr *eth = ctx_ptr(ctx, data); + + if (eth + 1 > ctx_ptr(ctx, data_end)) + goto out; + /* Ignore non-test packets */ + if (eth->h_proto != 0) + goto out; + + /* Expect no metadata */ + if (ctx->data_meta != ctx->data) + goto out; + + /* Packet write to trigger unclone in prologue */ + eth->h_proto = 42; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +/* + * Check that skb->data_meta..skb->data is empty if prog writes to packet + * _metadata_ using packet pointers. Applies only to cloned skbs. + */ +SEC("tc") +int clone_data_meta_empty_on_meta_write(struct __sk_buff *ctx) +{ + struct ethhdr *eth = ctx_ptr(ctx, data); + __u8 *md = ctx_ptr(ctx, data_meta); + + if (eth + 1 > ctx_ptr(ctx, data_end)) + goto out; + /* Ignore non-test packets */ + if (eth->h_proto != 0) + goto out; + + if (md + 1 > ctx_ptr(ctx, data)) { + /* Expect no metadata */ + test_pass = true; + } else { + /* Metadata write to trigger unclone in prologue */ + *md = 42; + } +out: + return TC_ACT_SHOT; +} + +/* + * Check that skb_meta dynptr is writable but empty if prog writes to packet + * _payload_ using a dynptr slice. Applies only to cloned skbs. + */ +SEC("tc") +int clone_dynptr_empty_on_data_slice_write(struct __sk_buff *ctx) +{ + struct bpf_dynptr data, meta; + struct ethhdr *eth; + + bpf_dynptr_from_skb(ctx, 0, &data); + eth = bpf_dynptr_slice_rdwr(&data, 0, NULL, sizeof(*eth)); + if (!eth) + goto out; + /* Ignore non-test packets */ + if (eth->h_proto != 0) + goto out; + + /* Expect no metadata */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) > 0) + goto out; + + /* Packet write to trigger unclone in prologue */ + eth->h_proto = 42; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +/* + * Check that skb_meta dynptr is writable but empty if prog writes to packet + * _metadata_ using a dynptr slice. Applies only to cloned skbs. + */ +SEC("tc") +int clone_dynptr_empty_on_meta_slice_write(struct __sk_buff *ctx) +{ + struct bpf_dynptr data, meta; + const struct ethhdr *eth; + __u8 *md; + + bpf_dynptr_from_skb(ctx, 0, &data); + eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); + if (!eth) + goto out; + /* Ignore non-test packets */ + if (eth->h_proto != 0) + goto out; + + /* Expect no metadata */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) > 0) + goto out; + + /* Metadata write to trigger unclone in prologue */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); + if (md) + *md = 42; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +/* + * Check that skb_meta dynptr is read-only before prog writes to packet payload + * using dynptr_write helper. Applies only to cloned skbs. + */ +SEC("tc") +int clone_dynptr_rdonly_before_data_dynptr_write(struct __sk_buff *ctx) +{ + struct bpf_dynptr data, meta; + const struct ethhdr *eth; + + bpf_dynptr_from_skb(ctx, 0, &data); + eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); + if (!eth) + goto out; + /* Ignore non-test packets */ + if (eth->h_proto != 0) + goto out; + + /* Expect read-only metadata before unclone */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + if (!bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != META_SIZE) + goto out; + + /* Helper write to payload will unclone the packet */ + bpf_dynptr_write(&data, offsetof(struct ethhdr, h_proto), "x", 1, 0); + + /* Expect no metadata after unclone */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != 0) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +/* + * Check that skb_meta dynptr is read-only if prog writes to packet + * metadata using dynptr_write helper. Applies only to cloned skbs. + */ +SEC("tc") +int clone_dynptr_rdonly_before_meta_dynptr_write(struct __sk_buff *ctx) +{ + struct bpf_dynptr data, meta; + const struct ethhdr *eth; + + bpf_dynptr_from_skb(ctx, 0, &data); + eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); + if (!eth) + goto out; + /* Ignore non-test packets */ + if (eth->h_proto != 0) + goto out; + + /* Expect read-only metadata */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + if (!bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != META_SIZE) + goto out; + + /* Metadata write. Expect failure. */ + bpf_dynptr_from_skb_meta(ctx, 0, &meta); + if (bpf_dynptr_write(&meta, 0, "x", 1, 0) != -EINVAL) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_pull_data.c b/tools/testing/selftests/bpf/progs/test_xdp_pull_data.c new file mode 100644 index 000000000000..c41a21413eaa --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_pull_data.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +int xdpf_sz; +int sinfo_sz; +int data_len; +int pull_len; + +#define XDP_PACKET_HEADROOM 256 + +SEC("xdp.frags") +int xdp_find_sizes(struct xdp_md *ctx) +{ + xdpf_sz = sizeof(struct xdp_frame); + sinfo_sz = __PAGE_SIZE - XDP_PACKET_HEADROOM - + (ctx->data_end - ctx->data); + + return XDP_PASS; +} + +SEC("xdp.frags") +int xdp_pull_data_prog(struct xdp_md *ctx) +{ + __u8 *data_end = (void *)(long)ctx->data_end; + __u8 *data = (void *)(long)ctx->data; + __u8 *val_p; + int err; + + if (data_len != data_end - data) + return XDP_DROP; + + err = bpf_xdp_pull_data(ctx, pull_len); + if (err) + return XDP_DROP; + + val_p = (void *)(long)ctx->data + 1024; + if (val_p + 1 > (void *)(long)ctx->data_end) + return XDP_DROP; + + if (*val_p != 0xbb) + return XDP_DROP; + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/timer_interrupt.c b/tools/testing/selftests/bpf/progs/timer_interrupt.c new file mode 100644 index 000000000000..19180a455f40 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_interrupt.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +#define CLOCK_MONOTONIC 1 + +int preempt_count; +int in_interrupt; +int in_interrupt_cb; + +struct elem { + struct bpf_timer t; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} array SEC(".maps"); + +static int timer_in_interrupt(void *map, int *key, struct bpf_timer *timer) +{ + preempt_count = get_preempt_count(); + in_interrupt_cb = bpf_in_interrupt(); + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(test_timer_interrupt) +{ + struct bpf_timer *timer; + int key = 0; + + timer = bpf_map_lookup_elem(&array, &key); + if (!timer) + return 0; + + in_interrupt = bpf_in_interrupt(); + bpf_timer_init(timer, &array, CLOCK_MONOTONIC); + bpf_timer_set_callback(timer, timer_in_interrupt); + bpf_timer_start(timer, 0, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/tracing_failure.c b/tools/testing/selftests/bpf/progs/tracing_failure.c index d41665d2ec8c..65e485c4468c 100644 --- a/tools/testing/selftests/bpf/progs/tracing_failure.c +++ b/tools/testing/selftests/bpf/progs/tracing_failure.c @@ -18,3 +18,15 @@ int BPF_PROG(test_spin_unlock, struct bpf_spin_lock *lock) { return 0; } + +SEC("?fentry/__rcu_read_lock") +int BPF_PROG(tracing_deny) +{ + return 0; +} + +SEC("?fexit/do_exit") +int BPF_PROG(fexit_noreturns) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/tracing_struct.c b/tools/testing/selftests/bpf/progs/tracing_struct.c index c435a3a8328a..d460732e2023 100644 --- a/tools/testing/selftests/bpf/progs/tracing_struct.c +++ b/tools/testing/selftests/bpf/progs/tracing_struct.c @@ -18,6 +18,18 @@ struct bpf_testmod_struct_arg_3 { int b[]; }; +union bpf_testmod_union_arg_1 { + char a; + short b; + struct bpf_testmod_struct_arg_1 arg; +}; + +union bpf_testmod_union_arg_2 { + int a; + long b; + struct bpf_testmod_struct_arg_2 arg; +}; + long t1_a_a, t1_a_b, t1_b, t1_c, t1_ret, t1_nregs; __u64 t1_reg0, t1_reg1, t1_reg2, t1_reg3; long t2_a, t2_b_a, t2_b_b, t2_c, t2_ret; @@ -26,6 +38,9 @@ long t4_a_a, t4_b, t4_c, t4_d, t4_e_a, t4_e_b, t4_ret; long t5_ret; int t6; +long ut1_a_a, ut1_b, ut1_c; +long ut2_a, ut2_b_a, ut2_b_b; + SEC("fentry/bpf_testmod_test_struct_arg_1") int BPF_PROG2(test_struct_arg_1, struct bpf_testmod_struct_arg_2, a, int, b, int, c) { @@ -130,4 +145,22 @@ int BPF_PROG2(test_struct_arg_11, struct bpf_testmod_struct_arg_3 *, a) return 0; } +SEC("fexit/bpf_testmod_test_union_arg_1") +int BPF_PROG2(test_union_arg_1, union bpf_testmod_union_arg_1, a, int, b, int, c) +{ + ut1_a_a = a.arg.a; + ut1_b = b; + ut1_c = c; + return 0; +} + +SEC("fexit/bpf_testmod_test_union_arg_2") +int BPF_PROG2(test_union_arg_2, int, a, union bpf_testmod_union_arg_2, b) +{ + ut2_a = a; + ut2_b_a = b.arg.a; + ut2_b_b = b.arg.b; + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c index 044a6d78923e..3d5f30c29ae3 100644 --- a/tools/testing/selftests/bpf/progs/trigger_bench.c +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -97,6 +97,12 @@ int bench_trigger_kprobe_multi(void *ctx) return 0; } +SEC("?kprobe.multi/bpf_get_numa_node_id") +int bench_kprobe_multi_empty(void *ctx) +{ + return 0; +} + SEC("?kretprobe.multi/bpf_get_numa_node_id") int bench_trigger_kretprobe_multi(void *ctx) { @@ -104,6 +110,12 @@ int bench_trigger_kretprobe_multi(void *ctx) return 0; } +SEC("?kretprobe.multi/bpf_get_numa_node_id") +int bench_kretprobe_multi_empty(void *ctx) +{ + return 0; +} + SEC("?fentry/bpf_get_numa_node_id") int bench_trigger_fentry(void *ctx) { diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall.c b/tools/testing/selftests/bpf/progs/uprobe_syscall.c index 8a4fa6c7ef59..e08c31669e5a 100644 --- a/tools/testing/selftests/bpf/progs/uprobe_syscall.c +++ b/tools/testing/selftests/bpf/progs/uprobe_syscall.c @@ -7,8 +7,8 @@ struct pt_regs regs; char _license[] SEC("license") = "GPL"; -SEC("uretprobe//proc/self/exe:uretprobe_regs_trigger") -int uretprobe(struct pt_regs *ctx) +SEC("uprobe") +int probe(struct pt_regs *ctx) { __builtin_memcpy(®s, ctx, sizeof(regs)); return 0; diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c index 0d7f1a7db2e2..915d38591bf6 100644 --- a/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c +++ b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include "vmlinux.h" #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/usdt.bpf.h> #include <string.h> struct pt_regs regs; @@ -8,10 +10,64 @@ struct pt_regs regs; char _license[] SEC("license") = "GPL"; int executed = 0; +int pid; + +SEC("uprobe") +int BPF_UPROBE(test_uprobe) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + executed++; + return 0; +} + +SEC("uretprobe") +int BPF_URETPROBE(test_uretprobe) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + executed++; + return 0; +} + +SEC("uprobe.multi") +int test_uprobe_multi(struct pt_regs *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + executed++; + return 0; +} SEC("uretprobe.multi") -int test(struct pt_regs *regs) +int test_uretprobe_multi(struct pt_regs *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + executed++; + return 0; +} + +SEC("uprobe.session") +int test_uprobe_session(struct pt_regs *ctx) { - executed = 1; + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + executed++; + return 0; +} + +SEC("usdt") +int test_usdt(struct pt_regs *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + executed++; return 0; } diff --git a/tools/testing/selftests/bpf/progs/uretprobe_stack.c b/tools/testing/selftests/bpf/progs/uretprobe_stack.c index 9fdcf396b8f4..a2951e2f1711 100644 --- a/tools/testing/selftests/bpf/progs/uretprobe_stack.c +++ b/tools/testing/selftests/bpf/progs/uretprobe_stack.c @@ -26,8 +26,8 @@ int usdt_len; SEC("uprobe//proc/self/exe:target_1") int BPF_UPROBE(uprobe_1) { - /* target_1 is recursive wit depth of 2, so we capture two separate - * stack traces, depending on which occurence it is + /* target_1 is recursive with depth of 2, so we capture two separate + * stack traces, depending on which occurrence it is */ static bool recur = false; diff --git a/tools/testing/selftests/bpf/progs/verifier_and.c b/tools/testing/selftests/bpf/progs/verifier_and.c index e97e518516b6..2b4fdca162be 100644 --- a/tools/testing/selftests/bpf/progs/verifier_and.c +++ b/tools/testing/selftests/bpf/progs/verifier_and.c @@ -85,8 +85,14 @@ l0_%=: r0 = r0; \ SEC("socket") __description("check known subreg with unknown reg") -__success __failure_unpriv __msg_unpriv("R1 !read_ok") +__success __success_unpriv __retval(0) +#ifdef SPEC_V1 +__xlated_unpriv("if w0 < 0x1 goto pc+2") +__xlated_unpriv("nospec") /* inserted to prevent `R1 !read_ok'` */ +__xlated_unpriv("goto pc-1") /* `r1 = *(u32*)(r1 + 512)`, sanitized dead code */ +__xlated_unpriv("r0 = 0") +#endif __naked void known_subreg_with_unknown_reg(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_arena.c b/tools/testing/selftests/bpf/progs/verifier_arena.c index 67509c5d3982..7f4827eede3c 100644 --- a/tools/testing/selftests/bpf/progs/verifier_arena.c +++ b/tools/testing/selftests/bpf/progs/verifier_arena.c @@ -3,6 +3,7 @@ #define BPF_NO_KFUNC_PROTOTYPES #include <vmlinux.h> +#include <errno.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" @@ -114,6 +115,111 @@ int basic_alloc3(void *ctx) return 0; } +SEC("syscall") +__success __retval(0) +int basic_reserve1(void *ctx) +{ +#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) + char __arena *page; + int ret; + + page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0); + if (!page) + return 1; + + page += __PAGE_SIZE; + + /* Reserve the second page */ + ret = bpf_arena_reserve_pages(&arena, page, 1); + if (ret) + return 2; + + /* Try to explicitly allocate the reserved page. */ + page = bpf_arena_alloc_pages(&arena, page, 1, NUMA_NO_NODE, 0); + if (page) + return 3; + + /* Try to implicitly allocate the page (since there's only 2 of them). */ + page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0); + if (page) + return 4; +#endif + return 0; +} + +SEC("syscall") +__success __retval(0) +int basic_reserve2(void *ctx) +{ +#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) + char __arena *page; + int ret; + + page = arena_base(&arena); + ret = bpf_arena_reserve_pages(&arena, page, 1); + if (ret) + return 1; + + page = bpf_arena_alloc_pages(&arena, page, 1, NUMA_NO_NODE, 0); + if ((u64)page) + return 2; +#endif + return 0; +} + +/* Reserve the same page twice, should return -EBUSY. */ +SEC("syscall") +__success __retval(0) +int reserve_twice(void *ctx) +{ +#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) + char __arena *page; + int ret; + + page = arena_base(&arena); + + ret = bpf_arena_reserve_pages(&arena, page, 1); + if (ret) + return 1; + + ret = bpf_arena_reserve_pages(&arena, page, 1); + if (ret != -EBUSY) + return 2; +#endif + return 0; +} + +/* Try to reserve past the end of the arena. */ +SEC("syscall") +__success __retval(0) +int reserve_invalid_region(void *ctx) +{ +#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) + char __arena *page; + int ret; + + /* Try a NULL pointer. */ + ret = bpf_arena_reserve_pages(&arena, NULL, 3); + if (ret != -EINVAL) + return 1; + + page = arena_base(&arena); + + ret = bpf_arena_reserve_pages(&arena, page, 3); + if (ret != -EINVAL) + return 2; + + ret = bpf_arena_reserve_pages(&arena, page, 4096); + if (ret != -EINVAL) + return 3; + + ret = bpf_arena_reserve_pages(&arena, page, (1ULL << 32) - 1); + if (ret != -EINVAL) + return 4; +#endif + return 0; +} + SEC("iter.s/bpf_map") __success __log_level(2) int iter_maps1(struct bpf_iter__bpf_map *ctx) diff --git a/tools/testing/selftests/bpf/progs/verifier_arena_large.c b/tools/testing/selftests/bpf/progs/verifier_arena_large.c index f94f30cf1bb8..f19e15400b3e 100644 --- a/tools/testing/selftests/bpf/progs/verifier_arena_large.c +++ b/tools/testing/selftests/bpf/progs/verifier_arena_large.c @@ -67,6 +67,104 @@ int big_alloc1(void *ctx) return 0; } +/* Try to access a reserved page. Behavior should be identical with accessing unallocated pages. */ +SEC("syscall") +__success __retval(0) +int access_reserved(void *ctx) +{ +#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) + volatile char __arena *page; + char __arena *base; + const size_t len = 4; + int ret, i; + + /* Get a separate region of the arena. */ + page = base = arena_base(&arena) + 16384 * PAGE_SIZE; + + ret = bpf_arena_reserve_pages(&arena, base, len); + if (ret) + return 1; + + /* Try to dirty reserved memory. */ + for (i = 0; i < len && can_loop; i++) + *page = 0x5a; + + for (i = 0; i < len && can_loop; i++) { + page = (volatile char __arena *)(base + i * PAGE_SIZE); + + /* + * Error out in case either the write went through, + * or the address has random garbage. + */ + if (*page == 0x5a) + return 2 + 2 * i; + + if (*page) + return 2 + 2 * i + 1; + } +#endif + return 0; +} + +/* Try to allocate a region overlapping with a reservation. */ +SEC("syscall") +__success __retval(0) +int request_partially_reserved(void *ctx) +{ +#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) + volatile char __arena *page; + char __arena *base; + int ret; + + /* Add an arbitrary page offset. */ + page = base = arena_base(&arena) + 4096 * __PAGE_SIZE; + + ret = bpf_arena_reserve_pages(&arena, base + 3 * __PAGE_SIZE, 4); + if (ret) + return 1; + + page = bpf_arena_alloc_pages(&arena, base, 5, NUMA_NO_NODE, 0); + if ((u64)page != 0ULL) + return 2; +#endif + return 0; +} + +SEC("syscall") +__success __retval(0) +int free_reserved(void *ctx) +{ +#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) + char __arena *addr; + char __arena *page; + int ret; + + /* Add an arbitrary page offset. */ + addr = arena_base(&arena) + 32768 * __PAGE_SIZE; + + page = bpf_arena_alloc_pages(&arena, addr, 2, NUMA_NO_NODE, 0); + if (!page) + return 1; + + ret = bpf_arena_reserve_pages(&arena, addr + 2 * __PAGE_SIZE, 2); + if (ret) + return 2; + + /* + * Reserved and allocated pages should be interchangeable for + * bpf_arena_free_pages(). Free a reserved and an allocated + * page with a single call. + */ + bpf_arena_free_pages(&arena, addr + __PAGE_SIZE , 2); + + /* The free call above should have succeeded, so this allocation should too. */ + page = bpf_arena_alloc_pages(&arena, addr + __PAGE_SIZE, 2, NUMA_NO_NODE, 0); + if (!page) + return 3; +#endif + return 0; +} + #if defined(__BPF_FEATURE_ADDR_SPACE_CAST) #define PAGE_CNT 100 __u8 __arena * __arena page[PAGE_CNT]; /* occupies the first page */ @@ -142,6 +240,7 @@ int big_alloc2(void *ctx) return 5; bpf_arena_free_pages(&arena, (void __arena *)pg, 2); page[i] = NULL; + barrier(); page[i + 1] = NULL; cond_break; } diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index 0eb33bb801b5..0a72e0228ea9 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -2,6 +2,7 @@ /* Converted from tools/testing/selftests/bpf/verifier/bounds.c */ #include <linux/bpf.h> +#include <../../../include/linux/filter.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" @@ -620,8 +621,14 @@ l1_%=: exit; \ SEC("socket") __description("bounds check mixed 32bit and 64bit arithmetic. test1") -__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'") +__success __success_unpriv __retval(0) +#ifdef SPEC_V1 +__xlated_unpriv("goto pc+2") +__xlated_unpriv("nospec") /* inserted to prevent `R0 invalid mem access 'scalar'` */ +__xlated_unpriv("goto pc-1") /* sanitized dead code */ +__xlated_unpriv("exit") +#endif __naked void _32bit_and_64bit_arithmetic_test1(void) { asm volatile (" \ @@ -643,8 +650,14 @@ l1_%=: exit; \ SEC("socket") __description("bounds check mixed 32bit and 64bit arithmetic. test2") -__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'") +__success __success_unpriv __retval(0) +#ifdef SPEC_V1 +__xlated_unpriv("goto pc+2") +__xlated_unpriv("nospec") /* inserted to prevent `R0 invalid mem access 'scalar'` */ +__xlated_unpriv("goto pc-1") /* sanitized dead code */ +__xlated_unpriv("exit") +#endif __naked void _32bit_and_64bit_arithmetic_test2(void) { asm volatile (" \ @@ -691,9 +704,14 @@ l0_%=: r0 = 0; \ SEC("socket") __description("bounds check for reg = 0, reg xor 1") -__success __failure_unpriv -__msg_unpriv("R0 min value is outside of the allowed memory range") +__success __success_unpriv __retval(0) +#ifdef SPEC_V1 +__xlated_unpriv("if r1 != 0x0 goto pc+2") +__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */ +__xlated_unpriv("goto pc-1") /* sanitized dead code */ +__xlated_unpriv("r0 = 0") +#endif __naked void reg_0_reg_xor_1(void) { asm volatile (" \ @@ -719,9 +737,14 @@ l1_%=: r0 = 0; \ SEC("socket") __description("bounds check for reg32 = 0, reg32 xor 1") -__success __failure_unpriv -__msg_unpriv("R0 min value is outside of the allowed memory range") +__success __success_unpriv __retval(0) +#ifdef SPEC_V1 +__xlated_unpriv("if w1 != 0x0 goto pc+2") +__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */ +__xlated_unpriv("goto pc-1") /* sanitized dead code */ +__xlated_unpriv("r0 = 0") +#endif __naked void reg32_0_reg32_xor_1(void) { asm volatile (" \ @@ -747,9 +770,14 @@ l1_%=: r0 = 0; \ SEC("socket") __description("bounds check for reg = 2, reg xor 3") -__success __failure_unpriv -__msg_unpriv("R0 min value is outside of the allowed memory range") +__success __success_unpriv __retval(0) +#ifdef SPEC_V1 +__xlated_unpriv("if r1 > 0x0 goto pc+2") +__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */ +__xlated_unpriv("goto pc-1") /* sanitized dead code */ +__xlated_unpriv("r0 = 0") +#endif __naked void reg_2_reg_xor_3(void) { asm volatile (" \ @@ -829,9 +857,14 @@ l1_%=: r0 = 0; \ SEC("socket") __description("bounds check for reg > 0, reg xor 3") -__success __failure_unpriv -__msg_unpriv("R0 min value is outside of the allowed memory range") +__success __success_unpriv __retval(0) +#ifdef SPEC_V1 +__xlated_unpriv("if r1 >= 0x0 goto pc+2") +__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */ +__xlated_unpriv("goto pc-1") /* sanitized dead code */ +__xlated_unpriv("r0 = 0") +#endif __naked void reg_0_reg_xor_3(void) { asm volatile (" \ @@ -858,9 +891,14 @@ l1_%=: r0 = 0; \ SEC("socket") __description("bounds check for reg32 > 0, reg32 xor 3") -__success __failure_unpriv -__msg_unpriv("R0 min value is outside of the allowed memory range") +__success __success_unpriv __retval(0) +#ifdef SPEC_V1 +__xlated_unpriv("if w1 >= 0x0 goto pc+2") +__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */ +__xlated_unpriv("goto pc-1") /* sanitized dead code */ +__xlated_unpriv("r0 = 0") +#endif __naked void reg32_0_reg32_xor_3(void) { asm volatile (" \ @@ -888,7 +926,7 @@ l1_%=: r0 = 0; \ SEC("socket") __description("bounds check for non const xor src dst") __success __log_level(2) -__msg("5: (af) r0 ^= r6 ; R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))") +__msg("5: (af) r0 ^= r6 ; R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))") __naked void non_const_xor_src_dst(void) { asm volatile (" \ @@ -909,7 +947,7 @@ __naked void non_const_xor_src_dst(void) SEC("socket") __description("bounds check for non const or src dst") __success __log_level(2) -__msg("5: (4f) r0 |= r6 ; R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))") +__msg("5: (4f) r0 |= r6 ; R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))") __naked void non_const_or_src_dst(void) { asm volatile (" \ @@ -930,7 +968,7 @@ __naked void non_const_or_src_dst(void) SEC("socket") __description("bounds check for non const mul regs") __success __log_level(2) -__msg("5: (2f) r0 *= r6 ; R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=3825,var_off=(0x0; 0xfff))") +__msg("5: (2f) r0 *= r6 ; R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=3825,var_off=(0x0; 0xfff))") __naked void non_const_mul_regs(void) { asm volatile (" \ @@ -1028,7 +1066,7 @@ l0_%=: r0 = 0; \ SEC("xdp") __description("bound check with JMP_JSLT for crossing 64-bit signed boundary") __success __retval(0) -__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */ +__flag(BPF_F_TEST_REG_INVARIANTS) __naked void crossing_64_bit_signed_boundary_2(void) { asm volatile (" \ @@ -1203,7 +1241,7 @@ l0_%=: r0 = 0; \ SEC("tc") __description("multiply mixed sign bounds. test 1") __success __log_level(2) -__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=umin=0x1bc16d5cd4927ee1,smax=umax=0x1bc16d674ec80000,smax32=0x7ffffeff,umax32=0xfffffeff,var_off=(0x1bc16d4000000000; 0x3ffffffeff))") +__msg("r6 *= r7 {{.*}}; R6=scalar(smin=umin=0x1bc16d5cd4927ee1,smax=umax=0x1bc16d674ec80000,smax32=0x7ffffeff,umax32=0xfffffeff,var_off=(0x1bc16d4000000000; 0x3ffffffeff))") __naked void mult_mixed0_sign(void) { asm volatile ( @@ -1226,7 +1264,7 @@ __naked void mult_mixed0_sign(void) SEC("tc") __description("multiply mixed sign bounds. test 2") __success __log_level(2) -__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=smin32=-100,smax=smax32=200)") +__msg("r6 *= r7 {{.*}}; R6=scalar(smin=smin32=-100,smax=smax32=200)") __naked void mult_mixed1_sign(void) { asm volatile ( @@ -1249,7 +1287,7 @@ __naked void mult_mixed1_sign(void) SEC("tc") __description("multiply negative bounds") __success __log_level(2) -__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=umin=smin32=umin32=0x3ff280b0,smax=umax=smax32=umax32=0x3fff0001,var_off=(0x3ff00000; 0xf81ff))") +__msg("r6 *= r7 {{.*}}; R6=scalar(smin=umin=smin32=umin32=0x3ff280b0,smax=umax=smax32=umax32=0x3fff0001,var_off=(0x3ff00000; 0xf81ff))") __naked void mult_sign_bounds(void) { asm volatile ( @@ -1273,7 +1311,7 @@ __naked void mult_sign_bounds(void) SEC("tc") __description("multiply bounds that don't cross signed boundary") __success __log_level(2) -__msg("r8 *= r6 {{.*}}; R6_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=11,var_off=(0x0; 0xb)) R8_w=scalar(smin=0,smax=umax=0x7b96bb0a94a3a7cd,var_off=(0x0; 0x7fffffffffffffff))") +__msg("r8 *= r6 {{.*}}; R6=scalar(smin=smin32=0,smax=umax=smax32=umax32=11,var_off=(0x0; 0xb)) R8=scalar(smin=0,smax=umax=0x7b96bb0a94a3a7cd,var_off=(0x0; 0x7fffffffffffffff))") __naked void mult_no_sign_crossing(void) { asm volatile ( @@ -1293,7 +1331,7 @@ __naked void mult_no_sign_crossing(void) SEC("tc") __description("multiplication overflow, result in unbounded reg. test 1") __success __log_level(2) -__msg("r6 *= r7 {{.*}}; R6_w=scalar()") +__msg("r6 *= r7 {{.*}}; R6=scalar()") __naked void mult_unsign_ovf(void) { asm volatile ( @@ -1315,7 +1353,7 @@ __naked void mult_unsign_ovf(void) SEC("tc") __description("multiplication overflow, result in unbounded reg. test 2") __success __log_level(2) -__msg("r6 *= r7 {{.*}}; R6_w=scalar()") +__msg("r6 *= r7 {{.*}}; R6=scalar()") __naked void mult_sign_ovf(void) { asm volatile ( @@ -1334,4 +1372,341 @@ __naked void mult_sign_ovf(void) __imm(bpf_skb_store_bytes) : __clobber_all); } + +SEC("socket") +__description("64-bit addition, all outcomes overflow") +__success __log_level(2) +__msg("5: (0f) r3 += r3 {{.*}} R3=scalar(umin=0x4000000000000000,umax=0xfffffffffffffffe)") +__retval(0) +__naked void add64_full_overflow(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r4 = r0;" + "r3 = 0xa000000000000000 ll;" + "r3 |= r4;" + "r3 += r3;" + "r0 = 0;" + "exit" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("64-bit addition, partial overflow, result in unbounded reg") +__success __log_level(2) +__msg("4: (0f) r3 += r3 {{.*}} R3=scalar()") +__retval(0) +__naked void add64_partial_overflow(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r4 = r0;" + "r3 = 2;" + "r3 |= r4;" + "r3 += r3;" + "r0 = 0;" + "exit" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("32-bit addition overflow, all outcomes overflow") +__success __log_level(2) +__msg("4: (0c) w3 += w3 {{.*}} R3=scalar(smin=umin=umin32=0x40000000,smax=umax=umax32=0xfffffffe,var_off=(0x0; 0xffffffff))") +__retval(0) +__naked void add32_full_overflow(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "w4 = w0;" + "w3 = 0xa0000000;" + "w3 |= w4;" + "w3 += w3;" + "r0 = 0;" + "exit" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("32-bit addition, partial overflow, result in unbounded u32 bounds") +__success __log_level(2) +__msg("4: (0c) w3 += w3 {{.*}} R3=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))") +__retval(0) +__naked void add32_partial_overflow(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "w4 = w0;" + "w3 = 2;" + "w3 |= w4;" + "w3 += w3;" + "r0 = 0;" + "exit" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("64-bit subtraction, all outcomes underflow") +__success __log_level(2) +__msg("6: (1f) r3 -= r1 {{.*}} R3=scalar(umin=1,umax=0x8000000000000000)") +__retval(0) +__naked void sub64_full_overflow(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r1 = r0;" + "r2 = 0x8000000000000000 ll;" + "r1 |= r2;" + "r3 = 0;" + "r3 -= r1;" + "r0 = 0;" + "exit" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("64-bit subtraction, partial overflow, result in unbounded reg") +__success __log_level(2) +__msg("3: (1f) r3 -= r2 {{.*}} R3=scalar()") +__retval(0) +__naked void sub64_partial_overflow(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r3 = r0;" + "r2 = 1;" + "r3 -= r2;" + "r0 = 0;" + "exit" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("32-bit subtraction overflow, all outcomes underflow") +__success __log_level(2) +__msg("5: (1c) w3 -= w1 {{.*}} R3=scalar(smin=umin=umin32=1,smax=umax=umax32=0x80000000,var_off=(0x0; 0xffffffff))") +__retval(0) +__naked void sub32_full_overflow(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "w1 = w0;" + "w2 = 0x80000000;" + "w1 |= w2;" + "w3 = 0;" + "w3 -= w1;" + "r0 = 0;" + "exit" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("32-bit subtraction, partial overflow, result in unbounded u32 bounds") +__success __log_level(2) +__msg("3: (1c) w3 -= w2 {{.*}} R3=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))") +__retval(0) +__naked void sub32_partial_overflow(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "w3 = w0;" + "w2 = 1;" + "w3 -= w2;" + "r0 = 0;" + "exit" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("dead branch on jset, does not result in invariants violation error") +__success __log_level(2) +__retval(0) __flag(BPF_F_TEST_REG_INVARIANTS) +__naked void jset_range_analysis(void) +{ + asm volatile (" \ + call %[bpf_get_netns_cookie]; \ + if r0 == 0 goto l0_%=; \ + if r0 & 0xffffffff goto +0; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_netns_cookie) + : __clobber_all); +} + +/* This test covers the bounds deduction on 64bits when the s64 and u64 ranges + * overlap on the negative side. At instruction 7, the ranges look as follows: + * + * 0 umin=0xfffffcf1 umax=0xff..ff6e U64_MAX + * | [xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx] | + * |----------------------------|------------------------------| + * |xxxxxxxxxx] [xxxxxxxxxxxx| + * 0 smax=0xeffffeee smin=-655 -1 + * + * We should therefore deduce the following new bounds: + * + * 0 u64=[0xff..ffd71;0xff..ff6e] U64_MAX + * | [xxx] | + * |----------------------------|------------------------------| + * | [xxx] | + * 0 s64=[-655;-146] -1 + * + * Without the deduction cross sign boundary, we end up with an invariant + * violation error. + */ +SEC("socket") +__description("bounds deduction cross sign boundary, negative overlap") +__success __log_level(2) __flag(BPF_F_TEST_REG_INVARIANTS) +__msg("7: (1f) r0 -= r6 {{.*}} R0=scalar(smin=smin32=-655,smax=smax32=-146,umin=0xfffffffffffffd71,umax=0xffffffffffffff6e,umin32=0xfffffd71,umax32=0xffffff6e,var_off=(0xfffffffffffffc00; 0x3ff))") +__retval(0) +__naked void bounds_deduct_negative_overlap(void) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + w3 = w0; \ + w6 = (s8)w0; \ + r0 = (s8)r0; \ + if w6 >= 0xf0000000 goto l0_%=; \ + r0 += r6; \ + r6 += 400; \ + r0 -= r6; \ + if r3 < r0 goto l0_%=; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* This test covers the bounds deduction on 64bits when the s64 and u64 ranges + * overlap on the positive side. At instruction 3, the ranges look as follows: + * + * 0 umin=0 umax=0xffffffffffffff00 U64_MAX + * [xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx] | + * |----------------------------|------------------------------| + * |xxxxxxxx] [xxxxxxxx| + * 0 smax=127 smin=-128 -1 + * + * We should therefore deduce the following new bounds: + * + * 0 u64=[0;127] U64_MAX + * [xxxxxxxx] | + * |----------------------------|------------------------------| + * [xxxxxxxx] | + * 0 s64=[0;127] -1 + * + * Without the deduction cross sign boundary, the program is rejected due to + * the frame pointer write. + */ +SEC("socket") +__description("bounds deduction cross sign boundary, positive overlap") +__success __log_level(2) __flag(BPF_F_TEST_REG_INVARIANTS) +__msg("3: (2d) if r0 > r1 {{.*}} R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=127,var_off=(0x0; 0x7f))") +__retval(0) +__naked void bounds_deduct_positive_overlap(void) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + r0 = (s8)r0; \ + r1 = 0xffffffffffffff00; \ + if r0 > r1 goto l0_%=; \ + if r0 < 128 goto l0_%=; \ + r10 = 0; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* This test is the same as above, but the s64 and u64 ranges overlap in two + * places. At instruction 3, the ranges look as follows: + * + * 0 umin=0 umax=0xffffffffffffff80 U64_MAX + * [xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx] | + * |----------------------------|------------------------------| + * |xxxxxxxx] [xxxxxxxx| + * 0 smax=127 smin=-128 -1 + * + * 0xffffffffffffff80 = (u64)-128. We therefore can't deduce anything new and + * the program should fail due to the frame pointer write. + */ +SEC("socket") +__description("bounds deduction cross sign boundary, two overlaps") +__failure __flag(BPF_F_TEST_REG_INVARIANTS) +__msg("3: (2d) if r0 > r1 {{.*}} R0=scalar(smin=smin32=-128,smax=smax32=127,umax=0xffffffffffffff80)") +__msg("frame pointer is read only") +__naked void bounds_deduct_two_overlaps(void) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + r0 = (s8)r0; \ + r1 = 0xffffffffffffff80; \ + if r0 > r1 goto l0_%=; \ + if r0 < 128 goto l0_%=; \ + r10 = 0; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("dead jne branch due to disagreeing tnums") +__success __log_level(2) +__naked void jne_disagreeing_tnums(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + w0 = w0; \ + r0 >>= 30; \ + r0 <<= 30; \ + r1 = r0; \ + r1 += 1024; \ + if r1 != r0 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("dead jeq branch due to disagreeing tnums") +__success __log_level(2) +__naked void jeq_disagreeing_tnums(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + w0 = w0; \ + r0 >>= 30; \ + r0 <<= 30; \ + r1 = r0; \ + r1 += 1024; \ + if r1 == r0 goto +1; \ + exit; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c index c506afbdd936..260a6df264e3 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c @@ -159,13 +159,16 @@ __failure_unpriv __naked void deducing_bounds_from_const_10(void) { asm volatile (" \ + r6 = r1; \ r0 = 0; \ if r0 s<= 0 goto l0_%=; \ -l0_%=: /* Marks reg as unknown. */ \ - r0 = -r0; \ - r0 -= r1; \ +l0_%=: /* Marks r0 as unknown. */ \ + call %[bpf_get_prandom_u32]; \ + r0 -= r6; \ exit; \ -" ::: __clobber_all); +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c index c258b0722e04..fb4fa465d67c 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c +++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c @@ -660,19 +660,24 @@ __naked void may_goto_interaction_x86_64(void) SEC("raw_tp") __arch_arm64 -__log_level(4) __msg("stack depth 16") -/* may_goto counter at -16 */ -__xlated("0: *(u64 *)(r10 -16) =") -__xlated("1: r1 = 1") -__xlated("2: call bpf_get_smp_processor_id") +__log_level(4) __msg("stack depth 24") +/* may_goto counter at -24 */ +__xlated("0: *(u64 *)(r10 -24) =") +/* may_goto timestamp at -16 */ +__xlated("1: *(u64 *)(r10 -16) =") +__xlated("2: r1 = 1") +__xlated("3: call bpf_get_smp_processor_id") /* may_goto expansion starts */ -__xlated("3: r11 = *(u64 *)(r10 -16)") -__xlated("4: if r11 == 0x0 goto pc+3") -__xlated("5: r11 -= 1") -__xlated("6: *(u64 *)(r10 -16) = r11") +__xlated("4: r11 = *(u64 *)(r10 -24)") +__xlated("5: if r11 == 0x0 goto pc+6") +__xlated("6: r11 -= 1") +__xlated("7: if r11 != 0x0 goto pc+2") +__xlated("8: r11 = -24") +__xlated("9: call unknown") +__xlated("10: *(u64 *)(r10 -24) = r11") /* may_goto expansion ends */ -__xlated("7: *(u64 *)(r10 -8) = r1") -__xlated("8: exit") +__xlated("11: *(u64 *)(r10 -8) = r1") +__xlated("12: exit") __success __naked void may_goto_interaction_arm64(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_ctx.c b/tools/testing/selftests/bpf/progs/verifier_ctx.c index a83809a1dbbf..5ebf7d9bcc55 100644 --- a/tools/testing/selftests/bpf/progs/verifier_ctx.c +++ b/tools/testing/selftests/bpf/progs/verifier_ctx.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Converted from tools/testing/selftests/bpf/verifier/ctx.c */ -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include "bpf_misc.h" @@ -218,4 +218,78 @@ __naked void null_check_8_null_bind(void) : __clobber_all); } +#define narrow_load(type, ctx, field) \ + SEC(type) \ + __description("narrow load on field " #field " of " #ctx) \ + __failure __msg("invalid bpf_context access") \ + __naked void invalid_narrow_load##ctx##field(void) \ + { \ + asm volatile (" \ + r1 = *(u32 *)(r1 + %[off]); \ + r0 = 0; \ + exit;" \ + : \ + : __imm_const(off, offsetof(struct ctx, field) + 4) \ + : __clobber_all); \ + } + +narrow_load("cgroup/getsockopt", bpf_sockopt, sk); +narrow_load("cgroup/getsockopt", bpf_sockopt, optval); +narrow_load("cgroup/getsockopt", bpf_sockopt, optval_end); +narrow_load("tc", __sk_buff, sk); +narrow_load("cgroup/bind4", bpf_sock_addr, sk); +narrow_load("sockops", bpf_sock_ops, sk); +narrow_load("sockops", bpf_sock_ops, skb_data); +narrow_load("sockops", bpf_sock_ops, skb_data_end); +narrow_load("sockops", bpf_sock_ops, skb_hwtstamp); + +#define unaligned_access(type, ctx, field) \ + SEC(type) \ + __description("unaligned access on field " #field " of " #ctx) \ + __failure __msg("invalid bpf_context access") \ + __naked void unaligned_ctx_access_##ctx##field(void) \ + { \ + asm volatile (" \ + r1 = *(u%[size] *)(r1 + %[off]); \ + r0 = 0; \ + exit;" \ + : \ + : __imm_const(size, sizeof_field(struct ctx, field) * 8), \ + __imm_const(off, offsetof(struct ctx, field) + 1) \ + : __clobber_all); \ + } + +unaligned_access("flow_dissector", __sk_buff, data); +unaligned_access("netfilter", bpf_nf_ctx, skb); + +#define padding_access(type, ctx, prev_field, sz) \ + SEC(type) \ + __description("access on " #ctx " padding after " #prev_field) \ + __naked void padding_ctx_access_##ctx(void) \ + { \ + asm volatile (" \ + r1 = *(u%[size] *)(r1 + %[off]); \ + r0 = 0; \ + exit;" \ + : \ + : __imm_const(size, sz * 8), \ + __imm_const(off, offsetofend(struct ctx, prev_field)) \ + : __clobber_all); \ + } + +__failure __msg("invalid bpf_context access") +padding_access("cgroup/bind4", bpf_sock_addr, msg_src_ip6[3], 4); + +__success +padding_access("sk_lookup", bpf_sk_lookup, remote_port, 2); + +__failure __msg("invalid bpf_context access") +padding_access("tc", __sk_buff, tstamp_type, 2); + +__failure __msg("invalid bpf_context access") +padding_access("cgroup/post_bind4", bpf_sock, dst_port, 2); + +__failure __msg("invalid bpf_context access") +padding_access("sk_reuseport", sk_reuseport_md, hash, 4); + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_div_overflow.c b/tools/testing/selftests/bpf/progs/verifier_div_overflow.c index 458984da804c..34e0c012ee76 100644 --- a/tools/testing/selftests/bpf/progs/verifier_div_overflow.c +++ b/tools/testing/selftests/bpf/progs/verifier_div_overflow.c @@ -77,7 +77,7 @@ l0_%=: exit; \ SEC("tc") __description("MOD32 overflow, check 1") -__success __retval(INT_MIN) +__success __retval(_INT_MIN) __naked void mod32_overflow_check_1(void) { asm volatile (" \ @@ -92,7 +92,7 @@ __naked void mod32_overflow_check_1(void) SEC("tc") __description("MOD32 overflow, check 2") -__success __retval(INT_MIN) +__success __retval(_INT_MIN) __naked void mod32_overflow_check_2(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c index 4ab0ef18d7eb..6630a92b1b47 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c @@ -179,4 +179,132 @@ int BPF_PROG(trusted_acq_rel, struct task_struct *task, u64 clone_flags) return subprog_trusted_acq_rel(task); } +__weak int subprog_untrusted_bad_tags(struct task_struct *task __arg_untrusted __arg_nullable) +{ + return task->pid; +} + +SEC("tp_btf/sys_enter") +__failure +__msg("arg#0 untrusted cannot be combined with any other tags") +int untrusted_bad_tags(void *ctx) +{ + return subprog_untrusted_bad_tags(0); +} + +struct local_type_wont_be_accepted {}; + +__weak int subprog_untrusted_bad_type(struct local_type_wont_be_accepted *p __arg_untrusted) +{ + return 0; +} + +SEC("tp_btf/sys_enter") +__failure +__msg("arg#0 reference type('STRUCT local_type_wont_be_accepted') has no matches") +int untrusted_bad_type(void *ctx) +{ + return subprog_untrusted_bad_type(bpf_rdonly_cast(0, 0)); +} + +__weak int subprog_untrusted(const volatile struct task_struct *restrict task __arg_untrusted) +{ + return task->pid; +} + +SEC("tp_btf/sys_enter") +__success +__log_level(2) +__msg("r1 = {{.*}}; {{.*}}R1=trusted_ptr_task_struct()") +__msg("Func#1 ('subprog_untrusted') is global and assumed valid.") +__msg("Validating subprog_untrusted() func#1...") +__msg(": R1=untrusted_ptr_task_struct") +int trusted_to_untrusted(void *ctx) +{ + return subprog_untrusted(bpf_get_current_task_btf()); +} + +char mem[16]; +u32 off; + +SEC("tp_btf/sys_enter") +__success +int anything_to_untrusted(void *ctx) +{ + /* untrusted to untrusted */ + subprog_untrusted(bpf_core_cast(0, struct task_struct)); + /* wrong type to untrusted */ + subprog_untrusted((void *)bpf_core_cast(0, struct bpf_verifier_env)); + /* map value to untrusted */ + subprog_untrusted((void *)mem); + /* scalar to untrusted */ + subprog_untrusted(0); + /* variable offset to untrusted (map) */ + subprog_untrusted((void *)mem + off); + /* variable offset to untrusted (trusted) */ + subprog_untrusted((void *)bpf_get_current_task_btf() + off); + return 0; +} + +__weak int subprog_untrusted2(struct task_struct *task __arg_untrusted) +{ + return subprog_trusted_task_nullable(task); +} + +SEC("tp_btf/sys_enter") +__failure +__msg("R1 type=untrusted_ptr_ expected=ptr_, trusted_ptr_, rcu_ptr_") +__msg("Caller passes invalid args into func#{{.*}} ('subprog_trusted_task_nullable')") +int untrusted_to_trusted(void *ctx) +{ + return subprog_untrusted2(bpf_get_current_task_btf()); +} + +__weak int subprog_void_untrusted(void *p __arg_untrusted) +{ + return *(int *)p; +} + +__weak int subprog_char_untrusted(char *p __arg_untrusted) +{ + return *(int *)p; +} + +__weak int subprog_enum_untrusted(enum bpf_attach_type *p __arg_untrusted) +{ + return *(int *)p; +} + +SEC("tp_btf/sys_enter") +__success +__log_level(2) +__msg("r1 = {{.*}}; {{.*}}R1=trusted_ptr_task_struct()") +__msg("Func#1 ('subprog_void_untrusted') is global and assumed valid.") +__msg("Validating subprog_void_untrusted() func#1...") +__msg(": R1=rdonly_untrusted_mem(sz=0)") +int trusted_to_untrusted_mem(void *ctx) +{ + return subprog_void_untrusted(bpf_get_current_task_btf()); +} + +SEC("tp_btf/sys_enter") +__success +int anything_to_untrusted_mem(void *ctx) +{ + /* untrusted to untrusted mem */ + subprog_void_untrusted(bpf_core_cast(0, struct task_struct)); + /* map value to untrusted mem */ + subprog_void_untrusted(mem); + /* scalar to untrusted mem */ + subprog_void_untrusted(0); + /* variable offset to untrusted mem (map) */ + subprog_void_untrusted((void *)mem + off); + /* variable offset to untrusted mem (trusted) */ + subprog_void_untrusted(bpf_get_current_task_btf() + off); + /* variable offset to untrusted char/enum (map) */ + subprog_char_untrusted(mem + off); + subprog_enum_untrusted((void *)mem + off); + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c index 52edee41caf6..c8494b682c31 100644 --- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c +++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c @@ -3,6 +3,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" +#include "bpf_arena_common.h" #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \ @@ -10,6 +11,12 @@ defined(__TARGET_ARCH_loongarch)) && \ __clang_major__ >= 18 +struct { + __uint(type, BPF_MAP_TYPE_ARENA); + __uint(map_flags, BPF_F_MMAPABLE); + __uint(max_entries, 1); +} arena SEC(".maps"); + SEC("socket") __description("LDSX, S8") __success __success_unpriv __retval(-2) @@ -65,7 +72,7 @@ __naked void ldsx_s32(void) SEC("socket") __description("LDSX, S8 range checking, privileged") __log_level(2) __success __retval(1) -__msg("R1_w=scalar(smin=smin32=-128,smax=smax32=127)") +__msg("R1=scalar(smin=smin32=-128,smax=smax32=127)") __naked void ldsx_s8_range_priv(void) { asm volatile ( @@ -256,6 +263,175 @@ __naked void ldsx_ctx_8(void) : __clobber_all); } +SEC("syscall") +__description("Arena LDSX Disasm") +__success +__arch_x86_64 +__jited("movslq 0x10(%rax,%r12), %r14") +__jited("movswq 0x18(%rax,%r12), %r14") +__jited("movsbq 0x20(%rax,%r12), %r14") +__jited("movslq 0x10(%rdi,%r12), %r15") +__jited("movswq 0x18(%rdi,%r12), %r15") +__jited("movsbq 0x20(%rdi,%r12), %r15") +__arch_arm64 +__jited("add x11, x7, x28") +__jited("ldrsw x21, [x11, #0x10]") +__jited("add x11, x7, x28") +__jited("ldrsh x21, [x11, #0x18]") +__jited("add x11, x7, x28") +__jited("ldrsb x21, [x11, #0x20]") +__jited("add x11, x0, x28") +__jited("ldrsw x22, [x11, #0x10]") +__jited("add x11, x0, x28") +__jited("ldrsh x22, [x11, #0x18]") +__jited("add x11, x0, x28") +__jited("ldrsb x22, [x11, #0x20]") +__naked void arena_ldsx_disasm(void *ctx) +{ + asm volatile ( + "r1 = %[arena] ll;" + "r2 = 0;" + "r3 = 1;" + "r4 = %[numa_no_node];" + "r5 = 0;" + "call %[bpf_arena_alloc_pages];" + "r0 = addr_space_cast(r0, 0x0, 0x1);" + "r1 = r0;" + "r8 = *(s32 *)(r0 + 16);" + "r8 = *(s16 *)(r0 + 24);" + "r8 = *(s8 *)(r0 + 32);" + "r9 = *(s32 *)(r1 + 16);" + "r9 = *(s16 *)(r1 + 24);" + "r9 = *(s8 *)(r1 + 32);" + "r0 = 0;" + "exit;" + :: __imm(bpf_arena_alloc_pages), + __imm_addr(arena), + __imm_const(numa_no_node, NUMA_NO_NODE) + : __clobber_all + ); +} + +SEC("syscall") +__description("Arena LDSX Exception") +__success __retval(0) +__arch_x86_64 +__arch_arm64 +__naked void arena_ldsx_exception(void *ctx) +{ + asm volatile ( + "r1 = %[arena] ll;" + "r0 = 0xdeadbeef;" + "r0 = addr_space_cast(r0, 0x0, 0x1);" + "r1 = 0x3fe;" + "*(u64 *)(r0 + 0) = r1;" + "r0 = *(s8 *)(r0 + 0);" + "exit;" + : + : __imm_addr(arena) + : __clobber_all + ); +} + +SEC("syscall") +__description("Arena LDSX, S8") +__success __retval(-1) +__arch_x86_64 +__arch_arm64 +__naked void arena_ldsx_s8(void *ctx) +{ + asm volatile ( + "r1 = %[arena] ll;" + "r2 = 0;" + "r3 = 1;" + "r4 = %[numa_no_node];" + "r5 = 0;" + "call %[bpf_arena_alloc_pages];" + "r0 = addr_space_cast(r0, 0x0, 0x1);" + "r1 = 0x3fe;" + "*(u64 *)(r0 + 0) = r1;" +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + "r0 = *(s8 *)(r0 + 0);" +#else + "r0 = *(s8 *)(r0 + 7);" +#endif + "r0 >>= 1;" + "exit;" + :: __imm(bpf_arena_alloc_pages), + __imm_addr(arena), + __imm_const(numa_no_node, NUMA_NO_NODE) + : __clobber_all + ); +} + +SEC("syscall") +__description("Arena LDSX, S16") +__success __retval(-1) +__arch_x86_64 +__arch_arm64 +__naked void arena_ldsx_s16(void *ctx) +{ + asm volatile ( + "r1 = %[arena] ll;" + "r2 = 0;" + "r3 = 1;" + "r4 = %[numa_no_node];" + "r5 = 0;" + "call %[bpf_arena_alloc_pages];" + "r0 = addr_space_cast(r0, 0x0, 0x1);" + "r1 = 0x3fffe;" + "*(u64 *)(r0 + 0) = r1;" +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + "r0 = *(s16 *)(r0 + 0);" +#else + "r0 = *(s16 *)(r0 + 6);" +#endif + "r0 >>= 1;" + "exit;" + :: __imm(bpf_arena_alloc_pages), + __imm_addr(arena), + __imm_const(numa_no_node, NUMA_NO_NODE) + : __clobber_all + ); +} + +SEC("syscall") +__description("Arena LDSX, S32") +__success __retval(-1) +__arch_x86_64 +__arch_arm64 +__naked void arena_ldsx_s32(void *ctx) +{ + asm volatile ( + "r1 = %[arena] ll;" + "r2 = 0;" + "r3 = 1;" + "r4 = %[numa_no_node];" + "r5 = 0;" + "call %[bpf_arena_alloc_pages];" + "r0 = addr_space_cast(r0, 0x0, 0x1);" + "r1 = 0xfffffffe;" + "*(u64 *)(r0 + 0) = r1;" +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + "r0 = *(s32 *)(r0 + 0);" +#else + "r0 = *(s32 *)(r0 + 4);" +#endif + "r0 >>= 1;" + "exit;" + :: __imm(bpf_arena_alloc_pages), + __imm_addr(arena), + __imm_const(numa_no_node, NUMA_NO_NODE) + : __clobber_all + ); +} + +/* to retain debug info for BTF generation */ +void kfunc_root(void) +{ + bpf_arena_alloc_pages(0, 0, 0, 0, 0); +} + #else SEC("socket") diff --git a/tools/testing/selftests/bpf/progs/verifier_live_stack.c b/tools/testing/selftests/bpf/progs/verifier_live_stack.c new file mode 100644 index 000000000000..c0e808509268 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_live_stack.c @@ -0,0 +1,294 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, long long); +} map SEC(".maps"); + +SEC("socket") +__log_level(2) +__msg("(0) frame 0 insn 2 +written -8") +__msg("(0) frame 0 insn 1 +live -24") +__msg("(0) frame 0 insn 1 +written -8") +__msg("(0) frame 0 insn 0 +live -8,-24") +__msg("(0) frame 0 insn 0 +written -8") +__msg("(0) live stack update done in 2 iterations") +__naked void simple_read_simple_write(void) +{ + asm volatile ( + "r1 = *(u64 *)(r10 - 8);" + "r2 = *(u64 *)(r10 - 24);" + "*(u64 *)(r10 - 8) = r1;" + "r0 = 0;" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("(0) frame 0 insn 1 +live -8") +__not_msg("(0) frame 0 insn 1 +written") +__msg("(0) live stack update done in 2 iterations") +__msg("(0) frame 0 insn 1 +live -16") +__msg("(0) frame 0 insn 1 +written -32") +__msg("(0) live stack update done in 2 iterations") +__naked void read_write_join(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "if r0 > 42 goto 1f;" + "r0 = *(u64 *)(r10 - 8);" + "*(u64 *)(r10 - 32) = r0;" + "*(u64 *)(r10 - 40) = r0;" + "exit;" +"1:" + "r0 = *(u64 *)(r10 - 16);" + "*(u64 *)(r10 - 32) = r0;" + "exit;" + :: __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("2: (25) if r0 > 0x2a goto pc+1") +__msg("7: (95) exit") +__msg("(0) frame 0 insn 2 +written -16") +__msg("(0) live stack update done in 2 iterations") +__msg("7: (95) exit") +__not_msg("(0) frame 0 insn 2") +__msg("(0) live stack update done in 1 iterations") +__naked void must_write_not_same_slot(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r1 = -8;" + "if r0 > 42 goto 1f;" + "r1 = -16;" +"1:" + "r2 = r10;" + "r2 += r1;" + "*(u64 *)(r2 + 0) = r0;" + "exit;" + :: __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("(0) frame 0 insn 0 +written -8,-16") +__msg("(0) live stack update done in 2 iterations") +__msg("(0) frame 0 insn 0 +written -8") +__msg("(0) live stack update done in 2 iterations") +__naked void must_write_not_same_type(void) +{ + asm volatile ( + "*(u64*)(r10 - 8) = 0;" + "r2 = r10;" + "r2 += -8;" + "r1 = %[map] ll;" + "call %[bpf_map_lookup_elem];" + "if r0 != 0 goto 1f;" + "r0 = r10;" + "r0 += -16;" +"1:" + "*(u64 *)(r0 + 0) = 42;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_map_lookup_elem), + __imm_addr(map) + : __clobber_all); +} + +SEC("socket") +__log_level(2) +__msg("(2,4) frame 0 insn 4 +written -8") +__msg("(2,4) live stack update done in 2 iterations") +__msg("(0) frame 0 insn 2 +written -8") +__msg("(0) live stack update done in 2 iterations") +__naked void caller_stack_write(void) +{ + asm volatile ( + "r1 = r10;" + "r1 += -8;" + "call write_first_param;" + "exit;" + ::: __clobber_all); +} + +static __used __naked void write_first_param(void) +{ + asm volatile ( + "*(u64 *)(r1 + 0) = 7;" + "r0 = 0;" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__log_level(2) +/* caller_stack_read() function */ +__msg("2: .12345.... (85) call pc+4") +__msg("5: .12345.... (85) call pc+1") +__msg("6: 0......... (95) exit") +/* read_first_param() function */ +__msg("7: .1........ (79) r0 = *(u64 *)(r1 +0)") +__msg("8: 0......... (95) exit") +/* update for callsite at (2) */ +__msg("(2,7) frame 0 insn 7 +live -8") +__msg("(2,7) live stack update done in 2 iterations") +__msg("(0) frame 0 insn 2 +live -8") +__msg("(0) live stack update done in 2 iterations") +/* update for callsite at (5) */ +__msg("(5,7) frame 0 insn 7 +live -16") +__msg("(5,7) live stack update done in 2 iterations") +__msg("(0) frame 0 insn 5 +live -16") +__msg("(0) live stack update done in 2 iterations") +__naked void caller_stack_read(void) +{ + asm volatile ( + "r1 = r10;" + "r1 += -8;" + "call read_first_param;" + "r1 = r10;" + "r1 += -16;" + "call read_first_param;" + "exit;" + ::: __clobber_all); +} + +static __used __naked void read_first_param(void) +{ + asm volatile ( + "r0 = *(u64 *)(r1 + 0);" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__flag(BPF_F_TEST_STATE_FREQ) +__log_level(2) +/* read_first_param2() function */ +__msg(" 9: .1........ (79) r0 = *(u64 *)(r1 +0)") +__msg("10: .......... (b7) r0 = 0") +__msg("11: 0......... (05) goto pc+0") +__msg("12: 0......... (95) exit") +/* + * The purpose of the test is to check that checkpoint in + * read_first_param2() stops path traversal. This will only happen if + * verifier understands that fp[0]-8 at insn (12) is not alive. + */ +__msg("12: safe") +__msg("processed 20 insns") +__naked void caller_stack_pruning(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "if r0 == 42 goto 1f;" + "r0 = %[map] ll;" +"1:" + "*(u64 *)(r10 - 8) = r0;" + "r1 = r10;" + "r1 += -8;" + /* + * fp[0]-8 is either pointer to map or a scalar, + * preventing state pruning at checkpoint created for call. + */ + "call read_first_param2;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm_addr(map) + : __clobber_all); +} + +static __used __naked void read_first_param2(void) +{ + asm volatile ( + "r0 = *(u64 *)(r1 + 0);" + "r0 = 0;" + /* + * Checkpoint at goto +0 should fire, + * as caller stack fp[0]-8 is not alive at this point. + */ + "goto +0;" + "exit;" + ::: __clobber_all); +} + +SEC("socket") +__flag(BPF_F_TEST_STATE_FREQ) +__failure +__msg("R1 type=scalar expected=map_ptr") +__naked void caller_stack_pruning_callback(void) +{ + asm volatile ( + "r0 = %[map] ll;" + "*(u64 *)(r10 - 8) = r0;" + "r1 = 2;" + "r2 = loop_cb ll;" + "r3 = r10;" + "r3 += -8;" + "r4 = 0;" + /* + * fp[0]-8 is either pointer to map or a scalar, + * preventing state pruning at checkpoint created for call. + */ + "call %[bpf_loop];" + "r0 = 42;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_loop), + __imm_addr(map) + : __clobber_all); +} + +static __used __naked void loop_cb(void) +{ + asm volatile ( + /* + * Checkpoint at function entry should not fire, as caller + * stack fp[0]-8 is alive at this point. + */ + "r6 = r2;" + "r1 = *(u64 *)(r6 + 0);" + "*(u64*)(r10 - 8) = 7;" + "r2 = r10;" + "r2 += -8;" + "call %[bpf_map_lookup_elem];" + /* + * This should stop verifier on a second loop iteration, + * but only if verifier correctly maintains that fp[0]-8 + * is still alive. + */ + "*(u64 *)(r6 + 0) = 0;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_map_lookup_elem), + __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* + * Because of a bug in verifier.c:compute_postorder() + * the program below overflowed traversal queue in that function. + */ +SEC("socket") +__naked void syzbot_postorder_bug1(void) +{ + asm volatile ( + "r0 = 0;" + "if r0 != 0 goto -1;" + "exit;" + ::: __clobber_all); +} diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c index e07b43b78fd2..fbdde80e7b90 100644 --- a/tools/testing/selftests/bpf/progs/verifier_loops1.c +++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c @@ -283,4 +283,25 @@ exit_%=: \ : __clobber_all); } +/* + * This test case triggered a bug in verifier.c:maybe_exit_scc(). + * Speculative execution path reaches stack access instruction, + * stops and triggers maybe_exit_scc() w/o accompanying maybe_enter_scc() call. + */ +SEC("socket") +__arch_x86_64 +__caps_unpriv(CAP_BPF) +__naked void maybe_exit_scc_bug1(void) +{ + asm volatile ( + "r0 = 100;" +"1:" + /* Speculative execution path reaches and stops here. */ + "*(u64 *)(r10 - 512) = r0;" + /* Condition is always false, but verifier speculatively executes the true branch. */ + "if r0 <= 0x0 goto 1b;" + "exit;" + ::: __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_map_in_map.c b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c index 7d088ba99ea5..16b761e510f0 100644 --- a/tools/testing/selftests/bpf/progs/verifier_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c @@ -139,4 +139,122 @@ __naked void on_the_inner_map_pointer(void) : __clobber_all); } +SEC("socket") +__description("map_ptr is never null") +__success +__naked void map_ptr_is_never_null(void) +{ + asm volatile (" \ + r0 = 0; \ + r1 = %[map_in_map] ll; \ + if r1 != 0 goto l0_%=; \ + r10 = 42; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_in_map) + : __clobber_all); +} + +SEC("socket") +__description("map_ptr is never null inner") +__success +__naked void map_ptr_is_never_null_inner(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_in_map] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l0_%=; \ + if r0 != 0 goto l0_%=; \ + r10 = 42; \ +l0_%=: exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_in_map) + : __clobber_all); +} + +SEC("socket") +__description("map_ptr is never null inner spill fill") +__success +__naked void map_ptr_is_never_null_inner_spill_fill(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u32*)(r10 - 4) = r1; \ + r2 = r10; \ + r2 += -4; \ + r1 = %[map_in_map] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 != 0 goto l0_%=; \ + exit; \ +l0_%=: *(u64 *)(r10 -16) = r0; \ + r1 = *(u64 *)(r10 -16); \ + if r1 == 0 goto l1_%=; \ + exit; \ +l1_%=: r10 = 42; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_in_map) + : __clobber_all); +} + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); + __array(values, struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(max_entries, 64 * 1024); + }); +} rb_in_map SEC(".maps"); + +struct rb_ctx { + void *rb; + struct bpf_dynptr dptr; +}; + +static __always_inline struct rb_ctx __rb_event_reserve(__u32 sz) +{ + struct rb_ctx rb_ctx = {}; + void *rb; + __u32 cpu = bpf_get_smp_processor_id(); + __u32 rb_slot = cpu & 1; + + rb = bpf_map_lookup_elem(&rb_in_map, &rb_slot); + if (!rb) + return rb_ctx; + + rb_ctx.rb = rb; + bpf_ringbuf_reserve_dynptr(rb, sz, 0, &rb_ctx.dptr); + + return rb_ctx; +} + +static __noinline void __rb_event_submit(struct rb_ctx *ctx) +{ + if (!ctx->rb) + return; + + /* If the verifier (incorrectly) concludes that ctx->rb can be + * NULL at this point, we'll get "BPF_EXIT instruction in main + * prog would lead to reference leak" error + */ + bpf_ringbuf_submit_dynptr(&ctx->dptr, 0); +} + +SEC("socket") +int map_ptr_is_never_null_rb(void *ctx) +{ + struct rb_ctx event_ctx = __rb_event_reserve(256); + __rb_event_submit(&event_ctx); + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_map_ptr.c b/tools/testing/selftests/bpf/progs/verifier_map_ptr.c index 11a079145966..e2767d27d8aa 100644 --- a/tools/testing/selftests/bpf/progs/verifier_map_ptr.c +++ b/tools/testing/selftests/bpf/progs/verifier_map_ptr.c @@ -70,10 +70,13 @@ __naked void bpf_map_ptr_write_rejected(void) : __clobber_all); } +/* The first element of struct bpf_map is a SHA256 hash of 32 bytes, accessing + * into this array is valid. The opts field is now at offset 33. + */ SEC("socket") __description("bpf_map_ptr: read non-existent field rejected") __failure -__msg("cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4") +__msg("cannot access ptr member ops with moff 32 in struct bpf_map with off 33 size 4") __failure_unpriv __msg_unpriv("access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN") __flag(BPF_F_ANY_ALIGNMENT) @@ -82,7 +85,7 @@ __naked void read_non_existent_field_rejected(void) asm volatile (" \ r6 = 0; \ r1 = %[map_array_48b] ll; \ - r6 = *(u32*)(r1 + 1); \ + r6 = *(u32*)(r1 + 33); \ r0 = 1; \ exit; \ " : diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c index 3966d827f288..6d1edaef9213 100644 --- a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c +++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c @@ -9,6 +9,8 @@ SEC("raw_tp") __description("may_goto 0") __arch_x86_64 +__arch_s390x +__arch_arm64 __xlated("0: r0 = 1") __xlated("1: exit") __success @@ -27,6 +29,8 @@ __naked void may_goto_simple(void) SEC("raw_tp") __description("batch 2 of may_goto 0") __arch_x86_64 +__arch_s390x +__arch_arm64 __xlated("0: r0 = 1") __xlated("1: exit") __success @@ -47,6 +51,8 @@ __naked void may_goto_batch_0(void) SEC("raw_tp") __description("may_goto batch with offsets 2/1/0") __arch_x86_64 +__arch_s390x +__arch_arm64 __xlated("0: r0 = 1") __xlated("1: exit") __success @@ -69,8 +75,10 @@ __naked void may_goto_batch_1(void) } SEC("raw_tp") -__description("may_goto batch with offsets 2/0 - x86_64") +__description("may_goto batch with offsets 2/0") __arch_x86_64 +__arch_s390x +__arch_arm64 __xlated("0: *(u64 *)(r10 -16) = 65535") __xlated("1: *(u64 *)(r10 -8) = 0") __xlated("2: r11 = *(u64 *)(r10 -16)") @@ -84,33 +92,7 @@ __xlated("9: r0 = 1") __xlated("10: r0 = 2") __xlated("11: exit") __success -__naked void may_goto_batch_2_x86_64(void) -{ - asm volatile ( - ".8byte %[may_goto1];" - ".8byte %[may_goto3];" - "r0 = 1;" - "r0 = 2;" - "exit;" - : - : __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)), - __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0)) - : __clobber_all); -} - -SEC("raw_tp") -__description("may_goto batch with offsets 2/0 - arm64") -__arch_arm64 -__xlated("0: *(u64 *)(r10 -8) = 8388608") -__xlated("1: r11 = *(u64 *)(r10 -8)") -__xlated("2: if r11 == 0x0 goto pc+3") -__xlated("3: r11 -= 1") -__xlated("4: *(u64 *)(r10 -8) = r11") -__xlated("5: r0 = 1") -__xlated("6: r0 = 2") -__xlated("7: exit") -__success -__naked void may_goto_batch_2_arm64(void) +__naked void may_goto_batch_2(void) { asm volatile ( ".8byte %[may_goto1];" diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c index 994bbc346d25..a4d8814eb5ed 100644 --- a/tools/testing/selftests/bpf/progs/verifier_movsx.c +++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c @@ -245,7 +245,13 @@ l0_%=: \ SEC("socket") __description("MOV32SX, S8, var_off not u32_max, positive after s8 extension") __success __retval(0) -__failure_unpriv __msg_unpriv("frame pointer is read only") +__success_unpriv +#ifdef SPEC_V1 +__xlated_unpriv("w0 = 0") +__xlated_unpriv("exit") +__xlated_unpriv("nospec") /* inserted to prevent `frame pointer is read only` */ +__xlated_unpriv("goto pc-1") +#endif __naked void mov64sx_s32_varoff_2(void) { asm volatile (" \ @@ -267,7 +273,13 @@ l0_%=: \ SEC("socket") __description("MOV32SX, S8, var_off not u32_max, negative after s8 extension") __success __retval(0) -__failure_unpriv __msg_unpriv("frame pointer is read only") +__success_unpriv +#ifdef SPEC_V1 +__xlated_unpriv("w0 = 0") +__xlated_unpriv("exit") +__xlated_unpriv("nospec") /* inserted to prevent `frame pointer is read only` */ +__xlated_unpriv("goto pc-1") +#endif __naked void mov64sx_s32_varoff_3(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_mul.c b/tools/testing/selftests/bpf/progs/verifier_mul.c new file mode 100644 index 000000000000..7145fe3351d5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_mul.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Nandakumar Edamana */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +/* Intended to test the abstract multiplication technique(s) used by + * the verifier. Using assembly to avoid compiler optimizations. + */ +SEC("fentry/bpf_fentry_test1") +void BPF_PROG(mul_precise, int x) +{ + /* First, force the verifier to be uncertain about the value: + * unsigned int a = (bpf_get_prandom_u32() & 0x2) | 0x1; + * + * Assuming the verifier is using tnum, a must be tnum{.v=0x1, .m=0x2}. + * Then a * 0x3 would be m0m1 (m for uncertain). Added imprecision + * would cause the following to fail, because the required return value + * is 0: + * return (a * 0x3) & 0x4); + */ + asm volatile ("\ + call %[bpf_get_prandom_u32];\ + r0 &= 0x2;\ + r0 |= 0x1;\ + r0 *= 0x3;\ + r0 &= 0x4;\ + if r0 != 0 goto l0_%=;\ + r0 = 0;\ + goto l1_%=;\ +l0_%=:\ + r0 = 1;\ +l1_%=:\ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c index 9fe5d255ee37..1fe090cd6744 100644 --- a/tools/testing/selftests/bpf/progs/verifier_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_precision.c @@ -144,21 +144,21 @@ SEC("?raw_tp") __success __log_level(2) /* * Without the bug fix there will be no history between "last_idx 3 first_idx 3" - * and "parent state regs=" lines. "R0_w=6" parts are here to help anchor + * and "parent state regs=" lines. "R0=6" parts are here to help anchor * expected log messages to the one specific mark_chain_precision operation. * * This is quite fragile: if verifier checkpointing heuristic changes, this * might need adjusting. */ -__msg("2: (07) r0 += 1 ; R0_w=6") +__msg("2: (07) r0 += 1 ; R0=6") __msg("3: (35) if r0 >= 0xa goto pc+1") __msg("mark_precise: frame0: last_idx 3 first_idx 3 subseq_idx -1") __msg("mark_precise: frame0: regs=r0 stack= before 2: (07) r0 += 1") __msg("mark_precise: frame0: regs=r0 stack= before 1: (07) r0 += 1") __msg("mark_precise: frame0: regs=r0 stack= before 4: (05) goto pc-4") __msg("mark_precise: frame0: regs=r0 stack= before 3: (35) if r0 >= 0xa goto pc+1") -__msg("mark_precise: frame0: parent state regs= stack=: R0_rw=P4") -__msg("3: R0_w=6") +__msg("mark_precise: frame0: parent state regs= stack=: R0=P4") +__msg("3: R0=6") __naked int state_loop_first_last_equal(void) { asm volatile ( @@ -231,4 +231,74 @@ __naked void bpf_cond_op_not_r10(void) ::: __clobber_all); } +SEC("lsm.s/socket_connect") +__success __log_level(2) +__msg("0: (b7) r0 = 1 ; R0=1") +__msg("1: (84) w0 = -w0 ; R0=0xffffffff") +__msg("mark_precise: frame0: last_idx 2 first_idx 0 subseq_idx -1") +__msg("mark_precise: frame0: regs=r0 stack= before 1: (84) w0 = -w0") +__msg("mark_precise: frame0: regs=r0 stack= before 0: (b7) r0 = 1") +__naked int bpf_neg_2(void) +{ + /* + * lsm.s/socket_connect requires a return value within [-4095, 0]. + * Returning -1 is allowed + */ + asm volatile ( + "r0 = 1;" + "w0 = -w0;" + "exit;" + ::: __clobber_all); +} + +SEC("lsm.s/socket_connect") +__failure __msg("At program exit the register R0 has") +__naked int bpf_neg_3(void) +{ + /* + * lsm.s/socket_connect requires a return value within [-4095, 0]. + * Returning -10000 is not allowed. + */ + asm volatile ( + "r0 = 10000;" + "w0 = -w0;" + "exit;" + ::: __clobber_all); +} + +SEC("lsm.s/socket_connect") +__success __log_level(2) +__msg("0: (b7) r0 = 1 ; R0=1") +__msg("1: (87) r0 = -r0 ; R0=-1") +__msg("mark_precise: frame0: last_idx 2 first_idx 0 subseq_idx -1") +__msg("mark_precise: frame0: regs=r0 stack= before 1: (87) r0 = -r0") +__msg("mark_precise: frame0: regs=r0 stack= before 0: (b7) r0 = 1") +__naked int bpf_neg_4(void) +{ + /* + * lsm.s/socket_connect requires a return value within [-4095, 0]. + * Returning -1 is allowed + */ + asm volatile ( + "r0 = 1;" + "r0 = -r0;" + "exit;" + ::: __clobber_all); +} + +SEC("lsm.s/socket_connect") +__failure __msg("At program exit the register R0 has") +__naked int bpf_neg_5(void) +{ + /* + * lsm.s/socket_connect requires a return value within [-4095, 0]. + * Returning -10000 is not allowed. + */ + asm volatile ( + "r0 = 10000;" + "r0 = -r0;" + "exit;" + ::: __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_private_stack.c b/tools/testing/selftests/bpf/progs/verifier_private_stack.c index fc91b414364e..1ecd34ebde19 100644 --- a/tools/testing/selftests/bpf/progs/verifier_private_stack.c +++ b/tools/testing/selftests/bpf/progs/verifier_private_stack.c @@ -8,7 +8,7 @@ /* From include/linux/filter.h */ #define MAX_BPF_STACK 512 -#if defined(__TARGET_ARCH_x86) +#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64) struct elem { struct bpf_timer t; @@ -30,6 +30,18 @@ __jited(" movabsq $0x{{.*}}, %r9") __jited(" addq %gs:{{.*}}, %r9") __jited(" movl $0x2a, %edi") __jited(" movq %rdi, -0x100(%r9)") +__arch_arm64 +__jited(" stp x25, x27, [sp, {{.*}}]!") +__jited(" mov x27, {{.*}}") +__jited(" movk x27, {{.*}}, lsl #16") +__jited(" movk x27, {{.*}}") +__jited(" mrs x10, TPIDR_EL{{[0-1]}}") +__jited(" add x27, x27, x10") +__jited(" add x25, x27, {{.*}}") +__jited(" mov x0, #0x2a") +__jited(" str x0, [x27]") +__jited("...") +__jited(" ldp x25, x27, [sp], {{.*}}") __naked void private_stack_single_prog(void) { asm volatile (" \ @@ -45,6 +57,9 @@ __description("No private stack") __success __arch_x86_64 __jited(" subq $0x8, %rsp") +__arch_arm64 +__jited(" mov x25, sp") +__jited(" sub sp, sp, #0x10") __naked void no_private_stack_nested(void) { asm volatile (" \ @@ -81,6 +96,19 @@ __jited(" pushq %r9") __jited(" callq 0x{{.*}}") __jited(" popq %r9") __jited(" xorl %eax, %eax") +__arch_arm64 +__jited(" stp x25, x27, [sp, {{.*}}]!") +__jited(" mov x27, {{.*}}") +__jited(" movk x27, {{.*}}, lsl #16") +__jited(" movk x27, {{.*}}") +__jited(" mrs x10, TPIDR_EL{{[0-1]}}") +__jited(" add x27, x27, x10") +__jited(" add x25, x27, {{.*}}") +__jited(" mov x0, #0x2a") +__jited(" str x0, [x27]") +__jited(" bl {{.*}}") +__jited("...") +__jited(" ldp x25, x27, [sp], {{.*}}") __naked void private_stack_nested_1(void) { asm volatile (" \ @@ -131,6 +159,24 @@ __jited(" movq %rdi, -0x200(%r9)") __jited(" pushq %r9") __jited(" callq") __jited(" popq %r9") +__arch_arm64 +__jited("func #1") +__jited("...") +__jited(" stp x25, x27, [sp, {{.*}}]!") +__jited(" mov x27, {{.*}}") +__jited(" movk x27, {{.*}}, lsl #16") +__jited(" movk x27, {{.*}}") +__jited(" mrs x10, TPIDR_EL{{[0-1]}}") +__jited(" add x27, x27, x10") +__jited(" add x25, x27, {{.*}}") +__jited(" bl 0x{{.*}}") +__jited(" add x7, x0, #0x0") +__jited(" mov x0, #0x2a") +__jited(" str x0, [x27]") +__jited(" bl 0x{{.*}}") +__jited(" add x7, x0, #0x0") +__jited(" mov x7, #0x0") +__jited(" ldp x25, x27, [sp], {{.*}}") __naked void private_stack_callback(void) { asm volatile (" \ @@ -154,6 +200,28 @@ __arch_x86_64 __jited(" pushq %r9") __jited(" callq") __jited(" popq %r9") +__arch_arm64 +__jited(" stp x29, x30, [sp, #-0x10]!") +__jited(" mov x29, sp") +__jited(" stp xzr, x26, [sp, #-0x10]!") +__jited(" mov x26, sp") +__jited(" stp x19, x20, [sp, #-0x10]!") +__jited(" stp x21, x22, [sp, #-0x10]!") +__jited(" stp x23, x24, [sp, #-0x10]!") +__jited(" stp x25, x26, [sp, #-0x10]!") +__jited(" stp x27, x28, [sp, #-0x10]!") +__jited(" mov x27, {{.*}}") +__jited(" movk x27, {{.*}}, lsl #16") +__jited(" movk x27, {{.*}}") +__jited(" mrs x10, TPIDR_EL{{[0-1]}}") +__jited(" add x27, x27, x10") +__jited(" add x25, x27, {{.*}}") +__jited(" mov x0, #0x2a") +__jited(" str x0, [x27]") +__jited(" mov x0, #0x0") +__jited(" bl 0x{{.*}}") +__jited(" add x7, x0, #0x0") +__jited(" ldp x27, x28, [sp], #0x10") int private_stack_exception_main_prog(void) { asm volatile (" \ @@ -179,6 +247,19 @@ __jited(" movq %rdi, -0x200(%r9)") __jited(" pushq %r9") __jited(" callq") __jited(" popq %r9") +__arch_arm64 +__jited(" stp x27, x28, [sp, #-0x10]!") +__jited(" mov x27, {{.*}}") +__jited(" movk x27, {{.*}}, lsl #16") +__jited(" movk x27, {{.*}}") +__jited(" mrs x10, TPIDR_EL{{[0-1]}}") +__jited(" add x27, x27, x10") +__jited(" add x25, x27, {{.*}}") +__jited(" mov x0, #0x2a") +__jited(" str x0, [x27]") +__jited(" bl 0x{{.*}}") +__jited(" add x7, x0, #0x0") +__jited(" ldp x27, x28, [sp], #0x10") int private_stack_exception_sub_prog(void) { asm volatile (" \ @@ -220,6 +301,10 @@ __description("Private stack, async callback, not nested") __success __retval(0) __arch_x86_64 __jited(" movabsq $0x{{.*}}, %r9") +__arch_arm64 +__jited(" mrs x10, TPIDR_EL{{[0-1]}}") +__jited(" add x27, x27, x10") +__jited(" add x25, x27, {{.*}}") int private_stack_async_callback_1(void) { struct bpf_timer *arr_timer; @@ -241,6 +326,8 @@ __description("Private stack, async callback, potential nesting") __success __retval(0) __arch_x86_64 __jited(" subq $0x100, %rsp") +__arch_arm64 +__jited(" sub sp, sp, #0x100") int private_stack_async_callback_2(void) { struct bpf_timer *arr_timer; diff --git a/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c b/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c index 683a882b3e6d..910365201f68 100644 --- a/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c +++ b/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c @@ -27,7 +27,7 @@ struct bpf_key {} __attribute__((preserve_access_index)); extern void bpf_key_put(struct bpf_key *key) __ksym; extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; -extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym; +extern struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym; /* BTF FUNC records are not generated for kfuncs referenced * from inline assembly. These records are necessary for diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c index 7c5e5e6d10eb..c0ce690ddb68 100644 --- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -349,11 +349,11 @@ __naked void precision_two_ids(void) SEC("socket") __success __log_level(2) __flag(BPF_F_TEST_STATE_FREQ) -/* check thar r0 and r6 have different IDs after 'if', +/* check that r0 and r6 have different IDs after 'if', * collect_linked_regs() can't tie more than 6 registers for a single insn. */ __msg("8: (25) if r0 > 0x7 goto pc+0 ; R0=scalar(id=1") -__msg("9: (bf) r6 = r6 ; R6_w=scalar(id=2") +__msg("9: (bf) r6 = r6 ; R6=scalar(id=2") /* check that r{0-5} are marked precise after 'if' */ __msg("frame0: regs=r0 stack= before 8: (25) if r0 > 0x7 goto pc+0") __msg("frame0: parent state regs=r0,r1,r2,r3,r4,r5 stack=:") @@ -779,12 +779,12 @@ __success __retval(0) /* Check that verifier believes r1/r0 are zero at exit */ __log_level(2) -__msg("4: (77) r1 >>= 32 ; R1_w=0") -__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0") +__msg("4: (77) r1 >>= 32 ; R1=0") +__msg("5: (bf) r0 = r1 ; R0=0 R1=0") __msg("6: (95) exit") __msg("from 3 to 4") -__msg("4: (77) r1 >>= 32 ; R1_w=0") -__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0") +__msg("4: (77) r1 >>= 32 ; R1=0") +__msg("5: (bf) r0 = r1 ; R0=0 R1=0") __msg("6: (95) exit") /* Verify that statements to randomize upper half of r1 had not been * generated. diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c index 0d5e56dffabb..2b4610b53382 100644 --- a/tools/testing/selftests/bpf/progs/verifier_sock.c +++ b/tools/testing/selftests/bpf/progs/verifier_sock.c @@ -1,14 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Converted from tools/testing/selftests/bpf/verifier/sock.c */ -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) -#define offsetofend(TYPE, MEMBER) \ - (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) - struct { __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); __uint(max_entries, 1); @@ -1073,6 +1069,48 @@ int invalidate_pkt_pointers_from_global_func(struct __sk_buff *sk) } __noinline +long xdp_pull_data2(struct xdp_md *x, __u32 len) +{ + return bpf_xdp_pull_data(x, len); +} + +__noinline +long xdp_pull_data1(struct xdp_md *x, __u32 len) +{ + return xdp_pull_data2(x, len); +} + +/* global function calls bpf_xdp_pull_data(), which invalidates packet + * pointers established before global function call. + */ +SEC("xdp") +__failure __msg("invalid mem access") +int invalidate_xdp_pkt_pointers_from_global_func(struct xdp_md *x) +{ + int *p = (void *)(long)x->data; + + if ((void *)(p + 1) > (void *)(long)x->data_end) + return XDP_DROP; + xdp_pull_data1(x, 0); + *p = 42; /* this is unsafe */ + return XDP_PASS; +} + +/* XDP packet changing kfunc calls invalidate packet pointers */ +SEC("xdp") +__failure __msg("invalid mem access") +int invalidate_xdp_pkt_pointers(struct xdp_md *x) +{ + int *p = (void *)(long)x->data; + + if ((void *)(p + 1) > (void *)(long)x->data_end) + return XDP_DROP; + bpf_xdp_pull_data(x, 0); + *p = 42; /* this is unsafe */ + return XDP_PASS; +} + +__noinline int tail_call(struct __sk_buff *sk) { bpf_tail_call_static(sk, &jmp_table, 0); diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index 1e5a511e8494..7a13dbd794b2 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -506,17 +506,17 @@ SEC("raw_tp") __log_level(2) __success /* fp-8 is spilled IMPRECISE value zero (represented by a zero value fake reg) */ -__msg("2: (7a) *(u64 *)(r10 -8) = 0 ; R10=fp0 fp-8_w=0") +__msg("2: (7a) *(u64 *)(r10 -8) = 0 ; R10=fp0 fp-8=0") /* but fp-16 is spilled IMPRECISE zero const reg */ -__msg("4: (7b) *(u64 *)(r10 -16) = r0 ; R0_w=0 R10=fp0 fp-16_w=0") +__msg("4: (7b) *(u64 *)(r10 -16) = r0 ; R0=0 R10=fp0 fp-16=0") /* validate that assigning R2 from STACK_SPILL with zero value doesn't mark register * precise immediately; if necessary, it will be marked precise later */ -__msg("6: (71) r2 = *(u8 *)(r10 -1) ; R2_w=0 R10=fp0 fp-8_w=0") +__msg("6: (71) r2 = *(u8 *)(r10 -1) ; R2=0 R10=fp0 fp-8=0") /* similarly, when R2 is assigned from spilled register, it is initially * imprecise, but will be marked precise later once it is used in precise context */ -__msg("10: (71) r2 = *(u8 *)(r10 -9) ; R2_w=0 R10=fp0 fp-16_w=0") +__msg("10: (71) r2 = *(u8 *)(r10 -9) ; R2=0 R10=fp0 fp-16=0") __msg("11: (0f) r1 += r2") __msg("mark_precise: frame0: last_idx 11 first_idx 0 subseq_idx -1") __msg("mark_precise: frame0: regs=r2 stack= before 10: (71) r2 = *(u8 *)(r10 -9)") @@ -598,7 +598,7 @@ __log_level(2) __success /* fp-4 is STACK_ZERO */ __msg("2: (62) *(u32 *)(r10 -4) = 0 ; R10=fp0 fp-8=0000????") -__msg("4: (71) r2 = *(u8 *)(r10 -1) ; R2_w=0 R10=fp0 fp-8=0000????") +__msg("4: (71) r2 = *(u8 *)(r10 -1) ; R2=0 R10=fp0 fp-8=0000????") __msg("5: (0f) r1 += r2") __msg("mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1") __msg("mark_precise: frame0: regs=r2 stack= before 4: (71) r2 = *(u8 *)(r10 -1)") @@ -640,25 +640,25 @@ SEC("raw_tp") __log_level(2) __flag(BPF_F_TEST_STATE_FREQ) __success /* make sure fp-8 is IMPRECISE fake register spill */ -__msg("3: (7a) *(u64 *)(r10 -8) = 1 ; R10=fp0 fp-8_w=1") +__msg("3: (7a) *(u64 *)(r10 -8) = 1 ; R10=fp0 fp-8=1") /* and fp-16 is spilled IMPRECISE const reg */ -__msg("5: (7b) *(u64 *)(r10 -16) = r0 ; R0_w=1 R10=fp0 fp-16_w=1") +__msg("5: (7b) *(u64 *)(r10 -16) = r0 ; R0=1 R10=fp0 fp-16=1") /* validate load from fp-8, which was initialized using BPF_ST_MEM */ -__msg("8: (79) r2 = *(u64 *)(r10 -8) ; R2_w=1 R10=fp0 fp-8=1") +__msg("8: (79) r2 = *(u64 *)(r10 -8) ; R2=1 R10=fp0 fp-8=1") __msg("9: (0f) r1 += r2") __msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1") __msg("mark_precise: frame0: regs=r2 stack= before 8: (79) r2 = *(u64 *)(r10 -8)") __msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6") /* note, fp-8 is precise, fp-16 is not yet precise, we'll get there */ -__msg("mark_precise: frame0: parent state regs= stack=-8: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_rw=P1 fp-16_w=1") +__msg("mark_precise: frame0: parent state regs= stack=-8: R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=P1 fp-16=1") __msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7") __msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0") __msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -16) = r0") __msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1") __msg("mark_precise: frame0: regs= stack=-8 before 3: (7a) *(u64 *)(r10 -8) = 1") -__msg("10: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1") +__msg("10: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1") /* validate load from fp-16, which was initialized using BPF_STX_MEM */ -__msg("12: (79) r2 = *(u64 *)(r10 -16) ; R2_w=1 R10=fp0 fp-16=1") +__msg("12: (79) r2 = *(u64 *)(r10 -16) ; R2=1 R10=fp0 fp-16=1") __msg("13: (0f) r1 += r2") __msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1") __msg("mark_precise: frame0: regs=r2 stack= before 12: (79) r2 = *(u64 *)(r10 -16)") @@ -668,12 +668,12 @@ __msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2") __msg("mark_precise: frame0: regs= stack=-16 before 8: (79) r2 = *(u64 *)(r10 -8)") __msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6") /* now both fp-8 and fp-16 are precise, very good */ -__msg("mark_precise: frame0: parent state regs= stack=-16: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_rw=P1 fp-16_rw=P1") +__msg("mark_precise: frame0: parent state regs= stack=-16: R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=P1 fp-16=P1") __msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7") __msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0") __msg("mark_precise: frame0: regs= stack=-16 before 5: (7b) *(u64 *)(r10 -16) = r0") __msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1") -__msg("14: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1") +__msg("14: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1") __naked void stack_load_preserves_const_precision(void) { asm volatile ( @@ -719,22 +719,22 @@ __success /* make sure fp-8 is 32-bit FAKE subregister spill */ __msg("3: (62) *(u32 *)(r10 -8) = 1 ; R10=fp0 fp-8=????1") /* but fp-16 is spilled IMPRECISE zero const reg */ -__msg("5: (63) *(u32 *)(r10 -16) = r0 ; R0_w=1 R10=fp0 fp-16=????1") +__msg("5: (63) *(u32 *)(r10 -16) = r0 ; R0=1 R10=fp0 fp-16=????1") /* validate load from fp-8, which was initialized using BPF_ST_MEM */ -__msg("8: (61) r2 = *(u32 *)(r10 -8) ; R2_w=1 R10=fp0 fp-8=????1") +__msg("8: (61) r2 = *(u32 *)(r10 -8) ; R2=1 R10=fp0 fp-8=????1") __msg("9: (0f) r1 += r2") __msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1") __msg("mark_precise: frame0: regs=r2 stack= before 8: (61) r2 = *(u32 *)(r10 -8)") __msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6") -__msg("mark_precise: frame0: parent state regs= stack=-8: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_r=????P1 fp-16=????1") +__msg("mark_precise: frame0: parent state regs= stack=-8: R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=????P1 fp-16=????1") __msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7") __msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0") __msg("mark_precise: frame0: regs= stack=-8 before 5: (63) *(u32 *)(r10 -16) = r0") __msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1") __msg("mark_precise: frame0: regs= stack=-8 before 3: (62) *(u32 *)(r10 -8) = 1") -__msg("10: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1") +__msg("10: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1") /* validate load from fp-16, which was initialized using BPF_STX_MEM */ -__msg("12: (61) r2 = *(u32 *)(r10 -16) ; R2_w=1 R10=fp0 fp-16=????1") +__msg("12: (61) r2 = *(u32 *)(r10 -16) ; R2=1 R10=fp0 fp-16=????1") __msg("13: (0f) r1 += r2") __msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1") __msg("mark_precise: frame0: regs=r2 stack= before 12: (61) r2 = *(u32 *)(r10 -16)") @@ -743,12 +743,12 @@ __msg("mark_precise: frame0: regs= stack=-16 before 10: (73) *(u8 *)(r1 +0) = r2 __msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2") __msg("mark_precise: frame0: regs= stack=-16 before 8: (61) r2 = *(u32 *)(r10 -8)") __msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6") -__msg("mark_precise: frame0: parent state regs= stack=-16: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_r=????P1 fp-16_r=????P1") +__msg("mark_precise: frame0: parent state regs= stack=-16: R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=????P1 fp-16=????P1") __msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7") __msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0") __msg("mark_precise: frame0: regs= stack=-16 before 5: (63) *(u32 *)(r10 -16) = r0") __msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1") -__msg("14: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1") +__msg("14: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1") __naked void stack_load_preserves_const_precision_subreg(void) { asm volatile ( diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index 9d415f7ce599..ac3e418c2a96 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -105,7 +105,7 @@ __msg("mark_precise: frame0: regs=r0 stack= before 4: (27) r0 *= 4") __msg("mark_precise: frame0: regs=r0 stack= before 3: (57) r0 &= 3") __msg("mark_precise: frame0: regs=r0 stack= before 10: (95) exit") __msg("mark_precise: frame1: regs=r0 stack= before 9: (bf) r0 = (s8)r10") -__msg("7: R0_w=scalar") +__msg("7: R0=scalar") __naked int fp_precise_subprog_result(void) { asm volatile ( @@ -141,7 +141,7 @@ __msg("mark_precise: frame1: regs=r0 stack= before 10: (bf) r0 = (s8)r1") * anyways, at which point we'll break precision chain */ __msg("mark_precise: frame1: regs=r1 stack= before 9: (bf) r1 = r10") -__msg("7: R0_w=scalar") +__msg("7: R0=scalar") __naked int sneaky_fp_precise_subprog_result(void) { asm volatile ( @@ -681,7 +681,7 @@ __msg("mark_precise: frame0: last_idx 10 first_idx 7 subseq_idx -1") __msg("mark_precise: frame0: regs=r7 stack= before 9: (bf) r1 = r8") __msg("mark_precise: frame0: regs=r7 stack= before 8: (27) r7 *= 4") __msg("mark_precise: frame0: regs=r7 stack= before 7: (79) r7 = *(u64 *)(r10 -8)") -__msg("mark_precise: frame0: parent state regs= stack=-8: R0_w=2 R6_w=1 R8_rw=map_value(map=.data.vals,ks=4,vs=16) R10=fp0 fp-8_rw=P1") +__msg("mark_precise: frame0: parent state regs= stack=-8: R0=2 R6=1 R8=map_value(map=.data.vals,ks=4,vs=16) R10=fp0 fp-8=P1") __msg("mark_precise: frame0: last_idx 18 first_idx 0 subseq_idx 7") __msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit") __msg("mark_precise: frame1: regs= stack= before 17: (0f) r0 += r2") diff --git a/tools/testing/selftests/bpf/progs/verifier_tailcall.c b/tools/testing/selftests/bpf/progs/verifier_tailcall.c new file mode 100644 index 000000000000..b4acce60fb9b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_tailcall.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} map_array SEC(".maps"); + +SEC("socket") +__description("invalid map type for tail call") +__failure __msg("expected prog array map for tail call") +__failure_unpriv +__naked void invalid_map_for_tail_call(void) +{ + asm volatile (" \ + r2 = %[map_array] ll; \ + r3 = 0; \ + call %[bpf_tail_call]; \ + exit; \ +" : + : __imm(bpf_tail_call), + __imm_addr(map_array) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_unpriv.c b/tools/testing/selftests/bpf/progs/verifier_unpriv.c index a4a5e2071604..28b4f7035ceb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_unpriv.c +++ b/tools/testing/selftests/bpf/progs/verifier_unpriv.c @@ -572,8 +572,14 @@ l0_%=: exit; \ SEC("socket") __description("alu32: mov u32 const") -__success __failure_unpriv __msg_unpriv("R7 invalid mem access 'scalar'") +__success __success_unpriv __retval(0) +#ifdef SPEC_V1 +__xlated_unpriv("if r0 == 0x0 goto pc+2") +__xlated_unpriv("nospec") /* inserted to prevent `R7 invalid mem access 'scalar'` */ +__xlated_unpriv("goto pc-1") /* sanitized dead code */ +__xlated_unpriv("exit") +#endif __naked void alu32_mov_u32_const(void) { asm volatile (" \ @@ -619,12 +625,11 @@ __naked void pass_pointer_to_tail_call(void) SEC("socket") __description("unpriv: cmp map pointer with zero") -__success __failure_unpriv __msg_unpriv("R1 pointer comparison") +__success __success_unpriv __retval(0) __naked void cmp_map_pointer_with_zero(void) { asm volatile (" \ - r1 = 0; \ r1 = %[map_hash_8b] ll; \ if r1 == 0 goto l0_%=; \ l0_%=: r0 = 0; \ @@ -635,6 +640,22 @@ l0_%=: r0 = 0; \ } SEC("socket") +__description("unpriv: cmp map pointer with const") +__success __failure_unpriv __msg_unpriv("R1 pointer comparison prohibited") +__retval(0) +__naked void cmp_map_pointer_with_const(void) +{ + asm volatile (" \ + r1 = %[map_hash_8b] ll; \ + if r1 == 0x0000beef goto l0_%=; \ +l0_%=: r0 = 0; \ + exit; \ +" : + : __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") __description("unpriv: write into frame pointer") __failure __msg("frame pointer is read only") __failure_unpriv @@ -723,4 +744,210 @@ l0_%=: r0 = 0; \ " ::: __clobber_all); } +SEC("socket") +__description("unpriv: Spectre v1 path-based type confusion of scalar as stack-ptr") +__success __success_unpriv __retval(0) +#ifdef SPEC_V1 +__xlated_unpriv("if r0 != 0x1 goto pc+2") +/* This nospec prevents the exploit because it forces the mispredicted (not + * taken) `if r0 != 0x0 goto l0_%=` to resolve before using r6 as a pointer. + * This causes the CPU to realize that `r6 = r9` should have never executed. It + * ensures that r6 always contains a readable stack slot ptr when the insn after + * the nospec executes. + */ +__xlated_unpriv("nospec") +__xlated_unpriv("r9 = *(u8 *)(r6 +0)") +#endif +__naked void unpriv_spec_v1_type_confusion(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + /* r0: pointer to a map array entry */ \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + /* r1, r2: prepared call args */ \ + r6 = r10; \ + r6 += -8; \ + /* r6: pointer to readable stack slot */ \ + r9 = 0xffffc900; \ + r9 <<= 32; \ + /* r9: scalar controlled by attacker */ \ + r0 = *(u64 *)(r0 + 0); /* cache miss */ \ + if r0 != 0x0 goto l0_%=; \ + r6 = r9; \ +l0_%=: if r0 != 0x1 goto l1_%=; \ + r9 = *(u8 *)(r6 + 0); \ +l1_%=: /* leak r9 */ \ + r9 &= 1; \ + r9 <<= 9; \ + *(u64*)(r10 - 8) = r9; \ + call %[bpf_map_lookup_elem]; \ + if r0 == 0 goto l2_%=; \ + /* leak secret into is_cached(map[0|512]): */ \ + r0 = *(u64 *)(r0 + 0); \ +l2_%=: \ + r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("unpriv: ldimm64 before Spectre v4 barrier") +__success __success_unpriv +__retval(0) +#ifdef SPEC_V4 +__xlated_unpriv("r1 = 0x2020200005642020") /* should not matter */ +__xlated_unpriv("*(u64 *)(r10 -8) = r1") +__xlated_unpriv("nospec") +#endif +__naked void unpriv_ldimm64_spectre_v4(void) +{ + asm volatile (" \ + r1 = 0x2020200005642020 ll; \ + *(u64 *)(r10 -8) = r1; \ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: Spectre v1 and v4 barrier") +__success __success_unpriv +__retval(0) +#ifdef SPEC_V1 +#ifdef SPEC_V4 +/* starts with r0 == r8 == r9 == 0 */ +__xlated_unpriv("if r8 != 0x0 goto pc+1") +__xlated_unpriv("goto pc+2") +__xlated_unpriv("if r9 == 0x0 goto pc+4") +__xlated_unpriv("r2 = r0") +/* Following nospec required to prevent following dangerous `*(u64 *)(NOT_FP -64) + * = r1` iff `if r9 == 0 goto pc+4` was mispredicted because of Spectre v1. The + * test therefore ensures the Spectre-v4--induced nospec does not prevent the + * Spectre-v1--induced speculative path from being fully analyzed. + */ +__xlated_unpriv("nospec") /* Spectre v1 */ +__xlated_unpriv("*(u64 *)(r2 -64) = r1") /* could be used to leak r2 */ +__xlated_unpriv("nospec") /* Spectre v4 */ +#endif +#endif +__naked void unpriv_spectre_v1_and_v4(void) +{ + asm volatile (" \ + r1 = 0; \ + *(u64*)(r10 - 8) = r1; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r8 = r0; \ + r2 = r10; \ + r2 += -8; \ + r1 = %[map_hash_8b] ll; \ + call %[bpf_map_lookup_elem]; \ + r9 = r0; \ + r0 = r10; \ + r1 = 0; \ + r2 = r10; \ + if r8 != 0 goto l0_%=; \ + if r9 != 0 goto l0_%=; \ + r0 = 0; \ +l0_%=: if r8 != 0 goto l1_%=; \ + goto l2_%=; \ +l1_%=: if r9 == 0 goto l3_%=; \ + r2 = r0; \ +l2_%=: *(u64 *)(r2 -64) = r1; \ +l3_%=: r0 = 0; \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_hash_8b) + : __clobber_all); +} + +SEC("socket") +__description("unpriv: Spectre v1 and v4 barrier (simple)") +__success __success_unpriv +__retval(0) +#ifdef SPEC_V1 +#ifdef SPEC_V4 +__xlated_unpriv("if r8 != 0x0 goto pc+1") +__xlated_unpriv("goto pc+2") +__xlated_unpriv("goto pc-1") /* if r9 == 0 goto l3_%= */ +__xlated_unpriv("goto pc-1") /* r2 = r0 */ +__xlated_unpriv("nospec") +__xlated_unpriv("*(u64 *)(r2 -64) = r1") +__xlated_unpriv("nospec") +#endif +#endif +__naked void unpriv_spectre_v1_and_v4_simple(void) +{ + asm volatile (" \ + r8 = 0; \ + r9 = 0; \ + r0 = r10; \ + r1 = 0; \ + r2 = r10; \ + if r8 != 0 goto l0_%=; \ + if r9 != 0 goto l0_%=; \ + r0 = 0; \ +l0_%=: if r8 != 0 goto l1_%=; \ + goto l2_%=; \ +l1_%=: if r9 == 0 goto l3_%=; \ + r2 = r0; \ +l2_%=: *(u64 *)(r2 -64) = r1; \ +l3_%=: r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + +SEC("socket") +__description("unpriv: ldimm64 before Spectre v1 and v4 barrier (simple)") +__success __success_unpriv +__retval(0) +#ifdef SPEC_V1 +#ifdef SPEC_V4 +__xlated_unpriv("if r8 != 0x0 goto pc+1") +__xlated_unpriv("goto pc+4") +__xlated_unpriv("goto pc-1") /* if r9 == 0 goto l3_%= */ +__xlated_unpriv("goto pc-1") /* r2 = r0 */ +__xlated_unpriv("goto pc-1") /* r1 = 0x2020200005642020 ll */ +__xlated_unpriv("goto pc-1") /* second part of ldimm64 */ +__xlated_unpriv("nospec") +__xlated_unpriv("*(u64 *)(r2 -64) = r1") +__xlated_unpriv("nospec") +#endif +#endif +__naked void unpriv_ldimm64_spectre_v1_and_v4_simple(void) +{ + asm volatile (" \ + r8 = 0; \ + r9 = 0; \ + r0 = r10; \ + r1 = 0; \ + r2 = r10; \ + if r8 != 0 goto l0_%=; \ + if r9 != 0 goto l0_%=; \ + r0 = 0; \ +l0_%=: if r8 != 0 goto l1_%=; \ + goto l2_%=; \ +l1_%=: if r9 == 0 goto l3_%=; \ + r2 = r0; \ + r1 = 0x2020200005642020 ll; \ +l2_%=: *(u64 *)(r2 -64) = r1; \ +l3_%=: r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c index a9ab37d3b9e2..2129e4353fd9 100644 --- a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c +++ b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c @@ -3,6 +3,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "../../../include/linux/filter.h" #include "bpf_misc.h" #define MAX_ENTRIES 11 @@ -146,6 +147,24 @@ l0_%=: exit; \ : __clobber_all); } +SEC("socket") +__description("map_ptr illegal alu op, map_ptr = -map_ptr") +__failure __msg("R0 invalid mem access 'scalar'") +__failure_unpriv __msg_unpriv("R0 pointer arithmetic prohibited") +__flag(BPF_F_ANY_ALIGNMENT) +__naked void map_ptr_illegal_alu_op(void) +{ + asm volatile (" \ + r0 = %[map_hash_48b] ll; \ + r0 = -r0; \ + r1 = 22; \ + *(u64*)(r0 + 0) = r1; \ + exit; \ +" : + : __imm_addr(map_hash_48b) + : __clobber_all); +} + SEC("flow_dissector") __description("flow_keys illegal alu op with variable offset") __failure __msg("R7 pointer arithmetic on flow_keys prohibited") @@ -165,4 +184,32 @@ __naked void flow_keys_illegal_variable_offset_alu(void) : __clobber_all); } +#define DEFINE_BAD_OFFSET_TEST(name, op, off, imm) \ + SEC("socket") \ + __failure __msg("BPF_ALU uses reserved fields") \ + __naked void name(void) \ + { \ + asm volatile( \ + "r0 = 1;" \ + ".8byte %[insn];" \ + "r0 = 0;" \ + "exit;" \ + : \ + : __imm_insn(insn, BPF_RAW_INSN((op), 0, 0, (off), (imm))) \ + : __clobber_all); \ + } + +/* + * Offset fields of 0 and 1 are legal for BPF_{DIV,MOD} instructions. + * Offset fields of 0 are legal for the rest of ALU instructions. + * Test that error is reported for illegal offsets, assuming that tests + * for legal offsets exist. + */ +DEFINE_BAD_OFFSET_TEST(bad_offset_divx, BPF_ALU64 | BPF_DIV | BPF_X, -1, 0) +DEFINE_BAD_OFFSET_TEST(bad_offset_modk, BPF_ALU64 | BPF_MOD | BPF_K, -1, 1) +DEFINE_BAD_OFFSET_TEST(bad_offset_addx, BPF_ALU64 | BPF_ADD | BPF_X, -1, 0) +DEFINE_BAD_OFFSET_TEST(bad_offset_divx2, BPF_ALU64 | BPF_DIV | BPF_X, 2, 0) +DEFINE_BAD_OFFSET_TEST(bad_offset_modk2, BPF_ALU64 | BPF_MOD | BPF_K, 2, 1) +DEFINE_BAD_OFFSET_TEST(bad_offset_addx2, BPF_ALU64 | BPF_ADD | BPF_X, 1, 0) + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c index 5ba6e53571c8..af7938ce56cb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c +++ b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c @@ -231,6 +231,10 @@ __retval(1) __naked void ptr_unknown_vs_unknown_lt(void) { asm volatile (" \ + r8 = r1; \ + call %[bpf_get_prandom_u32]; \ + r9 = r0; \ + r1 = r8; \ r0 = *(u32*)(r1 + %[__sk_buff_len]); \ r1 = 0; \ *(u64*)(r10 - 8) = r1; \ @@ -245,11 +249,11 @@ l1_%=: call %[bpf_map_lookup_elem]; \ r4 = *(u8*)(r0 + 0); \ if r4 == 1 goto l3_%=; \ r1 = 6; \ - r1 = -r1; \ + r1 = r9; \ r1 &= 0x3; \ goto l4_%=; \ l3_%=: r1 = 6; \ - r1 = -r1; \ + r1 = r9; \ r1 &= 0x7; \ l4_%=: r1 += r0; \ r0 = *(u8*)(r1 + 0); \ @@ -259,7 +263,8 @@ l2_%=: r0 = 1; \ : __imm(bpf_map_lookup_elem), __imm_addr(map_array_48b), __imm_addr(map_hash_16b), - __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)), + __imm(bpf_get_prandom_u32) : __clobber_all); } @@ -271,6 +276,10 @@ __retval(1) __naked void ptr_unknown_vs_unknown_gt(void) { asm volatile (" \ + r8 = r1; \ + call %[bpf_get_prandom_u32]; \ + r9 = r0; \ + r1 = r8; \ r0 = *(u32*)(r1 + %[__sk_buff_len]); \ r1 = 0; \ *(u64*)(r10 - 8) = r1; \ @@ -285,11 +294,11 @@ l1_%=: call %[bpf_map_lookup_elem]; \ r4 = *(u8*)(r0 + 0); \ if r4 == 1 goto l3_%=; \ r1 = 6; \ - r1 = -r1; \ + r1 = r9; \ r1 &= 0x7; \ goto l4_%=; \ l3_%=: r1 = 6; \ - r1 = -r1; \ + r1 = r9; \ r1 &= 0x3; \ l4_%=: r1 += r0; \ r0 = *(u8*)(r1 + 0); \ @@ -299,7 +308,8 @@ l2_%=: r0 = 1; \ : __imm(bpf_map_lookup_elem), __imm_addr(map_array_48b), __imm_addr(map_hash_16b), - __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)) + __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)), + __imm(bpf_get_prandom_u32) : __clobber_all); } @@ -398,7 +408,8 @@ l2_%=: r0 = 1; \ SEC("socket") __description("map access: mixing value pointer and scalar, 1") -__success __failure_unpriv __msg_unpriv("R2 pointer comparison prohibited") +__success __failure_unpriv +__msg_unpriv("R2 tried to add from different maps, paths or scalars, pointer arithmetic with it prohibited for !root") __retval(0) __naked void value_pointer_and_scalar_1(void) { @@ -433,6 +444,7 @@ l2_%=: /* common instruction */ \ l3_%=: /* branch B */ \ r0 = 0x13371337; \ /* verifier follows fall-through */ \ + /* unpriv: nospec (inserted to prevent `R2 pointer comparison prohibited`) */\ if r2 != 0x100000 goto l4_%=; \ r0 = 0; \ exit; \ @@ -450,7 +462,8 @@ l4_%=: /* fake-dead code; targeted from branch A to \ SEC("socket") __description("map access: mixing value pointer and scalar, 2") -__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'") +__success __failure_unpriv +__msg_unpriv("R2 tried to add from different maps, paths or scalars, pointer arithmetic with it prohibited for !root") __retval(0) __naked void value_pointer_and_scalar_2(void) { @@ -492,6 +505,7 @@ l4_%=: /* fake-dead code; targeted from branch A to \ * prevent dead code sanitization, rejected \ * via branch B however \ */ \ + /* unpriv: nospec (inserted to prevent `R0 invalid mem access 'scalar'`) */\ r0 = *(u8*)(r0 + 0); \ r0 = 0; \ exit; \ @@ -1296,9 +1310,13 @@ l0_%=: r0 = 1; \ SEC("socket") __description("map access: value_ptr -= unknown scalar, 2") -__success __failure_unpriv -__msg_unpriv("R0 pointer arithmetic of map value goes out of range") +__success __success_unpriv __retval(1) +#ifdef SPEC_V1 +__xlated_unpriv("r1 &= 7") +__xlated_unpriv("nospec") /* inserted to prevent `R0 pointer arithmetic of map value goes out of range` */ +__xlated_unpriv("r0 -= r1") +#endif __naked void value_ptr_unknown_scalar_2_2(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_var_off.c b/tools/testing/selftests/bpf/progs/verifier_var_off.c index 1d36d01b746e..f345466bca68 100644 --- a/tools/testing/selftests/bpf/progs/verifier_var_off.c +++ b/tools/testing/selftests/bpf/progs/verifier_var_off.c @@ -114,8 +114,8 @@ __naked void stack_write_priv_vs_unpriv(void) } /* Similar to the previous test, but this time also perform a read from the - * address written to with a variable offset. The read is allowed, showing that, - * after a variable-offset write, a priviledged program can read the slots that + * address written to with a variable offet. The read is allowed, showing that, + * after a variable-offset write, a privileged program can read the slots that * were in the range of that write (even if the verifier doesn't actually know if * the slot being read was really written to or not. * @@ -157,7 +157,7 @@ __naked void stack_write_followed_by_read(void) SEC("socket") __description("variable-offset stack write clobbers spilled regs") __failure -/* In the priviledged case, dereferencing a spilled-and-then-filled +/* In the privileged case, dereferencing a spilled-and-then-filled * register is rejected because the previous variable offset stack * write might have overwritten the spilled pointer (i.e. we lose track * of the spilled register when we analyze the write). diff --git a/tools/testing/selftests/bpf/test_bpftool_map.sh b/tools/testing/selftests/bpf/test_bpftool_map.sh new file mode 100755 index 000000000000..515b1df0501e --- /dev/null +++ b/tools/testing/selftests/bpf/test_bpftool_map.sh @@ -0,0 +1,398 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +TESTNAME="bpftool_map" +BPF_FILE="security_bpf_map.bpf.o" +BPF_ITER_FILE="bpf_iter_map_elem.bpf.o" +PROTECTED_MAP_NAME="prot_map" +NOT_PROTECTED_MAP_NAME="not_prot_map" +BPF_FS_TMP_PARENT="/tmp" +BPF_FS_PARENT=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts) +BPF_FS_PARENT=${BPF_FS_PARENT:-$BPF_FS_TMP_PARENT} +# bpftool will mount bpf file system under BPF_DIR if it is not mounted +# under BPF_FS_PARENT. +BPF_DIR="$BPF_FS_PARENT/test_$TESTNAME" +SCRIPT_DIR=$(dirname $(realpath "$0")) +BPF_FILE_PATH="$SCRIPT_DIR/$BPF_FILE" +BPF_ITER_FILE_PATH="$SCRIPT_DIR/$BPF_ITER_FILE" +BPFTOOL_PATH="bpftool" +# Assume the script is located under tools/testing/selftests/bpf/ +KDIR_ROOT_DIR=$(realpath "$SCRIPT_DIR"/../../../../) + +_cleanup() +{ + set +eu + + # If BPF_DIR is a mount point this will not remove the mount point itself. + [ -d "$BPF_DIR" ] && rm -rf "$BPF_DIR" 2> /dev/null + + # Unmount if BPF filesystem was temporarily created. + if [ "$BPF_FS_PARENT" = "$BPF_FS_TMP_PARENT" ]; then + # A loop and recursive unmount are required as bpftool might + # create multiple mounts. For example, a bind mount of the directory + # to itself. The bind mount is created to change mount propagation + # flags on an actual mount point. + max_attempts=3 + attempt=0 + while mountpoint -q "$BPF_DIR" && [ $attempt -lt $max_attempts ]; do + umount -R "$BPF_DIR" 2>/dev/null + attempt=$((attempt+1)) + done + + # The directory still exists. Remove it now. + [ -d "$BPF_DIR" ] && rm -rf "$BPF_DIR" 2>/dev/null + fi +} + +cleanup_skip() +{ + echo "selftests: $TESTNAME [SKIP]" + _cleanup + + exit $ksft_skip +} + +cleanup() +{ + if [ "$?" = 0 ]; then + echo "selftests: $TESTNAME [PASS]" + else + echo "selftests: $TESTNAME [FAILED]" + fi + _cleanup +} + +check_root_privileges() { + if [ $(id -u) -ne 0 ]; then + echo "Need root privileges" + exit $ksft_skip + fi +} + +# Function to verify bpftool path. +# Parameters: +# $1: bpftool path +verify_bpftool_path() { + local bpftool_path="$1" + if ! "$bpftool_path" version > /dev/null 2>&1; then + echo "Could not run test without bpftool" + exit $ksft_skip + fi +} + +# Function to verify BTF support. +# The test requires BTF support for fmod_ret programs. +verify_btf_support() { + if [ ! -f /sys/kernel/btf/vmlinux ]; then + echo "Could not run test without BTF support" + exit $ksft_skip + fi +} + +# Function to initialize map entries with keys [0..2] and values set to 0. +# Parameters: +# $1: Map name +# $2: bpftool path +initialize_map_entries() { + local map_name="$1" + local bpftool_path="$2" + + for key in 0 1 2; do + "$bpftool_path" map update name "$map_name" key $key 0 0 0 value 0 0 0 $key + done +} + +# Test read access to the map. +# Parameters: +# $1: Name command (name/pinned) +# $2: Map name +# $3: bpftool path +# $4: key +access_for_read() { + local name_cmd="$1" + local map_name="$2" + local bpftool_path="$3" + local key="$4" + + # Test read access to the map. + if ! "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then + echo " Read access to $key in $map_name failed" + exit 1 + fi + + # Test read access to map's BTF data. + if ! "$bpftool_path" btf dump map "$name_cmd" "$map_name" 1>/dev/null; then + echo " Read access to $map_name for BTF data failed" + exit 1 + fi +} + +# Test write access to the map. +# Parameters: +# $1: Name command (name/pinned) +# $2: Map name +# $3: bpftool path +# $4: key +# $5: Whether write should succeed (true/false) +access_for_write() { + local name_cmd="$1" + local map_name="$2" + local bpftool_path="$3" + local key="$4" + local write_should_succeed="$5" + local value="1 1 1 1" + + if "$bpftool_path" map update "$name_cmd" "$map_name" key $key value \ + $value 2>/dev/null; then + if [ "$write_should_succeed" = "false" ]; then + echo " Write access to $key in $map_name succeeded but should have failed" + exit 1 + fi + else + if [ "$write_should_succeed" = "true" ]; then + echo " Write access to $key in $map_name failed but should have succeeded" + exit 1 + fi + fi +} + +# Test entry deletion for the map. +# Parameters: +# $1: Name command (name/pinned) +# $2: Map name +# $3: bpftool path +# $4: key +# $5: Whether write should succeed (true/false) +access_for_deletion() { + local name_cmd="$1" + local map_name="$2" + local bpftool_path="$3" + local key="$4" + local write_should_succeed="$5" + local value="1 1 1 1" + + # Test deletion by key for the map. + # Before deleting, check the key exists. + if ! "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then + echo " Key $key does not exist in $map_name" + exit 1 + fi + + # Delete by key. + if "$bpftool_path" map delete "$name_cmd" "$map_name" key $key 2>/dev/null; then + if [ "$write_should_succeed" = "false" ]; then + echo " Deletion for $key in $map_name succeeded but should have failed" + exit 1 + fi + else + if [ "$write_should_succeed" = "true" ]; then + echo " Deletion for $key in $map_name failed but should have succeeded" + exit 1 + fi + fi + + # After deleting, check the entry existence according to the expected status. + if "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then + if [ "$write_should_succeed" = "true" ]; then + echo " Key $key for $map_name was not deleted but should have been deleted" + exit 1 + fi + else + if [ "$write_should_succeed" = "false" ]; then + echo "Key $key for $map_name was deleted but should have not been deleted" + exit 1 + fi + fi + + # Test creation of map's deleted entry, if deletion was successful. + # Otherwise, the entry exists. + if "$bpftool_path" map update "$name_cmd" "$map_name" key $key value \ + $value 2>/dev/null; then + if [ "$write_should_succeed" = "false" ]; then + echo " Write access to $key in $map_name succeeded after deletion attempt but should have failed" + exit 1 + fi + else + if [ "$write_should_succeed" = "true" ]; then + echo " Write access to $key in $map_name failed after deletion attempt but should have succeeded" + exit 1 + fi + fi +} + +# Test map elements iterator. +# Parameters: +# $1: Name command (name/pinned) +# $2: Map name +# $3: bpftool path +# $4: BPF_DIR +# $5: bpf iterator object file path +iterate_map_elem() { + local name_cmd="$1" + local map_name="$2" + local bpftool_path="$3" + local bpf_dir="$4" + local bpf_file="$5" + local pin_path="$bpf_dir/map_iterator" + + "$bpftool_path" iter pin "$bpf_file" "$pin_path" map "$name_cmd" "$map_name" + if [ ! -f "$pin_path" ]; then + echo " Failed to pin iterator to $pin_path" + exit 1 + fi + + cat "$pin_path" 1>/dev/null + rm "$pin_path" 2>/dev/null +} + +# Function to test map access with configurable write expectations +# Parameters: +# $1: Name command (name/pinned) +# $2: Map name +# $3: bpftool path +# $4: key for rw +# $5: key to delete +# $6: Whether write should succeed (true/false) +# $7: BPF_DIR +# $8: bpf iterator object file path +access_map() { + local name_cmd="$1" + local map_name="$2" + local bpftool_path="$3" + local key_for_rw="$4" + local key_to_del="$5" + local write_should_succeed="$6" + local bpf_dir="$7" + local bpf_iter_file_path="$8" + + access_for_read "$name_cmd" "$map_name" "$bpftool_path" "$key_for_rw" + access_for_write "$name_cmd" "$map_name" "$bpftool_path" "$key_for_rw" \ + "$write_should_succeed" + access_for_deletion "$name_cmd" "$map_name" "$bpftool_path" "$key_to_del" \ + "$write_should_succeed" + iterate_map_elem "$name_cmd" "$map_name" "$bpftool_path" "$bpf_dir" \ + "$bpf_iter_file_path" +} + +# Function to test map access with configurable write expectations +# Parameters: +# $1: Map name +# $2: bpftool path +# $3: BPF_DIR +# $4: Whether write should succeed (true/false) +# $5: bpf iterator object file path +test_map_access() { + local map_name="$1" + local bpftool_path="$2" + local bpf_dir="$3" + local pin_path="$bpf_dir/${map_name}_pinned" + local write_should_succeed="$4" + local bpf_iter_file_path="$5" + + # Test access to the map by name. + access_map "name" "$map_name" "$bpftool_path" "0 0 0 0" "1 0 0 0" \ + "$write_should_succeed" "$bpf_dir" "$bpf_iter_file_path" + + # Pin the map to the BPF filesystem + "$bpftool_path" map pin name "$map_name" "$pin_path" + if [ ! -e "$pin_path" ]; then + echo " Failed to pin $map_name" + exit 1 + fi + + # Test access to the pinned map. + access_map "pinned" "$pin_path" "$bpftool_path" "0 0 0 0" "2 0 0 0" \ + "$write_should_succeed" "$bpf_dir" "$bpf_iter_file_path" +} + +# Function to test map creation and map-of-maps +# Parameters: +# $1: bpftool path +# $2: BPF_DIR +test_map_creation_and_map_of_maps() { + local bpftool_path="$1" + local bpf_dir="$2" + local outer_map_name="outer_map_tt" + local inner_map_name="inner_map_tt" + + "$bpftool_path" map create "$bpf_dir/$inner_map_name" type array key 4 \ + value 4 entries 4 name "$inner_map_name" + if [ ! -f "$bpf_dir/$inner_map_name" ]; then + echo " Failed to create inner map file at $bpf_dir/$outer_map_name" + return 1 + fi + + "$bpftool_path" map create "$bpf_dir/$outer_map_name" type hash_of_maps \ + key 4 value 4 entries 2 name "$outer_map_name" inner_map name "$inner_map_name" + if [ ! -f "$bpf_dir/$outer_map_name" ]; then + echo " Failed to create outer map file at $bpf_dir/$outer_map_name" + return 1 + fi + + # Add entries to the outer map by name and by pinned path. + "$bpftool_path" map update pinned "$bpf_dir/$outer_map_name" key 0 0 0 0 \ + value pinned "$bpf_dir/$inner_map_name" + "$bpftool_path" map update name "$outer_map_name" key 1 0 0 0 value \ + name "$inner_map_name" + + # The outer map should be full by now. + # The following map update command is expected to fail. + if "$bpftool_path" map update name "$outer_map_name" key 2 0 0 0 value name \ + "$inner_map_name" 2>/dev/null; then + echo " Update for $outer_map_name succeeded but should have failed" + exit 1 + fi +} + +# Function to test map access with the btf list command +# Parameters: +# $1: bpftool path +test_map_access_with_btf_list() { + local bpftool_path="$1" + + # The btf list command iterates over maps for + # loaded BPF programs. + if ! "$bpftool_path" btf list 1>/dev/null; then + echo " Failed to access btf data" + exit 1 + fi +} + +set -eu + +trap cleanup_skip EXIT + +check_root_privileges + +verify_bpftool_path "$BPFTOOL_PATH" + +verify_btf_support + +trap cleanup EXIT + +# Load and attach the BPF programs to control maps access. +"$BPFTOOL_PATH" prog loadall "$BPF_FILE_PATH" "$BPF_DIR" autoattach + +initialize_map_entries "$PROTECTED_MAP_NAME" "$BPFTOOL_PATH" +initialize_map_entries "$NOT_PROTECTED_MAP_NAME" "$BPFTOOL_PATH" + +# Activate the map protection mechanism. Protection status is controlled +# by a value stored in the prot_status_map at index 0. +"$BPFTOOL_PATH" map update name prot_status_map key 0 0 0 0 value 1 0 0 0 + +# Test protected map (write should fail). +test_map_access "$PROTECTED_MAP_NAME" "$BPFTOOL_PATH" "$BPF_DIR" "false" \ + "$BPF_ITER_FILE_PATH" + +# Test not protected map (write should succeed). +test_map_access "$NOT_PROTECTED_MAP_NAME" "$BPFTOOL_PATH" "$BPF_DIR" "true" \ + "$BPF_ITER_FILE_PATH" + +test_map_creation_and_map_of_maps "$BPFTOOL_PATH" "$BPF_DIR" + +test_map_access_with_btf_list "$BPFTOOL_PATH" + +exit 0 diff --git a/tools/testing/selftests/bpf/test_kmods/Makefile b/tools/testing/selftests/bpf/test_kmods/Makefile index d4e50c4509c9..63c4d3f6a12f 100644 --- a/tools/testing/selftests/bpf/test_kmods/Makefile +++ b/tools/testing/selftests/bpf/test_kmods/Makefile @@ -8,7 +8,7 @@ Q = @ endif MODULES = bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ - bpf_test_modorder_y.ko + bpf_test_modorder_y.ko bpf_test_rqspinlock.ko $(foreach m,$(MODULES),$(eval obj-m += $(m:.ko=.o))) diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c new file mode 100644 index 000000000000..769206fc70e4 --- /dev/null +++ b/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c @@ -0,0 +1,209 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <linux/sched.h> +#include <linux/smp.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/prandom.h> +#include <asm/rqspinlock.h> +#include <linux/perf_event.h> +#include <linux/kthread.h> +#include <linux/atomic.h> +#include <linux/slab.h> + +static struct perf_event_attr hw_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 1, + .sample_period = 100000, +}; + +static rqspinlock_t lock_a; +static rqspinlock_t lock_b; + +static struct perf_event **rqsl_evts; +static int rqsl_nevts; + +static bool test_ab = false; +module_param(test_ab, bool, 0644); +MODULE_PARM_DESC(test_ab, "Test ABBA situations instead of AA situations"); + +static struct task_struct **rqsl_threads; +static int rqsl_nthreads; +static atomic_t rqsl_ready_cpus = ATOMIC_INIT(0); + +static int pause = 0; + +static bool nmi_locks_a(int cpu) +{ + return (cpu & 1) && test_ab; +} + +static int rqspinlock_worker_fn(void *arg) +{ + int cpu = smp_processor_id(); + unsigned long flags; + int ret; + + if (cpu) { + atomic_inc(&rqsl_ready_cpus); + + while (!kthread_should_stop()) { + if (READ_ONCE(pause)) { + msleep(1000); + continue; + } + if (nmi_locks_a(cpu)) + ret = raw_res_spin_lock_irqsave(&lock_b, flags); + else + ret = raw_res_spin_lock_irqsave(&lock_a, flags); + mdelay(20); + if (nmi_locks_a(cpu) && !ret) + raw_res_spin_unlock_irqrestore(&lock_b, flags); + else if (!ret) + raw_res_spin_unlock_irqrestore(&lock_a, flags); + cpu_relax(); + } + return 0; + } + + while (!kthread_should_stop()) { + int expected = rqsl_nthreads > 0 ? rqsl_nthreads - 1 : 0; + int ready = atomic_read(&rqsl_ready_cpus); + + if (ready == expected && !READ_ONCE(pause)) { + for (int i = 0; i < rqsl_nevts; i++) + perf_event_enable(rqsl_evts[i]); + pr_err("Waiting 5 secs to pause the test\n"); + msleep(1000 * 5); + WRITE_ONCE(pause, 1); + pr_err("Paused the test\n"); + } else { + msleep(1000); + cpu_relax(); + } + } + return 0; +} + +static void nmi_cb(struct perf_event *event, struct perf_sample_data *data, + struct pt_regs *regs) +{ + int cpu = smp_processor_id(); + unsigned long flags; + int ret; + + if (!cpu || READ_ONCE(pause)) + return; + + if (nmi_locks_a(cpu)) + ret = raw_res_spin_lock_irqsave(&lock_a, flags); + else + ret = raw_res_spin_lock_irqsave(test_ab ? &lock_b : &lock_a, flags); + + mdelay(10); + + if (nmi_locks_a(cpu) && !ret) + raw_res_spin_unlock_irqrestore(&lock_a, flags); + else if (!ret) + raw_res_spin_unlock_irqrestore(test_ab ? &lock_b : &lock_a, flags); +} + +static void free_rqsl_threads(void) +{ + int i; + + if (rqsl_threads) { + for_each_online_cpu(i) { + if (rqsl_threads[i]) + kthread_stop(rqsl_threads[i]); + } + kfree(rqsl_threads); + } +} + +static void free_rqsl_evts(void) +{ + int i; + + if (rqsl_evts) { + for (i = 0; i < rqsl_nevts; i++) { + if (rqsl_evts[i]) + perf_event_release_kernel(rqsl_evts[i]); + } + kfree(rqsl_evts); + } +} + +static int bpf_test_rqspinlock_init(void) +{ + int i, ret; + int ncpus = num_online_cpus(); + + pr_err("Mode = %s\n", test_ab ? "ABBA" : "AA"); + + if (ncpus < 3) + return -ENOTSUPP; + + raw_res_spin_lock_init(&lock_a); + raw_res_spin_lock_init(&lock_b); + + rqsl_evts = kcalloc(ncpus - 1, sizeof(*rqsl_evts), GFP_KERNEL); + if (!rqsl_evts) + return -ENOMEM; + rqsl_nevts = ncpus - 1; + + for (i = 1; i < ncpus; i++) { + struct perf_event *e; + + e = perf_event_create_kernel_counter(&hw_attr, i, NULL, nmi_cb, NULL); + if (IS_ERR(e)) { + ret = PTR_ERR(e); + goto err_perf_events; + } + rqsl_evts[i - 1] = e; + } + + rqsl_threads = kcalloc(ncpus, sizeof(*rqsl_threads), GFP_KERNEL); + if (!rqsl_threads) { + ret = -ENOMEM; + goto err_perf_events; + } + rqsl_nthreads = ncpus; + + for_each_online_cpu(i) { + struct task_struct *t; + + t = kthread_create(rqspinlock_worker_fn, NULL, "rqsl_w/%d", i); + if (IS_ERR(t)) { + ret = PTR_ERR(t); + goto err_threads_create; + } + kthread_bind(t, i); + rqsl_threads[i] = t; + wake_up_process(t); + } + return 0; + +err_threads_create: + free_rqsl_threads(); +err_perf_events: + free_rqsl_evts(); + return ret; +} + +module_init(bpf_test_rqspinlock_init); + +static void bpf_test_rqspinlock_exit(void) +{ + free_rqsl_threads(); + free_rqsl_evts(); +} + +module_exit(bpf_test_rqspinlock_exit); + +MODULE_AUTHOR("Kumar Kartikeya Dwivedi"); +MODULE_DESCRIPTION("BPF rqspinlock stress test module"); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c index e9e918cdf31f..8074bc5f6f20 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c @@ -62,6 +62,18 @@ struct bpf_testmod_struct_arg_5 { long d; }; +union bpf_testmod_union_arg_1 { + char a; + short b; + struct bpf_testmod_struct_arg_1 arg; +}; + +union bpf_testmod_union_arg_2 { + int a; + long b; + struct bpf_testmod_struct_arg_2 arg; +}; + __bpf_hook_start(); noinline int @@ -129,6 +141,20 @@ bpf_testmod_test_struct_arg_9(u64 a, void *b, short c, int d, void *e, char f, } noinline int +bpf_testmod_test_union_arg_1(union bpf_testmod_union_arg_1 a, int b, int c) +{ + bpf_testmod_test_struct_arg_result = a.arg.a + b + c; + return bpf_testmod_test_struct_arg_result; +} + +noinline int +bpf_testmod_test_union_arg_2(int a, union bpf_testmod_union_arg_2 b) +{ + bpf_testmod_test_struct_arg_result = a + b.arg.a + b.arg.b; + return bpf_testmod_test_struct_arg_result; +} + +noinline int bpf_testmod_test_arg_ptr_to_struct(struct bpf_testmod_struct_arg_1 *a) { bpf_testmod_test_struct_arg_result = a->a; return bpf_testmod_test_struct_arg_result; @@ -218,6 +244,16 @@ __bpf_kfunc void bpf_kfunc_rcu_task_test(struct task_struct *ptr) { } +__bpf_kfunc struct task_struct *bpf_kfunc_ret_rcu_test(void) +{ + return NULL; +} + +__bpf_kfunc int *bpf_kfunc_ret_rcu_test_nostruct(int rdonly_buf_size) +{ + return NULL; +} + __bpf_kfunc struct bpf_testmod_ctx * bpf_testmod_ctx_create(int *err) { @@ -398,6 +434,8 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, struct bpf_testmod_struct_arg_3 *struct_arg3; struct bpf_testmod_struct_arg_4 struct_arg4 = {21, 22}; struct bpf_testmod_struct_arg_5 struct_arg5 = {23, 24, 25, 26}; + union bpf_testmod_union_arg_1 union_arg1 = { .arg = {1} }; + union bpf_testmod_union_arg_2 union_arg2 = { .arg = {2, 3} }; int i = 1; while (bpf_testmod_return_ptr(i)) @@ -415,6 +453,9 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, (void)bpf_testmod_test_struct_arg_9(16, (void *)17, 18, 19, (void *)20, 21, 22, struct_arg5, 27); + (void)bpf_testmod_test_union_arg_1(union_arg1, 4, 5); + (void)bpf_testmod_test_union_arg_2(6, union_arg2); + (void)bpf_testmod_test_arg_ptr_to_struct(&struct_arg1_2); (void)trace_bpf_testmod_test_raw_tp_null_tp(NULL); @@ -501,14 +542,20 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { #ifdef __x86_64__ static int +uprobe_handler(struct uprobe_consumer *self, struct pt_regs *regs, __u64 *data) +{ + regs->cx = 0x87654321feebdaed; + return 0; +} + +static int uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func, struct pt_regs *regs, __u64 *data) { regs->ax = 0x12345678deadbeef; - regs->cx = 0x87654321feebdaed; regs->r11 = (u64) -1; - return true; + return 0; } struct testmod_uprobe { @@ -520,6 +567,7 @@ struct testmod_uprobe { static DEFINE_MUTEX(testmod_uprobe_mutex); static struct testmod_uprobe uprobe = { + .consumer.handler = uprobe_handler, .consumer.ret_handler = uprobe_ret_handler, }; @@ -623,6 +671,8 @@ BTF_ID_FLAGS(func, bpf_kfunc_trusted_vma_test, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_kfunc_trusted_task_test, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_kfunc_trusted_num_test, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_kfunc_rcu_task_test, KF_RCU) +BTF_ID_FLAGS(func, bpf_kfunc_ret_rcu_test, KF_RET_NULL | KF_RCU_PROTECTED) +BTF_ID_FLAGS(func, bpf_kfunc_ret_rcu_test_nostruct, KF_RET_NULL | KF_RCU_PROTECTED) BTF_ID_FLAGS(func, bpf_testmod_ctx_create, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_testmod_ctx_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_testmod_ops3_call_test_1) @@ -1057,6 +1107,8 @@ __bpf_kfunc int bpf_kfunc_st_ops_inc10(struct st_ops_args *args) return args->a; } +__bpf_kfunc int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id); + BTF_KFUNCS_START(bpf_testmod_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc) BTF_ID_FLAGS(func, bpf_kfunc_call_test1) @@ -1097,6 +1149,7 @@ BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_prologue, KF_TRUSTED_ARGS | KF_SLEEPABL BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_epilogue, KF_TRUSTED_ARGS | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_pro_epilogue, KF_TRUSTED_ARGS | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_kfunc_st_ops_inc10, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_kfunc_multi_st_ops_test_1, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_testmod_check_kfunc_ids) static int bpf_testmod_ops_init(struct btf *btf) @@ -1528,6 +1581,114 @@ static struct bpf_struct_ops testmod_st_ops = { .owner = THIS_MODULE, }; +struct hlist_head multi_st_ops_list; +static DEFINE_SPINLOCK(multi_st_ops_lock); + +static int multi_st_ops_init(struct btf *btf) +{ + spin_lock_init(&multi_st_ops_lock); + INIT_HLIST_HEAD(&multi_st_ops_list); + + return 0; +} + +static int multi_st_ops_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + return 0; +} + +static struct bpf_testmod_multi_st_ops *multi_st_ops_find_nolock(u32 id) +{ + struct bpf_testmod_multi_st_ops *st_ops; + + hlist_for_each_entry(st_ops, &multi_st_ops_list, node) { + if (st_ops->id == id) + return st_ops; + } + + return NULL; +} + +int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id) +{ + struct bpf_testmod_multi_st_ops *st_ops; + unsigned long flags; + int ret = -1; + + spin_lock_irqsave(&multi_st_ops_lock, flags); + st_ops = multi_st_ops_find_nolock(id); + if (st_ops) + ret = st_ops->test_1(args); + spin_unlock_irqrestore(&multi_st_ops_lock, flags); + + return ret; +} + +static int multi_st_ops_reg(void *kdata, struct bpf_link *link) +{ + struct bpf_testmod_multi_st_ops *st_ops = + (struct bpf_testmod_multi_st_ops *)kdata; + unsigned long flags; + int err = 0; + u32 id; + + if (!st_ops->test_1) + return -EINVAL; + + id = bpf_struct_ops_id(kdata); + + spin_lock_irqsave(&multi_st_ops_lock, flags); + if (multi_st_ops_find_nolock(id)) { + pr_err("multi_st_ops(id:%d) has already been registered\n", id); + err = -EEXIST; + goto unlock; + } + + st_ops->id = id; + hlist_add_head(&st_ops->node, &multi_st_ops_list); +unlock: + spin_unlock_irqrestore(&multi_st_ops_lock, flags); + + return err; +} + +static void multi_st_ops_unreg(void *kdata, struct bpf_link *link) +{ + struct bpf_testmod_multi_st_ops *st_ops; + unsigned long flags; + u32 id; + + id = bpf_struct_ops_id(kdata); + + spin_lock_irqsave(&multi_st_ops_lock, flags); + st_ops = multi_st_ops_find_nolock(id); + if (st_ops) + hlist_del(&st_ops->node); + spin_unlock_irqrestore(&multi_st_ops_lock, flags); +} + +static int bpf_testmod_multi_st_ops__test_1(struct st_ops_args *args) +{ + return 0; +} + +static struct bpf_testmod_multi_st_ops multi_st_ops_cfi_stubs = { + .test_1 = bpf_testmod_multi_st_ops__test_1, +}; + +struct bpf_struct_ops testmod_multi_st_ops = { + .verifier_ops = &bpf_testmod_verifier_ops, + .init = multi_st_ops_init, + .init_member = multi_st_ops_init_member, + .reg = multi_st_ops_reg, + .unreg = multi_st_ops_unreg, + .cfi_stubs = &multi_st_ops_cfi_stubs, + .name = "bpf_testmod_multi_st_ops", + .owner = THIS_MODULE, +}; + extern int bpf_fentry_test1(int a); static int bpf_testmod_init(void) @@ -1550,6 +1711,7 @@ static int bpf_testmod_init(void) ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops2, bpf_testmod_ops2); ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops3, bpf_testmod_ops3); ret = ret ?: register_bpf_struct_ops(&testmod_st_ops, bpf_testmod_st_ops); + ret = ret ?: register_bpf_struct_ops(&testmod_multi_st_ops, bpf_testmod_multi_st_ops); ret = ret ?: register_btf_id_dtor_kfuncs(bpf_testmod_dtors, ARRAY_SIZE(bpf_testmod_dtors), THIS_MODULE); diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h index c9fab51f16e2..f6e492f9d042 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h @@ -116,4 +116,10 @@ struct bpf_testmod_st_ops { struct module *owner; }; +struct bpf_testmod_multi_st_ops { + int (*test_1)(struct st_ops_args *args); + struct hlist_node node; + int id; +}; + #endif /* _BPF_TESTMOD_H */ diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h index b58817938deb..4df6fa6a92cb 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h @@ -158,5 +158,9 @@ void bpf_kfunc_trusted_vma_test(struct vm_area_struct *ptr) __ksym; void bpf_kfunc_trusted_task_test(struct task_struct *ptr) __ksym; void bpf_kfunc_trusted_num_test(int *ptr) __ksym; void bpf_kfunc_rcu_task_test(struct task_struct *ptr) __ksym; +struct task_struct *bpf_kfunc_ret_rcu_test(void) __ksym; +int *bpf_kfunc_ret_rcu_test_nostruct(int rdonly_buf_size) __ksym; + +int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id) __ksym; #endif /* _BPF_TESTMOD_KFUNC_H */ diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c index 4694422aa76c..88e4aeab21b7 100644 --- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c +++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c @@ -74,7 +74,7 @@ int main(int argc, char **argv) /* Let's try detach it before it was ever attached */ ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2); - if (ret != -1 || errno != ENOENT) { + if (ret != -ENOENT) { printf("bpf_prog_detach2 not attached should fail: %m\n"); return 1; } diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index 9551d8d5f8f9..74ecc281bb8c 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -2,7 +2,6 @@ /* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ #include <linux/capability.h> #include <stdlib.h> -#include <regex.h> #include <test_progs.h> #include <bpf/btf.h> @@ -20,10 +19,12 @@ #define TEST_TAG_EXPECT_FAILURE "comment:test_expect_failure" #define TEST_TAG_EXPECT_SUCCESS "comment:test_expect_success" #define TEST_TAG_EXPECT_MSG_PFX "comment:test_expect_msg=" +#define TEST_TAG_EXPECT_NOT_MSG_PFX "comment:test_expect_not_msg=" #define TEST_TAG_EXPECT_XLATED_PFX "comment:test_expect_xlated=" #define TEST_TAG_EXPECT_FAILURE_UNPRIV "comment:test_expect_failure_unpriv" #define TEST_TAG_EXPECT_SUCCESS_UNPRIV "comment:test_expect_success_unpriv" #define TEST_TAG_EXPECT_MSG_PFX_UNPRIV "comment:test_expect_msg_unpriv=" +#define TEST_TAG_EXPECT_NOT_MSG_PFX_UNPRIV "comment:test_expect_not_msg_unpriv=" #define TEST_TAG_EXPECT_XLATED_PFX_UNPRIV "comment:test_expect_xlated_unpriv=" #define TEST_TAG_LOG_LEVEL_PFX "comment:test_log_level=" #define TEST_TAG_PROG_FLAGS_PFX "comment:test_prog_flags=" @@ -38,9 +39,13 @@ #define TEST_TAG_JITED_PFX_UNPRIV "comment:test_jited_unpriv=" #define TEST_TAG_CAPS_UNPRIV "comment:test_caps_unpriv=" #define TEST_TAG_LOAD_MODE_PFX "comment:load_mode=" +#define TEST_TAG_EXPECT_STDERR_PFX "comment:test_expect_stderr=" +#define TEST_TAG_EXPECT_STDERR_PFX_UNPRIV "comment:test_expect_stderr_unpriv=" +#define TEST_TAG_EXPECT_STDOUT_PFX "comment:test_expect_stdout=" +#define TEST_TAG_EXPECT_STDOUT_PFX_UNPRIV "comment:test_expect_stdout_unpriv=" /* Warning: duplicated in bpf_misc.h */ -#define POINTER_VALUE 0xcafe4all +#define POINTER_VALUE 0xbadcafe #define TEST_DATA_LEN 64 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -61,24 +66,14 @@ enum load_mode { NO_JITED = 1 << 1, }; -struct expect_msg { - const char *substr; /* substring match */ - regex_t regex; - bool is_regex; - bool on_next_line; -}; - -struct expected_msgs { - struct expect_msg *patterns; - size_t cnt; -}; - struct test_subspec { char *name; bool expect_failure; struct expected_msgs expect_msgs; struct expected_msgs expect_xlated; struct expected_msgs jited; + struct expected_msgs stderr; + struct expected_msgs stdout; int retval; bool execute; __u64 caps; @@ -139,6 +134,10 @@ static void free_test_spec(struct test_spec *spec) free_msgs(&spec->unpriv.expect_xlated); free_msgs(&spec->priv.jited); free_msgs(&spec->unpriv.jited); + free_msgs(&spec->unpriv.stderr); + free_msgs(&spec->priv.stderr); + free_msgs(&spec->unpriv.stdout); + free_msgs(&spec->priv.stdout); free(spec->priv.name); free(spec->unpriv.name); @@ -206,7 +205,8 @@ static int compile_regex(const char *pattern, regex_t *regex) return 0; } -static int __push_msg(const char *pattern, bool on_next_line, struct expected_msgs *msgs) +static int __push_msg(const char *pattern, bool on_next_line, bool negative, + struct expected_msgs *msgs) { struct expect_msg *msg; void *tmp; @@ -222,6 +222,7 @@ static int __push_msg(const char *pattern, bool on_next_line, struct expected_ms msg = &msgs->patterns[msgs->cnt]; msg->on_next_line = on_next_line; msg->substr = pattern; + msg->negative = negative; msg->is_regex = false; if (strstr(pattern, "{{")) { err = compile_regex(pattern, &msg->regex); @@ -240,16 +241,16 @@ static int clone_msgs(struct expected_msgs *from, struct expected_msgs *to) for (i = 0; i < from->cnt; i++) { msg = &from->patterns[i]; - err = __push_msg(msg->substr, msg->on_next_line, to); + err = __push_msg(msg->substr, msg->on_next_line, msg->negative, to); if (err) return err; } return 0; } -static int push_msg(const char *substr, struct expected_msgs *msgs) +static int push_msg(const char *substr, bool negative, struct expected_msgs *msgs) { - return __push_msg(substr, false, msgs); + return __push_msg(substr, false, negative, msgs); } static int push_disasm_msg(const char *regex_str, bool *on_next_line, struct expected_msgs *msgs) @@ -260,7 +261,7 @@ static int push_disasm_msg(const char *regex_str, bool *on_next_line, struct exp *on_next_line = false; return 0; } - err = __push_msg(regex_str, *on_next_line, msgs); + err = __push_msg(regex_str, *on_next_line, false, msgs); if (err) return err; *on_next_line = true; @@ -318,20 +319,14 @@ static int parse_caps(const char *str, __u64 *val, const char *name) static int parse_retval(const char *str, int *val, const char *name) { - struct { - char *name; - int val; - } named_values[] = { - { "INT_MIN" , INT_MIN }, - { "POINTER_VALUE", POINTER_VALUE }, - { "TEST_DATA_LEN", TEST_DATA_LEN }, - }; - int i; - - for (i = 0; i < ARRAY_SIZE(named_values); ++i) { - if (strcmp(str, named_values[i].name) != 0) - continue; - *val = named_values[i].val; + /* + * INT_MIN is defined as (-INT_MAX -1), i.e. it doesn't expand to a + * single int and cannot be parsed with strtol, so we handle it + * separately here. In addition, it expands to different expressions in + * different compilers so we use a prefixed _INT_MIN instead. + */ + if (strcmp(str, "_INT_MIN") == 0) { + *val = INT_MIN; return 0; } @@ -380,6 +375,7 @@ enum arch { ARCH_X86_64 = 0x2, ARCH_ARM64 = 0x4, ARCH_RISCV64 = 0x8, + ARCH_S390X = 0x10, }; static int get_current_arch(void) @@ -390,6 +386,8 @@ static int get_current_arch(void) return ARCH_ARM64; #elif defined(__riscv) && __riscv_xlen == 64 return ARCH_RISCV64; +#elif defined(__s390x__) + return ARCH_S390X; #endif return ARCH_UNKNOWN; } @@ -410,6 +408,10 @@ static int parse_test_spec(struct test_loader *tester, bool xlated_on_next_line = true; bool unpriv_jit_on_next_line; bool jit_on_next_line; + bool stderr_on_next_line = true; + bool unpriv_stderr_on_next_line = true; + bool stdout_on_next_line = true; + bool unpriv_stdout_on_next_line = true; bool collect_jit = false; int func_id, i, err = 0; u32 arch_mask = 0; @@ -471,12 +473,22 @@ static int parse_test_spec(struct test_loader *tester, spec->auxiliary = true; spec->mode_mask |= UNPRIV; } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_MSG_PFX))) { - err = push_msg(msg, &spec->priv.expect_msgs); + err = push_msg(msg, false, &spec->priv.expect_msgs); + if (err) + goto cleanup; + spec->mode_mask |= PRIV; + } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_NOT_MSG_PFX))) { + err = push_msg(msg, true, &spec->priv.expect_msgs); if (err) goto cleanup; spec->mode_mask |= PRIV; } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_MSG_PFX_UNPRIV))) { - err = push_msg(msg, &spec->unpriv.expect_msgs); + err = push_msg(msg, false, &spec->unpriv.expect_msgs); + if (err) + goto cleanup; + spec->mode_mask |= UNPRIV; + } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_NOT_MSG_PFX_UNPRIV))) { + err = push_msg(msg, true, &spec->unpriv.expect_msgs); if (err) goto cleanup; spec->mode_mask |= UNPRIV; @@ -571,8 +583,10 @@ static int parse_test_spec(struct test_loader *tester, arch = ARCH_ARM64; } else if (strcmp(val, "RISCV64") == 0) { arch = ARCH_RISCV64; + } else if (strcmp(val, "s390x") == 0) { + arch = ARCH_S390X; } else { - PRINT_FAIL("bad arch spec: '%s'", val); + PRINT_FAIL("bad arch spec: '%s'\n", val); err = -EINVAL; goto cleanup; } @@ -599,6 +613,26 @@ static int parse_test_spec(struct test_loader *tester, err = -EINVAL; goto cleanup; } + } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDERR_PFX))) { + err = push_disasm_msg(msg, &stderr_on_next_line, + &spec->priv.stderr); + if (err) + goto cleanup; + } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDERR_PFX_UNPRIV))) { + err = push_disasm_msg(msg, &unpriv_stderr_on_next_line, + &spec->unpriv.stderr); + if (err) + goto cleanup; + } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDOUT_PFX))) { + err = push_disasm_msg(msg, &stdout_on_next_line, + &spec->priv.stdout); + if (err) + goto cleanup; + } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDOUT_PFX_UNPRIV))) { + err = push_disasm_msg(msg, &unpriv_stdout_on_next_line, + &spec->unpriv.stdout); + if (err) + goto cleanup; } } @@ -652,6 +686,10 @@ static int parse_test_spec(struct test_loader *tester, clone_msgs(&spec->priv.expect_xlated, &spec->unpriv.expect_xlated); if (spec->unpriv.jited.cnt == 0) clone_msgs(&spec->priv.jited, &spec->unpriv.jited); + if (spec->unpriv.stderr.cnt == 0) + clone_msgs(&spec->priv.stderr, &spec->unpriv.stderr); + if (spec->unpriv.stdout.cnt == 0) + clone_msgs(&spec->priv.stdout, &spec->unpriv.stdout); } spec->valid = true; @@ -713,44 +751,155 @@ static void emit_jited(const char *jited, bool force) fprintf(stdout, "JITED:\n=============\n%s=============\n", jited); } -static void validate_msgs(char *log_buf, struct expected_msgs *msgs, - void (*emit_fn)(const char *buf, bool force)) +static void emit_stderr(const char *stderr, bool force) { - const char *log = log_buf, *prev_match; + if (!force && env.verbosity == VERBOSE_NONE) + return; + fprintf(stdout, "STDERR:\n=============\n%s=============\n", stderr); +} + +static void emit_stdout(const char *bpf_stdout, bool force) +{ + if (!force && env.verbosity == VERBOSE_NONE) + return; + fprintf(stdout, "STDOUT:\n=============\n%s=============\n", bpf_stdout); +} + +static const char *match_msg(struct expect_msg *msg, const char **log) +{ + const char *match = NULL; regmatch_t reg_match[1]; - int prev_match_line; - int match_line; - int i, j, err; + int err; + + if (!msg->is_regex) { + match = strstr(*log, msg->substr); + if (match) + *log = match + strlen(msg->substr); + } else { + err = regexec(&msg->regex, *log, 1, reg_match, 0); + if (err == 0) { + match = *log + reg_match[0].rm_so; + *log += reg_match[0].rm_eo; + } + } + return match; +} + +static int count_lines(const char *start, const char *end) +{ + const char *tmp; + int n = 0; + + for (tmp = start; tmp < end; ++tmp) + if (*tmp == '\n') + n++; + return n; +} + +struct match { + const char *start; + const char *end; + int line; +}; + +/* + * Positive messages are matched sequentially, each next message + * is looked for starting from the end of a previous matched one. + */ +static void match_positive_msgs(const char *log, struct expected_msgs *msgs, struct match *matches) +{ + const char *prev_match; + int i, line; - prev_match_line = -1; - match_line = 0; prev_match = log; + line = 0; for (i = 0; i < msgs->cnt; i++) { struct expect_msg *msg = &msgs->patterns[i]; - const char *match = NULL, *pat_status; - bool wrong_line = false; - - if (!msg->is_regex) { - match = strstr(log, msg->substr); - if (match) - log = match + strlen(msg->substr); - } else { - err = regexec(&msg->regex, log, 1, reg_match, 0); - if (err == 0) { - match = log + reg_match[0].rm_so; - log += reg_match[0].rm_eo; + const char *match = NULL; + + if (msg->negative) + continue; + + match = match_msg(msg, &log); + if (match) { + line += count_lines(prev_match, match); + matches[i].start = match; + matches[i].end = log; + matches[i].line = line; + prev_match = match; + } + } +} + +/* + * Each negative messages N located between positive messages P1 and P2 + * is matched in the span P1.end .. P2.start. Consequently, negative messages + * are unordered within the span. + */ +static void match_negative_msgs(const char *log, struct expected_msgs *msgs, struct match *matches) +{ + const char *start = log, *end, *next, *match; + const char *log_end = log + strlen(log); + int i, j, next_positive; + + for (i = 0; i < msgs->cnt; i++) { + struct expect_msg *msg = &msgs->patterns[i]; + + /* positive message bumps span start */ + if (!msg->negative) { + start = matches[i].end ?: start; + continue; + } + + /* count stride of negative patterns and adjust span end */ + end = log_end; + for (next_positive = i + 1; next_positive < msgs->cnt; next_positive++) { + if (!msgs->patterns[next_positive].negative) { + end = matches[next_positive].start; + break; } } - if (match) { - for (; prev_match < match; ++prev_match) - if (*prev_match == '\n') - ++match_line; - wrong_line = msg->on_next_line && prev_match_line >= 0 && - prev_match_line + 1 != match_line; + /* try matching negative messages within identified span */ + for (j = i; j < next_positive; j++) { + next = start; + match = match_msg(msg, &next); + if (match && next <= end) { + matches[j].start = match; + matches[j].end = next; + } } - if (!match || wrong_line) { + /* -1 to account for i++ */ + i = next_positive - 1; + } +} + +void validate_msgs(const char *log_buf, struct expected_msgs *msgs, + void (*emit_fn)(const char *buf, bool force)) +{ + struct match matches[msgs->cnt]; + struct match *prev_match = NULL; + int i, j; + + memset(matches, 0, sizeof(*matches) * msgs->cnt); + match_positive_msgs(log_buf, msgs, matches); + match_negative_msgs(log_buf, msgs, matches); + + for (i = 0; i < msgs->cnt; i++) { + struct expect_msg *msg = &msgs->patterns[i]; + struct match *match = &matches[i]; + const char *pat_status; + bool unexpected; + bool wrong_line; + bool no_match; + + no_match = !msg->negative && !match->start; + wrong_line = !msg->negative && + msg->on_next_line && + prev_match && prev_match->line + 1 != match->line; + unexpected = msg->negative && match->start; + if (no_match || wrong_line || unexpected) { PRINT_FAIL("expect_msg\n"); if (env.verbosity == VERBOSE_NONE) emit_fn(log_buf, true /*force*/); @@ -760,8 +909,10 @@ static void validate_msgs(char *log_buf, struct expected_msgs *msgs, pat_status = "MATCHED "; else if (wrong_line) pat_status = "WRONG LINE"; - else + else if (no_match) pat_status = "EXPECTED "; + else + pat_status = "UNEXPECTED"; msg = &msgs->patterns[j]; fprintf(stderr, "%s %s: '%s'\n", pat_status, @@ -771,12 +922,13 @@ static void validate_msgs(char *log_buf, struct expected_msgs *msgs, if (wrong_line) { fprintf(stderr, "expecting match at line %d, actual match is at line %d\n", - prev_match_line + 1, match_line); + prev_match->line + 1, match->line); } break; } - prev_match_line = match_line; + if (!msg->negative) + prev_match = match; } } @@ -935,6 +1087,19 @@ out: return err; } +/* Read the bpf stream corresponding to the stream_id */ +static int get_stream(int stream_id, int prog_fd, char *text, size_t text_sz) +{ + LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts); + int ret; + + ret = bpf_prog_stream_read(prog_fd, stream_id, text, text_sz, &ropts); + ASSERT_GT(ret, 0, "stream read"); + text[ret] = '\0'; + + return ret; +} + /* this function is forced noinline and has short generic name to look better * in test_progs output (in case of a failure) */ @@ -1089,7 +1254,7 @@ void run_subtest(struct test_loader *tester, link = bpf_map__attach_struct_ops(map); if (!link) { PRINT_FAIL("bpf_map__attach_struct_ops failed for map %s: err=%d\n", - bpf_map__name(map), err); + bpf_map__name(map), -errno); goto tobj_cleanup; } links[links_cnt++] = link; @@ -1103,12 +1268,37 @@ void run_subtest(struct test_loader *tester, } } - do_prog_test_run(bpf_program__fd(tprog), &retval, - bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false); - if (retval != subspec->retval && subspec->retval != POINTER_VALUE) { + err = do_prog_test_run(bpf_program__fd(tprog), &retval, + bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false); + if (!err && retval != subspec->retval && subspec->retval != POINTER_VALUE) { PRINT_FAIL("Unexpected retval: %d != %d\n", retval, subspec->retval); goto tobj_cleanup; } + + if (subspec->stderr.cnt) { + err = get_stream(2, bpf_program__fd(tprog), + tester->log_buf, tester->log_buf_sz); + if (err <= 0) { + PRINT_FAIL("Unexpected retval from get_stream(): %d, errno = %d\n", + err, errno); + goto tobj_cleanup; + } + emit_stderr(tester->log_buf, false /*force*/); + validate_msgs(tester->log_buf, &subspec->stderr, emit_stderr); + } + + if (subspec->stdout.cnt) { + err = get_stream(1, bpf_program__fd(tprog), + tester->log_buf, tester->log_buf_sz); + if (err <= 0) { + PRINT_FAIL("Unexpected retval from get_stream(): %d, errno = %d\n", + err, errno); + goto tobj_cleanup; + } + emit_stdout(tester->log_buf, false /*force*/); + validate_msgs(tester->log_buf, &subspec->stdout, emit_stdout); + } + /* redo bpf_map__attach_struct_ops for each test */ while (links_cnt > 0) bpf_link__destroy(links[--links_cnt]); diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 986ce32b113a..3fae9ce46ca9 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -535,7 +535,7 @@ static void test_devmap_hash(unsigned int task, void *data) static void test_queuemap(unsigned int task, void *data) { const int MAP_SIZE = 32; - __u32 vals[MAP_SIZE + MAP_SIZE/2], val; + __u32 vals[MAP_SIZE + MAP_SIZE/2], val = 0; int fd, i; /* Fill test values to be used */ @@ -591,7 +591,7 @@ static void test_queuemap(unsigned int task, void *data) static void test_stackmap(unsigned int task, void *data) { const int MAP_SIZE = 32; - __u32 vals[MAP_SIZE + MAP_SIZE/2], val; + __u32 vals[MAP_SIZE + MAP_SIZE/2], val = 0; int fd, i; /* Fill test values to be used */ diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 309d9d4a8ace..02a85dda30e6 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -14,12 +14,14 @@ #include <netinet/in.h> #include <sys/select.h> #include <sys/socket.h> +#include <linux/keyctl.h> #include <sys/un.h> #include <bpf/btf.h> #include <time.h> #include "json_writer.h" #include "network_helpers.h" +#include "verification_cert.h" /* backtrace() and backtrace_symbols_fd() are glibc specific, * use header file when glibc is available and provide stub @@ -1928,6 +1930,13 @@ static void free_test_states(void) } } +static __u32 register_session_key(const char *key_data, size_t key_data_size) +{ + return syscall(__NR_add_key, "asymmetric", "libbpf_session_key", + (const void *)key_data, key_data_size, + KEY_SPEC_SESSION_KEYRING); +} + int main(int argc, char **argv) { static const struct argp argp = { @@ -1961,6 +1970,10 @@ int main(int argc, char **argv) /* Use libbpf 1.0 API mode */ libbpf_set_strict_mode(LIBBPF_STRICT_ALL); libbpf_set_print(libbpf_print_fn); + err = register_session_key((const char *)test_progs_verification_cert, + test_progs_verification_cert_len); + if (err < 0) + return err; traffic_monitor_set_print(traffic_monitor_print_fn); diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 870694f2a359..eebfc18cdcd2 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -7,6 +7,7 @@ #include <errno.h> #include <string.h> #include <assert.h> +#include <regex.h> #include <stdlib.h> #include <stdarg.h> #include <time.h> @@ -460,6 +461,34 @@ static inline void *u64_to_ptr(__u64 ptr) return (void *) (unsigned long) ptr; } +static inline __u32 id_from_prog_fd(int fd) +{ + struct bpf_prog_info prog_info = {}; + __u32 prog_info_len = sizeof(prog_info); + int err; + + err = bpf_obj_get_info_by_fd(fd, &prog_info, &prog_info_len); + if (!ASSERT_OK(err, "id_from_prog_fd")) + return 0; + + ASSERT_NEQ(prog_info.id, 0, "prog_info.id"); + return prog_info.id; +} + +static inline __u32 id_from_link_fd(int fd) +{ + struct bpf_link_info link_info = {}; + __u32 link_info_len = sizeof(link_info); + int err; + + err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len); + if (!ASSERT_OK(err, "id_from_link_fd")) + return 0; + + ASSERT_NEQ(link_info.id, 0, "link_info.id"); + return link_info.id; +} + int bpf_find_map(const char *test, struct bpf_object *obj, const char *name); int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); @@ -518,4 +547,20 @@ extern void test_loader_fini(struct test_loader *tester); test_loader_fini(&tester); \ }) +struct expect_msg { + const char *substr; /* substring match */ + regex_t regex; + bool is_regex; + bool on_next_line; + bool negative; +}; + +struct expected_msgs { + struct expect_msg *patterns; + size_t cnt; +}; + +void validate_msgs(const char *log_buf, struct expected_msgs *msgs, + void (*emit_fn)(const char *buf, bool force)); + #endif /* __TEST_PROGS_H */ diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index fd2da2234cc9..76568db7a664 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1372,7 +1372,7 @@ run: } else fprintf(stderr, "unknown test\n"); out: - /* Detatch and zero all the maps */ + /* Detach and zero all the maps */ bpf_prog_detach2(bpf_program__fd(progs[3]), cg_fd, BPF_CGROUP_SOCK_OPS); for (i = 0; i < ARRAY_SIZE(links); i++) { diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c index 595194453ff8..35b4893ccdf8 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_user.c +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -15,20 +15,18 @@ #include <bpf/libbpf.h> #include <sys/ioctl.h> #include <linux/rtnetlink.h> -#include <signal.h> #include <linux/perf_event.h> -#include <linux/err.h> -#include "bpf_util.h" #include "cgroup_helpers.h" #include "test_tcpnotify.h" -#include "trace_helpers.h" #include "testing_helpers.h" #define SOCKET_BUFFER_SIZE (getpagesize() < 8192L ? getpagesize() : 8192L) pthread_t tid; +static bool exit_thread; + int rx_callbacks; static void dummyfn(void *ctx, int cpu, void *data, __u32 size) @@ -45,7 +43,7 @@ void tcp_notifier_poller(struct perf_buffer *pb) { int err; - while (1) { + while (!exit_thread) { err = perf_buffer__poll(pb, 100); if (err < 0 && err != -EINTR) { printf("failed perf_buffer__poll: %d\n", err); @@ -78,15 +76,10 @@ int main(int argc, char **argv) int error = EXIT_FAILURE; struct bpf_object *obj; char test_script[80]; - cpu_set_t cpuset; __u32 key = 0; libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - CPU_ZERO(&cpuset); - CPU_SET(0, &cpuset); - pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset); - cg_fd = cgroup_setup_and_join(cg_path); if (cg_fd < 0) goto err; @@ -151,6 +144,13 @@ int main(int argc, char **argv) sleep(10); + exit_thread = true; + int ret = pthread_join(tid, NULL); + if (ret) { + printf("FAILED: pthread_join\n"); + goto err; + } + if (verify_result(&g)) { printf("FAILED: Wrong stats Expected %d calls, got %d\n", g.ncalls, rx_callbacks); diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh index 65aafe0003db..62db060298a4 100755 --- a/tools/testing/selftests/bpf/test_xsk.sh +++ b/tools/testing/selftests/bpf/test_xsk.sh @@ -241,4 +241,6 @@ done if [ $failures -eq 0 ]; then echo "All tests successful!" +else + exit 1 fi diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 5e9f16683be5..16eb37e5bad6 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -399,7 +399,7 @@ int unload_module(const char *name, bool verbose) return 0; } -int load_module(const char *path, bool verbose) +static int __load_module(const char *path, const char *param_values, bool verbose) { int fd; @@ -411,7 +411,7 @@ int load_module(const char *path, bool verbose) fprintf(stdout, "Can't find %s kernel module: %d\n", path, -errno); return -ENOENT; } - if (finit_module(fd, "", 0)) { + if (finit_module(fd, param_values, 0)) { fprintf(stdout, "Failed to load %s into the kernel: %d\n", path, -errno); close(fd); return -EINVAL; @@ -423,6 +423,16 @@ int load_module(const char *path, bool verbose) return 0; } +int load_module_params(const char *path, const char *param_values, bool verbose) +{ + return __load_module(path, param_values, verbose); +} + +int load_module(const char *path, bool verbose) +{ + return __load_module(path, "", verbose); +} + int unload_bpf_testmod(bool verbose) { return unload_module("bpf_testmod", verbose); diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index 46d7f7089f63..eb20d3772218 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -39,6 +39,7 @@ int kern_sync_rcu(void); int finit_module(int fd, const char *param_values, int flags); int delete_module(const char *name, int flags); int load_module(const char *path, bool verbose); +int load_module_params(const char *path, const char *param_values, bool verbose); int unload_module(const char *name, bool verbose); static inline __u64 get_time_ns(void) diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 81943c6254e6..eeaab7013ca2 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -17,7 +17,9 @@ #include <linux/limits.h> #include <libelf.h> #include <gelf.h> +#include "bpf/hashmap.h" #include "bpf/libbpf_internal.h" +#include "bpf_util.h" #define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe" #define DEBUGFS_PIPE "/sys/kernel/debug/tracing/trace_pipe" @@ -519,3 +521,235 @@ void read_trace_pipe(void) { read_trace_pipe_iter(trace_pipe_cb, NULL, 0); } + +static size_t symbol_hash(long key, void *ctx __maybe_unused) +{ + return str_hash((const char *) key); +} + +static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused) +{ + return strcmp((const char *) key1, (const char *) key2) == 0; +} + +static bool is_invalid_entry(char *buf, bool kernel) +{ + if (kernel && strchr(buf, '[')) + return true; + if (!kernel && !strchr(buf, '[')) + return true; + return false; +} + +static const char * const trace_blacklist[] = { + "migrate_disable", + "migrate_enable", + "rcu_read_unlock_strict", + "preempt_count_add", + "preempt_count_sub", + "__rcu_read_lock", + "__rcu_read_unlock", + "bpf_get_numa_node_id", +}; + +static bool skip_entry(char *name) +{ + int i; + + /* + * We attach to almost all kernel functions and some of them + * will cause 'suspicious RCU usage' when fprobe is attached + * to them. Filter out the current culprits - arch_cpu_idle + * default_idle and rcu_* functions. + */ + if (!strcmp(name, "arch_cpu_idle")) + return true; + if (!strcmp(name, "default_idle")) + return true; + if (!strncmp(name, "rcu_", 4)) + return true; + if (!strcmp(name, "bpf_dispatcher_xdp_func")) + return true; + if (!strncmp(name, "__ftrace_invalid_address__", + sizeof("__ftrace_invalid_address__") - 1)) + return true; + + for (i = 0; i < ARRAY_SIZE(trace_blacklist); i++) { + if (!strcmp(name, trace_blacklist[i])) + return true; + } + + return false; +} + +/* Do comparison by ignoring '.llvm.<hash>' suffixes. */ +static int compare_name(const char *name1, const char *name2) +{ + const char *res1, *res2; + int len1, len2; + + res1 = strstr(name1, ".llvm."); + res2 = strstr(name2, ".llvm."); + len1 = res1 ? res1 - name1 : strlen(name1); + len2 = res2 ? res2 - name2 : strlen(name2); + + if (len1 == len2) + return strncmp(name1, name2, len1); + if (len1 < len2) + return strncmp(name1, name2, len1) <= 0 ? -1 : 1; + return strncmp(name1, name2, len2) >= 0 ? 1 : -1; +} + +static int load_kallsyms_compare(const void *p1, const void *p2) +{ + return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name); +} + +static int search_kallsyms_compare(const void *p1, const struct ksym *p2) +{ + return compare_name(p1, p2->name); +} + +int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel) +{ + size_t cap = 0, cnt = 0; + char *name = NULL, *ksym_name, **syms = NULL; + struct hashmap *map; + struct ksyms *ksyms; + struct ksym *ks; + char buf[256]; + FILE *f; + int err = 0; + + ksyms = load_kallsyms_custom_local(load_kallsyms_compare); + if (!ksyms) + return -EINVAL; + + /* + * The available_filter_functions contains many duplicates, + * but other than that all symbols are usable to trace. + * Filtering out duplicates by using hashmap__add, which won't + * add existing entry. + */ + + if (access("/sys/kernel/tracing/trace", F_OK) == 0) + f = fopen("/sys/kernel/tracing/available_filter_functions", "r"); + else + f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r"); + + if (!f) + return -EINVAL; + + map = hashmap__new(symbol_hash, symbol_equal, NULL); + if (IS_ERR(map)) { + err = libbpf_get_error(map); + goto error; + } + + while (fgets(buf, sizeof(buf), f)) { + if (is_invalid_entry(buf, kernel)) + continue; + + free(name); + if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1) + continue; + if (skip_entry(name)) + continue; + + ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare); + if (!ks) { + err = -EINVAL; + goto error; + } + + ksym_name = ks->name; + err = hashmap__add(map, ksym_name, 0); + if (err == -EEXIST) { + err = 0; + continue; + } + if (err) + goto error; + + err = libbpf_ensure_mem((void **) &syms, &cap, + sizeof(*syms), cnt + 1); + if (err) + goto error; + + syms[cnt++] = ksym_name; + } + + *symsp = syms; + *cntp = cnt; + +error: + free(name); + fclose(f); + hashmap__free(map); + if (err) + free(syms); + return err; +} + +int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel) +{ + unsigned long *addr, *addrs, *tmp_addrs; + int err = 0, max_cnt, inc_cnt; + char *name = NULL; + size_t cnt = 0; + char buf[256]; + FILE *f; + + if (access("/sys/kernel/tracing/trace", F_OK) == 0) + f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r"); + else + f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r"); + + if (!f) + return -ENOENT; + + /* In my local setup, the number of entries is 50k+ so Let us initially + * allocate space to hold 64k entries. If 64k is not enough, incrementally + * increase 1k each time. + */ + max_cnt = 65536; + inc_cnt = 1024; + addrs = malloc(max_cnt * sizeof(long)); + if (addrs == NULL) { + err = -ENOMEM; + goto error; + } + + while (fgets(buf, sizeof(buf), f)) { + if (is_invalid_entry(buf, kernel)) + continue; + + free(name); + if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2) + continue; + if (skip_entry(name)) + continue; + + if (cnt == max_cnt) { + max_cnt += inc_cnt; + tmp_addrs = realloc(addrs, max_cnt * sizeof(long)); + if (!tmp_addrs) { + err = -ENOMEM; + goto error; + } + addrs = tmp_addrs; + } + + addrs[cnt++] = (unsigned long)addr; + } + + *addrsp = addrs; + *cntp = cnt; + +error: + free(name); + fclose(f); + if (err) + free(addrs); + return err; +} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index 2ce873c9f9aa..9437bdd4afa5 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -41,4 +41,7 @@ ssize_t get_rel_offset(uintptr_t addr); int read_build_id(const char *path, char *build_id, size_t size); +int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel); +int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel); + #endif diff --git a/tools/testing/selftests/bpf/unpriv_helpers.c b/tools/testing/selftests/bpf/unpriv_helpers.c index 220f6a963813..f997d7ec8fd0 100644 --- a/tools/testing/selftests/bpf/unpriv_helpers.c +++ b/tools/testing/selftests/bpf/unpriv_helpers.c @@ -1,15 +1,76 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <errno.h> +#include <limits.h> #include <stdbool.h> #include <stdlib.h> #include <stdio.h> #include <string.h> +#include <sys/utsname.h> #include <unistd.h> #include <fcntl.h> +#include <zlib.h> #include "unpriv_helpers.h" -static bool get_mitigations_off(void) +static gzFile open_config(void) +{ + struct utsname uts; + char buf[PATH_MAX]; + gzFile config; + + if (uname(&uts)) { + perror("uname"); + goto config_gz; + } + + snprintf(buf, sizeof(buf), "/boot/config-%s", uts.release); + config = gzopen(buf, "rb"); + if (config) + return config; + fprintf(stderr, "gzopen %s: %s\n", buf, strerror(errno)); + +config_gz: + config = gzopen("/proc/config.gz", "rb"); + if (!config) + perror("gzopen /proc/config.gz"); + return config; +} + +static int config_contains(const char *pat) +{ + const char *msg; + char buf[1024]; + gzFile config; + int n, err; + + config = open_config(); + if (!config) + return -1; + + for (;;) { + if (!gzgets(config, buf, sizeof(buf))) { + msg = gzerror(config, &err); + if (err == Z_ERRNO) + perror("gzgets /proc/config.gz"); + else if (err != Z_OK) + fprintf(stderr, "gzgets /proc/config.gz: %s", msg); + gzclose(config); + return -1; + } + n = strlen(buf); + if (buf[n - 1] == '\n') + buf[n - 1] = 0; + if (strcmp(buf, pat) == 0) { + gzclose(config); + return 1; + } + } + gzclose(config); + return 0; +} + +static bool cmdline_contains(const char *pat) { char cmdline[4096], *c; int fd, ret = false; @@ -27,7 +88,7 @@ static bool get_mitigations_off(void) cmdline[sizeof(cmdline) - 1] = '\0'; for (c = strtok(cmdline, " \n"); c; c = strtok(NULL, " \n")) { - if (strncmp(c, "mitigations=off", strlen(c))) + if (strncmp(c, pat, strlen(c))) continue; ret = true; break; @@ -37,8 +98,21 @@ out: return ret; } +static int get_mitigations_off(void) +{ + int enabled_in_config; + + if (cmdline_contains("mitigations=off")) + return 1; + enabled_in_config = config_contains("CONFIG_CPU_MITIGATIONS=y"); + if (enabled_in_config < 0) + return -1; + return !enabled_in_config; +} + bool get_unpriv_disabled(void) { + int mitigations_off; bool disabled; char buf[2]; FILE *fd; @@ -52,5 +126,19 @@ bool get_unpriv_disabled(void) disabled = true; } - return disabled ? true : get_mitigations_off(); + if (disabled) + return true; + + /* + * Some unpriv tests rely on spectre mitigations being on. + * If mitigations are off or status can't be determined + * assume that unpriv tests are disabled. + */ + mitigations_off = get_mitigations_off(); + if (mitigations_off < 0) { + fprintf(stderr, + "Can't determine if mitigations are enabled, disabling unpriv tests."); + return true; + } + return mitigations_off; } diff --git a/tools/testing/selftests/bpf/usdt.h b/tools/testing/selftests/bpf/usdt.h new file mode 100644 index 000000000000..549d1f774810 --- /dev/null +++ b/tools/testing/selftests/bpf/usdt.h @@ -0,0 +1,545 @@ +// SPDX-License-Identifier: BSD-2-Clause +/* + * This single-header library defines a collection of variadic macros for + * defining and triggering USDTs (User Statically-Defined Tracepoints): + * + * - For USDTs without associated semaphore: + * USDT(group, name, args...) + * + * - For USDTs with implicit (transparent to the user) semaphore: + * USDT_WITH_SEMA(group, name, args...) + * USDT_IS_ACTIVE(group, name) + * + * - For USDTs with explicit (user-defined and provided) semaphore: + * USDT_WITH_EXPLICIT_SEMA(sema, group, name, args...) + * USDT_SEMA_IS_ACTIVE(sema) + * + * all of which emit a NOP instruction into the instruction stream, and so + * have *zero* overhead for the surrounding code. USDTs are identified by + * a combination of `group` and `name` identifiers, which is used by external + * tracing tooling (tracers) for identifying exact USDTs of interest. + * + * USDTs can have an associated (2-byte) activity counter (USDT semaphore), + * automatically maintained by Linux kernel whenever any correctly written + * BPF-based tracer is attached to the USDT. This USDT semaphore can be used + * to check whether there is a need to do any extra data collection and + * processing for a given USDT (if necessary), and otherwise avoid extra work + * for a common case of USDT not being traced ("active"). + * + * See documentation for USDT_WITH_SEMA()/USDT_IS_ACTIVE() or + * USDT_WITH_EXPLICIT_SEMA()/USDT_SEMA_IS_ACTIVE() APIs below for details on + * working with USDTs with implicitly or explicitly associated + * USDT semaphores, respectively. + * + * There is also some additional data recorded into an auxiliary note + * section. The data in the note section describes the operands, in terms of + * size and location, used by tracing tooling to know where to find USDT + * arguments. Each location is encoded as an assembler operand string. + * Tracing tools (bpftrace and BPF-based tracers, systemtap, etc) insert + * breakpoints on top of the nop, and decode the location operand-strings, + * like an assembler, to find the values being passed. + * + * The operand strings are selected by the compiler for each operand. + * They are constrained by inline-assembler codes.The default is: + * + * #define USDT_ARG_CONSTRAINT nor + * + * This is a good default if the operands tend to be integral and + * moderate in number (smaller than number of registers). In other + * cases, the compiler may report "'asm' requires impossible reload" or + * similar. In this case, consider simplifying the macro call (fewer + * and simpler operands), reduce optimization, or override the default + * constraints string via: + * + * #define USDT_ARG_CONSTRAINT g + * #include <usdt.h> + * + * For some historical description of USDT v3 format (the one used by this + * library and generally recognized and assumed by BPF-based tracing tools) + * see [0]. The more formal specification can be found at [1]. Additional + * argument constraints information can be found at [2]. + * + * Original SystemTap's sys/sdt.h implementation ([3]) was used as a base for + * this USDT library implementation. Current implementation differs *a lot* in + * terms of exposed user API and general usability, which was the main goal + * and focus of the reimplementation work. Nevertheless, underlying recorded + * USDT definitions are fully binary compatible and any USDT-based tooling + * should work equally well with USDTs defined by either SystemTap's or this + * library's USDT implementation. + * + * [0] https://ecos.sourceware.org/ml/systemtap/2010-q3/msg00145.html + * [1] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation + * [2] https://gcc.gnu.org/onlinedocs/gcc/Constraints.html + * [3] https://sourceware.org/git/?p=systemtap.git;a=blob;f=includes/sys/sdt.h + */ +#ifndef __USDT_H +#define __USDT_H + +/* + * Changelog: + * + * 0.1.0 + * ----- + * - Initial release + */ +#define USDT_MAJOR_VERSION 0 +#define USDT_MINOR_VERSION 1 +#define USDT_PATCH_VERSION 0 + +/* C++20 and C23 added __VA_OPT__ as a standard replacement for non-standard `##__VA_ARGS__` extension */ +#if (defined(__STDC_VERSION__) && __STDC_VERSION__ > 201710L) || (defined(__cplusplus) && __cplusplus > 201703L) +#define __usdt_va_opt 1 +#define __usdt_va_args(...) __VA_OPT__(,) __VA_ARGS__ +#else +#define __usdt_va_args(...) , ##__VA_ARGS__ +#endif + +/* + * Trigger USDT with `group`:`name` identifier and pass through `args` as its + * arguments. Zero arguments are acceptable as well. No USDT semaphore is + * associated with this USDT. + * + * Such "semaphoreless" USDTs are commonly used when there is no extra data + * collection or processing needed to collect and prepare USDT arguments and + * they are just available in the surrounding code. USDT() macro will just + * record their locations in CPU registers or in memory for tracing tooling to + * be able to access them, if necessary. + */ +#ifdef __usdt_va_opt +#define USDT(group, name, ...) \ + __usdt_probe(group, name, __usdt_sema_none, 0 __VA_OPT__(,) __VA_ARGS__) +#else +#define USDT(group, name, ...) \ + __usdt_probe(group, name, __usdt_sema_none, 0, ##__VA_ARGS__) +#endif + +/* + * Trigger USDT with `group`:`name` identifier and pass through `args` as its + * arguments. Zero arguments are acceptable as well. USDT also get an + * implicitly-defined associated USDT semaphore, which will be "activated" by + * tracing tooling and can be used to check whether USDT is being actively + * observed. + * + * USDTs with semaphore are commonly used when there is a need to perform + * additional data collection and processing to prepare USDT arguments, which + * otherwise might not be necessary for the rest of application logic. In such + * case, USDT semaphore can be used to avoid unnecessary extra work. If USDT + * is not traced (which is presumed to be a common situation), the associated + * USDT semaphore is "inactive", and so there is no need to waste resources to + * prepare USDT arguments. Use USDT_IS_ACTIVE(group, name) to check whether + * USDT is "active". + * + * N.B. There is an inherent (albeit short) gap between checking whether USDT + * is active and triggering corresponding USDT, in which external tracer can + * be attached to an USDT and activate USDT semaphore after the activity check. + * If such a race occurs, tracers might miss one USDT execution. Tracers are + * expected to accommodate such possibility and this is expected to not be + * a problem for applications and tracers. + * + * N.B. Implicit USDT semaphore defined by USDT_WITH_SEMA() is contained + * within a single executable or shared library and is not shared outside + * them. I.e., if you use USDT_WITH_SEMA() with the same USDT group and name + * identifier across executable and shared library, it will work and won't + * conflict, per se, but will define independent USDT semaphores, one for each + * shared library/executable in which USDT_WITH_SEMA(group, name) is used. + * That is, if you attach to this USDT in one shared library (or executable), + * then only USDT semaphore within that shared library (or executable) will be + * updated by the kernel, while other libraries (or executable) will not see + * activated USDT semaphore. In short, it's best to use unique USDT group:name + * identifiers across different shared libraries (and, equivalently, between + * executable and shared library). This is advanced consideration and is + * rarely (if ever) seen in practice, but just to avoid surprises this is + * called out here. (Static libraries become a part of final executable, once + * linked by linker, so the above considerations don't apply to them.) + */ +#ifdef __usdt_va_opt +#define USDT_WITH_SEMA(group, name, ...) \ + __usdt_probe(group, name, \ + __usdt_sema_implicit, __usdt_sema_name(group, name) \ + __VA_OPT__(,) __VA_ARGS__) +#else +#define USDT_WITH_SEMA(group, name, ...) \ + __usdt_probe(group, name, \ + __usdt_sema_implicit, __usdt_sema_name(group, name), \ + ##__VA_ARGS__) +#endif + +struct usdt_sema { volatile unsigned short active; }; + +/* + * Check if USDT with `group`:`name` identifier is "active" (i.e., whether it + * is attached to by external tracing tooling and is actively observed). + * + * This macro can be used to decide whether any additional and potentially + * expensive data collection or processing should be done to pass extra + * information into the given USDT. It is assumed that USDT is triggered with + * USDT_WITH_SEMA() macro which will implicitly define associated USDT + * semaphore. (If one needs more control over USDT semaphore, see + * USDT_DEFINE_SEMA() and USDT_WITH_EXPLICIT_SEMA() macros below.) + * + * N.B. Such checks are necessarily racy and speculative. Between checking + * whether USDT is active and triggering the USDT itself, tracer can be + * detached with no notification. This race should be extremely rare and worst + * case should result in one-time wasted extra data collection and processing. + */ +#define USDT_IS_ACTIVE(group, name) ({ \ + extern struct usdt_sema __usdt_sema_name(group, name) \ + __usdt_asm_name(__usdt_sema_name(group, name)); \ + __usdt_sema_implicit(__usdt_sema_name(group, name)); \ + __usdt_sema_name(group, name).active > 0; \ +}) + +/* + * APIs for working with user-defined explicit USDT semaphores. + * + * This is a less commonly used advanced API for use cases in which user needs + * an explicit control over (potentially shared across multiple USDTs) USDT + * semaphore instance. This can be used when there is a group of logically + * related USDTs that all need extra data collection and processing whenever + * any of a family of related USDTs are "activated" (i.e., traced). In such + * a case, all such related USDTs will be associated with the same shared USDT + * semaphore defined with USDT_DEFINE_SEMA() and the USDTs themselves will be + * triggered with USDT_WITH_EXPLICIT_SEMA() macros, taking an explicit extra + * USDT semaphore identifier as an extra parameter. + */ + +/** + * Underlying C global variable name for user-defined USDT semaphore with + * `sema` identifier. Could be useful for debugging, but normally shouldn't be + * used explicitly. + */ +#define USDT_SEMA(sema) __usdt_sema_##sema + +/* + * Define storage for user-defined USDT semaphore `sema`. + * + * Should be used only once in non-header source file to let compiler allocate + * space for the semaphore variable. Just like with any other global variable. + * + * This macro can be used anywhere where global variable declaration is + * allowed. Just like with global variable definitions, there should be only + * one definition of user-defined USDT semaphore with given `sema` identifier, + * otherwise compiler or linker will complain about duplicate variable + * definition. + * + * For C++, it is allowed to use USDT_DEFINE_SEMA() both in global namespace + * and inside namespaces (including nested namespaces). Just make sure that + * USDT_DECLARE_SEMA() is placed within the namespace where this semaphore is + * referenced, or any of its parent namespaces, so the C++ language-level + * identifier is visible to the code that needs to reference the semaphore. + * At the lowest layer, USDT semaphores have global naming and visibility + * (they have a corresponding `__usdt_sema_<name>` symbol, which can be linked + * against from C or C++ code, if necessary). To keep it simple, putting + * USDT_DECLARE_SEMA() declarations into global namespaces is the simplest + * no-brainer solution. All these aspects are irrelevant for plain C, because + * C doesn't have namespaces and everything is always in the global namespace. + * + * N.B. Due to USDT metadata being recorded in non-allocatable ELF note + * section, it has limitations when it comes to relocations, which, in + * practice, means that it's not possible to correctly share USDT semaphores + * between main executable and shared libraries, or even between multiple + * shared libraries. USDT semaphore has to be contained to individual shared + * library or executable to avoid unpleasant surprises with half-working USDT + * semaphores. We enforce this by marking semaphore ELF symbols as having + * a hidden visibility. This is quite an advanced use case and consideration + * and for most users this should have no consequences whatsoever. + */ +#define USDT_DEFINE_SEMA(sema) \ + struct usdt_sema __usdt_sema_sec USDT_SEMA(sema) \ + __usdt_asm_name(USDT_SEMA(sema)) \ + __attribute__((visibility("hidden"))) = { 0 } + +/* + * Declare extern reference to user-defined USDT semaphore `sema`. + * + * Refers to a variable defined in another compilation unit by + * USDT_DEFINE_SEMA() and allows to use the same USDT semaphore across + * multiple compilation units (i.e., .c and .cpp files). + * + * See USDT_DEFINE_SEMA() notes above for C++ language usage peculiarities. + */ +#define USDT_DECLARE_SEMA(sema) \ + extern struct usdt_sema USDT_SEMA(sema) __usdt_asm_name(USDT_SEMA(sema)) + +/* + * Check if user-defined USDT semaphore `sema` is "active" (i.e., whether it + * is attached to by external tracing tooling and is actively observed). + * + * This macro can be used to decide whether any additional and potentially + * expensive data collection or processing should be done to pass extra + * information into USDT(s) associated with USDT semaphore `sema`. + * + * N.B. Such checks are necessarily racy. Between checking the state of USDT + * semaphore and triggering associated USDT(s), the active tracer might attach + * or detach. This race should be extremely rare and worst case should result + * in one-time missed USDT event or wasted extra data collection and + * processing. USDT-using tracers should be written with this in mind and is + * not a concern of the application defining USDTs with associated semaphore. + */ +#define USDT_SEMA_IS_ACTIVE(sema) (USDT_SEMA(sema).active > 0) + +/* + * Invoke USDT specified by `group` and `name` identifiers and associate + * explicitly user-defined semaphore `sema` with it. Pass through `args` as + * USDT arguments. `args` are optional and zero arguments are acceptable. + * + * Semaphore is defined with the help of USDT_DEFINE_SEMA() macro and can be + * checked whether active with USDT_SEMA_IS_ACTIVE(). + */ +#ifdef __usdt_va_opt +#define USDT_WITH_EXPLICIT_SEMA(sema, group, name, ...) \ + __usdt_probe(group, name, __usdt_sema_explicit, USDT_SEMA(sema), ##__VA_ARGS__) +#else +#define USDT_WITH_EXPLICIT_SEMA(sema, group, name, ...) \ + __usdt_probe(group, name, __usdt_sema_explicit, USDT_SEMA(sema) __VA_OPT__(,) __VA_ARGS__) +#endif + +/* + * Adjustable implementation aspects + */ +#ifndef USDT_ARG_CONSTRAINT +#if defined __powerpc__ +#define USDT_ARG_CONSTRAINT nZr +#elif defined __arm__ +#define USDT_ARG_CONSTRAINT g +#elif defined __loongarch__ +#define USDT_ARG_CONSTRAINT nmr +#else +#define USDT_ARG_CONSTRAINT nor +#endif +#endif /* USDT_ARG_CONSTRAINT */ + +#ifndef USDT_NOP +#if defined(__ia64__) || defined(__s390__) || defined(__s390x__) +#define USDT_NOP nop 0 +#else +#define USDT_NOP nop +#endif +#endif /* USDT_NOP */ + +/* + * Implementation details + */ +/* USDT name for implicitly-defined USDT semaphore, derived from group:name */ +#define __usdt_sema_name(group, name) __usdt_sema_##group##__##name +/* ELF section into which USDT semaphores are put */ +#define __usdt_sema_sec __attribute__((section(".probes"))) + +#define __usdt_concat(a, b) a ## b +#define __usdt_apply(fn, n) __usdt_concat(fn, n) + +#ifndef __usdt_nth +#define __usdt_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, N, ...) N +#endif + +#ifndef __usdt_narg +#ifdef __usdt_va_opt +#define __usdt_narg(...) __usdt_nth(_ __VA_OPT__(,) __VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#else +#define __usdt_narg(...) __usdt_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#endif +#endif /* __usdt_narg */ + +#define __usdt_hash # +#define __usdt_str_(x) #x +#define __usdt_str(x) __usdt_str_(x) + +#ifndef __usdt_asm_name +#define __usdt_asm_name(name) __asm__(__usdt_str(name)) +#endif + +#define __usdt_asm0() "\n" +#define __usdt_asm1(x) __usdt_str(x) "\n" +#define __usdt_asm2(x, ...) __usdt_str(x) "," __usdt_asm1(__VA_ARGS__) +#define __usdt_asm3(x, ...) __usdt_str(x) "," __usdt_asm2(__VA_ARGS__) +#define __usdt_asm4(x, ...) __usdt_str(x) "," __usdt_asm3(__VA_ARGS__) +#define __usdt_asm5(x, ...) __usdt_str(x) "," __usdt_asm4(__VA_ARGS__) +#define __usdt_asm6(x, ...) __usdt_str(x) "," __usdt_asm5(__VA_ARGS__) +#define __usdt_asm7(x, ...) __usdt_str(x) "," __usdt_asm6(__VA_ARGS__) +#define __usdt_asm8(x, ...) __usdt_str(x) "," __usdt_asm7(__VA_ARGS__) +#define __usdt_asm9(x, ...) __usdt_str(x) "," __usdt_asm8(__VA_ARGS__) +#define __usdt_asm10(x, ...) __usdt_str(x) "," __usdt_asm9(__VA_ARGS__) +#define __usdt_asm11(x, ...) __usdt_str(x) "," __usdt_asm10(__VA_ARGS__) +#define __usdt_asm12(x, ...) __usdt_str(x) "," __usdt_asm11(__VA_ARGS__) +#define __usdt_asm(...) __usdt_apply(__usdt_asm, __usdt_narg(__VA_ARGS__))(__VA_ARGS__) + +#ifdef __LP64__ +#define __usdt_asm_addr .8byte +#else +#define __usdt_asm_addr .4byte +#endif + +#define __usdt_asm_strz_(x) __usdt_asm1(.asciz #x) +#define __usdt_asm_strz(x) __usdt_asm_strz_(x) +#define __usdt_asm_str_(x) __usdt_asm1(.ascii #x) +#define __usdt_asm_str(x) __usdt_asm_str_(x) + +/* "semaphoreless" USDT case */ +#ifndef __usdt_sema_none +#define __usdt_sema_none(sema) +#endif + +/* implicitly defined __usdt_sema__group__name semaphore (using weak symbols) */ +#ifndef __usdt_sema_implicit +#define __usdt_sema_implicit(sema) \ + __asm__ __volatile__ ( \ + __usdt_asm1(.ifndef sema) \ + __usdt_asm3( .pushsection .probes, "aw", "progbits") \ + __usdt_asm1( .weak sema) \ + __usdt_asm1( .hidden sema) \ + __usdt_asm1( .align 2) \ + __usdt_asm1(sema:) \ + __usdt_asm1( .zero 2) \ + __usdt_asm2( .type sema, @object) \ + __usdt_asm2( .size sema, 2) \ + __usdt_asm1( .popsection) \ + __usdt_asm1(.endif) \ + ); +#endif + +/* externally defined semaphore using USDT_DEFINE_SEMA() and passed explicitly by user */ +#ifndef __usdt_sema_explicit +#define __usdt_sema_explicit(sema) \ + __asm__ __volatile__ ("" :: "m" (sema)); +#endif + +/* main USDT definition (nop and .note.stapsdt metadata) */ +#define __usdt_probe(group, name, sema_def, sema, ...) do { \ + sema_def(sema) \ + __asm__ __volatile__ ( \ + __usdt_asm( 990: USDT_NOP) \ + __usdt_asm3( .pushsection .note.stapsdt, "", "note") \ + __usdt_asm1( .balign 4) \ + __usdt_asm3( .4byte 992f-991f,994f-993f,3) \ + __usdt_asm1(991: .asciz "stapsdt") \ + __usdt_asm1(992: .balign 4) \ + __usdt_asm1(993: __usdt_asm_addr 990b) \ + __usdt_asm1( __usdt_asm_addr _.stapsdt.base) \ + __usdt_asm1( __usdt_asm_addr sema) \ + __usdt_asm_strz(group) \ + __usdt_asm_strz(name) \ + __usdt_asm_args(__VA_ARGS__) \ + __usdt_asm1( .ascii "\0") \ + __usdt_asm1(994: .balign 4) \ + __usdt_asm1( .popsection) \ + __usdt_asm1(.ifndef _.stapsdt.base) \ + __usdt_asm5( .pushsection .stapsdt.base,"aG","progbits",.stapsdt.base,comdat)\ + __usdt_asm1( .weak _.stapsdt.base) \ + __usdt_asm1( .hidden _.stapsdt.base) \ + __usdt_asm1(_.stapsdt.base:) \ + __usdt_asm1( .space 1) \ + __usdt_asm2( .size _.stapsdt.base, 1) \ + __usdt_asm1( .popsection) \ + __usdt_asm1(.endif) \ + :: __usdt_asm_ops(__VA_ARGS__) \ + ); \ +} while (0) + +/* + * NB: gdb PR24541 highlighted an unspecified corner of the sdt.h + * operand note format. + * + * The named register may be a longer or shorter (!) alias for the + * storage where the value in question is found. For example, on + * i386, 64-bit value may be put in register pairs, and a register + * name stored would identify just one of them. Previously, gcc was + * asked to emit the %w[id] (16-bit alias of some registers holding + * operands), even when a wider 32-bit value was used. + * + * Bottom line: the byte-width given before the @ sign governs. If + * there is a mismatch between that width and that of the named + * register, then a sys/sdt.h note consumer may need to employ + * architecture-specific heuristics to figure out where the compiler + * has actually put the complete value. + */ +#if defined(__powerpc__) || defined(__powerpc64__) +#define __usdt_argref(id) %I[id]%[id] +#elif defined(__i386__) +#define __usdt_argref(id) %k[id] /* gcc.gnu.org/PR80115 sourceware.org/PR24541 */ +#else +#define __usdt_argref(id) %[id] +#endif + +#define __usdt_asm_arg(n) __usdt_asm_str(%c[__usdt_asz##n]) \ + __usdt_asm1(.ascii "@") \ + __usdt_asm_str(__usdt_argref(__usdt_aval##n)) + +#define __usdt_asm_args0 /* no arguments */ +#define __usdt_asm_args1 __usdt_asm_arg(1) +#define __usdt_asm_args2 __usdt_asm_args1 __usdt_asm1(.ascii " ") __usdt_asm_arg(2) +#define __usdt_asm_args3 __usdt_asm_args2 __usdt_asm1(.ascii " ") __usdt_asm_arg(3) +#define __usdt_asm_args4 __usdt_asm_args3 __usdt_asm1(.ascii " ") __usdt_asm_arg(4) +#define __usdt_asm_args5 __usdt_asm_args4 __usdt_asm1(.ascii " ") __usdt_asm_arg(5) +#define __usdt_asm_args6 __usdt_asm_args5 __usdt_asm1(.ascii " ") __usdt_asm_arg(6) +#define __usdt_asm_args7 __usdt_asm_args6 __usdt_asm1(.ascii " ") __usdt_asm_arg(7) +#define __usdt_asm_args8 __usdt_asm_args7 __usdt_asm1(.ascii " ") __usdt_asm_arg(8) +#define __usdt_asm_args9 __usdt_asm_args8 __usdt_asm1(.ascii " ") __usdt_asm_arg(9) +#define __usdt_asm_args10 __usdt_asm_args9 __usdt_asm1(.ascii " ") __usdt_asm_arg(10) +#define __usdt_asm_args11 __usdt_asm_args10 __usdt_asm1(.ascii " ") __usdt_asm_arg(11) +#define __usdt_asm_args12 __usdt_asm_args11 __usdt_asm1(.ascii " ") __usdt_asm_arg(12) +#define __usdt_asm_args(...) __usdt_apply(__usdt_asm_args, __usdt_narg(__VA_ARGS__)) + +#define __usdt_is_arr(x) (__builtin_classify_type(x) == 14 || __builtin_classify_type(x) == 5) +#define __usdt_arg_size(x) (__usdt_is_arr(x) ? sizeof(void *) : sizeof(x)) + +/* + * We can't use __builtin_choose_expr() in C++, so fall back to table-based + * signedness determination for known types, utilizing templates magic. + */ +#ifdef __cplusplus + +#define __usdt_is_signed(x) (!__usdt_is_arr(x) && __usdt_t<__typeof(x)>::is_signed) + +#include <cstddef> + +template<typename T> struct __usdt_t { static const bool is_signed = false; }; +template<typename A> struct __usdt_t<A[]> : public __usdt_t<A *> {}; +template<typename A, size_t N> struct __usdt_t<A[N]> : public __usdt_t<A *> {}; + +#define __usdt_def_signed(T) \ +template<> struct __usdt_t<T> { static const bool is_signed = true; }; \ +template<> struct __usdt_t<const T> { static const bool is_signed = true; }; \ +template<> struct __usdt_t<volatile T> { static const bool is_signed = true; }; \ +template<> struct __usdt_t<const volatile T> { static const bool is_signed = true; } +#define __usdt_maybe_signed(T) \ +template<> struct __usdt_t<T> { static const bool is_signed = (T)-1 < (T)1; }; \ +template<> struct __usdt_t<const T> { static const bool is_signed = (T)-1 < (T)1; }; \ +template<> struct __usdt_t<volatile T> { static const bool is_signed = (T)-1 < (T)1; }; \ +template<> struct __usdt_t<const volatile T> { static const bool is_signed = (T)-1 < (T)1; } + +__usdt_def_signed(signed char); +__usdt_def_signed(short); +__usdt_def_signed(int); +__usdt_def_signed(long); +__usdt_def_signed(long long); +__usdt_maybe_signed(char); +__usdt_maybe_signed(wchar_t); + +#else /* !__cplusplus */ + +#define __usdt_is_inttype(x) (__builtin_classify_type(x) >= 1 && __builtin_classify_type(x) <= 4) +#define __usdt_inttype(x) __typeof(__builtin_choose_expr(__usdt_is_inttype(x), (x), 0U)) +#define __usdt_is_signed(x) ((__usdt_inttype(x))-1 < (__usdt_inttype(x))1) + +#endif /* __cplusplus */ + +#define __usdt_asm_op(n, x) \ + [__usdt_asz##n] "n" ((__usdt_is_signed(x) ? (int)-1 : 1) * (int)__usdt_arg_size(x)), \ + [__usdt_aval##n] __usdt_str(USDT_ARG_CONSTRAINT)(x) + +#define __usdt_asm_ops0() [__usdt_dummy] "g" (0) +#define __usdt_asm_ops1(x) __usdt_asm_op(1, x) +#define __usdt_asm_ops2(a,x) __usdt_asm_ops1(a), __usdt_asm_op(2, x) +#define __usdt_asm_ops3(a,b,x) __usdt_asm_ops2(a,b), __usdt_asm_op(3, x) +#define __usdt_asm_ops4(a,b,c,x) __usdt_asm_ops3(a,b,c), __usdt_asm_op(4, x) +#define __usdt_asm_ops5(a,b,c,d,x) __usdt_asm_ops4(a,b,c,d), __usdt_asm_op(5, x) +#define __usdt_asm_ops6(a,b,c,d,e,x) __usdt_asm_ops5(a,b,c,d,e), __usdt_asm_op(6, x) +#define __usdt_asm_ops7(a,b,c,d,e,f,x) __usdt_asm_ops6(a,b,c,d,e,f), __usdt_asm_op(7, x) +#define __usdt_asm_ops8(a,b,c,d,e,f,g,x) __usdt_asm_ops7(a,b,c,d,e,f,g), __usdt_asm_op(8, x) +#define __usdt_asm_ops9(a,b,c,d,e,f,g,h,x) __usdt_asm_ops8(a,b,c,d,e,f,g,h), __usdt_asm_op(9, x) +#define __usdt_asm_ops10(a,b,c,d,e,f,g,h,i,x) __usdt_asm_ops9(a,b,c,d,e,f,g,h,i), __usdt_asm_op(10, x) +#define __usdt_asm_ops11(a,b,c,d,e,f,g,h,i,j,x) __usdt_asm_ops10(a,b,c,d,e,f,g,h,i,j), __usdt_asm_op(11, x) +#define __usdt_asm_ops12(a,b,c,d,e,f,g,h,i,j,k,x) __usdt_asm_ops11(a,b,c,d,e,f,g,h,i,j,k), __usdt_asm_op(12, x) +#define __usdt_asm_ops(...) __usdt_apply(__usdt_asm_ops, __usdt_narg(__VA_ARGS__))(__VA_ARGS__) + +#endif /* __USDT_H */ diff --git a/tools/testing/selftests/bpf/verifier/bpf_st_mem.c b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c index b616575c3b00..ce13002c7a19 100644 --- a/tools/testing/selftests/bpf/verifier/bpf_st_mem.c +++ b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c @@ -93,7 +93,7 @@ .expected_attach_type = BPF_SK_LOOKUP, .result = VERBOSE_ACCEPT, .runs = -1, - .errstr = "0: (7a) *(u64 *)(r10 -8) = -44 ; R10=fp0 fp-8_w=-44\ + .errstr = "0: (7a) *(u64 *)(r10 -8) = -44 ; R10=fp0 fp-8=-44\ 2: (c5) if r0 s< 0x0 goto pc+2\ - R0_w=-44", + R0=-44", }, diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 18596ae0b0c1..c8d640802cce 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -1375,7 +1375,7 @@ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), /* write into map value */ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), - /* fetch secound map_value_ptr from the stack */ + /* fetch second map_value_ptr from the stack */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), /* write into map value */ @@ -1439,7 +1439,7 @@ /* second time with fp-16 */ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), - /* fetch secound map_value_ptr from the stack */ + /* fetch second map_value_ptr from the stack */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0), /* write into map value */ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), @@ -1493,7 +1493,7 @@ /* second time with fp-16 */ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4), BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), - /* fetch secound map_value_ptr from the stack */ + /* fetch second map_value_ptr from the stack */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0), /* write into map value */ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), @@ -2380,7 +2380,7 @@ */ BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), BPF_MOV64_REG(BPF_REG_9, BPF_REG_8), - /* r9 = *r9 ; verifier get's to this point via two paths: + /* r9 = *r9 ; verifier gets to this point via two paths: * ; (I) one including r9 = r8, verified first; * ; (II) one excluding r9 = r8, verified next. * ; After load of *r9 to r9 the frame[0].fp[-24].id == r9.id. @@ -2409,3 +2409,27 @@ .errstr_unpriv = "", .prog_type = BPF_PROG_TYPE_CGROUP_SKB, }, +{ + "calls: several args with ref_obj_id", + .insns = { + /* Reserve at least sizeof(struct iphdr) bytes in the ring buffer. + * With a smaller size, the verifier would reject the call to + * bpf_tcp_raw_gen_syncookie_ipv4 before we can reach the + * ref_obj_id error. + */ + BPF_MOV64_IMM(BPF_REG_2, 20), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve), + /* if r0 == 0 goto <exit> */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tcp_raw_gen_syncookie_ipv4), + BPF_EXIT_INSN(), + }, + .fixup_map_ringbuf = { 2 }, + .result = REJECT, + .errstr = "more than one arg with ref_obj_id", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c index ee454327e5c6..77207b498c6f 100644 --- a/tools/testing/selftests/bpf/verifier/dead_code.c +++ b/tools/testing/selftests/bpf/verifier/dead_code.c @@ -2,14 +2,13 @@ "dead code: start", .insns = { BPF_JMP_IMM(BPF_JA, 0, 0, 2), + /* unpriv: nospec (inserted to prevent "R9 !read_ok") */ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_JMP_IMM(BPF_JA, 0, 0, 2), BPF_MOV64_IMM(BPF_REG_0, 7), BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 10, -4), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R9 !read_ok", - .result_unpriv = REJECT, .result = ACCEPT, .retval = 7, }, diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c index 43776f6f92f4..91d83e9cb148 100644 --- a/tools/testing/selftests/bpf/verifier/jmp32.c +++ b/tools/testing/selftests/bpf/verifier/jmp32.c @@ -84,11 +84,10 @@ BPF_JMP32_IMM(BPF_JSET, BPF_REG_7, 0x10, 1), BPF_EXIT_INSN(), BPF_JMP32_IMM(BPF_JGE, BPF_REG_7, 0x10, 1), + /* unpriv: nospec (inserted to prevent "R9 !read_ok") */ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R9 !read_ok", - .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -149,11 +148,10 @@ BPF_JMP32_IMM(BPF_JEQ, BPF_REG_7, 0x10, 1), BPF_EXIT_INSN(), BPF_JMP32_IMM(BPF_JSGE, BPF_REG_7, 0xf, 1), + /* unpriv: nospec (inserted to prevent "R9 !read_ok") */ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R9 !read_ok", - .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -214,11 +212,10 @@ BPF_JMP32_IMM(BPF_JNE, BPF_REG_7, 0x10, 1), BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x10, 1), BPF_EXIT_INSN(), + /* unpriv: nospec (inserted to prevent "R9 !read_ok") */ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R9 !read_ok", - .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -283,11 +280,10 @@ BPF_JMP32_REG(BPF_JGE, BPF_REG_7, BPF_REG_8, 1), BPF_EXIT_INSN(), BPF_JMP32_IMM(BPF_JGE, BPF_REG_7, 0x7ffffff0, 1), + /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'scalar'", - .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -354,11 +350,10 @@ BPF_JMP32_REG(BPF_JGT, BPF_REG_7, BPF_REG_8, 1), BPF_EXIT_INSN(), BPF_JMP_IMM(BPF_JGT, BPF_REG_7, 0x7ffffff0, 1), + /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'scalar'", - .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -425,11 +420,10 @@ BPF_JMP32_REG(BPF_JLE, BPF_REG_7, BPF_REG_8, 1), BPF_EXIT_INSN(), BPF_JMP32_IMM(BPF_JLE, BPF_REG_7, 0x7ffffff0, 1), + /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'scalar'", - .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -496,11 +490,10 @@ BPF_JMP32_REG(BPF_JLT, BPF_REG_7, BPF_REG_8, 1), BPF_EXIT_INSN(), BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0x7ffffff0, 1), + /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'scalar'", - .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -567,11 +560,10 @@ BPF_JMP32_REG(BPF_JSGE, BPF_REG_7, BPF_REG_8, 1), BPF_EXIT_INSN(), BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0x7ffffff0, 1), + /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'scalar'", - .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -638,11 +630,10 @@ BPF_JMP32_REG(BPF_JSGT, BPF_REG_7, BPF_REG_8, 1), BPF_EXIT_INSN(), BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, -2, 1), + /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'scalar'", - .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -709,11 +700,10 @@ BPF_JMP32_REG(BPF_JSLE, BPF_REG_7, BPF_REG_8, 1), BPF_EXIT_INSN(), BPF_JMP_IMM(BPF_JSLE, BPF_REG_7, 0x7ffffff0, 1), + /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'scalar'", - .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -780,11 +770,10 @@ BPF_JMP32_REG(BPF_JSLT, BPF_REG_7, BPF_REG_8, 1), BPF_EXIT_INSN(), BPF_JMP32_IMM(BPF_JSLT, BPF_REG_7, -1, 1), + /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'scalar'", - .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c index 11fc68da735e..e901eefd774a 100644 --- a/tools/testing/selftests/bpf/verifier/jset.c +++ b/tools/testing/selftests/bpf/verifier/jset.c @@ -78,12 +78,11 @@ .insns = { BPF_MOV64_IMM(BPF_REG_0, 1), BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1), + /* unpriv: nospec (inserted to prevent "R9 !read_ok") */ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .errstr_unpriv = "R9 !read_ok", - .result_unpriv = REJECT, .retval = 1, .result = ACCEPT, }, @@ -136,13 +135,12 @@ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), BPF_ALU64_IMM(BPF_OR, BPF_REG_0, 2), BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 3, 1), + /* unpriv: nospec (inserted to prevent "R9 !read_ok") */ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .errstr_unpriv = "R9 !read_ok", - .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -154,16 +152,16 @@ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xff), BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0xf0, 3), BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 0x10, 1), + /* unpriv: nospec (inserted to prevent "R9 !read_ok") */ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0x10, 1), BPF_EXIT_INSN(), BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0x10, 1), + /* unpriv: nospec (inserted to prevent "R9 !read_ok") */ BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0), BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, - .errstr_unpriv = "R9 !read_ok", - .result_unpriv = REJECT, .result = ACCEPT, }, diff --git a/tools/testing/selftests/bpf/verify_sig_setup.sh b/tools/testing/selftests/bpf/verify_sig_setup.sh index f2cac42298ba..09179fb551f0 100755 --- a/tools/testing/selftests/bpf/verify_sig_setup.sh +++ b/tools/testing/selftests/bpf/verify_sig_setup.sh @@ -32,7 +32,7 @@ usage() exit 1 } -setup() +genkey() { local tmp_dir="$1" @@ -45,9 +45,14 @@ setup() openssl x509 -in ${tmp_dir}/signing_key.pem -out \ ${tmp_dir}/signing_key.der -outform der +} - key_id=$(cat ${tmp_dir}/signing_key.der | keyctl padd asymmetric ebpf_testing_key @s) +setup() +{ + local tmp_dir="$1" + genkey "${tmp_dir}" + key_id=$(cat ${tmp_dir}/signing_key.der | keyctl padd asymmetric ebpf_testing_key @s) keyring_id=$(keyctl newring ebpf_testing_keyring @s) keyctl link $key_id $keyring_id } @@ -105,6 +110,8 @@ main() if [[ "${action}" == "setup" ]]; then setup "${tmp_dir}" + elif [[ "${action}" == "genkey" ]]; then + genkey "${tmp_dir}" elif [[ "${action}" == "cleanup" ]]; then cleanup "${tmp_dir}" elif [[ "${action}" == "fsverity-create-sign" ]]; then diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index b2bb20b00952..e962f133250c 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -23,6 +23,7 @@ #include <float.h> #include <math.h> #include <limits.h> +#include <assert.h> #ifndef ARRAY_SIZE #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) @@ -49,6 +50,7 @@ enum stat_id { STACK, PROG_TYPE, ATTACH_TYPE, + MEMORY_PEAK, FILE_NAME, PROG_NAME, @@ -155,16 +157,36 @@ struct filter { bool abs; }; -struct var_preset { - char *name; +struct rvalue { enum { INTEGRAL, ENUMERATOR } type; union { long long ivalue; char *svalue; }; +}; + +struct field_access { + enum { FIELD_NAME, ARRAY_INDEX } type; + union { + char *name; + struct rvalue index; + }; +}; + +struct var_preset { + struct field_access *atoms; + int atom_count; + char *full_name; + struct rvalue value; bool applied; }; +enum dump_mode { + DUMP_NONE = 0, + DUMP_XLATED = 1, + DUMP_JITED = 2, +}; + static struct env { char **filenames; int filename_cnt; @@ -208,6 +230,10 @@ static struct env { int top_src_lines; struct var_preset *presets; int npresets; + char orig_cgroup[PATH_MAX]; + char stat_cgroup[PATH_MAX]; + int memory_peak_fd; + __u32 dump_mode; } env; static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args) @@ -219,6 +245,22 @@ static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va return vfprintf(stderr, format, args); } +#define log_errno(fmt, ...) log_errno_aux(__FILE__, __LINE__, fmt, ##__VA_ARGS__) + +__attribute__((format(printf, 3, 4))) +static int log_errno_aux(const char *file, int line, const char *fmt, ...) +{ + int err = -errno; + va_list ap; + + va_start(ap, fmt); + fprintf(stderr, "%s:%d: ", file, line); + vfprintf(stderr, fmt, ap); + fprintf(stderr, " failed with error '%s'.\n", strerror(errno)); + va_end(ap); + return err; +} + #ifndef VERISTAT_VERSION #define VERISTAT_VERSION "<kernel>" #endif @@ -236,6 +278,7 @@ const char argp_program_doc[] = enum { OPT_LOG_FIXED = 1000, OPT_LOG_SIZE = 1001, + OPT_DUMP = 1002, }; static const struct argp_option opts[] = { @@ -260,6 +303,7 @@ static const struct argp_option opts[] = { "Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" }, { "top-src-lines", 'S', "N", 0, "Emit N most frequent source code lines" }, { "set-global-vars", 'G', "GLOBAL", 0, "Set global variables provided in the expression, for example \"var1 = 1\"" }, + { "dump", OPT_DUMP, "DUMP_MODE", OPTION_ARG_OPTIONAL, "Print BPF program dump (xlated, jited)" }, {}, }; @@ -344,6 +388,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) fprintf(stderr, "invalid top N specifier: %s\n", arg); argp_usage(state); } + break; case 'C': env.comparison_mode = true; break; @@ -391,6 +436,16 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) return err; } break; + case OPT_DUMP: + if (!arg || strcasecmp(arg, "xlated") == 0) { + env.dump_mode |= DUMP_XLATED; + } else if (strcasecmp(arg, "jited") == 0) { + env.dump_mode |= DUMP_JITED; + } else { + fprintf(stderr, "Unrecognized dump mode '%s'\n", arg); + return -EINVAL; + } + break; default: return ARGP_ERR_UNKNOWN; } @@ -734,13 +789,13 @@ cleanup: } static const struct stat_specs default_csv_output_spec = { - .spec_cnt = 14, + .spec_cnt = 15, .ids = { FILE_NAME, PROG_NAME, VERDICT, DURATION, TOTAL_INSNS, TOTAL_STATES, PEAK_STATES, MAX_STATES_PER_INSN, MARK_READ_MAX_LEN, SIZE, JITED_SIZE, PROG_TYPE, ATTACH_TYPE, - STACK, + STACK, MEMORY_PEAK, }, }; @@ -781,6 +836,7 @@ static struct stat_def { [STACK] = {"Stack depth", {"stack_depth", "stack"}, }, [PROG_TYPE] = { "Program type", {"prog_type"}, }, [ATTACH_TYPE] = { "Attach type", {"attach_type", }, }, + [MEMORY_PEAK] = { "Peak memory (MiB)", {"mem_peak", }, }, }; static bool parse_stat_id_var(const char *name, size_t len, int *id, @@ -854,6 +910,18 @@ static bool is_desc_sym(char c) return c == 'v' || c == 'V' || c == '.' || c == '!' || c == '_'; } +static char *rtrim(char *str) +{ + int i; + + for (i = strlen(str) - 1; i > 0; --i) { + if (!isspace(str[i])) + break; + str[i] = '\0'; + } + return str; +} + static int parse_stat(const char *stat_name, struct stat_specs *specs) { int id; @@ -1182,6 +1250,7 @@ static void fixup_obj(struct bpf_object *obj, struct bpf_program *prog, const ch case BPF_MAP_TYPE_TASK_STORAGE: case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_CGROUP_STORAGE: + case BPF_MAP_TYPE_CGRP_STORAGE: break; case BPF_MAP_TYPE_STRUCT_OPS: mask_unrelated_struct_ops_progs(obj, map, prog); @@ -1278,16 +1347,273 @@ static int max_verifier_log_size(void) return log_size; } +static bool output_stat_enabled(int id) +{ + int i; + + for (i = 0; i < env.output_spec.spec_cnt; i++) + if (env.output_spec.ids[i] == id) + return true; + return false; +} + +__attribute__((format(printf, 2, 3))) +static int write_one_line(const char *file, const char *fmt, ...) +{ + int err, saved_errno; + va_list ap; + FILE *f; + + f = fopen(file, "w"); + if (!f) + return -1; + + va_start(ap, fmt); + errno = 0; + err = vfprintf(f, fmt, ap); + saved_errno = errno; + va_end(ap); + fclose(f); + errno = saved_errno; + return err < 0 ? -1 : 0; +} + +__attribute__((format(scanf, 3, 4))) +static int scanf_one_line(const char *file, int fields_expected, const char *fmt, ...) +{ + int res = 0, saved_errno = 0; + char *line = NULL; + size_t line_len; + va_list ap; + FILE *f; + + f = fopen(file, "r"); + if (!f) + return -1; + + va_start(ap, fmt); + while (getline(&line, &line_len, f) > 0) { + res = vsscanf(line, fmt, ap); + if (res == fields_expected) + goto out; + } + if (ferror(f)) { + saved_errno = errno; + res = -1; + } + +out: + va_end(ap); + free(line); + fclose(f); + errno = saved_errno; + return res; +} + +static void destroy_stat_cgroup(void) +{ + char buf[PATH_MAX]; + int err; + + close(env.memory_peak_fd); + + if (env.orig_cgroup[0]) { + snprintf(buf, sizeof(buf), "%s/cgroup.procs", env.orig_cgroup); + err = write_one_line(buf, "%d\n", getpid()); + if (err < 0) + log_errno("moving self to original cgroup %s\n", env.orig_cgroup); + } + + if (env.stat_cgroup[0]) { + err = rmdir(env.stat_cgroup); + if (err < 0) + log_errno("deletion of cgroup %s", env.stat_cgroup); + } + + env.memory_peak_fd = -1; + env.orig_cgroup[0] = 0; + env.stat_cgroup[0] = 0; +} + +/* + * Creates a cgroup at /sys/fs/cgroup/veristat-accounting-<pid>, + * moves current process to this cgroup. + */ +static void create_stat_cgroup(void) +{ + char cgroup_fs_mount[4096]; + char buf[4096]; + int err; + + env.memory_peak_fd = -1; + + if (!output_stat_enabled(MEMORY_PEAK)) + return; + + err = scanf_one_line("/proc/self/mounts", 2, "%*s %4095s cgroup2 %s", + cgroup_fs_mount, buf); + if (err != 2) { + if (err < 0) + log_errno("reading /proc/self/mounts"); + else if (!env.quiet) + fprintf(stderr, "Can't find cgroupfs v2 mount point.\n"); + goto err_out; + } + + /* cgroup-v2.rst promises the line "0::<group>" for cgroups v2 */ + err = scanf_one_line("/proc/self/cgroup", 1, "0::%4095s", buf); + if (err != 1) { + if (err < 0) + log_errno("reading /proc/self/cgroup"); + else if (!env.quiet) + fprintf(stderr, "Can't infer veristat process cgroup."); + goto err_out; + } + + snprintf(env.orig_cgroup, sizeof(env.orig_cgroup), "%s/%s", cgroup_fs_mount, buf); + + snprintf(buf, sizeof(buf), "%s/veristat-accounting-%d", cgroup_fs_mount, getpid()); + err = mkdir(buf, 0777); + if (err < 0) { + log_errno("creation of cgroup %s", buf); + goto err_out; + } + strcpy(env.stat_cgroup, buf); + + snprintf(buf, sizeof(buf), "%s/cgroup.procs", env.stat_cgroup); + err = write_one_line(buf, "%d\n", getpid()); + if (err < 0) { + log_errno("entering cgroup %s", buf); + goto err_out; + } + + snprintf(buf, sizeof(buf), "%s/memory.peak", env.stat_cgroup); + env.memory_peak_fd = open(buf, O_RDWR | O_APPEND); + if (env.memory_peak_fd < 0) { + log_errno("opening %s", buf); + goto err_out; + } + + return; + +err_out: + if (!env.quiet) + fprintf(stderr, "Memory usage metric unavailable.\n"); + destroy_stat_cgroup(); +} + +/* Current value of /sys/fs/cgroup/veristat-accounting-<pid>/memory.peak */ +static long cgroup_memory_peak(void) +{ + long err, memory_peak; + char buf[32]; + + if (env.memory_peak_fd < 0) + return -1; + + err = pread(env.memory_peak_fd, buf, sizeof(buf) - 1, 0); + if (err <= 0) { + log_errno("pread(%s/memory.peak)", env.stat_cgroup); + return -1; + } + + buf[err] = 0; + errno = 0; + memory_peak = strtoll(buf, NULL, 10); + if (errno) { + log_errno("%s/memory.peak:strtoll(%s)", env.stat_cgroup, buf); + return -1; + } + + return memory_peak; +} + +static int reset_stat_cgroup(void) +{ + char buf[] = "r\n"; + int err; + + if (env.memory_peak_fd < 0) + return -1; + + err = pwrite(env.memory_peak_fd, buf, sizeof(buf), 0); + if (err <= 0) { + log_errno("pwrite(%s/memory.peak)", env.stat_cgroup); + return -1; + } + return 0; +} + +static int parse_rvalue(const char *val, struct rvalue *rvalue) +{ + long long value; + char *val_end; + + if (val[0] == '-' || isdigit(val[0])) { + /* must be a number */ + errno = 0; + value = strtoll(val, &val_end, 0); + if (errno == ERANGE) { + errno = 0; + value = strtoull(val, &val_end, 0); + } + if (errno || *val_end != '\0') { + fprintf(stderr, "Failed to parse value '%s'\n", val); + return -EINVAL; + } + rvalue->ivalue = value; + rvalue->type = INTEGRAL; + } else { + /* if not a number, consider it enum value */ + rvalue->svalue = strdup(val); + if (!rvalue->svalue) + return -ENOMEM; + rvalue->type = ENUMERATOR; + } + return 0; +} + +static void dump(__u32 prog_id, enum dump_mode mode, const char *file_name, const char *prog_name) +{ + char command[64], buf[4096]; + FILE *fp; + int status; + + status = system("command -v bpftool > /dev/null 2>&1"); + if (status != 0) { + fprintf(stderr, "bpftool is not available, can't print program dump\n"); + return; + } + snprintf(command, sizeof(command), "bpftool prog dump %s id %u", + mode == DUMP_JITED ? "jited" : "xlated", prog_id); + fp = popen(command, "r"); + if (!fp) { + fprintf(stderr, "bpftool failed with error: %d\n", errno); + return; + } + + printf("DUMP (%s) %s/%s:\n", mode == DUMP_JITED ? "JITED" : "XLATED", file_name, prog_name); + while (fgets(buf, sizeof(buf), fp)) + fputs(buf, stdout); + fprintf(stdout, "\n"); + + if (ferror(fp)) + fprintf(stderr, "Failed to dump BPF prog with error: %d\n", errno); + + pclose(fp); +} + static int process_prog(const char *filename, struct bpf_object *obj, struct bpf_program *prog) { const char *base_filename = basename(strdupa(filename)); const char *prog_name = bpf_program__name(prog); + long mem_peak_a, mem_peak_b, mem_peak = -1; char *buf; int buf_sz, log_level; struct verif_stats *stats; struct bpf_prog_info info; __u32 info_len = sizeof(info); - int err = 0; + int err = 0, cgroup_err; void *tmp; int fd; @@ -1332,7 +1658,15 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf if (env.force_reg_invariants) bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_REG_INVARIANTS); - err = bpf_object__load(obj); + err = bpf_object__prepare(obj); + if (!err) { + cgroup_err = reset_stat_cgroup(); + mem_peak_a = cgroup_memory_peak(); + err = bpf_object__load(obj); + mem_peak_b = cgroup_memory_peak(); + if (!cgroup_err && mem_peak_a >= 0 && mem_peak_b >= 0) + mem_peak = mem_peak_b - mem_peak_a; + } env.progs_processed++; stats->file_name = strdup(base_filename); @@ -1341,11 +1675,17 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf stats->stats[SIZE] = bpf_program__insn_cnt(prog); stats->stats[PROG_TYPE] = bpf_program__type(prog); stats->stats[ATTACH_TYPE] = bpf_program__expected_attach_type(prog); + stats->stats[MEMORY_PEAK] = mem_peak < 0 ? -1 : mem_peak / (1024 * 1024); memset(&info, 0, info_len); fd = bpf_program__fd(prog); - if (fd > 0 && bpf_prog_get_info_by_fd(fd, &info, &info_len) == 0) + if (fd > 0 && bpf_prog_get_info_by_fd(fd, &info, &info_len) == 0) { stats->stats[JITED_SIZE] = info.jited_prog_len; + if (env.dump_mode & DUMP_JITED) + dump(info.id, DUMP_JITED, base_filename, prog_name); + if (env.dump_mode & DUMP_XLATED) + dump(info.id, DUMP_XLATED, base_filename, prog_name); + } parse_verif_log(buf, buf_sz, stats); @@ -1361,15 +1701,74 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf free(buf); return 0; -}; +} + +static int append_preset_atom(struct var_preset *preset, char *value, bool is_index) +{ + struct field_access *tmp; + int i = preset->atom_count; + int err; + + tmp = reallocarray(preset->atoms, i + 1, sizeof(*preset->atoms)); + if (!tmp) + return -ENOMEM; + + preset->atoms = tmp; + preset->atom_count++; + + if (is_index) { + preset->atoms[i].type = ARRAY_INDEX; + err = parse_rvalue(value, &preset->atoms[i].index); + if (err) + return err; + } else { + preset->atoms[i].type = FIELD_NAME; + preset->atoms[i].name = strdup(value); + if (!preset->atoms[i].name) + return -ENOMEM; + } + return 0; +} + +static int parse_var_atoms(const char *full_var, struct var_preset *preset) +{ + char expr[256], var[256], *name, *saveptr; + int n, len, off, err; + + snprintf(expr, sizeof(expr), "%s", full_var); + preset->atom_count = 0; + while ((name = strtok_r(preset->atom_count ? NULL : expr, ".", &saveptr))) { + len = strlen(name); + /* parse variable name */ + if (sscanf(name, "%[a-zA-Z0-9_] %n", var, &off) != 1) { + fprintf(stderr, "Can't parse %s\n", name); + return -EINVAL; + } + err = append_preset_atom(preset, var, false); + if (err) + return err; + + /* parse optional array indexes */ + while (off < len) { + if (sscanf(name + off, " [ %[a-zA-Z0-9_] ] %n", var, &n) != 1) { + fprintf(stderr, "Can't parse %s as index\n", name + off); + return -EINVAL; + } + err = append_preset_atom(preset, var, true); + if (err) + return err; + off += n; + } + } + return 0; +} static int append_var_preset(struct var_preset **presets, int *cnt, const char *expr) { void *tmp; struct var_preset *cur; - char var[256], val[256], *val_end; - long long value; - int n; + char var[256], val[256]; + int n, err; tmp = realloc(*presets, (*cnt + 1) * sizeof(**presets)); if (!tmp) @@ -1379,37 +1778,25 @@ static int append_var_preset(struct var_preset **presets, int *cnt, const char * memset(cur, 0, sizeof(*cur)); (*cnt)++; - if (sscanf(expr, "%s = %s %n", var, val, &n) != 2 || n != strlen(expr)) { + if (sscanf(expr, " %[][a-zA-Z0-9_. ] = %s %n", var, val, &n) != 2 || n != strlen(expr)) { fprintf(stderr, "Failed to parse expression '%s'\n", expr); return -EINVAL; } + /* Remove trailing spaces from var, as scanf may add those */ + rtrim(var); - if (val[0] == '-' || isdigit(val[0])) { - /* must be a number */ - errno = 0; - value = strtoll(val, &val_end, 0); - if (errno == ERANGE) { - errno = 0; - value = strtoull(val, &val_end, 0); - } - if (errno || *val_end != '\0') { - fprintf(stderr, "Failed to parse value '%s'\n", val); - return -EINVAL; - } - cur->ivalue = value; - cur->type = INTEGRAL; - } else { - /* if not a number, consider it enum value */ - cur->svalue = strdup(val); - if (!cur->svalue) - return -ENOMEM; - cur->type = ENUMERATOR; - } + err = parse_rvalue(val, &cur->value); + if (err) + return err; - cur->name = strdup(var); - if (!cur->name) + cur->full_name = strdup(var); + if (!cur->full_name) return -ENOMEM; + err = parse_var_atoms(var, cur); + if (err) + return err; + return 0; } @@ -1486,22 +1873,96 @@ static bool is_preset_supported(const struct btf_type *t) return btf_is_int(t) || btf_is_enum(t) || btf_is_enum64(t); } -const int btf_find_member(const struct btf *btf, - const struct btf_type *parent_type, - __u32 parent_offset, - const char *member_name, - int *member_tid, - __u32 *member_offset) +static int find_enum_value(const struct btf *btf, const char *name, long long *value) +{ + const struct btf_type *t; + int cnt, i; + long long lvalue; + + cnt = btf__type_cnt(btf); + for (i = 1; i != cnt; ++i) { + t = btf__type_by_id(btf, i); + + if (!btf_is_any_enum(t)) + continue; + + if (enum_value_from_name(btf, t, name, &lvalue) == 0) { + *value = lvalue; + return 0; + } + } + return -ESRCH; +} + +static int resolve_rvalue(struct btf *btf, const struct rvalue *rvalue, long long *result) +{ + int err = 0; + + switch (rvalue->type) { + case INTEGRAL: + *result = rvalue->ivalue; + return 0; + case ENUMERATOR: + err = find_enum_value(btf, rvalue->svalue, result); + if (err) { + fprintf(stderr, "Can't resolve enum value %s\n", rvalue->svalue); + return err; + } + return 0; + default: + fprintf(stderr, "Unknown rvalue type\n"); + return -EOPNOTSUPP; + } + return 0; +} + +static int adjust_var_secinfo_array(struct btf *btf, int tid, struct field_access *atom, + const char *array_name, struct btf_var_secinfo *sinfo) +{ + const struct btf_type *t; + struct btf_array *barr; + long long idx; + int err; + + tid = btf__resolve_type(btf, tid); + t = btf__type_by_id(btf, tid); + if (!btf_is_array(t)) { + fprintf(stderr, "Array index is not expected for %s\n", + array_name); + return -EINVAL; + } + barr = btf_array(t); + err = resolve_rvalue(btf, &atom->index, &idx); + if (err) + return err; + if (idx < 0 || idx >= barr->nelems) { + fprintf(stderr, "Array index %lld is out of bounds [0, %u): %s\n", + idx, barr->nelems, array_name); + return -EINVAL; + } + sinfo->size = btf__resolve_size(btf, barr->type); + sinfo->offset += sinfo->size * idx; + sinfo->type = btf__resolve_type(btf, barr->type); + return 0; +} + +static int adjust_var_secinfo_member(const struct btf *btf, + const struct btf_type *parent_type, + __u32 parent_offset, + const char *member_name, + struct btf_var_secinfo *sinfo) { int i; - if (!btf_is_composite(parent_type)) + if (!btf_is_composite(parent_type)) { + fprintf(stderr, "Can't resolve field %s for non-composite type\n", member_name); return -EINVAL; + } for (i = 0; i < btf_vlen(parent_type); ++i) { const struct btf_member *member; const struct btf_type *member_type; - int tid; + int tid, off; member = btf_members(parent_type) + i; tid = btf__resolve_type(btf, member->type); @@ -1509,6 +1970,7 @@ const int btf_find_member(const struct btf *btf, return -EINVAL; member_type = btf__type_by_id(btf, tid); + off = parent_offset + member->offset; if (member->name_off) { const char *name = btf__name_by_offset(btf, member->name_off); @@ -1518,48 +1980,62 @@ const int btf_find_member(const struct btf *btf, name); return -EINVAL; } - *member_offset = parent_offset + member->offset; - *member_tid = tid; + sinfo->offset += off / 8; + sinfo->type = tid; + sinfo->size = member_type->size; return 0; } } else if (btf_is_composite(member_type)) { int err; - err = btf_find_member(btf, member_type, parent_offset + member->offset, - member_name, member_tid, member_offset); + err = adjust_var_secinfo_member(btf, member_type, off, + member_name, sinfo); if (!err) return 0; } } - return -EINVAL; + return -ESRCH; } static int adjust_var_secinfo(struct btf *btf, const struct btf_type *t, - struct btf_var_secinfo *sinfo, const char *var) + struct btf_var_secinfo *sinfo, struct var_preset *preset) { - char expr[256], *saveptr; - const struct btf_type *base_type, *member_type; - int err, member_tid; - char *name; - __u32 member_offset = 0; + const struct btf_type *base_type; + const char *prev_name; + int err, i; + int tid; - base_type = btf__type_by_id(btf, btf__resolve_type(btf, t->type)); - snprintf(expr, sizeof(expr), "%s", var); - strtok_r(expr, ".", &saveptr); + assert(preset->atom_count > 0); + assert(preset->atoms[0].type == FIELD_NAME); - while ((name = strtok_r(NULL, ".", &saveptr))) { - err = btf_find_member(btf, base_type, 0, name, &member_tid, &member_offset); - if (err) { - fprintf(stderr, "Could not find member %s for variable %s\n", name, var); - return err; + tid = btf__resolve_type(btf, t->type); + base_type = btf__type_by_id(btf, tid); + prev_name = preset->atoms[0].name; + + for (i = 1; i < preset->atom_count; ++i) { + struct field_access *atom = preset->atoms + i; + + switch (atom->type) { + case ARRAY_INDEX: + err = adjust_var_secinfo_array(btf, tid, atom, prev_name, sinfo); + break; + case FIELD_NAME: + err = adjust_var_secinfo_member(btf, base_type, 0, atom->name, sinfo); + if (err == -ESRCH) + fprintf(stderr, "Can't find '%s'\n", atom->name); + prev_name = atom->name; + break; + default: + fprintf(stderr, "Unknown field_access type\n"); + return -EOPNOTSUPP; } - member_type = btf__type_by_id(btf, member_tid); - sinfo->offset += member_offset / 8; - sinfo->size = member_type->size; - sinfo->type = member_tid; - base_type = member_type; + if (err) + return err; + base_type = btf__type_by_id(btf, sinfo->type); + tid = sinfo->type; } + return 0; } @@ -1569,7 +2045,7 @@ static int set_global_var(struct bpf_object *obj, struct btf *btf, { const struct btf_type *base_type; void *ptr; - long long value = preset->ivalue; + long long value = preset->value.ivalue; size_t size; base_type = btf__type_by_id(btf, btf__resolve_type(btf, sinfo->type)); @@ -1578,22 +2054,23 @@ static int set_global_var(struct bpf_object *obj, struct btf *btf, return -EINVAL; } if (!is_preset_supported(base_type)) { - fprintf(stderr, "Setting value for type %s is not supported\n", - btf__name_by_offset(btf, base_type->name_off)); + fprintf(stderr, "Can't set %s. Only ints and enums are supported\n", + preset->full_name); return -EINVAL; } - if (preset->type == ENUMERATOR) { + if (preset->value.type == ENUMERATOR) { if (btf_is_any_enum(base_type)) { - if (enum_value_from_name(btf, base_type, preset->svalue, &value)) { + if (enum_value_from_name(btf, base_type, preset->value.svalue, &value)) { fprintf(stderr, "Failed to find integer value for enum element %s\n", - preset->svalue); + preset->value.svalue); return -EINVAL; } } else { fprintf(stderr, "Value %s is not supported for type %s\n", - preset->svalue, btf__name_by_offset(btf, base_type->name_off)); + preset->value.svalue, + btf__name_by_offset(btf, base_type->name_off)); return -EINVAL; } } @@ -1660,20 +2137,16 @@ static int set_global_vars(struct bpf_object *obj, struct var_preset *presets, i for (j = 0; j < n; ++j, ++sinfo) { const struct btf_type *var_type = btf__type_by_id(btf, sinfo->type); const char *var_name; - int var_len; if (!btf_is_var(var_type)) continue; var_name = btf__name_by_offset(btf, var_type->name_off); - var_len = strlen(var_name); for (k = 0; k < npresets; ++k) { struct btf_var_secinfo tmp_sinfo; - if (strncmp(var_name, presets[k].name, var_len) != 0 || - (presets[k].name[var_len] != '\0' && - presets[k].name[var_len] != '.')) + if (strcmp(var_name, presets[k].atoms[0].name) != 0) continue; if (presets[k].applied) { @@ -1683,7 +2156,7 @@ static int set_global_vars(struct bpf_object *obj, struct var_preset *presets, i } tmp_sinfo = *sinfo; err = adjust_var_secinfo(btf, var_type, - &tmp_sinfo, presets[k].name); + &tmp_sinfo, presets + k); if (err) return err; @@ -1698,7 +2171,8 @@ static int set_global_vars(struct bpf_object *obj, struct var_preset *presets, i for (i = 0; i < npresets; ++i) { if (!presets[i].applied) { fprintf(stderr, "Global variable preset %s has not been applied\n", - presets[i].name); + presets[i].full_name); + err = -EINVAL; } presets[i].applied = false; } @@ -1824,6 +2298,7 @@ static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2, case TOTAL_STATES: case PEAK_STATES: case MAX_STATES_PER_INSN: + case MEMORY_PEAK: case MARK_READ_MAX_LEN: { long v1 = s1->stats[id]; long v2 = s2->stats[id]; @@ -2053,6 +2528,7 @@ static void prepare_value(const struct verif_stats *s, enum stat_id id, case STACK: case SIZE: case JITED_SIZE: + case MEMORY_PEAK: *val = s ? s->stats[id] : 0; break; default: @@ -2139,6 +2615,7 @@ static int parse_stat_value(const char *str, enum stat_id id, struct verif_stats case MARK_READ_MAX_LEN: case SIZE: case JITED_SIZE: + case MEMORY_PEAK: case STACK: { long val; int err, n; @@ -2776,7 +3253,7 @@ static void output_prog_stats(void) static int handle_verif_mode(void) { - int i, err; + int i, err = 0; if (env.filename_cnt == 0) { fprintf(stderr, "Please provide path to BPF object file!\n\n"); @@ -2784,11 +3261,12 @@ static int handle_verif_mode(void) return -EINVAL; } + create_stat_cgroup(); for (i = 0; i < env.filename_cnt; i++) { err = process_obj(env.filenames[i]); if (err) { fprintf(stderr, "Failed to process '%s': %d\n", env.filenames[i], err); - return err; + goto out; } } @@ -2796,7 +3274,9 @@ static int handle_verif_mode(void) output_prog_stats(); - return 0; +out: + destroy_stat_cgroup(); + return err; } static int handle_replay_mode(void) @@ -2826,7 +3306,7 @@ static int handle_replay_mode(void) int main(int argc, char **argv) { - int err = 0, i; + int err = 0, i, j; if (argp_parse(&argp, argc, argv, 0, NULL, NULL)) return 1; @@ -2885,9 +3365,19 @@ int main(int argc, char **argv) } free(env.deny_filters); for (i = 0; i < env.npresets; ++i) { - free(env.presets[i].name); - if (env.presets[i].type == ENUMERATOR) - free(env.presets[i].svalue); + free(env.presets[i].full_name); + for (j = 0; j < env.presets[i].atom_count; ++j) { + switch (env.presets[i].atoms[j].type) { + case FIELD_NAME: + free(env.presets[i].atoms[j].name); + break; + case ARRAY_INDEX: + if (env.presets[i].atoms[j].index.type == ENUMERATOR) + free(env.presets[i].atoms[j].index.svalue); + break; + } + } + free(env.presets[i].atoms); } free(env.presets); return -err; diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh index 79505d294c44..2f869daf8a06 100755 --- a/tools/testing/selftests/bpf/vmtest.sh +++ b/tools/testing/selftests/bpf/vmtest.sh @@ -43,6 +43,15 @@ riscv64) BZIMAGE="arch/riscv/boot/Image" ARCH="riscv" ;; +ppc64el) + QEMU_BINARY=qemu-system-ppc64 + QEMU_CONSOLE="hvc0" + # KVM could not be tested for powerpc, therefore not enabled for now. + HOST_FLAGS=(-machine pseries -cpu POWER9) + CROSS_FLAGS=(-machine pseries -cpu POWER9) + BZIMAGE="vmlinux" + ARCH="powerpc" + ;; *) echo "Unsupported architecture" exit 1 diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index 1503a1d2faa0..9ed8c796645d 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -155,7 +155,7 @@ int main(int argc, char **argv) } if (!server) { - /* Only supports IPv4; see hints initiailization above. */ + /* Only supports IPv4; see hints initialization above. */ if (getaddrinfo(argv[optind], NULL, &hints, &a) || !a) { fprintf(stderr, "Could not resolve %s\n", argv[optind]); return 1; diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h index 93c2cc413cfc..48729da142c2 100644 --- a/tools/testing/selftests/bpf/xsk.h +++ b/tools/testing/selftests/bpf/xsk.h @@ -93,8 +93,8 @@ static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb) /* Refresh the local tail pointer. * cached_cons is r->size bigger than the real consumer pointer so * that this addition can be avoided in the more frequently - * executed code that computs free_entries in the beginning of - * this function. Without this optimization it whould have been + * executed code that computes free_entries in the beginning of + * this function. Without this optimization it would have been * free_entries = r->cached_prod - r->cached_cons + r->size. */ r->cached_cons = __atomic_load_n(r->consumer, __ATOMIC_ACQUIRE); diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index 0ced4026ee44..352adc8df2d1 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -109,6 +109,8 @@ #include <network_helpers.h> +#define MAX_TX_BUDGET_DEFAULT 32 + static bool opt_verbose; static bool opt_print_tests; static enum test_mode opt_mode = TEST_MODE_ALL; @@ -1091,11 +1093,45 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) return true; } +static u32 load_value(u32 *counter) +{ + return __atomic_load_n(counter, __ATOMIC_ACQUIRE); +} + +static bool kick_tx_with_check(struct xsk_socket_info *xsk, int *ret) +{ + u32 max_budget = MAX_TX_BUDGET_DEFAULT; + u32 cons, ready_to_send; + int delta; + + cons = load_value(xsk->tx.consumer); + ready_to_send = load_value(xsk->tx.producer) - cons; + *ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + + delta = load_value(xsk->tx.consumer) - cons; + /* By default, xsk should consume exact @max_budget descs at one + * send in this case where hitting the max budget limit in while + * loop is triggered in __xsk_generic_xmit(). Please make sure that + * the number of descs to be sent is larger than @max_budget, or + * else the tx.consumer will be updated in xskq_cons_peek_desc() + * in time which hides the issue we try to verify. + */ + if (ready_to_send > max_budget && delta != max_budget) + return false; + + return true; +} + static int kick_tx(struct xsk_socket_info *xsk) { int ret; - ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + if (xsk->check_consumer) { + if (!kick_tx_with_check(xsk, &ret)) + return TEST_FAILURE; + } else { + ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + } if (ret >= 0) return TEST_PASS; if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) { @@ -2240,25 +2276,13 @@ static int testapp_xdp_metadata_copy(struct test_spec *test) { struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; - struct bpf_map *data_map; - int count = 0; - int key = 0; test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_populate_metadata, skel_tx->progs.xsk_xdp_populate_metadata, skel_rx->maps.xsk, skel_tx->maps.xsk); test->ifobj_rx->use_metadata = true; - data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss"); - if (!data_map || !bpf_map__is_internal(data_map)) { - ksft_print_msg("Error: could not find bss section of XDP program\n"); - return TEST_FAILURE; - } - - if (bpf_map_update_elem(bpf_map__fd(data_map), &key, &count, BPF_ANY)) { - ksft_print_msg("Error: could not update count element\n"); - return TEST_FAILURE; - } + skel_rx->bss->count = 0; return testapp_validate_traffic(test); } @@ -2613,6 +2637,23 @@ static int testapp_adjust_tail_grow_mb(struct test_spec *test) XSK_UMEM__LARGE_FRAME_SIZE * 2); } +static int testapp_tx_queue_consumer(struct test_spec *test) +{ + int nr_packets; + + if (test->mode == TEST_MODE_ZC) { + ksft_test_result_skip("Can not run TX_QUEUE_CONSUMER test for ZC mode\n"); + return TEST_SKIP; + } + + nr_packets = MAX_TX_BUDGET_DEFAULT + 1; + pkt_stream_replace(test, nr_packets, MIN_PKT_SIZE); + test->ifobj_tx->xsk->batch_size = nr_packets; + test->ifobj_tx->xsk->check_consumer = true; + + return testapp_validate_traffic(test); +} + static void run_pkt_test(struct test_spec *test) { int ret; @@ -2723,6 +2764,7 @@ static const struct test_spec tests[] = { {.name = "XDP_ADJUST_TAIL_SHRINK_MULTI_BUFF", .test_func = testapp_adjust_tail_shrink_mb}, {.name = "XDP_ADJUST_TAIL_GROW", .test_func = testapp_adjust_tail_grow}, {.name = "XDP_ADJUST_TAIL_GROW_MULTI_BUFF", .test_func = testapp_adjust_tail_grow_mb}, + {.name = "TX_QUEUE_CONSUMER", .test_func = testapp_tx_queue_consumer}, }; static void print_tests(void) diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index 67fc44b2813b..4df3a5d329ac 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -95,6 +95,7 @@ struct xsk_socket_info { u32 batch_size; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; + bool check_consumer; }; struct pkt { |