diff options
Diffstat (limited to 'tools/testing/selftests/bpf')
81 files changed, 5525 insertions, 686 deletions
diff --git a/tools/testing/selftests/bpf/DENYLIST b/tools/testing/selftests/bpf/DENYLIST index f748f2c33b22..1789a61d0a9b 100644 --- a/tools/testing/selftests/bpf/DENYLIST +++ b/tools/testing/selftests/bpf/DENYLIST @@ -1,5 +1,6 @@ # 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 index 6d8feda27ce9..12e99c0277a8 100644 --- a/tools/testing/selftests/bpf/DENYLIST.aarch64 +++ b/tools/testing/selftests/bpf/DENYLIST.aarch64 @@ -1,3 +1 @@ -fentry_test/fentry_many_args # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524 -fexit_test/fexit_many_args # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524 tracing_struct/struct_many_args # struct_many_args:FAIL:tracing_struct_many_args__attach unexpected error: -524 diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 66bb50356be0..cf5ed3bee573 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -34,6 +34,9 @@ OPT_FLAGS ?= $(if $(RELEASE),-O2,-O0) LIBELF_CFLAGS := $(shell $(PKG_CONFIG) libelf --cflags 2>/dev/null) LIBELF_LIBS := $(shell $(PKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) +SKIP_DOCS ?= +SKIP_LLVM ?= + ifeq ($(srctree),) srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) @@ -172,6 +175,7 @@ override OUTPUT := $(patsubst %/,%,$(OUTPUT)) endif endif +ifneq ($(SKIP_LLVM),1) ifeq ($(feature-llvm),1) LLVM_CFLAGS += -DHAVE_LLVM_SUPPORT LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets @@ -180,13 +184,14 @@ ifeq ($(feature-llvm),1) # Prefer linking statically if it's available, otherwise fallback to shared ifeq ($(shell $(LLVM_CONFIG) --link-static --libs >/dev/null 2>&1 && echo static),static) LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-static --libs $(LLVM_CONFIG_LIB_COMPONENTS)) - LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-static --system-libs $(LLVM_CONFIG_LIB_COMPONENTS)) + LLVM_LDLIBS += $(filter-out -lxml2,$(shell $(LLVM_CONFIG) --link-static --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))) LLVM_LDLIBS += -lstdc++ else LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-shared --libs $(LLVM_CONFIG_LIB_COMPONENTS)) endif LLVM_LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags) endif +endif SCRATCH_DIR := $(OUTPUT)/tools BUILD_DIR := $(SCRATCH_DIR)/build @@ -358,7 +363,9 @@ $(CROSS_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ prefix= DESTDIR=$(SCRATCH_DIR)/ install-bin endif +ifneq ($(SKIP_DOCS),1) all: docs +endif docs: $(Q)RST2MAN_OPTS="--exit-status=1" $(MAKE) $(submake_extras) \ @@ -673,9 +680,6 @@ ifneq ($2:$(OUTPUT),:$(shell pwd)) $(Q)rsync -aq $$^ $(TRUNNER_OUTPUT)/ endif -$(OUTPUT)/$(TRUNNER_BINARY): LDLIBS += $$(LLVM_LDLIBS) -$(OUTPUT)/$(TRUNNER_BINARY): LDFLAGS += $$(LLVM_LDFLAGS) - # some X.test.o files have runtime dependencies on Y.bpf.o files $(OUTPUT)/$(TRUNNER_BINARY): | $(TRUNNER_BPF_OBJS) @@ -686,7 +690,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $(OUTPUT)/veristat \ | $(TRUNNER_BINARY)-extras $$(call msg,BINARY,,$$@) - $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) $$(LDFLAGS) -o $$@ + $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) $$(LLVM_LDLIBS) $$(LDFLAGS) $$(LLVM_LDFLAGS) -o $$@ $(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.bpf.o $$@ $(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/$(USE_BOOTSTRAP)bpftool \ $(OUTPUT)/$(if $2,$2/)bpftool @@ -811,6 +815,7 @@ $(OUTPUT)/bench_local_storage_create.o: $(OUTPUT)/bench_local_storage_create.ske $(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.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o \ @@ -831,6 +836,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \ $(OUTPUT)/bench_local_storage_create.o \ $(OUTPUT)/bench_htab_mem.o \ $(OUTPUT)/bench_bpf_crypto.o \ + $(OUTPUT)/bench_sockmap.o \ # $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@ diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index 1bd403a5ef7b..ddd73d06a1eb 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -283,6 +283,7 @@ extern struct argp bench_local_storage_create_argp; 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; static const struct argp_child bench_parsers[] = { { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 }, @@ -297,6 +298,7 @@ static const struct argp_child bench_parsers[] = { { &bench_htab_mem_argp, 0, "hash map memory benchmark", 0 }, { &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 }, {}, }; @@ -526,6 +528,12 @@ extern const struct bench bench_trig_uprobe_multi_push; extern const struct bench bench_trig_uretprobe_multi_push; extern const struct bench bench_trig_uprobe_multi_ret; extern const struct bench bench_trig_uretprobe_multi_ret; +#ifdef __x86_64__ +extern const struct bench bench_trig_uprobe_nop5; +extern const struct bench bench_trig_uretprobe_nop5; +extern const struct bench bench_trig_uprobe_multi_nop5; +extern const struct bench bench_trig_uretprobe_multi_nop5; +#endif extern const struct bench bench_rb_libbpf; extern const struct bench bench_rb_custom; @@ -549,6 +557,7 @@ extern const struct bench bench_local_storage_create; 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; static const struct bench *benchs[] = { &bench_count_global, @@ -586,6 +595,12 @@ static const struct bench *benchs[] = { &bench_trig_uretprobe_multi_push, &bench_trig_uprobe_multi_ret, &bench_trig_uretprobe_multi_ret, +#ifdef __x86_64__ + &bench_trig_uprobe_nop5, + &bench_trig_uretprobe_nop5, + &bench_trig_uprobe_multi_nop5, + &bench_trig_uretprobe_multi_nop5, +#endif /* ringbuf/perfbuf benchmarks */ &bench_rb_libbpf, &bench_rb_custom, @@ -609,6 +624,7 @@ static const struct bench *benchs[] = { &bench_htab_mem, &bench_crypto_encrypt, &bench_crypto_decrypt, + &bench_sockmap, }; static void find_benchmark(void) diff --git a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c index 926ee822143e..297e32390cd1 100644 --- a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c +++ b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c @@ -279,6 +279,7 @@ static void htab_mem_read_mem_cgrp_file(const char *name, unsigned long *value) } got = read(fd, buf, sizeof(buf) - 1); + close(fd); if (got <= 0) { *value = 0; return; @@ -286,8 +287,6 @@ static void htab_mem_read_mem_cgrp_file(const char *name, unsigned long *value) buf[got] = 0; *value = strtoull(buf, NULL, 0); - - close(fd); } static void htab_mem_measure(struct bench_res *res) diff --git a/tools/testing/selftests/bpf/benchs/bench_sockmap.c b/tools/testing/selftests/bpf/benchs/bench_sockmap.c new file mode 100644 index 000000000000..8ebf563a67a2 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_sockmap.c @@ -0,0 +1,598 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <error.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <sys/sendfile.h> +#include <arpa/inet.h> +#include <fcntl.h> +#include <argp.h> +#include "bench.h" +#include "bench_sockmap_prog.skel.h" + +#define FILE_SIZE (128 * 1024) +#define DATA_REPEAT_SIZE 10 + +static const char snd_data[DATA_REPEAT_SIZE] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9}; + +/* c1 <-> [p1, p2] <-> c2 + * RX bench(BPF_SK_SKB_STREAM_VERDICT): + * ARG_FW_RX_PASS: + * send(p2) -> recv(c2) -> bpf skb passthrough -> recv(c2) + * ARG_FW_RX_VERDICT_EGRESS: + * send(c1) -> verdict skb to tx queuec of p2 -> recv(c2) + * ARG_FW_RX_VERDICT_INGRESS: + * send(c1) -> verdict skb to rx queuec of c2 -> recv(c2) + * + * TX bench(BPF_SK_MSG_VERDIC): + * ARG_FW_TX_PASS: + * send(p2) -> bpf msg passthrough -> send(p2) -> recv(c2) + * ARG_FW_TX_VERDICT_INGRESS: + * send(p2) -> verdict msg to rx queue of c2 -> recv(c2) + * ARG_FW_TX_VERDICT_EGRESS: + * send(p1) -> verdict msg to tx queue of p2 -> recv(c2) + */ +enum SOCKMAP_ARG_FLAG { + ARG_FW_RX_NORMAL = 11000, + ARG_FW_RX_PASS, + ARG_FW_RX_VERDICT_EGRESS, + ARG_FW_RX_VERDICT_INGRESS, + ARG_FW_TX_NORMAL, + ARG_FW_TX_PASS, + ARG_FW_TX_VERDICT_INGRESS, + ARG_FW_TX_VERDICT_EGRESS, + ARG_CTL_RX_STRP, + ARG_CONSUMER_DELAY_TIME, + ARG_PRODUCER_DURATION, +}; + +#define TXMODE_NORMAL() \ + ((ctx.mode) == ARG_FW_TX_NORMAL) + +#define TXMODE_BPF_INGRESS() \ + ((ctx.mode) == ARG_FW_TX_VERDICT_INGRESS) + +#define TXMODE_BPF_EGRESS() \ + ((ctx.mode) == ARG_FW_TX_VERDICT_EGRESS) + +#define TXMODE_BPF_PASS() \ + ((ctx.mode) == ARG_FW_TX_PASS) + +#define TXMODE_BPF() ( \ + TXMODE_BPF_PASS() || \ + TXMODE_BPF_INGRESS() || \ + TXMODE_BPF_EGRESS()) + +#define TXMODE() ( \ + TXMODE_NORMAL() || \ + TXMODE_BPF()) + +#define RXMODE_NORMAL() \ + ((ctx.mode) == ARG_FW_RX_NORMAL) + +#define RXMODE_BPF_PASS() \ + ((ctx.mode) == ARG_FW_RX_PASS) + +#define RXMODE_BPF_VERDICT_EGRESS() \ + ((ctx.mode) == ARG_FW_RX_VERDICT_EGRESS) + +#define RXMODE_BPF_VERDICT_INGRESS() \ + ((ctx.mode) == ARG_FW_RX_VERDICT_INGRESS) + +#define RXMODE_BPF_VERDICT() ( \ + RXMODE_BPF_VERDICT_INGRESS() || \ + RXMODE_BPF_VERDICT_EGRESS()) + +#define RXMODE_BPF() ( \ + RXMODE_BPF_PASS() || \ + RXMODE_BPF_VERDICT()) + +#define RXMODE() ( \ + RXMODE_NORMAL() || \ + RXMODE_BPF()) + +static struct socmap_ctx { + struct bench_sockmap_prog *skel; + enum SOCKMAP_ARG_FLAG mode; + #define c1 fds[0] + #define p1 fds[1] + #define c2 fds[2] + #define p2 fds[3] + #define sfd fds[4] + int fds[5]; + long send_calls; + long read_calls; + long prod_send; + long user_read; + int file_size; + int delay_consumer; + int prod_run_time; + int strp_size; +} ctx = { + .prod_send = 0, + .user_read = 0, + .file_size = FILE_SIZE, + .mode = ARG_FW_RX_VERDICT_EGRESS, + .fds = {0}, + .delay_consumer = 0, + .prod_run_time = 0, + .strp_size = 0, +}; + +static void bench_sockmap_prog_destroy(void) +{ + int i; + + for (i = 0; i < sizeof(ctx.fds); i++) { + if (ctx.fds[0] > 0) + close(ctx.fds[i]); + } + + bench_sockmap_prog__destroy(ctx.skel); +} + +static void init_addr(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static bool set_non_block(int fd, bool blocking) +{ + int flags = fcntl(fd, F_GETFL, 0); + + if (flags == -1) + return false; + flags = blocking ? (flags | O_NONBLOCK) : (flags & ~O_NONBLOCK); + return (fcntl(fd, F_SETFL, flags) == 0); +} + +static int create_pair(int *c, int *p, int type) +{ + struct sockaddr_storage addr; + int err, cfd, pfd; + socklen_t addr_len = sizeof(struct sockaddr_storage); + + err = getsockname(ctx.sfd, (struct sockaddr *)&addr, &addr_len); + if (err) { + fprintf(stderr, "getsockname error %d\n", errno); + return err; + } + cfd = socket(AF_INET, type, 0); + if (cfd < 0) { + fprintf(stderr, "socket error %d\n", errno); + return err; + } + + err = connect(cfd, (struct sockaddr *)&addr, addr_len); + if (err && errno != EINPROGRESS) { + fprintf(stderr, "connect error %d\n", errno); + return err; + } + + pfd = accept(ctx.sfd, NULL, NULL); + if (pfd < 0) { + fprintf(stderr, "accept error %d\n", errno); + return err; + } + *c = cfd; + *p = pfd; + return 0; +} + +static int create_sockets(void) +{ + struct sockaddr_storage addr; + int err, one = 1; + socklen_t addr_len; + + init_addr(&addr, &addr_len); + ctx.sfd = socket(AF_INET, SOCK_STREAM, 0); + if (ctx.sfd < 0) { + fprintf(stderr, "socket error:%d\n", errno); + return ctx.sfd; + } + err = setsockopt(ctx.sfd, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) { + fprintf(stderr, "setsockopt error:%d\n", errno); + return err; + } + + err = bind(ctx.sfd, (struct sockaddr *)&addr, addr_len); + if (err) { + fprintf(stderr, "bind error:%d\n", errno); + return err; + } + + err = listen(ctx.sfd, SOMAXCONN); + if (err) { + fprintf(stderr, "listen error:%d\n", errno); + return err; + } + + err = create_pair(&ctx.c1, &ctx.p1, SOCK_STREAM); + if (err) { + fprintf(stderr, "create_pair 1 error\n"); + return err; + } + + err = create_pair(&ctx.c2, &ctx.p2, SOCK_STREAM); + if (err) { + fprintf(stderr, "create_pair 2 error\n"); + return err; + } + printf("create socket fd c1:%d p1:%d c2:%d p2:%d\n", + ctx.c1, ctx.p1, ctx.c2, ctx.p2); + return 0; +} + +static void validate(void) +{ + if (env.consumer_cnt != 2 || env.producer_cnt != 1 || + !env.affinity) + goto err; + return; +err: + fprintf(stderr, "argument '-c 2 -p 1 -a' is necessary"); + exit(1); +} + +static int setup_rx_sockmap(void) +{ + int verdict, pass, parser, map; + int zero = 0, one = 1; + int err; + + parser = bpf_program__fd(ctx.skel->progs.prog_skb_parser); + verdict = bpf_program__fd(ctx.skel->progs.prog_skb_verdict); + pass = bpf_program__fd(ctx.skel->progs.prog_skb_pass); + map = bpf_map__fd(ctx.skel->maps.sock_map_rx); + + if (ctx.strp_size != 0) { + ctx.skel->bss->pkt_size = ctx.strp_size; + err = bpf_prog_attach(parser, map, BPF_SK_SKB_STREAM_PARSER, 0); + if (err) + return err; + } + + if (RXMODE_BPF_VERDICT()) + err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); + else if (RXMODE_BPF_PASS()) + err = bpf_prog_attach(pass, map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) + return err; + + if (RXMODE_BPF_PASS()) + return bpf_map_update_elem(map, &zero, &ctx.c2, BPF_NOEXIST); + + err = bpf_map_update_elem(map, &zero, &ctx.p1, BPF_NOEXIST); + if (err < 0) + return err; + + if (RXMODE_BPF_VERDICT_INGRESS()) { + ctx.skel->bss->verdict_dir = BPF_F_INGRESS; + err = bpf_map_update_elem(map, &one, &ctx.c2, BPF_NOEXIST); + } else { + err = bpf_map_update_elem(map, &one, &ctx.p2, BPF_NOEXIST); + } + if (err < 0) + return err; + + return 0; +} + +static int setup_tx_sockmap(void) +{ + int zero = 0, one = 1; + int prog, map; + int err; + + map = bpf_map__fd(ctx.skel->maps.sock_map_tx); + prog = TXMODE_BPF_PASS() ? + bpf_program__fd(ctx.skel->progs.prog_skmsg_pass) : + bpf_program__fd(ctx.skel->progs.prog_skmsg_verdict); + + err = bpf_prog_attach(prog, map, BPF_SK_MSG_VERDICT, 0); + if (err) + return err; + + if (TXMODE_BPF_EGRESS()) { + err = bpf_map_update_elem(map, &zero, &ctx.p1, BPF_NOEXIST); + err |= bpf_map_update_elem(map, &one, &ctx.p2, BPF_NOEXIST); + } else { + ctx.skel->bss->verdict_dir = BPF_F_INGRESS; + err = bpf_map_update_elem(map, &zero, &ctx.p2, BPF_NOEXIST); + err |= bpf_map_update_elem(map, &one, &ctx.c2, BPF_NOEXIST); + } + + if (err < 0) + return err; + + return 0; +} + +static void setup(void) +{ + int err; + + ctx.skel = bench_sockmap_prog__open_and_load(); + if (!ctx.skel) { + fprintf(stderr, "error loading skel\n"); + exit(1); + } + + if (create_sockets()) { + fprintf(stderr, "create_net_mode error\n"); + goto err; + } + + if (RXMODE_BPF()) { + err = setup_rx_sockmap(); + if (err) { + fprintf(stderr, "setup_rx_sockmap error:%d\n", err); + goto err; + } + } else if (TXMODE_BPF()) { + err = setup_tx_sockmap(); + if (err) { + fprintf(stderr, "setup_tx_sockmap error:%d\n", err); + goto err; + } + } else { + fprintf(stderr, "unknown sockmap bench mode: %d\n", ctx.mode); + goto err; + } + + return; + +err: + bench_sockmap_prog_destroy(); + exit(1); +} + +static void measure(struct bench_res *res) +{ + res->drops = atomic_swap(&ctx.prod_send, 0); + res->hits = atomic_swap(&ctx.skel->bss->process_byte, 0); + res->false_hits = atomic_swap(&ctx.user_read, 0); + res->important_hits = atomic_swap(&ctx.send_calls, 0); + res->important_hits |= atomic_swap(&ctx.read_calls, 0) << 32; +} + +static void verify_data(int *check_pos, char *buf, int rcv) +{ + for (int i = 0 ; i < rcv; i++) { + if (buf[i] != snd_data[(*check_pos) % DATA_REPEAT_SIZE]) { + fprintf(stderr, "verify data fail"); + exit(1); + } + (*check_pos)++; + if (*check_pos >= FILE_SIZE) + *check_pos = 0; + } +} + +static void *consumer(void *input) +{ + int rcv, sent; + int check_pos = 0; + int tid = (long)input; + int recv_buf_size = FILE_SIZE; + char *buf = malloc(recv_buf_size); + int delay_read = ctx.delay_consumer; + + if (!buf) { + fprintf(stderr, "fail to init read buffer"); + return NULL; + } + + while (true) { + if (tid == 1) { + /* consumer 1 is unused for tx test and stream verdict test */ + if (RXMODE_BPF() || TXMODE()) + return NULL; + /* it's only for RX_NORMAL which service as reserve-proxy mode */ + rcv = read(ctx.p1, buf, recv_buf_size); + if (rcv < 0) { + fprintf(stderr, "fail to read p1"); + return NULL; + } + + sent = send(ctx.p2, buf, recv_buf_size, 0); + if (sent < 0) { + fprintf(stderr, "fail to send p2"); + return NULL; + } + } else { + if (delay_read != 0) { + if (delay_read < 0) + return NULL; + sleep(delay_read); + delay_read = 0; + } + /* read real endpoint by consumer 0 */ + atomic_inc(&ctx.read_calls); + rcv = read(ctx.c2, buf, recv_buf_size); + if (rcv < 0 && errno != EAGAIN) { + fprintf(stderr, "%s fail to read c2 %d\n", __func__, errno); + return NULL; + } + verify_data(&check_pos, buf, rcv); + atomic_add(&ctx.user_read, rcv); + } + } + + return NULL; +} + +static void *producer(void *input) +{ + int off = 0, fp, need_sent, sent; + int file_size = ctx.file_size; + struct timespec ts1, ts2; + int target; + FILE *file; + + file = tmpfile(); + if (!file) { + fprintf(stderr, "create file for sendfile"); + return NULL; + } + + /* we need simple verify */ + for (int i = 0; i < file_size; i++) { + if (fwrite(&snd_data[off], sizeof(char), 1, file) != 1) { + fprintf(stderr, "init tmpfile error"); + return NULL; + } + if (++off >= sizeof(snd_data)) + off = 0; + } + fflush(file); + fseek(file, 0, SEEK_SET); + + fp = fileno(file); + need_sent = file_size; + clock_gettime(CLOCK_MONOTONIC, &ts1); + + if (RXMODE_BPF_VERDICT()) + target = ctx.c1; + else if (TXMODE_BPF_EGRESS()) + target = ctx.p1; + else + target = ctx.p2; + set_non_block(target, true); + while (true) { + if (ctx.prod_run_time) { + clock_gettime(CLOCK_MONOTONIC, &ts2); + if (ts2.tv_sec - ts1.tv_sec > ctx.prod_run_time) + return NULL; + } + + errno = 0; + atomic_inc(&ctx.send_calls); + sent = sendfile(target, fp, NULL, need_sent); + if (sent < 0) { + if (errno != EAGAIN && errno != ENOMEM && errno != ENOBUFS) { + fprintf(stderr, "sendfile return %d, errorno %d:%s\n", + sent, errno, strerror(errno)); + return NULL; + } + continue; + } else if (sent < need_sent) { + need_sent -= sent; + atomic_add(&ctx.prod_send, sent); + continue; + } + atomic_add(&ctx.prod_send, need_sent); + need_sent = file_size; + lseek(fp, 0, SEEK_SET); + } + + return NULL; +} + +static void report_progress(int iter, struct bench_res *res, long delta_ns) +{ + double speed_mbs, prod_mbs, bpf_mbs, send_hz, read_hz; + + prod_mbs = res->drops / 1000000.0 / (delta_ns / 1000000000.0); + speed_mbs = res->false_hits / 1000000.0 / (delta_ns / 1000000000.0); + bpf_mbs = res->hits / 1000000.0 / (delta_ns / 1000000000.0); + send_hz = (res->important_hits & 0xFFFFFFFF) / (delta_ns / 1000000000.0); + read_hz = (res->important_hits >> 32) / (delta_ns / 1000000000.0); + + printf("Iter %3d (%7.3lfus): ", + iter, (delta_ns - 1000000000) / 1000.0); + printf("Send Speed %8.3lf MB/s (%8.3lf calls/s), BPF Speed %8.3lf MB/s, " + "Rcv Speed %8.3lf MB/s (%8.3lf calls/s)\n", + prod_mbs, send_hz, bpf_mbs, speed_mbs, read_hz); +} + +static void report_final(struct bench_res res[], int res_cnt) +{ + double verdict_mbs_mean = 0.0; + long verdict_total = 0; + int i; + + for (i = 0; i < res_cnt; i++) { + verdict_mbs_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt); + verdict_total += res[i].hits / 1000000.0; + } + + printf("Summary: total trans %8.3lu MB \u00B1 %5.3lf MB/s\n", + verdict_total, verdict_mbs_mean); +} + +static const struct argp_option opts[] = { + { "rx-normal", ARG_FW_RX_NORMAL, NULL, 0, + "simple reserve-proxy mode, no bfp enabled"}, + { "rx-pass", ARG_FW_RX_PASS, NULL, 0, + "run bpf prog but no redir applied"}, + { "rx-strp", ARG_CTL_RX_STRP, "Byte", 0, + "enable strparser and set the encapsulation size"}, + { "rx-verdict-egress", ARG_FW_RX_VERDICT_EGRESS, NULL, 0, + "forward data with bpf(stream verdict)"}, + { "rx-verdict-ingress", ARG_FW_RX_VERDICT_INGRESS, NULL, 0, + "forward data with bpf(stream verdict)"}, + { "tx-normal", ARG_FW_TX_NORMAL, NULL, 0, + "simple c-s mode, no bfp enabled"}, + { "tx-pass", ARG_FW_TX_PASS, NULL, 0, + "run bpf prog but no redir applied"}, + { "tx-verdict-ingress", ARG_FW_TX_VERDICT_INGRESS, NULL, 0, + "forward msg to ingress queue of another socket"}, + { "tx-verdict-egress", ARG_FW_TX_VERDICT_EGRESS, NULL, 0, + "forward msg to egress queue of another socket"}, + { "delay-consumer", ARG_CONSUMER_DELAY_TIME, "SEC", 0, + "delay consumer start"}, + { "producer-duration", ARG_PRODUCER_DURATION, "SEC", 0, + "producer duration"}, + {}, +}; + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + switch (key) { + case ARG_FW_RX_NORMAL...ARG_FW_TX_VERDICT_EGRESS: + ctx.mode = key; + break; + case ARG_CONSUMER_DELAY_TIME: + ctx.delay_consumer = strtol(arg, NULL, 10); + break; + case ARG_PRODUCER_DURATION: + ctx.prod_run_time = strtol(arg, NULL, 10); + break; + case ARG_CTL_RX_STRP: + ctx.strp_size = strtol(arg, NULL, 10); + break; + default: + return ARGP_ERR_UNKNOWN; + } + + return 0; +} + +/* exported into benchmark runner */ +const struct argp bench_sockmap_argp = { + .options = opts, + .parser = parse_arg, +}; + +/* Benchmark performance of creating bpf local storage */ +const struct bench bench_sockmap = { + .name = "sockmap", + .argp = &bench_sockmap_argp, + .validate = validate, + .setup = setup, + .producer_thread = producer, + .consumer_thread = consumer, + .measure = measure, + .report_progress = report_progress, + .report_final = report_final, +}; diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 32e9f194d449..82327657846e 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -333,6 +333,20 @@ static void *uprobe_producer_ret(void *input) return NULL; } +#ifdef __x86_64__ +__nocf_check __weak void uprobe_target_nop5(void) +{ + asm volatile (".byte 0x0f, 0x1f, 0x44, 0x00, 0x00"); +} + +static void *uprobe_producer_nop5(void *input) +{ + while (true) + uprobe_target_nop5(); + return NULL; +} +#endif + static void usetup(bool use_retprobe, bool use_multi, void *target_addr) { size_t uprobe_offset; @@ -448,6 +462,28 @@ static void uretprobe_multi_ret_setup(void) usetup(true, true /* use_multi */, &uprobe_target_ret); } +#ifdef __x86_64__ +static void uprobe_nop5_setup(void) +{ + usetup(false, false /* !use_multi */, &uprobe_target_nop5); +} + +static void uretprobe_nop5_setup(void) +{ + usetup(true, false /* !use_multi */, &uprobe_target_nop5); +} + +static void uprobe_multi_nop5_setup(void) +{ + usetup(false, true /* use_multi */, &uprobe_target_nop5); +} + +static void uretprobe_multi_nop5_setup(void) +{ + usetup(true, true /* use_multi */, &uprobe_target_nop5); +} +#endif + const struct bench bench_trig_syscall_count = { .name = "trig-syscall-count", .validate = trigger_validate, @@ -506,3 +542,9 @@ BENCH_TRIG_USERMODE(uprobe_multi_ret, ret, "uprobe-multi-ret"); BENCH_TRIG_USERMODE(uretprobe_multi_nop, nop, "uretprobe-multi-nop"); BENCH_TRIG_USERMODE(uretprobe_multi_push, push, "uretprobe-multi-push"); BENCH_TRIG_USERMODE(uretprobe_multi_ret, ret, "uretprobe-multi-ret"); +#ifdef __x86_64__ +BENCH_TRIG_USERMODE(uprobe_nop5, nop5, "uprobe-nop5"); +BENCH_TRIG_USERMODE(uretprobe_nop5, nop5, "uretprobe-nop5"); +BENCH_TRIG_USERMODE(uprobe_multi_nop5, nop5, "uprobe-multi-nop5"); +BENCH_TRIG_USERMODE(uretprobe_multi_nop5, nop5, "uretprobe-multi-nop5"); +#endif diff --git a/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh index af169f831f2f..03f55405484b 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh @@ -2,7 +2,7 @@ set -eufo pipefail -for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret} +for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop5} do summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-) printf "%-15s: %s\n" $i "$summary" diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 6535c8ae3c46..5e512a1d09d1 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -591,4 +591,9 @@ extern int bpf_iter_kmem_cache_new(struct bpf_iter_kmem_cache *it) __weak __ksym extern struct kmem_cache *bpf_iter_kmem_cache_next(struct bpf_iter_kmem_cache *it) __weak __ksym; extern void bpf_iter_kmem_cache_destroy(struct bpf_iter_kmem_cache *it) __weak __ksym; +struct bpf_iter_dmabuf; +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; + #endif diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index c378d5d07e02..f74e1ea0ad3b 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -22,6 +22,8 @@ CONFIG_CRYPTO_AES=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_DMABUF_HEAPS=y +CONFIG_DMABUF_HEAPS_SYSTEM=y CONFIG_DUMMY=y CONFIG_DYNAMIC_FTRACE=y CONFIG_FPROBE=y @@ -71,8 +73,10 @@ CONFIG_NET_IPGRE=y CONFIG_NET_IPGRE_DEMUX=y CONFIG_NET_IPIP=y CONFIG_NET_MPLS_GSO=y +CONFIG_NET_SCH_BPF=y CONFIG_NET_SCH_FQ=y CONFIG_NET_SCH_INGRESS=y +CONFIG_NET_SCH_HTB=y CONFIG_NET_SCHED=y CONFIG_NETDEVSIM=y CONFIG_NETFILTER=y @@ -106,6 +110,7 @@ CONFIG_SECURITY=y CONFIG_SECURITYFS=y CONFIG_SYN_COOKIES=y CONFIG_TEST_BPF=m +CONFIG_UDMABUF=y CONFIG_USERFAULTFD=y CONFIG_VSOCKETS=y CONFIG_VXLAN=y diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64 index 3720b7611523..e1495a4bbc99 100644 --- a/tools/testing/selftests/bpf/config.aarch64 +++ b/tools/testing/selftests/bpf/config.aarch64 @@ -158,7 +158,6 @@ CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_TUN=y CONFIG_UNIX=y CONFIG_UPROBES=y -CONFIG_USELIB=y CONFIG_USER_NS=y CONFIG_VETH=y CONFIG_VLAN_8021Q=y diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x index 706931a8c2c6..26c3bc2ce11d 100644 --- a/tools/testing/selftests/bpf/config.s390x +++ b/tools/testing/selftests/bpf/config.s390x @@ -128,7 +128,6 @@ CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_TUN=y CONFIG_UNIX=y CONFIG_UPROBES=y -CONFIG_USELIB=y CONFIG_USER_NS=y CONFIG_VETH=y CONFIG_VLAN_8021Q=y 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 7565fc7690c2..0223fce4db2b 100644 --- a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c @@ -51,9 +51,11 @@ static void test_arena_spin_lock_size(int size) struct arena_spin_lock *skel; pthread_t thread_id[16]; int prog_fd, i, err; + int nthreads; void *ret; - if (get_nprocs() < 2) { + nthreads = MIN(get_nprocs(), ARRAY_SIZE(thread_id)); + if (nthreads < 2) { test__skip(); return; } @@ -66,25 +68,25 @@ static void test_arena_spin_lock_size(int size) goto end; } skel->bss->cs_count = size; - skel->bss->limit = repeat * 16; + skel->bss->limit = repeat * nthreads; - ASSERT_OK(pthread_barrier_init(&barrier, NULL, 16), "barrier init"); + ASSERT_OK(pthread_barrier_init(&barrier, NULL, nthreads), "barrier init"); prog_fd = bpf_program__fd(skel->progs.prog); - for (i = 0; i < 16; i++) { + for (i = 0; i < nthreads; i++) { err = pthread_create(&thread_id[i], NULL, &spin_lock_thread, &prog_fd); if (!ASSERT_OK(err, "pthread_create")) goto end_barrier; } - for (i = 0; i < 16; i++) { + for (i = 0; i < nthreads; i++) { if (!ASSERT_OK(pthread_join(thread_id[i], &ret), "pthread_join")) goto end_barrier; if (!ASSERT_EQ(ret, &prog_fd, "ret == prog_fd")) goto end_barrier; } - ASSERT_EQ(skel->bss->counter, repeat * 16, "check counter value"); + ASSERT_EQ(skel->bss->counter, repeat * nthreads, "check counter value"); end_barrier: pthread_barrier_destroy(&barrier); diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index 329c7862b52d..cabc51c2ca6b 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -122,6 +122,85 @@ cleanup: test_attach_probe_manual__destroy(skel); } +/* attach uprobe/uretprobe long event name testings */ +static void test_attach_uprobe_long_event_name(void) +{ + DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts); + struct bpf_link *uprobe_link, *uretprobe_link; + struct test_attach_probe_manual *skel; + ssize_t uprobe_offset; + char path[PATH_MAX] = {0}; + + skel = test_attach_probe_manual__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_kprobe_manual_open_and_load")) + return; + + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) + goto cleanup; + + if (!ASSERT_GT(readlink("/proc/self/exe", path, PATH_MAX - 1), 0, "readlink")) + goto cleanup; + + /* manual-attach uprobe/uretprobe */ + uprobe_opts.attach_mode = PROBE_ATTACH_MODE_LEGACY; + uprobe_opts.ref_ctr_offset = 0; + uprobe_opts.retprobe = false; + uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe, + 0 /* self pid */, + path, + uprobe_offset, + &uprobe_opts); + if (!ASSERT_OK_PTR(uprobe_link, "attach_uprobe_long_event_name")) + goto cleanup; + skel->links.handle_uprobe = uprobe_link; + + uprobe_opts.retprobe = true; + uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe, + -1 /* any pid */, + path, + uprobe_offset, &uprobe_opts); + if (!ASSERT_OK_PTR(uretprobe_link, "attach_uretprobe_long_event_name")) + goto cleanup; + skel->links.handle_uretprobe = uretprobe_link; + +cleanup: + test_attach_probe_manual__destroy(skel); +} + +/* attach kprobe/kretprobe long event name testings */ +static void test_attach_kprobe_long_event_name(void) +{ + DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, kprobe_opts); + struct bpf_link *kprobe_link, *kretprobe_link; + struct test_attach_probe_manual *skel; + + skel = test_attach_probe_manual__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_kprobe_manual_open_and_load")) + return; + + /* manual-attach kprobe/kretprobe */ + kprobe_opts.attach_mode = PROBE_ATTACH_MODE_LEGACY; + kprobe_opts.retprobe = false; + kprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kprobe, + "bpf_testmod_looooooooooooooooooooooooooooooong_name", + &kprobe_opts); + if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe_long_event_name")) + goto cleanup; + skel->links.handle_kprobe = kprobe_link; + + kprobe_opts.retprobe = true; + kretprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kretprobe, + "bpf_testmod_looooooooooooooooooooooooooooooong_name", + &kprobe_opts); + if (!ASSERT_OK_PTR(kretprobe_link, "attach_kretprobe_long_event_name")) + goto cleanup; + skel->links.handle_kretprobe = kretprobe_link; + +cleanup: + test_attach_probe_manual__destroy(skel); +} + static void test_attach_probe_auto(struct test_attach_probe *skel) { struct bpf_link *uprobe_err_link; @@ -323,6 +402,11 @@ void test_attach_probe(void) if (test__start_subtest("uprobe-ref_ctr")) test_uprobe_ref_ctr(skel); + if (test__start_subtest("uprobe-long_name")) + test_attach_uprobe_long_event_name(); + if (test__start_subtest("kprobe-long_name")) + test_attach_kprobe_long_event_name(); + cleanup: test_attach_probe__destroy(skel); ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_cleanup"); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c index dbd13f8e42a7..dd6512fa652b 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -63,6 +63,12 @@ static void test_bpf_nf_ct(int mode) .repeat = 1, ); + if (SYS_NOFAIL("iptables-legacy --version")) { + fprintf(stdout, "Missing required iptables-legacy tool\n"); + test__skip(); + return; + } + skel = test_bpf_nf__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_bpf_nf__open_and_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c new file mode 100644 index 000000000000..730357cd0c9a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/pkt_sched.h> +#include <linux/rtnetlink.h> +#include <test_progs.h> + +#include "network_helpers.h" +#include "bpf_qdisc_fifo.skel.h" +#include "bpf_qdisc_fq.skel.h" +#include "bpf_qdisc_fail__incompl_ops.skel.h" + +#define LO_IFINDEX 1 + +static const unsigned int total_bytes = 10 * 1024 * 1024; + +static void do_test(char *qdisc) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX, + .attach_point = BPF_TC_QDISC, + .parent = TC_H_ROOT, + .handle = 0x8000000, + .qdisc = qdisc); + int srv_fd = -1, cli_fd = -1; + int err; + + err = bpf_tc_hook_create(&hook); + if (!ASSERT_OK(err, "attach qdisc")) + return; + + srv_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0); + if (!ASSERT_OK_FD(srv_fd, "start server")) + goto done; + + cli_fd = connect_to_fd(srv_fd, 0); + if (!ASSERT_OK_FD(cli_fd, "connect to client")) + goto done; + + err = send_recv_data(srv_fd, cli_fd, total_bytes); + ASSERT_OK(err, "send_recv_data"); + +done: + if (srv_fd != -1) + close(srv_fd); + if (cli_fd != -1) + close(cli_fd); + + bpf_tc_hook_destroy(&hook); +} + +static void test_fifo(void) +{ + struct bpf_qdisc_fifo *fifo_skel; + + fifo_skel = bpf_qdisc_fifo__open_and_load(); + if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load")) + return; + + if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach")) + goto out; + + do_test("bpf_fifo"); +out: + bpf_qdisc_fifo__destroy(fifo_skel); +} + +static void test_fq(void) +{ + struct bpf_qdisc_fq *fq_skel; + + fq_skel = bpf_qdisc_fq__open_and_load(); + if (!ASSERT_OK_PTR(fq_skel, "bpf_qdisc_fq__open_and_load")) + return; + + if (!ASSERT_OK(bpf_qdisc_fq__attach(fq_skel), "bpf_qdisc_fq__attach")) + goto out; + + do_test("bpf_fq"); +out: + bpf_qdisc_fq__destroy(fq_skel); +} + +static void test_qdisc_attach_to_mq(void) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, + .attach_point = BPF_TC_QDISC, + .parent = TC_H_MAKE(1 << 16, 1), + .handle = 0x11 << 16, + .qdisc = "bpf_fifo"); + struct bpf_qdisc_fifo *fifo_skel; + int err; + + fifo_skel = bpf_qdisc_fifo__open_and_load(); + if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load")) + return; + + if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach")) + goto out; + + SYS(out, "ip link add veth0 type veth peer veth1"); + hook.ifindex = if_nametoindex("veth0"); + SYS(out, "tc qdisc add dev veth0 root handle 1: mq"); + + err = bpf_tc_hook_create(&hook); + ASSERT_OK(err, "attach qdisc"); + + bpf_tc_hook_destroy(&hook); + + SYS(out, "tc qdisc delete dev veth0 root mq"); +out: + bpf_qdisc_fifo__destroy(fifo_skel); +} + +static void test_qdisc_attach_to_non_root(void) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX, + .attach_point = BPF_TC_QDISC, + .parent = TC_H_MAKE(1 << 16, 1), + .handle = 0x11 << 16, + .qdisc = "bpf_fifo"); + struct bpf_qdisc_fifo *fifo_skel; + int err; + + fifo_skel = bpf_qdisc_fifo__open_and_load(); + if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load")) + return; + + if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach")) + goto out; + + SYS(out, "tc qdisc add dev lo root handle 1: htb"); + SYS(out_del_htb, "tc class add dev lo parent 1: classid 1:1 htb rate 75Kbit"); + + err = bpf_tc_hook_create(&hook); + if (!ASSERT_ERR(err, "attach qdisc")) + bpf_tc_hook_destroy(&hook); + +out_del_htb: + SYS(out, "tc qdisc delete dev lo root htb"); +out: + bpf_qdisc_fifo__destroy(fifo_skel); +} + +static void test_incompl_ops(void) +{ + struct bpf_qdisc_fail__incompl_ops *skel; + struct bpf_link *link; + + skel = bpf_qdisc_fail__incompl_ops__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_qdisc_fifo__open_and_load")) + return; + + link = bpf_map__attach_struct_ops(skel->maps.test); + if (!ASSERT_ERR_PTR(link, "bpf_map__attach_struct_ops")) + bpf_link__destroy(link); + + bpf_qdisc_fail__incompl_ops__destroy(skel); +} + +static int get_default_qdisc(char *qdisc_name) +{ + FILE *f; + int num; + + f = fopen("/proc/sys/net/core/default_qdisc", "r"); + if (!f) + return -errno; + + num = fscanf(f, "%s", qdisc_name); + fclose(f); + + return num == 1 ? 0 : -EFAULT; +} + +static void test_default_qdisc_attach_to_mq(void) +{ + char default_qdisc[IFNAMSIZ] = {}; + struct bpf_qdisc_fifo *fifo_skel; + struct netns_obj *netns = NULL; + int err; + + fifo_skel = bpf_qdisc_fifo__open_and_load(); + if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load")) + return; + + if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach")) + goto out; + + err = get_default_qdisc(default_qdisc); + if (!ASSERT_OK(err, "read sysctl net.core.default_qdisc")) + goto out; + + err = write_sysctl("/proc/sys/net/core/default_qdisc", "bpf_fifo"); + if (!ASSERT_OK(err, "write sysctl net.core.default_qdisc")) + goto out; + + netns = netns_new("bpf_qdisc_ns", true); + if (!ASSERT_OK_PTR(netns, "netns_new")) + goto out; + + SYS(out, "ip link add veth0 type veth peer veth1"); + SYS(out, "tc qdisc add dev veth0 root handle 1: mq"); + + ASSERT_EQ(fifo_skel->bss->init_called, true, "init_called"); + + SYS(out, "tc qdisc delete dev veth0 root mq"); +out: + netns_free(netns); + if (default_qdisc[0]) + write_sysctl("/proc/sys/net/core/default_qdisc", default_qdisc); + + bpf_qdisc_fifo__destroy(fifo_skel); +} + +void test_ns_bpf_qdisc(void) +{ + if (test__start_subtest("fifo")) + test_fifo(); + if (test__start_subtest("fq")) + test_fq(); + if (test__start_subtest("attach to mq")) + test_qdisc_attach_to_mq(); + if (test__start_subtest("attach to non root")) + test_qdisc_attach_to_non_root(); + if (test__start_subtest("incompl_ops")) + test_incompl_ops(); +} + +void serial_test_bpf_qdisc_default(void) +{ + test_default_qdisc_attach_to_mq(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c index d9024c7a892a..5bc15bb6b7ce 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c @@ -440,6 +440,105 @@ cleanup: btf__free(btf1); } +/* Ensure module split BTF dedup worked correctly; when dedup fails badly + * core kernel types are in split BTF also, so ensure that references to + * such types point at base - not split - BTF. + * + * bpf_testmod_test_write() has multiple core kernel type parameters; + * + * ssize_t + * bpf_testmod_test_write(struct file *file, struct kobject *kobj, + * struct bin_attribute *bin_attr, + * char *buf, loff_t off, size_t len); + * + * Ensure each of the FUNC_PROTO params is a core kernel type. + * + * Do the same for + * + * __bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk); + * + * ...and + * + * __bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb); + * + */ +const char *mod_funcs[] = { + "bpf_testmod_test_write", + "bpf_kfunc_call_test3", + "bpf_kfunc_call_test_pass_ctx" +}; + +static void test_split_module(void) +{ + struct btf *vmlinux_btf, *btf1 = NULL; + int i, nr_base_types; + + vmlinux_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(vmlinux_btf, "vmlinux_btf")) + return; + nr_base_types = btf__type_cnt(vmlinux_btf); + if (!ASSERT_GT(nr_base_types, 0, "nr_base_types")) + goto cleanup; + + btf1 = btf__parse_split("/sys/kernel/btf/bpf_testmod", vmlinux_btf); + if (!ASSERT_OK_PTR(btf1, "split_btf")) + return; + + for (i = 0; i < ARRAY_SIZE(mod_funcs); i++) { + const struct btf_param *p; + const struct btf_type *t; + __u16 vlen; + __u32 id; + int j; + + id = btf__find_by_name_kind(btf1, mod_funcs[i], BTF_KIND_FUNC); + if (!ASSERT_GE(id, nr_base_types, "func_id")) + goto cleanup; + t = btf__type_by_id(btf1, id); + if (!ASSERT_OK_PTR(t, "func_id_type")) + goto cleanup; + t = btf__type_by_id(btf1, t->type); + if (!ASSERT_OK_PTR(t, "func_proto_id_type")) + goto cleanup; + if (!ASSERT_EQ(btf_is_func_proto(t), true, "is_func_proto")) + goto cleanup; + vlen = btf_vlen(t); + + for (j = 0, p = btf_params(t); j < vlen; j++, p++) { + /* bpf_testmod uses resilient split BTF, so any + * reference types will be added to split BTF and their + * associated targets will be base BTF types; for example + * for a "struct sock *" the PTR will be in split BTF + * while the "struct sock" will be in base. + * + * In some cases like loff_t we have to resolve + * multiple typedefs hence the while() loop below. + * + * Note that resilient split BTF generation depends + * on pahole version, so we do not assert that + * reference types are in split BTF, as if pahole + * does not support resilient split BTF they will + * also be base BTF types. + */ + id = p->type; + do { + t = btf__type_by_id(btf1, id); + if (!ASSERT_OK_PTR(t, "param_ref_type")) + goto cleanup; + if (!btf_is_mod(t) && !btf_is_ptr(t) && !btf_is_typedef(t)) + break; + id = t->type; + } while (true); + + if (!ASSERT_LT(id, nr_base_types, "verify_base_type")) + goto cleanup; + } + } +cleanup: + btf__free(btf1); + btf__free(vmlinux_btf); +} + void test_btf_dedup_split() { if (test__start_subtest("split_simple")) @@ -450,4 +549,6 @@ void test_btf_dedup_split() test_split_fwd_resolve(); if (test__start_subtest("split_dup_struct_in_cu")) test_split_dup_struct_in_cu(); + if (test__start_subtest("split_module")) + test_split_module(); } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_split.c b/tools/testing/selftests/bpf/prog_tests/btf_split.c index eef1158676ed..3696fb9a05ed 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_split.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_split.c @@ -12,10 +12,11 @@ static void btf_dump_printf(void *ctx, const char *fmt, va_list args) vfprintf(ctx, fmt, args); } -void test_btf_split() { +static void __test_btf_split(bool multi) +{ struct btf_dump *d = NULL; const struct btf_type *t; - struct btf *btf1, *btf2; + struct btf *btf1, *btf2, *btf3 = NULL; int str_off, i, err; btf1 = btf__new_empty(); @@ -63,14 +64,46 @@ void test_btf_split() { ASSERT_EQ(btf_vlen(t), 3, "split_struct_vlen"); ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "s2", "split_struct_name"); + if (multi) { + btf3 = btf__new_empty_split(btf2); + if (!ASSERT_OK_PTR(btf3, "multi_split_btf")) + goto cleanup; + } else { + btf3 = btf2; + } + + btf__add_union(btf3, "u1", 16); /* [5] union u1 { */ + btf__add_field(btf3, "f1", 4, 0, 0); /* struct s2 f1; */ + btf__add_field(btf3, "uf2", 1, 0, 0); /* int f2; */ + /* } */ + + if (multi) { + t = btf__type_by_id(btf2, 5); + ASSERT_NULL(t, "multisplit_type_in_first_split"); + } + + t = btf__type_by_id(btf3, 5); + if (!ASSERT_OK_PTR(t, "split_union_type")) + goto cleanup; + ASSERT_EQ(btf_is_union(t), true, "split_union_kind"); + ASSERT_EQ(btf_vlen(t), 2, "split_union_vlen"); + ASSERT_STREQ(btf__str_by_offset(btf3, t->name_off), "u1", "split_union_name"); + ASSERT_EQ(btf__type_cnt(btf3), 6, "split_type_cnt"); + + t = btf__type_by_id(btf3, 1); + if (!ASSERT_OK_PTR(t, "split_base_type")) + goto cleanup; + ASSERT_EQ(btf_is_int(t), true, "split_base_int"); + ASSERT_STREQ(btf__str_by_offset(btf3, t->name_off), "int", "split_base_type_name"); + /* BTF-to-C dump of split BTF */ dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz); if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream")) return; - d = btf_dump__new(btf2, btf_dump_printf, dump_buf_file, NULL); + d = btf_dump__new(btf3, btf_dump_printf, dump_buf_file, NULL); if (!ASSERT_OK_PTR(d, "btf_dump__new")) goto cleanup; - for (i = 1; i < btf__type_cnt(btf2); i++) { + for (i = 1; i < btf__type_cnt(btf3); i++) { err = btf_dump__dump_type(d, i); ASSERT_OK(err, "dump_type_ok"); } @@ -79,12 +112,15 @@ void test_btf_split() { ASSERT_STREQ(dump_buf, "struct s1 {\n" " int f1;\n" -"};\n" -"\n" +"};\n\n" "struct s2 {\n" " struct s1 f1;\n" " int f2;\n" " int *f3;\n" +"};\n\n" +"union u1 {\n" +" struct s2 f1;\n" +" int uf2;\n" "};\n\n", "c_dump"); cleanup: @@ -94,4 +130,14 @@ cleanup: btf_dump__free(d); btf__free(btf1); btf__free(btf2); + if (btf2 != btf3) + btf__free(btf3); +} + +void test_btf_split(void) +{ + if (test__start_subtest("single_split")) + __test_btf_split(false); + if (test__start_subtest("multi_split")) + __test_btf_split(true); } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_sysfs.c b/tools/testing/selftests/bpf/prog_tests/btf_sysfs.c new file mode 100644 index 000000000000..3923e64c4c1d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/btf_sysfs.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* Copyright (c) 2025 Isovalent */ + +#include <test_progs.h> +#include <bpf/btf.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <fcntl.h> +#include <unistd.h> + +static void test_btf_mmap_sysfs(const char *path, struct btf *base) +{ + struct stat st; + __u64 btf_size, end; + void *raw_data = NULL; + int fd = -1; + long page_size; + struct btf *btf = NULL; + + page_size = sysconf(_SC_PAGESIZE); + if (!ASSERT_GE(page_size, 0, "get_page_size")) + goto cleanup; + + if (!ASSERT_OK(stat(path, &st), "stat_btf")) + goto cleanup; + + btf_size = st.st_size; + end = (btf_size + page_size - 1) / page_size * page_size; + + fd = open(path, O_RDONLY); + if (!ASSERT_GE(fd, 0, "open_btf")) + goto cleanup; + + raw_data = mmap(NULL, btf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + if (!ASSERT_EQ(raw_data, MAP_FAILED, "mmap_btf_writable")) + goto cleanup; + + raw_data = mmap(NULL, btf_size, PROT_READ, MAP_SHARED, fd, 0); + if (!ASSERT_EQ(raw_data, MAP_FAILED, "mmap_btf_shared")) + goto cleanup; + + raw_data = mmap(NULL, end + 1, PROT_READ, MAP_PRIVATE, fd, 0); + if (!ASSERT_EQ(raw_data, MAP_FAILED, "mmap_btf_invalid_size")) + goto cleanup; + + raw_data = mmap(NULL, end, PROT_READ, MAP_PRIVATE, fd, 0); + if (!ASSERT_OK_PTR(raw_data, "mmap_btf")) + goto cleanup; + + if (!ASSERT_EQ(mprotect(raw_data, btf_size, PROT_READ | PROT_WRITE), -1, + "mprotect_writable")) + goto cleanup; + + if (!ASSERT_EQ(mprotect(raw_data, btf_size, PROT_READ | PROT_EXEC), -1, + "mprotect_executable")) + goto cleanup; + + /* Check padding is zeroed */ + for (int i = btf_size; i < end; i++) { + if (((__u8 *)raw_data)[i] != 0) { + PRINT_FAIL("tail of BTF is not zero at page offset %d\n", i); + goto cleanup; + } + } + + btf = btf__new_split(raw_data, btf_size, base); + if (!ASSERT_OK_PTR(btf, "parse_btf")) + goto cleanup; + +cleanup: + btf__free(btf); + if (raw_data && raw_data != MAP_FAILED) + munmap(raw_data, btf_size); + if (fd >= 0) + close(fd); +} + +void test_btf_sysfs(void) +{ + test_btf_mmap_sysfs("/sys/kernel/btf/vmlinux", NULL); +} diff --git a/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c b/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c new file mode 100644 index 000000000000..6c2b0c3dbcd8 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Google */ + +#include <test_progs.h> +#include <bpf/libbpf.h> +#include <bpf/btf.h> +#include "dmabuf_iter.skel.h" + +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <unistd.h> + +#include <linux/dma-buf.h> +#include <linux/dma-heap.h> +#include <linux/udmabuf.h> + +static int udmabuf = -1; +static const char udmabuf_test_buffer_name[DMA_BUF_NAME_LEN] = "udmabuf_test_buffer_for_iter"; +static size_t udmabuf_test_buffer_size; +static int sysheap_dmabuf = -1; +static const char sysheap_test_buffer_name[DMA_BUF_NAME_LEN] = "sysheap_test_buffer_for_iter"; +static size_t sysheap_test_buffer_size; + +static int create_udmabuf(void) +{ + struct udmabuf_create create; + int dev_udmabuf, memfd, local_udmabuf; + + udmabuf_test_buffer_size = 10 * getpagesize(); + + if (!ASSERT_LE(sizeof(udmabuf_test_buffer_name), DMA_BUF_NAME_LEN, "NAMETOOLONG")) + return -1; + + memfd = memfd_create("memfd_test", MFD_ALLOW_SEALING); + if (!ASSERT_OK_FD(memfd, "memfd_create")) + return -1; + + if (!ASSERT_OK(ftruncate(memfd, udmabuf_test_buffer_size), "ftruncate")) + goto close_memfd; + + if (!ASSERT_OK(fcntl(memfd, F_ADD_SEALS, F_SEAL_SHRINK), "seal")) + goto close_memfd; + + dev_udmabuf = open("/dev/udmabuf", O_RDONLY); + if (!ASSERT_OK_FD(dev_udmabuf, "open udmabuf")) + goto close_memfd; + + memset(&create, 0, sizeof(create)); + create.memfd = memfd; + create.flags = UDMABUF_FLAGS_CLOEXEC; + create.offset = 0; + create.size = udmabuf_test_buffer_size; + + local_udmabuf = ioctl(dev_udmabuf, UDMABUF_CREATE, &create); + close(dev_udmabuf); + if (!ASSERT_OK_FD(local_udmabuf, "udmabuf_create")) + goto close_memfd; + + if (!ASSERT_OK(ioctl(local_udmabuf, DMA_BUF_SET_NAME_B, udmabuf_test_buffer_name), "name")) + goto close_udmabuf; + + return local_udmabuf; + +close_udmabuf: + close(local_udmabuf); +close_memfd: + close(memfd); + return -1; +} + +static int create_sys_heap_dmabuf(void) +{ + sysheap_test_buffer_size = 20 * getpagesize(); + + struct dma_heap_allocation_data data = { + .len = sysheap_test_buffer_size, + .fd = 0, + .fd_flags = O_RDWR | O_CLOEXEC, + .heap_flags = 0, + }; + int heap_fd, ret; + + if (!ASSERT_LE(sizeof(sysheap_test_buffer_name), DMA_BUF_NAME_LEN, "NAMETOOLONG")) + return -1; + + heap_fd = open("/dev/dma_heap/system", O_RDONLY); + if (!ASSERT_OK_FD(heap_fd, "open dma heap")) + return -1; + + ret = ioctl(heap_fd, DMA_HEAP_IOCTL_ALLOC, &data); + close(heap_fd); + if (!ASSERT_OK(ret, "syheap alloc")) + return -1; + + if (!ASSERT_OK(ioctl(data.fd, DMA_BUF_SET_NAME_B, sysheap_test_buffer_name), "name")) + goto close_sysheap_dmabuf; + + return data.fd; + +close_sysheap_dmabuf: + close(data.fd); + return -1; +} + +static int create_test_buffers(void) +{ + udmabuf = create_udmabuf(); + sysheap_dmabuf = create_sys_heap_dmabuf(); + + if (udmabuf < 0 || sysheap_dmabuf < 0) + return -1; + + return 0; +} + +static void destroy_test_buffers(void) +{ + close(udmabuf); + udmabuf = -1; + + close(sysheap_dmabuf); + sysheap_dmabuf = -1; +} + +enum Fields { INODE, SIZE, NAME, EXPORTER, FIELD_COUNT }; +struct DmabufInfo { + unsigned long inode; + unsigned long size; + char name[DMA_BUF_NAME_LEN]; + char exporter[32]; +}; + +static bool check_dmabuf_info(const struct DmabufInfo *bufinfo, + unsigned long size, + const char *name, const char *exporter) +{ + return size == bufinfo->size && + !strcmp(name, bufinfo->name) && + !strcmp(exporter, bufinfo->exporter); +} + +static void subtest_dmabuf_iter_check_no_infinite_reads(struct dmabuf_iter *skel) +{ + int iter_fd; + char buf[256]; + + iter_fd = bpf_iter_create(bpf_link__fd(skel->links.dmabuf_collector)); + if (!ASSERT_OK_FD(iter_fd, "iter_create")) + return; + + while (read(iter_fd, buf, sizeof(buf)) > 0) + ; /* Read out all contents */ + + /* Next reads should return 0 */ + ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read"); + + close(iter_fd); +} + +static void subtest_dmabuf_iter_check_default_iter(struct dmabuf_iter *skel) +{ + bool found_test_sysheap_dmabuf = false; + bool found_test_udmabuf = false; + struct DmabufInfo bufinfo; + size_t linesize = 0; + char *line = NULL; + FILE *iter_file; + int iter_fd, f = INODE; + + iter_fd = bpf_iter_create(bpf_link__fd(skel->links.dmabuf_collector)); + if (!ASSERT_OK_FD(iter_fd, "iter_create")) + return; + + iter_file = fdopen(iter_fd, "r"); + if (!ASSERT_OK_PTR(iter_file, "fdopen")) + goto close_iter_fd; + + while (getline(&line, &linesize, iter_file) != -1) { + if (f % FIELD_COUNT == INODE) { + ASSERT_EQ(sscanf(line, "%ld", &bufinfo.inode), 1, + "read inode"); + } else if (f % FIELD_COUNT == SIZE) { + ASSERT_EQ(sscanf(line, "%ld", &bufinfo.size), 1, + "read size"); + } else if (f % FIELD_COUNT == NAME) { + ASSERT_EQ(sscanf(line, "%s", bufinfo.name), 1, + "read name"); + } else if (f % FIELD_COUNT == EXPORTER) { + ASSERT_EQ(sscanf(line, "%31s", bufinfo.exporter), 1, + "read exporter"); + + if (check_dmabuf_info(&bufinfo, + sysheap_test_buffer_size, + sysheap_test_buffer_name, + "system")) + found_test_sysheap_dmabuf = true; + else if (check_dmabuf_info(&bufinfo, + udmabuf_test_buffer_size, + udmabuf_test_buffer_name, + "udmabuf")) + found_test_udmabuf = true; + } + ++f; + } + + ASSERT_EQ(f % FIELD_COUNT, INODE, "number of fields"); + + ASSERT_TRUE(found_test_sysheap_dmabuf, "found_test_sysheap_dmabuf"); + ASSERT_TRUE(found_test_udmabuf, "found_test_udmabuf"); + + free(line); + fclose(iter_file); +close_iter_fd: + close(iter_fd); +} + +static void subtest_dmabuf_iter_check_open_coded(struct dmabuf_iter *skel, int map_fd) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + char key[DMA_BUF_NAME_LEN]; + int err, fd; + bool found; + + /* No need to attach it, just run it directly */ + fd = bpf_program__fd(skel->progs.iter_dmabuf_for_each); + + err = bpf_prog_test_run_opts(fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; + + if (!ASSERT_OK(bpf_map_get_next_key(map_fd, NULL, key), "get next key")) + return; + + do { + ASSERT_OK(bpf_map_lookup_elem(map_fd, key, &found), "lookup"); + ASSERT_TRUE(found, "found test buffer"); + } while (bpf_map_get_next_key(map_fd, key, key)); +} + +void test_dmabuf_iter(void) +{ + struct dmabuf_iter *skel = NULL; + int map_fd; + const bool f = false; + + skel = dmabuf_iter__open_and_load(); + if (!ASSERT_OK_PTR(skel, "dmabuf_iter__open_and_load")) + return; + + map_fd = bpf_map__fd(skel->maps.testbuf_hash); + if (!ASSERT_OK_FD(map_fd, "map_fd")) + goto destroy_skel; + + if (!ASSERT_OK(bpf_map_update_elem(map_fd, udmabuf_test_buffer_name, &f, BPF_ANY), + "insert udmabuf")) + goto destroy_skel; + if (!ASSERT_OK(bpf_map_update_elem(map_fd, sysheap_test_buffer_name, &f, BPF_ANY), + "insert sysheap buffer")) + goto destroy_skel; + + if (!ASSERT_OK(create_test_buffers(), "create_test_buffers")) + goto destroy; + + if (!ASSERT_OK(dmabuf_iter__attach(skel), "skel_attach")) + goto destroy; + + if (test__start_subtest("no_infinite_reads")) + subtest_dmabuf_iter_check_no_infinite_reads(skel); + if (test__start_subtest("default_iter")) + subtest_dmabuf_iter_check_default_iter(skel); + if (test__start_subtest("open_coded")) + subtest_dmabuf_iter_check_open_coded(skel, map_fd); + +destroy: + destroy_test_buffers(); +destroy_skel: + dmabuf_iter__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index e29cc16124c2..62e7ec775f24 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -33,10 +33,19 @@ static struct { {"test_dynptr_skb_no_buff", SETUP_SKB_PROG}, {"test_dynptr_skb_strcmp", SETUP_SKB_PROG}, {"test_dynptr_skb_tp_btf", SETUP_SKB_PROG_TP}, + {"test_probe_read_user_dynptr", SETUP_XDP_PROG}, + {"test_probe_read_kernel_dynptr", SETUP_XDP_PROG}, + {"test_probe_read_user_str_dynptr", SETUP_XDP_PROG}, + {"test_probe_read_kernel_str_dynptr", SETUP_XDP_PROG}, + {"test_copy_from_user_dynptr", SETUP_SYSCALL_SLEEP}, + {"test_copy_from_user_str_dynptr", SETUP_SYSCALL_SLEEP}, + {"test_copy_from_user_task_dynptr", SETUP_SYSCALL_SLEEP}, + {"test_copy_from_user_task_str_dynptr", SETUP_SYSCALL_SLEEP}, }; static void verify_success(const char *prog_name, enum test_setup_type setup_type) { + char user_data[384] = {[0 ... 382] = 'a', '\0'}; struct dynptr_success *skel; struct bpf_program *prog; struct bpf_link *link; @@ -58,6 +67,10 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ if (!ASSERT_OK(err, "dynptr_success__load")) goto cleanup; + skel->bss->user_ptr = user_data; + skel->data->test_len[0] = sizeof(user_data); + memcpy(skel->bss->expected_str, user_data, sizeof(user_data)); + switch (setup_type) { case SETUP_SYSCALL_SLEEP: link = bpf_program__attach(prog); diff --git a/tools/testing/selftests/bpf/prog_tests/fd_htab_lookup.c b/tools/testing/selftests/bpf/prog_tests/fd_htab_lookup.c new file mode 100644 index 000000000000..ca46fdd6e1ae --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/fd_htab_lookup.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025. Huawei Technologies Co., Ltd */ +#define _GNU_SOURCE +#include <stdbool.h> +#include <test_progs.h> +#include "fd_htab_lookup.skel.h" + +struct htab_op_ctx { + int fd; + int loop; + unsigned int entries; + bool stop; +}; + +#define ERR_TO_RETVAL(where, err) ((void *)(long)(((where) << 12) | (-err))) + +static void *htab_lookup_fn(void *arg) +{ + struct htab_op_ctx *ctx = arg; + int i = 0; + + while (i++ < ctx->loop && !ctx->stop) { + unsigned int j; + + for (j = 0; j < ctx->entries; j++) { + unsigned int key = j, zero = 0, value; + int inner_fd, err; + + err = bpf_map_lookup_elem(ctx->fd, &key, &value); + if (err) { + ctx->stop = true; + return ERR_TO_RETVAL(1, err); + } + + inner_fd = bpf_map_get_fd_by_id(value); + if (inner_fd < 0) { + /* The old map has been freed */ + if (inner_fd == -ENOENT) + continue; + ctx->stop = true; + return ERR_TO_RETVAL(2, inner_fd); + } + + err = bpf_map_lookup_elem(inner_fd, &zero, &value); + if (err) { + close(inner_fd); + ctx->stop = true; + return ERR_TO_RETVAL(3, err); + } + close(inner_fd); + + if (value != key) { + ctx->stop = true; + return ERR_TO_RETVAL(4, -EINVAL); + } + } + } + + return NULL; +} + +static void *htab_update_fn(void *arg) +{ + struct htab_op_ctx *ctx = arg; + int i = 0; + + while (i++ < ctx->loop && !ctx->stop) { + unsigned int j; + + for (j = 0; j < ctx->entries; j++) { + unsigned int key = j, zero = 0; + int inner_fd, err; + + inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL); + if (inner_fd < 0) { + ctx->stop = true; + return ERR_TO_RETVAL(1, inner_fd); + } + + err = bpf_map_update_elem(inner_fd, &zero, &key, 0); + if (err) { + close(inner_fd); + ctx->stop = true; + return ERR_TO_RETVAL(2, err); + } + + err = bpf_map_update_elem(ctx->fd, &key, &inner_fd, BPF_EXIST); + if (err) { + close(inner_fd); + ctx->stop = true; + return ERR_TO_RETVAL(3, err); + } + close(inner_fd); + } + } + + return NULL; +} + +static int setup_htab(int fd, unsigned int entries) +{ + unsigned int i; + + for (i = 0; i < entries; i++) { + unsigned int key = i, zero = 0; + int inner_fd, err; + + inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL); + if (!ASSERT_OK_FD(inner_fd, "new array")) + return -1; + + err = bpf_map_update_elem(inner_fd, &zero, &key, 0); + if (!ASSERT_OK(err, "init array")) { + close(inner_fd); + return -1; + } + + err = bpf_map_update_elem(fd, &key, &inner_fd, 0); + if (!ASSERT_OK(err, "init outer")) { + close(inner_fd); + return -1; + } + close(inner_fd); + } + + return 0; +} + +static int get_int_from_env(const char *name, int dft) +{ + const char *value; + + value = getenv(name); + if (!value) + return dft; + + return atoi(value); +} + +void test_fd_htab_lookup(void) +{ + unsigned int i, wr_nr = 8, rd_nr = 16; + pthread_t tids[wr_nr + rd_nr]; + struct fd_htab_lookup *skel; + struct htab_op_ctx ctx; + int err; + + skel = fd_htab_lookup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fd_htab_lookup__open_and_load")) + return; + + ctx.fd = bpf_map__fd(skel->maps.outer_map); + ctx.loop = get_int_from_env("FD_HTAB_LOOP_NR", 5); + ctx.stop = false; + ctx.entries = 8; + + err = setup_htab(ctx.fd, ctx.entries); + if (err) + goto destroy; + + memset(tids, 0, sizeof(tids)); + for (i = 0; i < wr_nr; i++) { + err = pthread_create(&tids[i], NULL, htab_update_fn, &ctx); + if (!ASSERT_OK(err, "pthread_create")) { + ctx.stop = true; + goto reap; + } + } + for (i = 0; i < rd_nr; i++) { + err = pthread_create(&tids[i + wr_nr], NULL, htab_lookup_fn, &ctx); + if (!ASSERT_OK(err, "pthread_create")) { + ctx.stop = true; + goto reap; + } + } + +reap: + for (i = 0; i < wr_nr + rd_nr; i++) { + void *ret = NULL; + char desc[32]; + + if (!tids[i]) + continue; + + snprintf(desc, sizeof(desc), "thread %u", i + 1); + err = pthread_join(tids[i], &ret); + ASSERT_OK(err, desc); + ASSERT_EQ(ret, NULL, desc); + } +destroy: + fd_htab_lookup__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c index e59af2aa6601..e40114620751 100644 --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -37,6 +37,7 @@ static noinline void uprobe_func(void) static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long addr, ssize_t offset, ssize_t entry_offset) { + ssize_t ref_ctr_offset = entry_offset /* ref_ctr_offset for uprobes */; struct bpf_link_info info; __u32 len = sizeof(info); char buf[PATH_MAX]; @@ -97,6 +98,7 @@ again: case BPF_PERF_EVENT_UPROBE: case BPF_PERF_EVENT_URETPROBE: ASSERT_EQ(info.perf_event.uprobe.offset, offset, "uprobe_offset"); + ASSERT_EQ(info.perf_event.uprobe.ref_ctr_offset, ref_ctr_offset, "uprobe_ref_ctr_offset"); ASSERT_EQ(info.perf_event.uprobe.name_len, strlen(UPROBE_FILE) + 1, "name_len"); @@ -241,20 +243,32 @@ static void test_uprobe_fill_link_info(struct test_fill_link_info *skel, .retprobe = type == BPF_PERF_EVENT_URETPROBE, .bpf_cookie = PERF_EVENT_COOKIE, ); + const char *sema[1] = { + "uprobe_link_info_sema_1", + }; + __u64 *ref_ctr_offset; struct bpf_link *link; int link_fd, err; + err = elf_resolve_syms_offsets("/proc/self/exe", 1, sema, + (unsigned long **) &ref_ctr_offset, STT_OBJECT); + if (!ASSERT_OK(err, "elf_resolve_syms_offsets_object")) + return; + + opts.ref_ctr_offset = *ref_ctr_offset; link = bpf_program__attach_uprobe_opts(skel->progs.uprobe_run, 0, /* self pid */ UPROBE_FILE, uprobe_offset, &opts); if (!ASSERT_OK_PTR(link, "attach_uprobe")) - return; + goto out; link_fd = bpf_link__fd(link); - err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, 0); + err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, *ref_ctr_offset); ASSERT_OK(err, "verify_perf_link_info"); bpf_link__destroy(link); +out: + free(ref_ctr_offset); } static int verify_kmulti_link_info(int fd, bool retprobe, bool has_cookies) diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c index 8e13a3416a21..1de14b111931 100644 --- a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c @@ -104,7 +104,7 @@ void test_kmem_cache_iter(void) goto destroy; memset(buf, 0, sizeof(buf)); - while (read(iter_fd, buf, sizeof(buf) > 0)) { + while (read(iter_fd, buf, sizeof(buf)) > 0) { /* Read out all contents */ printf("%s", buf); } diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c index 77d07e0a4a55..5266c7022863 100644 --- a/tools/testing/selftests/bpf/prog_tests/linked_list.c +++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c @@ -7,6 +7,7 @@ #include "linked_list.skel.h" #include "linked_list_fail.skel.h" +#include "linked_list_peek.skel.h" static char log_buf[1024 * 1024]; @@ -805,3 +806,8 @@ void test_linked_list(void) test_linked_list_success(LIST_IN_LIST, true); test_linked_list_success(TEST_ALL, false); } + +void test_linked_list_peek(void) +{ + RUN_TESTS(linked_list_peek); +} diff --git a/tools/testing/selftests/bpf/prog_tests/rbtree.c b/tools/testing/selftests/bpf/prog_tests/rbtree.c index 9818f06c97c5..d8f3d7a45fe9 100644 --- a/tools/testing/selftests/bpf/prog_tests/rbtree.c +++ b/tools/testing/selftests/bpf/prog_tests/rbtree.c @@ -8,6 +8,7 @@ #include "rbtree_fail.skel.h" #include "rbtree_btf_fail__wrong_node_type.skel.h" #include "rbtree_btf_fail__add_wrong_type.skel.h" +#include "rbtree_search.skel.h" static void test_rbtree_add_nodes(void) { @@ -187,3 +188,8 @@ void test_rbtree_fail(void) { RUN_TESTS(rbtree_fail); } + +void test_rbtree_search(void) +{ + RUN_TESTS(rbtree_search); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index 0b9bd1d6f7cc..10a0ab954b8a 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -37,8 +37,10 @@ configure_stack(void) tc = popen("tc -V", "r"); if (CHECK_FAIL(!tc)) return false; - if (CHECK_FAIL(!fgets(tc_version, sizeof(tc_version), tc))) + if (CHECK_FAIL(!fgets(tc_version, sizeof(tc_version), tc))) { + pclose(tc); return false; + } if (strstr(tc_version, ", libbpf ")) prog = "test_sk_assign_libbpf.bpf.o"; else 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 d56e18b25528..a4517bee34d5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c @@ -7,14 +7,433 @@ #define TEST_NS "sock_iter_batch_netns" +static const int init_batch_size = 16; static const int nr_soreuse = 4; +struct iter_out { + int idx; + __u64 cookie; +} __packed; + +struct sock_count { + __u64 cookie; + int count; +}; + +static int insert(__u64 cookie, struct sock_count counts[], int counts_len) +{ + int insert = -1; + int i = 0; + + for (; i < counts_len; i++) { + if (!counts[i].cookie) { + insert = i; + } else if (counts[i].cookie == cookie) { + insert = i; + break; + } + } + if (insert < 0) + return insert; + + counts[insert].cookie = cookie; + counts[insert].count++; + + return counts[insert].count; +} + +static int read_n(int iter_fd, int n, struct sock_count counts[], + int counts_len) +{ + struct iter_out out; + int nread = 1; + int i = 0; + + for (; nread > 0 && (n < 0 || i < n); i++) { + nread = read(iter_fd, &out, sizeof(out)); + if (!nread || !ASSERT_EQ(nread, sizeof(out), "nread")) + break; + ASSERT_GE(insert(out.cookie, counts, counts_len), 0, "insert"); + } + + ASSERT_TRUE(n < 0 || i == n, "n < 0 || i == n"); + + return i; +} + +static __u64 socket_cookie(int fd) +{ + __u64 cookie; + socklen_t cookie_len = sizeof(cookie); + + if (!ASSERT_OK(getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie, + &cookie_len), "getsockopt(SO_COOKIE)")) + return 0; + return cookie; +} + +static bool was_seen(int fd, struct sock_count counts[], int counts_len) +{ + __u64 cookie = socket_cookie(fd); + int i = 0; + + for (; cookie && i < counts_len; i++) + if (cookie == counts[i].cookie) + return true; + + return false; +} + +static int get_seen_socket(int *fds, struct sock_count counts[], int n) +{ + int i = 0; + + for (; i < n; i++) + if (was_seen(fds[i], counts, n)) + return i; + return -1; +} + +static int get_nth_socket(int *fds, int fds_len, struct bpf_link *link, int n) +{ + int i, nread, iter_fd; + int nth_sock_idx = -1; + struct iter_out out; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create")) + return -1; + + for (; n >= 0; n--) { + nread = read(iter_fd, &out, sizeof(out)); + if (!nread || !ASSERT_GE(nread, 1, "nread")) + goto done; + } + + for (i = 0; i < fds_len && nth_sock_idx < 0; i++) + if (fds[i] >= 0 && socket_cookie(fds[i]) == out.cookie) + nth_sock_idx = i; +done: + close(iter_fd); + return nth_sock_idx; +} + +static int get_seen_count(int fd, struct sock_count counts[], int n) +{ + __u64 cookie = socket_cookie(fd); + int count = 0; + int i = 0; + + for (; cookie && !count && i < n; i++) + if (cookie == counts[i].cookie) + count = counts[i].count; + + return count; +} + +static void check_n_were_seen_once(int *fds, int fds_len, int n, + struct sock_count counts[], int counts_len) +{ + int seen_once = 0; + int seen_cnt; + int i = 0; + + for (; i < fds_len; i++) { + /* Skip any sockets that were closed or that weren't seen + * exactly once. + */ + if (fds[i] < 0) + continue; + seen_cnt = get_seen_count(fds[i], counts, counts_len); + if (seen_cnt && ASSERT_EQ(seen_cnt, 1, "seen_cnt")) + seen_once++; + } + + ASSERT_EQ(seen_once, n, "seen_once"); +} + +static void remove_seen(int family, int sock_type, const char *addr, __u16 port, + int *socks, int socks_len, struct sock_count *counts, + int counts_len, struct bpf_link *link, int iter_fd) +{ + int close_idx; + + /* Iterate through the first socks_len - 1 sockets. */ + read_n(iter_fd, socks_len - 1, counts, counts_len); + + /* Make sure we saw socks_len - 1 sockets exactly once. */ + check_n_were_seen_once(socks, socks_len, socks_len - 1, counts, + counts_len); + + /* Close a socket we've already seen to remove it from the bucket. */ + close_idx = get_seen_socket(socks, counts, counts_len); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + close(socks[close_idx]); + 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(socks, socks_len, 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, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int close_idx; + + /* Iterate through the first socket. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Make sure we saw a socket from fds. */ + check_n_were_seen_once(socks, 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(socks, socks_len, link, 1); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + close(socks[close_idx]); + 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(socks, socks_len, 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, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int close_idx, i; + + /* Iterate through the first socket. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Make sure we saw a socket from fds. */ + check_n_were_seen_once(socks, 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. + */ + for (i = 0; i < socks_len - 1; i++) { + close_idx = get_nth_socket(socks, socks_len, link, 1); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + close(socks[close_idx]); + socks[close_idx] = -1; + } + + /* Make sure there are no more sockets returned */ + ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n"); +} + +static void add_some(int family, int sock_type, const char *addr, __u16 port, + int *socks, int socks_len, struct sock_count *counts, + int counts_len, struct bpf_link *link, int iter_fd) +{ + int *new_socks = NULL; + + /* Iterate through the first socks_len - 1 sockets. */ + read_n(iter_fd, socks_len - 1, counts, counts_len); + + /* Make sure we saw socks_len - 1 sockets exactly once. */ + check_n_were_seen_once(socks, socks_len, socks_len - 1, counts, + counts_len); + + /* Double the number of sockets in the bucket. */ + new_socks = start_reuseport_server(family, sock_type, addr, port, 0, + socks_len); + if (!ASSERT_OK_PTR(new_socks, "start_reuseport_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(socks, socks_len, socks_len, counts, + counts_len); +done: + free_fds(new_socks, socks_len); +} + +static void force_realloc(int family, int sock_type, const char *addr, + __u16 port, int *socks, int socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int *new_socks = NULL; + + /* Iterate through the first socket just to initialize the batch. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Double the number of sockets in the bucket to force a realloc on the + * next read. + */ + new_socks = start_reuseport_server(family, sock_type, addr, port, 0, + socks_len); + if (!ASSERT_OK_PTR(new_socks, "start_reuseport_server")) + goto done; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure each socket from the first set was seen exactly once. */ + check_n_were_seen_once(socks, socks_len, socks_len, counts, + counts_len); +done: + free_fds(new_socks, socks_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 counts_len, struct bpf_link *link, int iter_fd); + const char *description; + int init_socks; + int max_socks; + int sock_type; + int family; +}; + +static struct test_case resume_tests[] = { + { + .description = "udp: resume after removing a seen socket", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_DGRAM, + .family = AF_INET6, + .test = remove_seen, + }, + { + .description = "udp: resume after removing one unseen socket", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_DGRAM, + .family = AF_INET6, + .test = remove_unseen, + }, + { + .description = "udp: resume after removing all unseen sockets", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_DGRAM, + .family = AF_INET6, + .test = remove_all, + }, + { + .description = "udp: resume after adding a few sockets", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_DGRAM, + /* Use AF_INET so that new sockets are added to the head of the + * bucket's list. + */ + .family = AF_INET, + .test = add_some, + }, + { + .description = "udp: force a realloc to occur", + .init_socks = init_batch_size, + .max_socks = init_batch_size * 2, + .sock_type = SOCK_DGRAM, + /* 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, + }, +}; + +static void do_resume_test(struct test_case *tc) +{ + struct sock_iter_batch *skel = NULL; + static const __u16 port = 10001; + struct bpf_link *link = NULL; + struct sock_count *counts; + int err, iter_fd = -1; + const char *addr; + int *fds = NULL; + int local_port; + + counts = calloc(tc->max_socks, sizeof(*counts)); + if (!ASSERT_OK_PTR(counts, "counts")) + goto done; + skel = sock_iter_batch__open(); + if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open")) + goto done; + + /* Prepare a bucket of sockets in the kernel hashtable */ + addr = tc->family == AF_INET6 ? "::1" : "127.0.0.1"; + fds = start_reuseport_server(tc->family, tc->sock_type, addr, port, 0, + 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); + skel->rodata->sf = tc->family; + + err = sock_iter_batch__load(skel); + if (!ASSERT_OK(err, "sock_iter_batch__load")) + goto done; + + link = bpf_program__attach_iter(tc->sock_type == SOCK_STREAM ? + skel->progs.iter_tcp_soreuse : + skel->progs.iter_udp_soreuse, + 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; + + tc->test(tc->family, tc->sock_type, addr, port, fds, tc->init_socks, + counts, tc->max_socks, link, iter_fd); +done: + free(counts); + free_fds(fds, tc->init_socks); + if (iter_fd >= 0) + close(iter_fd); + bpf_link__destroy(link); + sock_iter_batch__destroy(skel); +} + +static void do_resume_tests(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(resume_tests); i++) { + if (test__start_subtest(resume_tests[i].description)) { + do_resume_test(&resume_tests[i]); + } + } +} + static void do_test(int sock_type, bool onebyone) { int err, i, nread, to_read, total_read, iter_fd = -1; - int first_idx, second_idx, indices[nr_soreuse]; + struct iter_out outputs[nr_soreuse]; struct bpf_link *link = NULL; struct sock_iter_batch *skel; + int first_idx, second_idx; int *fds[2] = {}; skel = sock_iter_batch__open(); @@ -34,6 +453,7 @@ static void do_test(int sock_type, bool onebyone) goto done; skel->rodata->ports[i] = ntohs(local_port); } + skel->rodata->sf = AF_INET6; err = sock_iter_batch__load(skel); if (!ASSERT_OK(err, "sock_iter_batch__load")) @@ -55,38 +475,38 @@ static void do_test(int sock_type, bool onebyone) * from a bucket and leave one socket out from * that bucket on purpose. */ - to_read = (nr_soreuse - 1) * sizeof(*indices); + to_read = (nr_soreuse - 1) * sizeof(*outputs); total_read = 0; first_idx = -1; do { - nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read); - if (nread <= 0 || nread % sizeof(*indices)) + nread = read(iter_fd, outputs, onebyone ? sizeof(*outputs) : to_read); + if (nread <= 0 || nread % sizeof(*outputs)) break; total_read += nread; if (first_idx == -1) - first_idx = indices[0]; - for (i = 0; i < nread / sizeof(*indices); i++) - ASSERT_EQ(indices[i], first_idx, "first_idx"); + first_idx = outputs[0].idx; + for (i = 0; i < nread / sizeof(*outputs); i++) + ASSERT_EQ(outputs[i].idx, first_idx, "first_idx"); } while (total_read < to_read); - ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread"); + ASSERT_EQ(nread, onebyone ? sizeof(*outputs) : to_read, "nread"); ASSERT_EQ(total_read, to_read, "total_read"); free_fds(fds[first_idx], nr_soreuse); fds[first_idx] = NULL; /* Read the "whole" second bucket */ - to_read = nr_soreuse * sizeof(*indices); + to_read = nr_soreuse * sizeof(*outputs); total_read = 0; second_idx = !first_idx; do { - nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read); - if (nread <= 0 || nread % sizeof(*indices)) + nread = read(iter_fd, outputs, onebyone ? sizeof(*outputs) : to_read); + if (nread <= 0 || nread % sizeof(*outputs)) break; total_read += nread; - for (i = 0; i < nread / sizeof(*indices); i++) - ASSERT_EQ(indices[i], second_idx, "second_idx"); + for (i = 0; i < nread / sizeof(*outputs); i++) + ASSERT_EQ(outputs[i].idx, second_idx, "second_idx"); } while (total_read <= to_read); ASSERT_EQ(nread, 0, "nread"); /* Both so_reuseport ports should be in different buckets, so @@ -128,6 +548,7 @@ void test_sock_iter_batch(void) do_test(SOCK_DGRAM, true); do_test(SOCK_DGRAM, false); } + do_resume_tests(); close_netns(nstoken); done: diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h index 1bdfb79ef009..e02cabcc814e 100644 --- a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h @@ -3,6 +3,7 @@ #ifndef __SOCKET_HELPERS__ #define __SOCKET_HELPERS__ +#include <sys/un.h> #include <linux/vm_sockets.h> /* include/linux/net.h */ @@ -169,6 +170,15 @@ static inline void init_addr_loopback6(struct sockaddr_storage *ss, *len = sizeof(*addr6); } +static inline void init_addr_loopback_unix(struct sockaddr_storage *ss, + socklen_t *len) +{ + struct sockaddr_un *addr = memset(ss, 0, sizeof(*ss)); + + addr->sun_family = AF_UNIX; + *len = sizeof(sa_family_t); +} + static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss, socklen_t *len) { @@ -190,6 +200,9 @@ static inline void init_addr_loopback(int family, struct sockaddr_storage *ss, case AF_INET6: init_addr_loopback6(ss, len); return; + case AF_UNIX: + init_addr_loopback_unix(ss, len); + return; case AF_VSOCK: init_addr_loopback_vsock(ss, len); return; @@ -315,21 +328,27 @@ static inline int create_pair(int family, int sotype, int *p0, int *p1) { __close_fd int s, c = -1, p = -1; struct sockaddr_storage addr; - socklen_t len = sizeof(addr); + socklen_t len; int err; s = socket_loopback(family, sotype); if (s < 0) return s; - err = xgetsockname(s, sockaddr(&addr), &len); - if (err) - return err; - c = xsocket(family, sotype, 0); if (c < 0) return c; + init_addr_loopback(family, &addr, &len); + err = xbind(c, sockaddr(&addr), len); + if (err) + return err; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + err = connect(c, sockaddr(&addr), len); if (err) { if (errno != EINPROGRESS) { @@ -391,4 +410,59 @@ static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1, return err; } +static inline const char *socket_kind_to_str(int sock_fd) +{ + socklen_t opt_len; + int domain, type; + + opt_len = sizeof(domain); + if (getsockopt(sock_fd, SOL_SOCKET, SO_DOMAIN, &domain, &opt_len)) + FAIL_ERRNO("getsockopt(SO_DOMAIN)"); + + opt_len = sizeof(type); + if (getsockopt(sock_fd, SOL_SOCKET, SO_TYPE, &type, &opt_len)) + FAIL_ERRNO("getsockopt(SO_TYPE)"); + + switch (domain) { + case AF_INET: + switch (type) { + case SOCK_STREAM: + return "tcp4"; + case SOCK_DGRAM: + return "udp4"; + } + break; + case AF_INET6: + switch (type) { + case SOCK_STREAM: + return "tcp6"; + case SOCK_DGRAM: + return "udp6"; + } + break; + case AF_UNIX: + switch (type) { + case SOCK_STREAM: + return "u_str"; + case SOCK_DGRAM: + return "u_dgr"; + case SOCK_SEQPACKET: + return "u_seq"; + } + break; + case AF_VSOCK: + switch (type) { + case SOCK_STREAM: + return "v_str"; + case SOCK_DGRAM: + return "v_dgr"; + case SOCK_SEQPACKET: + return "v_seq"; + } + break; + } + + return "???"; +} + #endif // __SOCKET_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h index 3e5571dd578d..d815efac52fd 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -5,12 +5,15 @@ #define MAX_TEST_NAME 80 +#define u32(v) ((u32){(v)}) +#define u64(v) ((u64){(v)}) + #define __always_unused __attribute__((__unused__)) #define xbpf_map_delete_elem(fd, key) \ ({ \ int __ret = bpf_map_delete_elem((fd), (key)); \ - if (__ret < 0) \ + if (__ret < 0) \ FAIL_ERRNO("map_delete"); \ __ret; \ }) @@ -18,7 +21,7 @@ #define xbpf_map_lookup_elem(fd, key, val) \ ({ \ int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ - if (__ret < 0) \ + if (__ret < 0) \ FAIL_ERRNO("map_lookup"); \ __ret; \ }) @@ -26,7 +29,7 @@ #define xbpf_map_update_elem(fd, key, val, flags) \ ({ \ int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ - if (__ret < 0) \ + if (__ret < 0) \ FAIL_ERRNO("map_update"); \ __ret; \ }) @@ -35,7 +38,7 @@ ({ \ int __ret = \ bpf_prog_attach((prog), (target), (type), (flags)); \ - if (__ret < 0) \ + if (__ret < 0) \ FAIL_ERRNO("prog_attach(" #type ")"); \ __ret; \ }) @@ -43,7 +46,7 @@ #define xbpf_prog_detach2(prog, target, type) \ ({ \ int __ret = bpf_prog_detach2((prog), (target), (type)); \ - if (__ret < 0) \ + if (__ret < 0) \ FAIL_ERRNO("prog_detach2(" #type ")"); \ __ret; \ }) @@ -66,21 +69,15 @@ __ret; \ }) -static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) +static inline int add_to_sockmap(int mapfd, int fd1, int fd2) { - u64 value; - u32 key; int err; - key = 0; - value = fd1; - err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + err = xbpf_map_update_elem(mapfd, &u32(0), &u64(fd1), BPF_NOEXIST); if (err) return err; - key = 1; - value = fd2; - return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + return xbpf_map_update_elem(mapfd, &u32(1), &u64(fd2), BPF_NOEXIST); } #endif // __SOCKMAP_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index 0a99fd404f6d..b6c471da5c28 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -3,76 +3,62 @@ /* * Tests for sockmap/sockhash holding kTLS sockets. */ - +#include <error.h> #include <netinet/tcp.h> +#include <linux/tls.h> #include "test_progs.h" +#include "sockmap_helpers.h" +#include "test_skmsg_load_helpers.skel.h" +#include "test_sockmap_ktls.skel.h" #define MAX_TEST_NAME 80 #define TCP_ULP 31 -static int tcp_server(int family) +static int init_ktls_pairs(int c, int p) { - int err, s; - - s = socket(family, SOCK_STREAM, 0); - if (!ASSERT_GE(s, 0, "socket")) - return -1; - - err = listen(s, SOMAXCONN); - if (!ASSERT_OK(err, "listen")) - return -1; - - return s; -} + int err; + struct tls12_crypto_info_aes_gcm_128 crypto_rx; + struct tls12_crypto_info_aes_gcm_128 crypto_tx; -static int disconnect(int fd) -{ - struct sockaddr unspec = { AF_UNSPEC }; + err = setsockopt(c, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls")); + if (!ASSERT_OK(err, "setsockopt(TCP_ULP)")) + goto out; - return connect(fd, &unspec, sizeof(unspec)); + err = setsockopt(p, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls")); + if (!ASSERT_OK(err, "setsockopt(TCP_ULP)")) + goto out; + + memset(&crypto_rx, 0, sizeof(crypto_rx)); + memset(&crypto_tx, 0, sizeof(crypto_tx)); + crypto_rx.info.version = TLS_1_2_VERSION; + crypto_tx.info.version = TLS_1_2_VERSION; + crypto_rx.info.cipher_type = TLS_CIPHER_AES_GCM_128; + crypto_tx.info.cipher_type = TLS_CIPHER_AES_GCM_128; + + err = setsockopt(c, SOL_TLS, TLS_TX, &crypto_tx, sizeof(crypto_tx)); + if (!ASSERT_OK(err, "setsockopt(TLS_TX)")) + goto out; + + err = setsockopt(p, SOL_TLS, TLS_RX, &crypto_rx, sizeof(crypto_rx)); + if (!ASSERT_OK(err, "setsockopt(TLS_RX)")) + goto out; + return 0; +out: + return -1; } -/* Disconnect (unhash) a kTLS socket after removing it from sockmap. */ -static void test_sockmap_ktls_disconnect_after_delete(int family, int map) +static int create_ktls_pairs(int family, int sotype, int *c, int *p) { - struct sockaddr_storage addr = {0}; - socklen_t len = sizeof(addr); - int err, cli, srv, zero = 0; - - srv = tcp_server(family); - if (srv == -1) - return; - - err = getsockname(srv, (struct sockaddr *)&addr, &len); - if (!ASSERT_OK(err, "getsockopt")) - goto close_srv; + int err; - cli = socket(family, SOCK_STREAM, 0); - if (!ASSERT_GE(cli, 0, "socket")) - goto close_srv; - - err = connect(cli, (struct sockaddr *)&addr, len); - if (!ASSERT_OK(err, "connect")) - goto close_cli; - - err = bpf_map_update_elem(map, &zero, &cli, 0); - if (!ASSERT_OK(err, "bpf_map_update_elem")) - goto close_cli; - - err = setsockopt(cli, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls")); - if (!ASSERT_OK(err, "setsockopt(TCP_ULP)")) - goto close_cli; - - err = bpf_map_delete_elem(map, &zero); - if (!ASSERT_OK(err, "bpf_map_delete_elem")) - goto close_cli; - - err = disconnect(cli); + err = create_pair(family, sotype, c, p); + if (!ASSERT_OK(err, "create_pair()")) + return -1; -close_cli: - close(cli); -close_srv: - close(srv); + err = init_ktls_pairs(*c, *p); + if (!ASSERT_OK(err, "init_ktls_pairs(c, p)")) + return -1; + return 0; } static void test_sockmap_ktls_update_fails_when_sock_has_ulp(int family, int map) @@ -145,6 +131,189 @@ static const char *fmt_test_name(const char *subtest_name, int family, return test_name; } +static void test_sockmap_ktls_offload(int family, int sotype) +{ + int err; + int c = 0, p = 0, sent, recvd; + char msg[12] = "hello world\0"; + char rcv[13]; + + err = create_ktls_pairs(family, sotype, &c, &p); + if (!ASSERT_OK(err, "create_ktls_pairs()")) + goto out; + + sent = send(c, msg, sizeof(msg), 0); + if (!ASSERT_OK(err, "send(msg)")) + goto out; + + recvd = recv(p, rcv, sizeof(rcv), 0); + if (!ASSERT_OK(err, "recv(msg)") || + !ASSERT_EQ(recvd, sent, "length mismatch")) + goto out; + + ASSERT_OK(memcmp(msg, rcv, sizeof(msg)), "data mismatch"); + +out: + if (c) + close(c); + if (p) + close(p); +} + +static void test_sockmap_ktls_tx_cork(int family, int sotype, bool push) +{ + int err, off; + int i, j; + int start_push = 0, push_len = 0; + int c = 0, p = 0, one = 1, sent, recvd; + int prog_fd, map_fd; + char msg[12] = "hello world\0"; + char rcv[20] = {0}; + struct test_sockmap_ktls *skel; + + 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; + + skel->bss->cork_byte = sizeof(msg); + if (push) { + start_push = 1; + push_len = 2; + } + skel->bss->push_start = start_push; + skel->bss->push_end = push_len; + + off = sizeof(msg) / 2; + sent = send(c, msg, off, 0); + if (!ASSERT_EQ(sent, off, "send(msg)")) + goto out; + + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1); + if (!ASSERT_EQ(-1, recvd, "expected no data")) + goto out; + + /* send remaining msg */ + sent = send(c, msg + off, sizeof(msg) - off, 0); + if (!ASSERT_EQ(sent, sizeof(msg) - off, "send remaining data")) + goto out; + + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1); + if (!ASSERT_OK(err, "recv(msg)") || + !ASSERT_EQ(recvd, sizeof(msg) + push_len, "check length mismatch")) + goto out; + + for (i = 0, j = 0; i < recvd;) { + /* skip checking the data that has been pushed in */ + if (i >= start_push && i <= start_push + push_len - 1) { + i++; + continue; + } + if (!ASSERT_EQ(rcv[i], msg[j], "data mismatch")) + goto out; + i++; + j++; + } +out: + if (c) + close(c); + if (p) + close(p); + test_sockmap_ktls__destroy(skel); +} + +static void test_sockmap_ktls_tx_no_buf(int family, int sotype, bool push) +{ + int c = -1, p = -1, one = 1, two = 2; + struct test_sockmap_ktls *skel; + unsigned char *data = NULL; + struct msghdr msg = {0}; + struct iovec iov[2]; + int prog_fd, map_fd; + int txrx_buf = 1024; + int iov_length = 8192; + int err; + + 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; + + err = setsockopt(c, SOL_SOCKET, SO_RCVBUFFORCE, &txrx_buf, sizeof(int)); + err |= setsockopt(p, SOL_SOCKET, SO_SNDBUFFORCE, &txrx_buf, sizeof(int)); + if (!ASSERT_OK(err, "set buf limit")) + goto out; + + prog_fd = bpf_program__fd(skel->progs.prog_sk_policy_redir); + 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 = bpf_map_update_elem(map_fd, &two, &p, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p)")) + goto out; + + skel->bss->apply_bytes = 1024; + + err = init_ktls_pairs(c, p); + if (!ASSERT_OK(err, "init_ktls_pairs(c, p)")) + goto out; + + data = calloc(iov_length, sizeof(char)); + if (!data) + goto out; + + iov[0].iov_base = data; + iov[0].iov_len = iov_length; + iov[1].iov_base = data; + iov[1].iov_len = iov_length; + msg.msg_iov = iov; + msg.msg_iovlen = 2; + + for (;;) { + err = sendmsg(c, &msg, MSG_DONTWAIT); + if (err <= 0) + break; + } + +out: + if (data) + free(data); + if (c != -1) + close(c); + if (p != -1) + close(p); + + test_sockmap_ktls__destroy(skel); +} + static void run_tests(int family, enum bpf_map_type map_type) { int map; @@ -153,18 +322,30 @@ static void run_tests(int family, enum bpf_map_type map_type) if (!ASSERT_GE(map, 0, "bpf_map_create")) return; - if (test__start_subtest(fmt_test_name("disconnect_after_delete", family, map_type))) - test_sockmap_ktls_disconnect_after_delete(family, map); if (test__start_subtest(fmt_test_name("update_fails_when_sock_has_ulp", family, map_type))) test_sockmap_ktls_update_fails_when_sock_has_ulp(family, map); close(map); } +static void run_ktls_test(int family, int sotype) +{ + if (test__start_subtest("tls simple offload")) + test_sockmap_ktls_offload(family, sotype); + if (test__start_subtest("tls tx cork")) + test_sockmap_ktls_tx_cork(family, sotype, false); + if (test__start_subtest("tls tx cork with push")) + 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); +} + void test_sockmap_ktls(void) { run_tests(AF_INET, BPF_MAP_TYPE_SOCKMAP); run_tests(AF_INET, BPF_MAP_TYPE_SOCKHASH); run_tests(AF_INET6, BPF_MAP_TYPE_SOCKMAP); run_tests(AF_INET6, BPF_MAP_TYPE_SOCKHASH); + run_ktls_test(AF_INET, SOCK_STREAM); + run_ktls_test(AF_INET6, SOCK_STREAM); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 4ee1148d22be..1d98eee7a2c3 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -1366,237 +1366,6 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map, } } -static void pairs_redir_to_connected(int cli0, int peer0, int cli1, int peer1, - int sock_mapfd, int nop_mapfd, - int verd_mapfd, enum redir_mode mode, - int send_flags) -{ - const char *log_prefix = redir_mode_str(mode); - unsigned int pass; - int err, n; - u32 key; - char b; - - zero_verdict_count(verd_mapfd); - - err = add_to_sockmap(sock_mapfd, peer0, peer1); - if (err) - return; - - if (nop_mapfd >= 0) { - err = add_to_sockmap(nop_mapfd, cli0, cli1); - if (err) - return; - } - - /* Last byte is OOB data when send_flags has MSG_OOB bit set */ - n = xsend(cli1, "ab", 2, send_flags); - if (n >= 0 && n < 2) - FAIL("%s: incomplete send", log_prefix); - if (n < 2) - return; - - key = SK_PASS; - err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass); - if (err) - return; - if (pass != 1) - FAIL("%s: want pass count 1, have %d", log_prefix, pass); - - n = recv_timeout(mode == REDIR_INGRESS ? peer0 : cli0, &b, 1, 0, IO_TIMEOUT_SEC); - if (n < 0) - FAIL_ERRNO("%s: recv_timeout", log_prefix); - if (n == 0) - FAIL("%s: incomplete recv", log_prefix); - - if (send_flags & MSG_OOB) { - /* Check that we can't read OOB while in sockmap */ - errno = 0; - n = recv(peer1, &b, 1, MSG_OOB | MSG_DONTWAIT); - if (n != -1 || errno != EOPNOTSUPP) - FAIL("%s: recv(MSG_OOB): expected EOPNOTSUPP: retval=%d errno=%d", - log_prefix, n, errno); - - /* Remove peer1 from sockmap */ - xbpf_map_delete_elem(sock_mapfd, &(int){ 1 }); - - /* Check that OOB was dropped on redirect */ - errno = 0; - n = recv(peer1, &b, 1, MSG_OOB | MSG_DONTWAIT); - if (n != -1 || errno != EINVAL) - FAIL("%s: recv(MSG_OOB): expected EINVAL: retval=%d errno=%d", - log_prefix, n, errno); - } -} - -static void unix_redir_to_connected(int sotype, int sock_mapfd, - int verd_mapfd, enum redir_mode mode) -{ - int c0, c1, p0, p1; - int sfd[2]; - - if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd)) - return; - c0 = sfd[0], p0 = sfd[1]; - - if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd)) - goto close0; - c1 = sfd[0], p1 = sfd[1]; - - pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, - mode, NO_FLAGS); - - xclose(c1); - xclose(p1); -close0: - xclose(c0); - xclose(p0); -} - -static void unix_skb_redir_to_connected(struct test_sockmap_listen *skel, - struct bpf_map *inner_map, int sotype) -{ - int verdict = bpf_program__fd(skel->progs.prog_skb_verdict); - int verdict_map = bpf_map__fd(skel->maps.verdict_map); - int sock_map = bpf_map__fd(inner_map); - int err; - - err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0); - if (err) - return; - - skel->bss->test_ingress = false; - unix_redir_to_connected(sotype, sock_map, verdict_map, REDIR_EGRESS); - skel->bss->test_ingress = true; - unix_redir_to_connected(sotype, sock_map, verdict_map, REDIR_INGRESS); - - xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT); -} - -static void test_unix_redir(struct test_sockmap_listen *skel, struct bpf_map *map, - int sotype) -{ - const char *family_name, *map_name; - char s[MAX_TEST_NAME]; - - family_name = family_str(AF_UNIX); - map_name = map_type_str(map); - snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__); - if (!test__start_subtest(s)) - return; - unix_skb_redir_to_connected(skel, map, sotype); -} - -/* Returns two connected loopback vsock sockets */ -static int vsock_socketpair_connectible(int sotype, int *v0, int *v1) -{ - return create_pair(AF_VSOCK, sotype | SOCK_NONBLOCK, v0, v1); -} - -static void vsock_unix_redir_connectible(int sock_mapfd, int verd_mapfd, - enum redir_mode mode, int sotype) -{ - const char *log_prefix = redir_mode_str(mode); - char a = 'a', b = 'b'; - int u0, u1, v0, v1; - int sfd[2]; - unsigned int pass; - int err, n; - u32 key; - - zero_verdict_count(verd_mapfd); - - if (socketpair(AF_UNIX, SOCK_STREAM | SOCK_NONBLOCK, 0, sfd)) - return; - - u0 = sfd[0]; - u1 = sfd[1]; - - err = vsock_socketpair_connectible(sotype, &v0, &v1); - if (err) { - FAIL("vsock_socketpair_connectible() failed"); - goto close_uds; - } - - err = add_to_sockmap(sock_mapfd, u0, v0); - if (err) { - FAIL("add_to_sockmap failed"); - goto close_vsock; - } - - n = write(v1, &a, sizeof(a)); - if (n < 0) - FAIL_ERRNO("%s: write", log_prefix); - if (n == 0) - FAIL("%s: incomplete write", log_prefix); - if (n < 1) - goto out; - - n = xrecv_nonblock(mode == REDIR_INGRESS ? u0 : u1, &b, sizeof(b), 0); - if (n < 0) - FAIL("%s: recv() err, errno=%d", log_prefix, errno); - if (n == 0) - FAIL("%s: incomplete recv", log_prefix); - if (b != a) - FAIL("%s: vsock socket map failed, %c != %c", log_prefix, a, b); - - key = SK_PASS; - err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass); - if (err) - goto out; - if (pass != 1) - FAIL("%s: want pass count 1, have %d", log_prefix, pass); -out: - key = 0; - bpf_map_delete_elem(sock_mapfd, &key); - key = 1; - bpf_map_delete_elem(sock_mapfd, &key); - -close_vsock: - close(v0); - close(v1); - -close_uds: - close(u0); - close(u1); -} - -static void vsock_unix_skb_redir_connectible(struct test_sockmap_listen *skel, - struct bpf_map *inner_map, - int sotype) -{ - int verdict = bpf_program__fd(skel->progs.prog_skb_verdict); - int verdict_map = bpf_map__fd(skel->maps.verdict_map); - int sock_map = bpf_map__fd(inner_map); - int err; - - err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0); - if (err) - return; - - skel->bss->test_ingress = false; - vsock_unix_redir_connectible(sock_map, verdict_map, REDIR_EGRESS, sotype); - skel->bss->test_ingress = true; - vsock_unix_redir_connectible(sock_map, verdict_map, REDIR_INGRESS, sotype); - - xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT); -} - -static void test_vsock_redir(struct test_sockmap_listen *skel, struct bpf_map *map) -{ - const char *family_name, *map_name; - char s[MAX_TEST_NAME]; - - family_name = family_str(AF_VSOCK); - map_name = map_type_str(map); - snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__); - if (!test__start_subtest(s)) - return; - - vsock_unix_skb_redir_connectible(skel, map, SOCK_STREAM); - vsock_unix_skb_redir_connectible(skel, map, SOCK_SEQPACKET); -} - static void test_reuseport(struct test_sockmap_listen *skel, struct bpf_map *map, int family, int sotype) { @@ -1637,224 +1406,6 @@ static void test_reuseport(struct test_sockmap_listen *skel, } } -static int inet_socketpair(int family, int type, int *s, int *c) -{ - return create_pair(family, type | SOCK_NONBLOCK, s, c); -} - -static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, - enum redir_mode mode) -{ - int c0, c1, p0, p1; - int err; - - err = inet_socketpair(family, SOCK_DGRAM, &p0, &c0); - if (err) - return; - err = inet_socketpair(family, SOCK_DGRAM, &p1, &c1); - if (err) - goto close_cli0; - - pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, - mode, NO_FLAGS); - - xclose(c1); - xclose(p1); -close_cli0: - xclose(c0); - xclose(p0); -} - -static void udp_skb_redir_to_connected(struct test_sockmap_listen *skel, - struct bpf_map *inner_map, int family) -{ - int verdict = bpf_program__fd(skel->progs.prog_skb_verdict); - int verdict_map = bpf_map__fd(skel->maps.verdict_map); - int sock_map = bpf_map__fd(inner_map); - int err; - - err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0); - if (err) - return; - - skel->bss->test_ingress = false; - udp_redir_to_connected(family, sock_map, verdict_map, REDIR_EGRESS); - skel->bss->test_ingress = true; - udp_redir_to_connected(family, sock_map, verdict_map, REDIR_INGRESS); - - xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT); -} - -static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map, - int family) -{ - const char *family_name, *map_name; - char s[MAX_TEST_NAME]; - - family_name = family_str(family); - map_name = map_type_str(map); - snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__); - if (!test__start_subtest(s)) - return; - udp_skb_redir_to_connected(skel, map, family); -} - -static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, - int verd_mapfd, enum redir_mode mode) -{ - int c0, c1, p0, p1; - int sfd[2]; - int err; - - if (socketpair(AF_UNIX, type | SOCK_NONBLOCK, 0, sfd)) - return; - c0 = sfd[0], p0 = sfd[1]; - - err = inet_socketpair(family, type, &p1, &c1); - if (err) - goto close; - - pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, -1, verd_mapfd, - mode, NO_FLAGS); - - xclose(c1); - xclose(p1); -close: - xclose(c0); - xclose(p0); -} - -static void inet_unix_skb_redir_to_connected(struct test_sockmap_listen *skel, - struct bpf_map *inner_map, int family) -{ - int verdict = bpf_program__fd(skel->progs.prog_skb_verdict); - int verdict_map = bpf_map__fd(skel->maps.verdict_map); - int sock_map = bpf_map__fd(inner_map); - int err; - - err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0); - if (err) - return; - - skel->bss->test_ingress = false; - inet_unix_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map, - REDIR_EGRESS); - inet_unix_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map, - REDIR_EGRESS); - skel->bss->test_ingress = true; - inet_unix_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map, - REDIR_INGRESS); - inet_unix_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map, - REDIR_INGRESS); - - xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT); -} - -static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, - int nop_mapfd, int verd_mapfd, - enum redir_mode mode, int send_flags) -{ - int c0, c1, p0, p1; - int sfd[2]; - int err; - - err = inet_socketpair(family, type, &p0, &c0); - if (err) - return; - - if (socketpair(AF_UNIX, type | SOCK_NONBLOCK, 0, sfd)) - goto close_cli0; - c1 = sfd[0], p1 = sfd[1]; - - pairs_redir_to_connected(c0, p0, c1, p1, sock_mapfd, nop_mapfd, - verd_mapfd, mode, send_flags); - - xclose(c1); - xclose(p1); -close_cli0: - xclose(c0); - xclose(p0); -} - -static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel, - struct bpf_map *inner_map, int family) -{ - int verdict = bpf_program__fd(skel->progs.prog_skb_verdict); - int nop_map = bpf_map__fd(skel->maps.nop_map); - int verdict_map = bpf_map__fd(skel->maps.verdict_map); - int sock_map = bpf_map__fd(inner_map); - int err; - - err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0); - if (err) - return; - - skel->bss->test_ingress = false; - unix_inet_redir_to_connected(family, SOCK_DGRAM, - sock_map, -1, verdict_map, - REDIR_EGRESS, NO_FLAGS); - unix_inet_redir_to_connected(family, SOCK_STREAM, - sock_map, -1, verdict_map, - REDIR_EGRESS, NO_FLAGS); - - unix_inet_redir_to_connected(family, SOCK_DGRAM, - sock_map, nop_map, verdict_map, - REDIR_EGRESS, NO_FLAGS); - unix_inet_redir_to_connected(family, SOCK_STREAM, - sock_map, nop_map, verdict_map, - REDIR_EGRESS, NO_FLAGS); - - /* MSG_OOB not supported by AF_UNIX SOCK_DGRAM */ - unix_inet_redir_to_connected(family, SOCK_STREAM, - sock_map, nop_map, verdict_map, - REDIR_EGRESS, MSG_OOB); - - skel->bss->test_ingress = true; - unix_inet_redir_to_connected(family, SOCK_DGRAM, - sock_map, -1, verdict_map, - REDIR_INGRESS, NO_FLAGS); - unix_inet_redir_to_connected(family, SOCK_STREAM, - sock_map, -1, verdict_map, - REDIR_INGRESS, NO_FLAGS); - - unix_inet_redir_to_connected(family, SOCK_DGRAM, - sock_map, nop_map, verdict_map, - REDIR_INGRESS, NO_FLAGS); - unix_inet_redir_to_connected(family, SOCK_STREAM, - sock_map, nop_map, verdict_map, - REDIR_INGRESS, NO_FLAGS); - - /* MSG_OOB not supported by AF_UNIX SOCK_DGRAM */ - unix_inet_redir_to_connected(family, SOCK_STREAM, - sock_map, nop_map, verdict_map, - REDIR_INGRESS, MSG_OOB); - - xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT); -} - -static void test_udp_unix_redir(struct test_sockmap_listen *skel, struct bpf_map *map, - int family) -{ - const char *family_name, *map_name; - struct netns_obj *netns; - char s[MAX_TEST_NAME]; - - family_name = family_str(family); - map_name = map_type_str(map); - snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__); - if (!test__start_subtest(s)) - return; - - netns = netns_new("sockmap_listen", true); - if (!ASSERT_OK_PTR(netns, "netns_new")) - return; - - inet_unix_skb_redir_to_connected(skel, map, family); - unix_inet_skb_redir_to_connected(skel, map, family); - - netns_free(netns); -} - static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map, int family) { @@ -1863,8 +1414,6 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map, test_redir(skel, map, family, SOCK_STREAM); test_reuseport(skel, map, family, SOCK_STREAM); test_reuseport(skel, map, family, SOCK_DGRAM); - test_udp_redir(skel, map, family); - test_udp_unix_redir(skel, map, family); } void serial_test_sockmap_listen(void) @@ -1880,16 +1429,10 @@ void serial_test_sockmap_listen(void) skel->bss->test_sockmap = true; run_tests(skel, skel->maps.sock_map, AF_INET); run_tests(skel, skel->maps.sock_map, AF_INET6); - test_unix_redir(skel, skel->maps.sock_map, SOCK_DGRAM); - test_unix_redir(skel, skel->maps.sock_map, SOCK_STREAM); - test_vsock_redir(skel, skel->maps.sock_map); skel->bss->test_sockmap = false; run_tests(skel, skel->maps.sock_hash, AF_INET); run_tests(skel, skel->maps.sock_hash, AF_INET6); - test_unix_redir(skel, skel->maps.sock_hash, SOCK_DGRAM); - test_unix_redir(skel, skel->maps.sock_hash, SOCK_STREAM); - test_vsock_redir(skel, skel->maps.sock_hash); test_sockmap_listen__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_redir.c b/tools/testing/selftests/bpf/prog_tests/sockmap_redir.c new file mode 100644 index 000000000000..9c461d93113d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_redir.c @@ -0,0 +1,465 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test for sockmap/sockhash redirection. + * + * BPF_MAP_TYPE_SOCKMAP + * BPF_MAP_TYPE_SOCKHASH + * x + * sk_msg-to-egress + * sk_msg-to-ingress + * sk_skb-to-egress + * sk_skb-to-ingress + * x + * AF_INET, SOCK_STREAM + * AF_INET6, SOCK_STREAM + * AF_INET, SOCK_DGRAM + * AF_INET6, SOCK_DGRAM + * AF_UNIX, SOCK_STREAM + * AF_UNIX, SOCK_DGRAM + * AF_VSOCK, SOCK_STREAM + * AF_VSOCK, SOCK_SEQPACKET + */ + +#include <errno.h> +#include <error.h> +#include <sched.h> +#include <stdio.h> +#include <unistd.h> + +#include <netinet/in.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/un.h> +#include <linux/string.h> +#include <linux/vm_sockets.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "linux/const.h" +#include "test_progs.h" +#include "sockmap_helpers.h" +#include "test_sockmap_redir.skel.h" + +/* The meaning of SUPPORTED is "will redirect packet as expected". + */ +#define SUPPORTED _BITUL(0) + +/* Note on sk_skb-to-ingress ->af_vsock: + * + * Peer socket may receive the packet some time after the return from sendmsg(). + * In a typical usage scenario, recvmsg() will block until the redirected packet + * appears in the destination queue, or timeout if the packet was dropped. By + * that point, the verdict map has already been updated to reflect what has + * happened. + * + * But sk_skb-to-ingress/af_vsock is an unsupported combination, so no recvmsg() + * takes place. Which means we may race the execution of the verdict logic and + * read map_verd before it has been updated, i.e. we might observe + * map_verd[SK_DROP]=0 instead of map_verd[SK_DROP]=1. + * + * This confuses the selftest logic: if there was no packet dropped, where's the + * packet? So here's a heuristic: on map_verd[SK_DROP]=map_verd[SK_PASS]=0 + * (which implies the verdict program has not been ran) just re-read the verdict + * map again. + */ +#define UNSUPPORTED_RACY_VERD _BITUL(1) + +enum prog_type { + SK_MSG_EGRESS, + SK_MSG_INGRESS, + SK_SKB_EGRESS, + SK_SKB_INGRESS, +}; + +enum { + SEND_INNER = 0, + SEND_OUTER, +}; + +enum { + RECV_INNER = 0, + RECV_OUTER, +}; + +struct maps { + int in; + int out; + int verd; +}; + +struct combo_spec { + enum prog_type prog_type; + const char *in, *out; +}; + +struct redir_spec { + const char *name; + int idx_send; + int idx_recv; + enum prog_type prog_type; +}; + +struct socket_spec { + int family; + int sotype; + int send_flags; + int in[2]; + int out[2]; +}; + +static int socket_spec_pairs(struct socket_spec *s) +{ + return create_socket_pairs(s->family, s->sotype, + &s->in[0], &s->out[0], + &s->in[1], &s->out[1]); +} + +static void socket_spec_close(struct socket_spec *s) +{ + xclose(s->in[0]); + xclose(s->in[1]); + xclose(s->out[0]); + xclose(s->out[1]); +} + +static void get_redir_params(struct redir_spec *redir, + struct test_sockmap_redir *skel, int *prog_fd, + enum bpf_attach_type *attach_type, + int *redirect_flags) +{ + enum prog_type type = redir->prog_type; + struct bpf_program *prog; + bool sk_msg; + + sk_msg = type == SK_MSG_INGRESS || type == SK_MSG_EGRESS; + prog = sk_msg ? skel->progs.prog_msg_verdict : skel->progs.prog_skb_verdict; + + *prog_fd = bpf_program__fd(prog); + *attach_type = sk_msg ? BPF_SK_MSG_VERDICT : BPF_SK_SKB_VERDICT; + + if (type == SK_MSG_INGRESS || type == SK_SKB_INGRESS) + *redirect_flags = BPF_F_INGRESS; + else + *redirect_flags = 0; +} + +static void try_recv(const char *prefix, int fd, int flags, bool expect_success) +{ + ssize_t n; + char buf; + + errno = 0; + n = recv(fd, &buf, 1, flags); + if (n < 0 && expect_success) + FAIL_ERRNO("%s: unexpected failure: retval=%zd", prefix, n); + if (!n && !expect_success) + FAIL("%s: expected failure: retval=%zd", prefix, n); +} + +static void handle_unsupported(int sd_send, int sd_peer, int sd_in, int sd_out, + int sd_recv, int map_verd, int status) +{ + unsigned int drop, pass; + char recv_buf; + ssize_t n; + +get_verdict: + if (xbpf_map_lookup_elem(map_verd, &u32(SK_DROP), &drop) || + xbpf_map_lookup_elem(map_verd, &u32(SK_PASS), &pass)) + return; + + if (pass == 0 && drop == 0 && (status & UNSUPPORTED_RACY_VERD)) { + sched_yield(); + goto get_verdict; + } + + if (pass != 0) { + FAIL("unsupported: wanted verdict pass 0, have %u", pass); + return; + } + + /* If nothing was dropped, packet should have reached the peer */ + if (drop == 0) { + errno = 0; + n = recv_timeout(sd_peer, &recv_buf, 1, 0, IO_TIMEOUT_SEC); + if (n != 1) + FAIL_ERRNO("unsupported: packet missing, retval=%zd", n); + } + + /* Ensure queues are empty */ + try_recv("bpf.recv(sd_send)", sd_send, MSG_DONTWAIT, false); + if (sd_in != sd_send) + try_recv("bpf.recv(sd_in)", sd_in, MSG_DONTWAIT, false); + + try_recv("bpf.recv(sd_out)", sd_out, MSG_DONTWAIT, false); + if (sd_recv != sd_out) + try_recv("bpf.recv(sd_recv)", sd_recv, MSG_DONTWAIT, false); +} + +static void test_send_redir_recv(int sd_send, int send_flags, int sd_peer, + int sd_in, int sd_out, int sd_recv, + struct maps *maps, int status) +{ + unsigned int drop, pass; + char *send_buf = "ab"; + char recv_buf = '\0'; + ssize_t n, len = 1; + + /* Zero out the verdict map */ + if (xbpf_map_update_elem(maps->verd, &u32(SK_DROP), &u32(0), BPF_ANY) || + xbpf_map_update_elem(maps->verd, &u32(SK_PASS), &u32(0), BPF_ANY)) + return; + + if (xbpf_map_update_elem(maps->in, &u32(0), &u64(sd_in), BPF_NOEXIST)) + return; + + if (xbpf_map_update_elem(maps->out, &u32(0), &u64(sd_out), BPF_NOEXIST)) + goto del_in; + + /* Last byte is OOB data when send_flags has MSG_OOB bit set */ + if (send_flags & MSG_OOB) + len++; + n = send(sd_send, send_buf, len, send_flags); + if (n >= 0 && n < len) + FAIL("incomplete send"); + if (n < 0) { + /* sk_msg redirect combo not supported? */ + if (status & SUPPORTED || errno != EACCES) + FAIL_ERRNO("send"); + goto out; + } + + if (!(status & SUPPORTED)) { + handle_unsupported(sd_send, sd_peer, sd_in, sd_out, sd_recv, + maps->verd, status); + goto out; + } + + errno = 0; + n = recv_timeout(sd_recv, &recv_buf, 1, 0, IO_TIMEOUT_SEC); + if (n != 1) { + FAIL_ERRNO("recv_timeout()"); + goto out; + } + + /* Check verdict _after_ recv(); af_vsock may need time to catch up */ + if (xbpf_map_lookup_elem(maps->verd, &u32(SK_DROP), &drop) || + xbpf_map_lookup_elem(maps->verd, &u32(SK_PASS), &pass)) + goto out; + + if (drop != 0 || pass != 1) + FAIL("unexpected verdict drop/pass: wanted 0/1, have %u/%u", + drop, pass); + + if (recv_buf != send_buf[0]) + FAIL("recv(): payload check, %02x != %02x", recv_buf, send_buf[0]); + + if (send_flags & MSG_OOB) { + /* Fail reading OOB while in sockmap */ + try_recv("bpf.recv(sd_out, MSG_OOB)", sd_out, + MSG_OOB | MSG_DONTWAIT, false); + + /* Remove sd_out from sockmap */ + xbpf_map_delete_elem(maps->out, &u32(0)); + + /* Check that OOB was dropped on redirect */ + try_recv("recv(sd_out, MSG_OOB)", sd_out, + MSG_OOB | MSG_DONTWAIT, false); + + goto del_in; + } +out: + xbpf_map_delete_elem(maps->out, &u32(0)); +del_in: + xbpf_map_delete_elem(maps->in, &u32(0)); +} + +static int is_redir_supported(enum prog_type type, const char *in, + const char *out) +{ + /* Matching based on strings returned by socket_kind_to_str(): + * tcp4, udp4, tcp6, udp6, u_str, u_dgr, v_str, v_seq + * Plus a wildcard: any + * Not in use: u_seq, v_dgr + */ + struct combo_spec *c, combos[] = { + /* Send to local: TCP -> any, but vsock */ + { SK_MSG_INGRESS, "tcp", "tcp" }, + { SK_MSG_INGRESS, "tcp", "udp" }, + { SK_MSG_INGRESS, "tcp", "u_str" }, + { SK_MSG_INGRESS, "tcp", "u_dgr" }, + + /* Send to egress: TCP -> TCP */ + { SK_MSG_EGRESS, "tcp", "tcp" }, + + /* Ingress to egress: any -> any */ + { SK_SKB_EGRESS, "any", "any" }, + + /* Ingress to local: any -> any, but vsock */ + { SK_SKB_INGRESS, "any", "tcp" }, + { SK_SKB_INGRESS, "any", "udp" }, + { SK_SKB_INGRESS, "any", "u_str" }, + { SK_SKB_INGRESS, "any", "u_dgr" }, + }; + + for (c = combos; c < combos + ARRAY_SIZE(combos); c++) { + if (c->prog_type == type && + (!strcmp(c->in, "any") || strstarts(in, c->in)) && + (!strcmp(c->out, "any") || strstarts(out, c->out))) + return SUPPORTED; + } + + return 0; +} + +static int get_support_status(enum prog_type type, const char *in, + const char *out) +{ + int status = is_redir_supported(type, in, out); + + if (type == SK_SKB_INGRESS && strstarts(out, "v_")) + status |= UNSUPPORTED_RACY_VERD; + + return status; +} + +static void test_socket(enum bpf_map_type type, struct redir_spec *redir, + struct maps *maps, struct socket_spec *s_in, + struct socket_spec *s_out) +{ + int fd_in, fd_out, fd_send, fd_peer, fd_recv, flags, status; + const char *in_str, *out_str; + char s[MAX_TEST_NAME]; + + fd_in = s_in->in[0]; + fd_out = s_out->out[0]; + fd_send = s_in->in[redir->idx_send]; + fd_peer = s_in->in[redir->idx_send ^ 1]; + fd_recv = s_out->out[redir->idx_recv]; + flags = s_in->send_flags; + + in_str = socket_kind_to_str(fd_in); + out_str = socket_kind_to_str(fd_out); + status = get_support_status(redir->prog_type, in_str, out_str); + + snprintf(s, sizeof(s), + "%-4s %-17s %-5s %s %-5s%6s", + /* hash sk_skb-to-ingress u_str → v_str (OOB) */ + type == BPF_MAP_TYPE_SOCKMAP ? "map" : "hash", + redir->name, + in_str, + status & SUPPORTED ? "→" : " ", + out_str, + (flags & MSG_OOB) ? "(OOB)" : ""); + + if (!test__start_subtest(s)) + return; + + test_send_redir_recv(fd_send, flags, fd_peer, fd_in, fd_out, fd_recv, + maps, status); +} + +static void test_redir(enum bpf_map_type type, struct redir_spec *redir, + struct maps *maps) +{ + struct socket_spec *s, sockets[] = { + { AF_INET, SOCK_STREAM }, + // { AF_INET, SOCK_STREAM, MSG_OOB }, /* Known to be broken */ + { AF_INET6, SOCK_STREAM }, + { AF_INET, SOCK_DGRAM }, + { AF_INET6, SOCK_DGRAM }, + { AF_UNIX, SOCK_STREAM }, + { AF_UNIX, SOCK_STREAM, MSG_OOB }, + { AF_UNIX, SOCK_DGRAM }, + // { AF_UNIX, SOCK_SEQPACKET}, /* Unsupported BPF_MAP_UPDATE_ELEM */ + { AF_VSOCK, SOCK_STREAM }, + // { AF_VSOCK, SOCK_DGRAM }, /* Unsupported socket() */ + { AF_VSOCK, SOCK_SEQPACKET }, + }; + + for (s = sockets; s < sockets + ARRAY_SIZE(sockets); s++) + if (socket_spec_pairs(s)) + goto out; + + /* Intra-proto */ + for (s = sockets; s < sockets + ARRAY_SIZE(sockets); s++) + test_socket(type, redir, maps, s, s); + + /* Cross-proto */ + for (int i = 0; i < ARRAY_SIZE(sockets); i++) { + for (int j = 0; j < ARRAY_SIZE(sockets); j++) { + struct socket_spec *out = &sockets[j]; + struct socket_spec *in = &sockets[i]; + + /* Skip intra-proto and between variants */ + if (out->send_flags || + (in->family == out->family && + in->sotype == out->sotype)) + continue; + + test_socket(type, redir, maps, in, out); + } + } +out: + while (--s >= sockets) + socket_spec_close(s); +} + +static void test_map(enum bpf_map_type type) +{ + struct redir_spec *r, redirs[] = { + { "sk_msg-to-ingress", SEND_INNER, RECV_INNER, SK_MSG_INGRESS }, + { "sk_msg-to-egress", SEND_INNER, RECV_OUTER, SK_MSG_EGRESS }, + { "sk_skb-to-egress", SEND_OUTER, RECV_OUTER, SK_SKB_EGRESS }, + { "sk_skb-to-ingress", SEND_OUTER, RECV_INNER, SK_SKB_INGRESS }, + }; + + for (r = redirs; r < redirs + ARRAY_SIZE(redirs); r++) { + enum bpf_attach_type attach_type; + struct test_sockmap_redir *skel; + struct maps maps; + int prog_fd; + + skel = test_sockmap_redir__open_and_load(); + if (!skel) { + FAIL("open_and_load"); + return; + } + + switch (type) { + case BPF_MAP_TYPE_SOCKMAP: + maps.in = bpf_map__fd(skel->maps.nop_map); + maps.out = bpf_map__fd(skel->maps.sock_map); + break; + case BPF_MAP_TYPE_SOCKHASH: + maps.in = bpf_map__fd(skel->maps.nop_hash); + maps.out = bpf_map__fd(skel->maps.sock_hash); + break; + default: + FAIL("Unsupported bpf_map_type"); + return; + } + + skel->bss->redirect_type = type; + maps.verd = bpf_map__fd(skel->maps.verdict_map); + get_redir_params(r, skel, &prog_fd, &attach_type, + &skel->bss->redirect_flags); + + if (xbpf_prog_attach(prog_fd, maps.in, attach_type, 0)) + return; + + test_redir(type, r, &maps); + + if (xbpf_prog_detach2(prog_fd, maps.in, attach_type)) + return; + + test_sockmap_redir__destroy(skel); + } +} + +void serial_test_sockmap_redir(void) +{ + test_map(BPF_MAP_TYPE_SOCKMAP); + test_map(BPF_MAP_TYPE_SOCKHASH); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index c85798966aec..76d72a59365e 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -56,6 +56,8 @@ #define MAC_DST_FWD "00:11:22:33:44:55" #define MAC_DST "00:22:33:44:55:66" +#define MAC_SRC_FWD "00:33:44:55:66:77" +#define MAC_SRC "00:44:55:66:77:88" #define IFADDR_STR_LEN 18 #define PING_ARGS "-i 0.2 -c 3 -w 10 -q" @@ -207,11 +209,10 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) int err; if (result->dev_mode == MODE_VETH) { - SYS(fail, "ip link add src type veth peer name src_fwd"); - SYS(fail, "ip link add dst type veth peer name dst_fwd"); - - SYS(fail, "ip link set dst_fwd address " MAC_DST_FWD); - SYS(fail, "ip link set dst address " MAC_DST); + SYS(fail, "ip link add src address " MAC_SRC " type veth " + "peer name src_fwd address " MAC_SRC_FWD); + SYS(fail, "ip link add dst address " MAC_DST " type veth " + "peer name dst_fwd address " MAC_DST_FWD); } else if (result->dev_mode == MODE_NETKIT) { err = create_netkit(NETKIT_L3, "src", "src_fwd"); if (!ASSERT_OK(err, "create_ifindex_src")) diff --git a/tools/testing/selftests/bpf/prog_tests/test_btf_ext.c b/tools/testing/selftests/bpf/prog_tests/test_btf_ext.c new file mode 100644 index 000000000000..7d1b478c99a0 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_btf_ext.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms Inc. */ +#include <test_progs.h> +#include "test_btf_ext.skel.h" +#include "btf_helpers.h" + +static void subtest_line_func_info(void) +{ + struct test_btf_ext *skel; + struct bpf_prog_info info; + struct bpf_line_info line_info[128], *libbpf_line_info; + struct bpf_func_info func_info[128], *libbpf_func_info; + __u32 info_len = sizeof(info), libbbpf_line_info_cnt, libbbpf_func_info_cnt; + int err, fd; + + skel = test_btf_ext__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + fd = bpf_program__fd(skel->progs.global_func); + + memset(&info, 0, sizeof(info)); + info.line_info = ptr_to_u64(&line_info); + info.nr_line_info = sizeof(line_info); + info.line_info_rec_size = sizeof(*line_info); + err = bpf_prog_get_info_by_fd(fd, &info, &info_len); + if (!ASSERT_OK(err, "prog_line_info")) + goto out; + + libbpf_line_info = bpf_program__line_info(skel->progs.global_func); + libbbpf_line_info_cnt = bpf_program__line_info_cnt(skel->progs.global_func); + + memset(&info, 0, sizeof(info)); + info.func_info = ptr_to_u64(&func_info); + info.nr_func_info = sizeof(func_info); + info.func_info_rec_size = sizeof(*func_info); + err = bpf_prog_get_info_by_fd(fd, &info, &info_len); + if (!ASSERT_OK(err, "prog_func_info")) + goto out; + + libbpf_func_info = bpf_program__func_info(skel->progs.global_func); + libbbpf_func_info_cnt = bpf_program__func_info_cnt(skel->progs.global_func); + + if (!ASSERT_OK_PTR(libbpf_line_info, "bpf_program__line_info")) + goto out; + if (!ASSERT_EQ(libbbpf_line_info_cnt, info.nr_line_info, "line_info_cnt")) + goto out; + if (!ASSERT_OK_PTR(libbpf_func_info, "bpf_program__func_info")) + goto out; + if (!ASSERT_EQ(libbbpf_func_info_cnt, info.nr_func_info, "func_info_cnt")) + goto out; + ASSERT_MEMEQ(libbpf_line_info, line_info, libbbpf_line_info_cnt * sizeof(*line_info), + "line_info"); + ASSERT_MEMEQ(libbpf_func_info, func_info, libbbpf_func_info_cnt * sizeof(*func_info), + "func_info"); +out: + test_btf_ext__destroy(skel); +} + +void test_btf_ext(void) +{ + if (test__start_subtest("line_func_info")) + subtest_line_func_info(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c index a95b42bf744a..47b56c258f3f 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_veristat.c +++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c @@ -63,6 +63,9 @@ static void test_set_global_vars_succeeds(void) " -G \"var_eb = EB2\" "\ " -G \"var_ec = EC2\" "\ " -G \"var_b = 1\" "\ + " -G \"struct1.struct2.u.var_u8 = 170\" "\ + " -G \"union1.struct3.var_u8_l = 0xaa\" "\ + " -G \"union1.struct3.var_u8_h = 0xaa\" "\ "-vl2 > %s", fix->veristat, fix->tmpfile); read(fix->fd, fix->output, fix->sz); @@ -78,6 +81,8 @@ static void test_set_global_vars_succeeds(void) __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"); out: teardown_fixture(fix); diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index e66a57970d28..c9da06741104 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -14,6 +14,7 @@ #include "verifier_bounds_deduction_non_const.skel.h" #include "verifier_bounds_mix_sign_unsign.skel.h" #include "verifier_bpf_get_stack.skel.h" +#include "verifier_bpf_trap.skel.h" #include "verifier_bswap.skel.h" #include "verifier_btf_ctx_access.skel.h" #include "verifier_btf_unreliable_prog.skel.h" @@ -148,6 +149,7 @@ void test_verifier_bounds_deduction(void) { RUN(verifier_bounds_deduction); void test_verifier_bounds_deduction_non_const(void) { RUN(verifier_bounds_deduction_non_const); } void test_verifier_bounds_mix_sign_unsign(void) { RUN(verifier_bounds_mix_sign_unsign); } void test_verifier_bpf_get_stack(void) { RUN(verifier_bpf_get_stack); } +void test_verifier_bpf_trap(void) { RUN(verifier_bpf_trap); } void test_verifier_bswap(void) { RUN(verifier_bswap); } void test_verifier_btf_ctx_access(void) { RUN(verifier_btf_ctx_access); } void test_verifier_btf_unreliable_prog(void) { RUN(verifier_btf_unreliable_prog); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index 3d47878ef6bf..19f92affc2da 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -351,9 +351,10 @@ void test_xdp_metadata(void) struct xdp_metadata2 *bpf_obj2 = NULL; struct xdp_metadata *bpf_obj = NULL; struct bpf_program *new_prog, *prog; + struct bpf_devmap_val devmap_e = {}; + struct bpf_map *prog_arr, *devmap; struct nstoken *tok = NULL; __u32 queue_id = QUEUE_ID; - struct bpf_map *prog_arr; struct xsk tx_xsk = {}; struct xsk rx_xsk = {}; __u32 val, key = 0; @@ -409,6 +410,13 @@ void test_xdp_metadata(void) bpf_program__set_ifindex(prog, rx_ifindex); bpf_program__set_flags(prog, BPF_F_XDP_DEV_BOUND_ONLY); + /* Make sure we can load a dev-bound program that performs + * XDP_REDIRECT into a devmap. + */ + new_prog = bpf_object__find_program_by_name(bpf_obj->obj, "redirect"); + bpf_program__set_ifindex(new_prog, rx_ifindex); + bpf_program__set_flags(new_prog, BPF_F_XDP_DEV_BOUND_ONLY); + if (!ASSERT_OK(xdp_metadata__load(bpf_obj), "load skeleton")) goto out; @@ -423,6 +431,18 @@ void test_xdp_metadata(void) "update prog_arr")) goto out; + /* Make sure we can't add dev-bound programs to devmaps. */ + devmap = bpf_object__find_map_by_name(bpf_obj->obj, "dev_map"); + if (!ASSERT_OK_PTR(devmap, "no dev_map found")) + goto out; + + devmap_e.bpf_prog.fd = val; + if (!ASSERT_ERR(bpf_map__update_elem(devmap, &key, sizeof(key), + &devmap_e, sizeof(devmap_e), + BPF_ANY), + "update dev_map")) + goto out; + /* Attach BPF program to RX interface. */ ret = bpf_xdp_attach(rx_ifindex, diff --git a/tools/testing/selftests/bpf/progs/bench_sockmap_prog.c b/tools/testing/selftests/bpf/progs/bench_sockmap_prog.c new file mode 100644 index 000000000000..079bf3794b3a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bench_sockmap_prog.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +long process_byte = 0; +int verdict_dir = 0; +int dropped = 0; +int pkt_size = 0; +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_rx SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map_tx SEC(".maps"); + +SEC("sk_skb/stream_parser") +int prog_skb_parser(struct __sk_buff *skb) +{ + return pkt_size; +} + +SEC("sk_skb/stream_verdict") +int prog_skb_verdict(struct __sk_buff *skb) +{ + int one = 1; + int ret = bpf_sk_redirect_map(skb, &sock_map_rx, one, verdict_dir); + + if (ret == SK_DROP) + dropped++; + __sync_fetch_and_add(&process_byte, skb->len); + return ret; +} + +SEC("sk_skb/stream_verdict") +int prog_skb_pass(struct __sk_buff *skb) +{ + __sync_fetch_and_add(&process_byte, skb->len); + return SK_PASS; +} + +SEC("sk_msg") +int prog_skmsg_verdict(struct sk_msg_md *msg) +{ + int one = 1; + + __sync_fetch_and_add(&process_byte, msg->size); + return bpf_msg_redirect_map(msg, &sock_map_tx, one, verdict_dir); +} + +SEC("sk_msg") +int prog_skmsg_pass(struct sk_msg_md *msg) +{ + __sync_fetch_and_add(&process_byte, msg->size); + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h index fb8dc0768999..d67466c1ff77 100644 --- a/tools/testing/selftests/bpf/bpf_arena_spin_lock.h +++ b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h @@ -32,6 +32,7 @@ extern unsigned long CONFIG_NR_CPUS __kconfig; struct __qspinlock { union { atomic_t val; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ struct { u8 locked; u8 pending; @@ -40,6 +41,17 @@ struct __qspinlock { u16 locked_pending; u16 tail; }; +#else + struct { + u16 tail; + u16 locked_pending; + }; + struct { + u8 reserved[2]; + u8 pending; + u8 locked; + }; +#endif }; }; @@ -95,9 +107,6 @@ struct arena_qnode { #define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET) #define _Q_PENDING_VAL (1U << _Q_PENDING_OFFSET) -#define likely(x) __builtin_expect(!!(x), 1) -#define unlikely(x) __builtin_expect(!!(x), 0) - struct arena_qnode __arena qnodes[_Q_MAX_CPUS][_Q_MAX_NODES]; static inline u32 encode_tail(int cpu, int idx) diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index 863df7c0fdd0..6e208e24ba3b 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -225,8 +225,9 @@ #define CAN_USE_BPF_ST #endif -#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \ - (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) +#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \ + (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \ + (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) #define CAN_USE_LOAD_ACQ_STORE_REL #endif diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h b/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h new file mode 100644 index 000000000000..3754f581b328 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _BPF_QDISC_COMMON_H +#define _BPF_QDISC_COMMON_H + +#define NET_XMIT_SUCCESS 0x00 +#define NET_XMIT_DROP 0x01 /* skb dropped */ +#define NET_XMIT_CN 0x02 /* congestion notification */ + +#define TC_PRIO_CONTROL 7 +#define TC_PRIO_MAX 15 + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) + +struct bpf_sk_buff_ptr; + +static struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb) +{ + return (struct qdisc_skb_cb *)skb->cb; +} + +static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb) +{ + return qdisc_skb_cb(skb)->pkt_len; +} + +#endif diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c new file mode 100644 index 000000000000..f188062ed730 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include "bpf_experimental.h" +#include "bpf_qdisc_common.h" + +char _license[] SEC("license") = "GPL"; + +SEC("struct_ops") +int BPF_PROG(bpf_qdisc_test_enqueue, struct sk_buff *skb, struct Qdisc *sch, + struct bpf_sk_buff_ptr *to_free) +{ + bpf_qdisc_skb_drop(skb, to_free); + return NET_XMIT_DROP; +} + +SEC("struct_ops") +struct sk_buff *BPF_PROG(bpf_qdisc_test_dequeue, struct Qdisc *sch) +{ + return NULL; +} + +SEC("struct_ops") +void BPF_PROG(bpf_qdisc_test_reset, struct Qdisc *sch) +{ +} + +SEC("struct_ops") +void BPF_PROG(bpf_qdisc_test_destroy, struct Qdisc *sch) +{ +} + +SEC(".struct_ops") +struct Qdisc_ops test = { + .enqueue = (void *)bpf_qdisc_test_enqueue, + .dequeue = (void *)bpf_qdisc_test_dequeue, + .reset = (void *)bpf_qdisc_test_reset, + .destroy = (void *)bpf_qdisc_test_destroy, + .id = "bpf_qdisc_test", +}; + diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c new file mode 100644 index 000000000000..1de2be3e370b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include "bpf_experimental.h" +#include "bpf_qdisc_common.h" + +char _license[] SEC("license") = "GPL"; + +struct skb_node { + struct sk_buff __kptr * skb; + struct bpf_list_node node; +}; + +private(A) struct bpf_spin_lock q_fifo_lock; +private(A) struct bpf_list_head q_fifo __contains(skb_node, node); + +bool init_called; + +SEC("struct_ops/bpf_fifo_enqueue") +int BPF_PROG(bpf_fifo_enqueue, struct sk_buff *skb, struct Qdisc *sch, + struct bpf_sk_buff_ptr *to_free) +{ + struct skb_node *skbn; + u32 pkt_len; + + if (sch->q.qlen == sch->limit) + goto drop; + + skbn = bpf_obj_new(typeof(*skbn)); + if (!skbn) + goto drop; + + pkt_len = qdisc_pkt_len(skb); + + sch->q.qlen++; + skb = bpf_kptr_xchg(&skbn->skb, skb); + if (skb) + bpf_qdisc_skb_drop(skb, to_free); + + bpf_spin_lock(&q_fifo_lock); + bpf_list_push_back(&q_fifo, &skbn->node); + bpf_spin_unlock(&q_fifo_lock); + + sch->qstats.backlog += pkt_len; + return NET_XMIT_SUCCESS; +drop: + bpf_qdisc_skb_drop(skb, to_free); + return NET_XMIT_DROP; +} + +SEC("struct_ops/bpf_fifo_dequeue") +struct sk_buff *BPF_PROG(bpf_fifo_dequeue, struct Qdisc *sch) +{ + struct bpf_list_node *node; + struct sk_buff *skb = NULL; + struct skb_node *skbn; + + bpf_spin_lock(&q_fifo_lock); + node = bpf_list_pop_front(&q_fifo); + bpf_spin_unlock(&q_fifo_lock); + if (!node) + return NULL; + + skbn = container_of(node, struct skb_node, node); + skb = bpf_kptr_xchg(&skbn->skb, skb); + bpf_obj_drop(skbn); + if (!skb) + return NULL; + + sch->qstats.backlog -= qdisc_pkt_len(skb); + bpf_qdisc_bstats_update(sch, skb); + sch->q.qlen--; + + return skb; +} + +SEC("struct_ops/bpf_fifo_init") +int BPF_PROG(bpf_fifo_init, struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + sch->limit = 1000; + init_called = true; + return 0; +} + +SEC("struct_ops/bpf_fifo_reset") +void BPF_PROG(bpf_fifo_reset, struct Qdisc *sch) +{ + struct bpf_list_node *node; + struct skb_node *skbn; + int i; + + bpf_for(i, 0, sch->q.qlen) { + struct sk_buff *skb = NULL; + + bpf_spin_lock(&q_fifo_lock); + node = bpf_list_pop_front(&q_fifo); + bpf_spin_unlock(&q_fifo_lock); + + if (!node) + break; + + skbn = container_of(node, struct skb_node, node); + skb = bpf_kptr_xchg(&skbn->skb, skb); + if (skb) + bpf_kfree_skb(skb); + bpf_obj_drop(skbn); + } + sch->q.qlen = 0; +} + +SEC("struct_ops") +void BPF_PROG(bpf_fifo_destroy, struct Qdisc *sch) +{ +} + +SEC(".struct_ops") +struct Qdisc_ops fifo = { + .enqueue = (void *)bpf_fifo_enqueue, + .dequeue = (void *)bpf_fifo_dequeue, + .init = (void *)bpf_fifo_init, + .reset = (void *)bpf_fifo_reset, + .destroy = (void *)bpf_fifo_destroy, + .id = "bpf_fifo", +}; + diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c new file mode 100644 index 000000000000..1a3233a275c7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c @@ -0,0 +1,756 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* bpf_fq is intended for testing the bpf qdisc infrastructure and not a direct + * copy of sch_fq. bpf_fq implements the scheduling algorithm of sch_fq before + * 29f834aa326e ("net_sched: sch_fq: add 3 bands and WRR scheduling") was + * introduced. It gives each flow a fair chance to transmit packets in a + * round-robin fashion. Note that for flow pacing, bpf_fq currently only + * respects skb->tstamp but not skb->sk->sk_pacing_rate. In addition, if there + * are multiple bpf_fq instances, they will have a shared view of flows and + * configuration since some key data structure such as fq_prio_flows, + * fq_nonprio_flows, and fq_bpf_data are global. + * + * To use bpf_fq alone without running selftests, use the following commands. + * + * 1. Register bpf_fq to the kernel + * bpftool struct_ops register bpf_qdisc_fq.bpf.o /sys/fs/bpf + * 2. Add bpf_fq to an interface + * tc qdisc add dev <interface name> root handle <handle> bpf_fq + * 3. Delete bpf_fq attached to the interface + * tc qdisc delete dev <interface name> root + * 4. Unregister bpf_fq + * bpftool struct_ops unregister name fq + * + * The qdisc name, bpf_fq, used in tc commands is defined by Qdisc_ops.id. + * The struct_ops_map_name, fq, used in the bpftool command is the name of the + * Qdisc_ops. + * + * SEC(".struct_ops") + * struct Qdisc_ops fq = { + * ... + * .id = "bpf_fq", + * }; + */ + +#include <vmlinux.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include "bpf_experimental.h" +#include "bpf_qdisc_common.h" + +char _license[] SEC("license") = "GPL"; + +#define NSEC_PER_USEC 1000L +#define NSEC_PER_SEC 1000000000L + +#define NUM_QUEUE (1 << 20) + +struct fq_bpf_data { + u32 quantum; + u32 initial_quantum; + u32 flow_refill_delay; + u32 flow_plimit; + u64 horizon; + u32 orphan_mask; + u32 timer_slack; + u64 time_next_delayed_flow; + u64 unthrottle_latency_ns; + u8 horizon_drop; + u32 new_flow_cnt; + u32 old_flow_cnt; + u64 ktime_cache; +}; + +enum { + CLS_RET_PRIO = 0, + CLS_RET_NONPRIO = 1, + CLS_RET_ERR = 2, +}; + +struct skb_node { + u64 tstamp; + struct sk_buff __kptr * skb; + struct bpf_rb_node node; +}; + +struct fq_flow_node { + int credit; + u32 qlen; + u64 age; + u64 time_next_packet; + struct bpf_list_node list_node; + struct bpf_rb_node rb_node; + struct bpf_rb_root queue __contains(skb_node, node); + struct bpf_spin_lock lock; + struct bpf_refcount refcount; +}; + +struct dequeue_nonprio_ctx { + bool stop_iter; + u64 expire; + u64 now; +}; + +struct remove_flows_ctx { + bool gc_only; + u32 reset_cnt; + u32 reset_max; +}; + +struct unset_throttled_flows_ctx { + bool unset_all; + u64 now; +}; + +struct fq_stashed_flow { + struct fq_flow_node __kptr * flow; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u64); + __type(value, struct fq_stashed_flow); + __uint(max_entries, NUM_QUEUE); +} fq_nonprio_flows SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u64); + __type(value, struct fq_stashed_flow); + __uint(max_entries, 1); +} fq_prio_flows SEC(".maps"); + +private(A) struct bpf_spin_lock fq_delayed_lock; +private(A) struct bpf_rb_root fq_delayed __contains(fq_flow_node, rb_node); + +private(B) struct bpf_spin_lock fq_new_flows_lock; +private(B) struct bpf_list_head fq_new_flows __contains(fq_flow_node, list_node); + +private(C) struct bpf_spin_lock fq_old_flows_lock; +private(C) struct bpf_list_head fq_old_flows __contains(fq_flow_node, list_node); + +private(D) struct fq_bpf_data q; + +/* Wrapper for bpf_kptr_xchg that expects NULL dst */ +static void bpf_kptr_xchg_back(void *map_val, void *ptr) +{ + void *ret; + + ret = bpf_kptr_xchg(map_val, ptr); + if (ret) + bpf_obj_drop(ret); +} + +static bool skbn_tstamp_less(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct skb_node *skbn_a; + struct skb_node *skbn_b; + + skbn_a = container_of(a, struct skb_node, node); + skbn_b = container_of(b, struct skb_node, node); + + return skbn_a->tstamp < skbn_b->tstamp; +} + +static bool fn_time_next_packet_less(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct fq_flow_node *flow_a; + struct fq_flow_node *flow_b; + + flow_a = container_of(a, struct fq_flow_node, rb_node); + flow_b = container_of(b, struct fq_flow_node, rb_node); + + return flow_a->time_next_packet < flow_b->time_next_packet; +} + +static void +fq_flows_add_head(struct bpf_list_head *head, struct bpf_spin_lock *lock, + struct fq_flow_node *flow, u32 *flow_cnt) +{ + bpf_spin_lock(lock); + bpf_list_push_front(head, &flow->list_node); + bpf_spin_unlock(lock); + *flow_cnt += 1; +} + +static void +fq_flows_add_tail(struct bpf_list_head *head, struct bpf_spin_lock *lock, + struct fq_flow_node *flow, u32 *flow_cnt) +{ + bpf_spin_lock(lock); + bpf_list_push_back(head, &flow->list_node); + bpf_spin_unlock(lock); + *flow_cnt += 1; +} + +static void +fq_flows_remove_front(struct bpf_list_head *head, struct bpf_spin_lock *lock, + struct bpf_list_node **node, u32 *flow_cnt) +{ + bpf_spin_lock(lock); + *node = bpf_list_pop_front(head); + bpf_spin_unlock(lock); + *flow_cnt -= 1; +} + +static bool +fq_flows_is_empty(struct bpf_list_head *head, struct bpf_spin_lock *lock) +{ + struct bpf_list_node *node; + + bpf_spin_lock(lock); + node = bpf_list_pop_front(head); + if (node) { + bpf_list_push_front(head, node); + bpf_spin_unlock(lock); + return false; + } + bpf_spin_unlock(lock); + + return true; +} + +/* flow->age is used to denote the state of the flow (not-detached, detached, throttled) + * as well as the timestamp when the flow is detached. + * + * 0: not-detached + * 1 - (~0ULL-1): detached + * ~0ULL: throttled + */ +static void fq_flow_set_detached(struct fq_flow_node *flow) +{ + flow->age = bpf_jiffies64(); +} + +static bool fq_flow_is_detached(struct fq_flow_node *flow) +{ + return flow->age != 0 && flow->age != ~0ULL; +} + +static bool sk_listener(struct sock *sk) +{ + return (1 << sk->__sk_common.skc_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); +} + +static void fq_gc(void); + +static int fq_new_flow(void *flow_map, struct fq_stashed_flow **sflow, u64 hash) +{ + struct fq_stashed_flow tmp = {}; + struct fq_flow_node *flow; + int ret; + + flow = bpf_obj_new(typeof(*flow)); + if (!flow) + return -ENOMEM; + + flow->credit = q.initial_quantum, + flow->qlen = 0, + flow->age = 1, + flow->time_next_packet = 0, + + ret = bpf_map_update_elem(flow_map, &hash, &tmp, 0); + if (ret == -ENOMEM || ret == -E2BIG) { + fq_gc(); + bpf_map_update_elem(&fq_nonprio_flows, &hash, &tmp, 0); + } + + *sflow = bpf_map_lookup_elem(flow_map, &hash); + if (!*sflow) { + bpf_obj_drop(flow); + return -ENOMEM; + } + + bpf_kptr_xchg_back(&(*sflow)->flow, flow); + return 0; +} + +static int +fq_classify(struct sk_buff *skb, struct fq_stashed_flow **sflow) +{ + struct sock *sk = skb->sk; + int ret = CLS_RET_NONPRIO; + u64 hash = 0; + + if ((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL) { + *sflow = bpf_map_lookup_elem(&fq_prio_flows, &hash); + ret = CLS_RET_PRIO; + } else { + if (!sk || sk_listener(sk)) { + hash = bpf_skb_get_hash(skb) & q.orphan_mask; + /* Avoid collision with an existing flow hash, which + * only uses the lower 32 bits of hash, by setting the + * upper half of hash to 1. + */ + hash |= (1ULL << 32); + } else if (sk->__sk_common.skc_state == TCP_CLOSE) { + hash = bpf_skb_get_hash(skb) & q.orphan_mask; + hash |= (1ULL << 32); + } else { + hash = sk->__sk_common.skc_hash; + } + *sflow = bpf_map_lookup_elem(&fq_nonprio_flows, &hash); + } + + if (!*sflow) + ret = fq_new_flow(&fq_nonprio_flows, sflow, hash) < 0 ? + CLS_RET_ERR : CLS_RET_NONPRIO; + + return ret; +} + +static bool fq_packet_beyond_horizon(struct sk_buff *skb) +{ + return (s64)skb->tstamp > (s64)(q.ktime_cache + q.horizon); +} + +SEC("struct_ops/bpf_fq_enqueue") +int BPF_PROG(bpf_fq_enqueue, struct sk_buff *skb, struct Qdisc *sch, + struct bpf_sk_buff_ptr *to_free) +{ + struct fq_flow_node *flow = NULL, *flow_copy; + struct fq_stashed_flow *sflow; + u64 time_to_send, jiffies; + struct skb_node *skbn; + int ret; + + if (sch->q.qlen >= sch->limit) + goto drop; + + if (!skb->tstamp) { + time_to_send = q.ktime_cache = bpf_ktime_get_ns(); + } else { + if (fq_packet_beyond_horizon(skb)) { + q.ktime_cache = bpf_ktime_get_ns(); + if (fq_packet_beyond_horizon(skb)) { + if (q.horizon_drop) + goto drop; + + skb->tstamp = q.ktime_cache + q.horizon; + } + } + time_to_send = skb->tstamp; + } + + ret = fq_classify(skb, &sflow); + if (ret == CLS_RET_ERR) + goto drop; + + flow = bpf_kptr_xchg(&sflow->flow, flow); + if (!flow) + goto drop; + + if (ret == CLS_RET_NONPRIO) { + if (flow->qlen >= q.flow_plimit) { + bpf_kptr_xchg_back(&sflow->flow, flow); + goto drop; + } + + if (fq_flow_is_detached(flow)) { + flow_copy = bpf_refcount_acquire(flow); + + jiffies = bpf_jiffies64(); + if ((s64)(jiffies - (flow_copy->age + q.flow_refill_delay)) > 0) { + if (flow_copy->credit < q.quantum) + flow_copy->credit = q.quantum; + } + flow_copy->age = 0; + fq_flows_add_tail(&fq_new_flows, &fq_new_flows_lock, flow_copy, + &q.new_flow_cnt); + } + } + + skbn = bpf_obj_new(typeof(*skbn)); + if (!skbn) { + bpf_kptr_xchg_back(&sflow->flow, flow); + goto drop; + } + + skbn->tstamp = skb->tstamp = time_to_send; + + sch->qstats.backlog += qdisc_pkt_len(skb); + + skb = bpf_kptr_xchg(&skbn->skb, skb); + if (skb) + bpf_qdisc_skb_drop(skb, to_free); + + bpf_spin_lock(&flow->lock); + bpf_rbtree_add(&flow->queue, &skbn->node, skbn_tstamp_less); + bpf_spin_unlock(&flow->lock); + + flow->qlen++; + bpf_kptr_xchg_back(&sflow->flow, flow); + + sch->q.qlen++; + return NET_XMIT_SUCCESS; + +drop: + bpf_qdisc_skb_drop(skb, to_free); + sch->qstats.drops++; + return NET_XMIT_DROP; +} + +static int fq_unset_throttled_flows(u32 index, struct unset_throttled_flows_ctx *ctx) +{ + struct bpf_rb_node *node = NULL; + struct fq_flow_node *flow; + + bpf_spin_lock(&fq_delayed_lock); + + node = bpf_rbtree_first(&fq_delayed); + if (!node) { + bpf_spin_unlock(&fq_delayed_lock); + return 1; + } + + flow = container_of(node, struct fq_flow_node, rb_node); + if (!ctx->unset_all && flow->time_next_packet > ctx->now) { + q.time_next_delayed_flow = flow->time_next_packet; + bpf_spin_unlock(&fq_delayed_lock); + return 1; + } + + node = bpf_rbtree_remove(&fq_delayed, &flow->rb_node); + + bpf_spin_unlock(&fq_delayed_lock); + + if (!node) + return 1; + + flow = container_of(node, struct fq_flow_node, rb_node); + flow->age = 0; + fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt); + + return 0; +} + +static void fq_flow_set_throttled(struct fq_flow_node *flow) +{ + flow->age = ~0ULL; + + if (q.time_next_delayed_flow > flow->time_next_packet) + q.time_next_delayed_flow = flow->time_next_packet; + + bpf_spin_lock(&fq_delayed_lock); + bpf_rbtree_add(&fq_delayed, &flow->rb_node, fn_time_next_packet_less); + bpf_spin_unlock(&fq_delayed_lock); +} + +static void fq_check_throttled(u64 now) +{ + struct unset_throttled_flows_ctx ctx = { + .unset_all = false, + .now = now, + }; + unsigned long sample; + + if (q.time_next_delayed_flow > now) + return; + + sample = (unsigned long)(now - q.time_next_delayed_flow); + q.unthrottle_latency_ns -= q.unthrottle_latency_ns >> 3; + q.unthrottle_latency_ns += sample >> 3; + + q.time_next_delayed_flow = ~0ULL; + bpf_loop(NUM_QUEUE, fq_unset_throttled_flows, &ctx, 0); +} + +static struct sk_buff* +fq_dequeue_nonprio_flows(u32 index, struct dequeue_nonprio_ctx *ctx) +{ + u64 time_next_packet, time_to_send; + struct bpf_rb_node *rb_node; + struct sk_buff *skb = NULL; + struct bpf_list_head *head; + struct bpf_list_node *node; + struct bpf_spin_lock *lock; + struct fq_flow_node *flow; + struct skb_node *skbn; + bool is_empty; + u32 *cnt; + + if (q.new_flow_cnt) { + head = &fq_new_flows; + lock = &fq_new_flows_lock; + cnt = &q.new_flow_cnt; + } else if (q.old_flow_cnt) { + head = &fq_old_flows; + lock = &fq_old_flows_lock; + cnt = &q.old_flow_cnt; + } else { + if (q.time_next_delayed_flow != ~0ULL) + ctx->expire = q.time_next_delayed_flow; + goto break_loop; + } + + fq_flows_remove_front(head, lock, &node, cnt); + if (!node) + goto break_loop; + + flow = container_of(node, struct fq_flow_node, list_node); + if (flow->credit <= 0) { + flow->credit += q.quantum; + fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt); + return NULL; + } + + bpf_spin_lock(&flow->lock); + rb_node = bpf_rbtree_first(&flow->queue); + if (!rb_node) { + bpf_spin_unlock(&flow->lock); + is_empty = fq_flows_is_empty(&fq_old_flows, &fq_old_flows_lock); + if (head == &fq_new_flows && !is_empty) { + fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt); + } else { + fq_flow_set_detached(flow); + bpf_obj_drop(flow); + } + return NULL; + } + + skbn = container_of(rb_node, struct skb_node, node); + time_to_send = skbn->tstamp; + + time_next_packet = (time_to_send > flow->time_next_packet) ? + time_to_send : flow->time_next_packet; + if (ctx->now < time_next_packet) { + bpf_spin_unlock(&flow->lock); + flow->time_next_packet = time_next_packet; + fq_flow_set_throttled(flow); + return NULL; + } + + rb_node = bpf_rbtree_remove(&flow->queue, rb_node); + bpf_spin_unlock(&flow->lock); + + if (!rb_node) + goto add_flow_and_break; + + skbn = container_of(rb_node, struct skb_node, node); + skb = bpf_kptr_xchg(&skbn->skb, skb); + bpf_obj_drop(skbn); + + if (!skb) + goto add_flow_and_break; + + flow->credit -= qdisc_skb_cb(skb)->pkt_len; + flow->qlen--; + +add_flow_and_break: + fq_flows_add_head(head, lock, flow, cnt); + +break_loop: + ctx->stop_iter = true; + return skb; +} + +static struct sk_buff *fq_dequeue_prio(void) +{ + struct fq_flow_node *flow = NULL; + struct fq_stashed_flow *sflow; + struct bpf_rb_node *rb_node; + struct sk_buff *skb = NULL; + struct skb_node *skbn; + u64 hash = 0; + + sflow = bpf_map_lookup_elem(&fq_prio_flows, &hash); + if (!sflow) + return NULL; + + flow = bpf_kptr_xchg(&sflow->flow, flow); + if (!flow) + return NULL; + + bpf_spin_lock(&flow->lock); + rb_node = bpf_rbtree_first(&flow->queue); + if (!rb_node) { + bpf_spin_unlock(&flow->lock); + goto out; + } + + skbn = container_of(rb_node, struct skb_node, node); + rb_node = bpf_rbtree_remove(&flow->queue, &skbn->node); + bpf_spin_unlock(&flow->lock); + + if (!rb_node) + goto out; + + skbn = container_of(rb_node, struct skb_node, node); + skb = bpf_kptr_xchg(&skbn->skb, skb); + bpf_obj_drop(skbn); + +out: + bpf_kptr_xchg_back(&sflow->flow, flow); + + return skb; +} + +SEC("struct_ops/bpf_fq_dequeue") +struct sk_buff *BPF_PROG(bpf_fq_dequeue, struct Qdisc *sch) +{ + struct dequeue_nonprio_ctx cb_ctx = {}; + struct sk_buff *skb = NULL; + int i; + + if (!sch->q.qlen) + goto out; + + skb = fq_dequeue_prio(); + if (skb) + goto dequeue; + + q.ktime_cache = cb_ctx.now = bpf_ktime_get_ns(); + fq_check_throttled(q.ktime_cache); + bpf_for(i, 0, sch->limit) { + skb = fq_dequeue_nonprio_flows(i, &cb_ctx); + if (cb_ctx.stop_iter) + break; + }; + + if (skb) { +dequeue: + sch->q.qlen--; + sch->qstats.backlog -= qdisc_pkt_len(skb); + bpf_qdisc_bstats_update(sch, skb); + return skb; + } + + if (cb_ctx.expire) + bpf_qdisc_watchdog_schedule(sch, cb_ctx.expire, q.timer_slack); +out: + return NULL; +} + +static int fq_remove_flows_in_list(u32 index, void *ctx) +{ + struct bpf_list_node *node; + struct fq_flow_node *flow; + + bpf_spin_lock(&fq_new_flows_lock); + node = bpf_list_pop_front(&fq_new_flows); + bpf_spin_unlock(&fq_new_flows_lock); + if (!node) { + bpf_spin_lock(&fq_old_flows_lock); + node = bpf_list_pop_front(&fq_old_flows); + bpf_spin_unlock(&fq_old_flows_lock); + if (!node) + return 1; + } + + flow = container_of(node, struct fq_flow_node, list_node); + bpf_obj_drop(flow); + + return 0; +} + +extern unsigned CONFIG_HZ __kconfig; + +/* limit number of collected flows per round */ +#define FQ_GC_MAX 8 +#define FQ_GC_AGE (3*CONFIG_HZ) + +static bool fq_gc_candidate(struct fq_flow_node *flow) +{ + u64 jiffies = bpf_jiffies64(); + + return fq_flow_is_detached(flow) && + ((s64)(jiffies - (flow->age + FQ_GC_AGE)) > 0); +} + +static int +fq_remove_flows(struct bpf_map *flow_map, u64 *hash, + struct fq_stashed_flow *sflow, struct remove_flows_ctx *ctx) +{ + if (sflow->flow && + (!ctx->gc_only || fq_gc_candidate(sflow->flow))) { + bpf_map_delete_elem(flow_map, hash); + ctx->reset_cnt++; + } + + return ctx->reset_cnt < ctx->reset_max ? 0 : 1; +} + +static void fq_gc(void) +{ + struct remove_flows_ctx cb_ctx = { + .gc_only = true, + .reset_cnt = 0, + .reset_max = FQ_GC_MAX, + }; + + bpf_for_each_map_elem(&fq_nonprio_flows, fq_remove_flows, &cb_ctx, 0); +} + +SEC("struct_ops/bpf_fq_reset") +void BPF_PROG(bpf_fq_reset, struct Qdisc *sch) +{ + struct unset_throttled_flows_ctx utf_ctx = { + .unset_all = true, + }; + struct remove_flows_ctx rf_ctx = { + .gc_only = false, + .reset_cnt = 0, + .reset_max = NUM_QUEUE, + }; + struct fq_stashed_flow *sflow; + u64 hash = 0; + + sch->q.qlen = 0; + sch->qstats.backlog = 0; + + bpf_for_each_map_elem(&fq_nonprio_flows, fq_remove_flows, &rf_ctx, 0); + + rf_ctx.reset_cnt = 0; + bpf_for_each_map_elem(&fq_prio_flows, fq_remove_flows, &rf_ctx, 0); + fq_new_flow(&fq_prio_flows, &sflow, hash); + + bpf_loop(NUM_QUEUE, fq_remove_flows_in_list, NULL, 0); + q.new_flow_cnt = 0; + q.old_flow_cnt = 0; + + bpf_loop(NUM_QUEUE, fq_unset_throttled_flows, &utf_ctx, 0); +} + +SEC("struct_ops/bpf_fq_init") +int BPF_PROG(bpf_fq_init, struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct net_device *dev = sch->dev_queue->dev; + u32 psched_mtu = dev->mtu + dev->hard_header_len; + struct fq_stashed_flow *sflow; + u64 hash = 0; + + if (fq_new_flow(&fq_prio_flows, &sflow, hash) < 0) + return -ENOMEM; + + sch->limit = 10000; + q.initial_quantum = 10 * psched_mtu; + q.quantum = 2 * psched_mtu; + q.flow_refill_delay = 40; + q.flow_plimit = 100; + q.horizon = 10ULL * NSEC_PER_SEC; + q.horizon_drop = 1; + q.orphan_mask = 1024 - 1; + q.timer_slack = 10 * NSEC_PER_USEC; + q.time_next_delayed_flow = ~0ULL; + q.unthrottle_latency_ns = 0ULL; + q.new_flow_cnt = 0; + q.old_flow_cnt = 0; + + return 0; +} + +SEC("struct_ops") +void BPF_PROG(bpf_fq_destroy, struct Qdisc *sch) +{ +} + +SEC(".struct_ops") +struct Qdisc_ops fq = { + .enqueue = (void *)bpf_fq_enqueue, + .dequeue = (void *)bpf_fq_dequeue, + .reset = (void *)bpf_fq_reset, + .init = (void *)bpf_fq_init, + .destroy = (void *)bpf_fq_destroy, + .id = "bpf_fq", +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 659694162739..17db400f0e0d 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -128,6 +128,7 @@ #define sk_refcnt __sk_common.skc_refcnt #define sk_state __sk_common.skc_state #define sk_net __sk_common.skc_net +#define sk_rcv_saddr __sk_common.skc_rcv_saddr #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_flags __sk_common.skc_flags diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c index 38f78d9345de..69f81cb555ca 100644 --- a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c +++ b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c @@ -30,22 +30,27 @@ int BPF_PROG(test_percpu2, struct bpf_testmod_btf_type_tag_2 *arg) /* trace_cgroup_mkdir(struct cgroup *cgrp, const char *path) * - * struct cgroup_rstat_cpu { + * struct css_rstat_cpu { * ... - * struct cgroup *updated_children; + * struct cgroup_subsys_state *updated_children; * ... * }; * - * struct cgroup { + * struct cgroup_subsys_state { + * ... + * struct css_rstat_cpu __percpu *rstat_cpu; * ... - * struct cgroup_rstat_cpu __percpu *rstat_cpu; + * }; + * + * struct cgroup { + * struct cgroup_subsys_state self; * ... * }; */ SEC("tp_btf/cgroup_mkdir") int BPF_PROG(test_percpu_load, struct cgroup *cgrp, const char *path) { - g = (__u64)cgrp->rstat_cpu->updated_children; + g = (__u64)cgrp->self.rstat_cpu->updated_children; return 0; } @@ -56,7 +61,8 @@ int BPF_PROG(test_percpu_helper, struct cgroup *cgrp, const char *path) __u32 cpu; cpu = bpf_get_smp_processor_id(); - rstat = (struct cgroup_rstat_cpu *)bpf_per_cpu_ptr(cgrp->rstat_cpu, cpu); + rstat = (struct cgroup_rstat_cpu *)bpf_per_cpu_ptr( + cgrp->self.rstat_cpu, cpu); if (rstat) { /* READ_ONCE */ *(volatile int *)rstat; diff --git a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c index c74362854948..ff189a736ad8 100644 --- a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c +++ b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c @@ -37,8 +37,9 @@ struct { __type(value, struct attach_counter); } attach_counters SEC(".maps"); -extern void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) __ksym; -extern void cgroup_rstat_flush(struct cgroup *cgrp) __ksym; +extern void css_rstat_updated( + struct cgroup_subsys_state *css, int cpu) __ksym; +extern void css_rstat_flush(struct cgroup_subsys_state *css) __ksym; static uint64_t cgroup_id(struct cgroup *cgrp) { @@ -75,7 +76,7 @@ int BPF_PROG(counter, struct cgroup *dst_cgrp, struct task_struct *leader, else if (create_percpu_attach_counter(cg_id, 1)) return 0; - cgroup_rstat_updated(dst_cgrp, bpf_get_smp_processor_id()); + css_rstat_updated(&dst_cgrp->self, bpf_get_smp_processor_id()); return 0; } @@ -141,7 +142,7 @@ int BPF_PROG(dumper, struct bpf_iter_meta *meta, struct cgroup *cgrp) return 1; /* Flush the stats to make sure we get the most updated numbers */ - cgroup_rstat_flush(cgrp); + css_rstat_flush(&cgrp->self); total_counter = bpf_map_lookup_elem(&attach_counters, &cg_id); if (!total_counter) { diff --git a/tools/testing/selftests/bpf/progs/dmabuf_iter.c b/tools/testing/selftests/bpf/progs/dmabuf_iter.c new file mode 100644 index 000000000000..13cdb11fdeb2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/dmabuf_iter.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Google LLC */ +#include <vmlinux.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> + +/* From uapi/linux/dma-buf.h */ +#define DMA_BUF_NAME_LEN 32 + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, DMA_BUF_NAME_LEN); + __type(value, bool); + __uint(max_entries, 5); +} testbuf_hash SEC(".maps"); + +/* + * Fields output by this iterator are delimited by newlines. Convert any + * newlines in user-provided printed strings to spaces. + */ +static void sanitize_string(char *src, size_t size) +{ + for (char *c = src; (size_t)(c - src) < size && *c; ++c) + if (*c == '\n') + *c = ' '; +} + +SEC("iter/dmabuf") +int dmabuf_collector(struct bpf_iter__dmabuf *ctx) +{ + const struct dma_buf *dmabuf = ctx->dmabuf; + struct seq_file *seq = ctx->meta->seq; + unsigned long inode = 0; + size_t size; + const char *pname, *exporter; + char name[DMA_BUF_NAME_LEN] = {'\0'}; + + if (!dmabuf) + return 0; + + if (BPF_CORE_READ_INTO(&inode, dmabuf, file, f_inode, i_ino) || + bpf_core_read(&size, sizeof(size), &dmabuf->size) || + bpf_core_read(&pname, sizeof(pname), &dmabuf->name) || + bpf_core_read(&exporter, sizeof(exporter), &dmabuf->exp_name)) + return 1; + + /* Buffers are not required to be named */ + if (pname) { + if (bpf_probe_read_kernel(name, sizeof(name), pname)) + return 1; + + /* Name strings can be provided by userspace */ + sanitize_string(name, sizeof(name)); + } + + BPF_SEQ_PRINTF(seq, "%lu\n%llu\n%s\n%s\n", inode, size, name, exporter); + return 0; +} + +SEC("syscall") +int iter_dmabuf_for_each(const void *ctx) +{ + struct dma_buf *d; + + bpf_for_each(dmabuf, d) { + char name[DMA_BUF_NAME_LEN]; + const char *pname; + bool *found; + long len; + int i; + + if (bpf_core_read(&pname, sizeof(pname), &d->name)) + return 1; + + /* Buffers are not required to be named */ + if (!pname) + continue; + + len = bpf_probe_read_kernel_str(name, sizeof(name), pname); + if (len < 0) + return 1; + + /* + * The entire name buffer is used as a map key. + * Zeroize any uninitialized trailing bytes after the NUL. + */ + bpf_for(i, len, DMA_BUF_NAME_LEN) + name[i] = 0; + + found = bpf_map_lookup_elem(&testbuf_hash, name); + if (found) { + bool t = true; + + bpf_map_update_elem(&testbuf_hash, name, &t, BPF_EXIST); + } + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index e1fba28e4a86..a0391f9da2d4 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -680,3 +680,233 @@ out: bpf_ringbuf_discard_dynptr(&ptr_buf, 0); 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 + * but less than the maximum bpf stack size (512). + */ +char expected_str[384]; +__u32 test_len[7] = {0/* placeholder */, 0, 1, 2, 255, 256, 257}; + +typedef int (*bpf_read_dynptr_fn_t)(struct bpf_dynptr *dptr, u32 off, + u32 size, const void *unsafe_ptr); + +/* Returns the offset just before the end of the maximum sized xdp fragment. + * Any write larger than 32 bytes will be split between 2 fragments. + */ +__u32 xdp_near_frag_end_offset(void) +{ + const __u32 headroom = 256; + const __u32 max_frag_size = __PAGE_SIZE - headroom - sizeof(struct skb_shared_info); + + /* 32 bytes before the approximate end of the fragment */ + return max_frag_size - 32; +} + +/* Use __always_inline on test_dynptr_probe[_str][_xdp]() and callbacks + * of type bpf_read_dynptr_fn_t to prevent compiler from generating + * indirect calls that make program fail to load with "unknown opcode" error. + */ +static __always_inline void test_dynptr_probe(void *ptr, bpf_read_dynptr_fn_t bpf_read_dynptr_fn) +{ + char buf[sizeof(expected_str)]; + struct bpf_dynptr ptr_buf; + int i; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + err = bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(buf), 0, &ptr_buf); + + bpf_for(i, 0, ARRAY_SIZE(test_len)) { + __u32 len = test_len[i]; + + err = err ?: bpf_read_dynptr_fn(&ptr_buf, 0, test_len[i], ptr); + if (len > sizeof(buf)) + break; + err = err ?: bpf_dynptr_read(&buf, len, &ptr_buf, 0, 0); + + if (err || bpf_memcmp(expected_str, buf, len)) + err = 1; + + /* Reset buffer and dynptr */ + __builtin_memset(buf, 0, sizeof(buf)); + err = err ?: bpf_dynptr_write(&ptr_buf, 0, buf, len, 0); + } + bpf_ringbuf_discard_dynptr(&ptr_buf, 0); +} + +static __always_inline void test_dynptr_probe_str(void *ptr, + bpf_read_dynptr_fn_t bpf_read_dynptr_fn) +{ + char buf[sizeof(expected_str)]; + struct bpf_dynptr ptr_buf; + __u32 cnt, i; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(buf), 0, &ptr_buf); + + bpf_for(i, 0, ARRAY_SIZE(test_len)) { + __u32 len = test_len[i]; + + cnt = bpf_read_dynptr_fn(&ptr_buf, 0, len, ptr); + if (cnt != len) + err = 1; + + if (len > sizeof(buf)) + continue; + err = err ?: bpf_dynptr_read(&buf, len, &ptr_buf, 0, 0); + if (!len) + continue; + if (err || bpf_memcmp(expected_str, buf, len - 1) || buf[len - 1] != '\0') + err = 1; + } + bpf_ringbuf_discard_dynptr(&ptr_buf, 0); +} + +static __always_inline void test_dynptr_probe_xdp(struct xdp_md *xdp, void *ptr, + bpf_read_dynptr_fn_t bpf_read_dynptr_fn) +{ + struct bpf_dynptr ptr_xdp; + char buf[sizeof(expected_str)]; + __u32 off, i; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + off = xdp_near_frag_end_offset(); + err = bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp); + + bpf_for(i, 0, ARRAY_SIZE(test_len)) { + __u32 len = test_len[i]; + + err = err ?: bpf_read_dynptr_fn(&ptr_xdp, off, len, ptr); + if (len > sizeof(buf)) + continue; + err = err ?: bpf_dynptr_read(&buf, len, &ptr_xdp, off, 0); + if (err || bpf_memcmp(expected_str, buf, len)) + err = 1; + /* Reset buffer and dynptr */ + __builtin_memset(buf, 0, sizeof(buf)); + err = err ?: bpf_dynptr_write(&ptr_xdp, off, buf, len, 0); + } +} + +static __always_inline void test_dynptr_probe_str_xdp(struct xdp_md *xdp, void *ptr, + bpf_read_dynptr_fn_t bpf_read_dynptr_fn) +{ + struct bpf_dynptr ptr_xdp; + char buf[sizeof(expected_str)]; + __u32 cnt, off, i; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + off = xdp_near_frag_end_offset(); + err = bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp); + if (err) + return; + + bpf_for(i, 0, ARRAY_SIZE(test_len)) { + __u32 len = test_len[i]; + + cnt = bpf_read_dynptr_fn(&ptr_xdp, off, len, ptr); + if (cnt != len) + err = 1; + + if (len > sizeof(buf)) + continue; + err = err ?: bpf_dynptr_read(&buf, len, &ptr_xdp, off, 0); + + if (!len) + continue; + if (err || bpf_memcmp(expected_str, buf, len - 1) || buf[len - 1] != '\0') + err = 1; + + __builtin_memset(buf, 0, sizeof(buf)); + err = err ?: bpf_dynptr_write(&ptr_xdp, off, buf, len, 0); + } +} + +SEC("xdp") +int test_probe_read_user_dynptr(struct xdp_md *xdp) +{ + test_dynptr_probe(user_ptr, bpf_probe_read_user_dynptr); + if (!err) + test_dynptr_probe_xdp(xdp, user_ptr, bpf_probe_read_user_dynptr); + return XDP_PASS; +} + +SEC("xdp") +int test_probe_read_kernel_dynptr(struct xdp_md *xdp) +{ + test_dynptr_probe(expected_str, bpf_probe_read_kernel_dynptr); + if (!err) + test_dynptr_probe_xdp(xdp, expected_str, bpf_probe_read_kernel_dynptr); + return XDP_PASS; +} + +SEC("xdp") +int test_probe_read_user_str_dynptr(struct xdp_md *xdp) +{ + test_dynptr_probe_str(user_ptr, bpf_probe_read_user_str_dynptr); + if (!err) + test_dynptr_probe_str_xdp(xdp, user_ptr, bpf_probe_read_user_str_dynptr); + return XDP_PASS; +} + +SEC("xdp") +int test_probe_read_kernel_str_dynptr(struct xdp_md *xdp) +{ + test_dynptr_probe_str(expected_str, bpf_probe_read_kernel_str_dynptr); + if (!err) + test_dynptr_probe_str_xdp(xdp, expected_str, bpf_probe_read_kernel_str_dynptr); + return XDP_PASS; +} + +SEC("fentry.s/" SYS_PREFIX "sys_nanosleep") +int test_copy_from_user_dynptr(void *ctx) +{ + test_dynptr_probe(user_ptr, bpf_copy_from_user_dynptr); + return 0; +} + +SEC("fentry.s/" SYS_PREFIX "sys_nanosleep") +int test_copy_from_user_str_dynptr(void *ctx) +{ + test_dynptr_probe_str(user_ptr, bpf_copy_from_user_str_dynptr); + return 0; +} + +static int bpf_copy_data_from_user_task(struct bpf_dynptr *dptr, u32 off, + u32 size, const void *unsafe_ptr) +{ + struct task_struct *task = bpf_get_current_task_btf(); + + return bpf_copy_from_user_task_dynptr(dptr, off, size, unsafe_ptr, task); +} + +static int bpf_copy_data_from_user_task_str(struct bpf_dynptr *dptr, u32 off, + u32 size, const void *unsafe_ptr) +{ + struct task_struct *task = bpf_get_current_task_btf(); + + return bpf_copy_from_user_task_str_dynptr(dptr, off, size, unsafe_ptr, task); +} + +SEC("fentry.s/" SYS_PREFIX "sys_nanosleep") +int test_copy_from_user_task_dynptr(void *ctx) +{ + test_dynptr_probe(user_ptr, bpf_copy_data_from_user_task); + return 0; +} + +SEC("fentry.s/" SYS_PREFIX "sys_nanosleep") +int test_copy_from_user_task_str_dynptr(void *ctx) +{ + test_dynptr_probe_str(user_ptr, bpf_copy_data_from_user_task_str); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/fd_htab_lookup.c b/tools/testing/selftests/bpf/progs/fd_htab_lookup.c new file mode 100644 index 000000000000..a4a9e1db626f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fd_htab_lookup.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025. Huawei Technologies Co., Ltd */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct inner_map_type { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, 4); + __uint(value_size, 4); + __uint(max_entries, 1); +} inner_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __uint(max_entries, 64); + __type(key, int); + __type(value, int); + __array(values, struct inner_map_type); +} outer_map SEC(".maps") = { + .values = { + [0] = &inner_map, + }, +}; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 427b72954b87..76adf4a8f2da 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -7,8 +7,6 @@ #include "bpf_misc.h" #include "bpf_compiler.h" -#define unlikely(x) __builtin_expect(!!(x), 0) - static volatile int zero = 0; int my_pid; diff --git a/tools/testing/selftests/bpf/progs/linked_list_peek.c b/tools/testing/selftests/bpf/progs/linked_list_peek.c new file mode 100644 index 000000000000..264e81bfb287 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/linked_list_peek.c @@ -0,0 +1,113 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +struct node_data { + struct bpf_list_node l; + int key; +}; + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock; +private(A) struct bpf_list_head ghead __contains(node_data, l); + +#define list_entry(ptr, type, member) container_of(ptr, type, member) +#define NR_NODES 16 + +int zero = 0; + +SEC("syscall") +__retval(0) +long list_peek(void *ctx) +{ + struct bpf_list_node *l_n; + struct node_data *n; + int i, err = 0; + + bpf_spin_lock(&glock); + l_n = bpf_list_front(&ghead); + bpf_spin_unlock(&glock); + if (l_n) + return __LINE__; + + bpf_spin_lock(&glock); + l_n = bpf_list_back(&ghead); + bpf_spin_unlock(&glock); + if (l_n) + return __LINE__; + + for (i = zero; i < NR_NODES && can_loop; i++) { + n = bpf_obj_new(typeof(*n)); + if (!n) + return __LINE__; + n->key = i; + bpf_spin_lock(&glock); + bpf_list_push_back(&ghead, &n->l); + bpf_spin_unlock(&glock); + } + + bpf_spin_lock(&glock); + + l_n = bpf_list_front(&ghead); + if (!l_n) { + err = __LINE__; + goto done; + } + + n = list_entry(l_n, struct node_data, l); + if (n->key != 0) { + err = __LINE__; + goto done; + } + + l_n = bpf_list_back(&ghead); + if (!l_n) { + err = __LINE__; + goto done; + } + + n = list_entry(l_n, struct node_data, l); + if (n->key != NR_NODES - 1) { + err = __LINE__; + goto done; + } + +done: + bpf_spin_unlock(&glock); + return err; +} + +#define TEST_FB(op, dolock) \ +SEC("syscall") \ +__failure __msg(MSG) \ +long test_##op##_spinlock_##dolock(void *ctx) \ +{ \ + struct bpf_list_node *l_n; \ + __u64 jiffies = 0; \ + \ + if (dolock) \ + bpf_spin_lock(&glock); \ + l_n = bpf_list_##op(&ghead); \ + if (l_n) \ + jiffies = bpf_jiffies64(); \ + if (dolock) \ + bpf_spin_unlock(&glock); \ + \ + return !!jiffies; \ +} + +#define MSG "call bpf_list_{{(front|back).+}}; R0{{(_w)?}}=ptr_or_null_node_data(id={{[0-9]+}},non_own_ref" +TEST_FB(front, true) +TEST_FB(back, true) +#undef MSG + +#define MSG "bpf_spin_lock at off=0 must be held for bpf_list_head" +TEST_FB(front, false) +TEST_FB(back, false) +#undef MSG + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/prepare.c b/tools/testing/selftests/bpf/progs/prepare.c index 1f1dd547e4ee..cfc1f48e0d28 100644 --- a/tools/testing/selftests/bpf/progs/prepare.c +++ b/tools/testing/selftests/bpf/progs/prepare.c @@ -2,7 +2,6 @@ /* Copyright (c) 2025 Meta */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> -//#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null.c b/tools/testing/selftests/bpf/progs/raw_tp_null.c index 5927054b6dd9..efa416f53968 100644 --- a/tools/testing/selftests/bpf/progs/raw_tp_null.c +++ b/tools/testing/selftests/bpf/progs/raw_tp_null.c @@ -10,7 +10,7 @@ char _license[] SEC("license") = "GPL"; int tid; int i; -SEC("tp_btf/bpf_testmod_test_raw_tp_null") +SEC("tp_btf/bpf_testmod_test_raw_tp_null_tp") int BPF_PROG(test_raw_tp_null, struct sk_buff *skb) { struct task_struct *task = bpf_get_current_task_btf(); diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c index 38d669957bf1..0d58114a4955 100644 --- a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c +++ b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c @@ -8,7 +8,7 @@ char _license[] SEC("license") = "GPL"; /* Ensure module parameter has PTR_MAYBE_NULL */ -SEC("tp_btf/bpf_testmod_test_raw_tp_null") +SEC("tp_btf/bpf_testmod_test_raw_tp_null_tp") __failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") int test_raw_tp_null_bpf_testmod_test_raw_tp_null_arg_1(void *ctx) { asm volatile("r1 = *(u64 *)(r1 +0); r1 = *(u64 *)(r1 +0);" ::: __clobber_all); diff --git a/tools/testing/selftests/bpf/progs/rbtree_fail.c b/tools/testing/selftests/bpf/progs/rbtree_fail.c index dbd5eee8e25e..4acb6af2dfe3 100644 --- a/tools/testing/selftests/bpf/progs/rbtree_fail.c +++ b/tools/testing/selftests/bpf/progs/rbtree_fail.c @@ -69,11 +69,11 @@ long rbtree_api_nolock_first(void *ctx) } SEC("?tc") -__failure __msg("rbtree_remove node input must be non-owning ref") +__retval(0) long rbtree_api_remove_unadded_node(void *ctx) { struct node_data *n, *m; - struct bpf_rb_node *res; + struct bpf_rb_node *res_n, *res_m; n = bpf_obj_new(typeof(*n)); if (!n) @@ -88,19 +88,20 @@ long rbtree_api_remove_unadded_node(void *ctx) bpf_spin_lock(&glock); bpf_rbtree_add(&groot, &n->node, less); - /* This remove should pass verifier */ - res = bpf_rbtree_remove(&groot, &n->node); - n = container_of(res, struct node_data, node); + res_n = bpf_rbtree_remove(&groot, &n->node); - /* This remove shouldn't, m isn't in an rbtree */ - res = bpf_rbtree_remove(&groot, &m->node); - m = container_of(res, struct node_data, node); + res_m = bpf_rbtree_remove(&groot, &m->node); bpf_spin_unlock(&glock); - if (n) - bpf_obj_drop(n); - if (m) - bpf_obj_drop(m); + bpf_obj_drop(m); + if (res_n) + bpf_obj_drop(container_of(res_n, struct node_data, node)); + if (res_m) { + bpf_obj_drop(container_of(res_m, struct node_data, node)); + /* m was not added to the rbtree */ + return 2; + } + return 0; } @@ -178,7 +179,7 @@ err_out: } SEC("?tc") -__failure __msg("rbtree_remove node input must be non-owning ref") +__failure __msg("bpf_rbtree_remove can only take non-owning or refcounted bpf_rb_node pointer") long rbtree_api_add_release_unlock_escape(void *ctx) { struct node_data *n; @@ -202,7 +203,7 @@ long rbtree_api_add_release_unlock_escape(void *ctx) } SEC("?tc") -__failure __msg("rbtree_remove node input must be non-owning ref") +__failure __msg("bpf_rbtree_remove can only take non-owning or refcounted bpf_rb_node pointer") long rbtree_api_first_release_unlock_escape(void *ctx) { struct bpf_rb_node *res; diff --git a/tools/testing/selftests/bpf/progs/rbtree_search.c b/tools/testing/selftests/bpf/progs/rbtree_search.c new file mode 100644 index 000000000000..098ef970fac1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/rbtree_search.c @@ -0,0 +1,206 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +struct node_data { + struct bpf_refcount ref; + struct bpf_rb_node r0; + struct bpf_rb_node r1; + int key0; + int key1; +}; + +#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8))) +private(A) struct bpf_spin_lock glock0; +private(A) struct bpf_rb_root groot0 __contains(node_data, r0); + +private(B) struct bpf_spin_lock glock1; +private(B) struct bpf_rb_root groot1 __contains(node_data, r1); + +#define rb_entry(ptr, type, member) container_of(ptr, type, member) +#define NR_NODES 16 + +int zero = 0; + +static bool less0(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = rb_entry(a, struct node_data, r0); + node_b = rb_entry(b, struct node_data, r0); + + return node_a->key0 < node_b->key0; +} + +static bool less1(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = rb_entry(a, struct node_data, r1); + node_b = rb_entry(b, struct node_data, r1); + + return node_a->key1 < node_b->key1; +} + +SEC("syscall") +__retval(0) +long rbtree_search(void *ctx) +{ + struct bpf_rb_node *rb_n, *rb_m, *gc_ns[NR_NODES]; + long lookup_key = NR_NODES / 2; + struct node_data *n, *m; + int i, nr_gc = 0; + + for (i = zero; i < NR_NODES && can_loop; i++) { + n = bpf_obj_new(typeof(*n)); + if (!n) + return __LINE__; + + m = bpf_refcount_acquire(n); + + n->key0 = i; + m->key1 = i; + + bpf_spin_lock(&glock0); + bpf_rbtree_add(&groot0, &n->r0, less0); + bpf_spin_unlock(&glock0); + + bpf_spin_lock(&glock1); + bpf_rbtree_add(&groot1, &m->r1, less1); + bpf_spin_unlock(&glock1); + } + + n = NULL; + bpf_spin_lock(&glock0); + rb_n = bpf_rbtree_root(&groot0); + while (can_loop) { + if (!rb_n) { + bpf_spin_unlock(&glock0); + return __LINE__; + } + + n = rb_entry(rb_n, struct node_data, r0); + if (lookup_key == n->key0) + break; + if (nr_gc < NR_NODES) + gc_ns[nr_gc++] = rb_n; + if (lookup_key < n->key0) + rb_n = bpf_rbtree_left(&groot0, rb_n); + else + rb_n = bpf_rbtree_right(&groot0, rb_n); + } + + if (!n || lookup_key != n->key0) { + bpf_spin_unlock(&glock0); + return __LINE__; + } + + for (i = 0; i < nr_gc; i++) { + rb_n = gc_ns[i]; + gc_ns[i] = bpf_rbtree_remove(&groot0, rb_n); + } + + m = bpf_refcount_acquire(n); + bpf_spin_unlock(&glock0); + + for (i = 0; i < nr_gc; i++) { + rb_n = gc_ns[i]; + if (rb_n) { + n = rb_entry(rb_n, struct node_data, r0); + bpf_obj_drop(n); + } + } + + if (!m) + return __LINE__; + + bpf_spin_lock(&glock1); + rb_m = bpf_rbtree_remove(&groot1, &m->r1); + bpf_spin_unlock(&glock1); + bpf_obj_drop(m); + if (!rb_m) + return __LINE__; + bpf_obj_drop(rb_entry(rb_m, struct node_data, r1)); + + return 0; +} + +#define TEST_ROOT(dolock) \ +SEC("syscall") \ +__failure __msg(MSG) \ +long test_root_spinlock_##dolock(void *ctx) \ +{ \ + struct bpf_rb_node *rb_n; \ + __u64 jiffies = 0; \ + \ + if (dolock) \ + bpf_spin_lock(&glock0); \ + rb_n = bpf_rbtree_root(&groot0); \ + if (rb_n) \ + jiffies = bpf_jiffies64(); \ + if (dolock) \ + bpf_spin_unlock(&glock0); \ + \ + return !!jiffies; \ +} + +#define TEST_LR(op, dolock) \ +SEC("syscall") \ +__failure __msg(MSG) \ +long test_##op##_spinlock_##dolock(void *ctx) \ +{ \ + struct bpf_rb_node *rb_n; \ + struct node_data *n; \ + __u64 jiffies = 0; \ + \ + bpf_spin_lock(&glock0); \ + rb_n = bpf_rbtree_root(&groot0); \ + if (!rb_n) { \ + bpf_spin_unlock(&glock0); \ + return 1; \ + } \ + n = rb_entry(rb_n, struct node_data, r0); \ + n = bpf_refcount_acquire(n); \ + bpf_spin_unlock(&glock0); \ + if (!n) \ + return 1; \ + \ + if (dolock) \ + bpf_spin_lock(&glock0); \ + rb_n = bpf_rbtree_##op(&groot0, &n->r0); \ + if (rb_n) \ + jiffies = bpf_jiffies64(); \ + if (dolock) \ + bpf_spin_unlock(&glock0); \ + \ + return !!jiffies; \ +} + +/* + * Use a spearate 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 + * instead of the log generated by the verifier. + */ +#define MSG "call bpf_rbtree_root{{.+}}; R0{{(_w)?}}=rcu_ptr_or_null_node_data(id={{[0-9]+}},non_own_ref" +TEST_ROOT(true) +#undef MSG +#define MSG "call bpf_rbtree_{{(left|right).+}}; R0{{(_w)?}}=rcu_ptr_or_null_node_data(id={{[0-9]+}},non_own_ref" +TEST_LR(left, true) +TEST_LR(right, true) +#undef MSG + +#define MSG "bpf_spin_lock at off=0 must be held for bpf_rb_root" +TEST_ROOT(false) +TEST_LR(left, false) +TEST_LR(right, false) +#undef MSG + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/set_global_vars.c b/tools/testing/selftests/bpf/progs/set_global_vars.c index 9adb5ba4cd4d..90f5656c3991 100644 --- a/tools/testing/selftests/bpf/progs/set_global_vars.c +++ b/tools/testing/selftests/bpf/progs/set_global_vars.c @@ -24,6 +24,44 @@ const volatile enum Enumu64 var_eb = EB1; const volatile enum Enums64 var_ec = EC1; const volatile bool var_b = false; +struct Struct { + int:16; + __u16 filler; + struct { + const __u16 filler2; + }; + struct Struct2 { + __u16 filler; + volatile struct { + const int:1; + union { + const volatile __u8 var_u8; + const volatile __s16 filler3; + const int:1; + } u; + }; + } struct2; +}; + +const volatile __u32 stru = 0; /* same prefix as below */ +const volatile struct Struct struct1 = {.struct2 = {.u = {.var_u8 = 1}}}; + +union Union { + __u16 var_u16; + struct Struct3 { + struct { + __u8 var_u8_l; + }; + struct { + struct { + __u8 var_u8_h; + }; + }; + } struct3; +}; + +const volatile union Union union1 = {.var_u16 = -1}; + char arr[4] = {0}; SEC("socket") @@ -43,5 +81,8 @@ int test_set_globals(void *ctx) a = var_eb; a = var_ec; a = var_b; + a = struct1.struct2.u.var_u8; + a = union1.var_u16; + return a; } diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c index 0107a24b7522..d330b1511979 100644 --- a/tools/testing/selftests/bpf/progs/setget_sockopt.c +++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c @@ -83,6 +83,14 @@ struct loop_ctx { struct sock *sk; }; +static bool sk_is_tcp(struct sock *sk) +{ + return (sk->__sk_common.skc_family == AF_INET || + sk->__sk_common.skc_family == AF_INET6) && + sk->sk_type == SOCK_STREAM && + sk->sk_protocol == IPPROTO_TCP; +} + static int bpf_test_sockopt_flip(void *ctx, struct sock *sk, const struct sockopt_test *t, int level) @@ -91,6 +99,9 @@ static int bpf_test_sockopt_flip(void *ctx, struct sock *sk, opt = t->opt; + if (opt == SO_TXREHASH && !sk_is_tcp(sk)) + return 0; + if (bpf_getsockopt(ctx, level, opt, &old, sizeof(old))) return 1; /* kernel initialized txrehash to 255 */ diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c index 96531b0d9d55..8f483337e103 100644 --- a/tools/testing/selftests/bpf/progs/sock_iter_batch.c +++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c @@ -17,6 +17,12 @@ static bool ipv6_addr_loopback(const struct in6_addr *a) a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0; } +static bool ipv4_addr_loopback(__be32 a) +{ + return a == bpf_ntohl(0x7f000001); +} + +volatile const unsigned int sf; volatile const __u16 ports[2]; unsigned int bucket[2]; @@ -26,16 +32,20 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) struct sock *sk = (struct sock *)ctx->sk_common; struct inet_hashinfo *hinfo; unsigned int hash; + __u64 sock_cookie; struct net *net; int idx; if (!sk) return 0; + sock_cookie = bpf_get_socket_cookie(sk); sk = bpf_core_cast(sk, struct sock); - if (sk->sk_family != AF_INET6 || + if (sk->sk_family != sf || sk->sk_state != TCP_LISTEN || - !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr)) + sk->sk_family == AF_INET6 ? + !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) : + !ipv4_addr_loopback(sk->sk_rcv_saddr)) return 0; if (sk->sk_num == ports[0]) @@ -52,6 +62,7 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) hinfo = net->ipv4.tcp_death_row.hashinfo; bucket[idx] = hash & hinfo->lhash2_mask; bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx)); + bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie)); return 0; } @@ -63,14 +74,18 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx) { struct sock *sk = (struct sock *)ctx->udp_sk; struct udp_table *udptable; + __u64 sock_cookie; int idx; if (!sk) return 0; + sock_cookie = bpf_get_socket_cookie(sk); sk = bpf_core_cast(sk, struct sock); - if (sk->sk_family != AF_INET6 || - !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr)) + if (sk->sk_family != sf || + sk->sk_family == AF_INET6 ? + !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) : + !ipv4_addr_loopback(sk->sk_rcv_saddr)) return 0; if (sk->sk_num == ports[0]) @@ -84,6 +99,7 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx) udptable = sk->sk_net.net->ipv4.udp_table; bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask; bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx)); + bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie)); return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_btf_ext.c b/tools/testing/selftests/bpf/progs/test_btf_ext.c new file mode 100644 index 000000000000..cdf20331db04 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_btf_ext.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2025 Meta Platforms Inc. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +__noinline static void f0(void) +{ + __u64 a = 1; + + __sink(a); +} + +SEC("xdp") +__u64 global_func(struct xdp_md *xdp) +{ + f0(); + return XDP_DROP; +} diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c index 7f3c233943b3..03d7f89787a1 100644 --- a/tools/testing/selftests/bpf/progs/test_module_attach.c +++ b/tools/testing/selftests/bpf/progs/test_module_attach.c @@ -19,7 +19,7 @@ int BPF_PROG(handle_raw_tp, __u32 raw_tp_bare_write_sz = 0; -SEC("raw_tp/bpf_testmod_test_write_bare") +SEC("raw_tp/bpf_testmod_test_write_bare_tp") int BPF_PROG(handle_raw_tp_bare, struct task_struct *task, struct bpf_testmod_test_write_ctx *write_ctx) { @@ -31,7 +31,7 @@ int raw_tp_writable_bare_in_val = 0; int raw_tp_writable_bare_early_ret = 0; int raw_tp_writable_bare_out_val = 0; -SEC("raw_tp.w/bpf_testmod_test_writable_bare") +SEC("raw_tp.w/bpf_testmod_test_writable_bare_tp") int BPF_PROG(handle_raw_tp_writable_bare, struct bpf_testmod_test_writable_ctx *writable) { diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c new file mode 100644 index 000000000000..8bdb9987c0c7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +int cork_byte; +int push_start; +int push_end; +int apply_bytes; + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map SEC(".maps"); + +SEC("sk_msg") +int prog_sk_policy(struct sk_msg_md *msg) +{ + if (cork_byte > 0) + bpf_msg_cork_bytes(msg, cork_byte); + if (push_start > 0 && push_end > 0) + bpf_msg_push_data(msg, push_start, push_end, 0); + + return SK_PASS; +} + +SEC("sk_msg") +int prog_sk_policy_redir(struct sk_msg_md *msg) +{ + int two = 2; + + bpf_msg_apply_bytes(msg, apply_bytes); + return bpf_msg_redirect_map(msg, &sock_map, two, 0); +} diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_redir.c b/tools/testing/selftests/bpf/progs/test_sockmap_redir.c new file mode 100644 index 000000000000..34d9f4f2f0a2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_redir.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC(".maps") struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} nop_map, sock_map; + +SEC(".maps") struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} nop_hash, sock_hash; + +SEC(".maps") struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, unsigned int); +} verdict_map; + +/* Set by user space */ +int redirect_type; +int redirect_flags; + +#define redirect_map(__data) \ + _Generic((__data), \ + struct __sk_buff * : bpf_sk_redirect_map, \ + struct sk_msg_md * : bpf_msg_redirect_map \ + )((__data), &sock_map, (__u32){0}, redirect_flags) + +#define redirect_hash(__data) \ + _Generic((__data), \ + struct __sk_buff * : bpf_sk_redirect_hash, \ + struct sk_msg_md * : bpf_msg_redirect_hash \ + )((__data), &sock_hash, &(__u32){0}, redirect_flags) + +#define DEFINE_PROG(__type, __param) \ +SEC("sk_" XSTR(__type)) \ +int prog_ ## __type ## _verdict(__param data) \ +{ \ + unsigned int *count; \ + int verdict; \ + \ + if (redirect_type == BPF_MAP_TYPE_SOCKMAP) \ + verdict = redirect_map(data); \ + else if (redirect_type == BPF_MAP_TYPE_SOCKHASH) \ + verdict = redirect_hash(data); \ + else \ + verdict = redirect_type - __MAX_BPF_MAP_TYPE; \ + \ + count = bpf_map_lookup_elem(&verdict_map, &verdict); \ + if (count) \ + (*count)++; \ + \ + return verdict; \ +} + +DEFINE_PROG(skb, struct __sk_buff *); +DEFINE_PROG(msg, struct sk_msg_md *); + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c index eb5cca1fce16..7d5293de1952 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c @@ -294,7 +294,9 @@ static int tcp_validate_sysctl(struct tcp_syncookie *ctx) (ctx->ipv6 && ctx->attrs.mss != MSS_LOCAL_IPV6)) goto err; - if (!ctx->attrs.wscale_ok || ctx->attrs.snd_wscale != 7) + if (!ctx->attrs.wscale_ok || + !ctx->attrs.snd_wscale || + ctx->attrs.snd_wscale >= BPF_SYNCOOKIE_WSCALE_MASK) goto err; if (!ctx->attrs.tstamp_ok) diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c index 39ff06f2c834..cf0547a613ff 100644 --- a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c +++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c @@ -6,14 +6,14 @@ #include "../test_kmods/bpf_testmod.h" #include "bpf_misc.h" -SEC("tp_btf/bpf_testmod_test_nullable_bare") +SEC("tp_btf/bpf_testmod_test_nullable_bare_tp") __failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx) { return nullable_ctx->len; } -SEC("tp_btf/bpf_testmod_test_nullable_bare") +SEC("tp_btf/bpf_testmod_test_nullable_bare_tp") int BPF_PROG(handle_tp_btf_nullable_bare2, struct bpf_testmod_test_read_ctx *nullable_ctx) { if (nullable_ctx) diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_trap.c b/tools/testing/selftests/bpf/progs/verifier_bpf_trap.c new file mode 100644 index 000000000000..35e2cdc00a01 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bpf_trap.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +#if __clang_major__ >= 21 && 0 +SEC("socket") +__description("__builtin_trap with simple c code") +__failure __msg("unexpected __bpf_trap() due to uninitialized variable?") +void bpf_builtin_trap_with_simple_c(void) +{ + __builtin_trap(); +} +#endif + +SEC("socket") +__description("__bpf_trap with simple c code") +__failure __msg("unexpected __bpf_trap() due to uninitialized variable?") +void bpf_trap_with_simple_c(void) +{ + __bpf_trap(); +} + +SEC("socket") +__description("__bpf_trap as the second-from-last insn") +__failure __msg("unexpected __bpf_trap() due to uninitialized variable?") +__naked void bpf_trap_at_func_end(void) +{ + asm volatile ( + "r0 = 0;" + "call %[__bpf_trap];" + "exit;" + : + : __imm(__bpf_trap) + : __clobber_all); +} + +SEC("socket") +__description("dead code __bpf_trap in the middle of code") +__success +__naked void dead_bpf_trap_in_middle(void) +{ + asm volatile ( + "r0 = 0;" + "if r0 == 0 goto +1;" + "call %[__bpf_trap];" + "r0 = 2;" + "exit;" + : + : __imm(__bpf_trap) + : __clobber_all); +} + +SEC("socket") +__description("reachable __bpf_trap in the middle of code") +__failure __msg("unexpected __bpf_trap() due to uninitialized variable?") +__naked void live_bpf_trap_in_middle(void) +{ + asm volatile ( + "r0 = 0;" + "if r0 == 1 goto +1;" + "call %[__bpf_trap];" + "r0 = 2;" + "exit;" + : + : __imm(__bpf_trap) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c index 28b939572cda..03942cec07e5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c @@ -65,4 +65,16 @@ __naked void ctx_access_u32_pointer_reject_8(void) " ::: __clobber_all); } +SEC("fentry/bpf_fentry_test10") +__description("btf_ctx_access const void pointer accept") +__success __retval(0) +__naked void ctx_access_const_void_pointer_accept(void) +{ + asm volatile (" \ + r2 = *(u64 *)(r1 + 0); /* load 1st argument value (const void pointer) */\ + r0 = 0; \ + exit; \ +" ::: __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_load_acquire.c b/tools/testing/selftests/bpf/progs/verifier_load_acquire.c index 77698d5a19e4..74f4f19c10b8 100644 --- a/tools/testing/selftests/bpf/progs/verifier_load_acquire.c +++ b/tools/testing/selftests/bpf/progs/verifier_load_acquire.c @@ -10,65 +10,81 @@ SEC("socket") __description("load-acquire, 8-bit") -__success __success_unpriv __retval(0x12) +__success __success_unpriv __retval(0) __naked void load_acquire_8(void) { asm volatile ( - "w1 = 0x12;" + "r0 = 0;" + "w1 = 0xfe;" "*(u8 *)(r10 - 1) = w1;" - ".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r10 - 1)); + ".8byte %[load_acquire_insn];" // w2 = load_acquire((u8 *)(r10 - 1)); + "if r2 == r1 goto 1f;" + "r0 = 1;" +"1:" "exit;" : : __imm_insn(load_acquire_insn, - BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -1)) + BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -1)) : __clobber_all); } SEC("socket") __description("load-acquire, 16-bit") -__success __success_unpriv __retval(0x1234) +__success __success_unpriv __retval(0) __naked void load_acquire_16(void) { asm volatile ( - "w1 = 0x1234;" + "r0 = 0;" + "w1 = 0xfedc;" "*(u16 *)(r10 - 2) = w1;" - ".8byte %[load_acquire_insn];" // w0 = load_acquire((u16 *)(r10 - 2)); + ".8byte %[load_acquire_insn];" // w2 = load_acquire((u16 *)(r10 - 2)); + "if r2 == r1 goto 1f;" + "r0 = 1;" +"1:" "exit;" : : __imm_insn(load_acquire_insn, - BPF_ATOMIC_OP(BPF_H, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -2)) + BPF_ATOMIC_OP(BPF_H, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -2)) : __clobber_all); } SEC("socket") __description("load-acquire, 32-bit") -__success __success_unpriv __retval(0x12345678) +__success __success_unpriv __retval(0) __naked void load_acquire_32(void) { asm volatile ( - "w1 = 0x12345678;" + "r0 = 0;" + "w1 = 0xfedcba09;" "*(u32 *)(r10 - 4) = w1;" - ".8byte %[load_acquire_insn];" // w0 = load_acquire((u32 *)(r10 - 4)); + ".8byte %[load_acquire_insn];" // w2 = load_acquire((u32 *)(r10 - 4)); + "if r2 == r1 goto 1f;" + "r0 = 1;" +"1:" "exit;" : : __imm_insn(load_acquire_insn, - BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -4)) + BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -4)) : __clobber_all); } SEC("socket") __description("load-acquire, 64-bit") -__success __success_unpriv __retval(0x1234567890abcdef) +__success __success_unpriv __retval(0) __naked void load_acquire_64(void) { asm volatile ( - "r1 = 0x1234567890abcdef ll;" + "r0 = 0;" + "r1 = 0xfedcba0987654321 ll;" "*(u64 *)(r10 - 8) = r1;" - ".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r10 - 8)); + ".8byte %[load_acquire_insn];" // r2 = load_acquire((u64 *)(r10 - 8)); + "if r2 == r1 goto 1f;" + "r0 = 1;" +"1:" "exit;" : : __imm_insn(load_acquire_insn, - BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -8)) + BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -8)) : __clobber_all); } diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c index 6662d4b39969..9fe5d255ee37 100644 --- a/tools/testing/selftests/bpf/progs/verifier_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_precision.c @@ -91,8 +91,7 @@ __naked int bpf_end_bswap(void) ::: __clobber_all); } -#if defined(ENABLE_ATOMICS_TESTS) && \ - (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) +#ifdef CAN_USE_LOAD_ACQ_STORE_REL SEC("?raw_tp") __success __log_level(2) @@ -138,7 +137,7 @@ __naked int bpf_store_release(void) : __clobber_all); } -#endif /* load-acquire, store-release */ +#endif /* CAN_USE_LOAD_ACQ_STORE_REL */ #endif /* v4 instruction */ SEC("?raw_tp") @@ -179,4 +178,57 @@ __naked int state_loop_first_last_equal(void) ); } +__used __naked static void __bpf_cond_op_r10(void) +{ + asm volatile ( + "r2 = 2314885393468386424 ll;" + "goto +0;" + "if r2 <= r10 goto +3;" + "if r1 >= -1835016 goto +0;" + "if r2 <= 8 goto +0;" + "if r3 <= 0 goto +0;" + "exit;" + ::: __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("8: (bd) if r2 <= r10 goto pc+3") +__msg("9: (35) if r1 >= 0xffe3fff8 goto pc+0") +__msg("10: (b5) if r2 <= 0x8 goto pc+0") +__msg("mark_precise: frame1: last_idx 10 first_idx 0 subseq_idx -1") +__msg("mark_precise: frame1: regs=r2 stack= before 9: (35) if r1 >= 0xffe3fff8 goto pc+0") +__msg("mark_precise: frame1: regs=r2 stack= before 8: (bd) if r2 <= r10 goto pc+3") +__msg("mark_precise: frame1: regs=r2 stack= before 7: (05) goto pc+0") +__naked void bpf_cond_op_r10(void) +{ + asm volatile ( + "r3 = 0 ll;" + "call __bpf_cond_op_r10;" + "r0 = 0;" + "exit;" + ::: __clobber_all); +} + +SEC("?raw_tp") +__success __log_level(2) +__msg("3: (bf) r3 = r10") +__msg("4: (bd) if r3 <= r2 goto pc+1") +__msg("5: (b5) if r2 <= 0x8 goto pc+2") +__msg("mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1") +__msg("mark_precise: frame0: regs=r2 stack= before 4: (bd) if r3 <= r2 goto pc+1") +__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r3 = r10") +__naked void bpf_cond_op_not_r10(void) +{ + asm volatile ( + "r0 = 0;" + "r2 = 2314885393468386424 ll;" + "r3 = r10;" + "if r3 <= r2 goto +1;" + "if r2 <= 8 goto +2;" + "r0 = 2 ll;" + "exit;" + ::: __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_store_release.c b/tools/testing/selftests/bpf/progs/verifier_store_release.c index c0442d5bb049..72f1eb006074 100644 --- a/tools/testing/selftests/bpf/progs/verifier_store_release.c +++ b/tools/testing/selftests/bpf/progs/verifier_store_release.c @@ -6,18 +6,21 @@ #include "../../../include/linux/filter.h" #include "bpf_misc.h" -#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \ - (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)) +#ifdef CAN_USE_LOAD_ACQ_STORE_REL SEC("socket") __description("store-release, 8-bit") -__success __success_unpriv __retval(0x12) +__success __success_unpriv __retval(0) __naked void store_release_8(void) { asm volatile ( + "r0 = 0;" "w1 = 0x12;" ".8byte %[store_release_insn];" // store_release((u8 *)(r10 - 1), w1); - "w0 = *(u8 *)(r10 - 1);" + "w2 = *(u8 *)(r10 - 1);" + "if r2 == r1 goto 1f;" + "r0 = 1;" +"1:" "exit;" : : __imm_insn(store_release_insn, @@ -27,13 +30,17 @@ __naked void store_release_8(void) SEC("socket") __description("store-release, 16-bit") -__success __success_unpriv __retval(0x1234) +__success __success_unpriv __retval(0) __naked void store_release_16(void) { asm volatile ( + "r0 = 0;" "w1 = 0x1234;" ".8byte %[store_release_insn];" // store_release((u16 *)(r10 - 2), w1); - "w0 = *(u16 *)(r10 - 2);" + "w2 = *(u16 *)(r10 - 2);" + "if r2 == r1 goto 1f;" + "r0 = 1;" +"1:" "exit;" : : __imm_insn(store_release_insn, @@ -43,13 +50,17 @@ __naked void store_release_16(void) SEC("socket") __description("store-release, 32-bit") -__success __success_unpriv __retval(0x12345678) +__success __success_unpriv __retval(0) __naked void store_release_32(void) { asm volatile ( + "r0 = 0;" "w1 = 0x12345678;" ".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 4), w1); - "w0 = *(u32 *)(r10 - 4);" + "w2 = *(u32 *)(r10 - 4);" + "if r2 == r1 goto 1f;" + "r0 = 1;" +"1:" "exit;" : : __imm_insn(store_release_insn, @@ -59,13 +70,17 @@ __naked void store_release_32(void) SEC("socket") __description("store-release, 64-bit") -__success __success_unpriv __retval(0x1234567890abcdef) +__success __success_unpriv __retval(0) __naked void store_release_64(void) { asm volatile ( + "r0 = 0;" "r1 = 0x1234567890abcdef ll;" ".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1); - "r0 = *(u64 *)(r10 - 8);" + "r2 = *(u64 *)(r10 - 8);" + "if r2 == r1 goto 1f;" + "r0 = 1;" +"1:" "exit;" : : __imm_insn(store_release_insn, @@ -271,7 +286,7 @@ __naked void store_release_with_invalid_reg(void) : __clobber_all); } -#else +#else /* CAN_USE_LOAD_ACQ_STORE_REL */ SEC("socket") __description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support store-release, use a dummy test") @@ -281,6 +296,6 @@ int dummy_test(void) return 0; } -#endif +#endif /* CAN_USE_LOAD_ACQ_STORE_REL */ char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c index 31ca229bb3c0..09bb8a038d52 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c @@ -19,6 +19,13 @@ struct { __type(value, __u32); } prog_arr SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 1); +} dev_map SEC(".maps"); + extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, @@ -95,4 +102,10 @@ int rx(struct xdp_md *ctx) return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } +SEC("xdp") +int redirect(struct xdp_md *ctx) +{ + return bpf_redirect_map(&dev_map, ctx->rx_queue_index, XDP_PASS); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c index ccde6a4c6319..683306db8594 100644 --- a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c +++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c @@ -4,6 +4,8 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/errno.h> #include "xsk_xdp_common.h" struct { @@ -14,6 +16,7 @@ struct { } xsk SEC(".maps"); static unsigned int idx; +int adjust_value = 0; int count = 0; SEC("xdp.frags") int xsk_def_prog(struct xdp_md *xdp) @@ -70,4 +73,51 @@ SEC("xdp") int xsk_xdp_shared_umem(struct xdp_md *xdp) return bpf_redirect_map(&xsk, idx, XDP_DROP); } +SEC("xdp.frags") int xsk_xdp_adjust_tail(struct xdp_md *xdp) +{ + __u32 buff_len, curr_buff_len; + int ret; + + buff_len = bpf_xdp_get_buff_len(xdp); + if (buff_len == 0) + return XDP_DROP; + + ret = bpf_xdp_adjust_tail(xdp, adjust_value); + if (ret < 0) { + /* Handle unsupported cases */ + if (ret == -EOPNOTSUPP) { + /* Set adjust_value to -EOPNOTSUPP to indicate to userspace that this case + * is unsupported + */ + adjust_value = -EOPNOTSUPP; + return bpf_redirect_map(&xsk, 0, XDP_DROP); + } + + return XDP_DROP; + } + + curr_buff_len = bpf_xdp_get_buff_len(xdp); + if (curr_buff_len != buff_len + adjust_value) + return XDP_DROP; + + if (curr_buff_len > buff_len) { + __u32 *pkt_data = (void *)(long)xdp->data; + __u32 len, words_to_end, seq_num; + + len = curr_buff_len - PKT_HDR_ALIGN; + words_to_end = len / sizeof(*pkt_data) - 1; + seq_num = words_to_end; + + /* Convert sequence number to network byte order. Store this in the last 4 bytes of + * the packet. Use 'adjust_value' to determine the position at the end of the + * packet for storing the sequence number. + */ + seq_num = __constant_htonl(words_to_end); + bpf_xdp_store_bytes(xdp, curr_buff_len - sizeof(seq_num), &seq_num, + sizeof(seq_num)); + } + + return bpf_redirect_map(&xsk, 0, XDP_DROP); +} + char _license[] SEC("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 3220f1d28697..e6c248e3ae54 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c @@ -134,6 +134,10 @@ bpf_testmod_test_arg_ptr_to_struct(struct bpf_testmod_struct_arg_1 *a) { return bpf_testmod_test_struct_arg_result; } +__weak noinline void bpf_testmod_looooooooooooooooooooooooooooooong_name(void) +{ +} + __bpf_kfunc void bpf_testmod_test_mod_kfunc(int i) { @@ -413,7 +417,7 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, (void)bpf_testmod_test_arg_ptr_to_struct(&struct_arg1_2); - (void)trace_bpf_testmod_test_raw_tp_null(NULL); + (void)trace_bpf_testmod_test_raw_tp_null_tp(NULL); bpf_testmod_test_struct_ops3(); @@ -431,14 +435,14 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, if (bpf_testmod_loop_test(101) > 100) trace_bpf_testmod_test_read(current, &ctx); - trace_bpf_testmod_test_nullable_bare(NULL); + trace_bpf_testmod_test_nullable_bare_tp(NULL); /* Magic number to enable writable tp */ if (len == 64) { struct bpf_testmod_test_writable_ctx writable = { .val = 1024, }; - trace_bpf_testmod_test_writable_bare(&writable); + trace_bpf_testmod_test_writable_bare_tp(&writable); if (writable.early_ret) return snprintf(buf, len, "%d\n", writable.val); } @@ -470,7 +474,7 @@ bpf_testmod_test_write(struct file *file, struct kobject *kobj, .len = len, }; - trace_bpf_testmod_test_write_bare(current, &ctx); + trace_bpf_testmod_test_write_bare_tp(current, &ctx); return -EIO; /* always fail */ } @@ -1340,7 +1344,7 @@ static int st_ops_gen_prologue_with_kfunc(struct bpf_insn *insn_buf, bool direct *insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, offsetof(struct st_ops_args, a)); *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 2); *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0); - *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_release_id), + *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_release_id); *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_8); *insn++ = prog->insnsi[0]; @@ -1379,7 +1383,7 @@ static int st_ops_gen_epilogue_with_kfunc(struct bpf_insn *insn_buf, const struc *insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, offsetof(struct st_ops_args, a)); *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 2); *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0); - *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_release_id), + *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_release_id); *insn++ = BPF_MOV64_REG(BPF_REG_0, BPF_REG_6); *insn++ = BPF_ALU64_IMM(BPF_MUL, BPF_REG_0, 2); *insn++ = BPF_EXIT_INSN(); diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index 49f2fc61061f..9551d8d5f8f9 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -1042,6 +1042,14 @@ void run_subtest(struct test_loader *tester, emit_verifier_log(tester->log_buf, false /*force*/); validate_msgs(tester->log_buf, &subspec->expect_msgs, emit_verifier_log); + /* Restore capabilities because the kernel will silently ignore requests + * for program info (such as xlated program text) if we are not + * bpf-capable. Also, for some reason test_verifier executes programs + * with all capabilities restored. Do the same here. + */ + if (restore_capabilities(&caps)) + goto tobj_cleanup; + if (subspec->expect_xlated.cnt) { err = get_xlated_program_text(bpf_program__fd(tprog), tester->log_buf, tester->log_buf_sz); @@ -1067,12 +1075,6 @@ void run_subtest(struct test_loader *tester, } if (should_do_test_run(spec, subspec)) { - /* For some reason test_verifier executes programs - * with all capabilities restored. Do the same here. - */ - if (restore_capabilities(&caps)) - goto tobj_cleanup; - /* Do bpf_map__attach_struct_ops() for each struct_ops map. * This should trigger bpf_struct_ops->reg callback on kernel side. */ diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 447b68509d76..27db34ecf3f5 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -734,7 +734,7 @@ static __u32 btf_raw_types[] = { BTF_MEMBER_ENC(71, 13, 128), /* struct prog_test_member __kptr *ptr; */ }; -static char bpf_vlog[UINT_MAX >> 8]; +static char bpf_vlog[UINT_MAX >> 5]; static int load_btf_spec(__u32 *types, int types_len, const char *strings, int strings_len) @@ -1559,10 +1559,10 @@ static void do_test_single(struct bpf_test *test, bool unpriv, test->errstr_unpriv : test->errstr; opts.expected_attach_type = test->expected_attach_type; - if (verbose) - opts.log_level = verif_log_level | 4; /* force stats */ - else if (expected_ret == VERBOSE_ACCEPT) + if (expected_ret == VERBOSE_ACCEPT) opts.log_level = 2; + else if (verbose) + opts.log_level = verif_log_level | 4; /* force stats */ else opts.log_level = DEFAULT_LIBBPF_LOG_LEVEL; opts.prog_flags = pflags; diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index a18972ffdeb6..b2bb20b00952 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -1486,7 +1486,84 @@ static bool is_preset_supported(const struct btf_type *t) return btf_is_int(t) || btf_is_enum(t) || btf_is_enum64(t); } -static int set_global_var(struct bpf_object *obj, struct btf *btf, const struct btf_type *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) +{ + int i; + + if (!btf_is_composite(parent_type)) + return -EINVAL; + + for (i = 0; i < btf_vlen(parent_type); ++i) { + const struct btf_member *member; + const struct btf_type *member_type; + int tid; + + member = btf_members(parent_type) + i; + tid = btf__resolve_type(btf, member->type); + if (tid < 0) + return -EINVAL; + + member_type = btf__type_by_id(btf, tid); + if (member->name_off) { + const char *name = btf__name_by_offset(btf, member->name_off); + + if (strcmp(member_name, name) == 0) { + if (btf_member_bitfield_size(parent_type, i) != 0) { + fprintf(stderr, "Bitfield presets are not supported %s\n", + name); + return -EINVAL; + } + *member_offset = parent_offset + member->offset; + *member_tid = tid; + 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); + if (!err) + return 0; + } + } + + return -EINVAL; +} + +static int adjust_var_secinfo(struct btf *btf, const struct btf_type *t, + struct btf_var_secinfo *sinfo, const char *var) +{ + char expr[256], *saveptr; + const struct btf_type *base_type, *member_type; + int err, member_tid; + char *name; + __u32 member_offset = 0; + + base_type = btf__type_by_id(btf, btf__resolve_type(btf, t->type)); + snprintf(expr, sizeof(expr), "%s", var); + strtok_r(expr, ".", &saveptr); + + 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; + } + 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; + } + return 0; +} + +static int set_global_var(struct bpf_object *obj, struct btf *btf, struct bpf_map *map, struct btf_var_secinfo *sinfo, struct var_preset *preset) { @@ -1495,9 +1572,9 @@ static int set_global_var(struct bpf_object *obj, struct btf *btf, const struct long long value = preset->ivalue; size_t size; - base_type = btf__type_by_id(btf, btf__resolve_type(btf, t->type)); + base_type = btf__type_by_id(btf, btf__resolve_type(btf, sinfo->type)); if (!base_type) { - fprintf(stderr, "Failed to resolve type %d\n", t->type); + fprintf(stderr, "Failed to resolve type %d\n", sinfo->type); return -EINVAL; } if (!is_preset_supported(base_type)) { @@ -1530,7 +1607,7 @@ static int set_global_var(struct bpf_object *obj, struct btf *btf, const struct if (value >= max_val || value < -max_val) { fprintf(stderr, "Variable %s value %lld is out of range [%lld; %lld]\n", - btf__name_by_offset(btf, t->name_off), value, + btf__name_by_offset(btf, base_type->name_off), value, is_signed ? -max_val : 0, max_val - 1); return -EINVAL; } @@ -1583,14 +1660,20 @@ 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) { - if (strcmp(var_name, presets[k].name) != 0) + 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] != '.')) continue; if (presets[k].applied) { @@ -1598,13 +1681,17 @@ static int set_global_vars(struct bpf_object *obj, struct var_preset *presets, i var_name); return -EINVAL; } + tmp_sinfo = *sinfo; + err = adjust_var_secinfo(btf, var_type, + &tmp_sinfo, presets[k].name); + if (err) + return err; - err = set_global_var(obj, btf, var_type, map, sinfo, presets + k); + err = set_global_var(obj, btf, map, &tmp_sinfo, presets + k); if (err) return err; presets[k].applied = true; - break; } } } diff --git a/tools/testing/selftests/bpf/xsk_xdp_common.h b/tools/testing/selftests/bpf/xsk_xdp_common.h index 5a6f36f07383..45810ff552da 100644 --- a/tools/testing/selftests/bpf/xsk_xdp_common.h +++ b/tools/testing/selftests/bpf/xsk_xdp_common.h @@ -4,6 +4,7 @@ #define XSK_XDP_COMMON_H_ #define MAX_SOCKETS 2 +#define PKT_HDR_ALIGN (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */ struct xdp_info { __u64 count; diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index 11f047b8af75..0ced4026ee44 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -524,6 +524,8 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, test->nb_sockets = 1; test->fail = false; test->set_ring = false; + test->adjust_tail = false; + test->adjust_tail_support = false; test->mtu = MAX_ETH_PKT_SIZE; test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog; test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk; @@ -757,14 +759,15 @@ static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream) return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len); } -static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) +static void pkt_stream_replace_ifobject(struct ifobject *ifobj, u32 nb_pkts, u32 pkt_len) { - struct pkt_stream *pkt_stream; + ifobj->xsk->pkt_stream = pkt_stream_generate(nb_pkts, pkt_len); +} - pkt_stream = pkt_stream_generate(nb_pkts, pkt_len); - test->ifobj_tx->xsk->pkt_stream = pkt_stream; - pkt_stream = pkt_stream_generate(nb_pkts, pkt_len); - test->ifobj_rx->xsk->pkt_stream = pkt_stream; +static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) +{ + pkt_stream_replace_ifobject(test->ifobj_tx, nb_pkts, pkt_len); + pkt_stream_replace_ifobject(test->ifobj_rx, nb_pkts, pkt_len); } static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len, @@ -991,6 +994,31 @@ static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) return true; } +static bool is_adjust_tail_supported(struct xsk_xdp_progs *skel_rx) +{ + struct bpf_map *data_map; + int adjust_value = 0; + int key = 0; + int ret; + + 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"); + exit_with_error(errno); + } + + ret = bpf_map_lookup_elem(bpf_map__fd(data_map), &key, &adjust_value); + if (ret) { + ksft_print_msg("Error: bpf_map_lookup_elem failed with error %d\n", ret); + exit_with_error(errno); + } + + /* Set the 'adjust_value' variable to -EOPNOTSUPP in the XDP program if the adjust_tail + * helper is not supported. Skip the adjust_tail test case in this scenario. + */ + return adjust_value != -EOPNOTSUPP; +} + static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb, u32 bytes_processed) { @@ -1767,8 +1795,13 @@ static void *worker_testapp_validate_rx(void *arg) if (!err && ifobject->validation_func) err = ifobject->validation_func(ifobject); - if (err) - report_failure(test); + + if (err) { + if (test->adjust_tail && !is_adjust_tail_supported(ifobject->xdp_progs)) + test->adjust_tail_support = false; + else + report_failure(test); + } pthread_exit(NULL); } @@ -2515,6 +2548,71 @@ static int testapp_hw_sw_max_ring_size(struct test_spec *test) return testapp_validate_traffic(test); } +static int testapp_xdp_adjust_tail(struct test_spec *test, int adjust_value) +{ + struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; + struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; + + test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_adjust_tail, + skel_tx->progs.xsk_xdp_adjust_tail, + skel_rx->maps.xsk, skel_tx->maps.xsk); + + skel_rx->bss->adjust_value = adjust_value; + + return testapp_validate_traffic(test); +} + +static int testapp_adjust_tail(struct test_spec *test, u32 value, u32 pkt_len) +{ + int ret; + + test->adjust_tail_support = true; + test->adjust_tail = true; + test->total_steps = 1; + + pkt_stream_replace_ifobject(test->ifobj_tx, DEFAULT_BATCH_SIZE, pkt_len); + pkt_stream_replace_ifobject(test->ifobj_rx, DEFAULT_BATCH_SIZE, pkt_len + value); + + ret = testapp_xdp_adjust_tail(test, value); + if (ret) + return ret; + + if (!test->adjust_tail_support) { + ksft_test_result_skip("%s %sResize pkt with bpf_xdp_adjust_tail() not supported\n", + mode_string(test), busy_poll_string(test)); + return TEST_SKIP; + } + + return 0; +} + +static int testapp_adjust_tail_shrink(struct test_spec *test) +{ + /* Shrink by 4 bytes for testing purpose */ + return testapp_adjust_tail(test, -4, MIN_PKT_SIZE * 2); +} + +static int testapp_adjust_tail_shrink_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + /* Shrink by the frag size */ + return testapp_adjust_tail(test, -XSK_UMEM__MAX_FRAME_SIZE, XSK_UMEM__LARGE_FRAME_SIZE * 2); +} + +static int testapp_adjust_tail_grow(struct test_spec *test) +{ + /* Grow by 4 bytes for testing purpose */ + return testapp_adjust_tail(test, 4, MIN_PKT_SIZE * 2); +} + +static int testapp_adjust_tail_grow_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + /* Grow by (frag_size - last_frag_Size) - 1 to stay inside the last fragment */ + return testapp_adjust_tail(test, (XSK_UMEM__MAX_FRAME_SIZE / 2) - 1, + XSK_UMEM__LARGE_FRAME_SIZE * 2); +} + static void run_pkt_test(struct test_spec *test) { int ret; @@ -2621,6 +2719,10 @@ static const struct test_spec tests[] = { {.name = "TOO_MANY_FRAGS", .test_func = testapp_too_many_frags}, {.name = "HW_SW_MIN_RING_SIZE", .test_func = testapp_hw_sw_min_ring_size}, {.name = "HW_SW_MAX_RING_SIZE", .test_func = testapp_hw_sw_max_ring_size}, + {.name = "XDP_ADJUST_TAIL_SHRINK", .test_func = testapp_adjust_tail_shrink}, + {.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}, }; static void print_tests(void) diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index e46e823f6a1a..67fc44b2813b 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -173,6 +173,8 @@ struct test_spec { u16 nb_sockets; bool fail; bool set_ring; + bool adjust_tail; + bool adjust_tail_support; enum test_mode mode; char name[MAX_TEST_NAME_SIZE]; }; |