diff options
Diffstat (limited to 'tools')
299 files changed, 16411 insertions, 3793 deletions
diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst index bc276388f432..68454ef28f58 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -25,6 +25,8 @@ GEN COMMANDS | **bpftool** **gen object** *OUTPUT_FILE* *INPUT_FILE* [*INPUT_FILE*...] | **bpftool** **gen skeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen subskeleton** *FILE* [**name** *OBJECT_NAME*] +| **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] | **bpftool** **gen help** DESCRIPTION @@ -149,6 +151,50 @@ DESCRIPTION (non-read-only) data from userspace, with same simplicity as for BPF side. + **bpftool gen subskeleton** *FILE* + Generate BPF subskeleton C header file for a given *FILE*. + + Subskeletons are similar to skeletons, except they do not own + the corresponding maps, programs, or global variables. They + require that the object file used to generate them is already + loaded into a *bpf_object* by some other means. + + This functionality is useful when a library is included into a + larger BPF program. A subskeleton for the library would have + access to all objects and globals defined in it, without + having to know about the larger program. + + Consequently, there are only two functions defined + for subskeletons: + + - **example__open(bpf_object\*)** + Instantiates a subskeleton from an already opened (but not + necessarily loaded) **bpf_object**. + + - **example__destroy()** + Frees the storage for the subskeleton but *does not* unload + any BPF programs or maps. + + **bpftool** **gen min_core_btf** *INPUT* *OUTPUT* *OBJECT* [*OBJECT*...] + Generate a minimum BTF file as *OUTPUT*, derived from a given + *INPUT* BTF file, containing all needed BTF types so one, or + more, given eBPF objects CO-RE relocations may be satisfied. + + When kernels aren't compiled with CONFIG_DEBUG_INFO_BTF, + libbpf, when loading an eBPF object, has to rely on external + BTF files to be able to calculate CO-RE relocations. + + Usually, an external BTF file is built from existing kernel + DWARF data using pahole. It contains all the types used by + its respective kernel image and, because of that, is big. + + The min_core_btf feature builds smaller BTF files, customized + to one or multiple eBPF objects, so they can be distributed + together with an eBPF CO-RE based application, turning the + application portable to different kernel versions. + + Check examples bellow for more information how to use it. + **bpftool gen help** Print short help message. @@ -215,7 +261,9 @@ This is example BPF application with two BPF programs and a mix of BPF maps and global variables. Source code is split across two source code files. **$ clang -target bpf -g example1.bpf.c -o example1.bpf.o** + **$ clang -target bpf -g example2.bpf.c -o example2.bpf.o** + **$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o** This set of commands compiles *example1.bpf.c* and *example2.bpf.c* @@ -329,3 +377,70 @@ BPF ELF object file *example.bpf.o*. my_static_var: 7 This is a stripped-out version of skeleton generated for above example code. + +min_core_btf +------------ + +**$ bpftool btf dump file 5.4.0-example.btf format raw** + +:: + + [1] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [2] CONST '(anon)' type_id=1 + [3] VOLATILE '(anon)' type_id=1 + [4] ARRAY '(anon)' type_id=1 index_type_id=21 nr_elems=2 + [5] PTR '(anon)' type_id=8 + [6] CONST '(anon)' type_id=5 + [7] INT 'char' size=1 bits_offset=0 nr_bits=8 encoding=(none) + [8] CONST '(anon)' type_id=7 + [9] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none) + <long output> + +**$ bpftool btf dump file one.bpf.o format raw** + +:: + + [1] PTR '(anon)' type_id=2 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=4 + 'ent' type_id=3 bits_offset=0 + 'id' type_id=7 bits_offset=64 + 'args' type_id=9 bits_offset=128 + '__data' type_id=12 bits_offset=512 + [3] STRUCT 'trace_entry' size=8 vlen=4 + 'type' type_id=4 bits_offset=0 + 'flags' type_id=5 bits_offset=16 + 'preempt_count' type_id=5 bits_offset=24 + <long output> + +**$ bpftool gen min_core_btf 5.4.0-example.btf 5.4.0-smaller.btf one.bpf.o** + +**$ bpftool btf dump file 5.4.0-smaller.btf format raw** + +:: + + [1] TYPEDEF 'pid_t' type_id=6 + [2] STRUCT 'trace_event_raw_sys_enter' size=64 vlen=1 + 'args' type_id=4 bits_offset=128 + [3] STRUCT 'task_struct' size=9216 vlen=2 + 'pid' type_id=1 bits_offset=17920 + 'real_parent' type_id=7 bits_offset=18048 + [4] ARRAY '(anon)' type_id=5 index_type_id=8 nr_elems=6 + [5] INT 'long unsigned int' size=8 bits_offset=0 nr_bits=64 encoding=(none) + [6] TYPEDEF '__kernel_pid_t' type_id=8 + [7] PTR '(anon)' type_id=3 + [8] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED + <end> + +Now, the "5.4.0-smaller.btf" file may be used by libbpf as an external BTF file +when loading the "one.bpf.o" object into the "5.4.0-example" kernel. Note that +the generated BTF file won't allow other eBPF objects to be loaded, just the +ones given to min_core_btf. + +:: + + LIBBPF_OPTS(bpf_object_open_opts, opts, .btf_custom_path = "5.4.0-smaller.btf"); + struct bpf_object *obj; + + obj = bpf_object__open_file("one.bpf.o", &opts); + + ... diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 7084dd9fa2f8..6965c94dfdaf 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -20,7 +20,8 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** } + *OBJECT* := { **map** | **program** | **link** | **cgroup** | **perf** | **net** | **feature** | + **btf** | **gen** | **struct_ops** | **iter** } *OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| } @@ -31,6 +32,8 @@ SYNOPSIS *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | **load** | **attach** | **detach** | **help** } + *LINK-COMMANDS* := { **show** | **list** | **pin** | **detach** | **help** } + *CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } *PERF-COMMANDS* := { **show** | **list** | **help** } @@ -39,6 +42,14 @@ SYNOPSIS *FEATURE-COMMANDS* := { **probe** | **help** } + *BTF-COMMANDS* := { **show** | **list** | **dump** | **help** } + + *GEN-COMMANDS* := { **object** | **skeleton** | **min_core_btf** | **help** } + + *STRUCT-OPS-COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** } + + *ITER-COMMANDS* := { **pin** | **help** } + DESCRIPTION =========== *bpftool* allows for inspection and simple modification of BPF objects diff --git a/tools/bpf/bpftool/Documentation/common_options.rst b/tools/bpf/bpftool/Documentation/common_options.rst index 908487b9c2ad..4107a586b68b 100644 --- a/tools/bpf/bpftool/Documentation/common_options.rst +++ b/tools/bpf/bpftool/Documentation/common_options.rst @@ -4,12 +4,13 @@ Print short help message (similar to **bpftool help**). -V, --version - Print version number (similar to **bpftool version**), and optional - features that were included when bpftool was compiled. Optional - features include linking against libbfd to provide the disassembler - for JIT-ted programs (**bpftool prog dump jited**) and usage of BPF - skeletons (some features like **bpftool prog profile** or showing - pids associated to BPF objects may rely on it). + Print bpftool's version number (similar to **bpftool version**), the + number of the libbpf version in use, and optional features that were + included when bpftool was compiled. Optional features include linking + against libbfd to provide the disassembler for JIT-ted programs + (**bpftool prog dump jited**) and usage of BPF skeletons (some + features like **bpftool prog profile** or showing pids associated to + BPF objects may rely on it). -j, --json Generate JSON output. For commands that cannot produce JSON, this diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 83369f55df61..9800f966fd51 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -18,37 +18,33 @@ BPF_DIR = $(srctree)/tools/lib/bpf ifneq ($(OUTPUT),) _OUTPUT := $(OUTPUT) else - _OUTPUT := $(CURDIR) + _OUTPUT := $(CURDIR)/ endif -BOOTSTRAP_OUTPUT := $(_OUTPUT)/bootstrap/ +BOOTSTRAP_OUTPUT := $(_OUTPUT)bootstrap/ -LIBBPF_OUTPUT := $(_OUTPUT)/libbpf/ +LIBBPF_OUTPUT := $(_OUTPUT)libbpf/ LIBBPF_DESTDIR := $(LIBBPF_OUTPUT) -LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include +LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf LIBBPF := $(LIBBPF_OUTPUT)libbpf.a LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/ LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT) -LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)/include +LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)include LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a -# We need to copy hashmap.h and nlattr.h which is not otherwise exported by -# libbpf, but still required by bpftool. -LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h) -LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h) - -ifeq ($(BPFTOOL_VERSION),) -BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion) -endif +# We need to copy hashmap.h, nlattr.h, relo_core.h and libbpf_internal.h +# which are not otherwise exported by libbpf, but still required by bpftool. +LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h relo_core.h libbpf_internal.h) +LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h relo_core.h libbpf_internal.h) $(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR): $(QUIET_MKDIR)mkdir -p $@ $(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \ - DESTDIR=$(LIBBPF_DESTDIR) prefix= $(LIBBPF) install_headers + DESTDIR=$(LIBBPF_DESTDIR:/=) prefix= $(LIBBPF) install_headers $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR) $(call QUIET_INSTALL, $@) @@ -56,7 +52,7 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_ $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT) $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \ - DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR) prefix= \ + DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR:/=) prefix= \ ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR) @@ -83,7 +79,9 @@ CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ -I$(srctree)/kernel/bpf/ \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi +ifneq ($(BPFTOOL_VERSION),) CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' +endif ifneq ($(EXTRA_CFLAGS),) CFLAGS += $(EXTRA_CFLAGS) endif @@ -95,7 +93,7 @@ INSTALL ?= install RM ?= rm -f FEATURE_USER = .bpftool -FEATURE_TESTS = libbfd disassembler-four-args reallocarray zlib libcap \ +FEATURE_TESTS = libbfd disassembler-four-args zlib libcap \ clang-bpf-co-re FEATURE_DISPLAY = libbfd disassembler-four-args zlib libcap \ clang-bpf-co-re @@ -120,10 +118,6 @@ ifeq ($(feature-disassembler-four-args), 1) CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE endif -ifeq ($(feature-reallocarray), 0) -CFLAGS += -DCOMPAT_NEED_REALLOCARRAY -endif - LIBS = $(LIBBPF) -lelf -lz LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz ifeq ($(feature-libcap), 1) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 493753a4962e..5df8d72c5179 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -1003,9 +1003,25 @@ _bpftool() ;; esac ;; + subskeleton) + case $prev in + $command) + _filedir + return 0 + ;; + *) + _bpftool_once_attr 'name' + return 0 + ;; + esac + ;; + min_core_btf) + _filedir + return 0 + ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'object skeleton help' -- "$cur" ) ) + COMPREPLY=( $( compgen -W 'object skeleton subskeleton help min_core_btf' -- "$cur" ) ) ;; esac ;; diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 59833125ac0a..a2c665beda87 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -902,7 +902,7 @@ static int do_show(int argc, char **argv) equal_fn_for_key_as_id, NULL); btf_map_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!btf_prog_table || !btf_map_table) { + if (IS_ERR(btf_prog_table) || IS_ERR(btf_map_table)) { hashmap__free(btf_prog_table); hashmap__free(btf_map_table); if (fd >= 0) diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 3571a281c43f..effe136119d7 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -50,6 +50,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, const char *attach_flags_str, int level) { + char prog_name[MAX_PROG_FULL_NAME]; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); int prog_fd; @@ -63,6 +64,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, return -1; } + get_prog_full_name(&info, prog_fd, prog_name, sizeof(prog_name)); if (json_output) { jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info.id); @@ -73,7 +75,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, jsonw_uint_field(json_wtr, "attach_type", attach_type); jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); - jsonw_string_field(json_wtr, "name", info.name); + jsonw_string_field(json_wtr, "name", prog_name); jsonw_end_object(json_wtr); } else { printf("%s%-8u ", level ? " " : "", info.id); @@ -81,7 +83,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, printf("%-15s", attach_type_name[attach_type]); else printf("type %-10u", attach_type); - printf(" %-15s %-15s\n", attach_flags_str, info.name); + printf(" %-15s %-15s\n", attach_flags_str, prog_name); } close(prog_fd); diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index fa8eb8134344..0c1e06cf50b9 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -24,6 +24,7 @@ #include <bpf/bpf.h> #include <bpf/hashmap.h> #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/btf.h> #include "main.h" @@ -55,7 +56,6 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", [BPF_CGROUP_GETSOCKOPT] = "getsockopt", [BPF_CGROUP_SETSOCKOPT] = "setsockopt", - [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", [BPF_SK_SKB_VERDICT] = "sk_skb_verdict", @@ -75,6 +75,7 @@ const char * const attach_type_name[__MAX_BPF_ATTACH_TYPE] = { [BPF_SK_REUSEPORT_SELECT] = "sk_skb_reuseport_select", [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_skb_reuseport_select_or_migrate", [BPF_PERF_EVENT] = "perf_event", + [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", }; void p_err(const char *fmt, ...) @@ -304,6 +305,49 @@ const char *get_fd_type_name(enum bpf_obj_type type) return names[type]; } +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len) +{ + const char *prog_name = prog_info->name; + const struct btf_type *func_type; + const struct bpf_func_info finfo = {}; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + struct btf *prog_btf = NULL; + + if (buff_len <= BPF_OBJ_NAME_LEN || + strlen(prog_info->name) < BPF_OBJ_NAME_LEN - 1) + goto copy_name; + + if (!prog_info->btf_id || prog_info->nr_func_info == 0) + goto copy_name; + + info.nr_func_info = 1; + info.func_info_rec_size = prog_info->func_info_rec_size; + if (info.func_info_rec_size > sizeof(finfo)) + info.func_info_rec_size = sizeof(finfo); + info.func_info = ptr_to_u64(&finfo); + + if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) + goto copy_name; + + prog_btf = btf__load_from_kernel_by_id(info.btf_id); + if (!prog_btf) + goto copy_name; + + func_type = btf__type_by_id(prog_btf, finfo.type_id); + if (!func_type || !btf_is_func(func_type)) + goto copy_name; + + prog_name = btf__name_by_offset(prog_btf, func_type->name_off); + +copy_name: + snprintf(name_buff, buff_len, "%s", prog_name); + + if (prog_btf) + btf__free(prog_btf); +} + int get_fd_type(int fd) { char path[PATH_MAX]; diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index e999159fa28d..c2f43a5d38e0 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -3,6 +3,7 @@ #include <ctype.h> #include <errno.h> +#include <fcntl.h> #include <string.h> #include <unistd.h> #include <net/if.h> @@ -45,6 +46,11 @@ static bool run_as_unprivileged; /* Miscellaneous utility functions */ +static bool grep(const char *buffer, const char *pattern) +{ + return !!strstr(buffer, pattern); +} + static bool check_procfs(void) { struct statfs st_fs; @@ -135,6 +141,32 @@ static void print_end_section(void) /* Probing functions */ +static int get_vendor_id(int ifindex) +{ + char ifname[IF_NAMESIZE], path[64], buf[8]; + ssize_t len; + int fd; + + if (!if_indextoname(ifindex, ifname)) + return -1; + + snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname); + + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) + return -1; + + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len < 0) + return -1; + if (len >= (ssize_t)sizeof(buf)) + return -1; + buf[len] = '\0'; + + return strtol(buf, NULL, 0); +} + static int read_procfs(const char *path) { char *endptr, *line = NULL; @@ -478,6 +510,40 @@ static bool probe_bpf_syscall(const char *define_prefix) return res; } +static bool +probe_prog_load_ifindex(enum bpf_prog_type prog_type, + const struct bpf_insn *insns, size_t insns_cnt, + char *log_buf, size_t log_buf_sz, + __u32 ifindex) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_sz, + .log_level = log_buf ? 1 : 0, + .prog_ifindex = ifindex, + ); + int fd; + + errno = 0; + fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts); + if (fd >= 0) + close(fd); + + return fd >= 0 && errno != EINVAL && errno != EOPNOTSUPP; +} + +static bool probe_prog_type_ifindex(enum bpf_prog_type prog_type, __u32 ifindex) +{ + /* nfp returns -EINVAL on exit(0) with TC offload */ + struct bpf_insn insns[2] = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN() + }; + + return probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), + NULL, 0, ifindex); +} + static void probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, const char *define_prefix, __u32 ifindex) @@ -487,8 +553,7 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, size_t maxlen; bool res; - if (ifindex) - /* Only test offload-able program types */ + if (ifindex) { switch (prog_type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_XDP: @@ -497,7 +562,11 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, return; } - res = bpf_probe_prog_type(prog_type, ifindex); + res = probe_prog_type_ifindex(prog_type, ifindex); + } else { + res = libbpf_probe_bpf_prog_type(prog_type, NULL); + } + #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for unprivileged users * check that we did not fail because of insufficient permissions @@ -526,6 +595,26 @@ probe_prog_type(enum bpf_prog_type prog_type, bool *supported_types, define_prefix); } +static bool probe_map_type_ifindex(enum bpf_map_type map_type, __u32 ifindex) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts); + int key_size, value_size, max_entries; + int fd; + + opts.map_ifindex = ifindex; + + key_size = sizeof(__u32); + value_size = sizeof(__u32); + max_entries = 1; + + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, + &opts); + if (fd >= 0) + close(fd); + + return fd >= 0; +} + static void probe_map_type(enum bpf_map_type map_type, const char *define_prefix, __u32 ifindex) @@ -535,7 +624,19 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, size_t maxlen; bool res; - res = bpf_probe_map_type(map_type, ifindex); + if (ifindex) { + switch (map_type) { + case BPF_MAP_TYPE_HASH: + case BPF_MAP_TYPE_ARRAY: + break; + default: + return; + } + + res = probe_map_type_ifindex(map_type, ifindex); + } else { + res = libbpf_probe_bpf_map_type(map_type, NULL); + } /* Probe result depends on the success of map creation, no additional * check required for unprivileged users @@ -559,6 +660,33 @@ probe_map_type(enum bpf_map_type map_type, const char *define_prefix, define_prefix); } +static bool +probe_helper_ifindex(enum bpf_func_id id, enum bpf_prog_type prog_type, + __u32 ifindex) +{ + struct bpf_insn insns[2] = { + BPF_EMIT_CALL(id), + BPF_EXIT_INSN() + }; + char buf[4096] = {}; + bool res; + + probe_prog_load_ifindex(prog_type, insns, ARRAY_SIZE(insns), buf, + sizeof(buf), ifindex); + res = !grep(buf, "invalid func ") && !grep(buf, "unknown func "); + + switch (get_vendor_id(ifindex)) { + case 0x19ee: /* Netronome specific */ + res = res && !grep(buf, "not supported by FW") && + !grep(buf, "unsupported function id"); + break; + default: + break; + } + + return res; +} + static void probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, const char *define_prefix, unsigned int id, @@ -567,7 +695,10 @@ probe_helper_for_progtype(enum bpf_prog_type prog_type, bool supported_type, bool res = false; if (supported_type) { - res = bpf_probe_helper(id, prog_type, ifindex); + if (ifindex) + res = probe_helper_ifindex(id, prog_type, ifindex); + else + res = libbpf_probe_bpf_helper(prog_type, id, NULL); #ifdef USE_LIBCAP /* Probe may succeed even if program load fails, for * unprivileged users check that we did not fail because of diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index b4695df2ea3d..7ba7ff55d2ea 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -14,6 +14,7 @@ #include <unistd.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/mman.h> @@ -63,11 +64,11 @@ static void get_obj_name(char *name, const char *file) sanitize_identifier(name); } -static void get_header_guard(char *guard, const char *obj_name) +static void get_header_guard(char *guard, const char *obj_name, const char *suffix) { int i; - sprintf(guard, "__%s_SKEL_H__", obj_name); + sprintf(guard, "__%s_%s__", obj_name, suffix); for (i = 0; guard[i]; i++) guard[i] = toupper(guard[i]); } @@ -208,15 +209,47 @@ static int codegen_datasec_def(struct bpf_object *obj, return 0; } +static const struct btf_type *find_type_for_map(struct btf *btf, const char *map_ident) +{ + int n = btf__type_cnt(btf), i; + char sec_ident[256]; + + for (i = 1; i < n; i++) { + const struct btf_type *t = btf__type_by_id(btf, i); + const char *name; + + if (!btf_is_datasec(t)) + continue; + + name = btf__str_by_offset(btf, t->name_off); + if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident))) + continue; + + if (strcmp(sec_ident, map_ident) == 0) + return t; + } + return NULL; +} + +static bool is_internal_mmapable_map(const struct bpf_map *map, char *buf, size_t sz) +{ + if (!bpf_map__is_internal(map) || !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + return false; + + if (!get_map_ident(map, buf, sz)) + return false; + + return true; +} + static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) { struct btf *btf = bpf_object__btf(obj); - int n = btf__type_cnt(btf); struct btf_dump *d; struct bpf_map *map; const struct btf_type *sec; - char sec_ident[256], map_ident[256]; - int i, err = 0; + char map_ident[256]; + int err = 0; d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); err = libbpf_get_error(d); @@ -225,31 +258,10 @@ static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) bpf_object__for_each_map(map, obj) { /* only generate definitions for memory-mapped internal maps */ - if (!bpf_map__is_internal(map)) + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) continue; - if (!(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) - continue; - - if (!get_map_ident(map, map_ident, sizeof(map_ident))) - continue; - - sec = NULL; - for (i = 1; i < n; i++) { - const struct btf_type *t = btf__type_by_id(btf, i); - const char *name; - - if (!btf_is_datasec(t)) - continue; - - name = btf__str_by_offset(btf, t->name_off); - if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident))) - continue; - if (strcmp(sec_ident, map_ident) == 0) { - sec = t; - break; - } - } + sec = find_type_for_map(btf, map_ident); /* In some cases (e.g., sections like .rodata.cst16 containing * compiler allocated string constants only) there will be @@ -274,6 +286,96 @@ out: return err; } +static bool btf_is_ptr_to_func_proto(const struct btf *btf, + const struct btf_type *v) +{ + return btf_is_ptr(v) && btf_is_func_proto(btf__type_by_id(btf, v->type)); +} + +static int codegen_subskel_datasecs(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct btf_dump *d; + struct bpf_map *map; + const struct btf_type *sec, *var; + const struct btf_var_secinfo *sec_var; + int i, err = 0, vlen; + char map_ident[256], sec_ident[256]; + bool strip_mods = false, needs_typeof = false; + const char *sec_name, *var_name; + __u32 var_type_id; + + d = btf_dump__new(btf, codegen_btf_dump_printf, NULL, NULL); + if (!d) + return -errno; + + bpf_object__for_each_map(map, obj) { + /* only generate definitions for memory-mapped internal maps */ + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) + continue; + + sec = find_type_for_map(btf, map_ident); + if (!sec) + continue; + + sec_name = btf__name_by_offset(btf, sec->name_off); + if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident))) + continue; + + strip_mods = strcmp(sec_name, ".kconfig") != 0; + printf(" struct %s__%s {\n", obj_name, sec_ident); + + sec_var = btf_var_secinfos(sec); + vlen = btf_vlen(sec); + for (i = 0; i < vlen; i++, sec_var++) { + DECLARE_LIBBPF_OPTS(btf_dump_emit_type_decl_opts, opts, + .indent_level = 2, + .strip_mods = strip_mods, + /* we'll print the name separately */ + .field_name = "", + ); + + var = btf__type_by_id(btf, sec_var->type); + var_name = btf__name_by_offset(btf, var->name_off); + var_type_id = var->type; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + /* The datasec member has KIND_VAR but we want the + * underlying type of the variable (e.g. KIND_INT). + */ + var = skip_mods_and_typedefs(btf, var->type, NULL); + + printf("\t\t"); + /* Func and array members require special handling. + * Instead of producing `typename *var`, they produce + * `typeof(typename) *var`. This allows us to keep a + * similar syntax where the identifier is just prefixed + * by *, allowing us to ignore C declaration minutiae. + */ + needs_typeof = btf_is_array(var) || btf_is_ptr_to_func_proto(btf, var); + if (needs_typeof) + printf("typeof("); + + err = btf_dump__emit_type_decl(d, var_type_id, &opts); + if (err) + goto out; + + if (needs_typeof) + printf(")"); + + printf(" *%s;\n", var_name); + } + printf(" } %s;\n", sec_ident); + } + +out: + btf_dump__free(d); + return err; +} + static void codegen(const char *template, ...) { const char *src, *end; @@ -362,6 +464,69 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map) return map_sz; } +/* Emit type size asserts for all top-level fields in memory-mapped internal maps. */ +static void codegen_asserts(struct bpf_object *obj, const char *obj_name) +{ + struct btf *btf = bpf_object__btf(obj); + struct bpf_map *map; + struct btf_var_secinfo *sec_var; + int i, vlen; + const struct btf_type *sec; + char map_ident[256], var_ident[256]; + + codegen("\ + \n\ + __attribute__((unused)) static void \n\ + %1$s__assert(struct %1$s *s) \n\ + { \n\ + #ifdef __cplusplus \n\ + #define _Static_assert static_assert \n\ + #endif \n\ + ", obj_name); + + bpf_object__for_each_map(map, obj) { + if (!is_internal_mmapable_map(map, map_ident, sizeof(map_ident))) + continue; + + sec = find_type_for_map(btf, map_ident); + if (!sec) { + /* best effort, couldn't find the type for this map */ + continue; + } + + sec_var = btf_var_secinfos(sec); + vlen = btf_vlen(sec); + + for (i = 0; i < vlen; i++, sec_var++) { + const struct btf_type *var = btf__type_by_id(btf, sec_var->type); + const char *var_name = btf__name_by_offset(btf, var->name_off); + long var_size; + + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + + var_size = btf__resolve_size(btf, var->type); + if (var_size < 0) + continue; + + var_ident[0] = '\0'; + strncat(var_ident, var_name, sizeof(var_ident) - 1); + sanitize_identifier(var_ident); + + printf("\t_Static_assert(sizeof(s->%s->%s) == %ld, \"unexpected size of '%s'\");\n", + map_ident, var_ident, var_size, var_ident); + } + } + codegen("\ + \n\ + #ifdef __cplusplus \n\ + #undef _Static_assert \n\ + #endif \n\ + } \n\ + "); +} + static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name) { struct bpf_program *prog; @@ -378,13 +543,16 @@ static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name) int prog_fd = skel->progs.%2$s.prog_fd; \n\ ", obj_name, bpf_program__name(prog)); - switch (bpf_program__get_type(prog)) { + switch (bpf_program__type(prog)) { case BPF_PROG_TYPE_RAW_TRACEPOINT: tp_name = strchr(bpf_program__section_name(prog), '/') + 1; - printf("\tint fd = bpf_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name); + printf("\tint fd = skel_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name); break; case BPF_PROG_TYPE_TRACING: - printf("\tint fd = bpf_raw_tracepoint_open(NULL, prog_fd);\n"); + if (bpf_program__expected_attach_type(prog) == BPF_TRACE_ITER) + printf("\tint fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER);\n"); + else + printf("\tint fd = skel_raw_tracepoint_open(NULL, prog_fd);\n"); break; default: printf("\tint fd = ((void)prog_fd, 0); /* auto-attach not supported */\n"); @@ -468,8 +636,8 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) if (!get_map_ident(map, ident, sizeof(ident))) continue; if (bpf_map__is_internal(map) && - (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) - printf("\tmunmap(skel->%1$s, %2$zd);\n", + (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) + printf("\tskel_free_map_data(skel->%1$s, skel->maps.%1$s.initial_value, %2$zd);\n", ident, bpf_map_mmap_sz(map)); codegen("\ \n\ @@ -478,7 +646,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) } codegen("\ \n\ - free(skel); \n\ + skel_free(skel); \n\ } \n\ ", obj_name); @@ -522,7 +690,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h { \n\ struct %1$s *skel; \n\ \n\ - skel = calloc(sizeof(*skel), 1); \n\ + skel = skel_alloc(sizeof(*skel)); \n\ if (!skel) \n\ goto cleanup; \n\ skel->ctx.sz = (void *)&skel->links - (void *)skel; \n\ @@ -532,27 +700,22 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h const void *mmap_data = NULL; size_t mmap_size = 0; - if (!get_map_ident(map, ident, sizeof(ident))) - continue; - - if (!bpf_map__is_internal(map) || - !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) continue; codegen("\ - \n\ - skel->%1$s = \n\ - mmap(NULL, %2$zd, PROT_READ | PROT_WRITE,\n\ - MAP_SHARED | MAP_ANONYMOUS, -1, 0); \n\ - if (skel->%1$s == (void *) -1) \n\ - goto cleanup; \n\ - memcpy(skel->%1$s, (void *)\"\\ \n\ - ", ident, bpf_map_mmap_sz(map)); + \n\ + skel->%1$s = skel_prep_map_data((void *)\"\\ \n\ + ", ident); mmap_data = bpf_map__initial_value(map, &mmap_size); print_hex(mmap_data, mmap_size); - printf("\", %2$zd);\n" - "\tskel->maps.%1$s.initial_value = (__u64)(long)skel->%1$s;\n", - ident, mmap_size); + codegen("\ + \n\ + \", %1$zd, %2$zd); \n\ + if (!skel->%3$s) \n\ + goto cleanup; \n\ + skel->maps.%3$s.initial_value = (__u64) (long) skel->%3$s;\n\ + ", bpf_map_mmap_sz(map), mmap_size, ident); } codegen("\ \n\ @@ -596,21 +759,21 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h bpf_object__for_each_map(map, obj) { const char *mmap_flags; - if (!get_map_ident(map, ident, sizeof(ident))) - continue; - - if (!bpf_map__is_internal(map) || - !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) continue; - if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG) + if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG) mmap_flags = "PROT_READ"; else mmap_flags = "PROT_READ | PROT_WRITE"; - printf("\tskel->%1$s =\n" - "\t\tmmap(skel->%1$s, %2$zd, %3$s, MAP_SHARED | MAP_FIXED,\n" - "\t\t\tskel->maps.%1$s.map_fd, 0);\n", + codegen("\ + \n\ + skel->%1$s = skel_finalize_map_data(&skel->maps.%1$s.initial_value, \n\ + %2$zd, %3$s, skel->maps.%1$s.map_fd);\n\ + if (!skel->%1$s) \n\ + return -ENOMEM; \n\ + ", ident, bpf_map_mmap_sz(map), mmap_flags); } codegen("\ @@ -632,8 +795,11 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h } \n\ return skel; \n\ } \n\ + \n\ ", obj_name); + codegen_asserts(obj, obj_name); + codegen("\ \n\ \n\ @@ -645,10 +811,95 @@ out: return err; } +static void +codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) +{ + struct bpf_map *map; + char ident[256]; + size_t i; + + if (!map_cnt) + return; + + codegen("\ + \n\ + \n\ + /* maps */ \n\ + s->map_cnt = %zu; \n\ + s->map_skel_sz = sizeof(*s->maps); \n\ + s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ + if (!s->maps) \n\ + goto err; \n\ + ", + map_cnt + ); + i = 0; + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + codegen("\ + \n\ + \n\ + s->maps[%zu].name = \"%s\"; \n\ + s->maps[%zu].map = &obj->maps.%s; \n\ + ", + i, bpf_map__name(map), i, ident); + /* memory-mapped internal maps */ + if (mmaped && is_internal_mmapable_map(map, ident, sizeof(ident))) { + printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", + i, ident); + } + i++; + } +} + +static void +codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_links) +{ + struct bpf_program *prog; + int i; + + if (!prog_cnt) + return; + + codegen("\ + \n\ + \n\ + /* programs */ \n\ + s->prog_cnt = %zu; \n\ + s->prog_skel_sz = sizeof(*s->progs); \n\ + s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ + if (!s->progs) \n\ + goto err; \n\ + ", + prog_cnt + ); + i = 0; + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + \n\ + s->progs[%1$zu].name = \"%2$s\"; \n\ + s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ + ", + i, bpf_program__name(prog)); + + if (populate_links) { + codegen("\ + \n\ + s->progs[%1$zu].link = &obj->links.%2$s;\n\ + ", + i, bpf_program__name(prog)); + } + i++; + } +} + static int do_skeleton(int argc, char **argv) { char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; - size_t i, map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; + size_t map_cnt = 0, prog_cnt = 0, file_sz, mmap_sz; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; struct bpf_object *obj = NULL; @@ -739,7 +990,7 @@ static int do_skeleton(int argc, char **argv) prog_cnt++; } - get_header_guard(header_guard, obj_name); + get_header_guard(header_guard, obj_name, "SKEL_H"); if (use_loader) { codegen("\ \n\ @@ -748,8 +999,6 @@ static int do_skeleton(int argc, char **argv) #ifndef %2$s \n\ #define %2$s \n\ \n\ - #include <stdlib.h> \n\ - #include <bpf/bpf.h> \n\ #include <bpf/skel_internal.h> \n\ \n\ struct %1$s { \n\ @@ -827,6 +1076,16 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ + \n\ + #ifdef __cplusplus \n\ + static inline struct %1$s *open(const struct bpf_object_open_opts *opts = nullptr);\n\ + static inline struct %1$s *open_and_load(); \n\ + static inline int load(struct %1$s *skel); \n\ + static inline int attach(struct %1$s *skel); \n\ + static inline void detach(struct %1$s *skel); \n\ + static inline void destroy(struct %1$s *skel); \n\ + static inline const void *elf_bytes(size_t *sz); \n\ + #endif /* __cplusplus */ \n\ }; \n\ \n\ static void \n\ @@ -927,7 +1186,6 @@ static int do_skeleton(int argc, char **argv) s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ if (!s) \n\ goto err; \n\ - obj->skeleton = s; \n\ \n\ s->sz = sizeof(*s); \n\ s->name = \"%1$s\"; \n\ @@ -935,71 +1193,16 @@ static int do_skeleton(int argc, char **argv) ", obj_name ); - if (map_cnt) { - codegen("\ - \n\ - \n\ - /* maps */ \n\ - s->map_cnt = %zu; \n\ - s->map_skel_sz = sizeof(*s->maps); \n\ - s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ - if (!s->maps) \n\ - goto err; \n\ - ", - map_cnt - ); - i = 0; - bpf_object__for_each_map(map, obj) { - if (!get_map_ident(map, ident, sizeof(ident))) - continue; - codegen("\ - \n\ - \n\ - s->maps[%zu].name = \"%s\"; \n\ - s->maps[%zu].map = &obj->maps.%s; \n\ - ", - i, bpf_map__name(map), i, ident); - /* memory-mapped internal maps */ - if (bpf_map__is_internal(map) && - (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) { - printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", - i, ident); - } - i++; - } - } - if (prog_cnt) { - codegen("\ - \n\ - \n\ - /* programs */ \n\ - s->prog_cnt = %zu; \n\ - s->prog_skel_sz = sizeof(*s->progs); \n\ - s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ - if (!s->progs) \n\ - goto err; \n\ - ", - prog_cnt - ); - i = 0; - bpf_object__for_each_program(prog, obj) { - codegen("\ - \n\ - \n\ - s->progs[%1$zu].name = \"%2$s\"; \n\ - s->progs[%1$zu].prog = &obj->progs.%2$s;\n\ - s->progs[%1$zu].link = &obj->links.%2$s;\n\ - ", - i, bpf_program__name(prog)); - i++; - } - } + codegen_maps_skeleton(obj, map_cnt, true /*mmaped*/); + codegen_progs_skeleton(obj, prog_cnt, true /*populate_links*/); + codegen("\ \n\ \n\ s->data = (void *)%2$s__elf_bytes(&s->data_sz); \n\ \n\ + obj->skeleton = s; \n\ return 0; \n\ err: \n\ bpf_object__destroy_skeleton(s); \n\ @@ -1021,7 +1224,25 @@ static int do_skeleton(int argc, char **argv) \"; \n\ } \n\ \n\ - #endif /* %s */ \n\ + #ifdef __cplusplus \n\ + struct %1$s *%1$s::open(const struct bpf_object_open_opts *opts) { return %1$s__open_opts(opts); }\n\ + struct %1$s *%1$s::open_and_load() { return %1$s__open_and_load(); } \n\ + int %1$s::load(struct %1$s *skel) { return %1$s__load(skel); } \n\ + int %1$s::attach(struct %1$s *skel) { return %1$s__attach(skel); } \n\ + void %1$s::detach(struct %1$s *skel) { %1$s__detach(skel); } \n\ + void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); } \n\ + const void *%1$s::elf_bytes(size_t *sz) { return %1$s__elf_bytes(sz); } \n\ + #endif /* __cplusplus */ \n\ + \n\ + ", + obj_name); + + codegen_asserts(obj, obj_name); + + codegen("\ + \n\ + \n\ + #endif /* %1$s */ \n\ ", header_guard); err = 0; @@ -1033,6 +1254,310 @@ out: return err; } +/* Subskeletons are like skeletons, except they don't own the bpf_object, + * associated maps, links, etc. Instead, they know about the existence of + * variables, maps, programs and are able to find their locations + * _at runtime_ from an already loaded bpf_object. + * + * This allows for library-like BPF objects to have userspace counterparts + * with access to their own items without having to know anything about the + * final BPF object that the library was linked into. + */ +static int do_subskeleton(int argc, char **argv) +{ + char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SUBSKEL_H__")]; + size_t i, len, file_sz, map_cnt = 0, prog_cnt = 0, mmap_sz, var_cnt = 0, var_idx = 0; + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data; + struct bpf_object *obj = NULL; + const char *file, *var_name; + char ident[256]; + int fd, err = -1, map_type_id; + const struct bpf_map *map; + struct bpf_program *prog; + struct btf *btf; + const struct btf_type *map_type, *var_type; + const struct btf_var_secinfo *var; + struct stat st; + + if (!REQ_ARGS(1)) { + usage(); + return -1; + } + file = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "name")) { + NEXT_ARG(); + + if (obj_name[0] != '\0') { + p_err("object name already specified"); + return -1; + } + + strncpy(obj_name, *argv, MAX_OBJ_NAME_LEN - 1); + obj_name[MAX_OBJ_NAME_LEN - 1] = '\0'; + } else { + p_err("unknown arg %s", *argv); + return -1; + } + + NEXT_ARG(); + } + + if (argc) { + p_err("extra unknown arguments"); + return -1; + } + + if (use_loader) { + p_err("cannot use loader for subskeletons"); + return -1; + } + + if (stat(file, &st)) { + p_err("failed to stat() %s: %s", file, strerror(errno)); + return -1; + } + file_sz = st.st_size; + mmap_sz = roundup(file_sz, sysconf(_SC_PAGE_SIZE)); + fd = open(file, O_RDONLY); + if (fd < 0) { + p_err("failed to open() %s: %s", file, strerror(errno)); + return -1; + } + obj_data = mmap(NULL, mmap_sz, PROT_READ, MAP_PRIVATE, fd, 0); + if (obj_data == MAP_FAILED) { + obj_data = NULL; + p_err("failed to mmap() %s: %s", file, strerror(errno)); + goto out; + } + if (obj_name[0] == '\0') + get_obj_name(obj_name, file); + + /* The empty object name allows us to use bpf_map__name and produce + * ELF section names out of it. (".data" instead of "obj.data") + */ + opts.object_name = ""; + obj = bpf_object__open_mem(obj_data, file_sz, &opts); + if (!obj) { + char err_buf[256]; + + libbpf_strerror(errno, err_buf, sizeof(err_buf)); + p_err("failed to open BPF object file: %s", err_buf); + obj = NULL; + goto out; + } + + btf = bpf_object__btf(obj); + if (!btf) { + err = -1; + p_err("need btf type information for %s", obj_name); + goto out; + } + + bpf_object__for_each_program(prog, obj) { + prog_cnt++; + } + + /* First, count how many variables we have to find. + * We need this in advance so the subskel can allocate the right + * amount of storage. + */ + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + + /* Also count all maps that have a name */ + map_cnt++; + + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) { + err = map_type_id; + goto out; + } + map_type = btf__type_by_id(btf, map_type_id); + + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + var_cnt++; + } + } + + get_header_guard(header_guard, obj_name, "SUBSKEL_H"); + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + \n\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include <errno.h> \n\ + #include <stdlib.h> \n\ + #include <bpf/libbpf.h> \n\ + \n\ + struct %1$s { \n\ + struct bpf_object *obj; \n\ + struct bpf_object_subskeleton *subskel; \n\ + ", obj_name, header_guard); + + if (map_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_map(map, obj) { + if (!get_map_ident(map, ident, sizeof(ident))) + continue; + printf("\t\tstruct bpf_map *%s;\n", ident); + } + printf("\t} maps;\n"); + } + + if (prog_cnt) { + printf("\tstruct {\n"); + bpf_object__for_each_program(prog, obj) { + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); + } + printf("\t} progs;\n"); + } + + err = codegen_subskel_datasecs(obj, obj_name); + if (err) + goto out; + + /* emit code that will allocate enough storage for all symbols */ + codegen("\ + \n\ + \n\ + #ifdef __cplusplus \n\ + static inline struct %1$s *open(const struct bpf_object *src);\n\ + static inline void destroy(struct %1$s *skel); \n\ + #endif /* __cplusplus */ \n\ + }; \n\ + \n\ + static inline void \n\ + %1$s__destroy(struct %1$s *skel) \n\ + { \n\ + if (!skel) \n\ + return; \n\ + if (skel->subskel) \n\ + bpf_object__destroy_subskeleton(skel->subskel);\n\ + free(skel); \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(const struct bpf_object *src) \n\ + { \n\ + struct %1$s *obj; \n\ + struct bpf_object_subskeleton *s; \n\ + int err; \n\ + \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ + if (!obj) { \n\ + errno = ENOMEM; \n\ + goto err; \n\ + } \n\ + s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\ + if (!s) { \n\ + errno = ENOMEM; \n\ + goto err; \n\ + } \n\ + s->sz = sizeof(*s); \n\ + s->obj = src; \n\ + s->var_skel_sz = sizeof(*s->vars); \n\ + obj->subskel = s; \n\ + \n\ + /* vars */ \n\ + s->var_cnt = %2$d; \n\ + s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\ + if (!s->vars) { \n\ + errno = ENOMEM; \n\ + goto err; \n\ + } \n\ + ", + obj_name, var_cnt + ); + + /* walk through each symbol and emit the runtime representation */ + bpf_object__for_each_map(map, obj) { + if (!is_internal_mmapable_map(map, ident, sizeof(ident))) + continue; + + map_type_id = bpf_map__btf_value_type_id(map); + if (map_type_id <= 0) + /* skip over internal maps with no type*/ + continue; + + map_type = btf__type_by_id(btf, map_type_id); + var = btf_var_secinfos(map_type); + len = btf_vlen(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + var_name = btf__name_by_offset(btf, var_type->name_off); + + if (btf_var(var_type)->linkage == BTF_VAR_STATIC) + continue; + + /* Note that we use the dot prefix in .data as the + * field access operator i.e. maps%s becomes maps.data + */ + codegen("\ + \n\ + \n\ + s->vars[%3$d].name = \"%1$s\"; \n\ + s->vars[%3$d].map = &obj->maps.%2$s; \n\ + s->vars[%3$d].addr = (void **) &obj->%2$s.%1$s;\n\ + ", var_name, ident, var_idx); + + var_idx++; + } + } + + codegen_maps_skeleton(obj, map_cnt, false /*mmaped*/); + codegen_progs_skeleton(obj, prog_cnt, false /*links*/); + + codegen("\ + \n\ + \n\ + err = bpf_object__open_subskeleton(s); \n\ + if (err) \n\ + goto err; \n\ + \n\ + return obj; \n\ + err: \n\ + %1$s__destroy(obj); \n\ + return NULL; \n\ + } \n\ + \n\ + #ifdef __cplusplus \n\ + struct %1$s *%1$s::open(const struct bpf_object *src) { return %1$s__open(src); }\n\ + void %1$s::destroy(struct %1$s *skel) { %1$s__destroy(skel); }\n\ + #endif /* __cplusplus */ \n\ + \n\ + #endif /* %2$s */ \n\ + ", + obj_name, header_guard); + err = 0; +out: + bpf_object__close(obj); + if (obj_data) + munmap(obj_data, mmap_sz); + close(fd); + return err; +} + static int do_object(int argc, char **argv) { struct bpf_linker *linker; @@ -1084,6 +1609,8 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %1$s %2$s object OUTPUT_FILE INPUT_FILE [INPUT_FILE...]\n" " %1$s %2$s skeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s subskeleton FILE [name OBJECT_NAME]\n" + " %1$s %2$s min_core_btf INPUT OUTPUT OBJECT [OBJECT...]\n" " %1$s %2$s help\n" "\n" " " HELP_SPEC_OPTIONS " |\n" @@ -1094,10 +1621,594 @@ static int do_help(int argc, char **argv) return 0; } +static int btf_save_raw(const struct btf *btf, const char *path) +{ + const void *data; + FILE *f = NULL; + __u32 data_sz; + int err = 0; + + data = btf__raw_data(btf, &data_sz); + if (!data) + return -ENOMEM; + + f = fopen(path, "wb"); + if (!f) + return -errno; + + if (fwrite(data, 1, data_sz, f) != data_sz) + err = -errno; + + fclose(f); + return err; +} + +struct btfgen_info { + struct btf *src_btf; + struct btf *marked_btf; /* btf structure used to mark used types */ +}; + +static size_t btfgen_hash_fn(const void *key, void *ctx) +{ + return (size_t)key; +} + +static bool btfgen_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +static void *u32_as_hash_key(__u32 x) +{ + return (void *)(uintptr_t)x; +} + +static void btfgen_free_info(struct btfgen_info *info) +{ + if (!info) + return; + + btf__free(info->src_btf); + btf__free(info->marked_btf); + + free(info); +} + +static struct btfgen_info * +btfgen_new_info(const char *targ_btf_path) +{ + struct btfgen_info *info; + int err; + + info = calloc(1, sizeof(*info)); + if (!info) + return NULL; + + info->src_btf = btf__parse(targ_btf_path, NULL); + if (!info->src_btf) { + err = -errno; + p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno)); + goto err_out; + } + + info->marked_btf = btf__parse(targ_btf_path, NULL); + if (!info->marked_btf) { + err = -errno; + p_err("failed parsing '%s' BTF file: %s", targ_btf_path, strerror(errno)); + goto err_out; + } + + return info; + +err_out: + btfgen_free_info(info); + errno = -err; + return NULL; +} + +#define MARKED UINT32_MAX + +static void btfgen_mark_member(struct btfgen_info *info, int type_id, int idx) +{ + const struct btf_type *t = btf__type_by_id(info->marked_btf, type_id); + struct btf_member *m = btf_members(t) + idx; + + m->name_off = MARKED; +} + +static int +btfgen_mark_type(struct btfgen_info *info, unsigned int type_id, bool follow_pointers) +{ + const struct btf_type *btf_type = btf__type_by_id(info->src_btf, type_id); + struct btf_type *cloned_type; + struct btf_param *param; + struct btf_array *array; + int err, i; + + if (type_id == 0) + return 0; + + /* mark type on cloned BTF as used */ + cloned_type = (struct btf_type *) btf__type_by_id(info->marked_btf, type_id); + cloned_type->name_off = MARKED; + + /* recursively mark other types needed by it */ + switch (btf_kind(btf_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + break; + case BTF_KIND_PTR: + if (follow_pointers) { + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + } + break; + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_TYPEDEF: + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + break; + case BTF_KIND_ARRAY: + array = btf_array(btf_type); + + /* mark array type */ + err = btfgen_mark_type(info, array->type, follow_pointers); + /* mark array's index type */ + err = err ? : btfgen_mark_type(info, array->index_type, follow_pointers); + if (err) + return err; + break; + case BTF_KIND_FUNC_PROTO: + /* mark ret type */ + err = btfgen_mark_type(info, btf_type->type, follow_pointers); + if (err) + return err; + + /* mark parameters types */ + param = btf_params(btf_type); + for (i = 0; i < btf_vlen(btf_type); i++) { + err = btfgen_mark_type(info, param->type, follow_pointers); + if (err) + return err; + param++; + } + break; + /* tells if some other type needs to be handled */ + default: + p_err("unsupported kind: %s (%d)", btf_kind_str(btf_type), type_id); + return -EINVAL; + } + + return 0; +} + +static int btfgen_record_field_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + struct btf *btf = info->src_btf; + const struct btf_type *btf_type; + struct btf_member *btf_member; + struct btf_array *array; + unsigned int type_id = targ_spec->root_type_id; + int idx, err; + + /* mark root type */ + btf_type = btf__type_by_id(btf, type_id); + err = btfgen_mark_type(info, type_id, false); + if (err) + return err; + + /* mark types for complex types (arrays, unions, structures) */ + for (int i = 1; i < targ_spec->raw_len; i++) { + /* skip typedefs and mods */ + while (btf_is_mod(btf_type) || btf_is_typedef(btf_type)) { + type_id = btf_type->type; + btf_type = btf__type_by_id(btf, type_id); + } + + switch (btf_kind(btf_type)) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + idx = targ_spec->raw_spec[i]; + btf_member = btf_members(btf_type) + idx; + + /* mark member */ + btfgen_mark_member(info, type_id, idx); + + /* mark member's type */ + type_id = btf_member->type; + btf_type = btf__type_by_id(btf, type_id); + err = btfgen_mark_type(info, type_id, false); + if (err) + return err; + break; + case BTF_KIND_ARRAY: + array = btf_array(btf_type); + type_id = array->type; + btf_type = btf__type_by_id(btf, type_id); + break; + default: + p_err("unsupported kind: %s (%d)", + btf_kind_str(btf_type), btf_type->type); + return -EINVAL; + } + } + + return 0; +} + +static int btfgen_record_type_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type(info, targ_spec->root_type_id, true); +} + +static int btfgen_record_enumval_relo(struct btfgen_info *info, struct bpf_core_spec *targ_spec) +{ + return btfgen_mark_type(info, targ_spec->root_type_id, false); +} + +static int btfgen_record_reloc(struct btfgen_info *info, struct bpf_core_spec *res) +{ + switch (res->relo_kind) { + case BPF_CORE_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_EXISTS: + case BPF_CORE_FIELD_SIGNED: + case BPF_CORE_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: + return btfgen_record_field_relo(info, res); + case BPF_CORE_TYPE_ID_LOCAL: /* BPF_CORE_TYPE_ID_LOCAL doesn't require kernel BTF */ + return 0; + case BPF_CORE_TYPE_ID_TARGET: + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_SIZE: + return btfgen_record_type_relo(info, res); + case BPF_CORE_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_VALUE: + return btfgen_record_enumval_relo(info, res); + default: + return -EINVAL; + } +} + +static struct bpf_core_cand_list * +btfgen_find_cands(const struct btf *local_btf, const struct btf *targ_btf, __u32 local_id) +{ + const struct btf_type *local_type; + struct bpf_core_cand_list *cands = NULL; + struct bpf_core_cand local_cand = {}; + size_t local_essent_len; + const char *local_name; + int err; + + local_cand.btf = local_btf; + local_cand.id = local_id; + + local_type = btf__type_by_id(local_btf, local_id); + if (!local_type) { + err = -EINVAL; + goto err_out; + } + + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (!local_name) { + err = -EINVAL; + goto err_out; + } + local_essent_len = bpf_core_essential_name_len(local_name); + + cands = calloc(1, sizeof(*cands)); + if (!cands) + return NULL; + + err = bpf_core_add_cands(&local_cand, local_essent_len, targ_btf, "vmlinux", 1, cands); + if (err) + goto err_out; + + return cands; + +err_out: + bpf_core_free_cands(cands); + errno = -err; + return NULL; +} + +/* Record relocation information for a single BPF object */ +static int btfgen_record_obj(struct btfgen_info *info, const char *obj_path) +{ + const struct btf_ext_info_sec *sec; + const struct bpf_core_relo *relo; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct btf_ext *btf_ext = NULL; + unsigned int relo_idx; + struct btf *btf = NULL; + size_t i; + int err; + + btf = btf__parse(obj_path, &btf_ext); + if (!btf) { + err = -errno; + p_err("failed to parse BPF object '%s': %s", obj_path, strerror(errno)); + return err; + } + + if (!btf_ext) { + p_err("failed to parse BPF object '%s': section %s not found", + obj_path, BTF_EXT_ELF_SEC); + err = -EINVAL; + goto out; + } + + if (btf_ext->core_relo_info.len == 0) { + err = 0; + goto out; + } + + cand_cache = hashmap__new(btfgen_hash_fn, btfgen_equal_fn, NULL); + if (IS_ERR(cand_cache)) { + err = PTR_ERR(cand_cache); + goto out; + } + + seg = &btf_ext->core_relo_info; + for_each_btf_ext_sec(seg, sec) { + for_each_btf_ext_rec(seg, sec, relo_idx, relo) { + struct bpf_core_spec specs_scratch[3] = {}; + struct bpf_core_relo_res targ_res = {}; + struct bpf_core_cand_list *cands = NULL; + const void *type_key = u32_as_hash_key(relo->type_id); + const char *sec_name = btf__name_by_offset(btf, sec->sec_name_off); + + if (relo->kind != BPF_CORE_TYPE_ID_LOCAL && + !hashmap__find(cand_cache, type_key, (void **)&cands)) { + cands = btfgen_find_cands(btf, info->src_btf, relo->type_id); + if (!cands) { + err = -errno; + goto out; + } + + err = hashmap__set(cand_cache, type_key, cands, NULL, NULL); + if (err) + goto out; + } + + err = bpf_core_calc_relo_insn(sec_name, relo, relo_idx, btf, cands, + specs_scratch, &targ_res); + if (err) + goto out; + + /* specs_scratch[2] is the target spec */ + err = btfgen_record_reloc(info, &specs_scratch[2]); + if (err) + goto out; + } + } + +out: + btf__free(btf); + btf_ext__free(btf_ext); + + if (!IS_ERR_OR_NULL(cand_cache)) { + hashmap__for_each_entry(cand_cache, entry, i) { + bpf_core_free_cands(entry->value); + } + hashmap__free(cand_cache); + } + + return err; +} + +static int btfgen_remap_id(__u32 *type_id, void *ctx) +{ + unsigned int *ids = ctx; + + *type_id = ids[*type_id]; + + return 0; +} + +/* Generate BTF from relocation information previously recorded */ +static struct btf *btfgen_get_btf(struct btfgen_info *info) +{ + struct btf *btf_new = NULL; + unsigned int *ids = NULL; + unsigned int i, n = btf__type_cnt(info->marked_btf); + int err = 0; + + btf_new = btf__new_empty(); + if (!btf_new) { + err = -errno; + goto err_out; + } + + ids = calloc(n, sizeof(*ids)); + if (!ids) { + err = -errno; + goto err_out; + } + + /* first pass: add all marked types to btf_new and add their new ids to the ids map */ + for (i = 1; i < n; i++) { + const struct btf_type *cloned_type, *type; + const char *name; + int new_id; + + cloned_type = btf__type_by_id(info->marked_btf, i); + + if (cloned_type->name_off != MARKED) + continue; + + type = btf__type_by_id(info->src_btf, i); + + /* add members for struct and union */ + if (btf_is_composite(type)) { + struct btf_member *cloned_m, *m; + unsigned short vlen; + int idx_src; + + name = btf__str_by_offset(info->src_btf, type->name_off); + + if (btf_is_struct(type)) + err = btf__add_struct(btf_new, name, type->size); + else + err = btf__add_union(btf_new, name, type->size); + + if (err < 0) + goto err_out; + new_id = err; + + cloned_m = btf_members(cloned_type); + m = btf_members(type); + vlen = btf_vlen(cloned_type); + for (idx_src = 0; idx_src < vlen; idx_src++, cloned_m++, m++) { + /* add only members that are marked as used */ + if (cloned_m->name_off != MARKED) + continue; + + name = btf__str_by_offset(info->src_btf, m->name_off); + err = btf__add_field(btf_new, name, m->type, + btf_member_bit_offset(cloned_type, idx_src), + btf_member_bitfield_size(cloned_type, idx_src)); + if (err < 0) + goto err_out; + } + } else { + err = btf__add_type(btf_new, info->src_btf, type); + if (err < 0) + goto err_out; + new_id = err; + } + + /* add ID mapping */ + ids[i] = new_id; + } + + /* second pass: fix up type ids */ + for (i = 1; i < btf__type_cnt(btf_new); i++) { + struct btf_type *btf_type = (struct btf_type *) btf__type_by_id(btf_new, i); + + err = btf_type_visit_type_ids(btf_type, btfgen_remap_id, ids); + if (err) + goto err_out; + } + + free(ids); + return btf_new; + +err_out: + btf__free(btf_new); + free(ids); + errno = -err; + return NULL; +} + +/* Create minimized BTF file for a set of BPF objects. + * + * The BTFGen algorithm is divided in two main parts: (1) collect the + * BTF types that are involved in relocations and (2) generate the BTF + * object using the collected types. + * + * In order to collect the types involved in the relocations, we parse + * the BTF and BTF.ext sections of the BPF objects and use + * bpf_core_calc_relo_insn() to get the target specification, this + * indicates how the types and fields are used in a relocation. + * + * Types are recorded in different ways according to the kind of the + * relocation. For field-based relocations only the members that are + * actually used are saved in order to reduce the size of the generated + * BTF file. For type-based relocations empty struct / unions are + * generated and for enum-based relocations the whole type is saved. + * + * The second part of the algorithm generates the BTF object. It creates + * an empty BTF object and fills it with the types recorded in the + * previous step. This function takes care of only adding the structure + * and union members that were marked as used and it also fixes up the + * type IDs on the generated BTF object. + */ +static int minimize_btf(const char *src_btf, const char *dst_btf, const char *objspaths[]) +{ + struct btfgen_info *info; + struct btf *btf_new = NULL; + int err, i; + + info = btfgen_new_info(src_btf); + if (!info) { + err = -errno; + p_err("failed to allocate info structure: %s", strerror(errno)); + goto out; + } + + for (i = 0; objspaths[i] != NULL; i++) { + err = btfgen_record_obj(info, objspaths[i]); + if (err) { + p_err("error recording relocations for %s: %s", objspaths[i], + strerror(errno)); + goto out; + } + } + + btf_new = btfgen_get_btf(info); + if (!btf_new) { + err = -errno; + p_err("error generating BTF: %s", strerror(errno)); + goto out; + } + + err = btf_save_raw(btf_new, dst_btf); + if (err) { + p_err("error saving btf file: %s", strerror(errno)); + goto out; + } + +out: + btf__free(btf_new); + btfgen_free_info(info); + + return err; +} + +static int do_min_core_btf(int argc, char **argv) +{ + const char *input, *output, **objs; + int i, err; + + if (!REQ_ARGS(3)) { + usage(); + return -1; + } + + input = GET_ARG(); + output = GET_ARG(); + + objs = (const char **) calloc(argc + 1, sizeof(*objs)); + if (!objs) { + p_err("failed to allocate array for object names"); + return -ENOMEM; + } + + i = 0; + while (argc) + objs[i++] = GET_ARG(); + + err = minimize_btf(input, output, objs); + free(objs); + return err; +} + static const struct cmd cmds[] = { - { "object", do_object }, - { "skeleton", do_skeleton }, - { "help", do_help }, + { "object", do_object }, + { "skeleton", do_skeleton }, + { "subskeleton", do_subskeleton }, + { "min_core_btf", do_min_core_btf}, + { "help", do_help }, { 0 } }; diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 2c258db0d352..97dec81950e5 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -2,6 +2,7 @@ /* Copyright (C) 2020 Facebook */ #include <errno.h> +#include <linux/err.h> #include <net/if.h> #include <stdio.h> #include <unistd.h> @@ -306,7 +307,7 @@ static int do_show(int argc, char **argv) if (show_pinned) { link_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!link_table) { + if (IS_ERR(link_table)) { p_err("failed to create hashmap for pinned paths"); return -1; } diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 020e91a542d5..e81227761f5d 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -71,6 +71,17 @@ static int do_help(int argc, char **argv) return 0; } +#ifndef BPFTOOL_VERSION +/* bpftool's major and minor version numbers are aligned on libbpf's. There is + * an offset of 6 for the version number, because bpftool's version was higher + * than libbpf's when we adopted this scheme. The patch number remains at 0 + * for now. Set BPFTOOL_VERSION to override. + */ +#define BPFTOOL_MAJOR_VERSION (LIBBPF_MAJOR_VERSION + 6) +#define BPFTOOL_MINOR_VERSION LIBBPF_MINOR_VERSION +#define BPFTOOL_PATCH_VERSION 0 +#endif + static int do_version(int argc, char **argv) { #ifdef HAVE_LIBBFD_SUPPORT @@ -88,7 +99,15 @@ static int do_version(int argc, char **argv) jsonw_start_object(json_wtr); /* root object */ jsonw_name(json_wtr, "version"); +#ifdef BPFTOOL_VERSION jsonw_printf(json_wtr, "\"%s\"", BPFTOOL_VERSION); +#else + jsonw_printf(json_wtr, "\"%d.%d.%d\"", BPFTOOL_MAJOR_VERSION, + BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION); +#endif + jsonw_name(json_wtr, "libbpf_version"); + jsonw_printf(json_wtr, "\"%d.%d\"", + libbpf_major_version(), libbpf_minor_version()); jsonw_name(json_wtr, "features"); jsonw_start_object(json_wtr); /* features */ @@ -101,7 +120,13 @@ static int do_version(int argc, char **argv) } else { unsigned int nb_features = 0; +#ifdef BPFTOOL_VERSION printf("%s v%s\n", bin_name, BPFTOOL_VERSION); +#else + printf("%s v%d.%d.%d\n", bin_name, BPFTOOL_MAJOR_VERSION, + BPFTOOL_MINOR_VERSION, BPFTOOL_PATCH_VERSION); +#endif + printf("using libbpf %s\n", libbpf_version_string()); printf("features:"); if (has_libbfd) { printf(" libbfd"); @@ -478,7 +503,11 @@ int main(int argc, char **argv) } if (!legacy_libbpf) { - ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + /* Allow legacy map definitions for skeleton generation. + * It will still be rejected if users use LIBBPF_STRICT_ALL + * mode for loading generated skeleton. + */ + ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL & ~LIBBPF_STRICT_MAP_DEFINITIONS); if (ret) p_err("failed to enable libbpf strict mode: %d", ret); } diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 8d76d937a62b..6e9277ffc68c 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -8,10 +8,10 @@ #undef GCC_VERSION #include <stdbool.h> #include <stdio.h> +#include <stdlib.h> #include <linux/bpf.h> #include <linux/compiler.h> #include <linux/kernel.h> -#include <tools/libc_compat.h> #include <bpf/hashmap.h> #include <bpf/libbpf.h> @@ -113,7 +113,9 @@ struct obj_ref { struct obj_refs { int ref_cnt; + bool has_bpf_cookie; struct obj_ref *refs; + __u64 bpf_cookie; }; struct btf; @@ -140,6 +142,10 @@ struct cmd { int cmd_select(const struct cmd *cmds, int argc, char **argv, int (*help)(int argc, char **argv)); +#define MAX_PROG_FULL_NAME 128 +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len); + int get_fd_type(int fd); const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index cc530a229812..c26378f20831 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -504,7 +504,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_uint_field(json_wtr, "max_entries", info->max_entries); if (memlock) - jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock)); + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); free(memlock); if (info->type == BPF_MAP_TYPE_PROG_ARRAY) { @@ -620,17 +620,14 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) u32_as_hash_field(info->id)) printf("\n\tpinned %s", (char *)entry->value); } - printf("\n"); if (frozen_str) { frozen = atoi(frozen_str); free(frozen_str); } - if (!info->btf_id && !frozen) - return 0; - - printf("\t"); + if (info->btf_id || frozen) + printf("\n\t"); if (info->btf_id) printf("btf_id %d", info->btf_id); @@ -699,7 +696,7 @@ static int do_show(int argc, char **argv) if (show_pinned) { map_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!map_table) { + if (IS_ERR(map_table)) { p_err("failed to create hashmap for pinned paths"); return -1; } @@ -805,29 +802,30 @@ static int maps_have_btf(int *fds, int nb_fds) static struct btf *btf_vmlinux; -static struct btf *get_map_kv_btf(const struct bpf_map_info *info) +static int get_map_kv_btf(const struct bpf_map_info *info, struct btf **btf) { - struct btf *btf = NULL; + int err = 0; if (info->btf_vmlinux_value_type_id) { if (!btf_vmlinux) { btf_vmlinux = libbpf_find_kernel_btf(); - if (libbpf_get_error(btf_vmlinux)) + err = libbpf_get_error(btf_vmlinux); + if (err) { p_err("failed to get kernel btf"); + return err; + } } - return btf_vmlinux; + *btf = btf_vmlinux; } else if (info->btf_value_type_id) { - int err; - - btf = btf__load_from_kernel_by_id(info->btf_id); - err = libbpf_get_error(btf); - if (err) { + *btf = btf__load_from_kernel_by_id(info->btf_id); + err = libbpf_get_error(*btf); + if (err) p_err("failed to get btf"); - btf = ERR_PTR(err); - } + } else { + *btf = NULL; } - return btf; + return err; } static void free_map_kv_btf(struct btf *btf) @@ -862,8 +860,7 @@ map_dump(int fd, struct bpf_map_info *info, json_writer_t *wtr, prev_key = NULL; if (wtr) { - btf = get_map_kv_btf(info); - err = libbpf_get_error(btf); + err = get_map_kv_btf(info, &btf); if (err) { goto exit_free; } @@ -1054,11 +1051,8 @@ static void print_key_value(struct bpf_map_info *info, void *key, json_writer_t *btf_wtr; struct btf *btf; - btf = btf__load_from_kernel_by_id(info->btf_id); - if (libbpf_get_error(btf)) { - p_err("failed to get btf"); + if (get_map_kv_btf(info, &btf)) return; - } if (json_output) { print_entry_json(info, key, value, btf); diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 649053704bd7..526a332c48e6 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -551,7 +551,7 @@ static int do_attach_detach_xdp(int progfd, enum net_attach_type attach_type, if (attach_type == NET_ATTACH_TYPE_XDP_OFFLOAD) flags |= XDP_FLAGS_HW_MODE; - return bpf_set_link_xdp_fd(ifindex, progfd, flags); + return bpf_xdp_attach(ifindex, progfd, flags, NULL); } static int do_attach(int argc, char **argv) diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index 56b598eee043..bb6c969a114a 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2020 Facebook */ #include <errno.h> +#include <linux/err.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -77,6 +78,8 @@ static void add_ref(struct hashmap *map, struct pid_iter_entry *e) ref->pid = e->pid; memcpy(ref->comm, e->comm, sizeof(ref->comm)); refs->ref_cnt = 1; + refs->has_bpf_cookie = e->has_bpf_cookie; + refs->bpf_cookie = e->bpf_cookie; err = hashmap__append(map, u32_as_hash_field(e->id), refs); if (err) @@ -101,7 +104,7 @@ int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) libbpf_print_fn_t default_print; *map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!*map) { + if (IS_ERR(*map)) { p_err("failed to create hashmap for PID references"); return -1; } @@ -204,6 +207,9 @@ void emit_obj_refs_json(struct hashmap *map, __u32 id, if (refs->ref_cnt == 0) break; + if (refs->has_bpf_cookie) + jsonw_lluint_field(json_writer, "bpf_cookie", refs->bpf_cookie); + jsonw_name(json_writer, "pids"); jsonw_start_array(json_writer); for (i = 0; i < refs->ref_cnt; i++) { @@ -233,6 +239,9 @@ void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) if (refs->ref_cnt == 0) break; + if (refs->has_bpf_cookie) + printf("\n\tbpf_cookie %llu", (unsigned long long) refs->bpf_cookie); + printf("%s", prefix); for (i = 0; i < refs->ref_cnt; i++) { struct obj_ref *ref = &refs->refs[i]; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 2a21d50516bc..bc4e05542c2b 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -26,6 +26,7 @@ #include <bpf/btf.h> #include <bpf/hashmap.h> #include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> #include <bpf/skel_internal.h> #include "cfg.h" @@ -424,8 +425,10 @@ out_free: free(value); } -static void print_prog_header_json(struct bpf_prog_info *info) +static void print_prog_header_json(struct bpf_prog_info *info, int fd) { + char prog_name[MAX_PROG_FULL_NAME]; + jsonw_uint_field(json_wtr, "id", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) jsonw_string_field(json_wtr, "type", @@ -433,8 +436,10 @@ static void print_prog_header_json(struct bpf_prog_info *info) else jsonw_uint_field(json_wtr, "type", info->type); - if (*info->name) - jsonw_string_field(json_wtr, "name", info->name); + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + jsonw_string_field(json_wtr, "name", prog_name); + } jsonw_name(json_wtr, "tag"); jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"", @@ -455,7 +460,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) char *memlock; jsonw_start_object(json_wtr); - print_prog_header_json(info); + print_prog_header_json(info, fd); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -480,7 +485,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) memlock = get_fdinfo(fd, "memlock"); if (memlock) - jsonw_int_field(json_wtr, "bytes_memlock", atoi(memlock)); + jsonw_int_field(json_wtr, "bytes_memlock", atoll(memlock)); free(memlock); if (info->nr_map_ids) @@ -507,16 +512,20 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_end_object(json_wtr); } -static void print_prog_header_plain(struct bpf_prog_info *info) +static void print_prog_header_plain(struct bpf_prog_info *info, int fd) { + char prog_name[MAX_PROG_FULL_NAME]; + printf("%u: ", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) printf("%s ", prog_type_name[info->type]); else printf("type %u ", info->type); - if (*info->name) - printf("name %s ", info->name); + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + printf("name %s ", prog_name); + } printf("tag "); fprint_hex(stdout, info->tag, BPF_TAG_SIZE, ""); @@ -534,7 +543,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) { char *memlock; - print_prog_header_plain(info); + print_prog_header_plain(info, fd); if (info->load_time) { char buf[32]; @@ -641,7 +650,7 @@ static int do_show(int argc, char **argv) if (show_pinned) { prog_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!prog_table) { + if (IS_ERR(prog_table)) { p_err("failed to create hashmap for pinned paths"); return -1; } @@ -972,10 +981,10 @@ static int do_dump(int argc, char **argv) if (json_output && nb_fds > 1) { jsonw_start_object(json_wtr); /* prog object */ - print_prog_header_json(&info); + print_prog_header_json(&info, fds[i]); jsonw_name(json_wtr, "insns"); } else if (nb_fds > 1) { - print_prog_header_plain(&info); + print_prog_header_plain(&info, fds[i]); } err = prog_dump(&info, mode, filepath, opcodes, visual, linum); @@ -1264,12 +1273,12 @@ static int do_run(int argc, char **argv) { char *data_fname_in = NULL, *data_fname_out = NULL; char *ctx_fname_in = NULL, *ctx_fname_out = NULL; - struct bpf_prog_test_run_attr test_attr = {0}; const unsigned int default_size = SZ_32K; void *data_in = NULL, *data_out = NULL; void *ctx_in = NULL, *ctx_out = NULL; unsigned int repeat = 1; int fd, err; + LIBBPF_OPTS(bpf_test_run_opts, test_attr); if (!REQ_ARGS(4)) return -1; @@ -1387,14 +1396,13 @@ static int do_run(int argc, char **argv) goto free_ctx_in; } - test_attr.prog_fd = fd; test_attr.repeat = repeat; test_attr.data_in = data_in; test_attr.data_out = data_out; test_attr.ctx_in = ctx_in; test_attr.ctx_out = ctx_out; - err = bpf_prog_test_run_xattr(&test_attr); + err = bpf_prog_test_run_opts(fd, &test_attr); if (err) { p_err("failed to run program: %s", strerror(errno)); goto free_ctx_out; @@ -1551,9 +1559,9 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) if (fd < 0) goto err_free_reuse_maps; - new_map_replace = reallocarray(map_replace, - old_map_fds + 1, - sizeof(*map_replace)); + new_map_replace = libbpf_reallocarray(map_replace, + old_map_fds + 1, + sizeof(*map_replace)); if (!new_map_replace) { p_err("mem alloc failed"); goto err_free_reuse_maps; @@ -2275,10 +2283,10 @@ static int do_profile(int argc, char **argv) profile_obj->rodata->num_metric = num_metric; /* adjust map sizes */ - bpf_map__resize(profile_obj->maps.events, num_metric * num_cpu); - bpf_map__resize(profile_obj->maps.fentry_readings, num_metric); - bpf_map__resize(profile_obj->maps.accum_readings, num_metric); - bpf_map__resize(profile_obj->maps.counts, 1); + bpf_map__set_max_entries(profile_obj->maps.events, num_metric * num_cpu); + bpf_map__set_max_entries(profile_obj->maps.fentry_readings, num_metric); + bpf_map__set_max_entries(profile_obj->maps.accum_readings, num_metric); + bpf_map__set_max_entries(profile_obj->maps.counts, 1); /* change target name */ profile_tgt_name = profile_target_name(profile_tgt_fd); diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c index f70702fcb224..eb05ea53afb1 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c +++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c @@ -38,6 +38,17 @@ static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type) } } +/* could be used only with BPF_LINK_TYPE_PERF_EVENT links */ +static __u64 get_bpf_cookie(struct bpf_link *link) +{ + struct bpf_perf_link *perf_link; + struct perf_event *event; + + perf_link = container_of(link, struct bpf_perf_link, link); + event = BPF_CORE_READ(perf_link, perf_file, private_data); + return BPF_CORE_READ(event, bpf_cookie); +} + SEC("iter/task_file") int iter(struct bpf_iter__task_file *ctx) { @@ -69,8 +80,19 @@ int iter(struct bpf_iter__task_file *ctx) if (file->f_op != fops) return 0; + __builtin_memset(&e, 0, sizeof(e)); e.pid = task->tgid; e.id = get_obj_id(file->private_data, obj_type); + + if (obj_type == BPF_OBJ_LINK) { + struct bpf_link *link = (struct bpf_link *) file->private_data; + + if (BPF_CORE_READ(link, type) == BPF_LINK_TYPE_PERF_EVENT) { + e.has_bpf_cookie = true; + e.bpf_cookie = get_bpf_cookie(link); + } + } + bpf_probe_read_kernel_str(&e.comm, sizeof(e.comm), task->group_leader->comm); bpf_seq_write(ctx->meta->seq, &e, sizeof(e)); diff --git a/tools/bpf/bpftool/skeleton/pid_iter.h b/tools/bpf/bpftool/skeleton/pid_iter.h index 5692cf257adb..bbb570d4cca6 100644 --- a/tools/bpf/bpftool/skeleton/pid_iter.h +++ b/tools/bpf/bpftool/skeleton/pid_iter.h @@ -6,6 +6,8 @@ struct pid_iter_entry { __u32 id; int pid; + __u64 bpf_cookie; + bool has_bpf_cookie; char comm[16]; }; diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 2f693b082bdb..e08a6ff2866c 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -480,7 +480,6 @@ static int do_unregister(int argc, char **argv) static int do_register(int argc, char **argv) { LIBBPF_OPTS(bpf_object_open_opts, open_opts); - const struct bpf_map_def *def; struct bpf_map_info info = {}; __u32 info_len = sizeof(info); int nr_errs = 0, nr_maps = 0; @@ -510,8 +509,7 @@ static int do_register(int argc, char **argv) } bpf_object__for_each_map(map, obj) { - def = bpf_map__def(map); - if (def->type != BPF_MAP_TYPE_STRUCT_OPS) + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) continue; link = bpf_map__attach_struct_ops(map); diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index f1f32e21d5cd..2d9cd6a7b3c8 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -8,6 +8,7 @@ #include <string.h> #include <sys/types.h> #include <bpf/libbpf.h> +#include <bpf/libbpf_internal.h> #include "disasm.h" #include "json_writer.h" @@ -32,8 +33,8 @@ void kernel_syms_load(struct dump_data *dd) return; while (fgets(buff, sizeof(buff), fp)) { - tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1, - sizeof(*dd->sym_mapping)); + tmp = libbpf_reallocarray(dd->sym_mapping, dd->sym_count + 1, + sizeof(*dd->sym_mapping)); if (!tmp) { out: free(dd->sym_mapping); diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index 320a88ac28c9..19a3112e271a 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -24,6 +24,8 @@ LD = $(HOSTLD) ARCH = $(HOSTARCH) RM ?= rm CROSS_COMPILE = +CFLAGS := $(KBUILD_HOSTCFLAGS) +LDFLAGS := $(KBUILD_HOSTLDFLAGS) OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ @@ -51,10 +53,10 @@ $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT) $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) \ - DESTDIR=$(LIBBPF_DESTDIR) prefix= \ + DESTDIR=$(LIBBPF_DESTDIR) prefix= EXTRA_CFLAGS="$(CFLAGS)" \ $(abspath $@) install_headers -CFLAGS := -g \ +CFLAGS += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b0383d371b9a..7604e7d5438f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -330,6 +330,8 @@ union bpf_iter_link_info { * *ctx_out*, *data_in* and *data_out* must be NULL. * *repeat* must be zero. * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * * Return * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. @@ -995,6 +997,7 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, + BPF_TRACE_KPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -1009,6 +1012,7 @@ enum bpf_link_type { BPF_LINK_TYPE_NETNS = 5, BPF_LINK_TYPE_XDP = 6, BPF_LINK_TYPE_PERF_EVENT = 7, + BPF_LINK_TYPE_KPROBE_MULTI = 8, MAX_BPF_LINK_TYPE, }; @@ -1111,6 +1115,16 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + +/* link_create.kprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_KPROBE_MULTI attach type to create return probe. + */ +#define BPF_F_KPROBE_MULTI_RETURN (1U << 0) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1225,6 +1239,8 @@ enum { /* If set, run the test on the cpu specified by bpf_attr.test.cpu */ #define BPF_F_TEST_RUN_ON_CPU (1U << 0) +/* If set, XDP frames will be transmitted after processing */ +#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { @@ -1386,6 +1402,7 @@ union bpf_attr { __aligned_u64 ctx_out; __u32 flags; __u32 cpu; + __u32 batch_size; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ @@ -1465,6 +1482,13 @@ union bpf_attr { */ __u64 bpf_cookie; } perf_event; + struct { + __u32 flags; + __u32 cnt; + __aligned_u64 syms; + __aligned_u64 addrs; + __aligned_u64 cookies; + } kprobe_multi; }; } link_create; @@ -1775,6 +1799,8 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. * Return * A 64-bit integer containing the current tgid and pid, and * created as such: @@ -1782,6 +1808,8 @@ union bpf_attr { * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. * Return * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. @@ -2256,6 +2284,8 @@ union bpf_attr { * The 32-bit hash. * * u64 bpf_get_current_task(void) + * Description + * Get the current task. * Return * A pointer to the current task struct. * @@ -2286,8 +2316,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if current task belongs to the cgroup2. - * * 1, if current task does not belong to the cgroup2. + * * 1, if current task belongs to the cgroup2. + * * 0, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) @@ -2369,6 +2399,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. * * long bpf_get_numa_node_id(void) * Description @@ -2466,6 +2498,8 @@ union bpf_attr { * A 8-byte long unique number or 0 if *sk* is NULL. * * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. * Return * The owner UID of the socket associated to *skb*. If the socket * is **NULL**, or if it is not a full socket (i.e. if it is a @@ -3240,6 +3274,9 @@ union bpf_attr { * The id is returned or 0 in case the id could not be retrieved. * * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. @@ -5018,6 +5055,94 @@ union bpf_attr { * * Return * The number of arguments of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * The syscall's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags) + * Description + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * Return + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. + * + * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type) + * Description + * Change the __sk_buff->tstamp_type to *tstamp_type* + * and set *tstamp* to the __sk_buff->tstamp together. + * + * If there is no need to change the __sk_buff->tstamp_type, + * the tstamp value can be directly written to __sk_buff->tstamp + * instead. + * + * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that + * will be kept during bpf_redirect_*(). A non zero + * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO + * *tstamp_type*. + * + * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used + * with a zero *tstamp*. + * + * Only IPv4 and IPv6 skb->protocol are supported. + * + * This function is most useful when it needs to set a + * mono delivery time to __sk_buff->tstamp and then + * bpf_redirect_*() to the egress of an iface. For example, + * changing the (rcv) timestamp in __sk_buff->tstamp at + * ingress to a mono delivery time and then bpf_redirect_*() + * to sch_fq@phy-dev. + * Return + * 0 on success. + * **-EINVAL** for invalid input + * **-EOPNOTSUPP** for unsupported protocol + * + * long bpf_ima_file_hash(struct file *file, void *dst, u32 size) + * Description + * Returns a calculated IMA hash of the *file*. + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5206,6 +5331,14 @@ union bpf_attr { FN(get_func_arg), \ FN(get_func_ret), \ FN(get_func_arg_cnt), \ + FN(get_retval), \ + FN(set_retval), \ + FN(xdp_get_buff_len), \ + FN(xdp_load_bytes), \ + FN(xdp_store_bytes), \ + FN(copy_from_user_task), \ + FN(skb_set_tstamp), \ + FN(ima_file_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5395,6 +5528,15 @@ union { \ __u64 :64; \ } __attribute__((aligned(8))) +enum { + BPF_SKB_TSTAMP_UNSPEC, + BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ + /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, + * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC + * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + */ +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -5435,7 +5577,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; - __u32 :32; /* Padding, future use. */ + __u8 tstamp_type; + __u32 :24; /* Padding, future use. */ __u64 hwtstamp; }; @@ -5500,7 +5643,8 @@ struct bpf_sock { __u32 src_ip4; __u32 src_ip6[4]; __u32 src_port; /* host byte order */ - __u32 dst_port; /* network byte order */ + __be16 dst_port; /* network byte order */ + __u16 :16; /* zero padding */ __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; @@ -6378,7 +6522,8 @@ struct bpf_sk_lookup { __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ __u32 remote_ip4; /* Network byte order */ __u32 remote_ip6[4]; /* Network byte order */ - __u32 remote_port; /* Network byte order */ + __be16 remote_port; /* Network byte order */ + __u16 :16; /* Zero padding */ __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 6218f93f5c1a..e1ba2d51b717 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -860,6 +860,7 @@ enum { IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, IFLA_BOND_MISSED_MAX, + IFLA_BOND_NS_IP6_TARGET, __IFLA_BOND_MAX, }; diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index f947b61b2107..b8b37fe76006 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -131,7 +131,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ sed 's/\[.*\]//' | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) @@ -194,7 +194,7 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ sed 's/\[.*\]//' | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}'| \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ diff -u $(OUTPUT)libbpf_global_syms.tmp \ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 550b4cbb6c99..cf27251adb92 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -29,6 +29,7 @@ #include <errno.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/kernel.h> #include <limits.h> #include <sys/resource.h> #include "bpf.h" @@ -111,7 +112,7 @@ int probe_memcg_account(void) BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns), BPF_EXIT_INSN(), }; - size_t insn_cnt = sizeof(insns) / sizeof(insns[0]); + size_t insn_cnt = ARRAY_SIZE(insns); union bpf_attr attr; int prog_fd; @@ -754,10 +755,10 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, .flags = flags, ); - return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts); + return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts); } -int bpf_prog_attach_xattr(int prog_fd, int target_fd, +int bpf_prog_attach_opts(int prog_fd, int target_fd, enum bpf_attach_type type, const struct bpf_prog_attach_opts *opts) { @@ -778,6 +779,11 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd, return libbpf_err_errno(ret); } +__attribute__((alias("bpf_prog_attach_opts"))) +int bpf_prog_attach_xattr(int prog_fd, int target_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); + int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { union bpf_attr attr; @@ -848,6 +854,15 @@ int bpf_link_create(int prog_fd, int target_fd, if (!OPTS_ZEROED(opts, perf_event)) return libbpf_err(-EINVAL); break; + case BPF_TRACE_KPROBE_MULTI: + attr.link_create.kprobe_multi.flags = OPTS_GET(opts, kprobe_multi.flags, 0); + attr.link_create.kprobe_multi.cnt = OPTS_GET(opts, kprobe_multi.cnt, 0); + attr.link_create.kprobe_multi.syms = ptr_to_u64(OPTS_GET(opts, kprobe_multi.syms, 0)); + attr.link_create.kprobe_multi.addrs = ptr_to_u64(OPTS_GET(opts, kprobe_multi.addrs, 0)); + attr.link_create.kprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, kprobe_multi.cookies, 0)); + if (!OPTS_ZEROED(opts, kprobe_multi)) + return libbpf_err(-EINVAL); + break; default: if (!OPTS_ZEROED(opts, flags)) return libbpf_err(-EINVAL); @@ -989,6 +1004,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) memset(&attr, 0, sizeof(attr)); attr.test.prog_fd = prog_fd; + attr.test.batch_size = OPTS_GET(opts, batch_size, 0); attr.test.cpu = OPTS_GET(opts, cpu, 0); attr.test.flags = OPTS_GET(opts, flags, 0); attr.test.repeat = OPTS_GET(opts, repeat, 0); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 14e0d97ad2cf..f4b4afb6d4ba 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -391,6 +391,10 @@ struct bpf_prog_attach_opts { LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); +LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_prog_attach_opts() instead") LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd, enum bpf_attach_type type, const struct bpf_prog_attach_opts *opts); @@ -409,10 +413,17 @@ struct bpf_link_create_opts { struct { __u64 bpf_cookie; } perf_event; + struct { + __u32 flags; + __u32 cnt; + const char **syms; + const unsigned long *addrs; + const __u64 *cookies; + } kprobe_multi; }; size_t :0; }; -#define bpf_link_create_opts__last_field perf_event +#define bpf_link_create_opts__last_field kprobe_multi.cookies LIBBPF_API int bpf_link_create(int prog_fd, int target_fd, enum bpf_attach_type attach_type, @@ -449,12 +460,14 @@ struct bpf_prog_test_run_attr { * out: length of cxt_out */ }; +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead") LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr); /* * bpf_prog_test_run does not check that data_out is large enough. Consider - * using bpf_prog_test_run_xattr instead. + * using bpf_prog_test_run_opts instead. */ +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead") LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, __u32 *duration); @@ -506,8 +519,9 @@ struct bpf_test_run_opts { __u32 duration; /* out: average per repetition in ns */ __u32 flags; __u32 cpu; + __u32 batch_size; }; -#define bpf_test_run_opts__last_field cpu +#define bpf_test_run_opts__last_field batch_size LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 963b1060d944..44df982d2a5c 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -133,7 +133,7 @@ struct bpf_map_def { unsigned int value_size; unsigned int max_entries; unsigned int map_flags; -}; +} __attribute__((deprecated("use BTF-defined maps in .maps section"))); enum libbpf_pin_type { LIBBPF_PIN_NONE, diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 90f56b0f585f..e3a8c947e89f 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -76,6 +76,9 @@ #define __PT_RC_REG ax #define __PT_SP_REG sp #define __PT_IP_REG ip +/* syscall uses r10 for PARM4 */ +#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) #else @@ -105,6 +108,9 @@ #define __PT_RC_REG rax #define __PT_SP_REG rsp #define __PT_IP_REG rip +/* syscall uses r10 for PARM4 */ +#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) #endif /* __i386__ */ @@ -112,6 +118,10 @@ #elif defined(bpf_target_s390) +struct pt_regs___s390 { + unsigned long orig_gpr2; +}; + /* s390 provides user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const user_pt_regs *)(x)) #define __PT_PARM1_REG gprs[2] @@ -124,6 +134,8 @@ #define __PT_RC_REG gprs[2] #define __PT_SP_REG gprs[15] #define __PT_IP_REG psw.addr +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; }) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2) #elif defined(bpf_target_arm) @@ -140,6 +152,10 @@ #elif defined(bpf_target_arm64) +struct pt_regs___arm64 { + unsigned long orig_x0; +}; + /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) #define __PT_PARM1_REG regs[0] @@ -152,6 +168,8 @@ #define __PT_RC_REG regs[0] #define __PT_SP_REG sp #define __PT_IP_REG pc +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; }) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0) #elif defined(bpf_target_mips) @@ -178,6 +196,8 @@ #define __PT_RC_REG gpr[3] #define __PT_SP_REG sp #define __PT_IP_REG nip +/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx #elif defined(bpf_target_sparc) @@ -206,10 +226,12 @@ #define __PT_PARM4_REG a3 #define __PT_PARM5_REG a4 #define __PT_RET_REG ra -#define __PT_FP_REG fp +#define __PT_FP_REG s0 #define __PT_RC_REG a5 #define __PT_SP_REG sp -#define __PT_IP_REG epc +#define __PT_IP_REG pc +/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx #endif @@ -263,6 +285,26 @@ struct pt_regs; #endif +#ifndef PT_REGS_PARM1_SYSCALL +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x) +#endif +#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x) +#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x) +#ifndef PT_REGS_PARM4_SYSCALL +#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x) +#endif +#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x) + +#ifndef PT_REGS_PARM1_CORE_SYSCALL +#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x) +#endif +#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x) +#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x) +#ifndef PT_REGS_PARM4_CORE_SYSCALL +#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x) +#endif +#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x) + #else /* defined(bpf_target_defined) */ #define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) @@ -290,8 +332,30 @@ struct pt_regs; #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + #endif /* defined(bpf_target_defined) */ +/* + * When invoked from a syscall handler kprobe, returns a pointer to a + * struct pt_regs containing syscall arguments and suitable for passing to + * PT_REGS_PARMn_SYSCALL() and PT_REGS_PARMn_CORE_SYSCALL(). + */ +#ifndef PT_REGS_SYSCALL_REGS +/* By default, assume that the arch selects ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ((struct pt_regs *)PT_REGS_PARM1(ctx)) +#endif + #ifndef ___bpf_concat #define ___bpf_concat(a, b) a ## b #endif @@ -406,4 +470,39 @@ typeof(name(0)) name(struct pt_regs *ctx) \ } \ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) +#define ___bpf_syscall_args0() ctx +#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs) +#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs) +#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs) +#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs) +#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs) +#define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args) + +/* + * BPF_KPROBE_SYSCALL is a variant of BPF_KPROBE, which is intended for + * tracing syscall functions, like __x64_sys_close. It hides the underlying + * platform-specific low-level way of getting syscall input arguments from + * struct pt_regs, and provides a familiar typed and named function arguments + * syntax and semantics of accessing syscall input parameters. + * + * Original struct pt_regs* context is preserved as 'ctx' argument. This might + * be necessary when using BPF helpers like bpf_perf_event_output(). + * + * This macro relies on BPF CO-RE support. + */ +#define BPF_KPROBE_SYSCALL(name, args...) \ +name(struct pt_regs *ctx); \ +static __attribute__((always_inline)) typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + struct pt_regs *regs = PT_REGS_SYSCALL_REGS(ctx); \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_syscall_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __attribute__((always_inline)) typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args) + #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 9aa19c89f758..1383e26c5d1f 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1620,20 +1620,37 @@ static int btf_commit_type(struct btf *btf, int data_sz) struct btf_pipe { const struct btf *src; struct btf *dst; + struct hashmap *str_off_map; /* map string offsets from src to dst */ }; static int btf_rewrite_str(__u32 *str_off, void *ctx) { struct btf_pipe *p = ctx; - int off; + void *mapped_off; + int off, err; if (!*str_off) /* nothing to do for empty strings */ return 0; + if (p->str_off_map && + hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) { + *str_off = (__u32)(long)mapped_off; + return 0; + } + off = btf__add_str(p->dst, btf__str_by_offset(p->src, *str_off)); if (off < 0) return off; + /* Remember string mapping from src to dst. It avoids + * performing expensive string comparisons. + */ + if (p->str_off_map) { + err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off); + if (err) + return err; + } + *str_off = off; return 0; } @@ -1680,6 +1697,9 @@ static int btf_rewrite_type_ids(__u32 *type_id, void *ctx) return 0; } +static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx); +static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx); + int btf__add_btf(struct btf *btf, const struct btf *src_btf) { struct btf_pipe p = { .src = src_btf, .dst = btf }; @@ -1713,6 +1733,11 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) if (!off) return libbpf_err(-ENOMEM); + /* Map the string offsets from src_btf to the offsets from btf to improve performance */ + p.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL); + if (IS_ERR(p.str_off_map)) + return libbpf_err(-ENOMEM); + /* bulk copy types data for all types from src_btf */ memcpy(t, src_btf->types_data, data_sz); @@ -1754,6 +1779,8 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) btf->hdr->str_off += data_sz; btf->nr_types += cnt; + hashmap__free(p.str_off_map); + /* return type ID of the first added BTF type */ return btf->start_id + btf->nr_types - cnt; err_out: @@ -1767,6 +1794,8 @@ err_out: * wasn't modified, so doesn't need restoring, see big comment above */ btf->hdr->str_len = old_strs_len; + hashmap__free(p.str_off_map); + return libbpf_err(err); } diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 061839f04525..951ac7475794 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -147,11 +147,10 @@ LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); LIBBPF_API int btf__fd(const struct btf *btf); LIBBPF_API void btf__set_fd(struct btf *btf, int fd); -LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__raw_data() instead") -LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset); +LIBBPF_DEPRECATED_SINCE(0, 7, "this API is not necessary when BTF-defined maps are used") LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, __u32 expected_key_size, __u32 expected_value_size, @@ -159,8 +158,7 @@ LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size); LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); -LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, - __u32 *size); +LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size); LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions") int btf_ext__reloc_func_info(const struct btf *btf, const struct btf_ext *btf_ext, @@ -171,8 +169,10 @@ int btf_ext__reloc_line_info(const struct btf *btf, const struct btf_ext *btf_ext, const char *sec_name, __u32 insns_cnt, void **line_info, __u32 *cnt); -LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); -LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info is deprecated; write custom func_info parsing to fetch rec_size") +__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info is deprecated; write custom line_info parsing to fetch rec_size") +__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); LIBBPF_API int btf__find_str(struct btf *btf, const char *s); LIBBPF_API int btf__add_str(struct btf *btf, const char *s); @@ -375,8 +375,28 @@ btf_dump__dump_type_data(struct btf_dump *d, __u32 id, const struct btf_dump_type_data_opts *opts); /* - * A set of helpers for easier BTF types handling + * A set of helpers for easier BTF types handling. + * + * The inline functions below rely on constants from the kernel headers which + * may not be available for applications including this header file. To avoid + * compilation errors, we define all the constants here that were added after + * the initial introduction of the BTF_KIND* constants. */ +#ifndef BTF_KIND_FUNC +#define BTF_KIND_FUNC 12 /* Function */ +#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ +#endif +#ifndef BTF_KIND_VAR +#define BTF_KIND_VAR 14 /* Variable */ +#define BTF_KIND_DATASEC 15 /* Section */ +#endif +#ifndef BTF_KIND_FLOAT +#define BTF_KIND_FLOAT 16 /* Floating point */ +#endif +/* The kernel header switched to enums, so these two were never #defined */ +#define BTF_KIND_DECL_TAG 17 /* Decl Tag */ +#define BTF_KIND_TYPE_TAG 18 /* Type Tag */ + static inline __u16 btf_kind(const struct btf_type *t) { return BTF_INFO_KIND(t->info); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index b9a3260c83cb..6b1bc1f43728 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -1505,6 +1505,11 @@ static const char *btf_dump_resolve_name(struct btf_dump *d, __u32 id, if (s->name_resolved) return *cached_name ? *cached_name : orig_name; + if (btf_is_fwd(t) || (btf_is_enum(t) && btf_vlen(t) == 0)) { + s->name_resolved = 1; + return orig_name; + } + dup_cnt = btf_dump_name_dups(d, name_map, orig_name); if (dup_cnt > 1) { const size_t max_len = 256; @@ -1861,14 +1866,16 @@ static int btf_dump_array_data(struct btf_dump *d, { const struct btf_array *array = btf_array(t); const struct btf_type *elem_type; - __u32 i, elem_size = 0, elem_type_id; + __u32 i, elem_type_id; + __s64 elem_size; bool is_array_member; elem_type_id = array->type; elem_type = skip_mods_and_typedefs(d->btf, elem_type_id, NULL); elem_size = btf__resolve_size(d->btf, elem_type_id); if (elem_size <= 0) { - pr_warn("unexpected elem size %d for array type [%u]\n", elem_size, id); + pr_warn("unexpected elem size %zd for array type [%u]\n", + (ssize_t)elem_size, id); return -EINVAL; } diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 8ecef1088ba2..927745b08014 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -1043,18 +1043,27 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, value = add_data(gen, pvalue, value_size); key = add_data(gen, &zero, sizeof(zero)); - /* if (map_desc[map_idx].initial_value) - * copy_from_user(value, initial_value, value_size); + /* if (map_desc[map_idx].initial_value) { + * if (ctx->flags & BPF_SKEL_KERNEL) + * bpf_probe_read_kernel(value, value_size, initial_value); + * else + * bpf_copy_from_user(value, value_size, initial_value); + * } */ emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6, sizeof(struct bpf_loader_ctx) + sizeof(struct bpf_map_desc) * map_idx + offsetof(struct bpf_map_desc, initial_value))); - emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 4)); + emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 8)); emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, value)); emit(gen, BPF_MOV64_IMM(BPF_REG_2, value_size)); + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, + offsetof(struct bpf_loader_ctx, flags))); + emit(gen, BPF_JMP_IMM(BPF_JSET, BPF_REG_0, BPF_SKEL_KERNEL, 2)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user)); + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); map_update_attr = add_data(gen, &attr, attr_size); move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c index 3c20b126d60d..aeb09c288716 100644 --- a/tools/lib/bpf/hashmap.c +++ b/tools/lib/bpf/hashmap.c @@ -75,7 +75,7 @@ void hashmap__clear(struct hashmap *map) void hashmap__free(struct hashmap *map) { - if (!map) + if (IS_ERR_OR_NULL(map)) return; hashmap__clear(map); @@ -238,4 +238,3 @@ bool hashmap__delete(struct hashmap *map, const void *key, return true; } - diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 7f10dd501a52..809fe209cdcc 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -156,14 +156,6 @@ enum libbpf_strict_mode libbpf_mode = LIBBPF_STRICT_NONE; int libbpf_set_strict_mode(enum libbpf_strict_mode mode) { - /* __LIBBPF_STRICT_LAST is the last power-of-2 value used + 1, so to - * get all possible values we compensate last +1, and then (2*x - 1) - * to get the bit mask - */ - if (mode != LIBBPF_STRICT_ALL - && (mode & ~((__LIBBPF_STRICT_LAST - 1) * 2 - 1))) - return errno = EINVAL, -EINVAL; - libbpf_mode = mode; return 0; } @@ -209,12 +201,6 @@ struct reloc_desc { }; }; -struct bpf_sec_def; - -typedef int (*init_fn_t)(struct bpf_program *prog, long cookie); -typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_opts *opts, long cookie); -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie); - /* stored as sec_def->cookie for all libbpf-supported SEC()s */ enum sec_def_flags { SEC_NONE = 0, @@ -235,17 +221,22 @@ enum sec_def_flags { SEC_SLEEPABLE = 8, /* allow non-strict prefix matching */ SEC_SLOPPY_PFX = 16, + /* BPF program support non-linear XDP buffer */ + SEC_XDP_FRAGS = 32, + /* deprecated sec definitions not supposed to be used */ + SEC_DEPRECATED = 64, }; struct bpf_sec_def { - const char *sec; + char *sec; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; long cookie; + int handler_id; - init_fn_t init_fn; - preload_fn_t preload_fn; - attach_fn_t attach_fn; + libbpf_prog_setup_fn_t prog_setup_fn; + libbpf_prog_prepare_load_fn_t prog_prepare_load_fn; + libbpf_prog_attach_fn_t prog_attach_fn; }; /* @@ -1378,22 +1369,20 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32 *size) { - int ret = -ENOENT; Elf_Data *data; Elf_Scn *scn; - *size = 0; if (!name) return -EINVAL; scn = elf_sec_by_name(obj, name); data = elf_sec_data(obj, scn); if (data) { - ret = 0; /* found it */ *size = data->d_size; + return 0; /* found it */ } - return *size ? 0 : ret; + return -ENOENT; } static int find_elf_var_offset(const struct bpf_object *obj, const char *name, __u32 *off) @@ -1529,6 +1518,9 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name) } static int +bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map); + +static int bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, const char *real_name, int sec_idx, void *data, size_t data_sz) { @@ -1575,6 +1567,9 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, return err; } + /* failures are fine because of maps like .rodata.str1.1 */ + (void) bpf_map_find_btf_info(obj, map); + if (data) memcpy(map->mmaped, data, data_sz); @@ -1937,6 +1932,11 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) if (obj->efile.maps_shndx < 0) return 0; + if (libbpf_mode & LIBBPF_STRICT_MAP_DEFINITIONS) { + pr_warn("legacy map definitions in SEC(\"maps\") are not supported\n"); + return -EOPNOTSUPP; + } + if (!symbols) return -EINVAL; @@ -1999,6 +1999,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return -LIBBPF_ERRNO__FORMAT; } + pr_warn("map '%s' (legacy): legacy map definitions are deprecated, use BTF-defined maps instead\n", map_name); + if (ELF64_ST_BIND(sym->st_info) == STB_LOCAL) { pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); return -ENOTSUP; @@ -2050,6 +2052,9 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) } memcpy(&map->def, def, sizeof(struct bpf_map_def)); } + + /* btf info may not exist but fill it in if it does exist */ + (void) bpf_map_find_btf_info(obj, map); } return 0; } @@ -2538,6 +2543,10 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, fill_map_from_def(map->inner_map, &inner_def); } + err = bpf_map_find_btf_info(obj, map); + if (err) + return err; + return 0; } @@ -2792,7 +2801,7 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, goto sort_vars; ret = find_elf_sec_sz(obj, name, &size); - if (ret || !size || (t->size && t->size != size)) { + if (ret || !size) { pr_debug("Invalid size for section %s: %u bytes\n", name, size); return -ENOENT; } @@ -3836,7 +3845,14 @@ static bool prog_is_subprog(const struct bpf_object *obj, * .text programs are subprograms (even if they are not called from * other programs), because libbpf never explicitly supported mixing * SEC()-designated BPF programs and .text entry-point BPF programs. + * + * In libbpf 1.0 strict mode, we always consider .text + * programs to be subprograms. */ + + if (libbpf_mode & LIBBPF_STRICT_SEC_NAME) + return prog->sec_idx == obj->efile.text_shndx; + return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; } @@ -4181,6 +4197,9 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) __u32 key_type_id = 0, value_type_id = 0; int ret; + if (!obj->btf) + return -ENOENT; + /* if it's BTF-defined map, we don't need to search for type IDs. * For struct_ops map, it does not need btf_key_type_id and * btf_value_type_id. @@ -4190,9 +4209,13 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) return 0; if (!bpf_map__is_internal(map)) { + pr_warn("Use of BPF_ANNOTATE_KV_PAIR is deprecated, use BTF-defined maps in .maps section instead\n"); +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size, def->value_size, &key_type_id, &value_type_id); +#pragma GCC diagnostic pop } else { /* * LLVM annotates global data differently in BTF, that is, @@ -4800,8 +4823,8 @@ bpf_object__reuse_map(struct bpf_map *map) } err = bpf_map__reuse_fd(map, pin_fd); + close(pin_fd); if (err) { - close(pin_fd); return err; } map->pinned = true; @@ -4854,7 +4877,6 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b LIBBPF_OPTS(bpf_map_create_opts, create_attr); struct bpf_map_def *def = &map->def; const char *map_name = NULL; - __u32 max_entries; int err = 0; if (kernel_supports(obj, FEAT_PROG_NAME)) @@ -4864,25 +4886,10 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.numa_node = map->numa_node; create_attr.map_extra = map->map_extra; - if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) { - int nr_cpus; - - nr_cpus = libbpf_num_possible_cpus(); - if (nr_cpus < 0) { - pr_warn("map '%s': failed to determine number of system CPUs: %d\n", - map->name, nr_cpus); - return nr_cpus; - } - pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus); - max_entries = nr_cpus; - } else { - max_entries = def->max_entries; - } - if (bpf_map__is_struct_ops(map)) create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; - if (obj->btf && btf__fd(obj->btf) >= 0 && !bpf_map_find_btf_info(obj, map)) { + if (obj->btf && btf__fd(obj->btf) >= 0) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; create_attr.btf_value_type_id = map->btf_value_type_id; @@ -4928,7 +4935,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b if (obj->gen_loader) { bpf_gen__map_create(obj->gen_loader, def->type, map_name, - def->key_size, def->value_size, max_entries, + def->key_size, def->value_size, def->max_entries, &create_attr, is_inner ? -1 : map - obj->maps); /* Pretend to have valid FD to pass various fd >= 0 checks. * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. @@ -4937,7 +4944,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b } else { map->fd = bpf_map_create(def->type, map_name, def->key_size, def->value_size, - max_entries, &create_attr); + def->max_entries, &create_attr); } if (map->fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { @@ -4954,7 +4961,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b map->btf_value_type_id = 0; map->fd = bpf_map_create(def->type, map_name, def->key_size, def->value_size, - max_entries, &create_attr); + def->max_entries, &create_attr); } err = map->fd < 0 ? -errno : 0; @@ -5058,6 +5065,24 @@ static int bpf_object_init_prog_arrays(struct bpf_object *obj) return 0; } +static int map_set_def_max_entries(struct bpf_map *map) +{ + if (map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !map->def.max_entries) { + int nr_cpus; + + nr_cpus = libbpf_num_possible_cpus(); + if (nr_cpus < 0) { + pr_warn("map '%s': failed to determine number of system CPUs: %d\n", + map->name, nr_cpus); + return nr_cpus; + } + pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus); + map->def.max_entries = nr_cpus; + } + + return 0; +} + static int bpf_object__create_maps(struct bpf_object *obj) { @@ -5090,6 +5115,10 @@ bpf_object__create_maps(struct bpf_object *obj) continue; } + err = map_set_def_max_entries(map); + if (err) + goto err_out; + retried = false; retry: if (map->pin_path) { @@ -5185,18 +5214,21 @@ size_t bpf_core_essential_name_len(const char *name) return n; } -static void bpf_core_free_cands(struct bpf_core_cand_list *cands) +void bpf_core_free_cands(struct bpf_core_cand_list *cands) { + if (!cands) + return; + free(cands->cands); free(cands); } -static int bpf_core_add_cands(struct bpf_core_cand *local_cand, - size_t local_essent_len, - const struct btf *targ_btf, - const char *targ_btf_name, - int targ_start_id, - struct bpf_core_cand_list *cands) +int bpf_core_add_cands(struct bpf_core_cand *local_cand, + size_t local_essent_len, + const struct btf *targ_btf, + const char *targ_btf_name, + int targ_start_id, + struct bpf_core_cand_list *cands) { struct bpf_core_cand *new_cands, *cand; const struct btf_type *t, *local_t; @@ -5523,11 +5555,12 @@ static int record_relo_core(struct bpf_program *prog, return 0; } -static int bpf_core_apply_relo(struct bpf_program *prog, - const struct bpf_core_relo *relo, - int relo_idx, - const struct btf *local_btf, - struct hashmap *cand_cache) +static int bpf_core_resolve_relo(struct bpf_program *prog, + const struct bpf_core_relo *relo, + int relo_idx, + const struct btf *local_btf, + struct hashmap *cand_cache, + struct bpf_core_relo_res *targ_res) { struct bpf_core_spec specs_scratch[3] = {}; const void *type_key = u32_as_hash_key(relo->type_id); @@ -5536,20 +5569,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog, const struct btf_type *local_type; const char *local_name; __u32 local_id = relo->type_id; - struct bpf_insn *insn; - int insn_idx, err; - - if (relo->insn_off % BPF_INSN_SZ) - return -EINVAL; - insn_idx = relo->insn_off / BPF_INSN_SZ; - /* adjust insn_idx from section frame of reference to the local - * program's frame of reference; (sub-)program code is not yet - * relocated, so it's enough to just subtract in-section offset - */ - insn_idx = insn_idx - prog->sec_insn_off; - if (insn_idx >= prog->insns_cnt) - return -EINVAL; - insn = &prog->insns[insn_idx]; + int err; local_type = btf__type_by_id(local_btf, local_id); if (!local_type) @@ -5559,15 +5579,6 @@ static int bpf_core_apply_relo(struct bpf_program *prog, if (!local_name) return -EINVAL; - if (prog->obj->gen_loader) { - const char *spec_str = btf__name_by_offset(local_btf, relo->access_str_off); - - pr_debug("record_relo_core: prog %td insn[%d] %s %s %s final insn_idx %d\n", - prog - prog->obj->programs, relo->insn_off / 8, - btf_kind_str(local_type), local_name, spec_str, insn_idx); - return record_relo_core(prog, relo, insn_idx); - } - if (relo->kind != BPF_CORE_TYPE_ID_LOCAL && !hashmap__find(cand_cache, type_key, (void **)&cands)) { cands = bpf_core_find_cands(prog->obj, local_btf, local_id); @@ -5584,19 +5595,21 @@ static int bpf_core_apply_relo(struct bpf_program *prog, } } - return bpf_core_apply_relo_insn(prog_name, insn, insn_idx, relo, - relo_idx, local_btf, cands, specs_scratch); + return bpf_core_calc_relo_insn(prog_name, relo, relo_idx, local_btf, cands, specs_scratch, + targ_res); } static int bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) { const struct btf_ext_info_sec *sec; + struct bpf_core_relo_res targ_res; const struct bpf_core_relo *rec; const struct btf_ext_info *seg; struct hashmap_entry *entry; struct hashmap *cand_cache = NULL; struct bpf_program *prog; + struct bpf_insn *insn; const char *sec_name; int i, err = 0, insn_idx, sec_idx; @@ -5647,6 +5660,8 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) sec_name, sec->num_info); for_each_btf_ext_rec(seg, sec, i, rec) { + if (rec->insn_off % BPF_INSN_SZ) + return -EINVAL; insn_idx = rec->insn_off / BPF_INSN_SZ; prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx); if (!prog) { @@ -5661,12 +5676,38 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) if (!prog->load) continue; - err = bpf_core_apply_relo(prog, rec, i, obj->btf, cand_cache); + /* adjust insn_idx from section frame of reference to the local + * program's frame of reference; (sub-)program code is not yet + * relocated, so it's enough to just subtract in-section offset + */ + insn_idx = insn_idx - prog->sec_insn_off; + if (insn_idx >= prog->insns_cnt) + return -EINVAL; + insn = &prog->insns[insn_idx]; + + if (prog->obj->gen_loader) { + err = record_relo_core(prog, rec, insn_idx); + if (err) { + pr_warn("prog '%s': relo #%d: failed to record relocation: %d\n", + prog->name, i, err); + goto out; + } + continue; + } + + err = bpf_core_resolve_relo(prog, rec, i, obj->btf, cand_cache, &targ_res); if (err) { pr_warn("prog '%s': relo #%d: failed to relocate: %d\n", prog->name, i, err); goto out; } + + err = bpf_core_patch_insn(prog->name, insn, insn_idx, rec, i, &targ_res); + if (err) { + pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n", + prog->name, i, insn_idx, err); + goto out; + } } } @@ -6549,9 +6590,9 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, int *btf_obj_fd, int *btf_type_id); -/* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */ -static int libbpf_preload_prog(struct bpf_program *prog, - struct bpf_prog_load_opts *opts, long cookie) +/* this is called as prog->sec_def->prog_prepare_load_fn for libbpf-supported sec_defs */ +static int libbpf_prepare_prog_load(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie) { enum sec_def_flags def = cookie; @@ -6562,6 +6603,13 @@ static int libbpf_preload_prog(struct bpf_program *prog, if (def & SEC_SLEEPABLE) opts->prog_flags |= BPF_F_SLEEPABLE; + if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS)) + opts->prog_flags |= BPF_F_XDP_HAS_FRAGS; + + if (def & SEC_DEPRECATED) + pr_warn("SEC(\"%s\") is deprecated, please see https://github.com/libbpf/libbpf/wiki/Libbpf-1.0-migration-guide#bpf-program-sec-annotation-deprecations for details\n", + prog->sec_name); + if ((prog->type == BPF_PROG_TYPE_TRACING || prog->type == BPF_PROG_TYPE_LSM || prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { @@ -6640,8 +6688,8 @@ static int bpf_object_load_prog_instance(struct bpf_object *obj, struct bpf_prog load_attr.fd_array = obj->fd_array; /* adjust load_attr if sec_def provides custom preload callback */ - if (prog->sec_def && prog->sec_def->preload_fn) { - err = prog->sec_def->preload_fn(prog, &load_attr, prog->sec_def->cookie); + if (prog->sec_def && prog->sec_def->prog_prepare_load_fn) { + err = prog->sec_def->prog_prepare_load_fn(prog, &load_attr, prog->sec_def->cookie); if (err < 0) { pr_warn("prog '%s': failed to prepare load attributes: %d\n", prog->name, err); @@ -6941,8 +6989,8 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object /* sec_def can have custom callback which should be called * after bpf_program is initialized to adjust its properties */ - if (prog->sec_def->init_fn) { - err = prog->sec_def->init_fn(prog, prog->sec_def->cookie); + if (prog->sec_def->prog_setup_fn) { + err = prog->sec_def->prog_setup_fn(prog, prog->sec_def->cookie); if (err < 0) { pr_warn("prog '%s': failed to initialize: %d\n", prog->name, err); @@ -7146,12 +7194,10 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) return 0; } -static int bpf_object__read_kallsyms_file(struct bpf_object *obj) +int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) { char sym_type, sym_name[500]; unsigned long long sym_addr; - const struct btf_type *t; - struct extern_desc *ext; int ret, err = 0; FILE *f; @@ -7170,35 +7216,51 @@ static int bpf_object__read_kallsyms_file(struct bpf_object *obj) if (ret != 3) { pr_warn("failed to read kallsyms entry: %d\n", ret); err = -EINVAL; - goto out; + break; } - ext = find_extern_by_name(obj, sym_name); - if (!ext || ext->type != EXT_KSYM) - continue; - - t = btf__type_by_id(obj->btf, ext->btf_id); - if (!btf_is_var(t)) - continue; - - if (ext->is_set && ext->ksym.addr != sym_addr) { - pr_warn("extern (ksym) '%s' resolution is ambiguous: 0x%llx or 0x%llx\n", - sym_name, ext->ksym.addr, sym_addr); - err = -EINVAL; - goto out; - } - if (!ext->is_set) { - ext->is_set = true; - ext->ksym.addr = sym_addr; - pr_debug("extern (ksym) %s=0x%llx\n", sym_name, sym_addr); - } + err = cb(sym_addr, sym_type, sym_name, ctx); + if (err) + break; } -out: fclose(f); return err; } +static int kallsyms_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) +{ + struct bpf_object *obj = ctx; + const struct btf_type *t; + struct extern_desc *ext; + + ext = find_extern_by_name(obj, sym_name); + if (!ext || ext->type != EXT_KSYM) + return 0; + + t = btf__type_by_id(obj->btf, ext->btf_id); + if (!btf_is_var(t)) + return 0; + + if (ext->is_set && ext->ksym.addr != sym_addr) { + pr_warn("extern (ksym) '%s' resolution is ambiguous: 0x%llx or 0x%llx\n", + sym_name, ext->ksym.addr, sym_addr); + return -EINVAL; + } + if (!ext->is_set) { + ext->is_set = true; + ext->ksym.addr = sym_addr; + pr_debug("extern (ksym) %s=0x%llx\n", sym_name, sym_addr); + } + return 0; +} + +static int bpf_object__read_kallsyms_file(struct bpf_object *obj) +{ + return libbpf_kallsyms_parse(kallsyms_cb, obj); +} + static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, __u16 kind, struct btf **res_btf, struct module_btf **res_mod_btf) @@ -7883,10 +7945,8 @@ int bpf_map__set_pin_path(struct bpf_map *map, const char *path) return 0; } -const char *bpf_map__get_pin_path(const struct bpf_map *map) -{ - return map->pin_path; -} +__alias(bpf_map__pin_path) +const char *bpf_map__get_pin_path(const struct bpf_map *map); const char *bpf_map__pin_path(const struct bpf_map *map) { @@ -8451,7 +8511,10 @@ static int bpf_program_nth_fd(const struct bpf_program *prog, int n) return fd; } -enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog) +__alias(bpf_program__type) +enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); + +enum bpf_prog_type bpf_program__type(const struct bpf_program *prog) { return prog->type; } @@ -8495,8 +8558,10 @@ BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS); BPF_PROG_TYPE_FNS(extension, BPF_PROG_TYPE_EXT); BPF_PROG_TYPE_FNS(sk_lookup, BPF_PROG_TYPE_SK_LOOKUP); -enum bpf_attach_type -bpf_program__get_expected_attach_type(const struct bpf_program *prog) +__alias(bpf_program__expected_attach_type) +enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog); + +enum bpf_attach_type bpf_program__expected_attach_type(const struct bpf_program *prog) { return prog->expected_attach_type; } @@ -8556,20 +8621,21 @@ int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log } #define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ - .sec = sec_pfx, \ + .sec = (char *)sec_pfx, \ .prog_type = BPF_PROG_TYPE_##ptype, \ .expected_attach_type = atype, \ .cookie = (long)(flags), \ - .preload_fn = libbpf_preload_prog, \ + .prog_prepare_load_fn = libbpf_prepare_prog_load, \ __VA_ARGS__ \ } -static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie); +static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link); static const struct bpf_sec_def section_defs[] = { SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE | SEC_SLOPPY_PFX), @@ -8579,8 +8645,10 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("uprobe/", KPROBE, 0, SEC_NONE), SEC_DEF("kretprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), SEC_DEF("uretprobe/", KPROBE, 0, SEC_NONE), + SEC_DEF("kprobe.multi/", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), + SEC_DEF("kretprobe.multi/", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX | SEC_DEPRECATED), SEC_DEF("action", SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX), SEC_DEF("tracepoint/", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("tp/", TRACEPOINT, 0, SEC_NONE, attach_tp), @@ -8599,9 +8667,15 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("lsm/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm), SEC_DEF("lsm.s/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), SEC_DEF("iter/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter), + SEC_DEF("iter.s/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_iter), SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), - SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), - SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp.frags/devmap", XDP, BPF_XDP_DEVMAP, SEC_XDP_FRAGS), + SEC_DEF("xdp/devmap", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), + SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE | SEC_DEPRECATED), + SEC_DEF("xdp.frags/cpumap", XDP, BPF_XDP_CPUMAP, SEC_XDP_FRAGS), + SEC_DEF("xdp/cpumap", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE | SEC_DEPRECATED), + SEC_DEF("xdp.frags", XDP, BPF_XDP, SEC_XDP_FRAGS), SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX), SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX), @@ -8643,61 +8717,167 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE | SEC_SLOPPY_PFX), }; -#define MAX_TYPE_NAME_SIZE 32 +static size_t custom_sec_def_cnt; +static struct bpf_sec_def *custom_sec_defs; +static struct bpf_sec_def custom_fallback_def; +static bool has_custom_fallback_def; -static const struct bpf_sec_def *find_sec_def(const char *sec_name) +static int last_custom_sec_def_handler_id; + +int libbpf_register_prog_handler(const char *sec, + enum bpf_prog_type prog_type, + enum bpf_attach_type exp_attach_type, + const struct libbpf_prog_handler_opts *opts) { - const struct bpf_sec_def *sec_def; - enum sec_def_flags sec_flags; - int i, n = ARRAY_SIZE(section_defs), len; - bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME; + struct bpf_sec_def *sec_def; - for (i = 0; i < n; i++) { - sec_def = §ion_defs[i]; - sec_flags = sec_def->cookie; - len = strlen(sec_def->sec); + if (!OPTS_VALID(opts, libbpf_prog_handler_opts)) + return libbpf_err(-EINVAL); - /* "type/" always has to have proper SEC("type/extras") form */ - if (sec_def->sec[len - 1] == '/') { - if (str_has_pfx(sec_name, sec_def->sec)) - return sec_def; - continue; - } + if (last_custom_sec_def_handler_id == INT_MAX) /* prevent overflow */ + return libbpf_err(-E2BIG); - /* "type+" means it can be either exact SEC("type") or - * well-formed SEC("type/extras") with proper '/' separator - */ - if (sec_def->sec[len - 1] == '+') { - len--; - /* not even a prefix */ - if (strncmp(sec_name, sec_def->sec, len) != 0) - continue; - /* exact match or has '/' separator */ - if (sec_name[len] == '\0' || sec_name[len] == '/') - return sec_def; - continue; - } + if (sec) { + sec_def = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt + 1, + sizeof(*sec_def)); + if (!sec_def) + return libbpf_err(-ENOMEM); - /* SEC_SLOPPY_PFX definitions are allowed to be just prefix - * matches, unless strict section name mode - * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the - * match has to be exact. - */ - if ((sec_flags & SEC_SLOPPY_PFX) && !strict) { - if (str_has_pfx(sec_name, sec_def->sec)) - return sec_def; - continue; - } + custom_sec_defs = sec_def; + sec_def = &custom_sec_defs[custom_sec_def_cnt]; + } else { + if (has_custom_fallback_def) + return libbpf_err(-EBUSY); - /* Definitions not marked SEC_SLOPPY_PFX (e.g., - * SEC("syscall")) are exact matches in both modes. - */ - if (strcmp(sec_name, sec_def->sec) == 0) + sec_def = &custom_fallback_def; + } + + sec_def->sec = sec ? strdup(sec) : NULL; + if (sec && !sec_def->sec) + return libbpf_err(-ENOMEM); + + sec_def->prog_type = prog_type; + sec_def->expected_attach_type = exp_attach_type; + sec_def->cookie = OPTS_GET(opts, cookie, 0); + + sec_def->prog_setup_fn = OPTS_GET(opts, prog_setup_fn, NULL); + sec_def->prog_prepare_load_fn = OPTS_GET(opts, prog_prepare_load_fn, NULL); + sec_def->prog_attach_fn = OPTS_GET(opts, prog_attach_fn, NULL); + + sec_def->handler_id = ++last_custom_sec_def_handler_id; + + if (sec) + custom_sec_def_cnt++; + else + has_custom_fallback_def = true; + + return sec_def->handler_id; +} + +int libbpf_unregister_prog_handler(int handler_id) +{ + struct bpf_sec_def *sec_defs; + int i; + + if (handler_id <= 0) + return libbpf_err(-EINVAL); + + if (has_custom_fallback_def && custom_fallback_def.handler_id == handler_id) { + memset(&custom_fallback_def, 0, sizeof(custom_fallback_def)); + has_custom_fallback_def = false; + return 0; + } + + for (i = 0; i < custom_sec_def_cnt; i++) { + if (custom_sec_defs[i].handler_id == handler_id) + break; + } + + if (i == custom_sec_def_cnt) + return libbpf_err(-ENOENT); + + free(custom_sec_defs[i].sec); + for (i = i + 1; i < custom_sec_def_cnt; i++) + custom_sec_defs[i - 1] = custom_sec_defs[i]; + custom_sec_def_cnt--; + + /* try to shrink the array, but it's ok if we couldn't */ + sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs)); + if (sec_defs) + custom_sec_defs = sec_defs; + + return 0; +} + +static bool sec_def_matches(const struct bpf_sec_def *sec_def, const char *sec_name, + bool allow_sloppy) +{ + size_t len = strlen(sec_def->sec); + + /* "type/" always has to have proper SEC("type/extras") form */ + if (sec_def->sec[len - 1] == '/') { + if (str_has_pfx(sec_name, sec_def->sec)) + return true; + return false; + } + + /* "type+" means it can be either exact SEC("type") or + * well-formed SEC("type/extras") with proper '/' separator + */ + if (sec_def->sec[len - 1] == '+') { + len--; + /* not even a prefix */ + if (strncmp(sec_name, sec_def->sec, len) != 0) + return false; + /* exact match or has '/' separator */ + if (sec_name[len] == '\0' || sec_name[len] == '/') + return true; + return false; + } + + /* SEC_SLOPPY_PFX definitions are allowed to be just prefix + * matches, unless strict section name mode + * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the + * match has to be exact. + */ + if (allow_sloppy && str_has_pfx(sec_name, sec_def->sec)) + return true; + + /* Definitions not marked SEC_SLOPPY_PFX (e.g., + * SEC("syscall")) are exact matches in both modes. + */ + return strcmp(sec_name, sec_def->sec) == 0; +} + +static const struct bpf_sec_def *find_sec_def(const char *sec_name) +{ + const struct bpf_sec_def *sec_def; + int i, n; + bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME, allow_sloppy; + + n = custom_sec_def_cnt; + for (i = 0; i < n; i++) { + sec_def = &custom_sec_defs[i]; + if (sec_def_matches(sec_def, sec_name, false)) return sec_def; } + + n = ARRAY_SIZE(section_defs); + for (i = 0; i < n; i++) { + sec_def = §ion_defs[i]; + allow_sloppy = (sec_def->cookie & SEC_SLOPPY_PFX) && !strict; + if (sec_def_matches(sec_def, sec_name, allow_sloppy)) + return sec_def; + } + + if (has_custom_fallback_def) + return &custom_fallback_def; + return NULL; } +#define MAX_TYPE_NAME_SIZE 32 + static char *libbpf_get_type_names(bool attach_type) { int i, len = ARRAY_SIZE(section_defs) * MAX_TYPE_NAME_SIZE; @@ -8713,7 +8893,7 @@ static char *libbpf_get_type_names(bool attach_type) const struct bpf_sec_def *sec_def = §ion_defs[i]; if (attach_type) { - if (sec_def->preload_fn != libbpf_preload_prog) + if (sec_def->prog_prepare_load_fn != libbpf_prepare_prog_load) continue; if (!(sec_def->cookie & SEC_ATTACHABLE)) @@ -9096,7 +9276,7 @@ int libbpf_attach_type_by_name(const char *name, return libbpf_err(-EINVAL); } - if (sec_def->preload_fn != libbpf_preload_prog) + if (sec_def->prog_prepare_load_fn != libbpf_prepare_prog_load) return libbpf_err(-EINVAL); if (!(sec_def->cookie & SEC_ATTACHABLE)) return libbpf_err(-EINVAL); @@ -9443,7 +9623,7 @@ static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, open_attr.file = attr->file; open_attr.prog_type = attr->prog_type; - obj = bpf_object__open_xattr(&open_attr); + obj = __bpf_object__open_xattr(&open_attr, 0); err = libbpf_get_error(obj); if (err) return libbpf_err(-ENOENT); @@ -9460,7 +9640,7 @@ static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, bpf_program__set_expected_attach_type(prog, attach_type); } - if (bpf_program__get_type(prog) == BPF_PROG_TYPE_UNSPEC) { + if (bpf_program__type(prog) == BPF_PROG_TYPE_UNSPEC) { /* * we haven't guessed from section name and user * didn't provide a fallback type, too bad... @@ -9477,7 +9657,7 @@ static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, } bpf_object__for_each_map(map, obj) { - if (!bpf_map__is_offload_neutral(map)) + if (map->def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) map->map_ifindex = attr->ifindex; } @@ -10070,14 +10250,146 @@ struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, return bpf_program__attach_kprobe_opts(prog, func_name, &opts); } -static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie) +/* Adapted from perf/util/string.c */ +static bool glob_match(const char *str, const char *pat) +{ + while (*str && *pat && *pat != '*') { + if (*pat == '?') { /* Matches any single character */ + str++; + pat++; + continue; + } + if (*str != *pat) + return false; + str++; + pat++; + } + /* Check wild card */ + if (*pat == '*') { + while (*pat == '*') + pat++; + if (!*pat) /* Tail wild card matches all */ + return true; + while (*str) + if (glob_match(str++, pat)) + return true; + } + return !*str && !*pat; +} + +struct kprobe_multi_resolve { + const char *pattern; + unsigned long *addrs; + size_t cap; + size_t cnt; +}; + +static int +resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) +{ + struct kprobe_multi_resolve *res = ctx; + int err; + + if (!glob_match(sym_name, res->pattern)) + return 0; + + err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long), + res->cnt + 1); + if (err) + return err; + + res->addrs[res->cnt++] = (unsigned long) sym_addr; + return 0; +} + +struct bpf_link * +bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, + const char *pattern, + const struct bpf_kprobe_multi_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, lopts); + struct kprobe_multi_resolve res = { + .pattern = pattern, + }; + struct bpf_link *link = NULL; + char errmsg[STRERR_BUFSIZE]; + const unsigned long *addrs; + int err, link_fd, prog_fd; + const __u64 *cookies; + const char **syms; + bool retprobe; + size_t cnt; + + if (!OPTS_VALID(opts, bpf_kprobe_multi_opts)) + return libbpf_err_ptr(-EINVAL); + + syms = OPTS_GET(opts, syms, false); + addrs = OPTS_GET(opts, addrs, false); + cnt = OPTS_GET(opts, cnt, false); + cookies = OPTS_GET(opts, cookies, false); + + if (!pattern && !addrs && !syms) + return libbpf_err_ptr(-EINVAL); + if (pattern && (addrs || syms || cookies || cnt)) + return libbpf_err_ptr(-EINVAL); + if (!pattern && !cnt) + return libbpf_err_ptr(-EINVAL); + if (addrs && syms) + return libbpf_err_ptr(-EINVAL); + + if (pattern) { + err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res); + if (err) + goto error; + if (!res.cnt) { + err = -ENOENT; + goto error; + } + addrs = res.addrs; + cnt = res.cnt; + } + + retprobe = OPTS_GET(opts, retprobe, false); + + lopts.kprobe_multi.syms = syms; + lopts.kprobe_multi.addrs = addrs; + lopts.kprobe_multi.cookies = cookies; + lopts.kprobe_multi.cnt = cnt; + lopts.kprobe_multi.flags = retprobe ? BPF_F_KPROBE_MULTI_RETURN : 0; + + link = calloc(1, sizeof(*link)); + if (!link) { + err = -ENOMEM; + goto error; + } + link->detach = &bpf_link__detach_fd; + + prog_fd = bpf_program__fd(prog); + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &lopts); + if (link_fd < 0) { + err = -errno; + pr_warn("prog '%s': failed to attach: %s\n", + prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto error; + } + link->fd = link_fd; + free(res.addrs); + return link; + +error: + free(link); + free(res.addrs); + return libbpf_err_ptr(err); +} + +static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link) { DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts); unsigned long offset = 0; - struct bpf_link *link; const char *func_name; char *func; - int n, err; + int n; opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/"); if (opts.retprobe) @@ -10087,21 +10399,43 @@ static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cooki n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset); if (n < 1) { - err = -EINVAL; pr_warn("kprobe name is invalid: %s\n", func_name); - return libbpf_err_ptr(err); + return -EINVAL; } if (opts.retprobe && offset != 0) { free(func); - err = -EINVAL; pr_warn("kretprobes do not support offset specification\n"); - return libbpf_err_ptr(err); + return -EINVAL; } opts.offset = offset; - link = bpf_program__attach_kprobe_opts(prog, func, &opts); + *link = bpf_program__attach_kprobe_opts(prog, func, &opts); free(func); - return link; + return libbpf_get_error(*link); +} + +static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + const char *spec; + char *pattern; + int n; + + opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe.multi/"); + if (opts.retprobe) + spec = prog->sec_name + sizeof("kretprobe.multi/") - 1; + else + spec = prog->sec_name + sizeof("kprobe.multi/") - 1; + + n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern); + if (n < 1) { + pr_warn("kprobe multi pattern is invalid: %s\n", pattern); + return -EINVAL; + } + + *link = bpf_program__attach_kprobe_multi_opts(prog, pattern, &opts); + free(pattern); + return libbpf_get_error(*link); } static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, @@ -10356,14 +10690,13 @@ struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog, return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL); } -static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) +static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link) { char *sec_name, *tp_cat, *tp_name; - struct bpf_link *link; sec_name = strdup(prog->sec_name); if (!sec_name) - return libbpf_err_ptr(-ENOMEM); + return -ENOMEM; /* extract "tp/<category>/<name>" or "tracepoint/<category>/<name>" */ if (str_has_pfx(prog->sec_name, "tp/")) @@ -10373,14 +10706,14 @@ static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) tp_name = strchr(tp_cat, '/'); if (!tp_name) { free(sec_name); - return libbpf_err_ptr(-EINVAL); + return -EINVAL; } *tp_name = '\0'; tp_name++; - link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); + *link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); free(sec_name); - return link; + return libbpf_get_error(*link); } struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, @@ -10413,7 +10746,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr return link; } -static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie) +static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link) { static const char *const prefixes[] = { "raw_tp/", @@ -10433,10 +10766,11 @@ static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cooki if (!tp_name) { pr_warn("prog '%s': invalid section name '%s'\n", prog->name, prog->sec_name); - return libbpf_err_ptr(-EINVAL); + return -EINVAL; } - return bpf_program__attach_raw_tracepoint(prog, tp_name); + *link = bpf_program__attach_raw_tracepoint(prog, tp_name); + return libbpf_get_error(link); } /* Common logic for all BPF program types that attach to a btf_id */ @@ -10479,14 +10813,16 @@ struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog) return bpf_program__attach_btf_id(prog); } -static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie) +static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link) { - return bpf_program__attach_trace(prog); + *link = bpf_program__attach_trace(prog); + return libbpf_get_error(*link); } -static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie) +static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link) { - return bpf_program__attach_lsm(prog); + *link = bpf_program__attach_lsm(prog); + return libbpf_get_error(*link); } static struct bpf_link * @@ -10511,7 +10847,7 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_fd; - attach_type = bpf_program__get_expected_attach_type(prog); + attach_type = bpf_program__expected_attach_type(prog); link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts); if (link_fd < 0) { link_fd = -errno; @@ -10615,17 +10951,33 @@ bpf_program__attach_iter(const struct bpf_program *prog, return link; } -static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie) +static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link) { - return bpf_program__attach_iter(prog, NULL); + *link = bpf_program__attach_iter(prog, NULL); + return libbpf_get_error(*link); } struct bpf_link *bpf_program__attach(const struct bpf_program *prog) { - if (!prog->sec_def || !prog->sec_def->attach_fn) - return libbpf_err_ptr(-ESRCH); + struct bpf_link *link = NULL; + int err; + + if (!prog->sec_def || !prog->sec_def->prog_attach_fn) + return libbpf_err_ptr(-EOPNOTSUPP); + + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, &link); + if (err) + return libbpf_err_ptr(err); - return prog->sec_def->attach_fn(prog, prog->sec_def->cookie); + /* When calling bpf_program__attach() explicitly, auto-attach support + * is expected to work, so NULL returned link is considered an error. + * This is different for skeleton's attach, see comment in + * bpf_object__attach_skeleton(). + */ + if (!link) + return libbpf_err_ptr(-EOPNOTSUPP); + + return link; } static int bpf_link__detach_struct_ops(struct bpf_link *link) @@ -10912,7 +11264,7 @@ struct perf_buffer *perf_buffer__new_raw_v0_6_0(int map_fd, size_t page_cnt, { struct perf_buffer_params p = {}; - if (page_cnt == 0 || !attr) + if (!attr) return libbpf_err_ptr(-EINVAL); if (!OPTS_VALID(opts, perf_buffer_raw_opts)) @@ -10953,7 +11305,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, __u32 map_info_len; int err, i, j, n; - if (page_cnt & (page_cnt - 1)) { + if (page_cnt == 0 || (page_cnt & (page_cnt - 1))) { pr_warn("page count should be power of two, but is %zu\n", page_cnt); return ERR_PTR(-EINVAL); @@ -11640,6 +11992,49 @@ int libbpf_num_possible_cpus(void) return tmp_cpus; } +static int populate_skeleton_maps(const struct bpf_object *obj, + struct bpf_map_skeleton *maps, + size_t map_cnt) +{ + int i; + + for (i = 0; i < map_cnt; i++) { + struct bpf_map **map = maps[i].map; + const char *name = maps[i].name; + void **mmaped = maps[i].mmaped; + + *map = bpf_object__find_map_by_name(obj, name); + if (!*map) { + pr_warn("failed to find skeleton map '%s'\n", name); + return -ESRCH; + } + + /* externs shouldn't be pre-setup from user code */ + if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) + *mmaped = (*map)->mmaped; + } + return 0; +} + +static int populate_skeleton_progs(const struct bpf_object *obj, + struct bpf_prog_skeleton *progs, + size_t prog_cnt) +{ + int i; + + for (i = 0; i < prog_cnt; i++) { + struct bpf_program **prog = progs[i].prog; + const char *name = progs[i].name; + + *prog = bpf_object__find_program_by_name(obj, name); + if (!*prog) { + pr_warn("failed to find skeleton program '%s'\n", name); + return -ESRCH; + } + } + return 0; +} + int bpf_object__open_skeleton(struct bpf_object_skeleton *s, const struct bpf_object_open_opts *opts) { @@ -11647,7 +12042,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s, .object_name = s->name, ); struct bpf_object *obj; - int i, err; + int err; /* Attempt to preserve opts->object_name, unless overriden by user * explicitly. Overwriting object name for skeletons is discouraged, @@ -11670,37 +12065,91 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s, } *s->obj = obj; + err = populate_skeleton_maps(obj, s->maps, s->map_cnt); + if (err) { + pr_warn("failed to populate skeleton maps for '%s': %d\n", s->name, err); + return libbpf_err(err); + } - for (i = 0; i < s->map_cnt; i++) { - struct bpf_map **map = s->maps[i].map; - const char *name = s->maps[i].name; - void **mmaped = s->maps[i].mmaped; + err = populate_skeleton_progs(obj, s->progs, s->prog_cnt); + if (err) { + pr_warn("failed to populate skeleton progs for '%s': %d\n", s->name, err); + return libbpf_err(err); + } - *map = bpf_object__find_map_by_name(obj, name); - if (!*map) { - pr_warn("failed to find skeleton map '%s'\n", name); - return libbpf_err(-ESRCH); - } + return 0; +} - /* externs shouldn't be pre-setup from user code */ - if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) - *mmaped = (*map)->mmaped; +int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s) +{ + int err, len, var_idx, i; + const char *var_name; + const struct bpf_map *map; + struct btf *btf; + __u32 map_type_id; + const struct btf_type *map_type, *var_type; + const struct bpf_var_skeleton *var_skel; + struct btf_var_secinfo *var; + + if (!s->obj) + return libbpf_err(-EINVAL); + + btf = bpf_object__btf(s->obj); + if (!btf) { + pr_warn("subskeletons require BTF at runtime (object %s)\n", + bpf_object__name(s->obj)); + return libbpf_err(-errno); } - for (i = 0; i < s->prog_cnt; i++) { - struct bpf_program **prog = s->progs[i].prog; - const char *name = s->progs[i].name; + err = populate_skeleton_maps(s->obj, s->maps, s->map_cnt); + if (err) { + pr_warn("failed to populate subskeleton maps: %d\n", err); + return libbpf_err(err); + } - *prog = bpf_object__find_program_by_name(obj, name); - if (!*prog) { - pr_warn("failed to find skeleton program '%s'\n", name); - return libbpf_err(-ESRCH); - } + err = populate_skeleton_progs(s->obj, s->progs, s->prog_cnt); + if (err) { + pr_warn("failed to populate subskeleton maps: %d\n", err); + return libbpf_err(err); } + for (var_idx = 0; var_idx < s->var_cnt; var_idx++) { + var_skel = &s->vars[var_idx]; + map = *var_skel->map; + map_type_id = bpf_map__btf_value_type_id(map); + map_type = btf__type_by_id(btf, map_type_id); + + if (!btf_is_datasec(map_type)) { + pr_warn("type for map '%1$s' is not a datasec: %2$s", + bpf_map__name(map), + __btf_kind_str(btf_kind(map_type))); + return libbpf_err(-EINVAL); + } + + len = btf_vlen(map_type); + var = btf_var_secinfos(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + var_name = btf__name_by_offset(btf, var_type->name_off); + if (strcmp(var_name, var_skel->name) == 0) { + *var_skel->addr = map->mmaped + var->offset; + break; + } + } + } return 0; } +void bpf_object__destroy_subskeleton(struct bpf_object_subskeleton *s) +{ + if (!s) + return; + free(s->maps); + free(s->progs); + free(s->vars); + free(s); +} + int bpf_object__load_skeleton(struct bpf_object_skeleton *s) { int i, err; @@ -11766,16 +12215,30 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) continue; /* auto-attaching not supported for this program */ - if (!prog->sec_def || !prog->sec_def->attach_fn) + if (!prog->sec_def || !prog->sec_def->prog_attach_fn) continue; - *link = bpf_program__attach(prog); - err = libbpf_get_error(*link); + /* if user already set the link manually, don't attempt auto-attach */ + if (*link) + continue; + + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, link); if (err) { - pr_warn("failed to auto-attach program '%s': %d\n", + pr_warn("prog '%s': failed to auto-attach: %d\n", bpf_program__name(prog), err); return libbpf_err(err); } + + /* It's possible that for some SEC() definitions auto-attach + * is supported in some cases (e.g., if definition completely + * specifies target information), but is not in other cases. + * SEC("uprobe") is one such case. If user specified target + * binary and function name, such BPF program can be + * auto-attached. But if not, it shouldn't trigger skeleton's + * attach to fail. It should just be skipped. + * attach_fn signals such case with returning 0 (no error) and + * setting link to NULL. + */ } return 0; @@ -11795,6 +12258,9 @@ void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) { + if (!s) + return; + if (s->progs) bpf_object__detach_skeleton(s); if (s->obj) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 8b9bc5e90c2b..05dde85e19a6 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -180,9 +180,11 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts); /* deprecated bpf_object__open variants */ +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open_mem() instead") LIBBPF_API struct bpf_object * bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, const char *name); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open_file() instead") LIBBPF_API struct bpf_object * bpf_object__open_xattr(struct bpf_object_open_attr *attr); @@ -244,8 +246,10 @@ struct bpf_object *bpf_object__next(struct bpf_object *prev); (pos) = (tmp), (tmp) = bpf_object__next(tmp)) typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog); LIBBPF_API int @@ -277,9 +281,10 @@ bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *prog) typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv, bpf_program_clear_priv_t clear_priv); - +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); @@ -420,6 +425,29 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, const char *func_name, const struct bpf_kprobe_opts *opts); +struct bpf_kprobe_multi_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* array of function symbols to attach */ + const char **syms; + /* array of function addresses to attach */ + const unsigned long *addrs; + /* array of user-provided values fetchable through bpf_get_attach_cookie */ + const __u64 *cookies; + /* number of elements in syms/addrs/cookies arrays */ + size_t cnt; + /* create return kprobes */ + bool retprobe; + size_t :0; +}; + +#define bpf_kprobe_multi_opts__last_field retprobe + +LIBBPF_API struct bpf_link * +bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, + const char *pattern, + const struct bpf_kprobe_multi_opts *opts); + struct bpf_uprobe_opts { /* size of this struct, for forward/backward compatiblity */ size_t sz; @@ -591,26 +619,39 @@ LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n); /* * Adjust type of BPF program. Default is kprobe. */ +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_lsm(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_sk_lookup(struct bpf_program *prog); -LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); +LIBBPF_API enum bpf_prog_type bpf_program__type(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); LIBBPF_API enum bpf_attach_type -bpf_program__get_expected_attach_type(const struct bpf_program *prog); +bpf_program__expected_attach_type(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type); @@ -631,18 +672,31 @@ LIBBPF_API int bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, const char *attach_func_name); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_lsm(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_sk_lookup(const struct bpf_program *prog); /* @@ -706,7 +760,8 @@ bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map); LIBBPF_API int bpf_map__fd(const struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); /* get map definition */ -LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use appropriate getters or setters instead") +const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); /* get map name */ LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); /* get/set map type */ @@ -715,6 +770,7 @@ LIBBPF_API int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type); /* get/set map size (max_entries) */ LIBBPF_API __u32 bpf_map__max_entries(const struct bpf_map *map); LIBBPF_API int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_map__set_max_entries() instead") LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); /* get/set map flags */ LIBBPF_API __u32 bpf_map__map_flags(const struct bpf_map *map); @@ -739,8 +795,10 @@ LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map); LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); @@ -757,7 +815,6 @@ LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); */ LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); -LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); LIBBPF_API const char *bpf_map__pin_path(const struct bpf_map *map); LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map); LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); @@ -832,13 +889,42 @@ struct bpf_xdp_set_link_opts { }; #define bpf_xdp_set_link_opts__last_field old_fd +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead") LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead") LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, const struct bpf_xdp_set_link_opts *opts); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query_id() instead") LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query() instead") LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags); +struct bpf_xdp_attach_opts { + size_t sz; + int old_prog_fd; + size_t :0; +}; +#define bpf_xdp_attach_opts__last_field old_prog_fd + +struct bpf_xdp_query_opts { + size_t sz; + __u32 prog_id; /* output */ + __u32 drv_prog_id; /* output */ + __u32 hw_prog_id; /* output */ + __u32 skb_prog_id; /* output */ + __u8 attach_mode; /* output */ + size_t :0; +}; +#define bpf_xdp_query_opts__last_field attach_mode + +LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, + const struct bpf_xdp_attach_opts *opts); +LIBBPF_API int bpf_xdp_detach(int ifindex, __u32 flags, + const struct bpf_xdp_attach_opts *opts); +LIBBPF_API int bpf_xdp_query(int ifindex, int flags, struct bpf_xdp_query_opts *opts); +LIBBPF_API int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id); + /* TC related API */ enum bpf_tc_attach_point { BPF_TC_INGRESS = 1 << 0, @@ -1226,6 +1312,35 @@ LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s); LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s); LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s); +struct bpf_var_skeleton { + const char *name; + struct bpf_map **map; + void **addr; +}; + +struct bpf_object_subskeleton { + size_t sz; /* size of this struct, for forward/backward compatibility */ + + const struct bpf_object *obj; + + int map_cnt; + int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */ + struct bpf_map_skeleton *maps; + + int prog_cnt; + int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */ + struct bpf_prog_skeleton *progs; + + int var_cnt; + int var_skel_sz; /* sizeof(struct bpf_var_skeleton) */ + struct bpf_var_skeleton *vars; +}; + +LIBBPF_API int +bpf_object__open_subskeleton(struct bpf_object_subskeleton *s); +LIBBPF_API void +bpf_object__destroy_subskeleton(struct bpf_object_subskeleton *s); + struct gen_loader_opts { size_t sz; /* size of this struct, for forward/backward compatiblity */ const char *data; @@ -1265,6 +1380,115 @@ LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker); LIBBPF_API void bpf_linker__free(struct bpf_linker *linker); +/* + * Custom handling of BPF program's SEC() definitions + */ + +struct bpf_prog_load_opts; /* defined in bpf.h */ + +/* Called during bpf_object__open() for each recognized BPF program. Callback + * can use various bpf_program__set_*() setters to adjust whatever properties + * are necessary. + */ +typedef int (*libbpf_prog_setup_fn_t)(struct bpf_program *prog, long cookie); + +/* Called right before libbpf performs bpf_prog_load() to load BPF program + * into the kernel. Callback can adjust opts as necessary. + */ +typedef int (*libbpf_prog_prepare_load_fn_t)(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie); + +/* Called during skeleton attach or through bpf_program__attach(). If + * auto-attach is not supported, callback should return 0 and set link to + * NULL (it's not considered an error during skeleton attach, but it will be + * an error for bpf_program__attach() calls). On error, error should be + * returned directly and link set to NULL. On success, return 0 and set link + * to a valid struct bpf_link. + */ +typedef int (*libbpf_prog_attach_fn_t)(const struct bpf_program *prog, long cookie, + struct bpf_link **link); + +struct libbpf_prog_handler_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* User-provided value that is passed to prog_setup_fn, + * prog_prepare_load_fn, and prog_attach_fn callbacks. Allows user to + * register one set of callbacks for multiple SEC() definitions and + * still be able to distinguish them, if necessary. For example, + * libbpf itself is using this to pass necessary flags (e.g., + * sleepable flag) to a common internal SEC() handler. + */ + long cookie; + /* BPF program initialization callback (see libbpf_prog_setup_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_setup_fn_t prog_setup_fn; + /* BPF program loading callback (see libbpf_prog_prepare_load_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_prepare_load_fn_t prog_prepare_load_fn; + /* BPF program attach callback (see libbpf_prog_attach_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_attach_fn_t prog_attach_fn; +}; +#define libbpf_prog_handler_opts__last_field prog_attach_fn + +/** + * @brief **libbpf_register_prog_handler()** registers a custom BPF program + * SEC() handler. + * @param sec section prefix for which custom handler is registered + * @param prog_type BPF program type associated with specified section + * @param exp_attach_type Expected BPF attach type associated with specified section + * @param opts optional cookie, callbacks, and other extra options + * @return Non-negative handler ID is returned on success. This handler ID has + * to be passed to *libbpf_unregister_prog_handler()* to unregister such + * custom handler. Negative error code is returned on error. + * + * *sec* defines which SEC() definitions are handled by this custom handler + * registration. *sec* can have few different forms: + * - if *sec* is just a plain string (e.g., "abc"), it will match only + * SEC("abc"). If BPF program specifies SEC("abc/whatever") it will result + * in an error; + * - if *sec* is of the form "abc/", proper SEC() form is + * SEC("abc/something"), where acceptable "something" should be checked by + * *prog_init_fn* callback, if there are additional restrictions; + * - if *sec* is of the form "abc+", it will successfully match both + * SEC("abc") and SEC("abc/whatever") forms; + * - if *sec* is NULL, custom handler is registered for any BPF program that + * doesn't match any of the registered (custom or libbpf's own) SEC() + * handlers. There could be only one such generic custom handler registered + * at any given time. + * + * All custom handlers (except the one with *sec* == NULL) are processed + * before libbpf's own SEC() handlers. It is allowed to "override" libbpf's + * SEC() handlers by registering custom ones for the same section prefix + * (i.e., it's possible to have custom SEC("perf_event/LLC-load-misses") + * handler). + * + * Note, like much of global libbpf APIs (e.g., libbpf_set_print(), + * libbpf_set_strict_mode(), etc)) these APIs are not thread-safe. User needs + * to ensure synchronization if there is a risk of running this API from + * multiple threads simultaneously. + */ +LIBBPF_API int libbpf_register_prog_handler(const char *sec, + enum bpf_prog_type prog_type, + enum bpf_attach_type exp_attach_type, + const struct libbpf_prog_handler_opts *opts); +/** + * @brief *libbpf_unregister_prog_handler()* unregisters previously registered + * custom BPF program SEC() handler. + * @param handler_id handler ID returned by *libbpf_register_prog_handler()* + * after successful registration + * @return 0 on success, negative error code if handler isn't found + * + * Note, like much of global libbpf APIs (e.g., libbpf_set_print(), + * libbpf_set_strict_mode(), etc)) these APIs are not thread-safe. User needs + * to ensure synchronization if there is a risk of running this API from + * multiple threads simultaneously. + */ +LIBBPF_API int libbpf_unregister_prog_handler(int handler_id); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 529783967793..dd35ee58bfaa 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -247,6 +247,7 @@ LIBBPF_0.0.8 { bpf_link_create; bpf_link_update; bpf_map__set_initial_value; + bpf_prog_attach_opts; bpf_program__attach_cgroup; bpf_program__attach_lsm; bpf_program__is_lsm; @@ -423,12 +424,27 @@ LIBBPF_0.6.0 { LIBBPF_0.7.0 { global: bpf_btf_load; + bpf_program__expected_attach_type; bpf_program__log_buf; bpf_program__log_level; bpf_program__set_log_buf; bpf_program__set_log_level; + bpf_program__type; + bpf_xdp_attach; + bpf_xdp_detach; + bpf_xdp_query; + bpf_xdp_query_id; libbpf_probe_bpf_helper; libbpf_probe_bpf_map_type; libbpf_probe_bpf_prog_type; libbpf_set_memlock_rlim_max; -}; +} LIBBPF_0.6.0; + +LIBBPF_0.8.0 { + global: + bpf_object__destroy_subskeleton; + bpf_object__open_subskeleton; + libbpf_register_prog_handler; + libbpf_unregister_prog_handler; + bpf_program__attach_kprobe_multi_opts; +} LIBBPF_0.7.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 1565679eb432..b6247dc7f8eb 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -92,6 +92,9 @@ # define offsetofend(TYPE, FIELD) \ (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) #endif +#ifndef __alias +#define __alias(symbol) __attribute__((alias(#symbol))) +#endif /* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is * a string literal known at compilation time or char * pointer known only at @@ -446,6 +449,11 @@ __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name, extern enum libbpf_strict_mode libbpf_mode; +typedef int (*kallsyms_cb_t)(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx); + +int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *arg); + /* handle direct returned errors */ static inline int libbpf_err(int ret) { @@ -526,4 +534,13 @@ static inline int ensure_good_fd(int fd) return fd; } +/* The following two functions are exposed to bpftool */ +int bpf_core_add_cands(struct bpf_core_cand *local_cand, + size_t local_essent_len, + const struct btf *targ_btf, + const char *targ_btf_name, + int targ_start_id, + struct bpf_core_cand_list *cands); +void bpf_core_free_cands(struct bpf_core_cand_list *cands); + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index 79131f761a27..d7bcbd01f66f 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -54,6 +54,10 @@ enum libbpf_strict_mode { * * Note, in this mode the program pin path will be based on the * function name instead of section name. + * + * Additionally, routines in the .text section are always considered + * sub-programs. Legacy behavior allows for a single routine in .text + * to be a program. */ LIBBPF_STRICT_SEC_NAME = 0x04, /* @@ -73,6 +77,11 @@ enum libbpf_strict_mode { * operation. */ LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10, + /* + * Error out on any SEC("maps") map definition, which are deprecated + * in favor of BTF-defined map definitions in SEC(".maps"). + */ + LIBBPF_STRICT_MAP_DEFINITIONS = 0x20, __LIBBPF_STRICT_LAST, }; @@ -81,6 +90,23 @@ LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); #define DECLARE_LIBBPF_OPTS LIBBPF_OPTS +/* "Discouraged" APIs which don't follow consistent libbpf naming patterns. + * They are normally a trivial aliases or wrappers for proper APIs and are + * left to minimize unnecessary disruption for users of libbpf. But they + * shouldn't be used going forward. + */ + +struct bpf_program; +struct bpf_map; +struct btf; +struct btf_ext; + +LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); +LIBBPF_API enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog); +LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); +LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); +LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index 0fefefc3500b..61f2039404b6 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 0 -#define LIBBPF_MINOR_VERSION 7 +#define LIBBPF_MINOR_VERSION 8 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 39f25e09b51e..cbc8967d5402 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -87,29 +87,75 @@ enum { NL_DONE, }; +static int netlink_recvmsg(int sock, struct msghdr *mhdr, int flags) +{ + int len; + + do { + len = recvmsg(sock, mhdr, flags); + } while (len < 0 && (errno == EINTR || errno == EAGAIN)); + + if (len < 0) + return -errno; + return len; +} + +static int alloc_iov(struct iovec *iov, int len) +{ + void *nbuf; + + nbuf = realloc(iov->iov_base, len); + if (!nbuf) + return -ENOMEM; + + iov->iov_base = nbuf; + iov->iov_len = len; + return 0; +} + static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq, __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn, void *cookie) { + struct iovec iov = {}; + struct msghdr mhdr = { + .msg_iov = &iov, + .msg_iovlen = 1, + }; bool multipart = true; struct nlmsgerr *err; struct nlmsghdr *nh; - char buf[4096]; int len, ret; + ret = alloc_iov(&iov, 4096); + if (ret) + goto done; + while (multipart) { start: multipart = false; - len = recv(sock, buf, sizeof(buf), 0); + len = netlink_recvmsg(sock, &mhdr, MSG_PEEK | MSG_TRUNC); if (len < 0) { - ret = -errno; + ret = len; + goto done; + } + + if (len > iov.iov_len) { + ret = alloc_iov(&iov, len); + if (ret) + goto done; + } + + len = netlink_recvmsg(sock, &mhdr, 0); + if (len < 0) { + ret = len; goto done; } if (len == 0) break; - for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); + for (nh = (struct nlmsghdr *)iov.iov_base; NLMSG_OK(nh, len); nh = NLMSG_NEXT(nh, len)) { if (nh->nlmsg_pid != nl_pid) { ret = -LIBBPF_ERRNO__WRNGPID; @@ -130,7 +176,8 @@ start: libbpf_nla_dump_errormsg(nh); goto done; case NLMSG_DONE: - return 0; + ret = 0; + goto done; default: break; } @@ -142,15 +189,17 @@ start: case NL_NEXT: goto start; case NL_DONE: - return 0; + ret = 0; + goto done; default: - return ret; + goto done; } } } } ret = 0; done: + free(iov.iov_base); return ret; } @@ -217,6 +266,28 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); } +int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts) +{ + int old_prog_fd, err; + + if (!OPTS_VALID(opts, bpf_xdp_attach_opts)) + return libbpf_err(-EINVAL); + + old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + if (old_prog_fd) + flags |= XDP_FLAGS_REPLACE; + else + old_prog_fd = -1; + + err = __bpf_set_link_xdp_fd_replace(ifindex, prog_fd, old_prog_fd, flags); + return libbpf_err(err); +} + +int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *opts) +{ + return bpf_xdp_attach(ifindex, -1, flags, opts); +} + int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, const struct bpf_xdp_set_link_opts *opts) { @@ -303,69 +374,98 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } -int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, - size_t info_size, __u32 flags) +int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) { - struct xdp_id_md xdp_id = {}; - __u32 mask; - int ret; struct libbpf_nla_req req = { .nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), .nh.nlmsg_type = RTM_GETLINK, .nh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, .ifinfo.ifi_family = AF_PACKET, }; + struct xdp_id_md xdp_id = {}; + int err; - if (flags & ~XDP_FLAGS_MASK || !info_size) + if (!OPTS_VALID(opts, bpf_xdp_query_opts)) + return libbpf_err(-EINVAL); + + if (xdp_flags & ~XDP_FLAGS_MASK) return libbpf_err(-EINVAL); /* Check whether the single {HW,DRV,SKB} mode is set */ - flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE); - mask = flags - 1; - if (flags && flags & mask) + xdp_flags &= XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE; + if (xdp_flags & (xdp_flags - 1)) return libbpf_err(-EINVAL); xdp_id.ifindex = ifindex; - xdp_id.flags = flags; + xdp_id.flags = xdp_flags; - ret = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, + err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, get_xdp_info, &xdp_id); - if (!ret) { - size_t sz = min(info_size, sizeof(xdp_id.info)); + if (err) + return libbpf_err(err); - memcpy(info, &xdp_id.info, sz); - memset((void *) info + sz, 0, info_size - sz); - } + OPTS_SET(opts, prog_id, xdp_id.info.prog_id); + OPTS_SET(opts, drv_prog_id, xdp_id.info.drv_prog_id); + OPTS_SET(opts, hw_prog_id, xdp_id.info.hw_prog_id); + OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id); + OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode); - return libbpf_err(ret); + return 0; } -static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags) +int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, + size_t info_size, __u32 flags) { - flags &= XDP_FLAGS_MODES; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + size_t sz; + int err; - if (info->attach_mode != XDP_ATTACHED_MULTI && !flags) - return info->prog_id; - if (flags & XDP_FLAGS_DRV_MODE) - return info->drv_prog_id; - if (flags & XDP_FLAGS_HW_MODE) - return info->hw_prog_id; - if (flags & XDP_FLAGS_SKB_MODE) - return info->skb_prog_id; + if (!info_size) + return libbpf_err(-EINVAL); + + err = bpf_xdp_query(ifindex, flags, &opts); + if (err) + return libbpf_err(err); + + /* struct xdp_link_info field layout matches struct bpf_xdp_query_opts + * layout after sz field + */ + sz = min(info_size, offsetofend(struct xdp_link_info, attach_mode)); + memcpy(info, &opts.prog_id, sz); + memset((void *)info + sz, 0, info_size - sz); return 0; } -int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id) { - struct xdp_link_info info; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); int ret; - ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags); - if (!ret) - *prog_id = get_xdp_id(&info, flags); + ret = bpf_xdp_query(ifindex, flags, &opts); + if (ret) + return libbpf_err(ret); - return libbpf_err(ret); + flags &= XDP_FLAGS_MODES; + + if (opts.attach_mode != XDP_ATTACHED_MULTI && !flags) + *prog_id = opts.prog_id; + else if (flags & XDP_FLAGS_DRV_MODE) + *prog_id = opts.drv_prog_id; + else if (flags & XDP_FLAGS_HW_MODE) + *prog_id = opts.hw_prog_id; + else if (flags & XDP_FLAGS_SKB_MODE) + *prog_id = opts.skb_prog_id; + else + *prog_id = 0; + + return 0; +} + + +int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +{ + return bpf_xdp_query_id(ifindex, flags, prog_id); } typedef int (*qdisc_config_t)(struct libbpf_nla_req *req); diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index 910865e29edc..f946f23eab20 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -775,31 +775,6 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, return 0; } -struct bpf_core_relo_res -{ - /* expected value in the instruction, unless validate == false */ - __u32 orig_val; - /* new value that needs to be patched up to */ - __u32 new_val; - /* relocation unsuccessful, poison instruction, but don't fail load */ - bool poison; - /* some relocations can't be validated against orig_val */ - bool validate; - /* for field byte offset relocations or the forms: - * *(T *)(rX + <off>) = rY - * rX = *(T *)(rY + <off>), - * we remember original and resolved field size to adjust direct - * memory loads of pointers and integers; this is necessary for 32-bit - * host kernel architectures, but also allows to automatically - * relocate fields that were resized from, e.g., u32 to u64, etc. - */ - bool fail_memsz_adjust; - __u32 orig_sz; - __u32 orig_type_id; - __u32 new_sz; - __u32 new_type_id; -}; - /* Calculate original and target relocation values, given local and target * specs and relocation kind. These values are calculated for each candidate. * If there are multiple candidates, resulting values should all be consistent @@ -951,9 +926,9 @@ static int insn_bytes_to_bpf_size(__u32 sz) * 5. *(T *)(rX + <off>) = rY, where T is one of {u8, u16, u32, u64}; * 6. *(T *)(rX + <off>) = <imm>, where T is one of {u8, u16, u32, u64}. */ -static int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn, - int insn_idx, const struct bpf_core_relo *relo, - int relo_idx, const struct bpf_core_relo_res *res) +int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn, + int insn_idx, const struct bpf_core_relo *relo, + int relo_idx, const struct bpf_core_relo_res *res) { __u32 orig_val, new_val; __u8 class; @@ -1128,7 +1103,7 @@ static void bpf_core_dump_spec(const char *prog_name, int level, const struct bp } /* - * CO-RE relocate single instruction. + * Calculate CO-RE relocation target result. * * The outline and important points of the algorithm: * 1. For given local type, find corresponding candidate target types. @@ -1177,18 +1152,18 @@ static void bpf_core_dump_spec(const char *prog_name, int level, const struct bp * between multiple relocations for the same type ID and is updated as some * of the candidates are pruned due to structural incompatibility. */ -int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, - int insn_idx, - const struct bpf_core_relo *relo, - int relo_idx, - const struct btf *local_btf, - struct bpf_core_cand_list *cands, - struct bpf_core_spec *specs_scratch) +int bpf_core_calc_relo_insn(const char *prog_name, + const struct bpf_core_relo *relo, + int relo_idx, + const struct btf *local_btf, + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch, + struct bpf_core_relo_res *targ_res) { struct bpf_core_spec *local_spec = &specs_scratch[0]; struct bpf_core_spec *cand_spec = &specs_scratch[1]; struct bpf_core_spec *targ_spec = &specs_scratch[2]; - struct bpf_core_relo_res cand_res, targ_res; + struct bpf_core_relo_res cand_res; const struct btf_type *local_type; const char *local_name; __u32 local_id; @@ -1223,12 +1198,12 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */ if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) { /* bpf_insn's imm value could get out of sync during linking */ - memset(&targ_res, 0, sizeof(targ_res)); - targ_res.validate = false; - targ_res.poison = false; - targ_res.orig_val = local_spec->root_type_id; - targ_res.new_val = local_spec->root_type_id; - goto patch_insn; + memset(targ_res, 0, sizeof(*targ_res)); + targ_res->validate = false; + targ_res->poison = false; + targ_res->orig_val = local_spec->root_type_id; + targ_res->new_val = local_spec->root_type_id; + return 0; } /* libbpf doesn't support candidate search for anonymous types */ @@ -1262,7 +1237,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, return err; if (j == 0) { - targ_res = cand_res; + *targ_res = cand_res; *targ_spec = *cand_spec; } else if (cand_spec->bit_offset != targ_spec->bit_offset) { /* if there are many field relo candidates, they @@ -1272,7 +1247,8 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, prog_name, relo_idx, cand_spec->bit_offset, targ_spec->bit_offset); return -EINVAL; - } else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) { + } else if (cand_res.poison != targ_res->poison || + cand_res.new_val != targ_res->new_val) { /* all candidates should result in the same relocation * decision and value, otherwise it's dangerous to * proceed due to ambiguity @@ -1280,7 +1256,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %u != %s %u\n", prog_name, relo_idx, cand_res.poison ? "failure" : "success", cand_res.new_val, - targ_res.poison ? "failure" : "success", targ_res.new_val); + targ_res->poison ? "failure" : "success", targ_res->new_val); return -EINVAL; } @@ -1314,19 +1290,10 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, prog_name, relo_idx); /* calculate single target relo result explicitly */ - err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, &targ_res); + err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, targ_res); if (err) return err; } -patch_insn: - /* bpf_core_patch_insn() should know how to handle missing targ_spec */ - err = bpf_core_patch_insn(prog_name, insn, insn_idx, relo, relo_idx, &targ_res); - if (err) { - pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n", - prog_name, relo_idx, relo->insn_off / 8, err); - return -EINVAL; - } - return 0; } diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h index 17799819ad7c..a28bf3711ce2 100644 --- a/tools/lib/bpf/relo_core.h +++ b/tools/lib/bpf/relo_core.h @@ -44,14 +44,44 @@ struct bpf_core_spec { __u32 bit_offset; }; -int bpf_core_apply_relo_insn(const char *prog_name, - struct bpf_insn *insn, int insn_idx, - const struct bpf_core_relo *relo, int relo_idx, - const struct btf *local_btf, - struct bpf_core_cand_list *cands, - struct bpf_core_spec *specs_scratch); +struct bpf_core_relo_res { + /* expected value in the instruction, unless validate == false */ + __u32 orig_val; + /* new value that needs to be patched up to */ + __u32 new_val; + /* relocation unsuccessful, poison instruction, but don't fail load */ + bool poison; + /* some relocations can't be validated against orig_val */ + bool validate; + /* for field byte offset relocations or the forms: + * *(T *)(rX + <off>) = rY + * rX = *(T *)(rY + <off>), + * we remember original and resolved field size to adjust direct + * memory loads of pointers and integers; this is necessary for 32-bit + * host kernel architectures, but also allows to automatically + * relocate fields that were resized from, e.g., u32 to u64, etc. + */ + bool fail_memsz_adjust; + __u32 orig_sz; + __u32 orig_type_id; + __u32 new_sz; + __u32 new_type_id; +}; + int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id); size_t bpf_core_essential_name_len(const char *name); + +int bpf_core_calc_relo_insn(const char *prog_name, + const struct bpf_core_relo *relo, int relo_idx, + const struct btf *local_btf, + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch, + struct bpf_core_relo_res *targ_res); + +int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn, + int insn_idx, const struct bpf_core_relo *relo, + int relo_idx, const struct bpf_core_relo_res *res); + #endif diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 0b84d8e6b72a..bd6f4505e7b1 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -3,9 +3,19 @@ #ifndef __SKEL_INTERNAL_H #define __SKEL_INTERNAL_H +#ifdef __KERNEL__ +#include <linux/fdtable.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/slab.h> +#include <linux/bpf.h> +#else #include <unistd.h> #include <sys/syscall.h> #include <sys/mman.h> +#include <stdlib.h> +#include "bpf.h" +#endif #ifndef __NR_bpf # if defined(__mips__) && defined(_ABIO32) @@ -25,24 +35,23 @@ * requested during loader program generation. */ struct bpf_map_desc { - union { - /* input for the loader prog */ - struct { - __aligned_u64 initial_value; - __u32 max_entries; - }; - /* output of the loader prog */ - struct { - int map_fd; - }; - }; + /* output of the loader prog */ + int map_fd; + /* input for the loader prog */ + __u32 max_entries; + __aligned_u64 initial_value; }; struct bpf_prog_desc { int prog_fd; }; +enum { + BPF_SKEL_KERNEL = (1ULL << 0), +}; + struct bpf_loader_ctx { - size_t sz; + __u32 sz; + __u32 flags; __u32 log_level; __u32 log_size; __u64 log_buf; @@ -57,12 +66,144 @@ struct bpf_load_and_run_opts { const char *errstr; }; +long bpf_sys_bpf(__u32 cmd, void *attr, __u32 attr_size); + static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, unsigned int size) { +#ifdef __KERNEL__ + return bpf_sys_bpf(cmd, attr, size); +#else return syscall(__NR_bpf, cmd, attr, size); +#endif +} + +#ifdef __KERNEL__ +static inline int close(int fd) +{ + return close_fd(fd); +} + +static inline void *skel_alloc(size_t size) +{ + struct bpf_loader_ctx *ctx = kzalloc(size, GFP_KERNEL); + + if (!ctx) + return NULL; + ctx->flags |= BPF_SKEL_KERNEL; + return ctx; +} + +static inline void skel_free(const void *p) +{ + kfree(p); +} + +/* skel->bss/rodata maps are populated the following way: + * + * For kernel use: + * skel_prep_map_data() allocates kernel memory that kernel module can directly access. + * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value. + * The loader program will perform probe_read_kernel() from maps.rodata.initial_value. + * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and + * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree + * is not nessary. + * + * For user space: + * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly. + * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value. + * The loader program will perform copy_from_user() from maps.rodata.initial_value. + * skel_finalize_map_data() remaps bpf array map value from the kernel memory into + * skel->rodata address. + * + * The "bpftool gen skeleton -L" command generates lskel.h that is suitable for + * both kernel and user space. The generated loader program does + * either bpf_probe_read_kernel() or bpf_copy_from_user() from initial_value + * depending on bpf_loader_ctx->flags. + */ +static inline void skel_free_map_data(void *p, __u64 addr, size_t sz) +{ + if (addr != ~0ULL) + kvfree(p); + /* When addr == ~0ULL the 'p' points to + * ((struct bpf_array *)map)->value. See skel_finalize_map_data. + */ +} + +static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz) +{ + void *addr; + + addr = kvmalloc(val_sz, GFP_KERNEL); + if (!addr) + return NULL; + memcpy(addr, val, val_sz); + return addr; +} + +static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd) +{ + struct bpf_map *map; + void *addr = NULL; + + kvfree((void *) (long) *init_val); + *init_val = ~0ULL; + + /* At this point bpf_load_and_run() finished without error and + * 'fd' is a valid bpf map FD. All sanity checks below should succeed. + */ + map = bpf_map_get(fd); + if (IS_ERR(map)) + return NULL; + if (map->map_type != BPF_MAP_TYPE_ARRAY) + goto out; + addr = ((struct bpf_array *)map)->value; + /* the addr stays valid, since FD is not closed */ +out: + bpf_map_put(map); + return addr; +} + +#else + +static inline void *skel_alloc(size_t size) +{ + return calloc(1, size); +} + +static inline void skel_free(void *p) +{ + free(p); +} + +static inline void skel_free_map_data(void *p, __u64 addr, size_t sz) +{ + munmap(p, sz); +} + +static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz) +{ + void *addr; + + addr = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (addr == (void *) -1) + return NULL; + memcpy(addr, val, val_sz); + return addr; } +static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd) +{ + void *addr; + + addr = mmap((void *) (long) *init_val, mmap_sz, flags, MAP_SHARED | MAP_FIXED, fd, 0); + if (addr == (void *) -1) + return NULL; + return addr; +} +#endif + static inline int skel_closenz(int fd) { if (fd > 0) @@ -70,22 +211,94 @@ static inline int skel_closenz(int fd) return -EINVAL; } +#ifndef offsetofend +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) +#endif + +static inline int skel_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries) +{ + const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + + attr.map_type = map_type; + strncpy(attr.map_name, map_name, sizeof(attr.map_name)); + attr.key_size = key_size; + attr.value_size = value_size; + attr.max_entries = max_entries; + + return skel_sys_bpf(BPF_MAP_CREATE, &attr, attr_sz); +} + +static inline int skel_map_update_elem(int fd, const void *key, + const void *value, __u64 flags) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = (long) key; + attr.value = (long) value; + attr.flags = flags; + + return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz); +} + +static inline int skel_raw_tracepoint_open(const char *name, int prog_fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint.prog_fd); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.raw_tracepoint.name = (long) name; + attr.raw_tracepoint.prog_fd = prog_fd; + + return skel_sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz); +} + +static inline int skel_link_create(int prog_fd, int target_fd, + enum bpf_attach_type attach_type) +{ + const size_t attr_sz = offsetofend(union bpf_attr, link_create.iter_info_len); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.link_create.prog_fd = prog_fd; + attr.link_create.target_fd = target_fd; + attr.link_create.attach_type = attach_type; + + return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz); +} + +#ifdef __KERNEL__ +#define set_err +#else +#define set_err err = -errno +#endif + static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) { int map_fd = -1, prog_fd = -1, key = 0, err; union bpf_attr attr; - map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1, NULL); + err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1); if (map_fd < 0) { opts->errstr = "failed to create loader map"; - err = -errno; + set_err; goto out; } - err = bpf_map_update_elem(map_fd, &key, opts->data, 0); + err = skel_map_update_elem(map_fd, &key, opts->data, 0); if (err < 0) { opts->errstr = "failed to update loader map"; - err = -errno; + set_err; goto out; } @@ -100,10 +313,10 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) attr.log_size = opts->ctx->log_size; attr.log_buf = opts->ctx->log_buf; attr.prog_flags = BPF_F_SLEEPABLE; - prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); + err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); if (prog_fd < 0) { opts->errstr = "failed to load loader prog"; - err = -errno; + set_err; goto out; } @@ -115,10 +328,12 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) if (err < 0 || (int)attr.test.retval < 0) { opts->errstr = "failed to execute loader prog"; if (err < 0) { - err = -errno; + set_err; } else { err = (int)attr.test.retval; +#ifndef __KERNEL__ errno = -err; +#endif } goto out; } diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index edafe56664f3..af136f73b09d 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -481,8 +481,8 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) BPF_EMIT_CALL(BPF_FUNC_redirect_map), BPF_EXIT_INSN(), }; - size_t insns_cnt[] = {sizeof(prog) / sizeof(struct bpf_insn), - sizeof(prog_redirect_flags) / sizeof(struct bpf_insn), + size_t insns_cnt[] = {ARRAY_SIZE(prog), + ARRAY_SIZE(prog_redirect_flags), }; struct bpf_insn *progs[] = {prog, prog_redirect_flags}; enum xsk_prog option = get_xsk_prog(); @@ -1193,12 +1193,23 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, int xsk_umem__delete(struct xsk_umem *umem) { + struct xdp_mmap_offsets off; + int err; + if (!umem) return 0; if (umem->refcount) return -EBUSY; + err = xsk_get_mmap_offsets(umem->fd, &off); + if (!err && umem->fill_save && umem->comp_save) { + munmap(umem->fill_save->ring - off.fr.desc, + off.fr.desc + umem->config.fill_size * sizeof(__u64)); + munmap(umem->comp_save->ring - off.cr.desc, + off.cr.desc + umem->config.comp_size * sizeof(__u64)); + } + close(umem->fd); free(umem); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index 8ac0a3a457ef..0bc25a56cfef 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -13,7 +13,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz) { struct bpf_object *obj; - obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL); + obj = bpf_object__open_mem(obj_buf, obj_buf_sz, NULL); if (libbpf_get_error(obj)) return TEST_FAIL; bpf_object__close(obj); diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 16ec605a9fe4..ec6d9e7b446d 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -54,6 +54,7 @@ static bool libbpf_initialized; struct bpf_object * bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) { + LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = name); struct bpf_object *obj; if (!libbpf_initialized) { @@ -61,7 +62,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) libbpf_initialized = true; } - obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name); + obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts); if (IS_ERR_OR_NULL(obj)) { pr_debug("bpf: failed to load buffer\n"); return ERR_PTR(-EINVAL); @@ -72,6 +73,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) struct bpf_object *bpf__prepare_load(const char *filename, bool source) { + LIBBPF_OPTS(bpf_object_open_opts, opts, .object_name = filename); struct bpf_object *obj; if (!libbpf_initialized) { @@ -94,7 +96,7 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source) return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE); } else pr_debug("bpf: successful builtin compilation\n"); - obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename); + obj = bpf_object__open_mem(obj_buf, obj_buf_sz, &opts); if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj) llvm__dump_obj(filename, obj_buf, obj_buf_sz); @@ -654,11 +656,11 @@ int bpf__probe(struct bpf_object *obj) } if (priv->is_tp) { - bpf_program__set_tracepoint(prog); + bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT); continue; } - bpf_program__set_kprobe(prog); + bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE); pev = &priv->pev; err = convert_perf_probe_events(pev, 1); @@ -1005,24 +1007,22 @@ __bpf_map__config_value(struct bpf_map *map, { struct bpf_map_op *op; const char *map_name = bpf_map__name(map); - const struct bpf_map_def *def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("Unable to get map definition from '%s'\n", - map_name); + if (!map) { + pr_debug("Map '%s' is invalid\n", map_name); return -BPF_LOADER_ERRNO__INTERNAL; } - if (def->type != BPF_MAP_TYPE_ARRAY) { + if (bpf_map__type(map) != BPF_MAP_TYPE_ARRAY) { pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; } - if (def->key_size < sizeof(unsigned int)) { + if (bpf_map__key_size(map) < sizeof(unsigned int)) { pr_debug("Map %s has incorrect key size\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE; } - switch (def->value_size) { + switch (bpf_map__value_size(map)) { case 1: case 2: case 4: @@ -1064,7 +1064,6 @@ __bpf_map__config_event(struct bpf_map *map, struct parse_events_term *term, struct evlist *evlist) { - const struct bpf_map_def *def; struct bpf_map_op *op; const char *map_name = bpf_map__name(map); struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str); @@ -1075,18 +1074,16 @@ __bpf_map__config_event(struct bpf_map *map, return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT; } - def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("Unable to get map definition from '%s'\n", - map_name); - return PTR_ERR(def); + if (!map) { + pr_debug("Map '%s' is invalid\n", map_name); + return PTR_ERR(map); } /* * No need to check key_size and value_size: * kernel has already checked them. */ - if (def->type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; @@ -1135,7 +1132,6 @@ config_map_indices_range_check(struct parse_events_term *term, const char *map_name) { struct parse_events_array *array = &term->array; - const struct bpf_map_def *def; unsigned int i; if (!array->nr_ranges) @@ -1146,10 +1142,8 @@ config_map_indices_range_check(struct parse_events_term *term, return -BPF_LOADER_ERRNO__INTERNAL; } - def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("ERROR: Unable to get map definition from '%s'\n", - map_name); + if (!map) { + pr_debug("Map '%s' is invalid\n", map_name); return -BPF_LOADER_ERRNO__INTERNAL; } @@ -1158,7 +1152,7 @@ config_map_indices_range_check(struct parse_events_term *term, size_t length = array->ranges[i].length; unsigned int idx = start + length - 1; - if (idx >= def->max_entries) { + if (idx >= bpf_map__max_entries(map)) { pr_debug("ERROR: index %d too large\n", idx); return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG; } @@ -1252,21 +1246,21 @@ out: } typedef int (*map_config_func_t)(const char *name, int map_fd, - const struct bpf_map_def *pdef, + const struct bpf_map *map, struct bpf_map_op *op, void *pkey, void *arg); static int foreach_key_array_all(map_config_func_t func, void *arg, const char *name, - int map_fd, const struct bpf_map_def *pdef, + int map_fd, const struct bpf_map *map, struct bpf_map_op *op) { unsigned int i; int err; - for (i = 0; i < pdef->max_entries; i++) { - err = func(name, map_fd, pdef, op, &i, arg); + for (i = 0; i < bpf_map__max_entries(map); i++) { + err = func(name, map_fd, map, op, &i, arg); if (err) { pr_debug("ERROR: failed to insert value to %s[%u]\n", name, i); @@ -1279,7 +1273,7 @@ foreach_key_array_all(map_config_func_t func, static int foreach_key_array_ranges(map_config_func_t func, void *arg, const char *name, int map_fd, - const struct bpf_map_def *pdef, + const struct bpf_map *map, struct bpf_map_op *op) { unsigned int i, j; @@ -1292,7 +1286,7 @@ foreach_key_array_ranges(map_config_func_t func, void *arg, for (j = 0; j < length; j++) { unsigned int idx = start + j; - err = func(name, map_fd, pdef, op, &idx, arg); + err = func(name, map_fd, map, op, &idx, arg); if (err) { pr_debug("ERROR: failed to insert value to %s[%u]\n", name, idx); @@ -1308,9 +1302,8 @@ bpf_map_config_foreach_key(struct bpf_map *map, map_config_func_t func, void *arg) { - int err, map_fd; + int err, map_fd, type; struct bpf_map_op *op; - const struct bpf_map_def *def; const char *name = bpf_map__name(map); struct bpf_map_priv *priv = bpf_map__priv(map); @@ -1323,9 +1316,8 @@ bpf_map_config_foreach_key(struct bpf_map *map, return 0; } - def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("ERROR: failed to get definition from map %s\n", name); + if (!map) { + pr_debug("Map '%s' is invalid\n", name); return -BPF_LOADER_ERRNO__INTERNAL; } map_fd = bpf_map__fd(map); @@ -1334,19 +1326,19 @@ bpf_map_config_foreach_key(struct bpf_map *map, return map_fd; } + type = bpf_map__type(map); list_for_each_entry(op, &priv->ops_list, list) { - switch (def->type) { + switch (type) { case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERF_EVENT_ARRAY: switch (op->key_type) { case BPF_MAP_KEY_ALL: err = foreach_key_array_all(func, arg, name, - map_fd, def, op); + map_fd, map, op); break; case BPF_MAP_KEY_RANGES: err = foreach_key_array_ranges(func, arg, name, - map_fd, def, - op); + map_fd, map, op); break; default: pr_debug("ERROR: keytype for map '%s' invalid\n", @@ -1455,7 +1447,7 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey, static int apply_obj_config_map_for_key(const char *name, int map_fd, - const struct bpf_map_def *pdef, + const struct bpf_map *map, struct bpf_map_op *op, void *pkey, void *arg __maybe_unused) { @@ -1464,7 +1456,7 @@ apply_obj_config_map_for_key(const char *name, int map_fd, switch (op->op_type) { case BPF_MAP_OP_SET_VALUE: err = apply_config_value_for_key(map_fd, pkey, - pdef->value_size, + bpf_map__value_size(map), op->v.value); break; case BPF_MAP_OP_SET_EVSEL: diff --git a/tools/perf/util/bpf_map.c b/tools/perf/util/bpf_map.c index eb853ca67cf4..c863ae0c5cb5 100644 --- a/tools/perf/util/bpf_map.c +++ b/tools/perf/util/bpf_map.c @@ -9,25 +9,25 @@ #include <stdlib.h> #include <unistd.h> -static bool bpf_map_def__is_per_cpu(const struct bpf_map_def *def) +static bool bpf_map__is_per_cpu(enum bpf_map_type type) { - return def->type == BPF_MAP_TYPE_PERCPU_HASH || - def->type == BPF_MAP_TYPE_PERCPU_ARRAY || - def->type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - def->type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE; + return type == BPF_MAP_TYPE_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_ARRAY || + type == BPF_MAP_TYPE_LRU_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE; } -static void *bpf_map_def__alloc_value(const struct bpf_map_def *def) +static void *bpf_map__alloc_value(const struct bpf_map *map) { - if (bpf_map_def__is_per_cpu(def)) - return malloc(round_up(def->value_size, 8) * sysconf(_SC_NPROCESSORS_CONF)); + if (bpf_map__is_per_cpu(bpf_map__type(map))) + return malloc(round_up(bpf_map__value_size(map), 8) * + sysconf(_SC_NPROCESSORS_CONF)); - return malloc(def->value_size); + return malloc(bpf_map__value_size(map)); } int bpf_map__fprintf(struct bpf_map *map, FILE *fp) { - const struct bpf_map_def *def = bpf_map__def(map); void *prev_key = NULL, *key, *value; int fd = bpf_map__fd(map), err; int printed = 0; @@ -35,15 +35,15 @@ int bpf_map__fprintf(struct bpf_map *map, FILE *fp) if (fd < 0) return fd; - if (IS_ERR(def)) - return PTR_ERR(def); + if (!map) + return PTR_ERR(map); err = -ENOMEM; - key = malloc(def->key_size); + key = malloc(bpf_map__key_size(map)); if (key == NULL) goto out; - value = bpf_map_def__alloc_value(def); + value = bpf_map__alloc_value(map); if (value == NULL) goto out_free_key; diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index 79d102304470..a2335e402145 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -89,6 +89,9 @@ ifeq ($(CC_NO_CLANG), 1) EXTRA_WARNINGS += -Wstrict-aliasing=3 else ifneq ($(CROSS_COMPILE),) +# Allow userspace to override CLANG_CROSS_FLAGS to specify their own +# sysroots and flags or to avoid the GCC call in pure Clang builds. +ifeq ($(CLANG_CROSS_FLAGS),) CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc 2>/dev/null)) ifneq ($(GCC_TOOLCHAIN_DIR),) @@ -96,6 +99,7 @@ CLANG_CROSS_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE)) CLANG_CROSS_FLAGS += --sysroot=$(shell $(CROSS_COMPILE)gcc -print-sysroot) CLANG_CROSS_FLAGS += --gcc-toolchain=$(realpath $(GCC_TOOLCHAIN_DIR)/..) endif # GCC_TOOLCHAIN_DIR +endif # CLANG_CROSS_FLAGS CFLAGS += $(CLANG_CROSS_FLAGS) AFLAGS += $(CLANG_CROSS_FLAGS) endif # CROSS_COMPILE diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 1dad8d617da8..595565eb68c0 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +bpftool bpf-helpers* bpf-syscall* test_verifier @@ -30,6 +31,7 @@ test_tcp_check_syncookie_user test_sysctl xdping test_cpp +*.subskel.h *.skel.h *.lskel.h /no_alu32 diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 42ffc24e9e71..3820608faf57 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -21,11 +21,11 @@ endif BPF_GCC ?= $(shell command -v bpf-gcc;) SAN_CFLAGS ?= -CFLAGS += -g -O0 -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS) \ +CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) LDFLAGS += $(SAN_CFLAGS) -LDLIBS += -lcap -lelf -lz -lrt -lpthread +LDLIBS += -lelf -lz -lrt -lpthread # Silence some warnings when compiled with clang ifneq ($(LLVM),) @@ -195,6 +195,7 @@ $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ) CGROUP_HELPERS := $(OUTPUT)/cgroup_helpers.o TESTING_HELPERS := $(OUTPUT)/testing_helpers.o TRACE_HELPERS := $(OUTPUT)/trace_helpers.o +CAP_HELPERS := $(OUTPUT)/cap_helpers.o $(OUTPUT)/test_dev_cgroup: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(OUTPUT)/test_skb_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) @@ -211,7 +212,7 @@ $(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS) $(OUTPUT)/xdping: $(TESTING_HELPERS) $(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS) $(OUTPUT)/test_maps: $(TESTING_HELPERS) -$(OUTPUT)/test_verifier: $(TESTING_HELPERS) +$(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS) BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ @@ -292,7 +293,7 @@ IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG)) -BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ +BPF_CFLAGS = -g -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR) \ -I$(abspath $(OUTPUT)/../usr/include) @@ -326,11 +327,17 @@ endef SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ - linked_vars.skel.h linked_maps.skel.h + linked_vars.skel.h linked_maps.skel.h \ + test_subskeleton.skel.h test_subskeleton_lib.skel.h + +# In the subskeleton case, we want the test_subskeleton_lib.subskel.h file +# but that's created as a side-effect of the skel.h generation. +test_subskeleton.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o test_subskeleton.o +test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c \ - map_ptr_kern.c core_kern.c + map_ptr_kern.c core_kern.c core_kern_overflow.c # Generate both light skeleton and libbpf skeleton for these LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test_subprog.c SKEL_BLACKLIST += $$(LSKELS) @@ -404,6 +411,7 @@ $(TRUNNER_BPF_SKELS): %.skel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT) $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o) $(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o) $(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@ + $(Q)$$(BPFTOOL) gen subskeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$(@:.skel.h=.subskel.h) $(TRUNNER_BPF_LSKELS): %.lskel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT) $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) @@ -421,6 +429,7 @@ $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT) $(Q)diff $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked3.o) $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) $(Q)$$(BPFTOOL) gen skeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$@ + $(Q)$$(BPFTOOL) gen subskeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$(@:.skel.h=.subskel.h) endif # ensure we set up tests.h header generation rule just once @@ -470,6 +479,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $$(call msg,BINARY,,$$@) $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ $(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.o $$@ + $(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/bootstrap/bpftool $(if $2,$2/)bpftool endef @@ -478,7 +488,8 @@ TRUNNER_TESTS_DIR := prog_tests TRUNNER_BPF_PROGS_DIR := progs TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ network_helpers.c testing_helpers.c \ - btf_helpers.c flow_dissector_load.h + btf_helpers.c flow_dissector_load.h \ + cap_helpers.c TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ ima_setup.sh \ $(wildcard progs/btf_dump_test_case_*.c) @@ -555,7 +566,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ - feature \ - $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h no_alu32 bpf_gcc bpf_testmod.ko) + feature bpftool \ + $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h no_alu32 bpf_gcc bpf_testmod.ko) .PHONY: docs docs-clean diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 42ef250c7acc..eb1b7541f39d 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -32,11 +32,19 @@ For more information on about using the script, run: $ tools/testing/selftests/bpf/vmtest.sh -h +In case of linker errors when running selftests, try using static linking: + +.. code-block:: console + + $ LDLIBS=-static vmtest.sh + +.. note:: Some distros may not support static linking. + .. note:: The script uses pahole and clang based on host environment setting. If you want to change pahole and llvm, you can change `PATH` environment variable in the beginning of script. -.. note:: The script currently only supports x86_64. +.. note:: The script currently only supports x86_64 and s390x architectures. Additional information about selftest failures are documented here. @@ -206,6 +214,8 @@ btf_tag test and Clang version The btf_tag selftest requires LLVM support to recognize the btf_decl_tag and btf_type_tag attributes. They are introduced in `Clang 14` [0_, 1_]. +The subtests ``btf_type_tag_user_{mod1, mod2, vmlinux}`` also requires +pahole version ``1.23``. Without them, the btf_tag selftest will be skipped and you will observe: diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index da8593b3494a..c2554f9695ff 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -151,7 +151,7 @@ static struct ringbuf_bench *ringbuf_setup_skeleton(void) /* record data + header take 16 bytes */ skel->rodata->wakeup_data_size = args.sample_rate * 16; - bpf_map__resize(skel->maps.ringbuf, args.ringbuf_sz); + bpf_map__set_max_entries(skel->maps.ringbuf, args.ringbuf_sz); if (ringbuf_bench__load(skel)) { fprintf(stderr, "failed to load skeleton\n"); diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 7f957c55a3ca..0c481de2833d 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -154,7 +154,6 @@ static void *uprobe_producer_without_nop(void *input) static void usetup(bool use_retprobe, bool use_nop) { size_t uprobe_offset; - ssize_t base_addr; struct bpf_link *link; setup_libbpf(); @@ -165,11 +164,10 @@ static void usetup(bool use_retprobe, bool use_nop) exit(1); } - base_addr = get_base_addr(); if (use_nop) - uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop, base_addr); + uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop); else - uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop, base_addr); + uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop); link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe, use_retprobe, diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index df3b292a8ffe..e585e1cefc77 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -13,6 +13,10 @@ #define CREATE_TRACE_POINTS #include "bpf_testmod-events.h" +typedef int (*func_proto_typedef)(long); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef); +typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1); + DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123; noinline void @@ -21,6 +25,41 @@ bpf_testmod_test_mod_kfunc(int i) *(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i; } +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 __user *p; +}; + +struct bpf_testmod_btf_type_tag_3 { + struct bpf_testmod_btf_type_tag_1 __percpu *p; +}; + +noinline int +bpf_testmod_test_btf_type_tag_user_1(struct bpf_testmod_btf_type_tag_1 __user *arg) { + BTF_TYPE_EMIT(func_proto_typedef); + BTF_TYPE_EMIT(func_proto_typedef_nested1); + BTF_TYPE_EMIT(func_proto_typedef_nested2); + return arg->a; +} + +noinline int +bpf_testmod_test_btf_type_tag_user_2(struct bpf_testmod_btf_type_tag_2 *arg) { + return arg->p->a; +} + +noinline int +bpf_testmod_test_btf_type_tag_percpu_1(struct bpf_testmod_btf_type_tag_1 __percpu *arg) { + return arg->a; +} + +noinline int +bpf_testmod_test_btf_type_tag_percpu_2(struct bpf_testmod_btf_type_tag_3 *arg) { + return arg->p->a; +} + noinline int bpf_testmod_loop_test(int n) { int i, sum = 0; @@ -109,26 +148,31 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .write = bpf_testmod_test_write, }; -BTF_SET_START(bpf_testmod_kfunc_ids) +BTF_SET_START(bpf_testmod_check_kfunc_ids) BTF_ID(func, bpf_testmod_test_mod_kfunc) -BTF_SET_END(bpf_testmod_kfunc_ids) +BTF_SET_END(bpf_testmod_check_kfunc_ids) + +static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &bpf_testmod_check_kfunc_ids, +}; -static DEFINE_KFUNC_BTF_ID_SET(&bpf_testmod_kfunc_ids, bpf_testmod_kfunc_btf_set); +extern int bpf_fentry_test1(int a); static int bpf_testmod_init(void) { int ret; - ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); - if (ret) + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); + if (ret < 0) return ret; - register_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); - return 0; + if (bpf_fentry_test1(0) < 0) + return -EINVAL; + return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } static void bpf_testmod_exit(void) { - unregister_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } diff --git a/tools/testing/selftests/bpf/cap_helpers.c b/tools/testing/selftests/bpf/cap_helpers.c new file mode 100644 index 000000000000..d5ac507401d7 --- /dev/null +++ b/tools/testing/selftests/bpf/cap_helpers.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "cap_helpers.h" + +/* Avoid including <sys/capability.h> from the libcap-devel package, + * so directly declare them here and use them from glibc. + */ +int capget(cap_user_header_t header, cap_user_data_t data); +int capset(cap_user_header_t header, const cap_user_data_t data); + +int cap_enable_effective(__u64 caps, __u64 *old_caps) +{ + struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3]; + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; + __u32 cap0 = caps; + __u32 cap1 = caps >> 32; + int err; + + err = capget(&hdr, data); + if (err) + return err; + + if (old_caps) + *old_caps = (__u64)(data[1].effective) << 32 | data[0].effective; + + if ((data[0].effective & cap0) == cap0 && + (data[1].effective & cap1) == cap1) + return 0; + + data[0].effective |= cap0; + data[1].effective |= cap1; + err = capset(&hdr, data); + if (err) + return err; + + return 0; +} + +int cap_disable_effective(__u64 caps, __u64 *old_caps) +{ + struct __user_cap_data_struct data[_LINUX_CAPABILITY_U32S_3]; + struct __user_cap_header_struct hdr = { + .version = _LINUX_CAPABILITY_VERSION_3, + }; + __u32 cap0 = caps; + __u32 cap1 = caps >> 32; + int err; + + err = capget(&hdr, data); + if (err) + return err; + + if (old_caps) + *old_caps = (__u64)(data[1].effective) << 32 | data[0].effective; + + if (!(data[0].effective & cap0) && !(data[1].effective & cap1)) + return 0; + + data[0].effective &= ~cap0; + data[1].effective &= ~cap1; + err = capset(&hdr, data); + if (err) + return err; + + return 0; +} diff --git a/tools/testing/selftests/bpf/cap_helpers.h b/tools/testing/selftests/bpf/cap_helpers.h new file mode 100644 index 000000000000..6d163530cb0f --- /dev/null +++ b/tools/testing/selftests/bpf/cap_helpers.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __CAP_HELPERS_H +#define __CAP_HELPERS_H + +#include <linux/types.h> +#include <linux/capability.h> + +#ifndef CAP_PERFMON +#define CAP_PERFMON 38 +#endif + +#ifndef CAP_BPF +#define CAP_BPF 39 +#endif + +int cap_enable_effective(__u64 caps, __u64 *old_caps); +int cap_disable_effective(__u64 caps, __u64 *old_caps); + +#endif diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index f6287132fa89..763db63a3890 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -48,3 +48,8 @@ CONFIG_IMA_READ_POLICY=y CONFIG_BLK_DEV_LOOP=y CONFIG_FUNCTION_TRACER=y CONFIG_DYNAMIC_FTRACE=y +CONFIG_NETFILTER=y +CONFIG_NF_DEFRAG_IPV4=y +CONFIG_NF_DEFRAG_IPV6=y +CONFIG_NF_CONNTRACK=y +CONFIG_USERFAULTFD=y diff --git a/tools/testing/selftests/bpf/ima_setup.sh b/tools/testing/selftests/bpf/ima_setup.sh index 8e62581113a3..8ecead4ccad0 100755 --- a/tools/testing/selftests/bpf/ima_setup.sh +++ b/tools/testing/selftests/bpf/ima_setup.sh @@ -12,7 +12,7 @@ LOG_FILE="$(mktemp /tmp/ima_setup.XXXX.log)" usage() { - echo "Usage: $0 <setup|cleanup|run> <existing_tmp_dir>" + echo "Usage: $0 <setup|cleanup|run|modify-bin|restore-bin|load-policy> <existing_tmp_dir>" exit 1 } @@ -51,6 +51,7 @@ setup() ensure_mount_securityfs echo "measure func=BPRM_CHECK fsuuid=${mount_uuid}" > ${IMA_POLICY_FILE} + echo "measure func=BPRM_CHECK fsuuid=${mount_uuid}" > ${mount_dir}/policy_test } cleanup() { @@ -77,6 +78,32 @@ run() exec "${copied_bin_path}" } +modify_bin() +{ + local tmp_dir="$1" + local mount_dir="${tmp_dir}/mnt" + local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})" + + echo "mod" >> "${copied_bin_path}" +} + +restore_bin() +{ + local tmp_dir="$1" + local mount_dir="${tmp_dir}/mnt" + local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})" + + truncate -s -4 "${copied_bin_path}" +} + +load_policy() +{ + local tmp_dir="$1" + local mount_dir="${tmp_dir}/mnt" + + echo ${mount_dir}/policy_test > ${IMA_POLICY_FILE} 2> /dev/null +} + catch() { local exit_code="$1" @@ -105,6 +132,12 @@ main() cleanup "${tmp_dir}" elif [[ "${action}" == "run" ]]; then run "${tmp_dir}" + elif [[ "${action}" == "modify-bin" ]]; then + modify_bin "${tmp_dir}" + elif [[ "${action}" == "restore-bin" ]]; then + restore_bin "${tmp_dir}" + elif [[ "${action}" == "load-policy" ]]; then + load_policy "${tmp_dir}" else echo "Unknown action: ${action}" exit 1 diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 6db1af8fdee7..2bb1f9b3841d 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -1,18 +1,25 @@ // SPDX-License-Identifier: GPL-2.0-only +#define _GNU_SOURCE + #include <errno.h> #include <stdbool.h> #include <stdio.h> #include <string.h> #include <unistd.h> +#include <sched.h> #include <arpa/inet.h> +#include <sys/mount.h> +#include <sys/stat.h> #include <linux/err.h> #include <linux/in.h> #include <linux/in6.h> +#include <linux/limits.h> #include "bpf_util.h" #include "network_helpers.h" +#include "test_progs.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) #define log_err(MSG, ...) ({ \ @@ -356,3 +363,82 @@ char *ping_command(int family) } return "ping"; } + +struct nstoken { + int orig_netns_fd; +}; + +static int setns_by_fd(int nsfd) +{ + int err; + + err = setns(nsfd, CLONE_NEWNET); + close(nsfd); + + if (!ASSERT_OK(err, "setns")) + return err; + + /* Switch /sys to the new namespace so that e.g. /sys/class/net + * reflects the devices in the new namespace. + */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "unshare")) + return err; + + /* Make our /sys mount private, so the following umount won't + * trigger the global umount in case it's shared. + */ + err = mount("none", "/sys", NULL, MS_PRIVATE, NULL); + if (!ASSERT_OK(err, "remount private /sys")) + return err; + + err = umount2("/sys", MNT_DETACH); + if (!ASSERT_OK(err, "umount2 /sys")) + return err; + + err = mount("sysfs", "/sys", "sysfs", 0, NULL); + if (!ASSERT_OK(err, "mount /sys")) + return err; + + err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL); + if (!ASSERT_OK(err, "mount /sys/fs/bpf")) + return err; + + return 0; +} + +struct nstoken *open_netns(const char *name) +{ + int nsfd; + char nspath[PATH_MAX]; + int err; + struct nstoken *token; + + token = malloc(sizeof(struct nstoken)); + if (!ASSERT_OK_PTR(token, "malloc token")) + return NULL; + + token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY); + if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net")) + goto fail; + + snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name); + nsfd = open(nspath, O_RDONLY | O_CLOEXEC); + if (!ASSERT_GE(nsfd, 0, "open netns fd")) + goto fail; + + err = setns_by_fd(nsfd); + if (!ASSERT_OK(err, "setns_by_fd")) + goto fail; + + return token; +fail: + free(token); + return NULL; +} + +void close_netns(struct nstoken *token) +{ + ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd"); + free(token); +} diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index d198181a5648..a4b3b2f9877b 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -55,4 +55,13 @@ int make_sockaddr(int family, const char *addr_str, __u16 port, struct sockaddr_storage *addr, socklen_t *len); char *ping_command(int family); +struct nstoken; +/** + * open_netns() - Switch to specified network namespace by name. + * + * Returns token with which to restore the original namespace + * using close_netns(). + */ +struct nstoken *open_netns(const char *name); +void close_netns(struct nstoken *token); #endif diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index 0ee29e11eaee..970f09156eb4 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -39,13 +39,13 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R1=ctx(off=0,imm=0)"}, {0, "R10=fp0"}, - {0, "R3_w=inv2"}, - {1, "R3_w=inv4"}, - {2, "R3_w=inv8"}, - {3, "R3_w=inv16"}, - {4, "R3_w=inv32"}, + {0, "R3_w=2"}, + {1, "R3_w=4"}, + {2, "R3_w=8"}, + {3, "R3_w=16"}, + {4, "R3_w=32"}, }, }, { @@ -67,19 +67,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R1=ctx(off=0,imm=0)"}, {0, "R10=fp0"}, - {0, "R3_w=inv1"}, - {1, "R3_w=inv2"}, - {2, "R3_w=inv4"}, - {3, "R3_w=inv8"}, - {4, "R3_w=inv16"}, - {5, "R3_w=inv1"}, - {6, "R4_w=inv32"}, - {7, "R4_w=inv16"}, - {8, "R4_w=inv8"}, - {9, "R4_w=inv4"}, - {10, "R4_w=inv2"}, + {0, "R3_w=1"}, + {1, "R3_w=2"}, + {2, "R3_w=4"}, + {3, "R3_w=8"}, + {4, "R3_w=16"}, + {5, "R3_w=1"}, + {6, "R4_w=32"}, + {7, "R4_w=16"}, + {8, "R4_w=8"}, + {9, "R4_w=4"}, + {10, "R4_w=2"}, }, }, { @@ -96,14 +96,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R1=ctx(off=0,imm=0)"}, {0, "R10=fp0"}, - {0, "R3_w=inv4"}, - {1, "R3_w=inv8"}, - {2, "R3_w=inv10"}, - {3, "R4_w=inv8"}, - {4, "R4_w=inv12"}, - {5, "R4_w=inv14"}, + {0, "R3_w=4"}, + {1, "R3_w=8"}, + {2, "R3_w=10"}, + {3, "R4_w=8"}, + {4, "R4_w=12"}, + {5, "R4_w=14"}, }, }, { @@ -118,12 +118,12 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R1=ctx(off=0,imm=0)"}, {0, "R10=fp0"}, - {0, "R3_w=inv7"}, - {1, "R3_w=inv7"}, - {2, "R3_w=inv14"}, - {3, "R3_w=inv56"}, + {0, "R3_w=7"}, + {1, "R3_w=7"}, + {2, "R3_w=14"}, + {3, "R3_w=56"}, }, }, @@ -161,19 +161,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {6, "R0_w=pkt(id=0,off=8,r=8,imm=0)"}, - {6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {7, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, - {8, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {9, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {10, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, - {12, "R3_w=pkt_end(id=0,off=0,imm=0)"}, - {17, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {18, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, - {19, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, - {20, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {21, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {22, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {6, "R0_w=pkt(off=8,r=8,imm=0)"}, + {6, "R3_w=scalar(umax=255,var_off=(0x0; 0xff))"}, + {7, "R3_w=scalar(umax=510,var_off=(0x0; 0x1fe))"}, + {8, "R3_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, + {9, "R3_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"}, + {10, "R3_w=scalar(umax=4080,var_off=(0x0; 0xff0))"}, + {12, "R3_w=pkt_end(off=0,imm=0)"}, + {17, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"}, + {18, "R4_w=scalar(umax=8160,var_off=(0x0; 0x1fe0))"}, + {19, "R4_w=scalar(umax=4080,var_off=(0x0; 0xff0))"}, + {20, "R4_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"}, + {21, "R4_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, + {22, "R4_w=scalar(umax=510,var_off=(0x0; 0x1fe))"}, }, }, { @@ -194,16 +194,16 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {7, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {8, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {9, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {10, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, - {11, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {12, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {13, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {14, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {15, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {6, "R3_w=scalar(umax=255,var_off=(0x0; 0xff))"}, + {7, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"}, + {8, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"}, + {9, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"}, + {10, "R4_w=scalar(umax=510,var_off=(0x0; 0x1fe))"}, + {11, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"}, + {12, "R4_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, + {13, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"}, + {14, "R4_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"}, + {15, "R4_w=scalar(umax=4080,var_off=(0x0; 0xff0))"}, }, }, { @@ -234,14 +234,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {2, "R5_w=pkt(id=0,off=0,r=0,imm=0)"}, - {4, "R5_w=pkt(id=0,off=14,r=0,imm=0)"}, - {5, "R4_w=pkt(id=0,off=14,r=0,imm=0)"}, - {9, "R2=pkt(id=0,off=0,r=18,imm=0)"}, - {10, "R5=pkt(id=0,off=14,r=18,imm=0)"}, - {10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {13, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, - {14, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, + {2, "R5_w=pkt(off=0,r=0,imm=0)"}, + {4, "R5_w=pkt(off=14,r=0,imm=0)"}, + {5, "R4_w=pkt(off=14,r=0,imm=0)"}, + {9, "R2=pkt(off=0,r=18,imm=0)"}, + {10, "R5=pkt(off=14,r=18,imm=0)"}, + {10, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"}, + {13, "R4_w=scalar(umax=65535,var_off=(0x0; 0xffff))"}, + {14, "R4_w=scalar(umax=65535,var_off=(0x0; 0xffff))"}, }, }, { @@ -296,59 +296,59 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {6, "R2_w=pkt(off=0,r=8,imm=0)"}, + {7, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, /* Offset is added to packet pointer R5, resulting in * known fixed offset, and variable offset from R6. */ - {11, "R5_w=pkt(id=1,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {11, "R5_w=pkt(id=1,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, * it's total offset is NET_IP_ALIGN + reg->off (0) + * reg->aux_off (14) which is 16. Then the variable * offset is considered using reg->aux_off_align which * is 4 and meets the load's requirements. */ - {15, "R4=pkt(id=1,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {15, "R5=pkt(id=1,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {15, "R4=pkt(id=1,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"}, + {15, "R5=pkt(id=1,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"}, /* Variable offset is added to R5 packet pointer, * resulting in auxiliary alignment of 4. */ - {17, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {17, "R5_w=pkt(id=2,off=0,r=0,umax=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5, resulting in * reg->off of 14. */ - {18, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {18, "R5_w=pkt(id=2,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off * (14) which is 16. Then the variable offset is 4-byte * aligned, so the total offset is 4-byte aligned and * meets the load's requirements. */ - {23, "R4=pkt(id=2,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {23, "R5=pkt(id=2,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {23, "R4=pkt(id=2,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"}, + {23, "R5=pkt(id=2,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5 packet pointer, * resulting in reg->off value of 14. */ - {25, "R5_w=pkt(id=0,off=14,r=8"}, + {25, "R5_w=pkt(off=14,r=8"}, /* Variable offset is added to R5, resulting in a * variable offset of (4n). */ - {26, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {26, "R5_w=pkt(id=3,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"}, /* Constant is added to R5 again, setting reg->off to 18. */ - {27, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {27, "R5_w=pkt(id=3,off=18,r=0,umax=1020,var_off=(0x0; 0x3fc))"}, /* And once more we add a variable; resulting var_off * is still (4n), fixed offset is not changed. * Also, we create a new reg->id. */ - {28, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"}, + {28, "R5_w=pkt(id=4,off=18,r=0,umax=2040,var_off=(0x0; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (18) * which is 20. Then the variable offset is (4n), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"}, - {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc)"}, + {33, "R4=pkt(id=4,off=22,r=22,umax=2040,var_off=(0x0; 0x7fc)"}, + {33, "R5=pkt(id=4,off=18,r=22,umax=2040,var_off=(0x0; 0x7fc)"}, }, }, { @@ -386,36 +386,36 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {6, "R2_w=pkt(off=0,r=8,imm=0)"}, + {7, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ - {8, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {8, "R6_w=scalar(umin=14,umax=1034,var_off=(0x2; 0x7fc))"}, /* Packet pointer has (4n+2) offset */ - {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, - {12, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, + {11, "R5_w=pkt(id=1,off=0,r=0,umin=14,umax=1034,var_off=(0x2; 0x7fc)"}, + {12, "R4=pkt(id=1,off=4,r=0,umin=14,umax=1034,var_off=(0x2; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, + {15, "R5=pkt(id=1,off=0,r=4,umin=14,umax=1034,var_off=(0x2; 0x7fc)"}, /* Newly read value in R6 was shifted left by 2, so has * known alignment of 4. */ - {17, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {17, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, /* Added (4n) to packet pointer's (4n+2) var_off, giving * another (4n+2). */ - {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, - {20, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, + {19, "R5_w=pkt(id=2,off=0,r=0,umin=14,umax=2054,var_off=(0x2; 0xffc)"}, + {20, "R4=pkt(id=2,off=4,r=0,umin=14,umax=2054,var_off=(0x2; 0xffc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, + {23, "R5=pkt(id=2,off=0,r=4,umin=14,umax=2054,var_off=(0x2; 0xffc)"}, }, }, { @@ -448,18 +448,18 @@ static struct bpf_align_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .matches = { - {3, "R5_w=pkt_end(id=0,off=0,imm=0)"}, + {3, "R5_w=pkt_end(off=0,imm=0)"}, /* (ptr - ptr) << 2 == unknown, (4n) */ - {5, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"}, + {5, "R5_w=scalar(smax=9223372036854775804,umax=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"}, /* (4n) + 14 == (4n+2). We blow our bounds, because * the add could overflow. */ - {6, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, + {6, "R5_w=scalar(smin=-9223372036854775806,smax=9223372036854775806,umin=2,umax=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ - {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {9, "R5=scalar(umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* packet pointer + nonnegative (4n+2) */ - {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, - {12, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {11, "R6_w=pkt(id=1,off=0,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {12, "R4_w=pkt(id=1,off=4,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -467,7 +467,7 @@ static struct bpf_align_test tests[] = { * So we did not get a 'range' on R6, and the access * attempt will fail. */ - {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {15, "R6_w=pkt(id=1,off=0,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, } }, { @@ -502,23 +502,23 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {6, "R2_w=pkt(off=0,r=8,imm=0)"}, + {8, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ - {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {9, "R6_w=scalar(umin=14,umax=1034,var_off=(0x2; 0x7fc))"}, /* New unknown value in R7 is (4n) */ - {10, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {10, "R7_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"}, /* Subtracting it from R6 blows our unsigned bounds */ - {11, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, + {11, "R6=scalar(smin=-1006,smax=1034,umin=2,umax=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>= 0 */ - {14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {14, "R6=scalar(umin=2,umax=1034,var_off=(0x2; 0x7fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc)"}, + {20, "R5=pkt(id=2,off=0,r=4,umin=2,umax=1034,var_off=(0x2; 0x7fc)"}, }, }, @@ -556,23 +556,23 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {9, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, + {6, "R2_w=pkt(off=0,r=8,imm=0)"}, + {9, "R6_w=scalar(umax=60,var_off=(0x0; 0x3c))"}, /* Adding 14 makes R6 be (4n+2) */ - {10, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, + {10, "R6_w=scalar(umin=14,umax=74,var_off=(0x2; 0x7c))"}, /* Subtracting from packet pointer overflows ubounds */ - {13, "R5_w=pkt(id=2,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"}, + {13, "R5_w=pkt(id=2,off=0,r=8,umin=18446744073709551542,umax=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"}, /* New unknown value in R7 is (4n), >= 76 */ - {14, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, + {14, "R7_w=scalar(umin=76,umax=1096,var_off=(0x0; 0x7fc))"}, /* Adding it to packet pointer gives nice bounds again */ - {16, "R5_w=pkt(id=3,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"}, + {16, "R5_w=pkt(id=3,off=0,r=0,umin=2,umax=1082,var_off=(0x2; 0xfffffffc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so * the total offset is 4-byte aligned and meets the * load's requirements. */ - {20, "R5=pkt(id=3,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"}, + {20, "R5=pkt(id=3,off=0,r=4,umin=2,umax=1082,var_off=(0x2; 0xfffffffc)"}, }, }, }; @@ -648,8 +648,8 @@ static int do_test_single(struct bpf_align_test *test) /* Check the next line as well in case the previous line * did not have a corresponding bpf insn. Example: * func#0 @0 - * 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 - * 0: (b7) r3 = 2 ; R3_w=inv2 + * 0: R1=ctx(off=0,imm=0) R10=fp0 + * 0: (b7) r3 = 2 ; R3_w=2 */ if (!strstr(line_ptr, m.match)) { cur_line = -1; diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c index 86b7d5d84eec..13e101f370a1 100644 --- a/tools/testing/selftests/bpf/prog_tests/atomics.c +++ b/tools/testing/selftests/bpf/prog_tests/atomics.c @@ -7,19 +7,15 @@ static void test_add(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__add__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(add)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.add.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run add", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->add64_value, 3, "add64_value"); ASSERT_EQ(skel->bss->add64_result, 1, "add64_result"); @@ -31,28 +27,20 @@ static void test_add(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->add_stack_result, 1, "add_stack_result"); ASSERT_EQ(skel->data->add_noreturn_value, 3, "add_noreturn_value"); - -cleanup: - close(link_fd); } static void test_sub(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__sub__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(sub)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.sub.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run sub", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->sub64_value, -1, "sub64_value"); ASSERT_EQ(skel->bss->sub64_result, 1, "sub64_result"); @@ -64,27 +52,20 @@ static void test_sub(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->sub_stack_result, 1, "sub_stack_result"); ASSERT_EQ(skel->data->sub_noreturn_value, -1, "sub_noreturn_value"); - -cleanup: - close(link_fd); } static void test_and(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__and__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(and)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.and.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run and", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->and64_value, 0x010ull << 32, "and64_value"); ASSERT_EQ(skel->bss->and64_result, 0x110ull << 32, "and64_result"); @@ -93,27 +74,20 @@ static void test_and(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->and32_result, 0x110, "and32_result"); ASSERT_EQ(skel->data->and_noreturn_value, 0x010ull << 32, "and_noreturn_value"); -cleanup: - close(link_fd); } static void test_or(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__or__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(or)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.or.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run or", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->or64_value, 0x111ull << 32, "or64_value"); ASSERT_EQ(skel->bss->or64_result, 0x110ull << 32, "or64_result"); @@ -122,26 +96,20 @@ static void test_or(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->or32_result, 0x110, "or32_result"); ASSERT_EQ(skel->data->or_noreturn_value, 0x111ull << 32, "or_noreturn_value"); -cleanup: - close(link_fd); } static void test_xor(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__xor__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(xor)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.xor.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run xor", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->xor64_value, 0x101ull << 32, "xor64_value"); ASSERT_EQ(skel->bss->xor64_result, 0x110ull << 32, "xor64_result"); @@ -150,26 +118,20 @@ static void test_xor(struct atomics_lskel *skel) ASSERT_EQ(skel->bss->xor32_result, 0x110, "xor32_result"); ASSERT_EQ(skel->data->xor_noreturn_value, 0x101ull << 32, "xor_nxoreturn_value"); -cleanup: - close(link_fd); } static void test_cmpxchg(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__cmpxchg__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(cmpxchg)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.cmpxchg.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run cmpxchg", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->cmpxchg64_value, 2, "cmpxchg64_value"); ASSERT_EQ(skel->bss->cmpxchg64_result_fail, 1, "cmpxchg_result_fail"); @@ -178,45 +140,34 @@ static void test_cmpxchg(struct atomics_lskel *skel) ASSERT_EQ(skel->data->cmpxchg32_value, 2, "lcmpxchg32_value"); ASSERT_EQ(skel->bss->cmpxchg32_result_fail, 1, "cmpxchg_result_fail"); ASSERT_EQ(skel->bss->cmpxchg32_result_succeed, 1, "cmpxchg_result_succeed"); - -cleanup: - close(link_fd); } static void test_xchg(struct atomics_lskel *skel) { int err, prog_fd; - __u32 duration = 0, retval; - int link_fd; - - link_fd = atomics_lskel__xchg__attach(skel); - if (!ASSERT_GT(link_fd, 0, "attach(xchg)")) - return; + LIBBPF_OPTS(bpf_test_run_opts, topts); + /* No need to attach it, just run it directly */ prog_fd = skel->progs.xchg.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run xchg", - "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) - goto cleanup; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err")) + return; + if (!ASSERT_OK(topts.retval, "test_run_opts retval")) + return; ASSERT_EQ(skel->data->xchg64_value, 2, "xchg64_value"); ASSERT_EQ(skel->bss->xchg64_result, 1, "xchg64_result"); ASSERT_EQ(skel->data->xchg32_value, 2, "xchg32_value"); ASSERT_EQ(skel->bss->xchg32_result, 1, "xchg32_result"); - -cleanup: - close(link_fd); } void test_atomics(void) { struct atomics_lskel *skel; - __u32 duration = 0; skel = atomics_lskel__open_and_load(); - if (CHECK(!skel, "skel_load", "atomics skeleton failed\n")) + if (!ASSERT_OK_PTR(skel, "atomics skeleton load")) return; if (skel->data->skip_tests) { diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index d0bd51eb23c8..d48f6e533e1e 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -5,9 +5,10 @@ /* this is how USDT semaphore is actually defined, except volatile modifier */ volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes"))); -/* attach point */ -static void method(void) { - return ; +/* uprobe attach point */ +static void trigger_func(void) +{ + asm volatile (""); } void test_attach_probe(void) @@ -17,8 +18,7 @@ void test_attach_probe(void) struct bpf_link *kprobe_link, *kretprobe_link; struct bpf_link *uprobe_link, *uretprobe_link; struct test_attach_probe* skel; - size_t uprobe_offset; - ssize_t base_addr, ref_ctr_offset; + ssize_t uprobe_offset, ref_ctr_offset; bool legacy; /* Check if new-style kprobe/uprobe API is supported. @@ -34,11 +34,9 @@ void test_attach_probe(void) */ legacy = access("/sys/bus/event_source/devices/kprobe/type", F_OK) != 0; - base_addr = get_base_addr(); - if (CHECK(base_addr < 0, "get_base_addr", - "failed to find base addr: %zd", base_addr)) + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) return; - uprobe_offset = get_uprobe_offset(&method, base_addr); ref_ctr_offset = get_rel_offset((uintptr_t)&uprobe_ref_ctr); if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset")) @@ -103,7 +101,7 @@ void test_attach_probe(void) goto cleanup; /* trigger & validate uprobe & uretprobe */ - method(); + trigger_func(); if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res", "wrong uprobe res: %d\n", skel->bss->uprobe_res)) diff --git a/tools/testing/selftests/bpf/prog_tests/bind_perm.c b/tools/testing/selftests/bpf/prog_tests/bind_perm.c index d0f06e40c16d..a1766a298bb7 100644 --- a/tools/testing/selftests/bpf/prog_tests/bind_perm.c +++ b/tools/testing/selftests/bpf/prog_tests/bind_perm.c @@ -1,13 +1,24 @@ // SPDX-License-Identifier: GPL-2.0 -#include <test_progs.h> -#include "bind_perm.skel.h" - +#define _GNU_SOURCE +#include <sched.h> +#include <stdlib.h> #include <sys/types.h> #include <sys/socket.h> -#include <sys/capability.h> + +#include "test_progs.h" +#include "cap_helpers.h" +#include "bind_perm.skel.h" static int duration; +static int create_netns(void) +{ + if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns")) + return -1; + + return 0; +} + void try_bind(int family, int port, int expected_errno) { struct sockaddr_storage addr = {}; @@ -38,43 +49,16 @@ close_socket: close(fd); } -bool cap_net_bind_service(cap_flag_value_t flag) -{ - const cap_value_t cap_net_bind_service = CAP_NET_BIND_SERVICE; - cap_flag_value_t original_value; - bool was_effective = false; - cap_t caps; - - caps = cap_get_proc(); - if (CHECK(!caps, "cap_get_proc", "errno %d", errno)) - goto free_caps; - - if (CHECK(cap_get_flag(caps, CAP_NET_BIND_SERVICE, CAP_EFFECTIVE, - &original_value), - "cap_get_flag", "errno %d", errno)) - goto free_caps; - - was_effective = (original_value == CAP_SET); - - if (CHECK(cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_net_bind_service, - flag), - "cap_set_flag", "errno %d", errno)) - goto free_caps; - - if (CHECK(cap_set_proc(caps), "cap_set_proc", "errno %d", errno)) - goto free_caps; - -free_caps: - CHECK(cap_free(caps), "cap_free", "errno %d", errno); - return was_effective; -} - void test_bind_perm(void) { - bool cap_was_effective; + const __u64 net_bind_svc_cap = 1ULL << CAP_NET_BIND_SERVICE; struct bind_perm *skel; + __u64 old_caps = 0; int cgroup_fd; + if (create_netns()) + return; + cgroup_fd = test__join_cgroup("/bind_perm"); if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno)) return; @@ -91,7 +75,8 @@ void test_bind_perm(void) if (!ASSERT_OK_PTR(skel, "bind_v6_prog")) goto close_skeleton; - cap_was_effective = cap_net_bind_service(CAP_CLEAR); + ASSERT_OK(cap_disable_effective(net_bind_svc_cap, &old_caps), + "cap_disable_effective"); try_bind(AF_INET, 110, EACCES); try_bind(AF_INET6, 110, EACCES); @@ -99,8 +84,9 @@ void test_bind_perm(void) try_bind(AF_INET, 111, 0); try_bind(AF_INET6, 111, 0); - if (cap_was_effective) - cap_net_bind_service(CAP_SET); + if (old_caps & net_bind_svc_cap) + ASSERT_OK(cap_enable_effective(net_bind_svc_cap, NULL), + "cap_enable_effective"); close_skeleton: bind_perm__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 5eea3c3a40fe..923a6139b2d8 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -7,6 +7,13 @@ #include <unistd.h> #include <test_progs.h> #include "test_bpf_cookie.skel.h" +#include "kprobe_multi.skel.h" + +/* uprobe attach point */ +static void trigger_func(void) +{ + asm volatile (""); +} static void kprobe_subtest(struct test_bpf_cookie *skel) { @@ -57,16 +64,188 @@ cleanup: bpf_link__destroy(retlink2); } +static void kprobe_multi_test_run(struct kprobe_multi *skel) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, prog_fd; + + prog_fd = bpf_program__fd(skel->progs.trigger); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); + + ASSERT_EQ(skel->bss->kprobe_test1_result, 1, "kprobe_test1_result"); + ASSERT_EQ(skel->bss->kprobe_test2_result, 1, "kprobe_test2_result"); + ASSERT_EQ(skel->bss->kprobe_test3_result, 1, "kprobe_test3_result"); + ASSERT_EQ(skel->bss->kprobe_test4_result, 1, "kprobe_test4_result"); + ASSERT_EQ(skel->bss->kprobe_test5_result, 1, "kprobe_test5_result"); + ASSERT_EQ(skel->bss->kprobe_test6_result, 1, "kprobe_test6_result"); + ASSERT_EQ(skel->bss->kprobe_test7_result, 1, "kprobe_test7_result"); + ASSERT_EQ(skel->bss->kprobe_test8_result, 1, "kprobe_test8_result"); + + ASSERT_EQ(skel->bss->kretprobe_test1_result, 1, "kretprobe_test1_result"); + ASSERT_EQ(skel->bss->kretprobe_test2_result, 1, "kretprobe_test2_result"); + ASSERT_EQ(skel->bss->kretprobe_test3_result, 1, "kretprobe_test3_result"); + ASSERT_EQ(skel->bss->kretprobe_test4_result, 1, "kretprobe_test4_result"); + ASSERT_EQ(skel->bss->kretprobe_test5_result, 1, "kretprobe_test5_result"); + ASSERT_EQ(skel->bss->kretprobe_test6_result, 1, "kretprobe_test6_result"); + ASSERT_EQ(skel->bss->kretprobe_test7_result, 1, "kretprobe_test7_result"); + ASSERT_EQ(skel->bss->kretprobe_test8_result, 1, "kretprobe_test8_result"); +} + +static void kprobe_multi_link_api_subtest(void) +{ + int prog_fd, link1_fd = -1, link2_fd = -1; + struct kprobe_multi *skel = NULL; + LIBBPF_OPTS(bpf_link_create_opts, opts); + unsigned long long addrs[8]; + __u64 cookies[8]; + + if (!ASSERT_OK(load_kallsyms(), "load_kallsyms")) + goto cleanup; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + skel->bss->test_cookie = true; + +#define GET_ADDR(__sym, __addr) ({ \ + __addr = ksym_get_addr(__sym); \ + if (!ASSERT_NEQ(__addr, 0, "ksym_get_addr " #__sym)) \ + goto cleanup; \ +}) + + GET_ADDR("bpf_fentry_test1", addrs[0]); + GET_ADDR("bpf_fentry_test2", addrs[1]); + GET_ADDR("bpf_fentry_test3", addrs[2]); + GET_ADDR("bpf_fentry_test4", addrs[3]); + GET_ADDR("bpf_fentry_test5", addrs[4]); + GET_ADDR("bpf_fentry_test6", addrs[5]); + GET_ADDR("bpf_fentry_test7", addrs[6]); + GET_ADDR("bpf_fentry_test8", addrs[7]); + +#undef GET_ADDR + + cookies[0] = 1; + cookies[1] = 2; + cookies[2] = 3; + cookies[3] = 4; + cookies[4] = 5; + cookies[5] = 6; + cookies[6] = 7; + cookies[7] = 8; + + opts.kprobe_multi.addrs = (const unsigned long *) &addrs; + opts.kprobe_multi.cnt = ARRAY_SIZE(addrs); + opts.kprobe_multi.cookies = (const __u64 *) &cookies; + prog_fd = bpf_program__fd(skel->progs.test_kprobe); + + link1_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &opts); + if (!ASSERT_GE(link1_fd, 0, "link1_fd")) + goto cleanup; + + cookies[0] = 8; + cookies[1] = 7; + cookies[2] = 6; + cookies[3] = 5; + cookies[4] = 4; + cookies[5] = 3; + cookies[6] = 2; + cookies[7] = 1; + + opts.kprobe_multi.flags = BPF_F_KPROBE_MULTI_RETURN; + prog_fd = bpf_program__fd(skel->progs.test_kretprobe); + + link2_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &opts); + if (!ASSERT_GE(link2_fd, 0, "link2_fd")) + goto cleanup; + + kprobe_multi_test_run(skel); + +cleanup: + close(link1_fd); + close(link2_fd); + kprobe_multi__destroy(skel); +} + +static void kprobe_multi_attach_api_subtest(void) +{ + struct bpf_link *link1 = NULL, *link2 = NULL; + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct kprobe_multi *skel = NULL; + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + __u64 cookies[8]; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + skel->bss->test_cookie = true; + + cookies[0] = 1; + cookies[1] = 2; + cookies[2] = 3; + cookies[3] = 4; + cookies[4] = 5; + cookies[5] = 6; + cookies[6] = 7; + cookies[7] = 8; + + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = cookies; + + link1 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + NULL, &opts); + if (!ASSERT_OK_PTR(link1, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + + cookies[0] = 8; + cookies[1] = 7; + cookies[2] = 6; + cookies[3] = 5; + cookies[4] = 4; + cookies[5] = 3; + cookies[6] = 2; + cookies[7] = 1; + + opts.retprobe = true; + + link2 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kretprobe, + NULL, &opts); + if (!ASSERT_OK_PTR(link2, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + + kprobe_multi_test_run(skel); + +cleanup: + bpf_link__destroy(link2); + bpf_link__destroy(link1); + kprobe_multi__destroy(skel); +} static void uprobe_subtest(struct test_bpf_cookie *skel) { DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts); struct bpf_link *link1 = NULL, *link2 = NULL; struct bpf_link *retlink1 = NULL, *retlink2 = NULL; - size_t uprobe_offset; - ssize_t base_addr; + ssize_t uprobe_offset; - base_addr = get_base_addr(); - uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr); + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) + goto cleanup; /* attach two uprobes */ opts.bpf_cookie = 0x100; @@ -99,7 +278,7 @@ static void uprobe_subtest(struct test_bpf_cookie *skel) goto cleanup; /* trigger uprobe && uretprobe */ - get_base_addr(); + trigger_func(); ASSERT_EQ(skel->bss->uprobe_res, 0x100 | 0x200, "uprobe_res"); ASSERT_EQ(skel->bss->uretprobe_res, 0x1000 | 0x2000, "uretprobe_res"); @@ -193,7 +372,7 @@ static void pe_subtest(struct test_bpf_cookie *skel) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (!ASSERT_GE(pfd, 0, "perf_fd")) goto cleanup; @@ -243,6 +422,10 @@ void test_bpf_cookie(void) if (test__start_subtest("kprobe")) kprobe_subtest(skel); + if (test__start_subtest("multi_kprobe_link_api")) + kprobe_multi_link_api_subtest(); + if (test__start_subtest("multi_kprobe_attach_api")) + kprobe_multi_attach_api_subtest(); if (test__start_subtest("uprobe")) uprobe_subtest(skel); if (test__start_subtest("tracepoint")) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index b84f859b1267..5142a7d130b2 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -138,6 +138,24 @@ static void test_task(void) bpf_iter_task__destroy(skel); } +static void test_task_sleepable(void) +{ + struct bpf_iter_task *skel; + + skel = bpf_iter_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + return; + + do_dummy_read(skel->progs.dump_task_sleepable); + + ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task, 0, + "num_expected_failure_copy_from_user_task"); + ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0, + "num_success_copy_from_user_task"); + + bpf_iter_task__destroy(skel); +} + static void test_task_stack(void) { struct bpf_iter_task_stack *skel; @@ -1252,6 +1270,8 @@ void test_bpf_iter(void) test_bpf_map(); if (test__start_subtest("task")) test_task(); + if (test__start_subtest("task_sleepable")) + test_task_sleepable(); if (test__start_subtest("task_stack")) test_task_stack(); if (test__start_subtest("task_file")) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c new file mode 100644 index 000000000000..ee725d4d98a5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ +#include <sys/socket.h> +#include <sys/un.h> +#include <test_progs.h> +#include "bpf_iter_setsockopt_unix.skel.h" + +#define NR_CASES 5 + +static int create_unix_socket(struct bpf_iter_setsockopt_unix *skel) +{ + struct sockaddr_un addr = { + .sun_family = AF_UNIX, + .sun_path = "", + }; + socklen_t len; + int fd, err; + + fd = socket(AF_UNIX, SOCK_STREAM, 0); + if (!ASSERT_NEQ(fd, -1, "socket")) + return -1; + + len = offsetof(struct sockaddr_un, sun_path); + err = bind(fd, (struct sockaddr *)&addr, len); + if (!ASSERT_OK(err, "bind")) + return -1; + + len = sizeof(addr); + err = getsockname(fd, (struct sockaddr *)&addr, &len); + if (!ASSERT_OK(err, "getsockname")) + return -1; + + memcpy(&skel->bss->sun_path, &addr.sun_path, + len - offsetof(struct sockaddr_un, sun_path)); + + return fd; +} + +static void test_sndbuf(struct bpf_iter_setsockopt_unix *skel, int fd) +{ + socklen_t optlen; + int i, err; + + for (i = 0; i < NR_CASES; i++) { + if (!ASSERT_NEQ(skel->data->sndbuf_getsockopt[i], -1, + "bpf_(get|set)sockopt")) + return; + + err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, + &(skel->data->sndbuf_setsockopt[i]), + sizeof(skel->data->sndbuf_setsockopt[i])); + if (!ASSERT_OK(err, "setsockopt")) + return; + + optlen = sizeof(skel->bss->sndbuf_getsockopt_expected[i]); + err = getsockopt(fd, SOL_SOCKET, SO_SNDBUF, + &(skel->bss->sndbuf_getsockopt_expected[i]), + &optlen); + if (!ASSERT_OK(err, "getsockopt")) + return; + + if (!ASSERT_EQ(skel->data->sndbuf_getsockopt[i], + skel->bss->sndbuf_getsockopt_expected[i], + "bpf_(get|set)sockopt")) + return; + } +} + +void test_bpf_iter_setsockopt_unix(void) +{ + struct bpf_iter_setsockopt_unix *skel; + int err, unix_fd, iter_fd; + char buf; + + skel = bpf_iter_setsockopt_unix__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + unix_fd = create_unix_socket(skel); + if (!ASSERT_NEQ(unix_fd, -1, "create_unix_server")) + goto destroy; + + skel->links.change_sndbuf = bpf_program__attach_iter(skel->progs.change_sndbuf, NULL); + if (!ASSERT_OK_PTR(skel->links.change_sndbuf, "bpf_program__attach_iter")) + goto destroy; + + iter_fd = bpf_iter_create(bpf_link__fd(skel->links.change_sndbuf)); + if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create")) + goto destroy; + + while ((err = read(iter_fd, &buf, sizeof(buf))) == -1 && + errno == EAGAIN) + ; + if (!ASSERT_OK(err, "read iter error")) + goto destroy; + + test_sndbuf(skel, unix_fd); +destroy: + bpf_iter_setsockopt_unix__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c new file mode 100644 index 000000000000..d43f548c572c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <unistd.h> +#include <pthread.h> +#include <sys/mman.h> +#include <stdatomic.h> +#include <test_progs.h> +#include <sys/syscall.h> +#include <linux/module.h> +#include <linux/userfaultfd.h> + +#include "ksym_race.skel.h" +#include "bpf_mod_race.skel.h" +#include "kfunc_call_race.skel.h" + +/* This test crafts a race between btf_try_get_module and do_init_module, and + * checks whether btf_try_get_module handles the invocation for a well-formed + * but uninitialized module correctly. Unless the module has completed its + * initcalls, the verifier should fail the program load and return ENXIO. + * + * userfaultfd is used to trigger a fault in an fmod_ret program, and make it + * sleep, then the BPF program is loaded and the return value from verifier is + * inspected. After this, the userfaultfd is closed so that the module loading + * thread makes forward progress, and fmod_ret injects an error so that the + * module load fails and it is freed. + * + * If the verifier succeeded in loading the supplied program, it will end up + * taking reference to freed module, and trigger a crash when the program fd + * is closed later. This is true for both kfuncs and ksyms. In both cases, + * the crash is triggered inside bpf_prog_free_deferred, when module reference + * is finally released. + */ + +struct test_config { + const char *str_open; + void *(*bpf_open_and_load)(); + void (*bpf_destroy)(void *); +}; + +enum test_state { + _TS_INVALID, + TS_MODULE_LOAD, + TS_MODULE_LOAD_FAIL, +}; + +static _Atomic enum test_state state = _TS_INVALID; + +static int sys_finit_module(int fd, const char *param_values, int flags) +{ + return syscall(__NR_finit_module, fd, param_values, flags); +} + +static int sys_delete_module(const char *name, unsigned int flags) +{ + return syscall(__NR_delete_module, name, flags); +} + +static int load_module(const char *mod) +{ + int ret, fd; + + fd = open("bpf_testmod.ko", O_RDONLY); + if (fd < 0) + return fd; + + ret = sys_finit_module(fd, "", 0); + close(fd); + if (ret < 0) + return ret; + return 0; +} + +static void *load_module_thread(void *p) +{ + + if (!ASSERT_NEQ(load_module("bpf_testmod.ko"), 0, "load_module_thread must fail")) + atomic_store(&state, TS_MODULE_LOAD); + else + atomic_store(&state, TS_MODULE_LOAD_FAIL); + return p; +} + +static int sys_userfaultfd(int flags) +{ + return syscall(__NR_userfaultfd, flags); +} + +static int test_setup_uffd(void *fault_addr) +{ + struct uffdio_register uffd_register = {}; + struct uffdio_api uffd_api = {}; + int uffd; + + uffd = sys_userfaultfd(O_CLOEXEC); + if (uffd < 0) + return -errno; + + uffd_api.api = UFFD_API; + uffd_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffd_api)) { + close(uffd); + return -1; + } + + uffd_register.range.start = (unsigned long)fault_addr; + uffd_register.range.len = 4096; + uffd_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) { + close(uffd); + return -1; + } + return uffd; +} + +static void test_bpf_mod_race_config(const struct test_config *config) +{ + void *fault_addr, *skel_fail; + struct bpf_mod_race *skel; + struct uffd_msg uffd_msg; + pthread_t load_mod_thrd; + _Atomic int *blockingp; + int uffd, ret; + + fault_addr = mmap(0, 4096, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (!ASSERT_NEQ(fault_addr, MAP_FAILED, "mmap for uffd registration")) + return; + + if (!ASSERT_OK(sys_delete_module("bpf_testmod", 0), "unload bpf_testmod")) + goto end_mmap; + + skel = bpf_mod_race__open(); + if (!ASSERT_OK_PTR(skel, "bpf_mod_kfunc_race__open")) + goto end_module; + + skel->rodata->bpf_mod_race_config.tgid = getpid(); + skel->rodata->bpf_mod_race_config.inject_error = -4242; + skel->rodata->bpf_mod_race_config.fault_addr = fault_addr; + if (!ASSERT_OK(bpf_mod_race__load(skel), "bpf_mod___load")) + goto end_destroy; + blockingp = (_Atomic int *)&skel->bss->bpf_blocking; + + if (!ASSERT_OK(bpf_mod_race__attach(skel), "bpf_mod_kfunc_race__attach")) + goto end_destroy; + + uffd = test_setup_uffd(fault_addr); + if (!ASSERT_GE(uffd, 0, "userfaultfd open + register address")) + goto end_destroy; + + if (!ASSERT_OK(pthread_create(&load_mod_thrd, NULL, load_module_thread, NULL), + "load module thread")) + goto end_uffd; + + /* Now, we either fail loading module, or block in bpf prog, spin to find out */ + while (!atomic_load(&state) && !atomic_load(blockingp)) + ; + if (!ASSERT_EQ(state, _TS_INVALID, "module load should block")) + goto end_join; + if (!ASSERT_EQ(*blockingp, 1, "module load blocked")) { + pthread_kill(load_mod_thrd, SIGKILL); + goto end_uffd; + } + + /* We might have set bpf_blocking to 1, but may have not blocked in + * bpf_copy_from_user. Read userfaultfd descriptor to verify that. + */ + if (!ASSERT_EQ(read(uffd, &uffd_msg, sizeof(uffd_msg)), sizeof(uffd_msg), + "read uffd block event")) + goto end_join; + if (!ASSERT_EQ(uffd_msg.event, UFFD_EVENT_PAGEFAULT, "read uffd event is pagefault")) + goto end_join; + + /* We know that load_mod_thrd is blocked in the fmod_ret program, the + * module state is still MODULE_STATE_COMING because mod->init hasn't + * returned. This is the time we try to load a program calling kfunc and + * check if we get ENXIO from verifier. + */ + skel_fail = config->bpf_open_and_load(); + ret = errno; + if (!ASSERT_EQ(skel_fail, NULL, config->str_open)) { + /* Close uffd to unblock load_mod_thrd */ + close(uffd); + uffd = -1; + while (atomic_load(blockingp) != 2) + ; + ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); + config->bpf_destroy(skel_fail); + goto end_join; + + } + ASSERT_EQ(ret, ENXIO, "verifier returns ENXIO"); + ASSERT_EQ(skel->data->res_try_get_module, false, "btf_try_get_module == false"); + + close(uffd); + uffd = -1; +end_join: + pthread_join(load_mod_thrd, NULL); + if (uffd < 0) + ASSERT_EQ(atomic_load(&state), TS_MODULE_LOAD_FAIL, "load_mod_thrd success"); +end_uffd: + if (uffd >= 0) + close(uffd); +end_destroy: + bpf_mod_race__destroy(skel); + ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); +end_module: + sys_delete_module("bpf_testmod", 0); + ASSERT_OK(load_module("bpf_testmod.ko"), "restore bpf_testmod"); +end_mmap: + munmap(fault_addr, 4096); + atomic_store(&state, _TS_INVALID); +} + +static const struct test_config ksym_config = { + .str_open = "ksym_race__open_and_load", + .bpf_open_and_load = (void *)ksym_race__open_and_load, + .bpf_destroy = (void *)ksym_race__destroy, +}; + +static const struct test_config kfunc_config = { + .str_open = "kfunc_call_race__open_and_load", + .bpf_open_and_load = (void *)kfunc_call_race__open_and_load, + .bpf_destroy = (void *)kfunc_call_race__destroy, +}; + +void serial_test_bpf_mod_race(void) +{ + if (test__start_subtest("ksym (used_btfs UAF)")) + test_bpf_mod_race_config(&ksym_config); + if (test__start_subtest("kfunc (kfunc_btf_tab UAF)")) + test_bpf_mod_race_config(&kfunc_config); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c new file mode 100644 index 000000000000..dd30b1e3a67c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> +#include "test_bpf_nf.skel.h" + +enum { + TEST_XDP, + TEST_TC_BPF, +}; + +void test_bpf_nf_ct(int mode) +{ + struct test_bpf_nf *skel; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + + skel = test_bpf_nf__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_bpf_nf__open_and_load")) + return; + + if (mode == TEST_XDP) + prog_fd = bpf_program__fd(skel->progs.nf_xdp_ct_test); + else + prog_fd = bpf_program__fd(skel->progs.nf_skb_ct_test); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "bpf_prog_test_run")) + goto end; + + ASSERT_EQ(skel->bss->test_einval_bpf_tuple, -EINVAL, "Test EINVAL for NULL bpf_tuple"); + ASSERT_EQ(skel->bss->test_einval_reserved, -EINVAL, "Test EINVAL for reserved not set to 0"); + ASSERT_EQ(skel->bss->test_einval_netns_id, -EINVAL, "Test EINVAL for netns_id < -1"); + ASSERT_EQ(skel->bss->test_einval_len_opts, -EINVAL, "Test EINVAL for len__opts != NF_BPF_CT_OPTS_SZ"); + ASSERT_EQ(skel->bss->test_eproto_l4proto, -EPROTO, "Test EPROTO for l4proto != TCP or UDP"); + ASSERT_EQ(skel->bss->test_enonet_netns_id, -ENONET, "Test ENONET for bad but valid netns_id"); + ASSERT_EQ(skel->bss->test_enoent_lookup, -ENOENT, "Test ENOENT for failed lookup"); + ASSERT_EQ(skel->bss->test_eafnosupport, -EAFNOSUPPORT, "Test EAFNOSUPPORT for invalid len__tuple"); +end: + test_bpf_nf__destroy(skel); +} + +void test_bpf_nf(void) +{ + if (test__start_subtest("xdp-ct")) + test_bpf_nf_ct(TEST_XDP); + if (test__start_subtest("tc-bpf-ct")) + test_bpf_nf_ct(TEST_TC_BPF); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 8ba53acf9eb4..ec823561b912 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3939,6 +3939,25 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { + .descr = "decl_tag test #15, func, invalid func proto", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_DECL_TAG_ENC(NAME_TBD, 3, 0), /* [2] */ + BTF_FUNC_ENC(NAME_TBD, 8), /* [3] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag\0func"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type_id", +}, +{ .descr = "type_tag test #1", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ @@ -4560,6 +4579,8 @@ static void do_test_file(unsigned int test_num) has_btf_ext = btf_ext != NULL; btf_ext__free(btf_ext); + /* temporary disable LIBBPF_STRICT_MAP_DEFINITIONS to test legacy maps */ + libbpf_set_strict_mode(LIBBPF_STRICT_ALL & ~LIBBPF_STRICT_MAP_DEFINITIONS); obj = bpf_object__open(test->file); err = libbpf_get_error(obj); if (CHECK(err, "obj: %d", err)) @@ -4684,6 +4705,8 @@ skip: fprintf(stderr, "OK"); done: + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + btf__free(btf); free(func_info); bpf_object__close(obj); @@ -6533,7 +6556,7 @@ done: static void do_test_info_raw(unsigned int test_num) { const struct prog_info_raw_test *test = &info_raw_tests[test_num - 1]; - unsigned int raw_btf_size, linfo_str_off, linfo_size; + unsigned int raw_btf_size, linfo_str_off, linfo_size = 0; int btf_fd = -1, prog_fd = -1, err = 0; void *raw_btf, *patched_linfo = NULL; const char *ret_next_str; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index 9e26903f9170..5fce7008d1ff 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -148,22 +148,38 @@ static void test_btf_dump_incremental(void) /* First, generate BTF corresponding to the following C code: * - * enum { VAL = 1 }; + * enum x; + * + * enum x { X = 1 }; + * + * enum { Y = 1 }; + * + * struct s; * * struct s { int x; }; * */ + id = btf__add_enum(btf, "x", 4); + ASSERT_EQ(id, 1, "enum_declaration_id"); + id = btf__add_enum(btf, "x", 4); + ASSERT_EQ(id, 2, "named_enum_id"); + err = btf__add_enum_value(btf, "X", 1); + ASSERT_OK(err, "named_enum_val_ok"); + id = btf__add_enum(btf, NULL, 4); - ASSERT_EQ(id, 1, "enum_id"); - err = btf__add_enum_value(btf, "VAL", 1); - ASSERT_OK(err, "enum_val_ok"); + ASSERT_EQ(id, 3, "anon_enum_id"); + err = btf__add_enum_value(btf, "Y", 1); + ASSERT_OK(err, "anon_enum_val_ok"); id = btf__add_int(btf, "int", 4, BTF_INT_SIGNED); - ASSERT_EQ(id, 2, "int_id"); + ASSERT_EQ(id, 4, "int_id"); + + id = btf__add_fwd(btf, "s", BTF_FWD_STRUCT); + ASSERT_EQ(id, 5, "fwd_id"); id = btf__add_struct(btf, "s", 4); - ASSERT_EQ(id, 3, "struct_id"); - err = btf__add_field(btf, "x", 2, 0, 0); + ASSERT_EQ(id, 6, "struct_id"); + err = btf__add_field(btf, "x", 4, 0, 0); ASSERT_OK(err, "field_ok"); for (i = 1; i < btf__type_cnt(btf); i++) { @@ -173,11 +189,20 @@ static void test_btf_dump_incremental(void) fflush(dump_buf_file); dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */ + ASSERT_STREQ(dump_buf, +"enum x;\n" +"\n" +"enum x {\n" +" X = 1,\n" +"};\n" +"\n" "enum {\n" -" VAL = 1,\n" +" Y = 1,\n" "};\n" "\n" +"struct s;\n" +"\n" "struct s {\n" " int x;\n" "};\n\n", "c_dump1"); @@ -199,10 +224,12 @@ static void test_btf_dump_incremental(void) fseek(dump_buf_file, 0, SEEK_SET); id = btf__add_struct(btf, "s", 4); - ASSERT_EQ(id, 4, "struct_id"); - err = btf__add_field(btf, "x", 1, 0, 0); + ASSERT_EQ(id, 7, "struct_id"); + err = btf__add_field(btf, "x", 2, 0, 0); + ASSERT_OK(err, "field_ok"); + err = btf__add_field(btf, "y", 3, 32, 0); ASSERT_OK(err, "field_ok"); - err = btf__add_field(btf, "s", 3, 32, 0); + err = btf__add_field(btf, "s", 6, 64, 0); ASSERT_OK(err, "field_ok"); for (i = 1; i < btf__type_cnt(btf); i++) { @@ -214,9 +241,10 @@ static void test_btf_dump_incremental(void) dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */ ASSERT_STREQ(dump_buf, "struct s___2 {\n" +" enum x x;\n" " enum {\n" -" VAL___2 = 1,\n" -" } x;\n" +" Y___2 = 1,\n" +" } y;\n" " struct s s;\n" "};\n\n" , "c_dump1"); diff --git a/tools/testing/selftests/bpf/prog_tests/btf_tag.c b/tools/testing/selftests/bpf/prog_tests/btf_tag.c index 88d63e23e35f..071430cd54de 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_tag.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_tag.c @@ -1,19 +1,22 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ #include <test_progs.h> -#include "btf_decl_tag.skel.h" +#include <bpf/btf.h> +#include "test_btf_decl_tag.skel.h" /* struct btf_type_tag_test is referenced in btf_type_tag.skel.h */ struct btf_type_tag_test { int **p; }; #include "btf_type_tag.skel.h" +#include "btf_type_tag_user.skel.h" +#include "btf_type_tag_percpu.skel.h" static void test_btf_decl_tag(void) { - struct btf_decl_tag *skel; + struct test_btf_decl_tag *skel; - skel = btf_decl_tag__open_and_load(); + skel = test_btf_decl_tag__open_and_load(); if (!ASSERT_OK_PTR(skel, "btf_decl_tag")) return; @@ -22,7 +25,7 @@ static void test_btf_decl_tag(void) test__skip(); } - btf_decl_tag__destroy(skel); + test_btf_decl_tag__destroy(skel); } static void test_btf_type_tag(void) @@ -41,10 +44,206 @@ static void test_btf_type_tag(void) btf_type_tag__destroy(skel); } +/* loads vmlinux_btf as well as module_btf. If the caller passes NULL as + * module_btf, it will not load module btf. + * + * Returns 0 on success. + * Return -1 On error. In case of error, the loaded btf will be freed and the + * input parameters will be set to pointing to NULL. + */ +static int load_btfs(struct btf **vmlinux_btf, struct btf **module_btf, + bool needs_vmlinux_tag) +{ + const char *module_name = "bpf_testmod"; + __s32 type_id; + + if (!env.has_testmod) { + test__skip(); + return -1; + } + + *vmlinux_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(*vmlinux_btf, "could not load vmlinux BTF")) + return -1; + + if (!needs_vmlinux_tag) + goto load_module_btf; + + /* skip the test if the vmlinux does not have __user tags */ + type_id = btf__find_by_name_kind(*vmlinux_btf, "user", BTF_KIND_TYPE_TAG); + if (type_id <= 0) { + printf("%s:SKIP: btf_type_tag attribute not in vmlinux btf", __func__); + test__skip(); + goto free_vmlinux_btf; + } + +load_module_btf: + /* skip loading module_btf, if not requested by caller */ + if (!module_btf) + return 0; + + *module_btf = btf__load_module_btf(module_name, *vmlinux_btf); + if (!ASSERT_OK_PTR(*module_btf, "could not load module BTF")) + goto free_vmlinux_btf; + + /* skip the test if the module does not have __user tags */ + type_id = btf__find_by_name_kind(*module_btf, "user", BTF_KIND_TYPE_TAG); + if (type_id <= 0) { + printf("%s:SKIP: btf_type_tag attribute not in %s", __func__, module_name); + test__skip(); + goto free_module_btf; + } + + return 0; + +free_module_btf: + btf__free(*module_btf); +free_vmlinux_btf: + btf__free(*vmlinux_btf); + + *vmlinux_btf = NULL; + if (module_btf) + *module_btf = NULL; + return -1; +} + +static void test_btf_type_tag_mod_user(bool load_test_user1) +{ + struct btf *vmlinux_btf = NULL, *module_btf = NULL; + struct btf_type_tag_user *skel; + int err; + + if (load_btfs(&vmlinux_btf, &module_btf, /*needs_vmlinux_tag=*/false)) + return; + + skel = btf_type_tag_user__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_user")) + goto cleanup; + + bpf_program__set_autoload(skel->progs.test_sys_getsockname, false); + if (load_test_user1) + bpf_program__set_autoload(skel->progs.test_user2, false); + else + bpf_program__set_autoload(skel->progs.test_user1, false); + + err = btf_type_tag_user__load(skel); + ASSERT_ERR(err, "btf_type_tag_user"); + + btf_type_tag_user__destroy(skel); + +cleanup: + btf__free(module_btf); + btf__free(vmlinux_btf); +} + +static void test_btf_type_tag_vmlinux_user(void) +{ + struct btf_type_tag_user *skel; + struct btf *vmlinux_btf = NULL; + int err; + + if (load_btfs(&vmlinux_btf, NULL, /*needs_vmlinux_tag=*/true)) + return; + + skel = btf_type_tag_user__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_user")) + goto cleanup; + + bpf_program__set_autoload(skel->progs.test_user2, false); + bpf_program__set_autoload(skel->progs.test_user1, false); + + err = btf_type_tag_user__load(skel); + ASSERT_ERR(err, "btf_type_tag_user"); + + btf_type_tag_user__destroy(skel); + +cleanup: + btf__free(vmlinux_btf); +} + +static void test_btf_type_tag_mod_percpu(bool load_test_percpu1) +{ + struct btf *vmlinux_btf, *module_btf; + struct btf_type_tag_percpu *skel; + int err; + + if (load_btfs(&vmlinux_btf, &module_btf, /*needs_vmlinux_tag=*/false)) + return; + + skel = btf_type_tag_percpu__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_percpu")) + goto cleanup; + + bpf_program__set_autoload(skel->progs.test_percpu_load, false); + bpf_program__set_autoload(skel->progs.test_percpu_helper, false); + if (load_test_percpu1) + bpf_program__set_autoload(skel->progs.test_percpu2, false); + else + bpf_program__set_autoload(skel->progs.test_percpu1, false); + + err = btf_type_tag_percpu__load(skel); + ASSERT_ERR(err, "btf_type_tag_percpu"); + + btf_type_tag_percpu__destroy(skel); + +cleanup: + btf__free(module_btf); + btf__free(vmlinux_btf); +} + +static void test_btf_type_tag_vmlinux_percpu(bool load_test) +{ + struct btf_type_tag_percpu *skel; + struct btf *vmlinux_btf = NULL; + int err; + + if (load_btfs(&vmlinux_btf, NULL, /*needs_vmlinux_tag=*/true)) + return; + + skel = btf_type_tag_percpu__open(); + if (!ASSERT_OK_PTR(skel, "btf_type_tag_percpu")) + goto cleanup; + + bpf_program__set_autoload(skel->progs.test_percpu2, false); + bpf_program__set_autoload(skel->progs.test_percpu1, false); + if (load_test) { + bpf_program__set_autoload(skel->progs.test_percpu_helper, false); + + err = btf_type_tag_percpu__load(skel); + ASSERT_ERR(err, "btf_type_tag_percpu_load"); + } else { + bpf_program__set_autoload(skel->progs.test_percpu_load, false); + + err = btf_type_tag_percpu__load(skel); + ASSERT_OK(err, "btf_type_tag_percpu_helper"); + } + + btf_type_tag_percpu__destroy(skel); + +cleanup: + btf__free(vmlinux_btf); +} + void test_btf_tag(void) { if (test__start_subtest("btf_decl_tag")) test_btf_decl_tag(); if (test__start_subtest("btf_type_tag")) test_btf_type_tag(); + + if (test__start_subtest("btf_type_tag_user_mod1")) + test_btf_type_tag_mod_user(true); + if (test__start_subtest("btf_type_tag_user_mod2")) + test_btf_type_tag_mod_user(false); + if (test__start_subtest("btf_type_tag_sys_user_vmlinux")) + test_btf_type_tag_vmlinux_user(); + + if (test__start_subtest("btf_type_tag_percpu_mod1")) + test_btf_type_tag_mod_percpu(true); + if (test__start_subtest("btf_type_tag_percpu_mod2")) + test_btf_type_tag_mod_percpu(false); + if (test__start_subtest("btf_type_tag_percpu_vmlinux_load")) + test_btf_type_tag_vmlinux_percpu(true); + if (test__start_subtest("btf_type_tag_percpu_vmlinux_helper")) + test_btf_type_tag_vmlinux_percpu(false); } diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c index 858916d11e2e..9367bd2f0ae1 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c @@ -14,7 +14,7 @@ static int prog_load(void) BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = 1 */ BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); return bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, prog, insns_cnt, "GPL", 0, diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c index d3e8f729c623..db0b7bac78d1 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -63,7 +63,7 @@ static int prog_load_cnt(int verdict, int val) BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); int ret; ret = bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, @@ -194,14 +194,14 @@ void serial_test_cgroup_attach_multi(void) attach_opts.flags = BPF_F_ALLOW_OVERRIDE | BPF_F_REPLACE; attach_opts.replace_prog_fd = allow_prog[0]; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_override", "unexpected success\n")) goto err; CHECK_FAIL(errno != EINVAL); attach_opts.flags = BPF_F_REPLACE; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_no_multi", "unexpected success\n")) goto err; @@ -209,7 +209,7 @@ void serial_test_cgroup_attach_multi(void) attach_opts.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE; attach_opts.replace_prog_fd = -1; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_bad_fd", "unexpected success\n")) goto err; @@ -217,7 +217,7 @@ void serial_test_cgroup_attach_multi(void) /* replacing a program that is not attached to cgroup should fail */ attach_opts.replace_prog_fd = allow_prog[3]; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_no_ent", "unexpected success\n")) goto err; @@ -225,14 +225,14 @@ void serial_test_cgroup_attach_multi(void) /* replace 1st from the top program */ attach_opts.replace_prog_fd = allow_prog[0]; - if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "prog_replace", "errno=%d\n", errno)) goto err; /* replace program with itself */ attach_opts.replace_prog_fd = allow_prog[6]; - if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "prog_replace", "errno=%d\n", errno)) goto err; diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c index 356547e849e2..9421a5b7f4e1 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c @@ -16,7 +16,7 @@ static int prog_load(int verdict) BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */ BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); return bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB, prog, insns_cnt, "GPL", 0, diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c new file mode 100644 index 000000000000..0b47c3c000c7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <test_progs.h> +#include <cgroup_helpers.h> +#include <network_helpers.h> + +#include "cgroup_getset_retval_setsockopt.skel.h" +#include "cgroup_getset_retval_getsockopt.skel.h" + +#define SOL_CUSTOM 0xdeadbeef + +static int zero; + +static void test_setsockopt_set(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, assert that + * we actually get that error when we run setsockopt() + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_set_and_get(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, and one that gets the + * previously set errno. Assert that we get the same errno back. + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EUNATCH, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_default_zero(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that gets the previously set errno. + * Assert that, without anything setting one, we get 0. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_OK(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_default_zero_and_set(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_get_retval = NULL, *link_set_eunatch = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that gets the previously set errno, and then + * one that sets the errno to EUNATCH. Assert that the get does not + * see EUNATCH set later, and does not prevent EUNATCH from being set. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + bpf_link__destroy(link_set_eunatch); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_set_eisconn = NULL; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, then one that sets EISCONN, + * and then one that gets the exported errno. Assert both the syscall + * and the helper sees the last set errno. + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EISCONN, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EISCONN, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_set_eisconn); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_legacy_eperm(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_legacy_eperm = NULL, *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that return a reject without setting errno + * (legacy reject), and one that gets the errno. Assert that for + * backward compatibility the syscall result in EPERM, and this + * is also visible to the helper. + */ + link_legacy_eperm = bpf_program__attach_cgroup(obj->progs.legacy_eperm, + cgroup_fd); + if (!ASSERT_OK_PTR(link_legacy_eperm, "cg-attach-legacy_eperm")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EPERM, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EPERM, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_legacy_eperm); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_legacy_no_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_legacy_eperm = NULL; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, then one that return a reject + * without setting errno, and then one that gets the exported errno. + * Assert both the syscall and the helper's errno are unaffected by + * the second prog (i.e. legacy rejects does not override the errno + * to EPERM). + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_legacy_eperm = bpf_program__attach_cgroup(obj->progs.legacy_eperm, + cgroup_fd); + if (!ASSERT_OK_PTR(link_legacy_eperm, "cg-attach-legacy_eperm")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EUNATCH, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_legacy_eperm); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_getsockopt_get(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_get_retval = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that gets previously set errno. Assert that the + * error from kernel is in both ctx_retval_value and retval_value. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EOPNOTSUPP, "getsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EOPNOTSUPP, "retval_value")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->ctx_retval_value, -EOPNOTSUPP, "ctx_retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +static void test_getsockopt_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_set_eisconn = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that sets retval to -EISCONN. Assert that this + * overrides the value from kernel. + */ + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + + if (!ASSERT_ERR(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EISCONN, "getsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eisconn); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +static void test_getsockopt_retval_sync(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_set_eisconn = NULL, *link_clear_retval = NULL; + struct bpf_link *link_get_retval = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that sets retval to -EISCONN, and one that clears + * ctx retval. Assert that the clearing ctx retval is synced to helper + * and clears any errors both from kernel and BPF.. + */ + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + link_clear_retval = bpf_program__attach_cgroup(obj->progs.clear_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_clear_retval, "cg-attach-clear_retval")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_OK(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->ctx_retval_value, 0, "ctx_retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eisconn); + bpf_link__destroy(link_clear_retval); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +void test_cgroup_getset_retval(void) +{ + int cgroup_fd = -1; + int sock_fd = -1; + + cgroup_fd = test__join_cgroup("/cgroup_getset_retval"); + if (!ASSERT_GE(cgroup_fd, 0, "cg-create")) + goto close_fd; + + sock_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 0, 0); + if (!ASSERT_GE(sock_fd, 0, "start-server")) + goto close_fd; + + if (test__start_subtest("setsockopt-set")) + test_setsockopt_set(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-set_and_get")) + test_setsockopt_set_and_get(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-default_zero")) + test_setsockopt_default_zero(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-default_zero_and_set")) + test_setsockopt_default_zero_and_set(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-override")) + test_setsockopt_override(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-legacy_eperm")) + test_setsockopt_legacy_eperm(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-legacy_no_override")) + test_setsockopt_legacy_no_override(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-get")) + test_getsockopt_get(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-override")) + test_getsockopt_override(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-retval_sync")) + test_getsockopt_retval_sync(cgroup_fd, sock_fd); + +close_fd: + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index f73e6e36b74d..12f4395f18b3 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -79,28 +79,21 @@ static void test_check_mtu_run_xdp(struct test_check_mtu *skel, struct bpf_program *prog, __u32 mtu_expect) { - const char *prog_name = bpf_program__name(prog); int retval_expect = XDP_PASS; __u32 mtu_result = 0; char buf[256] = {}; - int err; - struct bpf_prog_test_run_attr tattr = { + int err, prog_fd = bpf_program__fd(prog); + LIBBPF_OPTS(bpf_test_run_opts, topts, .repeat = 1, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .data_out = buf, .data_size_out = sizeof(buf), - .prog_fd = bpf_program__fd(prog), - }; - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != 0, "bpf_prog_test_run", - "prog_name:%s (err %d errno %d retval %d)\n", - prog_name, err, errno, tattr.retval); + ); - CHECK(tattr.retval != retval_expect, "retval", - "progname:%s unexpected retval=%d expected=%d\n", - prog_name, tattr.retval, retval_expect); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, retval_expect, "retval"); /* Extract MTU that BPF-prog got */ mtu_result = skel->bss->global_bpf_mtu_xdp; @@ -139,28 +132,21 @@ static void test_check_mtu_run_tc(struct test_check_mtu *skel, struct bpf_program *prog, __u32 mtu_expect) { - const char *prog_name = bpf_program__name(prog); int retval_expect = BPF_OK; __u32 mtu_result = 0; char buf[256] = {}; - int err; - struct bpf_prog_test_run_attr tattr = { - .repeat = 1, + int err, prog_fd = bpf_program__fd(prog); + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .data_out = buf, .data_size_out = sizeof(buf), - .prog_fd = bpf_program__fd(prog), - }; - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != 0, "bpf_prog_test_run", - "prog_name:%s (err %d errno %d retval %d)\n", - prog_name, err, errno, tattr.retval); + .repeat = 1, + ); - CHECK(tattr.retval != retval_expect, "retval", - "progname:%s unexpected retval=%d expected=%d\n", - prog_name, tattr.retval, retval_expect); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, retval_expect, "retval"); /* Extract MTU that BPF-prog got */ mtu_result = skel->bss->global_bpf_mtu_tc; diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c index e075d03ab630..224f016b0a53 100644 --- a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c @@ -161,7 +161,7 @@ static socklen_t prepare_addr(struct sockaddr_storage *addr, int family) } } -static bool was_decapsulated(struct bpf_prog_test_run_attr *tattr) +static bool was_decapsulated(struct bpf_test_run_opts *tattr) { return tattr->data_size_out < tattr->data_size_in; } @@ -367,12 +367,12 @@ static void close_fds(int *fds, int n) static void test_cls_redirect_common(struct bpf_program *prog) { - struct bpf_prog_test_run_attr tattr = {}; + LIBBPF_OPTS(bpf_test_run_opts, tattr); int families[] = { AF_INET, AF_INET6 }; struct sockaddr_storage ss; struct sockaddr *addr; socklen_t slen; - int i, j, err; + int i, j, err, prog_fd; int servers[__NR_KIND][ARRAY_SIZE(families)] = {}; int conns[__NR_KIND][ARRAY_SIZE(families)] = {}; struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)]; @@ -394,7 +394,7 @@ static void test_cls_redirect_common(struct bpf_program *prog) goto cleanup; } - tattr.prog_fd = bpf_program__fd(prog); + prog_fd = bpf_program__fd(prog); for (i = 0; i < ARRAY_SIZE(tests); i++) { struct test_cfg *test = &tests[i]; @@ -415,7 +415,7 @@ static void test_cls_redirect_common(struct bpf_program *prog) if (CHECK_FAIL(!tattr.data_size_in)) continue; - err = bpf_prog_test_run_xattr(&tattr); + err = bpf_prog_test_run_opts(prog_fd, &tattr); if (CHECK_FAIL(err)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/core_kern.c b/tools/testing/selftests/bpf/prog_tests/core_kern.c index 561c5185d886..6a5a1c019a5d 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_kern.c +++ b/tools/testing/selftests/bpf/prog_tests/core_kern.c @@ -7,8 +7,22 @@ void test_core_kern_lskel(void) { struct core_kern_lskel *skel; + int link_fd; skel = core_kern_lskel__open_and_load(); - ASSERT_OK_PTR(skel, "open_and_load"); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + link_fd = core_kern_lskel__core_relo_proto__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(core_relo_proto)")) + goto cleanup; + + /* trigger tracepoints */ + usleep(1); + ASSERT_TRUE(skel->bss->proto_out[0], "bpf_core_type_exists"); + ASSERT_FALSE(skel->bss->proto_out[1], "!bpf_core_type_exists"); + ASSERT_TRUE(skel->bss->proto_out[2], "bpf_core_type_exists. nested"); + +cleanup: core_kern_lskel__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/core_kern_overflow.c b/tools/testing/selftests/bpf/prog_tests/core_kern_overflow.c new file mode 100644 index 000000000000..04cc145bc26a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_kern_overflow.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "test_progs.h" +#include "core_kern_overflow.lskel.h" + +void test_core_kern_overflow_lskel(void) +{ + struct core_kern_overflow_lskel *skel; + + skel = core_kern_overflow_lskel__open_and_load(); + if (!ASSERT_NULL(skel, "open_and_load")) + core_kern_overflow_lskel__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index b8bdd1c3efca..f28f75aa9154 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -2,6 +2,7 @@ #include <test_progs.h> #include "progs/core_reloc_types.h" #include "bpf_testmod/bpf_testmod.h" +#include <linux/limits.h> #include <sys/mman.h> #include <sys/syscall.h> #include <bpf/btf.h> @@ -511,7 +512,7 @@ static int __trigger_module_test_read(const struct core_reloc_test_case *test) } -static struct core_reloc_test_case test_cases[] = { +static const struct core_reloc_test_case test_cases[] = { /* validate we can find kernel image and use its BTF for relocs */ { .case_name = "kernel", @@ -836,13 +837,27 @@ static size_t roundup_page(size_t sz) return (sz + page_size - 1) / page_size * page_size; } -void test_core_reloc(void) +static int run_btfgen(const char *src_btf, const char *dst_btf, const char *objpath) +{ + char command[4096]; + int n; + + n = snprintf(command, sizeof(command), + "./bpftool gen min_core_btf %s %s %s", + src_btf, dst_btf, objpath); + if (n < 0 || n >= sizeof(command)) + return -1; + + return system(command); +} + +static void run_core_reloc_tests(bool use_btfgen) { const size_t mmap_sz = roundup_page(sizeof(struct data)); DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts); - struct core_reloc_test_case *test_case; + struct core_reloc_test_case *test_case, test_case_copy; const char *tp_name, *probe_name; - int err, i, equal; + int err, i, equal, fd; struct bpf_link *link = NULL; struct bpf_map *data_map; struct bpf_program *prog; @@ -854,7 +869,11 @@ void test_core_reloc(void) my_pid_tgid = getpid() | ((uint64_t)syscall(SYS_gettid) << 32); for (i = 0; i < ARRAY_SIZE(test_cases); i++) { - test_case = &test_cases[i]; + char btf_file[] = "/tmp/core_reloc.btf.XXXXXX"; + + test_case_copy = test_cases[i]; + test_case = &test_case_copy; + if (!test__start_subtest(test_case->case_name)) continue; @@ -863,6 +882,26 @@ void test_core_reloc(void) continue; } + /* generate a "minimal" BTF file and use it as source */ + if (use_btfgen) { + + if (!test_case->btf_src_file || test_case->fails) { + test__skip(); + continue; + } + + fd = mkstemp(btf_file); + if (!ASSERT_GE(fd, 0, "btf_tmp")) + continue; + close(fd); /* we only need the path */ + err = run_btfgen(test_case->btf_src_file, btf_file, + test_case->bpf_obj_file); + if (!ASSERT_OK(err, "run_btfgen")) + continue; + + test_case->btf_src_file = btf_file; + } + if (test_case->setup) { err = test_case->setup(test_case); if (CHECK(err, "test_setup", "test #%d setup failed: %d\n", i, err)) @@ -872,7 +911,7 @@ void test_core_reloc(void) if (test_case->btf_src_file) { err = access(test_case->btf_src_file, R_OK); if (!ASSERT_OK(err, "btf_src_file")) - goto cleanup; + continue; } open_opts.btf_custom_path = test_case->btf_src_file; @@ -954,8 +993,20 @@ cleanup: CHECK_FAIL(munmap(mmap_data, mmap_sz)); mmap_data = NULL; } + if (use_btfgen) + remove(test_case->btf_src_file); bpf_link__destroy(link); link = NULL; bpf_object__close(obj); } } + +void test_core_reloc(void) +{ + run_core_reloc_tests(false); +} + +void test_core_reloc_btfgen(void) +{ + run_core_reloc_tests(true); +} diff --git a/tools/testing/selftests/bpf/prog_tests/custom_sec_handlers.c b/tools/testing/selftests/bpf/prog_tests/custom_sec_handlers.c new file mode 100644 index 000000000000..b2dfc5954aea --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/custom_sec_handlers.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ + +#include <test_progs.h> +#include "test_custom_sec_handlers.skel.h" + +#define COOKIE_ABC1 1 +#define COOKIE_ABC2 2 +#define COOKIE_CUSTOM 3 +#define COOKIE_FALLBACK 4 +#define COOKIE_KPROBE 5 + +static int custom_setup_prog(struct bpf_program *prog, long cookie) +{ + if (cookie == COOKIE_ABC1) + bpf_program__set_autoload(prog, false); + + return 0; +} + +static int custom_prepare_load_prog(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie) +{ + if (cookie == COOKIE_FALLBACK) + opts->prog_flags |= BPF_F_SLEEPABLE; + else if (cookie == COOKIE_ABC1) + ASSERT_FALSE(true, "unexpected preload for abc"); + + return 0; +} + +static int custom_attach_prog(const struct bpf_program *prog, long cookie, + struct bpf_link **link) +{ + switch (cookie) { + case COOKIE_ABC2: + *link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); + return libbpf_get_error(*link); + case COOKIE_CUSTOM: + *link = bpf_program__attach_tracepoint(prog, "syscalls", "sys_enter_nanosleep"); + return libbpf_get_error(*link); + case COOKIE_KPROBE: + case COOKIE_FALLBACK: + /* no auto-attach for SEC("xyz") and SEC("kprobe") */ + *link = NULL; + return 0; + default: + ASSERT_FALSE(true, "unexpected cookie"); + return -EINVAL; + } +} + +static int abc1_id; +static int abc2_id; +static int custom_id; +static int fallback_id; +static int kprobe_id; + +__attribute__((constructor)) +static void register_sec_handlers(void) +{ + LIBBPF_OPTS(libbpf_prog_handler_opts, abc1_opts, + .cookie = COOKIE_ABC1, + .prog_setup_fn = custom_setup_prog, + .prog_prepare_load_fn = custom_prepare_load_prog, + .prog_attach_fn = NULL, + ); + LIBBPF_OPTS(libbpf_prog_handler_opts, abc2_opts, + .cookie = COOKIE_ABC2, + .prog_setup_fn = custom_setup_prog, + .prog_prepare_load_fn = custom_prepare_load_prog, + .prog_attach_fn = custom_attach_prog, + ); + LIBBPF_OPTS(libbpf_prog_handler_opts, custom_opts, + .cookie = COOKIE_CUSTOM, + .prog_setup_fn = NULL, + .prog_prepare_load_fn = NULL, + .prog_attach_fn = custom_attach_prog, + ); + + abc1_id = libbpf_register_prog_handler("abc", BPF_PROG_TYPE_RAW_TRACEPOINT, 0, &abc1_opts); + abc2_id = libbpf_register_prog_handler("abc/", BPF_PROG_TYPE_RAW_TRACEPOINT, 0, &abc2_opts); + custom_id = libbpf_register_prog_handler("custom+", BPF_PROG_TYPE_TRACEPOINT, 0, &custom_opts); +} + +__attribute__((destructor)) +static void unregister_sec_handlers(void) +{ + libbpf_unregister_prog_handler(abc1_id); + libbpf_unregister_prog_handler(abc2_id); + libbpf_unregister_prog_handler(custom_id); +} + +void test_custom_sec_handlers(void) +{ + LIBBPF_OPTS(libbpf_prog_handler_opts, opts, + .prog_setup_fn = custom_setup_prog, + .prog_prepare_load_fn = custom_prepare_load_prog, + .prog_attach_fn = custom_attach_prog, + ); + struct test_custom_sec_handlers* skel; + int err; + + ASSERT_GT(abc1_id, 0, "abc1_id"); + ASSERT_GT(abc2_id, 0, "abc2_id"); + ASSERT_GT(custom_id, 0, "custom_id"); + + /* override libbpf's handle of SEC("kprobe/...") but also allow pure + * SEC("kprobe") due to "kprobe+" specifier. Register it as + * TRACEPOINT, just for fun. + */ + opts.cookie = COOKIE_KPROBE; + kprobe_id = libbpf_register_prog_handler("kprobe+", BPF_PROG_TYPE_TRACEPOINT, 0, &opts); + /* fallback treats everything as BPF_PROG_TYPE_SYSCALL program to test + * setting custom BPF_F_SLEEPABLE bit in preload handler + */ + opts.cookie = COOKIE_FALLBACK; + fallback_id = libbpf_register_prog_handler(NULL, BPF_PROG_TYPE_SYSCALL, 0, &opts); + + if (!ASSERT_GT(fallback_id, 0, "fallback_id") /* || !ASSERT_GT(kprobe_id, 0, "kprobe_id")*/) { + if (fallback_id > 0) + libbpf_unregister_prog_handler(fallback_id); + if (kprobe_id > 0) + libbpf_unregister_prog_handler(kprobe_id); + return; + } + + /* open skeleton and validate assumptions */ + skel = test_custom_sec_handlers__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__type(skel->progs.abc1), BPF_PROG_TYPE_RAW_TRACEPOINT, "abc1_type"); + ASSERT_FALSE(bpf_program__autoload(skel->progs.abc1), "abc1_autoload"); + + ASSERT_EQ(bpf_program__type(skel->progs.abc2), BPF_PROG_TYPE_RAW_TRACEPOINT, "abc2_type"); + ASSERT_EQ(bpf_program__type(skel->progs.custom1), BPF_PROG_TYPE_TRACEPOINT, "custom1_type"); + ASSERT_EQ(bpf_program__type(skel->progs.custom2), BPF_PROG_TYPE_TRACEPOINT, "custom2_type"); + ASSERT_EQ(bpf_program__type(skel->progs.kprobe1), BPF_PROG_TYPE_TRACEPOINT, "kprobe1_type"); + ASSERT_EQ(bpf_program__type(skel->progs.xyz), BPF_PROG_TYPE_SYSCALL, "xyz_type"); + + skel->rodata->my_pid = getpid(); + + /* now attempt to load everything */ + err = test_custom_sec_handlers__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + /* now try to auto-attach everything */ + err = test_custom_sec_handlers__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + skel->links.xyz = bpf_program__attach(skel->progs.kprobe1); + ASSERT_EQ(errno, EOPNOTSUPP, "xyz_attach_err"); + ASSERT_ERR_PTR(skel->links.xyz, "xyz_attach"); + + /* trigger programs */ + usleep(1); + + /* SEC("abc") is set to not auto-loaded */ + ASSERT_FALSE(skel->bss->abc1_called, "abc1_called"); + ASSERT_TRUE(skel->bss->abc2_called, "abc2_called"); + ASSERT_TRUE(skel->bss->custom1_called, "custom1_called"); + ASSERT_TRUE(skel->bss->custom2_called, "custom2_called"); + /* SEC("kprobe") shouldn't be auto-attached */ + ASSERT_FALSE(skel->bss->kprobe1_called, "kprobe1_called"); + /* SEC("xyz") shouldn't be auto-attached */ + ASSERT_FALSE(skel->bss->xyz_called, "xyz_called"); + +cleanup: + test_custom_sec_handlers__destroy(skel); + + ASSERT_OK(libbpf_unregister_prog_handler(fallback_id), "unregister_fallback"); + ASSERT_OK(libbpf_unregister_prog_handler(kprobe_id), "unregister_kprobe"); +} diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c index cbaa44ffb8c6..5aa52cc31dc2 100644 --- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c +++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c @@ -26,10 +26,10 @@ static void test_dummy_st_ops_attach(void) static void test_dummy_init_ret_value(void) { __u64 args[1] = {0}; - struct bpf_prog_test_run_attr attr = { - .ctx_size_in = sizeof(args), + LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, - }; + .ctx_size_in = sizeof(args), + ); struct dummy_st_ops *skel; int fd, err; @@ -38,8 +38,7 @@ static void test_dummy_init_ret_value(void) return; fd = bpf_program__fd(skel->progs.test_1); - attr.prog_fd = fd; - err = bpf_prog_test_run_xattr(&attr); + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); ASSERT_EQ(attr.retval, 0xf2f3f4f5, "test_ret"); @@ -53,10 +52,10 @@ static void test_dummy_init_ptr_arg(void) .val = exp_retval, }; __u64 args[1] = {(unsigned long)&in_state}; - struct bpf_prog_test_run_attr attr = { - .ctx_size_in = sizeof(args), + LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, - }; + .ctx_size_in = sizeof(args), + ); struct dummy_st_ops *skel; int fd, err; @@ -65,8 +64,7 @@ static void test_dummy_init_ptr_arg(void) return; fd = bpf_program__fd(skel->progs.test_1); - attr.prog_fd = fd; - err = bpf_prog_test_run_xattr(&attr); + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret"); ASSERT_EQ(attr.retval, exp_retval, "test_ret"); @@ -77,10 +75,10 @@ static void test_dummy_init_ptr_arg(void) static void test_dummy_multiple_args(void) { __u64 args[5] = {0, -100, 0x8a5f, 'c', 0x1234567887654321ULL}; - struct bpf_prog_test_run_attr attr = { - .ctx_size_in = sizeof(args), + LIBBPF_OPTS(bpf_test_run_opts, attr, .ctx_in = args, - }; + .ctx_size_in = sizeof(args), + ); struct dummy_st_ops *skel; int fd, err; size_t i; @@ -91,8 +89,7 @@ static void test_dummy_multiple_args(void) return; fd = bpf_program__fd(skel->progs.test_2); - attr.prog_fd = fd; - err = bpf_prog_test_run_xattr(&attr); + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); for (i = 0; i < ARRAY_SIZE(args); i++) { snprintf(name, sizeof(name), "arg %zu", i); diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 4374ac8a8a91..130f5b82d2e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -9,38 +9,34 @@ void test_fentry_fexit(void) struct fentry_test_lskel *fentry_skel = NULL; struct fexit_test_lskel *fexit_skel = NULL; __u64 *fentry_res, *fexit_res; - __u32 duration = 0, retval; int err, prog_fd, i; + LIBBPF_OPTS(bpf_test_run_opts, topts); fentry_skel = fentry_test_lskel__open_and_load(); - if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n")) + if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) goto close_prog; fexit_skel = fexit_test_lskel__open_and_load(); - if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n")) + if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) goto close_prog; err = fentry_test_lskel__attach(fentry_skel); - if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err)) + if (!ASSERT_OK(err, "fentry_attach")) goto close_prog; err = fexit_test_lskel__attach(fexit_skel); - if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) + if (!ASSERT_OK(err, "fexit_attach")) goto close_prog; prog_fd = fexit_skel->progs.test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6 test_run"); + ASSERT_OK(topts.retval, "ipv6 test retval"); fentry_res = (__u64 *)fentry_skel->bss; fexit_res = (__u64 *)fexit_skel->bss; printf("%lld\n", fentry_skel->bss->test1_result); for (i = 0; i < 8; i++) { - CHECK(fentry_res[i] != 1, "result", - "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]); - CHECK(fexit_res[i] != 1, "result", - "fexit_test%d failed err %lld\n", i + 1, fexit_res[i]); + ASSERT_EQ(fentry_res[i], 1, "fentry result"); + ASSERT_EQ(fexit_res[i], 1, "fexit result"); } close_prog: diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index 12921b3850d2..c0d1d61d5f66 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -6,9 +6,9 @@ static int fentry_test(struct fentry_test_lskel *fentry_skel) { int err, prog_fd, i; - __u32 duration = 0, retval; int link_fd; __u64 *result; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = fentry_test_lskel__attach(fentry_skel); if (!ASSERT_OK(err, "fentry_attach")) @@ -20,10 +20,9 @@ static int fentry_test(struct fentry_test_lskel *fentry_skel) return -1; prog_fd = fentry_skel->progs.test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); result = (__u64 *)fentry_skel->bss; for (i = 0; i < sizeof(*fentry_skel->bss) / sizeof(__u64); i++) { diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index c52f99f6a909..d9aad15e0d24 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -58,12 +58,17 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, test_cb cb) { struct bpf_object *obj = NULL, *tgt_obj; - __u32 retval, tgt_prog_id, info_len; + __u32 tgt_prog_id, info_len; struct bpf_prog_info prog_info = {}; struct bpf_program **prog = NULL, *p; struct bpf_link **link = NULL; int err, tgt_fd, i; struct btf *btf; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v6, + .data_size_in = sizeof(pkt_v6), + .repeat = 1, + ); err = bpf_prog_test_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, &tgt_obj, &tgt_fd); @@ -132,7 +137,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, &link_info, &info_len); ASSERT_OK(err, "link_fd_get_info"); ASSERT_EQ(link_info.tracing.attach_type, - bpf_program__get_expected_attach_type(prog[i]), + bpf_program__expected_attach_type(prog[i]), "link_attach_type"); ASSERT_EQ(link_info.tracing.target_obj_id, tgt_prog_id, "link_tgt_obj_id"); ASSERT_EQ(link_info.tracing.target_btf_id, btf_id, "link_tgt_btf_id"); @@ -147,10 +152,9 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, if (!run_prog) goto close_prog; - err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6), - NULL, NULL, &retval, NULL); + err = bpf_prog_test_run_opts(tgt_fd, &topts); ASSERT_OK(err, "prog_run"); - ASSERT_EQ(retval, 0, "prog_run_ret"); + ASSERT_EQ(topts.retval, 0, "prog_run_ret"); if (check_data_map(obj, prog_cnt, false)) goto close_prog; @@ -225,29 +229,31 @@ static int test_second_attach(struct bpf_object *obj) const char *tgt_obj_file = "./test_pkt_access.o"; struct bpf_program *prog = NULL; struct bpf_object *tgt_obj; - __u32 duration = 0, retval; struct bpf_link *link; int err = 0, tgt_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v6, + .data_size_in = sizeof(pkt_v6), + .repeat = 1, + ); prog = bpf_object__find_program_by_name(obj, prog_name); - if (CHECK(!prog, "find_prog", "prog %s not found\n", prog_name)) + if (!ASSERT_OK_PTR(prog, "find_prog")) return -ENOENT; err = bpf_prog_test_load(tgt_obj_file, BPF_PROG_TYPE_UNSPEC, &tgt_obj, &tgt_fd); - if (CHECK(err, "second_prog_load", "file %s err %d errno %d\n", - tgt_obj_file, err, errno)) + if (!ASSERT_OK(err, "second_prog_load")) return err; link = bpf_program__attach_freplace(prog, tgt_fd, tgt_name); if (!ASSERT_OK_PTR(link, "second_link")) goto out; - err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6), - NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) + err = bpf_prog_test_run_opts(tgt_fd, &topts); + if (!ASSERT_OK(err, "ipv6 test_run")) + goto out; + if (!ASSERT_OK(topts.retval, "ipv6 retval")) goto out; err = check_data_map(obj, 1, true); diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c index e4cede6b4b2d..3ee2107bbf7a 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c @@ -10,9 +10,7 @@ void test_fexit_stress(void) char test_skb[128] = {}; int fexit_fd[CNT] = {}; int link_fd[CNT] = {}; - __u32 duration = 0; char error[4096]; - __u32 prog_ret; int err, i, filter_fd; const struct bpf_insn trace_program[] = { @@ -36,9 +34,15 @@ void test_fexit_stress(void) .log_size = sizeof(error), ); + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = test_skb, + .data_size_in = sizeof(test_skb), + .repeat = 1, + ); + err = libbpf_find_vmlinux_btf_id("bpf_fentry_test1", trace_opts.expected_attach_type); - if (CHECK(err <= 0, "find_vmlinux_btf_id", "failed: %d\n", err)) + if (!ASSERT_GT(err, 0, "find_vmlinux_btf_id")) goto out; trace_opts.attach_btf_id = err; @@ -47,24 +51,20 @@ void test_fexit_stress(void) trace_program, sizeof(trace_program) / sizeof(struct bpf_insn), &trace_opts); - if (CHECK(fexit_fd[i] < 0, "fexit loaded", - "failed: %d errno %d\n", fexit_fd[i], errno)) + if (!ASSERT_GE(fexit_fd[i], 0, "fexit load")) goto out; link_fd[i] = bpf_raw_tracepoint_open(NULL, fexit_fd[i]); - if (CHECK(link_fd[i] < 0, "fexit attach failed", - "prog %d failed: %d err %d\n", i, link_fd[i], errno)) + if (!ASSERT_GE(link_fd[i], 0, "fexit attach")) goto out; } filter_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", skb_program, sizeof(skb_program) / sizeof(struct bpf_insn), &skb_opts); - if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n", - filter_fd, errno)) + if (!ASSERT_GE(filter_fd, 0, "test_program_loaded")) goto out; - err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, - 0, &prog_ret, 0); + err = bpf_prog_test_run_opts(filter_fd, &topts); close(filter_fd); CHECK_FAIL(err); out: diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index d4887d8bb396..101b7343036b 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -6,9 +6,9 @@ static int fexit_test(struct fexit_test_lskel *fexit_skel) { int err, prog_fd, i; - __u32 duration = 0, retval; int link_fd; __u64 *result; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = fexit_test_lskel__attach(fexit_skel); if (!ASSERT_OK(err, "fexit_attach")) @@ -20,10 +20,9 @@ static int fexit_test(struct fexit_test_lskel *fexit_skel) return -1; prog_fd = fexit_skel->progs.test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); result = (__u64 *)fexit_skel->bss; for (i = 0; i < sizeof(*fexit_skel->bss) / sizeof(__u64); i++) { diff --git a/tools/testing/selftests/bpf/prog_tests/find_vma.c b/tools/testing/selftests/bpf/prog_tests/find_vma.c index b74b3c0c555a..5165b38f0e59 100644 --- a/tools/testing/selftests/bpf/prog_tests/find_vma.c +++ b/tools/testing/selftests/bpf/prog_tests/find_vma.c @@ -7,12 +7,14 @@ #include "find_vma_fail1.skel.h" #include "find_vma_fail2.skel.h" -static void test_and_reset_skel(struct find_vma *skel, int expected_find_zero_ret) +static void test_and_reset_skel(struct find_vma *skel, int expected_find_zero_ret, bool need_test) { - ASSERT_EQ(skel->bss->found_vm_exec, 1, "found_vm_exec"); - ASSERT_EQ(skel->data->find_addr_ret, 0, "find_addr_ret"); - ASSERT_EQ(skel->data->find_zero_ret, expected_find_zero_ret, "find_zero_ret"); - ASSERT_OK_PTR(strstr(skel->bss->d_iname, "test_progs"), "find_test_progs"); + if (need_test) { + ASSERT_EQ(skel->bss->found_vm_exec, 1, "found_vm_exec"); + ASSERT_EQ(skel->data->find_addr_ret, 0, "find_addr_ret"); + ASSERT_EQ(skel->data->find_zero_ret, expected_find_zero_ret, "find_zero_ret"); + ASSERT_OK_PTR(strstr(skel->bss->d_iname, "test_progs"), "find_test_progs"); + } skel->bss->found_vm_exec = 0; skel->data->find_addr_ret = -1; @@ -30,17 +32,26 @@ static int open_pe(void) attr.type = PERF_TYPE_HARDWARE; attr.config = PERF_COUNT_HW_CPU_CYCLES; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, PERF_FLAG_FD_CLOEXEC); return pfd >= 0 ? pfd : -errno; } +static bool find_vma_pe_condition(struct find_vma *skel) +{ + return skel->bss->found_vm_exec == 0 || + skel->data->find_addr_ret != 0 || + skel->data->find_zero_ret == -1 || + strcmp(skel->bss->d_iname, "test_progs") != 0; +} + static void test_find_vma_pe(struct find_vma *skel) { struct bpf_link *link = NULL; volatile int j = 0; int pfd, i; + const int one_bn = 1000000000; pfd = open_pe(); if (pfd < 0) { @@ -57,10 +68,10 @@ static void test_find_vma_pe(struct find_vma *skel) if (!ASSERT_OK_PTR(link, "attach_perf_event")) goto cleanup; - for (i = 0; i < 1000000; ++i) + for (i = 0; i < one_bn && find_vma_pe_condition(skel); ++i) ++j; - test_and_reset_skel(skel, -EBUSY /* in nmi, irq_work is busy */); + test_and_reset_skel(skel, -EBUSY /* in nmi, irq_work is busy */, i == one_bn); cleanup: bpf_link__destroy(link); close(pfd); @@ -75,7 +86,7 @@ static void test_find_vma_kprobe(struct find_vma *skel) return; getpgid(skel->bss->target_pid); - test_and_reset_skel(skel, -ENOENT /* could not find vma for ptr 0 */); + test_and_reset_skel(skel, -ENOENT /* could not find vma for ptr 0 */, true); } static void test_illegal_write_vma(void) @@ -108,7 +119,6 @@ void serial_test_find_vma(void) skel->bss->addr = (__u64)(uintptr_t)test_find_vma_pe; test_find_vma_pe(skel); - usleep(100000); /* allow the irq_work to finish */ test_find_vma_kprobe(skel); find_vma__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index ac54e3f91d42..0c1661ea996e 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -13,8 +13,9 @@ #endif #define CHECK_FLOW_KEYS(desc, got, expected) \ - CHECK_ATTR(memcmp(&got, &expected, sizeof(got)) != 0, \ + _CHECK(memcmp(&got, &expected, sizeof(got)) != 0, \ desc, \ + topts.duration, \ "nhoff=%u/%u " \ "thoff=%u/%u " \ "addr_proto=0x%x/0x%x " \ @@ -457,7 +458,7 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) if (map_fd < 0) return -1; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -487,7 +488,7 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *keys) /* Keep in sync with 'flags' from eth_get_headlen. */ __u32 eth_get_headlen_flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG; - struct bpf_prog_test_run_attr tattr = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts); struct bpf_flow_keys flow_keys = {}; __u32 key = (__u32)(tests[i].keys.sport) << 16 | tests[i].keys.dport; @@ -503,13 +504,12 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *keys) CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno); err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys); - CHECK_ATTR(err, tests[i].name, "bpf_map_lookup_elem %d\n", err); + ASSERT_OK(err, "bpf_map_lookup_elem"); - CHECK_ATTR(err, tests[i].name, "skb-less err %d\n", err); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); err = bpf_map_delete_elem(keys_fd, &key); - CHECK_ATTR(err, tests[i].name, "bpf_map_delete_elem %d\n", err); + ASSERT_OK(err, "bpf_map_delete_elem"); } } @@ -573,27 +573,24 @@ void test_flow_dissector(void) for (i = 0; i < ARRAY_SIZE(tests); i++) { struct bpf_flow_keys flow_keys; - struct bpf_prog_test_run_attr tattr = { - .prog_fd = prog_fd, + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &tests[i].pkt, .data_size_in = sizeof(tests[i].pkt), .data_out = &flow_keys, - }; + ); static struct bpf_flow_keys ctx = {}; if (tests[i].flags) { - tattr.ctx_in = &ctx; - tattr.ctx_size_in = sizeof(ctx); + topts.ctx_in = &ctx; + topts.ctx_size_in = sizeof(ctx); ctx.flags = tests[i].flags; } - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) || - err || tattr.retval != 1, - tests[i].name, - "err %d errno %d retval %d duration %d size %u/%zu\n", - err, errno, tattr.retval, tattr.duration, - tattr.data_size_out, sizeof(flow_keys)); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 1, "test_run retval"); + ASSERT_EQ(topts.data_size_out, sizeof(flow_keys), + "test_run data_size_out"); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); } diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c index 93ac3f28226c..36afb409c25f 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c @@ -5,7 +5,6 @@ void serial_test_flow_dissector_load_bytes(void) { struct bpf_flow_keys flow_keys; - __u32 duration = 0, retval, size; struct bpf_insn prog[] = { // BPF_REG_1 - 1st argument: context // BPF_REG_2 - 2nd argument: offset, start at first byte @@ -27,22 +26,25 @@ void serial_test_flow_dissector_load_bytes(void) BPF_EXIT_INSN(), }; int fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = &flow_keys, + .data_size_out = sizeof(flow_keys), + .repeat = 1, + ); /* make sure bpf_skb_load_bytes is not allowed from skb-less context */ fd = bpf_test_load_program(BPF_PROG_TYPE_FLOW_DISSECTOR, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); - CHECK(fd < 0, - "flow_dissector-bpf_skb_load_bytes-load", - "fd %d errno %d\n", - fd, errno); + ASSERT_GE(fd, 0, "bpf_test_load_program good fd"); - err = bpf_prog_test_run(fd, 1, &pkt_v4, sizeof(pkt_v4), - &flow_keys, &size, &retval, &duration); - CHECK(size != sizeof(flow_keys) || err || retval != 1, - "flow_dissector-bpf_skb_load_bytes", - "err %d errno %d retval %d duration %d size %u/%zu\n", - err, errno, retval, duration, size, sizeof(flow_keys)); + err = bpf_prog_test_run_opts(fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.data_size_out, sizeof(flow_keys), + "test_run data_size_out"); + ASSERT_EQ(topts.retval, 1, "test_run retval"); if (fd >= -1) close(fd); diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c index 68eb12a287d4..044df13ee069 100644 --- a/tools/testing/selftests/bpf/prog_tests/for_each.c +++ b/tools/testing/selftests/bpf/prog_tests/for_each.c @@ -12,8 +12,13 @@ static void test_hash_map(void) int i, err, hashmap_fd, max_entries, percpu_map_fd; struct for_each_hash_map_elem *skel; __u64 *percpu_valbuf = NULL; - __u32 key, num_cpus, retval; + __u32 key, num_cpus; __u64 val; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = for_each_hash_map_elem__open_and_load(); if (!ASSERT_OK_PTR(skel, "for_each_hash_map_elem__open_and_load")) @@ -42,11 +47,10 @@ static void test_hash_map(void) if (!ASSERT_OK(err, "percpu_map_update")) goto out; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.test_pkt_access), - 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, - &retval, &duration); - if (CHECK(err || retval, "ipv4", "err %d errno %d retval %d\n", - err, errno, retval)) + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts); + duration = topts.duration; + if (CHECK(err || topts.retval, "ipv4", "err %d errno %d retval %d\n", + err, errno, topts.retval)) goto out; ASSERT_EQ(skel->bss->hashmap_output, 4, "hashmap_output"); @@ -69,11 +73,16 @@ out: static void test_array_map(void) { - __u32 key, num_cpus, max_entries, retval; + __u32 key, num_cpus, max_entries; int i, arraymap_fd, percpu_map_fd, err; struct for_each_array_map_elem *skel; __u64 *percpu_valbuf = NULL; __u64 val, expected_total; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = for_each_array_map_elem__open_and_load(); if (!ASSERT_OK_PTR(skel, "for_each_array_map_elem__open_and_load")) @@ -106,11 +115,10 @@ static void test_array_map(void) if (!ASSERT_OK(err, "percpu_map_update")) goto out; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.test_pkt_access), - 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, - &retval, &duration); - if (CHECK(err || retval, "ipv4", "err %d errno %d retval %d\n", - err, errno, retval)) + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts); + duration = topts.duration; + if (CHECK(err || topts.retval, "ipv4", "err %d errno %d retval %d\n", + err, errno, topts.retval)) goto out; ASSERT_EQ(skel->bss->arraymap_output, expected_total, "array_output"); diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c index 85c427119fe9..28cf63963cb7 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c +++ b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c @@ -5,8 +5,8 @@ void test_get_func_args_test(void) { struct get_func_args_test *skel = NULL; - __u32 duration = 0, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); skel = get_func_args_test__open_and_load(); if (!ASSERT_OK_PTR(skel, "get_func_args_test__open_and_load")) @@ -20,19 +20,17 @@ void test_get_func_args_test(void) * fentry/fexit programs. */ prog_fd = bpf_program__fd(skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); /* This runs bpf_modify_return_test function and triggers * fmod_ret_test and fexit_test programs. */ prog_fd = bpf_program__fd(skel->progs.fmod_ret_test); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 1234, "test_run"); + ASSERT_EQ(topts.retval, 1234, "test_run"); ASSERT_EQ(skel->bss->test1_result, 1, "test1_result"); ASSERT_EQ(skel->bss->test2_result, 1, "test2_result"); diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c index 02a465f36d59..938dbd4d7c2f 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c +++ b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c @@ -5,8 +5,8 @@ void test_get_func_ip_test(void) { struct get_func_ip_test *skel = NULL; - __u32 duration = 0, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts); skel = get_func_ip_test__open(); if (!ASSERT_OK_PTR(skel, "get_func_ip_test__open")) @@ -29,14 +29,12 @@ void test_get_func_ip_test(void) goto cleanup; prog_fd = bpf_program__fd(skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); prog_fd = bpf_program__fd(skel->progs.test5); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); diff --git a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c index 8d5a6023a1bb..5308de1ed478 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c @@ -27,7 +27,7 @@ void test_get_stackid_cannot_attach(void) return; /* override program type */ - bpf_program__set_perf_event(skel->progs.oncpu); + bpf_program__set_type(skel->progs.oncpu, BPF_PROG_TYPE_PERF_EVENT); err = test_stacktrace_build_id__load(skel); if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index 9da131b32e13..027685858925 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -29,7 +29,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) { "relocate .rodata reference", 10, ~0 }, }; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num); CHECK(err || num != tests[i].num, tests[i].name, "err %d result %llx expected %llx\n", @@ -58,7 +58,7 @@ static void test_global_data_string(struct bpf_object *obj, __u32 duration) { "relocate .bss reference", 4, "\0\0hello" }, }; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, str); CHECK(err || memcmp(str, tests[i].str, sizeof(str)), tests[i].name, "err %d result \'%s\' expected \'%s\'\n", @@ -92,7 +92,7 @@ static void test_global_data_struct(struct bpf_object *obj, __u32 duration) { "relocate .data reference", 3, { 41, 0xeeeeefef, 0x2111111111111111ULL, } }, }; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, &val); CHECK(err || memcmp(&val, &tests[i].val, sizeof(val)), tests[i].name, "err %d result { %u, %u, %llu } expected { %u, %u, %llu }\n", @@ -121,7 +121,7 @@ static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration) if (CHECK_FAIL(map_fd < 0)) return; - buff = malloc(bpf_map__def(map)->value_size); + buff = malloc(bpf_map__value_size(map)); if (buff) err = bpf_map_update_elem(map_fd, &zero, buff, 0); free(buff); @@ -132,24 +132,26 @@ static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration) void test_global_data(void) { const char *file = "./test_global_data.o"; - __u32 duration = 0, retval; struct bpf_object *obj; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (CHECK(err, "load program", "error %d loading %s\n", err, file)) + if (!ASSERT_OK(err, "load program")) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "pass global data run", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "pass global data run err"); + ASSERT_OK(topts.retval, "pass global data run retval"); - test_global_data_number(obj, duration); - test_global_data_string(obj, duration); - test_global_data_struct(obj, duration); - test_global_data_rdonly(obj, duration); + test_global_data_number(obj, topts.duration); + test_global_data_string(obj, topts.duration); + test_global_data_struct(obj, topts.duration); + test_global_data_rdonly(obj, topts.duration); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c index 1db86eab101b..57331c606964 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c @@ -20,7 +20,7 @@ void test_global_data_init(void) if (CHECK_FAIL(!map || !bpf_map__is_internal(map))) goto out; - sz = bpf_map__def(map)->value_size; + sz = bpf_map__value_size(map); newval = malloc(sz); if (CHECK_FAIL(!newval)) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/global_func_args.c b/tools/testing/selftests/bpf/prog_tests/global_func_args.c index 93a2439237b0..29039a36cce5 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_func_args.c +++ b/tools/testing/selftests/bpf/prog_tests/global_func_args.c @@ -40,19 +40,21 @@ static void test_global_func_args0(struct bpf_object *obj) void test_global_func_args(void) { const char *file = "./test_global_func_args.o"; - __u32 retval; struct bpf_object *obj; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); if (CHECK(err, "load program", "error %d loading %s\n", err, file)) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "pass global func args run", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_OK(topts.retval, "test_run retval"); test_global_func_args0(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c index ce10d2fc3a6c..1cee6957285e 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c @@ -53,24 +53,24 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) void serial_test_kfree_skb(void) { struct __sk_buff skb = {}; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &pkt_v6, .data_size_in = sizeof(pkt_v6), .ctx_in = &skb, .ctx_size_in = sizeof(skb), - }; + ); struct kfree_skb *skel = NULL; struct bpf_link *link; struct bpf_object *obj; struct perf_buffer *pb = NULL; - int err; + int err, prog_fd; bool passed = false; __u32 duration = 0; const int zero = 0; bool test_ok[2]; err = bpf_prog_test_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS, - &obj, &tattr.prog_fd); + &obj, &prog_fd); if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) return; @@ -100,11 +100,9 @@ void serial_test_kfree_skb(void) goto close_prog; memcpy(skb.cb, &cb, sizeof(cb)); - err = bpf_prog_test_run_xattr(&tattr); - duration = tattr.duration; - CHECK(err || tattr.retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, tattr.retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6 test_run"); + ASSERT_OK(topts.retval, "ipv6 test_run retval"); /* read perf buffer */ err = perf_buffer__poll(pb, 100); diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 7d7445ccc141..c00eb974eb85 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -9,23 +9,31 @@ static void test_main(void) { struct kfunc_call_test_lskel *skel; - int prog_fd, retval, err; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = kfunc_call_test_lskel__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel")) return; prog_fd = skel->progs.kfunc_call_test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test1)"); - ASSERT_EQ(retval, 12, "test1-retval"); + ASSERT_EQ(topts.retval, 12, "test1-retval"); prog_fd = skel->progs.kfunc_call_test2.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test2)"); - ASSERT_EQ(retval, 3, "test2-retval"); + ASSERT_EQ(topts.retval, 3, "test2-retval"); + + prog_fd = skel->progs.kfunc_call_test_ref_btf_id.prog_fd; + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "bpf_prog_test_run(test_ref_btf_id)"); + ASSERT_EQ(topts.retval, 0, "test_ref_btf_id-retval"); kfunc_call_test_lskel__destroy(skel); } @@ -33,17 +41,21 @@ static void test_main(void) static void test_subprog(void) { struct kfunc_call_test_subprog *skel; - int prog_fd, retval, err; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = kfunc_call_test_subprog__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel")) return; prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test1)"); - ASSERT_EQ(retval, 10, "test1-retval"); + ASSERT_EQ(topts.retval, 10, "test1-retval"); ASSERT_NEQ(skel->data->active_res, -1, "active_res"); ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res"); @@ -53,17 +65,21 @@ static void test_subprog(void) static void test_subprog_lskel(void) { struct kfunc_call_test_subprog_lskel *skel; - int prog_fd, retval, err; + int prog_fd, err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); skel = kfunc_call_test_subprog_lskel__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel")) return; prog_fd = skel->progs.kfunc_call_test1.prog_fd; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "bpf_prog_test_run(test1)"); - ASSERT_EQ(retval, 10, "test1-retval"); + ASSERT_EQ(topts.retval, 10, "test1-retval"); ASSERT_NEQ(skel->data->active_res, -1, "active_res"); ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res"); diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c new file mode 100644 index 000000000000..b9876b55fc0c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "kprobe_multi.skel.h" +#include "trace_helpers.h" + +static void kprobe_multi_test_run(struct kprobe_multi *skel, bool test_return) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, prog_fd; + + prog_fd = bpf_program__fd(skel->progs.trigger); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); + + ASSERT_EQ(skel->bss->kprobe_test1_result, 1, "kprobe_test1_result"); + ASSERT_EQ(skel->bss->kprobe_test2_result, 1, "kprobe_test2_result"); + ASSERT_EQ(skel->bss->kprobe_test3_result, 1, "kprobe_test3_result"); + ASSERT_EQ(skel->bss->kprobe_test4_result, 1, "kprobe_test4_result"); + ASSERT_EQ(skel->bss->kprobe_test5_result, 1, "kprobe_test5_result"); + ASSERT_EQ(skel->bss->kprobe_test6_result, 1, "kprobe_test6_result"); + ASSERT_EQ(skel->bss->kprobe_test7_result, 1, "kprobe_test7_result"); + ASSERT_EQ(skel->bss->kprobe_test8_result, 1, "kprobe_test8_result"); + + if (test_return) { + ASSERT_EQ(skel->bss->kretprobe_test1_result, 1, "kretprobe_test1_result"); + ASSERT_EQ(skel->bss->kretprobe_test2_result, 1, "kretprobe_test2_result"); + ASSERT_EQ(skel->bss->kretprobe_test3_result, 1, "kretprobe_test3_result"); + ASSERT_EQ(skel->bss->kretprobe_test4_result, 1, "kretprobe_test4_result"); + ASSERT_EQ(skel->bss->kretprobe_test5_result, 1, "kretprobe_test5_result"); + ASSERT_EQ(skel->bss->kretprobe_test6_result, 1, "kretprobe_test6_result"); + ASSERT_EQ(skel->bss->kretprobe_test7_result, 1, "kretprobe_test7_result"); + ASSERT_EQ(skel->bss->kretprobe_test8_result, 1, "kretprobe_test8_result"); + } +} + +static void test_skel_api(void) +{ + struct kprobe_multi *skel = NULL; + int err; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kprobe_multi__open_and_load")) + goto cleanup; + + skel->bss->pid = getpid(); + err = kprobe_multi__attach(skel); + if (!ASSERT_OK(err, "kprobe_multi__attach")) + goto cleanup; + + kprobe_multi_test_run(skel, true); + +cleanup: + kprobe_multi__destroy(skel); +} + +static void test_link_api(struct bpf_link_create_opts *opts) +{ + int prog_fd, link1_fd = -1, link2_fd = -1; + struct kprobe_multi *skel = NULL; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + prog_fd = bpf_program__fd(skel->progs.test_kprobe); + link1_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, opts); + if (!ASSERT_GE(link1_fd, 0, "link_fd")) + goto cleanup; + + opts->kprobe_multi.flags = BPF_F_KPROBE_MULTI_RETURN; + prog_fd = bpf_program__fd(skel->progs.test_kretprobe); + link2_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, opts); + if (!ASSERT_GE(link2_fd, 0, "link_fd")) + goto cleanup; + + kprobe_multi_test_run(skel, true); + +cleanup: + if (link1_fd != -1) + close(link1_fd); + if (link2_fd != -1) + close(link2_fd); + kprobe_multi__destroy(skel); +} + +#define GET_ADDR(__sym, __addr) ({ \ + __addr = ksym_get_addr(__sym); \ + if (!ASSERT_NEQ(__addr, 0, "kallsyms load failed for " #__sym)) \ + return; \ +}) + +static void test_link_api_addrs(void) +{ + LIBBPF_OPTS(bpf_link_create_opts, opts); + unsigned long long addrs[8]; + + GET_ADDR("bpf_fentry_test1", addrs[0]); + GET_ADDR("bpf_fentry_test2", addrs[1]); + GET_ADDR("bpf_fentry_test3", addrs[2]); + GET_ADDR("bpf_fentry_test4", addrs[3]); + GET_ADDR("bpf_fentry_test5", addrs[4]); + GET_ADDR("bpf_fentry_test6", addrs[5]); + GET_ADDR("bpf_fentry_test7", addrs[6]); + GET_ADDR("bpf_fentry_test8", addrs[7]); + + opts.kprobe_multi.addrs = (const unsigned long*) addrs; + opts.kprobe_multi.cnt = ARRAY_SIZE(addrs); + test_link_api(&opts); +} + +static void test_link_api_syms(void) +{ + LIBBPF_OPTS(bpf_link_create_opts, opts); + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + + opts.kprobe_multi.syms = syms; + opts.kprobe_multi.cnt = ARRAY_SIZE(syms); + test_link_api(&opts); +} + +static void +test_attach_api(const char *pattern, struct bpf_kprobe_multi_opts *opts) +{ + struct bpf_link *link1 = NULL, *link2 = NULL; + struct kprobe_multi *skel = NULL; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + link1 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + pattern, opts); + if (!ASSERT_OK_PTR(link1, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + + if (opts) { + opts->retprobe = true; + link2 = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kretprobe, + pattern, opts); + if (!ASSERT_OK_PTR(link2, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + } + + kprobe_multi_test_run(skel, !!opts); + +cleanup: + bpf_link__destroy(link2); + bpf_link__destroy(link1); + kprobe_multi__destroy(skel); +} + +static void test_attach_api_pattern(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + + test_attach_api("bpf_fentry_test*", &opts); + test_attach_api("bpf_fentry_test?", NULL); +} + +static void test_attach_api_addrs(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + unsigned long long addrs[8]; + + GET_ADDR("bpf_fentry_test1", addrs[0]); + GET_ADDR("bpf_fentry_test2", addrs[1]); + GET_ADDR("bpf_fentry_test3", addrs[2]); + GET_ADDR("bpf_fentry_test4", addrs[3]); + GET_ADDR("bpf_fentry_test5", addrs[4]); + GET_ADDR("bpf_fentry_test6", addrs[5]); + GET_ADDR("bpf_fentry_test7", addrs[6]); + GET_ADDR("bpf_fentry_test8", addrs[7]); + + opts.addrs = (const unsigned long *) addrs; + opts.cnt = ARRAY_SIZE(addrs); + test_attach_api(NULL, &opts); +} + +static void test_attach_api_syms(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + test_attach_api(NULL, &opts); +} + +static void test_attach_api_fails(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + struct kprobe_multi *skel = NULL; + struct bpf_link *link = NULL; + unsigned long long addrs[2]; + const char *syms[2] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + }; + __u64 cookies[2]; + + addrs[0] = ksym_get_addr("bpf_fentry_test1"); + addrs[1] = ksym_get_addr("bpf_fentry_test2"); + + if (!ASSERT_FALSE(!addrs[0] || !addrs[1], "ksym_get_addr")) + goto cleanup; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load")) + goto cleanup; + + skel->bss->pid = getpid(); + + /* fail_1 - pattern and opts NULL */ + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + NULL, NULL); + if (!ASSERT_ERR_PTR(link, "fail_1")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_1_error")) + goto cleanup; + + /* fail_2 - both addrs and syms set */ + opts.addrs = (const unsigned long *) addrs; + opts.syms = syms; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = NULL; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + NULL, &opts); + if (!ASSERT_ERR_PTR(link, "fail_2")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_2_error")) + goto cleanup; + + /* fail_3 - pattern and addrs set */ + opts.addrs = (const unsigned long *) addrs; + opts.syms = NULL; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = NULL; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + "ksys_*", &opts); + if (!ASSERT_ERR_PTR(link, "fail_3")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_3_error")) + goto cleanup; + + /* fail_4 - pattern and cnt set */ + opts.addrs = NULL; + opts.syms = NULL; + opts.cnt = ARRAY_SIZE(syms); + opts.cookies = NULL; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + "ksys_*", &opts); + if (!ASSERT_ERR_PTR(link, "fail_4")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_4_error")) + goto cleanup; + + /* fail_5 - pattern and cookies */ + opts.addrs = NULL; + opts.syms = NULL; + opts.cnt = 0; + opts.cookies = cookies; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe, + "ksys_*", &opts); + if (!ASSERT_ERR_PTR(link, "fail_5")) + goto cleanup; + + if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_5_error")) + goto cleanup; + +cleanup: + bpf_link__destroy(link); + kprobe_multi__destroy(skel); +} + +void test_kprobe_multi_test(void) +{ + if (!ASSERT_OK(load_kallsyms(), "load_kallsyms")) + return; + + if (test__start_subtest("skel_api")) + test_skel_api(); + if (test__start_subtest("link_api_addrs")) + test_link_api_syms(); + if (test__start_subtest("link_api_syms")) + test_link_api_addrs(); + if (test__start_subtest("attach_api_pattern")) + test_attach_api_pattern(); + if (test__start_subtest("attach_api_addrs")) + test_attach_api_addrs(); + if (test__start_subtest("attach_api_syms")) + test_attach_api_syms(); + if (test__start_subtest("attach_api_fails")) + test_attach_api_fails(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c index d490ad80eccb..a1ebac70ec29 100644 --- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c @@ -6,11 +6,15 @@ #include "test_ksyms_module.lskel.h" #include "test_ksyms_module.skel.h" -void test_ksyms_module_lskel(void) +static void test_ksyms_module_lskel(void) { struct test_ksyms_module_lskel *skel; - int retval; int err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); if (!env.has_testmod) { test__skip(); @@ -20,20 +24,24 @@ void test_ksyms_module_lskel(void) skel = test_ksyms_module_lskel__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_ksyms_module_lskel__open_and_load")) return; - err = bpf_prog_test_run(skel->progs.load.prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(skel->progs.load.prog_fd, &topts); if (!ASSERT_OK(err, "bpf_prog_test_run")) goto cleanup; - ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(topts.retval, 0, "retval"); ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); cleanup: test_ksyms_module_lskel__destroy(skel); } -void test_ksyms_module_libbpf(void) +static void test_ksyms_module_libbpf(void) { struct test_ksyms_module *skel; - int retval, err; + int err; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); if (!env.has_testmod) { test__skip(); @@ -43,11 +51,10 @@ void test_ksyms_module_libbpf(void) skel = test_ksyms_module__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open")) return; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.load), 1, &pkt_v4, - sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL); + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.load), &topts); if (!ASSERT_OK(err, "bpf_prog_test_run")) goto cleanup; - ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(topts.retval, 0, "retval"); ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); cleanup: test_ksyms_module__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c index 540ef28fabff..55f733ff4109 100644 --- a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c +++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c @@ -23,12 +23,16 @@ static void test_l4lb(const char *file) __u8 flags; } real_def = {.dst = MAGIC_VAL}; __u32 ch_key = 11, real_num = 3; - __u32 duration, retval, size; int err, i, prog_fd, map_fd; __u64 bytes = 0, pkts = 0; struct bpf_object *obj; char buf[128]; u32 *magic = (u32 *)buf; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = NUM_ITER, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) @@ -49,19 +53,24 @@ static void test_l4lb(const char *file) goto out; bpf_map_update_elem(map_fd, &real_num, &real_def, 0); - err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 54 || - *magic != MAGIC_VAL, "ipv4", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + topts.data_in = &pkt_v4; + topts.data_size_in = sizeof(pkt_v4); - err = bpf_prog_test_run(prog_fd, NUM_ITER, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); - CHECK(err || retval != 7/*TC_ACT_REDIRECT*/ || size != 74 || - *magic != MAGIC_VAL, "ipv6", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 7 /*TC_ACT_REDIRECT*/, "ipv4 test_run retval"); + ASSERT_EQ(topts.data_size_out, 54, "ipv4 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv4 magic"); + + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = sizeof(buf); /* reset out size */ + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 7 /*TC_ACT_REDIRECT*/, "ipv6 test_run retval"); + ASSERT_EQ(topts.data_size_out, 74, "ipv6 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv6 magic"); map_fd = bpf_find_map(__func__, obj, "stats"); if (map_fd < 0) diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c index e469b023962b..fe9a23e65ef4 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_buf.c +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -78,7 +78,7 @@ static void obj_load_log_buf(void) ASSERT_OK_PTR(strstr(libbpf_log_buf, "prog 'bad_prog': BPF program load failed"), "libbpf_log_not_empty"); ASSERT_OK_PTR(strstr(obj_log_buf, "DATASEC license"), "obj_log_not_empty"); - ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx(id=0,off=0,imm=0) R10=fp0"), + ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"), "good_log_verbose"); ASSERT_OK_PTR(strstr(bad_log_buf, "invalid access to map value, value_size=16 off=16000 size=4"), "bad_log_not_empty"); @@ -175,7 +175,7 @@ static void bpf_prog_load_log_buf(void) opts.log_level = 2; fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL", good_prog_insns, good_prog_insn_cnt, &opts); - ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx(id=0,off=0,imm=0) R10=fp0"), "good_log_2"); + ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"), "good_log_2"); ASSERT_GE(fd, 0, "good_fd2"); if (fd >= 0) close(fd); @@ -202,7 +202,7 @@ static void bpf_btf_load_log_buf(void) const void *raw_btf_data; __u32 raw_btf_size; struct btf *btf; - char *log_buf; + char *log_buf = NULL; int fd = -1; btf = btf__new_empty(); diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c index 23d19e9cf26a..e4e99b37df64 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c @@ -4,14 +4,17 @@ static void *spin_lock_thread(void *arg) { - __u32 duration, retval; int err, prog_fd = *(u32 *) arg; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 10000, + ); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run_opts err"); + ASSERT_OK(topts.retval, "test_run_opts retval"); - err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); pthread_exit(arg); } diff --git a/tools/testing/selftests/bpf/prog_tests/map_ptr.c b/tools/testing/selftests/bpf/prog_tests/map_ptr.c index 273725504f11..43e502acf050 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_ptr.c +++ b/tools/testing/selftests/bpf/prog_tests/map_ptr.c @@ -9,10 +9,16 @@ void test_map_ptr(void) { struct map_ptr_kern_lskel *skel; - __u32 duration = 0, retval; char buf[128]; int err; int page_size = getpagesize(); + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); skel = map_ptr_kern_lskel__open(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -26,14 +32,12 @@ void test_map_ptr(void) skel->bss->page_size = page_size; - err = bpf_prog_test_run(skel->progs.cg_skb.prog_fd, 1, &pkt_v4, - sizeof(pkt_v4), buf, NULL, &retval, NULL); + err = bpf_prog_test_run_opts(skel->progs.cg_skb.prog_fd, &topts); - if (CHECK(err, "test_run", "err=%d errno=%d\n", err, errno)) + if (!ASSERT_OK(err, "test_run")) goto cleanup; - if (CHECK(!retval, "retval", "retval=%d map_type=%u line=%u\n", retval, - skel->bss->g_map_type, skel->bss->g_line)) + if (!ASSERT_NEQ(topts.retval, 0, "test_run retval")) goto cleanup; cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c index b772fe30ce9b..5d9955af6247 100644 --- a/tools/testing/selftests/bpf/prog_tests/modify_return.c +++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c @@ -15,39 +15,31 @@ static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret) { struct modify_return *skel = NULL; int err, prog_fd; - __u32 duration = 0, retval; __u16 side_effect; __s16 ret; + LIBBPF_OPTS(bpf_test_run_opts, topts); skel = modify_return__open_and_load(); - if (CHECK(!skel, "skel_load", "modify_return skeleton failed\n")) + if (!ASSERT_OK_PTR(skel, "skel_load")) goto cleanup; err = modify_return__attach(skel); - if (CHECK(err, "modify_return", "attach failed: %d\n", err)) + if (!ASSERT_OK(err, "modify_return__attach failed")) goto cleanup; skel->bss->input_retval = input_retval; prog_fd = bpf_program__fd(skel->progs.fmod_ret_test); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, 0, - &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); - CHECK(err, "test_run", "err %d errno %d\n", err, errno); + side_effect = UPPER(topts.retval); + ret = LOWER(topts.retval); - side_effect = UPPER(retval); - ret = LOWER(retval); - - CHECK(ret != want_ret, "test_run", - "unexpected ret: %d, expected: %d\n", ret, want_ret); - CHECK(side_effect != want_side_effect, "modify_return", - "unexpected side_effect: %d\n", side_effect); - - CHECK(skel->bss->fentry_result != 1, "modify_return", - "fentry failed\n"); - CHECK(skel->bss->fexit_result != 1, "modify_return", - "fexit failed\n"); - CHECK(skel->bss->fmod_ret_result != 1, "modify_return", - "fmod_ret failed\n"); + ASSERT_EQ(ret, want_ret, "test_run ret"); + ASSERT_EQ(side_effect, want_side_effect, "modify_return side_effect"); + ASSERT_EQ(skel->bss->fentry_result, 1, "modify_return fentry_result"); + ASSERT_EQ(skel->bss->fexit_result, 1, "modify_return fexit_result"); + ASSERT_EQ(skel->bss->fmod_ret_result, 1, "modify_return fmod_ret_result"); cleanup: modify_return__destroy(skel); @@ -63,4 +55,3 @@ void serial_test_modify_return(void) 0 /* want_side_effect */, -EINVAL /* want_ret */); } - diff --git a/tools/testing/selftests/bpf/prog_tests/obj_name.c b/tools/testing/selftests/bpf/prog_tests/obj_name.c index 6194b776a28b..7093edca6e08 100644 --- a/tools/testing/selftests/bpf/prog_tests/obj_name.c +++ b/tools/testing/selftests/bpf/prog_tests/obj_name.c @@ -20,7 +20,7 @@ void test_obj_name(void) __u32 duration = 0; int i; - for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { + for (i = 0; i < ARRAY_SIZE(tests); i++) { size_t name_len = strlen(tests[i].name) + 1; union bpf_attr attr; size_t ncopy; diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c index 12c4f45cee1a..bc24f83339d6 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_branches.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c @@ -110,7 +110,7 @@ static void test_perf_branches_hw(void) attr.type = PERF_TYPE_HARDWARE; attr.config = PERF_COUNT_HW_CPU_CYCLES; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; attr.sample_type = PERF_SAMPLE_BRANCH_STACK; attr.branch_sample_type = PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); @@ -151,7 +151,7 @@ static void test_perf_branches_no_hw(void) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (CHECK(pfd < 0, "perf_event_open", "err %d\n", pfd)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c index ede07344f264..224eba6fef2e 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_link.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c @@ -39,7 +39,7 @@ void serial_test_perf_link(void) attr.type = PERF_TYPE_SOFTWARE; attr.config = PERF_COUNT_SW_CPU_CLOCK; attr.freq = 1; - attr.sample_freq = 4000; + attr.sample_freq = 1000; pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); if (!ASSERT_GE(pfd, 0, "perf_fd")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_access.c index 6628710ec3c6..0bcccdc34fbc 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_access.c @@ -6,23 +6,27 @@ void test_pkt_access(void) { const char *file = "./test_pkt_access.o"; struct bpf_object *obj; - __u32 duration, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 100000, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv4", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv4 test_run_opts err"); + ASSERT_OK(topts.retval, "ipv4 test_run_opts retval"); + + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = 0; /* reset from last call */ + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6 test_run_opts err"); + ASSERT_OK(topts.retval, "ipv6 test_run_opts retval"); - err = bpf_prog_test_run(prog_fd, 100000, &pkt_v6, sizeof(pkt_v6), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "ipv6", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c index c9d2d6a1bfcc..00ee1dd792aa 100644 --- a/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c +++ b/tools/testing/selftests/bpf/prog_tests/pkt_md_access.c @@ -6,18 +6,20 @@ void test_pkt_md_access(void) { const char *file = "./test_pkt_md_access.o"; struct bpf_object *obj; - __u32 duration, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 10, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run_opts err"); + ASSERT_OK(topts.retval, "test_run_opts retval"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c b/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c new file mode 100644 index 000000000000..1ccd2bdf8fa8 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> + +#include "test_pkt_access.skel.h" + +static const __u32 duration; + +static void check_run_cnt(int prog_fd, __u64 run_cnt) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int err; + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (CHECK(err, "get_prog_info", "failed to get bpf_prog_info for fd %d\n", prog_fd)) + return; + + CHECK(run_cnt != info.run_cnt, "run_cnt", + "incorrect number of repetitions, want %llu have %llu\n", run_cnt, info.run_cnt); +} + +void test_prog_run_opts(void) +{ + struct test_pkt_access *skel; + int err, stats_fd = -1, prog_fd; + char buf[10] = {}; + __u64 run_cnt = 0; + + LIBBPF_OPTS(bpf_test_run_opts, topts, + .repeat = 1, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = 5, + ); + + stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME); + if (!ASSERT_GE(stats_fd, 0, "enable_stats good fd")) + return; + + skel = test_pkt_access__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + prog_fd = bpf_program__fd(skel->progs.test_pkt_access); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_EQ(errno, ENOSPC, "test_run errno"); + ASSERT_ERR(err, "test_run"); + ASSERT_OK(topts.retval, "test_run retval"); + + ASSERT_EQ(topts.data_size_out, sizeof(pkt_v4), "test_run data_size_out"); + ASSERT_EQ(buf[5], 0, "overflow, BPF_PROG_TEST_RUN ignored size hint"); + + run_cnt += topts.repeat; + check_run_cnt(prog_fd, run_cnt); + + topts.data_out = NULL; + topts.data_size_out = 0; + topts.repeat = 2; + errno = 0; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(errno, "run_no_output errno"); + ASSERT_OK(err, "run_no_output err"); + ASSERT_OK(topts.retval, "run_no_output retval"); + + run_cnt += topts.repeat; + check_run_cnt(prog_fd, run_cnt); + +cleanup: + if (skel) + test_pkt_access__destroy(skel); + if (stats_fd >= 0) + close(stats_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c deleted file mode 100644 index 89fc98faf19e..000000000000 --- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c +++ /dev/null @@ -1,83 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <test_progs.h> -#include <network_helpers.h> - -#include "test_pkt_access.skel.h" - -static const __u32 duration; - -static void check_run_cnt(int prog_fd, __u64 run_cnt) -{ - struct bpf_prog_info info = {}; - __u32 info_len = sizeof(info); - int err; - - err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); - if (CHECK(err, "get_prog_info", "failed to get bpf_prog_info for fd %d\n", prog_fd)) - return; - - CHECK(run_cnt != info.run_cnt, "run_cnt", - "incorrect number of repetitions, want %llu have %llu\n", run_cnt, info.run_cnt); -} - -void test_prog_run_xattr(void) -{ - struct test_pkt_access *skel; - int err, stats_fd = -1; - char buf[10] = {}; - __u64 run_cnt = 0; - - struct bpf_prog_test_run_attr tattr = { - .repeat = 1, - .data_in = &pkt_v4, - .data_size_in = sizeof(pkt_v4), - .data_out = buf, - .data_size_out = 5, - }; - - stats_fd = bpf_enable_stats(BPF_STATS_RUN_TIME); - if (CHECK_ATTR(stats_fd < 0, "enable_stats", "failed %d\n", errno)) - return; - - skel = test_pkt_access__open_and_load(); - if (CHECK_ATTR(!skel, "open_and_load", "failed\n")) - goto cleanup; - - tattr.prog_fd = bpf_program__fd(skel->progs.test_pkt_access); - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err >= 0 || errno != ENOSPC || tattr.retval, "run", - "err %d errno %d retval %d\n", err, errno, tattr.retval); - - CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out", - "incorrect output size, want %zu have %u\n", - sizeof(pkt_v4), tattr.data_size_out); - - CHECK_ATTR(buf[5] != 0, "overflow", - "BPF_PROG_TEST_RUN ignored size hint\n"); - - run_cnt += tattr.repeat; - check_run_cnt(tattr.prog_fd, run_cnt); - - tattr.data_out = NULL; - tattr.data_size_out = 0; - tattr.repeat = 2; - errno = 0; - - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err || errno || tattr.retval, "run_no_output", - "err %d errno %d retval %d\n", err, errno, tattr.retval); - - tattr.data_size_out = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != -EINVAL, "run_wrong_size_out", "err %d\n", err); - - run_cnt += tattr.repeat; - check_run_cnt(tattr.prog_fd, run_cnt); - -cleanup: - if (skel) - test_pkt_access__destroy(skel); - if (stats_fd >= 0) - close(stats_fd); -} diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c index b9822f914eeb..d2743fc10032 100644 --- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c +++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c @@ -10,11 +10,18 @@ enum { static void test_queue_stack_map_by_type(int type) { const int MAP_SIZE = 32; - __u32 vals[MAP_SIZE], duration, retval, size, val; + __u32 vals[MAP_SIZE], val; int i, err, prog_fd, map_in_fd, map_out_fd; char file[32], buf[128]; struct bpf_object *obj; struct iphdr iph; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); /* Fill test values to be used */ for (i = 0; i < MAP_SIZE; i++) @@ -58,38 +65,37 @@ static void test_queue_stack_map_by_type(int type) pkt_v4.iph.saddr = vals[MAP_SIZE - 1 - i] * 5; } - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - if (err || retval || size != sizeof(pkt_v4)) + topts.data_size_out = sizeof(buf); + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (err || topts.retval || + topts.data_size_out != sizeof(pkt_v4)) break; memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); if (iph.daddr != val) break; } - CHECK(err || retval || size != sizeof(pkt_v4) || iph.daddr != val, - "bpf_map_pop_elem", - "err %d errno %d retval %d size %d iph->daddr %u\n", - err, errno, retval, size, iph.daddr); + ASSERT_OK(err, "bpf_map_pop_elem"); + ASSERT_OK(topts.retval, "bpf_map_pop_elem test retval"); + ASSERT_EQ(topts.data_size_out, sizeof(pkt_v4), + "bpf_map_pop_elem data_size_out"); + ASSERT_EQ(iph.daddr, val, "bpf_map_pop_elem iph.daddr"); /* Queue is empty, program should return TC_ACT_SHOT */ - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != 2 /* TC_ACT_SHOT */|| size != sizeof(pkt_v4), - "check-queue-stack-map-empty", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + topts.data_size_out = sizeof(buf); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "check-queue-stack-map-empty"); + ASSERT_EQ(topts.retval, 2 /* TC_ACT_SHOT */, + "check-queue-stack-map-empty test retval"); + ASSERT_EQ(topts.data_size_out, sizeof(pkt_v4), + "check-queue-stack-map-empty data_size_out"); /* Check that the program pushed elements correctly */ for (i = 0; i < MAP_SIZE; i++) { err = bpf_map_lookup_and_delete_elem(map_out_fd, NULL, &val); - if (err || val != vals[i] * 5) - break; + ASSERT_OK(err, "bpf_map_lookup_and_delete_elem"); + ASSERT_EQ(val, vals[i] * 5, "bpf_map_push_elem val"); } - - CHECK(i != MAP_SIZE && (err || val != vals[i] * 5), - "bpf_map_push_elem", "err %d value %u\n", err, val); - out: pkt_v4.iph.saddr = 0; bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c index 41720a62c4fa..fe5b8fae2c36 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c @@ -5,59 +5,54 @@ #include "bpf/libbpf_internal.h" #include "test_raw_tp_test_run.skel.h" -static int duration; - void test_raw_tp_test_run(void) { - struct bpf_prog_test_run_attr test_attr = {}; int comm_fd = -1, err, nr_online, i, prog_fd; __u64 args[2] = {0x1234ULL, 0x5678ULL}; int expected_retval = 0x1234 + 0x5678; struct test_raw_tp_test_run *skel; char buf[] = "new_name"; bool *online = NULL; - DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, - .ctx_in = args, - .ctx_size_in = sizeof(args), - .flags = BPF_F_TEST_RUN_ON_CPU, - ); + LIBBPF_OPTS(bpf_test_run_opts, opts, + .ctx_in = args, + .ctx_size_in = sizeof(args), + .flags = BPF_F_TEST_RUN_ON_CPU, + ); err = parse_cpu_mask_file("/sys/devices/system/cpu/online", &online, &nr_online); - if (CHECK(err, "parse_cpu_mask_file", "err %d\n", err)) + if (!ASSERT_OK(err, "parse_cpu_mask_file")) return; skel = test_raw_tp_test_run__open_and_load(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!ASSERT_OK_PTR(skel, "skel_open")) goto cleanup; err = test_raw_tp_test_run__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + if (!ASSERT_OK(err, "skel_attach")) goto cleanup; comm_fd = open("/proc/self/comm", O_WRONLY|O_TRUNC); - if (CHECK(comm_fd < 0, "open /proc/self/comm", "err %d\n", errno)) + if (!ASSERT_GE(comm_fd, 0, "open /proc/self/comm")) goto cleanup; err = write(comm_fd, buf, sizeof(buf)); - CHECK(err < 0, "task rename", "err %d", errno); + ASSERT_GE(err, 0, "task rename"); - CHECK(skel->bss->count == 0, "check_count", "didn't increase\n"); - CHECK(skel->data->on_cpu != 0xffffffff, "check_on_cpu", "got wrong value\n"); + ASSERT_NEQ(skel->bss->count, 0, "check_count"); + ASSERT_EQ(skel->data->on_cpu, 0xffffffff, "check_on_cpu"); prog_fd = bpf_program__fd(skel->progs.rename); - test_attr.prog_fd = prog_fd; - test_attr.ctx_in = args; - test_attr.ctx_size_in = sizeof(__u64); + opts.ctx_in = args; + opts.ctx_size_in = sizeof(__u64); - err = bpf_prog_test_run_xattr(&test_attr); - CHECK(err == 0, "test_run", "should fail for too small ctx\n"); + err = bpf_prog_test_run_opts(prog_fd, &opts); + ASSERT_NEQ(err, 0, "test_run should fail for too small ctx"); - test_attr.ctx_size_in = sizeof(args); - err = bpf_prog_test_run_xattr(&test_attr); - CHECK(err < 0, "test_run", "err %d\n", errno); - CHECK(test_attr.retval != expected_retval, "check_retval", - "expect 0x%x, got 0x%x\n", expected_retval, test_attr.retval); + opts.ctx_size_in = sizeof(args); + err = bpf_prog_test_run_opts(prog_fd, &opts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(opts.retval, expected_retval, "check_retval"); for (i = 0; i < nr_online; i++) { if (!online[i]) @@ -66,28 +61,23 @@ void test_raw_tp_test_run(void) opts.cpu = i; opts.retval = 0; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err < 0, "test_run_opts", "err %d\n", errno); - CHECK(skel->data->on_cpu != i, "check_on_cpu", - "expect %d got %d\n", i, skel->data->on_cpu); - CHECK(opts.retval != expected_retval, - "check_retval", "expect 0x%x, got 0x%x\n", - expected_retval, opts.retval); + ASSERT_OK(err, "test_run_opts"); + ASSERT_EQ(skel->data->on_cpu, i, "check_on_cpu"); + ASSERT_EQ(opts.retval, expected_retval, "check_retval"); } /* invalid cpu ID should fail with ENXIO */ opts.cpu = 0xffffffff; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err >= 0 || errno != ENXIO, - "test_run_opts_fail", - "should failed with ENXIO\n"); + ASSERT_EQ(errno, ENXIO, "test_run_opts should fail with ENXIO"); + ASSERT_ERR(err, "test_run_opts_fail"); /* non-zero cpu w/o BPF_F_TEST_RUN_ON_CPU should fail with EINVAL */ opts.cpu = 1; opts.flags = 0; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err >= 0 || errno != EINVAL, - "test_run_opts_fail", - "should failed with EINVAL\n"); + ASSERT_EQ(errno, EINVAL, "test_run_opts should fail with EINVAL"); + ASSERT_ERR(err, "test_run_opts_fail"); cleanup: close(comm_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c index 239baccabccb..f4aa7dab4766 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c @@ -56,21 +56,23 @@ void serial_test_raw_tp_writable_test_run(void) 0, }; - __u32 prog_ret; - int err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, - 0, &prog_ret, 0); + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = test_skb, + .data_size_in = sizeof(test_skb), + .repeat = 1, + ); + int err = bpf_prog_test_run_opts(filter_fd, &topts); CHECK(err != 42, "test_run", "tracepoint did not modify return value\n"); - CHECK(prog_ret != 0, "test_run_ret", + CHECK(topts.retval != 0, "test_run_ret", "socket_filter did not return 0\n"); close(tp_fd); - err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, 0, - &prog_ret, 0); + err = bpf_prog_test_run_opts(filter_fd, &topts); CHECK(err != 0, "test_run_notrace", "test_run failed with %d errno %d\n", err, errno); - CHECK(prog_ret != 0, "test_run_ret_notrace", + CHECK(topts.retval != 0, "test_run_ret_notrace", "socket_filter did not return 0\n"); out_filterfd: diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 776916b61c40..d71226e34c34 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -4,11 +4,11 @@ #include <sys/resource.h> #include "test_send_signal_kern.skel.h" -int sigusr1_received = 0; +static int sigusr1_received; static void sigusr1_handler(int signum) { - sigusr1_received++; + sigusr1_received = 1; } static void test_send_signal_common(struct perf_event_attr *attr, @@ -40,9 +40,10 @@ static void test_send_signal_common(struct perf_event_attr *attr, if (pid == 0) { int old_prio; + volatile int j = 0; /* install signal handler and notify parent */ - signal(SIGUSR1, sigusr1_handler); + ASSERT_NEQ(signal(SIGUSR1, sigusr1_handler), SIG_ERR, "signal"); close(pipe_c2p[0]); /* close read */ close(pipe_p2c[1]); /* close write */ @@ -63,9 +64,11 @@ static void test_send_signal_common(struct perf_event_attr *attr, ASSERT_EQ(read(pipe_p2c[0], buf, 1), 1, "pipe_read"); /* wait a little for signal handler */ - sleep(1); + for (int i = 0; i < 100000000 && !sigusr1_received; i++) + j /= i + j + 1; buf[0] = sigusr1_received ? '2' : '0'; + ASSERT_EQ(sigusr1_received, 1, "sigusr1_received"); ASSERT_EQ(write(pipe_c2p[1], buf, 1), 1, "pipe_write"); /* wait for parent notification and exit */ @@ -93,7 +96,7 @@ static void test_send_signal_common(struct perf_event_attr *attr, goto destroy_skel; } } else { - pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1, + pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1 /* cpu */, -1 /* group id */, 0 /* flags */); if (!ASSERT_GE(pmu_fd, 0, "perf_event_open")) { err = -1; @@ -110,9 +113,9 @@ static void test_send_signal_common(struct perf_event_attr *attr, ASSERT_EQ(read(pipe_c2p[0], buf, 1), 1, "pipe_read"); /* trigger the bpf send_signal */ - skel->bss->pid = pid; - skel->bss->sig = SIGUSR1; skel->bss->signal_thread = signal_thread; + skel->bss->sig = SIGUSR1; + skel->bss->pid = pid; /* notify child that bpf program can send_signal now */ ASSERT_EQ(write(pipe_p2c[1], buf, 1), 1, "pipe_write"); diff --git a/tools/testing/selftests/bpf/prog_tests/signal_pending.c b/tools/testing/selftests/bpf/prog_tests/signal_pending.c index aecfe662c070..70b49da5ca0a 100644 --- a/tools/testing/selftests/bpf/prog_tests/signal_pending.c +++ b/tools/testing/selftests/bpf/prog_tests/signal_pending.c @@ -13,10 +13,14 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type) struct itimerval timeo = { .it_value.tv_usec = 100000, /* 100ms */ }; - __u32 duration = 0, retval; int prog_fd; int err; int i; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 0xffffffff, + ); for (i = 0; i < ARRAY_SIZE(prog); i++) prog[i] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0); @@ -24,20 +28,17 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type) prog_fd = bpf_test_load_program(prog_type, prog, ARRAY_SIZE(prog), "GPL", 0, NULL, 0); - CHECK(prog_fd < 0, "test-run", "errno %d\n", errno); + ASSERT_GE(prog_fd, 0, "test-run load"); err = sigaction(SIGALRM, &sigalrm_action, NULL); - CHECK(err, "test-run-signal-sigaction", "errno %d\n", errno); + ASSERT_OK(err, "test-run-signal-sigaction"); err = setitimer(ITIMER_REAL, &timeo, NULL); - CHECK(err, "test-run-signal-timer", "errno %d\n", errno); - - err = bpf_prog_test_run(prog_fd, 0xffffffff, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(duration > 500000000, /* 500ms */ - "test-run-signal-duration", - "duration %dns > 500ms\n", - duration); + ASSERT_OK(err, "test-run-signal-timer"); + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_LE(topts.duration, 500000000 /* 500ms */, + "test-run-signal-duration"); signal(SIGALRM, SIG_DFL); } diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index b5319ba2ee27..ce0e555b5e38 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -20,97 +20,72 @@ void test_skb_ctx(void) .gso_size = 10, .hwtstamp = 11, }; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, tattr, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .ctx_in = &skb, .ctx_size_in = sizeof(skb), .ctx_out = &skb, .ctx_size_out = sizeof(skb), - }; + ); struct bpf_object *obj; - int err; - int i; + int err, prog_fd, i; - err = bpf_prog_test_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, &obj, - &tattr.prog_fd); - if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, + &obj, &prog_fd); + if (!ASSERT_OK(err, "load")) return; /* ctx_in != NULL, ctx_size_in == 0 */ tattr.ctx_size_in = 0; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "ctx_size_in", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "ctx_size_in"); tattr.ctx_size_in = sizeof(skb); /* ctx_out != NULL, ctx_size_out == 0 */ tattr.ctx_size_out = 0; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "ctx_size_out", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "ctx_size_out"); tattr.ctx_size_out = sizeof(skb); /* non-zero [len, tc_index] fields should be rejected*/ skb.len = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "len", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "len"); skb.len = 0; skb.tc_index = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "tc_index", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "tc_index"); skb.tc_index = 0; /* non-zero [hash, sk] fields should be rejected */ skb.hash = 1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "hash", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "hash"); skb.hash = 0; skb.sk = (struct bpf_sock *)1; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err == 0, "sk", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_NEQ(err, 0, "sk"); skb.sk = 0; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != 0 || tattr.retval, - "run", - "err %d errno %d retval %d\n", - err, errno, tattr.retval); - - CHECK_ATTR(tattr.ctx_size_out != sizeof(skb), - "ctx_size_out", - "incorrect output size, want %zu have %u\n", - sizeof(skb), tattr.ctx_size_out); + err = bpf_prog_test_run_opts(prog_fd, &tattr); + ASSERT_OK(err, "test_run"); + ASSERT_OK(tattr.retval, "test_run retval"); + ASSERT_EQ(tattr.ctx_size_out, sizeof(skb), "ctx_size_out"); for (i = 0; i < 5; i++) - CHECK_ATTR(skb.cb[i] != i + 2, - "ctx_out_cb", - "skb->cb[i] == %d, expected %d\n", - skb.cb[i], i + 2); - CHECK_ATTR(skb.priority != 7, - "ctx_out_priority", - "skb->priority == %d, expected %d\n", - skb.priority, 7); - CHECK_ATTR(skb.ifindex != 1, - "ctx_out_ifindex", - "skb->ifindex == %d, expected %d\n", - skb.ifindex, 1); - CHECK_ATTR(skb.ingress_ifindex != 11, - "ctx_out_ingress_ifindex", - "skb->ingress_ifindex == %d, expected %d\n", - skb.ingress_ifindex, 11); - CHECK_ATTR(skb.tstamp != 8, - "ctx_out_tstamp", - "skb->tstamp == %lld, expected %d\n", - skb.tstamp, 8); - CHECK_ATTR(skb.mark != 10, - "ctx_out_mark", - "skb->mark == %u, expected %d\n", - skb.mark, 10); + ASSERT_EQ(skb.cb[i], i + 2, "ctx_out_cb"); + ASSERT_EQ(skb.priority, 7, "ctx_out_priority"); + ASSERT_EQ(skb.ifindex, 1, "ctx_out_ifindex"); + ASSERT_EQ(skb.ingress_ifindex, 11, "ctx_out_ingress_ifindex"); + ASSERT_EQ(skb.tstamp, 8, "ctx_out_tstamp"); + ASSERT_EQ(skb.mark, 10, "ctx_out_mark"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c index 6f802a1c0800..97dc8b14be48 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_helpers.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_helpers.c @@ -9,22 +9,22 @@ void test_skb_helpers(void) .gso_segs = 8, .gso_size = 10, }; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = &pkt_v4, .data_size_in = sizeof(pkt_v4), .ctx_in = &skb, .ctx_size_in = sizeof(skb), .ctx_out = &skb, .ctx_size_out = sizeof(skb), - }; + ); struct bpf_object *obj; - int err; + int err, prog_fd; - err = bpf_prog_test_load("./test_skb_helpers.o", BPF_PROG_TYPE_SCHED_CLS, &obj, - &tattr.prog_fd); - if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load("./test_skb_helpers.o", + BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + if (!ASSERT_OK(err, "load")) return; - err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err, "len", "err %d errno %d\n", err, errno); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c index 9fc040eaa482..9d211b5c22c4 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c @@ -1,9 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ +#define _GNU_SOURCE #include <netinet/in.h> #include <arpa/inet.h> #include <unistd.h> +#include <sched.h> #include <stdlib.h> #include <string.h> #include <errno.h> @@ -20,6 +22,7 @@ enum bpf_linum_array_idx { EGRESS_LINUM_IDX, INGRESS_LINUM_IDX, + READ_SK_DST_PORT_LINUM_IDX, __NR_BPF_LINUM_ARRAY_IDX, }; @@ -42,8 +45,16 @@ static __u64 child_cg_id; static int linum_map_fd; static __u32 duration; -static __u32 egress_linum_idx = EGRESS_LINUM_IDX; -static __u32 ingress_linum_idx = INGRESS_LINUM_IDX; +static bool create_netns(void) +{ + if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns")) + return false; + + if (!ASSERT_OK(system("ip link set dev lo up"), "bring up lo")) + return false; + + return true; +} static void print_sk(const struct bpf_sock *sk, const char *prefix) { @@ -91,19 +102,24 @@ static void check_result(void) { struct bpf_tcp_sock srv_tp, cli_tp, listen_tp; struct bpf_sock srv_sk, cli_sk, listen_sk; - __u32 ingress_linum, egress_linum; + __u32 idx, ingress_linum, egress_linum, linum; int err; - err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx, - &egress_linum); + idx = EGRESS_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &egress_linum); CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d\n", err, errno); - err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx, - &ingress_linum); + idx = INGRESS_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &ingress_linum); CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d\n", err, errno); + idx = READ_SK_DST_PORT_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &linum); + ASSERT_OK(err, "bpf_map_lookup_elem(linum_map_fd, READ_SK_DST_PORT_IDX)"); + ASSERT_EQ(linum, 0, "failure in read_sk_dst_port on line"); + memcpy(&srv_sk, &skel->bss->srv_sk, sizeof(srv_sk)); memcpy(&srv_tp, &skel->bss->srv_tp, sizeof(srv_tp)); memcpy(&cli_sk, &skel->bss->cli_sk, sizeof(cli_sk)); @@ -262,7 +278,7 @@ static void test(void) char buf[DATA_LEN]; /* Prepare listen_fd */ - listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); + listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0xcafe, 0); /* start_server() has logged the error details */ if (CHECK_FAIL(listen_fd == -1)) goto done; @@ -330,8 +346,12 @@ done: void serial_test_sock_fields(void) { - struct bpf_link *egress_link = NULL, *ingress_link = NULL; int parent_cg_fd = -1, child_cg_fd = -1; + struct bpf_link *link; + + /* Use a dedicated netns to have a fixed listen port */ + if (!create_netns()) + return; /* Create a cgroup, get fd, and join it */ parent_cg_fd = test__join_cgroup(PARENT_CGROUP); @@ -352,15 +372,20 @@ void serial_test_sock_fields(void) if (CHECK(!skel, "test_sock_fields__open_and_load", "failed\n")) goto done; - egress_link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, - child_cg_fd); - if (!ASSERT_OK_PTR(egress_link, "attach_cgroup(egress)")) + link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(egress_read_sock_fields)")) + goto done; + skel->links.egress_read_sock_fields = link; + + link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(ingress_read_sock_fields)")) goto done; + skel->links.ingress_read_sock_fields = link; - ingress_link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, - child_cg_fd); - if (!ASSERT_OK_PTR(ingress_link, "attach_cgroup(ingress)")) + link = bpf_program__attach_cgroup(skel->progs.read_sk_dst_port, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(read_sk_dst_port")) goto done; + skel->links.read_sk_dst_port = link; linum_map_fd = bpf_map__fd(skel->maps.linum_map); sk_pkt_out_cnt_fd = bpf_map__fd(skel->maps.sk_pkt_out_cnt); @@ -369,8 +394,7 @@ void serial_test_sock_fields(void) test(); done: - bpf_link__destroy(egress_link); - bpf_link__destroy(ingress_link); + test_sock_fields__detach(skel); test_sock_fields__destroy(skel); if (child_cg_fd >= 0) close(child_cg_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 85db0f4cdd95..cec5c0882372 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -8,6 +8,7 @@ #include "test_sockmap_update.skel.h" #include "test_sockmap_invalid_update.skel.h" #include "test_sockmap_skb_verdict_attach.skel.h" +#include "test_sockmap_progs_query.skel.h" #include "bpf_iter_sockmap.skel.h" #define TCP_REPAIR 19 /* TCP sock is under repair right now */ @@ -139,12 +140,16 @@ out: static void test_sockmap_update(enum bpf_map_type map_type) { - struct bpf_prog_test_run_attr tattr; int err, prog, src, duration = 0; struct test_sockmap_update *skel; struct bpf_map *dst_map; const __u32 zero = 0; char dummy[14] = {0}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = dummy, + .data_size_in = sizeof(dummy), + .repeat = 1, + ); __s64 sk; sk = connected_socket_v4(); @@ -166,16 +171,10 @@ static void test_sockmap_update(enum bpf_map_type map_type) if (CHECK(err, "update_elem(src)", "errno=%u\n", errno)) goto out; - tattr = (struct bpf_prog_test_run_attr){ - .prog_fd = prog, - .repeat = 1, - .data_in = dummy, - .data_size_in = sizeof(dummy), - }; - - err = bpf_prog_test_run_xattr(&tattr); - if (CHECK_ATTR(err || !tattr.retval, "bpf_prog_test_run", - "errno=%u retval=%u\n", errno, tattr.retval)) + err = bpf_prog_test_run_opts(prog, &topts); + if (!ASSERT_OK(err, "test_run")) + goto out; + if (!ASSERT_NEQ(topts.retval, 0, "test_run retval")) goto out; compare_cookies(skel->maps.src, dst_map); @@ -315,6 +314,63 @@ out: test_sockmap_skb_verdict_attach__destroy(skel); } +static __u32 query_prog_id(int prog_fd) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int err; + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd") || + !ASSERT_EQ(info_len, sizeof(info), "bpf_obj_get_info_by_fd")) + return 0; + + return info.id; +} + +static void test_sockmap_progs_query(enum bpf_attach_type attach_type) +{ + struct test_sockmap_progs_query *skel; + int err, map_fd, verdict_fd; + __u32 attach_flags = 0; + __u32 prog_ids[3] = {}; + __u32 prog_cnt = 3; + + skel = test_sockmap_progs_query__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_sockmap_progs_query__open_and_load")) + return; + + map_fd = bpf_map__fd(skel->maps.sock_map); + + if (attach_type == BPF_SK_MSG_VERDICT) + verdict_fd = bpf_program__fd(skel->progs.prog_skmsg_verdict); + else + verdict_fd = bpf_program__fd(skel->progs.prog_skb_verdict); + + err = bpf_prog_query(map_fd, attach_type, 0 /* query flags */, + &attach_flags, prog_ids, &prog_cnt); + ASSERT_OK(err, "bpf_prog_query failed"); + ASSERT_EQ(attach_flags, 0, "wrong attach_flags on query"); + ASSERT_EQ(prog_cnt, 0, "wrong program count on query"); + + err = bpf_prog_attach(verdict_fd, map_fd, attach_type, 0); + if (!ASSERT_OK(err, "bpf_prog_attach failed")) + goto out; + + prog_cnt = 1; + err = bpf_prog_query(map_fd, attach_type, 0 /* query flags */, + &attach_flags, prog_ids, &prog_cnt); + ASSERT_OK(err, "bpf_prog_query failed"); + ASSERT_EQ(attach_flags, 0, "wrong attach_flags on query"); + ASSERT_EQ(prog_cnt, 1, "wrong program count on query"); + ASSERT_EQ(prog_ids[0], query_prog_id(verdict_fd), + "wrong prog_ids on query"); + + bpf_prog_detach2(verdict_fd, map_fd, attach_type); +out: + test_sockmap_progs_query__destroy(skel); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -341,4 +397,12 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_attach(BPF_SK_SKB_STREAM_VERDICT, BPF_SK_SKB_VERDICT); } + if (test__start_subtest("sockmap msg_verdict progs query")) + test_sockmap_progs_query(BPF_SK_MSG_VERDICT); + if (test__start_subtest("sockmap stream_parser progs query")) + test_sockmap_progs_query(BPF_SK_SKB_STREAM_PARSER); + if (test__start_subtest("sockmap stream_verdict progs query")) + test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT); + if (test__start_subtest("sockmap skb_verdict progs query")) + test_sockmap_progs_query(BPF_SK_SKB_VERDICT); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 7e21bfab6358..2cf0c7a3fe23 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -1413,14 +1413,12 @@ close_srv1: static void test_ops_cleanup(const struct bpf_map *map) { - const struct bpf_map_def *def; int err, mapfd; u32 key; - def = bpf_map__def(map); mapfd = bpf_map__fd(map); - for (key = 0; key < def->max_entries; key++) { + for (key = 0; key < bpf_map__max_entries(map); key++) { err = bpf_map_delete_elem(mapfd, &key); if (err && errno != EINVAL && errno != ENOENT) FAIL_ERRNO("map_delete: expected EINVAL/ENOENT"); @@ -1443,13 +1441,13 @@ static const char *family_str(sa_family_t family) static const char *map_type_str(const struct bpf_map *map) { - const struct bpf_map_def *def; + int type; - def = bpf_map__def(map); - if (IS_ERR(def)) + if (!map) return "invalid"; + type = bpf_map__type(map); - switch (def->type) { + switch (type) { case BPF_MAP_TYPE_SOCKMAP: return "sockmap"; case BPF_MAP_TYPE_SOCKHASH: diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 4b937e5dbaca..30a99d2ed5c6 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -173,11 +173,11 @@ static int getsetsockopt(void) } memset(&buf, 0, sizeof(buf)); - buf.zc.address = 12345; /* rejected by BPF */ + buf.zc.address = 12345; /* Not page aligned. Rejected by tcp_zerocopy_receive() */ optlen = sizeof(buf.zc); errno = 0; err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen); - if (errno != EPERM) { + if (errno != EINVAL) { log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d", err, errno); goto err; diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c index 6307f5d2b417..8e329eaee6d7 100644 --- a/tools/testing/selftests/bpf/prog_tests/spinlock.c +++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c @@ -4,14 +4,16 @@ static void *spin_lock_thread(void *arg) { - __u32 duration, retval; int err, prog_fd = *(u32 *) arg; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 10000, + ); - err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_OK(topts.retval, "test_run retval"); pthread_exit(arg); } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c index 0a91d8d9954b..f45a1d7b0a28 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c @@ -42,7 +42,7 @@ retry: return; /* override program type */ - bpf_program__set_perf_event(skel->progs.oncpu); + bpf_program__set_type(skel->progs.oncpu, BPF_PROG_TYPE_PERF_EVENT); err = test_stacktrace_build_id__load(skel); if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err)) diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c new file mode 100644 index 000000000000..1932b1e0685c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "stacktrace_map_skip.skel.h" + +#define TEST_STACK_DEPTH 2 + +void test_stacktrace_map_skip(void) +{ + struct stacktrace_map_skip *skel; + int stackid_hmap_fd, stackmap_fd, stack_amap_fd; + int err, stack_trace_len; + + skel = stacktrace_map_skip__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + /* find map fds */ + stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap); + if (!ASSERT_GE(stackid_hmap_fd, 0, "stackid_hmap fd")) + goto out; + + stackmap_fd = bpf_map__fd(skel->maps.stackmap); + if (!ASSERT_GE(stackmap_fd, 0, "stackmap fd")) + goto out; + + stack_amap_fd = bpf_map__fd(skel->maps.stack_amap); + if (!ASSERT_GE(stack_amap_fd, 0, "stack_amap fd")) + goto out; + + skel->bss->pid = getpid(); + + err = stacktrace_map_skip__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto out; + + /* give some time for bpf program run */ + sleep(1); + + /* disable stack trace collection */ + skel->bss->control = 1; + + /* for every element in stackid_hmap, we can find a corresponding one + * in stackmap, and vise versa. + */ + err = compare_map_keys(stackid_hmap_fd, stackmap_fd); + if (!ASSERT_OK(err, "compare_map_keys stackid_hmap vs. stackmap")) + goto out; + + err = compare_map_keys(stackmap_fd, stackid_hmap_fd); + if (!ASSERT_OK(err, "compare_map_keys stackmap vs. stackid_hmap")) + goto out; + + stack_trace_len = TEST_STACK_DEPTH * sizeof(__u64); + err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); + if (!ASSERT_OK(err, "compare_stack_ips stackmap vs. stack_amap")) + goto out; + + if (!ASSERT_EQ(skel->bss->failed, 0, "skip_failed")) + goto out; + +out: + stacktrace_map_skip__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs.c b/tools/testing/selftests/bpf/prog_tests/subprogs.c index 3f3d2ac4dd57..903f35a9e62e 100644 --- a/tools/testing/selftests/bpf/prog_tests/subprogs.c +++ b/tools/testing/selftests/bpf/prog_tests/subprogs.c @@ -1,32 +1,83 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ #include <test_progs.h> -#include <time.h> #include "test_subprogs.skel.h" #include "test_subprogs_unused.skel.h" -static int duration; +struct toggler_ctx { + int fd; + bool stop; +}; -void test_subprogs(void) +static void *toggle_jit_harden(void *arg) +{ + struct toggler_ctx *ctx = arg; + char two = '2'; + char zero = '0'; + + while (!ctx->stop) { + lseek(ctx->fd, SEEK_SET, 0); + write(ctx->fd, &two, sizeof(two)); + lseek(ctx->fd, SEEK_SET, 0); + write(ctx->fd, &zero, sizeof(zero)); + } + + return NULL; +} + +static void test_subprogs_with_jit_harden_toggling(void) +{ + struct toggler_ctx ctx; + pthread_t toggler; + int err; + unsigned int i, loop = 10; + + ctx.fd = open("/proc/sys/net/core/bpf_jit_harden", O_RDWR); + if (!ASSERT_GE(ctx.fd, 0, "open bpf_jit_harden")) + return; + + ctx.stop = false; + err = pthread_create(&toggler, NULL, toggle_jit_harden, &ctx); + if (!ASSERT_OK(err, "new toggler")) + goto out; + + /* Make toggler thread to run */ + usleep(1); + + for (i = 0; i < loop; i++) { + struct test_subprogs *skel = test_subprogs__open_and_load(); + + if (!ASSERT_OK_PTR(skel, "skel open")) + break; + test_subprogs__destroy(skel); + } + + ctx.stop = true; + pthread_join(toggler, NULL); +out: + close(ctx.fd); +} + +static void test_subprogs_alone(void) { struct test_subprogs *skel; struct test_subprogs_unused *skel2; int err; skel = test_subprogs__open_and_load(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!ASSERT_OK_PTR(skel, "skel_open")) return; err = test_subprogs__attach(skel); - if (CHECK(err, "skel_attach", "failed to attach skeleton: %d\n", err)) + if (!ASSERT_OK(err, "skel attach")) goto cleanup; usleep(1); - CHECK(skel->bss->res1 != 12, "res1", "got %d, exp %d\n", skel->bss->res1, 12); - CHECK(skel->bss->res2 != 17, "res2", "got %d, exp %d\n", skel->bss->res2, 17); - CHECK(skel->bss->res3 != 19, "res3", "got %d, exp %d\n", skel->bss->res3, 19); - CHECK(skel->bss->res4 != 36, "res4", "got %d, exp %d\n", skel->bss->res4, 36); + ASSERT_EQ(skel->bss->res1, 12, "res1"); + ASSERT_EQ(skel->bss->res2, 17, "res2"); + ASSERT_EQ(skel->bss->res3, 19, "res3"); + ASSERT_EQ(skel->bss->res4, 36, "res4"); skel2 = test_subprogs_unused__open_and_load(); ASSERT_OK_PTR(skel2, "unused_progs_skel"); @@ -35,3 +86,11 @@ void test_subprogs(void) cleanup: test_subprogs__destroy(skel); } + +void test_subprogs(void) +{ + if (test__start_subtest("subprogs_alone")) + test_subprogs_alone(); + if (test__start_subtest("subprogs_and_jit_harden")) + test_subprogs_with_jit_harden_toggling(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/subskeleton.c b/tools/testing/selftests/bpf/prog_tests/subskeleton.c new file mode 100644 index 000000000000..9c31b7004f9c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/subskeleton.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include "test_subskeleton.skel.h" +#include "test_subskeleton_lib.subskel.h" + +static void subskeleton_lib_setup(struct bpf_object *obj) +{ + struct test_subskeleton_lib *lib = test_subskeleton_lib__open(obj); + + if (!ASSERT_OK_PTR(lib, "open subskeleton")) + return; + + *lib->rodata.var1 = 1; + *lib->data.var2 = 2; + lib->bss.var3->var3_1 = 3; + lib->bss.var3->var3_2 = 4; + + test_subskeleton_lib__destroy(lib); +} + +static int subskeleton_lib_subresult(struct bpf_object *obj) +{ + struct test_subskeleton_lib *lib = test_subskeleton_lib__open(obj); + int result; + + if (!ASSERT_OK_PTR(lib, "open subskeleton")) + return -EINVAL; + + result = *lib->bss.libout1; + ASSERT_EQ(result, 1 + 2 + 3 + 4 + 5 + 6, "lib subresult"); + + ASSERT_OK_PTR(lib->progs.lib_perf_handler, "lib_perf_handler"); + ASSERT_STREQ(bpf_program__name(lib->progs.lib_perf_handler), + "lib_perf_handler", "program name"); + + ASSERT_OK_PTR(lib->maps.map1, "map1"); + ASSERT_STREQ(bpf_map__name(lib->maps.map1), "map1", "map name"); + + ASSERT_EQ(*lib->data.var5, 5, "__weak var5"); + ASSERT_EQ(*lib->data.var6, 6, "extern var6"); + ASSERT_TRUE(*lib->kconfig.CONFIG_BPF_SYSCALL, "CONFIG_BPF_SYSCALL"); + + test_subskeleton_lib__destroy(lib); + return result; +} + +void test_subskeleton(void) +{ + int err, result; + struct test_subskeleton *skel; + + skel = test_subskeleton__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + skel->rodata->rovar1 = 10; + skel->rodata->var1 = 1; + subskeleton_lib_setup(skel->obj); + + err = test_subskeleton__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + err = test_subskeleton__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + /* trigger tracepoint */ + usleep(1); + + result = subskeleton_lib_subresult(skel->obj) * 10; + ASSERT_EQ(skel->bss->out1, result, "unexpected calculation"); + +cleanup: + test_subskeleton__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/syscall.c b/tools/testing/selftests/bpf/prog_tests/syscall.c index 81e997a69f7a..f4d40001155a 100644 --- a/tools/testing/selftests/bpf/prog_tests/syscall.c +++ b/tools/testing/selftests/bpf/prog_tests/syscall.c @@ -20,20 +20,20 @@ void test_syscall(void) .log_buf = (uintptr_t) verifier_log, .log_size = sizeof(verifier_log), }; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, tattr, .ctx_in = &ctx, .ctx_size_in = sizeof(ctx), - }; + ); struct syscall *skel = NULL; __u64 key = 12, value = 0; - int err; + int err, prog_fd; skel = syscall__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_load")) goto cleanup; - tattr.prog_fd = bpf_program__fd(skel->progs.bpf_prog); - err = bpf_prog_test_run_xattr(&tattr); + prog_fd = bpf_program__fd(skel->progs.bpf_prog); + err = bpf_prog_test_run_opts(prog_fd, &tattr); ASSERT_EQ(err, 0, "err"); ASSERT_EQ(tattr.retval, 1, "retval"); ASSERT_GT(ctx.map_fd, 0, "ctx.map_fd"); diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index 5dc0f425bd11..c4da87ec3ba4 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -12,9 +12,13 @@ static void test_tailcall_1(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall1.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -37,7 +41,7 @@ static void test_tailcall_1(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -53,23 +57,21 @@ static void test_tailcall_1(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != i, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, i, "tailcall retval"); err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -85,13 +87,12 @@ static void test_tailcall_1(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - j = bpf_map__def(prog_array)->max_entries - 1 - i; + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + j = bpf_map__max_entries(prog_array) - 1 - i; snprintf(prog_name, sizeof(prog_name), "classifier_%d", j); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -107,33 +108,30 @@ static void test_tailcall_1(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - j = bpf_map__def(prog_array)->max_entries - 1 - i; + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + j = bpf_map__max_entries(prog_array) - 1 - i; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != j, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, j, "tailcall retval"); err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err >= 0 || errno != ENOENT)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); } out: @@ -150,9 +148,13 @@ static void test_tailcall_2(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall2.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -175,7 +177,7 @@ static void test_tailcall_2(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -191,30 +193,27 @@ static void test_tailcall_2(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 2, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 2, "tailcall retval"); i = 2; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); out: bpf_object__close(obj); } @@ -225,8 +224,12 @@ static void test_tailcall_count(const char *which) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load(which, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -262,10 +265,9 @@ static void test_tailcall_count(const char *which) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); data_map = bpf_object__find_map_by_name(obj, "tailcall.bss"); if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map))) @@ -277,18 +279,17 @@ static void test_tailcall_count(const char *which) i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val != 33, "tailcall count", "err %d errno %d count %d\n", - err, errno, val); + ASSERT_OK(err, "tailcall count"); + ASSERT_EQ(val, 33, "tailcall count"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); out: bpf_object__close(obj); } @@ -319,10 +320,14 @@ static void test_tailcall_4(void) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; static const int zero = 0; char buff[128] = {}; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall4.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -353,7 +358,7 @@ static void test_tailcall_4(void) if (CHECK_FAIL(map_fd < 0)) return; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -369,18 +374,17 @@ static void test_tailcall_4(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != i, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, i, "tailcall retval"); } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY); if (CHECK_FAIL(err)) goto out; @@ -389,10 +393,9 @@ static void test_tailcall_4(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); } out: bpf_object__close(obj); @@ -407,10 +410,14 @@ static void test_tailcall_5(void) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; static const int zero = 0; char buff[128] = {}; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall5.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -441,7 +448,7 @@ static void test_tailcall_5(void) if (CHECK_FAIL(map_fd < 0)) return; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -457,18 +464,17 @@ static void test_tailcall_5(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != i, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, i, "tailcall retval"); } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY); if (CHECK_FAIL(err)) goto out; @@ -477,10 +483,9 @@ static void test_tailcall_5(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 3, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 3, "tailcall retval"); } out: bpf_object__close(obj); @@ -495,8 +500,12 @@ static void test_tailcall_bpf2bpf_1(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf1.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -520,7 +529,7 @@ static void test_tailcall_bpf2bpf_1(void) goto out; /* nop -> jmp */ - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -536,10 +545,9 @@ static void test_tailcall_bpf2bpf_1(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - 0, &retval, &duration); - CHECK(err || retval != 1, "tailcall", - "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); /* jmp -> nop, call subprog that will do tailcall */ i = 1; @@ -547,10 +555,9 @@ static void test_tailcall_bpf2bpf_1(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - 0, &retval, &duration); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); /* make sure that subprog can access ctx and entry prog that * called this subprog can properly return @@ -560,11 +567,9 @@ static void test_tailcall_bpf2bpf_1(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - 0, &retval, &duration); - CHECK(err || retval != sizeof(pkt_v4) * 2, - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 2, "tailcall retval"); out: bpf_object__close(obj); } @@ -579,8 +584,12 @@ static void test_tailcall_bpf2bpf_2(void) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char buff[128] = {}; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = buff, + .data_size_in = sizeof(buff), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf2.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -616,10 +625,9 @@ static void test_tailcall_bpf2bpf_2(void) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 1, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, 1, "tailcall retval"); data_map = bpf_object__find_map_by_name(obj, "tailcall.bss"); if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map))) @@ -631,18 +639,17 @@ static void test_tailcall_bpf2bpf_2(void) i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val != 33, "tailcall count", "err %d errno %d count %d\n", - err, errno, val); + ASSERT_OK(err, "tailcall count"); + ASSERT_EQ(val, 33, "tailcall count"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, - &duration, &retval, NULL); - CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_OK(topts.retval, "tailcall retval"); out: bpf_object__close(obj); } @@ -657,8 +664,12 @@ static void test_tailcall_bpf2bpf_3(void) struct bpf_map *prog_array; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf3.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -681,7 +692,7 @@ static void test_tailcall_bpf2bpf_3(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -697,33 +708,27 @@ static void test_tailcall_bpf2bpf_3(void) goto out; } - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 3, - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 3, "tailcall retval"); i = 1; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4), - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4), "tailcall retval"); i = 0; err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 2, - "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 2, "tailcall retval"); out: bpf_object__close(obj); } @@ -754,8 +759,12 @@ static void test_tailcall_bpf2bpf_4(bool noise) struct bpf_map *prog_array, *data_map; struct bpf_program *prog; struct bpf_object *obj; - __u32 retval, duration; char prog_name[32]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); err = bpf_prog_test_load("tailcall_bpf2bpf4.o", BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); @@ -778,7 +787,7 @@ static void test_tailcall_bpf2bpf_4(bool noise) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -809,15 +818,14 @@ static void test_tailcall_bpf2bpf_4(bool noise) if (CHECK_FAIL(err)) goto out; - err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0, - &duration, &retval, NULL); - CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n", - err, errno, retval); + err = bpf_prog_test_run_opts(main_fd, &topts); + ASSERT_OK(err, "tailcall"); + ASSERT_EQ(topts.retval, sizeof(pkt_v4) * 3, "tailcall retval"); i = 0; err = bpf_map_lookup_elem(data_fd, &i, &val); - CHECK(err || val.count != 31, "tailcall count", "err %d errno %d count %d\n", - err, errno, val.count); + ASSERT_OK(err, "tailcall count"); + ASSERT_EQ(val.count, 31, "tailcall count"); out: bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c index 37c20b5ffa70..61935e7e056a 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c +++ b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c @@ -3,18 +3,22 @@ #include <test_progs.h> #include "test_task_pt_regs.skel.h" +/* uprobe attach point */ +static void trigger_func(void) +{ + asm volatile (""); +} + void test_task_pt_regs(void) { struct test_task_pt_regs *skel; struct bpf_link *uprobe_link; - size_t uprobe_offset; - ssize_t base_addr; + ssize_t uprobe_offset; bool match; - base_addr = get_base_addr(); - if (!ASSERT_GT(base_addr, 0, "get_base_addr")) + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) return; - uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr); skel = test_task_pt_regs__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -32,7 +36,7 @@ void test_task_pt_regs(void) skel->links.handle_uprobe = uprobe_link; /* trigger & validate uprobe */ - get_base_addr(); + trigger_func(); if (!ASSERT_EQ(skel->bss->uprobe_res, 1, "check_uprobe_res")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index c2426df58e17..7ad66a247c02 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -10,17 +10,15 @@ * to drop unexpected traffic. */ -#define _GNU_SOURCE - #include <arpa/inet.h> #include <linux/if.h> #include <linux/if_tun.h> #include <linux/limits.h> #include <linux/sysctl.h> -#include <sched.h> +#include <linux/time_types.h> +#include <linux/net_tstamp.h> #include <stdbool.h> #include <stdio.h> -#include <sys/mount.h> #include <sys/stat.h> #include <unistd.h> @@ -29,6 +27,11 @@ #include "test_tc_neigh_fib.skel.h" #include "test_tc_neigh.skel.h" #include "test_tc_peer.skel.h" +#include "test_tc_dtime.skel.h" + +#ifndef TCP_TX_DELAY +#define TCP_TX_DELAY 37 +#endif #define NS_SRC "ns_src" #define NS_FWD "ns_fwd" @@ -61,6 +64,7 @@ #define CHK_PROG_PIN_FILE "/sys/fs/bpf/test_tc_chk" #define TIMEOUT_MILLIS 10000 +#define NSEC_PER_SEC 1000000000ULL #define log_err(MSG, ...) \ fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ @@ -84,91 +88,6 @@ static int write_file(const char *path, const char *newval) return 0; } -struct nstoken { - int orig_netns_fd; -}; - -static int setns_by_fd(int nsfd) -{ - int err; - - err = setns(nsfd, CLONE_NEWNET); - close(nsfd); - - if (!ASSERT_OK(err, "setns")) - return err; - - /* Switch /sys to the new namespace so that e.g. /sys/class/net - * reflects the devices in the new namespace. - */ - err = unshare(CLONE_NEWNS); - if (!ASSERT_OK(err, "unshare")) - return err; - - /* Make our /sys mount private, so the following umount won't - * trigger the global umount in case it's shared. - */ - err = mount("none", "/sys", NULL, MS_PRIVATE, NULL); - if (!ASSERT_OK(err, "remount private /sys")) - return err; - - err = umount2("/sys", MNT_DETACH); - if (!ASSERT_OK(err, "umount2 /sys")) - return err; - - err = mount("sysfs", "/sys", "sysfs", 0, NULL); - if (!ASSERT_OK(err, "mount /sys")) - return err; - - err = mount("bpffs", "/sys/fs/bpf", "bpf", 0, NULL); - if (!ASSERT_OK(err, "mount /sys/fs/bpf")) - return err; - - return 0; -} - -/** - * open_netns() - Switch to specified network namespace by name. - * - * Returns token with which to restore the original namespace - * using close_netns(). - */ -static struct nstoken *open_netns(const char *name) -{ - int nsfd; - char nspath[PATH_MAX]; - int err; - struct nstoken *token; - - token = malloc(sizeof(struct nstoken)); - if (!ASSERT_OK_PTR(token, "malloc token")) - return NULL; - - token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY); - if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net")) - goto fail; - - snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name); - nsfd = open(nspath, O_RDONLY | O_CLOEXEC); - if (!ASSERT_GE(nsfd, 0, "open netns fd")) - goto fail; - - err = setns_by_fd(nsfd); - if (!ASSERT_OK(err, "setns_by_fd")) - goto fail; - - return token; -fail: - free(token); - return NULL; -} - -static void close_netns(struct nstoken *token) -{ - ASSERT_OK(setns_by_fd(token->orig_netns_fd), "setns_by_fd"); - free(token); -} - static int netns_setup_namespaces(const char *verb) { const char * const *ns = namespaces; @@ -440,6 +359,431 @@ static int set_forwarding(bool enable) return 0; } +static void rcv_tstamp(int fd, const char *expected, size_t s) +{ + struct __kernel_timespec pkt_ts = {}; + char ctl[CMSG_SPACE(sizeof(pkt_ts))]; + struct timespec now_ts; + struct msghdr msg = {}; + __u64 now_ns, pkt_ns; + struct cmsghdr *cmsg; + struct iovec iov; + char data[32]; + int ret; + + iov.iov_base = data; + iov.iov_len = sizeof(data); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = &ctl; + msg.msg_controllen = sizeof(ctl); + + ret = recvmsg(fd, &msg, 0); + if (!ASSERT_EQ(ret, s, "recvmsg")) + return; + ASSERT_STRNEQ(data, expected, s, "expected rcv data"); + + cmsg = CMSG_FIRSTHDR(&msg); + if (cmsg && cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SO_TIMESTAMPNS_NEW) + memcpy(&pkt_ts, CMSG_DATA(cmsg), sizeof(pkt_ts)); + + pkt_ns = pkt_ts.tv_sec * NSEC_PER_SEC + pkt_ts.tv_nsec; + ASSERT_NEQ(pkt_ns, 0, "pkt rcv tstamp"); + + ret = clock_gettime(CLOCK_REALTIME, &now_ts); + ASSERT_OK(ret, "clock_gettime"); + now_ns = now_ts.tv_sec * NSEC_PER_SEC + now_ts.tv_nsec; + + if (ASSERT_GE(now_ns, pkt_ns, "check rcv tstamp")) + ASSERT_LT(now_ns - pkt_ns, 5 * NSEC_PER_SEC, + "check rcv tstamp"); +} + +static void snd_tstamp(int fd, char *b, size_t s) +{ + struct sock_txtime opt = { .clockid = CLOCK_TAI }; + char ctl[CMSG_SPACE(sizeof(__u64))]; + struct timespec now_ts; + struct msghdr msg = {}; + struct cmsghdr *cmsg; + struct iovec iov; + __u64 now_ns; + int ret; + + ret = clock_gettime(CLOCK_TAI, &now_ts); + ASSERT_OK(ret, "clock_get_time(CLOCK_TAI)"); + now_ns = now_ts.tv_sec * NSEC_PER_SEC + now_ts.tv_nsec; + + iov.iov_base = b; + iov.iov_len = s; + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = &ctl; + msg.msg_controllen = sizeof(ctl); + + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_TXTIME; + cmsg->cmsg_len = CMSG_LEN(sizeof(now_ns)); + *(__u64 *)CMSG_DATA(cmsg) = now_ns; + + ret = setsockopt(fd, SOL_SOCKET, SO_TXTIME, &opt, sizeof(opt)); + ASSERT_OK(ret, "setsockopt(SO_TXTIME)"); + + ret = sendmsg(fd, &msg, 0); + ASSERT_EQ(ret, s, "sendmsg"); +} + +static void test_inet_dtime(int family, int type, const char *addr, __u16 port) +{ + int opt = 1, accept_fd = -1, client_fd = -1, listen_fd, err; + char buf[] = "testing testing"; + struct nstoken *nstoken; + + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns dst")) + return; + listen_fd = start_server(family, type, addr, port, 0); + close_netns(nstoken); + + if (!ASSERT_GE(listen_fd, 0, "listen")) + return; + + /* Ensure the kernel puts the (rcv) timestamp for all skb */ + err = setsockopt(listen_fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + &opt, sizeof(opt)); + if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS_NEW)")) + goto done; + + if (type == SOCK_STREAM) { + /* Ensure the kernel set EDT when sending out rst/ack + * from the kernel's ctl_sk. + */ + err = setsockopt(listen_fd, SOL_TCP, TCP_TX_DELAY, &opt, + sizeof(opt)); + if (!ASSERT_OK(err, "setsockopt(TCP_TX_DELAY)")) + goto done; + } + + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns src")) + goto done; + client_fd = connect_to_fd(listen_fd, TIMEOUT_MILLIS); + close_netns(nstoken); + + if (!ASSERT_GE(client_fd, 0, "connect_to_fd")) + goto done; + + if (type == SOCK_STREAM) { + int n; + + accept_fd = accept(listen_fd, NULL, NULL); + if (!ASSERT_GE(accept_fd, 0, "accept")) + goto done; + + n = write(client_fd, buf, sizeof(buf)); + if (!ASSERT_EQ(n, sizeof(buf), "send to server")) + goto done; + rcv_tstamp(accept_fd, buf, sizeof(buf)); + } else { + snd_tstamp(client_fd, buf, sizeof(buf)); + rcv_tstamp(listen_fd, buf, sizeof(buf)); + } + +done: + close(listen_fd); + if (accept_fd != -1) + close(accept_fd); + if (client_fd != -1) + close(client_fd); +} + +static int netns_load_dtime_bpf(struct test_tc_dtime *skel) +{ + struct nstoken *nstoken; + +#define PIN_FNAME(__file) "/sys/fs/bpf/" #__file +#define PIN(__prog) ({ \ + int err = bpf_program__pin(skel->progs.__prog, PIN_FNAME(__prog)); \ + if (!ASSERT_OK(err, "pin " #__prog)) \ + goto fail; \ + }) + + /* setup ns_src tc progs */ + nstoken = open_netns(NS_SRC); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC)) + return -1; + PIN(egress_host); + PIN(ingress_host); + SYS("tc qdisc add dev veth_src clsact"); + SYS("tc filter add dev veth_src ingress bpf da object-pinned " + PIN_FNAME(ingress_host)); + SYS("tc filter add dev veth_src egress bpf da object-pinned " + PIN_FNAME(egress_host)); + close_netns(nstoken); + + /* setup ns_dst tc progs */ + nstoken = open_netns(NS_DST); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_DST)) + return -1; + PIN(egress_host); + PIN(ingress_host); + SYS("tc qdisc add dev veth_dst clsact"); + SYS("tc filter add dev veth_dst ingress bpf da object-pinned " + PIN_FNAME(ingress_host)); + SYS("tc filter add dev veth_dst egress bpf da object-pinned " + PIN_FNAME(egress_host)); + close_netns(nstoken); + + /* setup ns_fwd tc progs */ + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD)) + return -1; + PIN(ingress_fwdns_prio100); + PIN(egress_fwdns_prio100); + PIN(ingress_fwdns_prio101); + PIN(egress_fwdns_prio101); + SYS("tc qdisc add dev veth_dst_fwd clsact"); + SYS("tc filter add dev veth_dst_fwd ingress prio 100 bpf da object-pinned " + PIN_FNAME(ingress_fwdns_prio100)); + SYS("tc filter add dev veth_dst_fwd ingress prio 101 bpf da object-pinned " + PIN_FNAME(ingress_fwdns_prio101)); + SYS("tc filter add dev veth_dst_fwd egress prio 100 bpf da object-pinned " + PIN_FNAME(egress_fwdns_prio100)); + SYS("tc filter add dev veth_dst_fwd egress prio 101 bpf da object-pinned " + PIN_FNAME(egress_fwdns_prio101)); + SYS("tc qdisc add dev veth_src_fwd clsact"); + SYS("tc filter add dev veth_src_fwd ingress prio 100 bpf da object-pinned " + PIN_FNAME(ingress_fwdns_prio100)); + SYS("tc filter add dev veth_src_fwd ingress prio 101 bpf da object-pinned " + PIN_FNAME(ingress_fwdns_prio101)); + SYS("tc filter add dev veth_src_fwd egress prio 100 bpf da object-pinned " + PIN_FNAME(egress_fwdns_prio100)); + SYS("tc filter add dev veth_src_fwd egress prio 101 bpf da object-pinned " + PIN_FNAME(egress_fwdns_prio101)); + close_netns(nstoken); + +#undef PIN + + return 0; + +fail: + close_netns(nstoken); + return -1; +} + +enum { + INGRESS_FWDNS_P100, + INGRESS_FWDNS_P101, + EGRESS_FWDNS_P100, + EGRESS_FWDNS_P101, + INGRESS_ENDHOST, + EGRESS_ENDHOST, + SET_DTIME, + __MAX_CNT, +}; + +const char *cnt_names[] = { + "ingress_fwdns_p100", + "ingress_fwdns_p101", + "egress_fwdns_p100", + "egress_fwdns_p101", + "ingress_endhost", + "egress_endhost", + "set_dtime", +}; + +enum { + TCP_IP6_CLEAR_DTIME, + TCP_IP4, + TCP_IP6, + UDP_IP4, + UDP_IP6, + TCP_IP4_RT_FWD, + TCP_IP6_RT_FWD, + UDP_IP4_RT_FWD, + UDP_IP6_RT_FWD, + UKN_TEST, + __NR_TESTS, +}; + +const char *test_names[] = { + "tcp ip6 clear dtime", + "tcp ip4", + "tcp ip6", + "udp ip4", + "udp ip6", + "tcp ip4 rt fwd", + "tcp ip6 rt fwd", + "udp ip4 rt fwd", + "udp ip6 rt fwd", +}; + +static const char *dtime_cnt_str(int test, int cnt) +{ + static char name[64]; + + snprintf(name, sizeof(name), "%s %s", test_names[test], cnt_names[cnt]); + + return name; +} + +static const char *dtime_err_str(int test, int cnt) +{ + static char name[64]; + + snprintf(name, sizeof(name), "%s %s errs", test_names[test], + cnt_names[cnt]); + + return name; +} + +static void test_tcp_clear_dtime(struct test_tc_dtime *skel) +{ + int i, t = TCP_IP6_CLEAR_DTIME; + __u32 *dtimes = skel->bss->dtimes[t]; + __u32 *errs = skel->bss->errs[t]; + + skel->bss->test = t; + test_inet_dtime(AF_INET6, SOCK_STREAM, IP6_DST, 0); + + ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0, + dtime_cnt_str(t, INGRESS_FWDNS_P100)); + ASSERT_EQ(dtimes[INGRESS_FWDNS_P101], 0, + dtime_cnt_str(t, INGRESS_FWDNS_P101)); + ASSERT_GT(dtimes[EGRESS_FWDNS_P100], 0, + dtime_cnt_str(t, EGRESS_FWDNS_P100)); + ASSERT_EQ(dtimes[EGRESS_FWDNS_P101], 0, + dtime_cnt_str(t, EGRESS_FWDNS_P101)); + ASSERT_GT(dtimes[EGRESS_ENDHOST], 0, + dtime_cnt_str(t, EGRESS_ENDHOST)); + ASSERT_GT(dtimes[INGRESS_ENDHOST], 0, + dtime_cnt_str(t, INGRESS_ENDHOST)); + + for (i = INGRESS_FWDNS_P100; i < __MAX_CNT; i++) + ASSERT_EQ(errs[i], 0, dtime_err_str(t, i)); +} + +static void test_tcp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd) +{ + __u32 *dtimes, *errs; + const char *addr; + int i, t; + + if (family == AF_INET) { + t = bpf_fwd ? TCP_IP4 : TCP_IP4_RT_FWD; + addr = IP4_DST; + } else { + t = bpf_fwd ? TCP_IP6 : TCP_IP6_RT_FWD; + addr = IP6_DST; + } + + dtimes = skel->bss->dtimes[t]; + errs = skel->bss->errs[t]; + + skel->bss->test = t; + test_inet_dtime(family, SOCK_STREAM, addr, 0); + + /* fwdns_prio100 prog does not read delivery_time_type, so + * kernel puts the (rcv) timetamp in __sk_buff->tstamp + */ + ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0, + dtime_cnt_str(t, INGRESS_FWDNS_P100)); + for (i = INGRESS_FWDNS_P101; i < SET_DTIME; i++) + ASSERT_GT(dtimes[i], 0, dtime_cnt_str(t, i)); + + for (i = INGRESS_FWDNS_P100; i < __MAX_CNT; i++) + ASSERT_EQ(errs[i], 0, dtime_err_str(t, i)); +} + +static void test_udp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd) +{ + __u32 *dtimes, *errs; + const char *addr; + int i, t; + + if (family == AF_INET) { + t = bpf_fwd ? UDP_IP4 : UDP_IP4_RT_FWD; + addr = IP4_DST; + } else { + t = bpf_fwd ? UDP_IP6 : UDP_IP6_RT_FWD; + addr = IP6_DST; + } + + dtimes = skel->bss->dtimes[t]; + errs = skel->bss->errs[t]; + + skel->bss->test = t; + test_inet_dtime(family, SOCK_DGRAM, addr, 0); + + ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0, + dtime_cnt_str(t, INGRESS_FWDNS_P100)); + /* non mono delivery time is not forwarded */ + ASSERT_EQ(dtimes[INGRESS_FWDNS_P101], 0, + dtime_cnt_str(t, INGRESS_FWDNS_P100)); + for (i = EGRESS_FWDNS_P100; i < SET_DTIME; i++) + ASSERT_GT(dtimes[i], 0, dtime_cnt_str(t, i)); + + for (i = INGRESS_FWDNS_P100; i < __MAX_CNT; i++) + ASSERT_EQ(errs[i], 0, dtime_err_str(t, i)); +} + +static void test_tc_redirect_dtime(struct netns_setup_result *setup_result) +{ + struct test_tc_dtime *skel; + struct nstoken *nstoken; + int err; + + skel = test_tc_dtime__open(); + if (!ASSERT_OK_PTR(skel, "test_tc_dtime__open")) + return; + + skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + + err = test_tc_dtime__load(skel); + if (!ASSERT_OK(err, "test_tc_dtime__load")) + goto done; + + if (netns_load_dtime_bpf(skel)) + goto done; + + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + goto done; + err = set_forwarding(false); + close_netns(nstoken); + if (!ASSERT_OK(err, "disable forwarding")) + goto done; + + test_tcp_clear_dtime(skel); + + test_tcp_dtime(skel, AF_INET, true); + test_tcp_dtime(skel, AF_INET6, true); + test_udp_dtime(skel, AF_INET, true); + test_udp_dtime(skel, AF_INET6, true); + + /* Test the kernel ip[6]_forward path instead + * of bpf_redirect_neigh(). + */ + nstoken = open_netns(NS_FWD); + if (!ASSERT_OK_PTR(nstoken, "setns fwd")) + goto done; + err = set_forwarding(true); + close_netns(nstoken); + if (!ASSERT_OK(err, "enable forwarding")) + goto done; + + test_tcp_dtime(skel, AF_INET, false); + test_tcp_dtime(skel, AF_INET6, false); + test_udp_dtime(skel, AF_INET, false); + test_udp_dtime(skel, AF_INET6, false); + +done: + test_tc_dtime__destroy(skel); +} + static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result) { struct nstoken *nstoken = NULL; @@ -787,6 +1131,7 @@ static void *test_tc_redirect_run_tests(void *arg) RUN_TEST(tc_redirect_peer_l3); RUN_TEST(tc_redirect_neigh); RUN_TEST(tc_redirect_neigh_fib); + RUN_TEST(tc_redirect_dtime); return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c new file mode 100644 index 000000000000..c381faaae741 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2022 Sony Group Corporation */ +#include <sys/prctl.h> +#include <test_progs.h> +#include "bpf_syscall_macro.skel.h" + +void test_bpf_syscall_macro(void) +{ + struct bpf_syscall_macro *skel = NULL; + int err; + int exp_arg1 = 1001; + unsigned long exp_arg2 = 12; + unsigned long exp_arg3 = 13; + unsigned long exp_arg4 = 14; + unsigned long exp_arg5 = 15; + + /* check whether it can open program */ + skel = bpf_syscall_macro__open(); + if (!ASSERT_OK_PTR(skel, "bpf_syscall_macro__open")) + return; + + skel->rodata->filter_pid = getpid(); + + /* check whether it can load program */ + err = bpf_syscall_macro__load(skel); + if (!ASSERT_OK(err, "bpf_syscall_macro__load")) + goto cleanup; + + /* check whether it can attach kprobe */ + err = bpf_syscall_macro__attach(skel); + if (!ASSERT_OK(err, "bpf_syscall_macro__attach")) + goto cleanup; + + /* check whether args of syscall are copied correctly */ + prctl(exp_arg1, exp_arg2, exp_arg3, exp_arg4, exp_arg5); +#if defined(__aarch64__) || defined(__s390__) + ASSERT_NEQ(skel->bss->arg1, exp_arg1, "syscall_arg1"); +#else + ASSERT_EQ(skel->bss->arg1, exp_arg1, "syscall_arg1"); +#endif + ASSERT_EQ(skel->bss->arg2, exp_arg2, "syscall_arg2"); + ASSERT_EQ(skel->bss->arg3, exp_arg3, "syscall_arg3"); + /* it cannot copy arg4 when uses PT_REGS_PARM4 on x86_64 */ +#ifdef __x86_64__ + ASSERT_NEQ(skel->bss->arg4_cx, exp_arg4, "syscall_arg4_from_cx"); +#else + ASSERT_EQ(skel->bss->arg4_cx, exp_arg4, "syscall_arg4_from_cx"); +#endif + ASSERT_EQ(skel->bss->arg4, exp_arg4, "syscall_arg4"); + ASSERT_EQ(skel->bss->arg5, exp_arg5, "syscall_arg5"); + + /* check whether args of syscall are copied correctly for CORE variants */ + ASSERT_EQ(skel->bss->arg1_core, exp_arg1, "syscall_arg1_core_variant"); + ASSERT_EQ(skel->bss->arg2_core, exp_arg2, "syscall_arg2_core_variant"); + ASSERT_EQ(skel->bss->arg3_core, exp_arg3, "syscall_arg3_core_variant"); + /* it cannot copy arg4 when uses PT_REGS_PARM4_CORE on x86_64 */ +#ifdef __x86_64__ + ASSERT_NEQ(skel->bss->arg4_core_cx, exp_arg4, "syscall_arg4_from_cx_core_variant"); +#else + ASSERT_EQ(skel->bss->arg4_core_cx, exp_arg4, "syscall_arg4_from_cx_core_variant"); +#endif + ASSERT_EQ(skel->bss->arg4_core, exp_arg4, "syscall_arg4_core_variant"); + ASSERT_EQ(skel->bss->arg5_core, exp_arg5, "syscall_arg5_core_variant"); + + ASSERT_EQ(skel->bss->option_syscall, exp_arg1, "BPF_KPROBE_SYSCALL_option"); + ASSERT_EQ(skel->bss->arg2_syscall, exp_arg2, "BPF_KPROBE_SYSCALL_arg2"); + ASSERT_EQ(skel->bss->arg3_syscall, exp_arg3, "BPF_KPROBE_SYSCALL_arg3"); + ASSERT_EQ(skel->bss->arg4_syscall, exp_arg4, "BPF_KPROBE_SYSCALL_arg4"); + ASSERT_EQ(skel->bss->arg5_syscall, exp_arg5, "BPF_KPROBE_SYSCALL_arg5"); + +cleanup: + bpf_syscall_macro__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c index 97d8a6f84f4a..b13feceb38f1 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_ima.c +++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c @@ -13,14 +13,17 @@ #include "ima.skel.h" -static int run_measured_process(const char *measured_dir, u32 *monitored_pid) +#define MAX_SAMPLES 4 + +static int _run_measured_process(const char *measured_dir, u32 *monitored_pid, + const char *cmd) { int child_pid, child_status; child_pid = fork(); if (child_pid == 0) { *monitored_pid = getpid(); - execlp("./ima_setup.sh", "./ima_setup.sh", "run", measured_dir, + execlp("./ima_setup.sh", "./ima_setup.sh", cmd, measured_dir, NULL); exit(errno); @@ -32,19 +35,39 @@ static int run_measured_process(const char *measured_dir, u32 *monitored_pid) return -EINVAL; } -static u64 ima_hash_from_bpf; +static int run_measured_process(const char *measured_dir, u32 *monitored_pid) +{ + return _run_measured_process(measured_dir, monitored_pid, "run"); +} + +static u64 ima_hash_from_bpf[MAX_SAMPLES]; +static int ima_hash_from_bpf_idx; static int process_sample(void *ctx, void *data, size_t len) { - ima_hash_from_bpf = *((u64 *)data); + if (ima_hash_from_bpf_idx >= MAX_SAMPLES) + return -ENOSPC; + + ima_hash_from_bpf[ima_hash_from_bpf_idx++] = *((u64 *)data); return 0; } +static void test_init(struct ima__bss *bss) +{ + ima_hash_from_bpf_idx = 0; + + bss->use_ima_file_hash = false; + bss->enable_bprm_creds_for_exec = false; + bss->enable_kernel_read_file = false; + bss->test_deny = false; +} + void test_test_ima(void) { char measured_dir_template[] = "/tmp/ima_measuredXXXXXX"; struct ring_buffer *ringbuf = NULL; const char *measured_dir; + u64 bin_true_sample; char cmd[256]; int err, duration = 0; @@ -72,13 +95,127 @@ void test_test_ima(void) if (CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno)) goto close_clean; + /* + * Test #1 + * - Goal: obtain a sample with the bpf_ima_inode_hash() helper + * - Expected result: 1 sample (/bin/true) + */ + test_init(skel->bss); err = run_measured_process(measured_dir, &skel->bss->monitored_pid); - if (CHECK(err, "run_measured_process", "err = %d\n", err)) + if (CHECK(err, "run_measured_process #1", "err = %d\n", err)) goto close_clean; err = ring_buffer__consume(ringbuf); ASSERT_EQ(err, 1, "num_samples_or_err"); - ASSERT_NEQ(ima_hash_from_bpf, 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + + /* + * Test #2 + * - Goal: obtain samples with the bpf_ima_file_hash() helper + * - Expected result: 2 samples (./ima_setup.sh, /bin/true) + */ + test_init(skel->bss); + skel->bss->use_ima_file_hash = true; + err = run_measured_process(measured_dir, &skel->bss->monitored_pid); + if (CHECK(err, "run_measured_process #2", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 2, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + bin_true_sample = ima_hash_from_bpf[1]; + + /* + * Test #3 + * - Goal: confirm that bpf_ima_inode_hash() returns a non-fresh digest + * - Expected result: 2 samples (/bin/true: non-fresh, fresh) + */ + test_init(skel->bss); + + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "modify-bin"); + if (CHECK(err, "modify-bin #3", "err = %d\n", err)) + goto close_clean; + + skel->bss->enable_bprm_creds_for_exec = true; + err = run_measured_process(measured_dir, &skel->bss->monitored_pid); + if (CHECK(err, "run_measured_process #3", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 2, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + ASSERT_EQ(ima_hash_from_bpf[0], bin_true_sample, "sample_equal_or_err"); + /* IMA refreshed the digest. */ + ASSERT_NEQ(ima_hash_from_bpf[1], bin_true_sample, + "sample_different_or_err"); + + /* + * Test #4 + * - Goal: verify that bpf_ima_file_hash() returns a fresh digest + * - Expected result: 4 samples (./ima_setup.sh: fresh, fresh; + * /bin/true: fresh, fresh) + */ + test_init(skel->bss); + skel->bss->use_ima_file_hash = true; + skel->bss->enable_bprm_creds_for_exec = true; + err = run_measured_process(measured_dir, &skel->bss->monitored_pid); + if (CHECK(err, "run_measured_process #4", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 4, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[2], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[3], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[2], bin_true_sample, + "sample_different_or_err"); + ASSERT_EQ(ima_hash_from_bpf[3], ima_hash_from_bpf[2], + "sample_equal_or_err"); + + skel->bss->use_ima_file_hash = false; + skel->bss->enable_bprm_creds_for_exec = false; + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "restore-bin"); + if (CHECK(err, "restore-bin #3", "err = %d\n", err)) + goto close_clean; + + /* + * Test #5 + * - Goal: obtain a sample from the kernel_read_file hook + * - Expected result: 2 samples (./ima_setup.sh, policy_test) + */ + test_init(skel->bss); + skel->bss->use_ima_file_hash = true; + skel->bss->enable_kernel_read_file = true; + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "load-policy"); + if (CHECK(err, "run_measured_process #5", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 2, "num_samples_or_err"); + ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash"); + ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash"); + + /* + * Test #6 + * - Goal: ensure that the kernel_read_file hook denies an operation + * - Expected result: 0 samples + */ + test_init(skel->bss); + skel->bss->enable_kernel_read_file = true; + skel->bss->test_deny = true; + err = _run_measured_process(measured_dir, &skel->bss->monitored_pid, + "load-policy"); + if (CHECK(!err, "run_measured_process #6", "err = %d\n", err)) + goto close_clean; + + err = ring_buffer__consume(ringbuf); + ASSERT_EQ(err, 0, "num_samples_or_err"); close_clean: snprintf(cmd, sizeof(cmd), "./ima_setup.sh cleanup %s", measured_dir); diff --git a/tools/testing/selftests/bpf/prog_tests/test_profiler.c b/tools/testing/selftests/bpf/prog_tests/test_profiler.c index 4ca275101ee0..de24e8f0e738 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_profiler.c +++ b/tools/testing/selftests/bpf/prog_tests/test_profiler.c @@ -8,20 +8,20 @@ static int sanity_run(struct bpf_program *prog) { - struct bpf_prog_test_run_attr test_attr = {}; + LIBBPF_OPTS(bpf_test_run_opts, test_attr); __u64 args[] = {1, 2, 3}; - __u32 duration = 0; int err, prog_fd; prog_fd = bpf_program__fd(prog); - test_attr.prog_fd = prog_fd; test_attr.ctx_in = args; test_attr.ctx_size_in = sizeof(args); - err = bpf_prog_test_run_xattr(&test_attr); - if (CHECK(err || test_attr.retval, "test_run", - "err %d errno %d retval %d duration %d\n", - err, errno, test_attr.retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &test_attr); + if (!ASSERT_OK(err, "test_run")) + return -1; + + if (!ASSERT_OK(test_attr.retval, "test_run retval")) return -1; + return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c index cf1215531920..ae93411fd582 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c +++ b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c @@ -6,15 +6,18 @@ static int sanity_run(struct bpf_program *prog) { - __u32 duration, retval; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); prog_fd = bpf_program__fd(prog); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - if (CHECK(err || retval != 123, "test_run", - "err %d errno %d retval %d duration %d\n", - err, errno, retval, duration)) + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run")) + return -1; + if (!ASSERT_EQ(topts.retval, 123, "test_run retval")) return -1; return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index 0f4e49e622cd..7eb049214859 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -6,7 +6,7 @@ static int timer(struct timer *timer_skel) { int err, prog_fd; - __u32 duration = 0, retval; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = timer__attach(timer_skel); if (!ASSERT_OK(err, "timer_attach")) @@ -16,10 +16,9 @@ static int timer(struct timer *timer_skel) ASSERT_EQ(timer_skel->data->callback2_check, 52, "callback2_check1"); prog_fd = bpf_program__fd(timer_skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); timer__detach(timer_skel); usleep(50); /* 10 usecs should be enough, but give it extra */ diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c index 949a0617869d..2ee5f5ae11d4 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c @@ -6,19 +6,18 @@ static int timer_mim(struct timer_mim *timer_skel) { - __u32 duration = 0, retval; __u64 cnt1, cnt2; int err, prog_fd, key1 = 1; + LIBBPF_OPTS(bpf_test_run_opts, topts); err = timer_mim__attach(timer_skel); if (!ASSERT_OK(err, "timer_attach")) return err; prog_fd = bpf_program__fd(timer_skel->progs.test1); - err = bpf_prog_test_run(prog_fd, 1, NULL, 0, - NULL, NULL, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); - ASSERT_EQ(retval, 0, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); timer_mim__detach(timer_skel); /* check that timer_cb[12] are incrementing 'cnt' */ diff --git a/tools/testing/selftests/bpf/prog_tests/trace_ext.c b/tools/testing/selftests/bpf/prog_tests/trace_ext.c index 924441d4362d..aabdff7bea3e 100644 --- a/tools/testing/selftests/bpf/prog_tests/trace_ext.c +++ b/tools/testing/selftests/bpf/prog_tests/trace_ext.c @@ -23,8 +23,12 @@ void test_trace_ext(void) int err, pkt_fd, ext_fd; struct bpf_program *prog; char buf[100]; - __u32 retval; __u64 len; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); /* open/load/attach test_pkt_md_access */ skel_pkt = test_pkt_md_access__open_and_load(); @@ -77,32 +81,32 @@ void test_trace_ext(void) /* load/attach tracing */ err = test_trace_ext_tracing__load(skel_trace); - if (CHECK(err, "setup", "tracing/test_pkt_md_access_new load failed\n")) { + if (!ASSERT_OK(err, "tracing/test_pkt_md_access_new load")) { libbpf_strerror(err, buf, sizeof(buf)); fprintf(stderr, "%s\n", buf); goto cleanup; } err = test_trace_ext_tracing__attach(skel_trace); - if (CHECK(err, "setup", "tracing/test_pkt_md_access_new attach failed: %d\n", err)) + if (!ASSERT_OK(err, "tracing/test_pkt_md_access_new attach")) goto cleanup; /* trigger the test */ - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), - NULL, NULL, &retval, &duration); - CHECK(err || retval, "run", "err %d errno %d retval %d\n", err, errno, retval); + err = bpf_prog_test_run_opts(pkt_fd, &topts); + ASSERT_OK(err, "test_run_opts err"); + ASSERT_OK(topts.retval, "test_run_opts retval"); bss_ext = skel_ext->bss; bss_trace = skel_trace->bss; len = bss_ext->ext_called; - CHECK(bss_ext->ext_called == 0, - "check", "failed to trigger freplace/test_pkt_md_access\n"); - CHECK(bss_trace->fentry_called != len, - "check", "failed to trigger fentry/test_pkt_md_access_new\n"); - CHECK(bss_trace->fexit_called != len, - "check", "failed to trigger fexit/test_pkt_md_access_new\n"); + ASSERT_NEQ(bss_ext->ext_called, 0, + "failed to trigger freplace/test_pkt_md_access"); + ASSERT_EQ(bss_trace->fentry_called, len, + "failed to trigger fentry/test_pkt_md_access_new"); + ASSERT_EQ(bss_trace->fexit_called, len, + "failed to trigger fexit/test_pkt_md_access_new"); cleanup: test_trace_ext_tracing__destroy(skel_trace); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp.c b/tools/testing/selftests/bpf/prog_tests/xdp.c index ac65456b7ab8..ec21c53cb1da 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp.c @@ -13,8 +13,14 @@ void test_xdp(void) char buf[128]; struct ipv6hdr iph6; struct iphdr iph; - __u32 duration, retval, size; int err, prog_fd, map_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) @@ -26,21 +32,23 @@ void test_xdp(void) bpf_map_update_elem(map_fd, &key4, &value4, 0); bpf_map_update_elem(map_fd, &key6, &value6, 0); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); + err = bpf_prog_test_run_opts(prog_fd, &topts); memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); - CHECK(err || retval != XDP_TX || size != 74 || - iph.protocol != IPPROTO_IPIP, "ipv4", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv4 test_run retval"); + ASSERT_EQ(topts.data_size_out, 74, "ipv4 test_run data_size_out"); + ASSERT_EQ(iph.protocol, IPPROTO_IPIP, "ipv4 test_run iph.protocol"); - err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = sizeof(buf); + + err = bpf_prog_test_run_opts(prog_fd, &topts); memcpy(&iph6, buf + sizeof(struct ethhdr), sizeof(iph6)); - CHECK(err || retval != XDP_TX || size != 114 || - iph6.nexthdr != IPPROTO_IPV6, "ipv6", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv6 test_run retval"); + ASSERT_EQ(topts.data_size_out, 114, "ipv6 test_run data_size_out"); + ASSERT_EQ(iph6.nexthdr, IPPROTO_IPV6, "ipv6 test_run iph6.nexthdr"); out: bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c new file mode 100644 index 000000000000..2f033da4cd45 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> + +static void test_xdp_update_frags(void) +{ + const char *file = "./test_xdp_update_frags.o"; + int err, prog_fd, max_skb_frags, buf_size, num; + struct bpf_program *prog; + struct bpf_object *obj; + __u32 *offset; + __u8 *buf; + FILE *f; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(128); + if (!ASSERT_OK_PTR(buf, "alloc buf 128b")) + goto out; + + memset(buf, 0, 128); + offset = (__u32 *)buf; + *offset = 16; + buf[*offset] = 0xaa; /* marker at offset 16 (head) */ + buf[*offset + 15] = 0xaa; /* marker at offset 31 (head) */ + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 128; + topts.data_size_out = 128; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[16,31]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[16], 0xbb, "xdp_update_frag buf[16]"); + ASSERT_EQ(buf[31], 0xbb, "xdp_update_frag buf[31]"); + + free(buf); + + buf = malloc(9000); + if (!ASSERT_OK_PTR(buf, "alloc buf 9Kb")) + goto out; + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 5000; + buf[*offset] = 0xaa; /* marker at offset 5000 (frag0) */ + buf[*offset + 15] = 0xaa; /* marker at offset 5015 (frag0) */ + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 9000; + topts.data_size_out = 9000; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[5000,5015]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[5000], 0xbb, "xdp_update_frag buf[5000]"); + ASSERT_EQ(buf[5015], 0xbb, "xdp_update_frag buf[5015]"); + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 3510; + buf[*offset] = 0xaa; /* marker at offset 3510 (head) */ + buf[*offset + 15] = 0xaa; /* marker at offset 3525 (frag0) */ + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[3510,3525]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[3510], 0xbb, "xdp_update_frag buf[3510]"); + ASSERT_EQ(buf[3525], 0xbb, "xdp_update_frag buf[3525]"); + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 7606; + buf[*offset] = 0xaa; /* marker at offset 7606 (frag0) */ + buf[*offset + 15] = 0xaa; /* marker at offset 7621 (frag1) */ + + err = bpf_prog_test_run_opts(prog_fd, &topts); + + /* test_xdp_update_frags: buf[7606,7621]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(topts.retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[7606], 0xbb, "xdp_update_frag buf[7606]"); + ASSERT_EQ(buf[7621], 0xbb, "xdp_update_frag buf[7621]"); + + free(buf); + + /* test_xdp_update_frags: unsupported buffer size */ + f = fopen("/proc/sys/net/core/max_skb_frags", "r"); + if (!ASSERT_OK_PTR(f, "max_skb_frag file pointer")) + goto out; + + num = fscanf(f, "%d", &max_skb_frags); + fclose(f); + + if (!ASSERT_EQ(num, 1, "max_skb_frags read failed")) + goto out; + + /* xdp_buff linear area size is always set to 4096 in the + * bpf_prog_test_run_xdp routine. + */ + buf_size = 4096 + (max_skb_frags + 1) * sysconf(_SC_PAGE_SIZE); + buf = malloc(buf_size); + if (!ASSERT_OK_PTR(buf, "alloc buf")) + goto out; + + memset(buf, 0, buf_size); + offset = (__u32 *)buf; + *offset = 16; + buf[*offset] = 0xaa; + buf[*offset + 15] = 0xaa; + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = buf_size; + topts.data_size_out = buf_size; + + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_EQ(err, -ENOMEM, + "unsupported buf size, possible non-default /proc/sys/net/core/max_skb_flags?"); + free(buf); +out: + bpf_object__close(obj); +} + +void test_xdp_adjust_frags(void) +{ + if (test__start_subtest("xdp_adjust_frags")) + test_xdp_update_frags(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 3f5a17c38be5..21ceac24e174 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -5,28 +5,35 @@ static void test_xdp_adjust_tail_shrink(void) { const char *file = "./test_xdp_adjust_tail_shrink.o"; - __u32 duration, retval, size, expect_sz; + __u32 expect_sz; struct bpf_object *obj; int err, prog_fd; char buf[128]; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (CHECK_FAIL(err)) + if (ASSERT_OK(err, "test_xdp_adjust_tail_shrink")) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - - CHECK(err || retval != XDP_DROP, - "ipv4", "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(topts.retval, XDP_DROP, "ipv4 retval"); expect_sz = sizeof(pkt_v6) - 20; /* Test shrink with 20 bytes */ - err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); - CHECK(err || retval != XDP_TX || size != expect_sz, - "ipv6", "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, retval, size, expect_sz); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_size_out = sizeof(buf); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv6 retval"); + ASSERT_EQ(topts.data_size_out, expect_sz, "ipv6 size"); + bpf_object__close(obj); } @@ -35,25 +42,31 @@ static void test_xdp_adjust_tail_grow(void) const char *file = "./test_xdp_adjust_tail_grow.o"; struct bpf_object *obj; char buf[4096]; /* avoid segfault: large buf to hold grow results */ - __u32 duration, retval, size, expect_sz; + __u32 expect_sz; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = 1, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (CHECK_FAIL(err)) + if (ASSERT_OK(err, "test_xdp_adjust_tail_grow")) return; - err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != XDP_DROP, - "ipv4", "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(topts.retval, XDP_DROP, "ipv4 retval"); expect_sz = sizeof(pkt_v6) + 40; /* Test grow with 40 bytes */ - err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6) /* 74 */, - buf, &size, &retval, &duration); - CHECK(err || retval != XDP_TX || size != expect_sz, - "ipv6", "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, retval, size, expect_sz); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "ipv6"); + ASSERT_EQ(topts.retval, XDP_TX, "ipv6 retval"); + ASSERT_EQ(topts.data_size_out, expect_sz, "ipv6 size"); bpf_object__close(obj); } @@ -65,18 +78,18 @@ static void test_xdp_adjust_tail_grow2(void) int tailroom = 320; /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info))*/; struct bpf_object *obj; int err, cnt, i; - int max_grow; + int max_grow, prog_fd; - struct bpf_prog_test_run_attr tattr = { + LIBBPF_OPTS(bpf_test_run_opts, tattr, .repeat = 1, .data_in = &buf, .data_out = &buf, .data_size_in = 0, /* Per test */ .data_size_out = 0, /* Per test */ - }; + ); - err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &tattr.prog_fd); - if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (ASSERT_OK(err, "test_xdp_adjust_tail_grow")) return; /* Test case-64 */ @@ -84,49 +97,171 @@ static void test_xdp_adjust_tail_grow2(void) tattr.data_size_in = 64; /* Determine test case via pkt size */ tattr.data_size_out = 128; /* Limit copy_size */ /* Kernel side alloc packet memory area that is zero init */ - err = bpf_prog_test_run_xattr(&tattr); + err = bpf_prog_test_run_opts(prog_fd, &tattr); - CHECK_ATTR(errno != ENOSPC /* Due limit copy_size in bpf_test_finish */ - || tattr.retval != XDP_TX - || tattr.data_size_out != 192, /* Expected grow size */ - "case-64", - "err %d errno %d retval %d size %d\n", - err, errno, tattr.retval, tattr.data_size_out); + ASSERT_EQ(errno, ENOSPC, "case-64 errno"); /* Due limit copy_size in bpf_test_finish */ + ASSERT_EQ(tattr.retval, XDP_TX, "case-64 retval"); + ASSERT_EQ(tattr.data_size_out, 192, "case-64 data_size_out"); /* Expected grow size */ /* Extra checks for data contents */ - CHECK_ATTR(tattr.data_size_out != 192 - || buf[0] != 1 || buf[63] != 1 /* 0-63 memset to 1 */ - || buf[64] != 0 || buf[127] != 0 /* 64-127 memset to 0 */ - || buf[128] != 1 || buf[191] != 1, /*128-191 memset to 1 */ - "case-64-data", - "err %d errno %d retval %d size %d\n", - err, errno, tattr.retval, tattr.data_size_out); + ASSERT_EQ(buf[0], 1, "case-64-data buf[0]"); /* 0-63 memset to 1 */ + ASSERT_EQ(buf[63], 1, "case-64-data buf[63]"); + ASSERT_EQ(buf[64], 0, "case-64-data buf[64]"); /* 64-127 memset to 0 */ + ASSERT_EQ(buf[127], 0, "case-64-data buf[127]"); + ASSERT_EQ(buf[128], 1, "case-64-data buf[128]"); /* 128-191 memset to 1 */ + ASSERT_EQ(buf[191], 1, "case-64-data buf[191]"); /* Test case-128 */ memset(buf, 2, sizeof(buf)); tattr.data_size_in = 128; /* Determine test case via pkt size */ tattr.data_size_out = sizeof(buf); /* Copy everything */ - err = bpf_prog_test_run_xattr(&tattr); + err = bpf_prog_test_run_opts(prog_fd, &tattr); max_grow = 4096 - XDP_PACKET_HEADROOM - tailroom; /* 3520 */ - CHECK_ATTR(err - || tattr.retval != XDP_TX - || tattr.data_size_out != max_grow,/* Expect max grow size */ - "case-128", - "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, tattr.retval, tattr.data_size_out, max_grow); + ASSERT_OK(err, "case-128"); + ASSERT_EQ(tattr.retval, XDP_TX, "case-128 retval"); + ASSERT_EQ(tattr.data_size_out, max_grow, "case-128 data_size_out"); /* Expect max grow */ /* Extra checks for data content: Count grow size, will contain zeros */ for (i = 0, cnt = 0; i < sizeof(buf); i++) { if (buf[i] == 0) cnt++; } - CHECK_ATTR((cnt != (max_grow - tattr.data_size_in)) /* Grow increase */ - || tattr.data_size_out != max_grow, /* Total grow size */ - "case-128-data", - "err %d errno %d retval %d size %d grow-size %d\n", - err, errno, tattr.retval, tattr.data_size_out, cnt); + ASSERT_EQ(cnt, max_grow - tattr.data_size_in, "case-128-data cnt"); /* Grow increase */ + ASSERT_EQ(tattr.data_size_out, max_grow, "case-128-data data_size_out"); /* Total grow */ + + bpf_object__close(obj); +} + +static void test_xdp_adjust_frags_tail_shrink(void) +{ + const char *file = "./test_xdp_adjust_tail_shrink.o"; + __u32 exp_size; + struct bpf_program *prog; + struct bpf_object *obj; + int err, prog_fd; + __u8 *buf; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + /* For the individual test cases, the first byte in the packet + * indicates which test will be run. + */ + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(9000); + if (!ASSERT_OK_PTR(buf, "alloc buf 9Kb")) + goto out; + + memset(buf, 0, 9000); + + /* Test case removing 10 bytes from last frag, NOT freeing it */ + exp_size = 8990; /* 9000 - 10 */ + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 9000; + topts.data_size_out = 9000; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb-10b"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb-10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb-10b size"); + + /* Test case removing one of two pages, assuming 4K pages */ + buf[0] = 1; + exp_size = 4900; /* 9000 - 4100 */ + + topts.data_size_out = 9000; /* reset from previous invocation */ + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb-4Kb"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb-4Kb retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb-4Kb size"); + + /* Test case removing two pages resulting in a linear xdp_buff */ + buf[0] = 2; + exp_size = 800; /* 9000 - 8200 */ + topts.data_size_out = 9000; /* reset from previous invocation */ + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb-9Kb"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb-9Kb retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb-9Kb size"); + + free(buf); +out: + bpf_object__close(obj); +} + +static void test_xdp_adjust_frags_tail_grow(void) +{ + const char *file = "./test_xdp_adjust_tail_grow.o"; + __u32 exp_size; + struct bpf_program *prog; + struct bpf_object *obj; + int err, i, prog_fd; + __u8 *buf; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(16384); + if (!ASSERT_OK_PTR(buf, "alloc buf 16Kb")) + goto out; + + /* Test case add 10 bytes to last frag */ + memset(buf, 1, 16384); + exp_size = 9000 + 10; + + topts.data_in = buf; + topts.data_out = buf; + topts.data_size_in = 9000; + topts.data_size_out = 16384; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb+10b"); + ASSERT_EQ(topts.retval, XDP_TX, "9Kb+10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb+10b size"); + + for (i = 0; i < 9000; i++) + ASSERT_EQ(buf[i], 1, "9Kb+10b-old"); + + for (i = 9000; i < 9010; i++) + ASSERT_EQ(buf[i], 0, "9Kb+10b-new"); + + for (i = 9010; i < 16384; i++) + ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched"); + + /* Test a too large grow */ + memset(buf, 1, 16384); + exp_size = 9001; + + topts.data_in = topts.data_out = buf; + topts.data_size_in = 9001; + topts.data_size_out = 16384; + err = bpf_prog_test_run_opts(prog_fd, &topts); + + ASSERT_OK(err, "9Kb+10b"); + ASSERT_EQ(topts.retval, XDP_DROP, "9Kb+10b retval"); + ASSERT_EQ(topts.data_size_out, exp_size, "9Kb+10b size"); + free(buf); +out: bpf_object__close(obj); } @@ -138,4 +273,8 @@ void test_xdp_adjust_tail(void) test_xdp_adjust_tail_grow(); if (test__start_subtest("xdp_adjust_tail_grow2")) test_xdp_adjust_tail_grow2(); + if (test__start_subtest("xdp_adjust_frags_tail_shrink")) + test_xdp_adjust_frags_tail_shrink(); + if (test__start_subtest("xdp_adjust_frags_tail_grow")) + test_xdp_adjust_frags_tail_grow(); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c index c6fa390e3aa1..62aa3edda5e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c @@ -11,8 +11,7 @@ void serial_test_xdp_attach(void) const char *file = "./test_xdp.o"; struct bpf_prog_info info = {}; int err, fd1, fd2, fd3; - DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, - .old_fd = -1); + LIBBPF_OPTS(bpf_xdp_attach_opts, opts); len = sizeof(info); @@ -38,49 +37,47 @@ void serial_test_xdp_attach(void) if (CHECK_FAIL(err)) goto out_2; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd1, XDP_FLAGS_REPLACE, - &opts); + err = bpf_xdp_attach(IFINDEX_LO, fd1, XDP_FLAGS_REPLACE, &opts); if (CHECK(err, "load_ok", "initial load failed")) goto out_close; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (CHECK(err || id0 != id1, "id1_check", "loaded prog id %u != id1 %u, err %d", id0, id1, err)) goto out_close; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE, - &opts); + err = bpf_xdp_attach(IFINDEX_LO, fd2, XDP_FLAGS_REPLACE, &opts); if (CHECK(!err, "load_fail", "load with expected id didn't fail")) goto out; - opts.old_fd = fd1; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd2, 0, &opts); + opts.old_prog_fd = fd1; + err = bpf_xdp_attach(IFINDEX_LO, fd2, 0, &opts); if (CHECK(err, "replace_ok", "replace valid old_fd failed")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (CHECK(err || id0 != id2, "id2_check", "loaded prog id %u != id2 %u, err %d", id0, id2, err)) goto out_close; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, fd3, 0, &opts); + err = bpf_xdp_attach(IFINDEX_LO, fd3, 0, &opts); if (CHECK(!err, "replace_fail", "replace invalid old_fd didn't fail")) goto out; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts); + err = bpf_xdp_detach(IFINDEX_LO, 0, &opts); if (CHECK(!err, "remove_fail", "remove invalid old_fd didn't fail")) goto out; - opts.old_fd = fd2; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, 0, &opts); + opts.old_prog_fd = fd2; + err = bpf_xdp_detach(IFINDEX_LO, 0, &opts); if (CHECK(err, "remove_ok", "remove valid old_fd failed")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (CHECK(err || id0 != 0, "unload_check", "loaded prog id %u != 0, err %d", id0, err)) goto out_close; out: - bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); + bpf_xdp_detach(IFINDEX_LO, 0, NULL); out_close: bpf_object__close(obj3); out_2: diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index c98a897ad692..76967d8ace9c 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -10,40 +10,101 @@ struct meta { int pkt_len; }; +struct test_ctx_s { + bool passed; + int pkt_size; +}; + +struct test_ctx_s test_ctx; + static void on_sample(void *ctx, int cpu, void *data, __u32 size) { - int duration = 0; struct meta *meta = (struct meta *)data; struct ipv4_packet *trace_pkt_v4 = data + sizeof(*meta); + unsigned char *raw_pkt = data + sizeof(*meta); + struct test_ctx_s *tst_ctx = ctx; + + ASSERT_GE(size, sizeof(pkt_v4) + sizeof(*meta), "check_size"); + ASSERT_EQ(meta->ifindex, if_nametoindex("lo"), "check_meta_ifindex"); + ASSERT_EQ(meta->pkt_len, tst_ctx->pkt_size, "check_meta_pkt_len"); + ASSERT_EQ(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), 0, + "check_packet_content"); + + if (meta->pkt_len > sizeof(pkt_v4)) { + for (int i = 0; i < meta->pkt_len - sizeof(pkt_v4); i++) + ASSERT_EQ(raw_pkt[i + sizeof(pkt_v4)], (unsigned char)i, + "check_packet_content"); + } + + tst_ctx->passed = true; +} - if (CHECK(size < sizeof(pkt_v4) + sizeof(*meta), - "check_size", "size %u < %zu\n", - size, sizeof(pkt_v4) + sizeof(*meta))) - return; +#define BUF_SZ 9000 - if (CHECK(meta->ifindex != if_nametoindex("lo"), "check_meta_ifindex", - "meta->ifindex = %d\n", meta->ifindex)) +static void run_xdp_bpf2bpf_pkt_size(int pkt_fd, struct perf_buffer *pb, + struct test_xdp_bpf2bpf *ftrace_skel, + int pkt_size) +{ + __u8 *buf, *buf_in; + int err; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + if (!ASSERT_LE(pkt_size, BUF_SZ, "pkt_size") || + !ASSERT_GE(pkt_size, sizeof(pkt_v4), "pkt_size")) return; - if (CHECK(meta->pkt_len != sizeof(pkt_v4), "check_meta_pkt_len", - "meta->pkt_len = %zd\n", sizeof(pkt_v4))) + buf_in = malloc(BUF_SZ); + if (!ASSERT_OK_PTR(buf_in, "buf_in malloc()")) return; - if (CHECK(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), - "check_packet_content", "content not the same\n")) + buf = malloc(BUF_SZ); + if (!ASSERT_OK_PTR(buf, "buf malloc()")) { + free(buf_in); return; + } + + test_ctx.passed = false; + test_ctx.pkt_size = pkt_size; + + memcpy(buf_in, &pkt_v4, sizeof(pkt_v4)); + if (pkt_size > sizeof(pkt_v4)) { + for (int i = 0; i < (pkt_size - sizeof(pkt_v4)); i++) + buf_in[i + sizeof(pkt_v4)] = i; + } + + /* Run test program */ + topts.data_in = buf_in; + topts.data_size_in = pkt_size; + topts.data_out = buf; + topts.data_size_out = BUF_SZ; + + err = bpf_prog_test_run_opts(pkt_fd, &topts); + + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(topts.retval, XDP_PASS, "ipv4 retval"); + ASSERT_EQ(topts.data_size_out, pkt_size, "ipv4 size"); + + /* Make sure bpf_xdp_output() was triggered and it sent the expected + * data to the perf ring buffer. + */ + err = perf_buffer__poll(pb, 100); + + ASSERT_GE(err, 0, "perf_buffer__poll"); + ASSERT_TRUE(test_ctx.passed, "test passed"); + /* Verify test results */ + ASSERT_EQ(ftrace_skel->bss->test_result_fentry, if_nametoindex("lo"), + "fentry result"); + ASSERT_EQ(ftrace_skel->bss->test_result_fexit, XDP_PASS, "fexit result"); - *(bool *)ctx = true; + free(buf); + free(buf_in); } void test_xdp_bpf2bpf(void) { - __u32 duration = 0, retval, size; - char buf[128]; int err, pkt_fd, map_fd; - bool passed = false; - struct iphdr iph; - struct iptnl_info value4 = {.family = AF_INET}; + int pkt_sizes[] = {sizeof(pkt_v4), 1024, 4100, 8200}; + struct iptnl_info value4 = {.family = AF_INET6}; struct test_xdp *pkt_skel = NULL; struct test_xdp_bpf2bpf *ftrace_skel = NULL; struct vip key4 = {.protocol = 6, .family = AF_INET}; @@ -52,7 +113,7 @@ void test_xdp_bpf2bpf(void) /* Load XDP program to introspect */ pkt_skel = test_xdp__open_and_load(); - if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n")) + if (!ASSERT_OK_PTR(pkt_skel, "test_xdp__open_and_load")) return; pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel); @@ -62,7 +123,7 @@ void test_xdp_bpf2bpf(void) /* Load trace program */ ftrace_skel = test_xdp_bpf2bpf__open(); - if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n")) + if (!ASSERT_OK_PTR(ftrace_skel, "test_xdp_bpf2bpf__open")) goto out; /* Demonstrate the bpf_program__set_attach_target() API rather than @@ -77,50 +138,24 @@ void test_xdp_bpf2bpf(void) bpf_program__set_attach_target(prog, pkt_fd, "_xdp_tx_iptunnel"); err = test_xdp_bpf2bpf__load(ftrace_skel); - if (CHECK(err, "__load", "ftrace skeleton failed\n")) + if (!ASSERT_OK(err, "test_xdp_bpf2bpf__load")) goto out; err = test_xdp_bpf2bpf__attach(ftrace_skel); - if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err)) + if (!ASSERT_OK(err, "test_xdp_bpf2bpf__attach")) goto out; /* Set up perf buffer */ - pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 1, - on_sample, NULL, &passed, NULL); + pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 8, + on_sample, NULL, &test_ctx, NULL); if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto out; - /* Run test program */ - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); - if (CHECK(err || retval != XDP_TX || size != 74 || - iph.protocol != IPPROTO_IPIP, "ipv4", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size)) - goto out; - - /* Make sure bpf_xdp_output() was triggered and it sent the expected - * data to the perf ring buffer. - */ - err = perf_buffer__poll(pb, 100); - if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err)) - goto out; - - CHECK_FAIL(!passed); - - /* Verify test results */ - if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"), - "result", "fentry failed err %llu\n", - ftrace_skel->bss->test_result_fentry)) - goto out; - - CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result", - "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit); - + for (int i = 0; i < ARRAY_SIZE(pkt_sizes); i++) + run_xdp_bpf2bpf_pkt_size(pkt_fd, pb, ftrace_skel, + pkt_sizes[i]); out: - if (pb) - perf_buffer__free(pb); + perf_buffer__free(pb); test_xdp__destroy(pkt_skel); test_xdp_bpf2bpf__destroy(ftrace_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c index fd812bd43600..f775a1613833 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -3,11 +3,12 @@ #include <linux/if_link.h> #include <test_progs.h> +#include "test_xdp_with_cpumap_frags_helpers.skel.h" #include "test_xdp_with_cpumap_helpers.skel.h" #define IFINDEX_LO 1 -void serial_test_xdp_cpumap_attach(void) +static void test_xdp_with_cpumap_helpers(void) { struct test_xdp_with_cpumap_helpers *skel; struct bpf_prog_info info = {}; @@ -23,11 +24,11 @@ void serial_test_xdp_cpumap_attach(void) return; prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog); - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_OK(err, "Generic attach of program with 8-byte CPUMAP")) goto out_close; - err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); ASSERT_OK(err, "XDP program detach"); prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm); @@ -45,15 +46,76 @@ void serial_test_xdp_cpumap_attach(void) ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id"); /* can not attach BPF_XDP_CPUMAP program to a device */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_CPUMAP program")) - bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); val.qsize = 192; val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog); err = bpf_map_update_elem(map_fd, &idx, &val, 0); ASSERT_NEQ(err, 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry"); + /* Try to attach BPF_XDP program with frags to cpumap when we have + * already loaded a BPF_XDP program on the map + */ + idx = 1; + val.qsize = 192; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to cpumap entry"); + out_close: test_xdp_with_cpumap_helpers__destroy(skel); } + +static void test_xdp_with_cpumap_frags_helpers(void) +{ + struct test_xdp_with_cpumap_frags_helpers *skel; + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + struct bpf_cpumap_val val = { + .qsize = 192, + }; + int err, frags_prog_fd, map_fd; + __u32 idx = 0; + + skel = test_xdp_with_cpumap_frags_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_cpumap_helpers__open_and_load")) + return; + + frags_prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags); + map_fd = bpf_map__fd(skel->maps.cpu_map); + err = bpf_obj_get_info_by_fd(frags_prog_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = frags_prog_fd; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add program to cpumap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read cpumap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, + "Match program id to cpumap entry prog_id"); + + /* Try to attach BPF_XDP program to cpumap when we have + * already loaded a BPF_XDP program with frags on the map + */ + idx = 1; + val.qsize = 192; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program to cpumap entry"); + +out_close: + test_xdp_with_cpumap_frags_helpers__destroy(skel); +} + +void serial_test_xdp_cpumap_attach(void) +{ + if (test__start_subtest("CPUMAP with programs in entries")) + test_xdp_with_cpumap_helpers(); + + if (test__start_subtest("CPUMAP with frags programs in entries")) + test_xdp_with_cpumap_frags_helpers(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index 3079d5568f8f..ead40016c324 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -4,6 +4,7 @@ #include <test_progs.h> #include "test_xdp_devmap_helpers.skel.h" +#include "test_xdp_with_devmap_frags_helpers.skel.h" #include "test_xdp_with_devmap_helpers.skel.h" #define IFINDEX_LO 1 @@ -25,11 +26,11 @@ static void test_xdp_with_devmap_helpers(void) return; dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog); - err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_OK(err, "Generic attach of program with 8-byte devmap")) goto out_close; - err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); ASSERT_OK(err, "XDP program detach"); dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); @@ -47,15 +48,24 @@ static void test_xdp_with_devmap_helpers(void) ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id"); /* can not attach BPF_XDP_DEVMAP program to a device */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_DEVMAP program")) - bpf_set_link_xdp_fd(IFINDEX_LO, -1, XDP_FLAGS_SKB_MODE); + bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); val.ifindex = 1; val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_prog); err = bpf_map_update_elem(map_fd, &idx, &val, 0); ASSERT_NEQ(err, 0, "Add non-BPF_XDP_DEVMAP program to devmap entry"); + /* Try to attach BPF_XDP program with frags to devmap when we have + * already loaded a BPF_XDP program on the map + */ + idx = 1; + val.ifindex = 1; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_dm_frags); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to devmap entry"); + out_close: test_xdp_with_devmap_helpers__destroy(skel); } @@ -71,12 +81,57 @@ static void test_neg_xdp_devmap_helpers(void) } } +static void test_xdp_with_devmap_frags_helpers(void) +{ + struct test_xdp_with_devmap_frags_helpers *skel; + struct bpf_prog_info info = {}; + struct bpf_devmap_val val = { + .ifindex = IFINDEX_LO, + }; + __u32 len = sizeof(info); + int err, dm_fd_frags, map_fd; + __u32 idx = 0; + + skel = test_xdp_with_devmap_frags_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load")) + return; + + dm_fd_frags = bpf_program__fd(skel->progs.xdp_dummy_dm_frags); + map_fd = bpf_map__fd(skel->maps.dm_ports); + err = bpf_obj_get_info_by_fd(dm_fd_frags, &info, &len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = dm_fd_frags; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add frags program to devmap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read devmap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, + "Match program id to devmap entry prog_id"); + + /* Try to attach BPF_XDP program to devmap when we have + * already loaded a BPF_XDP program with frags on the map + */ + idx = 1; + val.ifindex = 1; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_dm); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program to devmap entry"); + +out_close: + test_xdp_with_devmap_frags_helpers__destroy(skel); +} void serial_test_xdp_devmap_attach(void) { if (test__start_subtest("DEVMAP with programs in entries")) test_xdp_with_devmap_helpers(); + if (test__start_subtest("DEVMAP with frags programs in entries")) + test_xdp_with_devmap_frags_helpers(); + if (test__start_subtest("Verifier check of DEVMAP programs")) test_neg_xdp_devmap_helpers(); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c new file mode 100644 index 000000000000..a50971c6cf4a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -0,0 +1,201 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> +#include <net/if.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ipv6.h> +#include <linux/in6.h> +#include <linux/udp.h> +#include <bpf/bpf_endian.h> +#include "test_xdp_do_redirect.skel.h" + +#define SYS(fmt, ...) \ + ({ \ + char cmd[1024]; \ + snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \ + if (!ASSERT_OK(system(cmd), cmd)) \ + goto out; \ + }) + +struct udp_packet { + struct ethhdr eth; + struct ipv6hdr iph; + struct udphdr udp; + __u8 payload[64 - sizeof(struct udphdr) + - sizeof(struct ethhdr) - sizeof(struct ipv6hdr)]; +} __packed; + +static struct udp_packet pkt_udp = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IPV6), + .eth.h_dest = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}, + .eth.h_source = {0x66, 0x77, 0x88, 0x99, 0xaa, 0xbb}, + .iph.version = 6, + .iph.nexthdr = IPPROTO_UDP, + .iph.payload_len = bpf_htons(sizeof(struct udp_packet) + - offsetof(struct udp_packet, udp)), + .iph.hop_limit = 2, + .iph.saddr.s6_addr16 = {bpf_htons(0xfc00), 0, 0, 0, 0, 0, 0, bpf_htons(1)}, + .iph.daddr.s6_addr16 = {bpf_htons(0xfc00), 0, 0, 0, 0, 0, 0, bpf_htons(2)}, + .udp.source = bpf_htons(1), + .udp.dest = bpf_htons(1), + .udp.len = bpf_htons(sizeof(struct udp_packet) + - offsetof(struct udp_packet, udp)), + .payload = {0x42}, /* receiver XDP program matches on this */ +}; + +static int attach_tc_prog(struct bpf_tc_hook *hook, int fd) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1, .prog_fd = fd); + int ret; + + ret = bpf_tc_hook_create(hook); + if (!ASSERT_OK(ret, "create tc hook")) + return ret; + + ret = bpf_tc_attach(hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) { + bpf_tc_hook_destroy(hook); + return ret; + } + + return 0; +} + +/* The maximum permissible size is: PAGE_SIZE - sizeof(struct xdp_page_head) - + * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes + */ +#define MAX_PKT_SIZE 3368 +static void test_max_pkt_size(int fd) +{ + char data[MAX_PKT_SIZE + 1] = {}; + int err; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = MAX_PKT_SIZE, + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = 1, + ); + err = bpf_prog_test_run_opts(fd, &opts); + ASSERT_OK(err, "prog_run_max_size"); + + opts.data_size_in += 1; + err = bpf_prog_test_run_opts(fd, &opts); + ASSERT_EQ(err, -EINVAL, "prog_run_too_big"); +} + +#define NUM_PKTS 10000 +void test_xdp_do_redirect(void) +{ + int err, xdp_prog_fd, tc_prog_fd, ifindex_src, ifindex_dst; + char data[sizeof(pkt_udp) + sizeof(__u32)]; + struct test_xdp_do_redirect *skel = NULL; + struct nstoken *nstoken = NULL; + struct bpf_link *link; + + struct xdp_md ctx_in = { .data = sizeof(__u32), + .data_end = sizeof(data) }; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = sizeof(data), + .ctx_in = &ctx_in, + .ctx_size_in = sizeof(ctx_in), + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = NUM_PKTS, + .batch_size = 64, + ); + DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, + .attach_point = BPF_TC_INGRESS); + + memcpy(&data[sizeof(__u32)], &pkt_udp, sizeof(pkt_udp)); + *((__u32 *)data) = 0x42; /* metadata test value */ + + skel = test_xdp_do_redirect__open(); + if (!ASSERT_OK_PTR(skel, "skel")) + return; + + /* The XDP program we run with bpf_prog_run() will cycle through all + * three xmit (PASS/TX/REDIRECT) return codes starting from above, and + * ending up with PASS, so we should end up with two packets on the dst + * iface and NUM_PKTS-2 in the TC hook. We match the packets on the UDP + * payload. + */ + SYS("ip netns add testns"); + nstoken = open_netns("testns"); + if (!ASSERT_OK_PTR(nstoken, "setns")) + goto out; + + SYS("ip link add veth_src type veth peer name veth_dst"); + SYS("ip link set dev veth_src address 00:11:22:33:44:55"); + SYS("ip link set dev veth_dst address 66:77:88:99:aa:bb"); + SYS("ip link set dev veth_src up"); + SYS("ip link set dev veth_dst up"); + SYS("ip addr add dev veth_src fc00::1/64"); + SYS("ip addr add dev veth_dst fc00::2/64"); + SYS("ip neigh add fc00::2 dev veth_src lladdr 66:77:88:99:aa:bb"); + + /* We enable forwarding in the test namespace because that will cause + * the packets that go through the kernel stack (with XDP_PASS) to be + * forwarded back out the same interface (because of the packet dst + * combined with the interface addresses). When this happens, the + * regular forwarding path will end up going through the same + * veth_xdp_xmit() call as the XDP_REDIRECT code, which can cause a + * deadlock if it happens on the same CPU. There's a local_bh_disable() + * in the test_run code to prevent this, but an earlier version of the + * code didn't have this, so we keep the test behaviour to make sure the + * bug doesn't resurface. + */ + SYS("sysctl -qw net.ipv6.conf.all.forwarding=1"); + + ifindex_src = if_nametoindex("veth_src"); + ifindex_dst = if_nametoindex("veth_dst"); + if (!ASSERT_NEQ(ifindex_src, 0, "ifindex_src") || + !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst")) + goto out; + + memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN); + skel->rodata->ifindex_out = ifindex_src; /* redirect back to the same iface */ + skel->rodata->ifindex_in = ifindex_src; + ctx_in.ingress_ifindex = ifindex_src; + tc_hook.ifindex = ifindex_src; + + if (!ASSERT_OK(test_xdp_do_redirect__load(skel), "load")) + goto out; + + link = bpf_program__attach_xdp(skel->progs.xdp_count_pkts, ifindex_dst); + if (!ASSERT_OK_PTR(link, "prog_attach")) + goto out; + skel->links.xdp_count_pkts = link; + + tc_prog_fd = bpf_program__fd(skel->progs.tc_count_pkts); + if (attach_tc_prog(&tc_hook, tc_prog_fd)) + goto out; + + xdp_prog_fd = bpf_program__fd(skel->progs.xdp_redirect); + err = bpf_prog_test_run_opts(xdp_prog_fd, &opts); + if (!ASSERT_OK(err, "prog_run")) + goto out_tc; + + /* wait for the packets to be flushed */ + kern_sync_rcu(); + + /* There will be one packet sent through XDP_REDIRECT and one through + * XDP_TX; these will show up on the XDP counting program, while the + * rest will be counted at the TC ingress hook (and the counting program + * resets the packet payload so they don't get counted twice even though + * they are re-xmited out the veth device + */ + ASSERT_EQ(skel->bss->pkts_seen_xdp, 2, "pkt_count_xdp"); + ASSERT_EQ(skel->bss->pkts_seen_zero, 2, "pkt_count_zero"); + ASSERT_EQ(skel->bss->pkts_seen_tc, NUM_PKTS - 2, "pkt_count_tc"); + + test_max_pkt_size(bpf_program__fd(skel->progs.xdp_count_pkts)); + +out_tc: + bpf_tc_hook_destroy(&tc_hook); +out: + if (nstoken) + close_netns(nstoken); + system("ip netns del testns"); + test_xdp_do_redirect__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c index abe48e82e1dc..0d01ff6cb91a 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c @@ -14,13 +14,13 @@ void serial_test_xdp_info(void) /* Get prog_id for XDP_ATTACHED_NONE mode */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &prog_id); if (CHECK(err, "get_xdp_none", "errno=%d\n", errno)) return; if (CHECK(prog_id, "prog_id_none", "unexpected prog_id=%u\n", prog_id)) return; - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_query_id(IFINDEX_LO, XDP_FLAGS_SKB_MODE, &prog_id); if (CHECK(err, "get_xdp_none_skb", "errno=%d\n", errno)) return; if (CHECK(prog_id, "prog_id_none_skb", "unexpected prog_id=%u\n", @@ -37,32 +37,32 @@ void serial_test_xdp_info(void) if (CHECK(err, "get_prog_info", "errno=%d\n", errno)) goto out_close; - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL); if (CHECK(err, "set_xdp_skb", "errno=%d\n", errno)) goto out_close; /* Get prog_id for single prog mode */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &prog_id); if (CHECK(err, "get_xdp", "errno=%d\n", errno)) goto out; if (CHECK(prog_id != info.id, "prog_id", "prog_id not available\n")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_SKB_MODE); + err = bpf_xdp_query_id(IFINDEX_LO, XDP_FLAGS_SKB_MODE, &prog_id); if (CHECK(err, "get_xdp_skb", "errno=%d\n", errno)) goto out; if (CHECK(prog_id != info.id, "prog_id_skb", "prog_id not available\n")) goto out; - err = bpf_get_link_xdp_id(IFINDEX_LO, &prog_id, XDP_FLAGS_DRV_MODE); + err = bpf_xdp_query_id(IFINDEX_LO, XDP_FLAGS_DRV_MODE, &prog_id); if (CHECK(err, "get_xdp_drv", "errno=%d\n", errno)) goto out; if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id)) goto out; out: - bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); + bpf_xdp_detach(IFINDEX_LO, 0, NULL); out_close: bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c index b2b357f8c74c..3e9d5c5521f0 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c @@ -8,9 +8,9 @@ void serial_test_xdp_link(void) { - DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1); struct test_xdp_link *skel1 = NULL, *skel2 = NULL; __u32 id1, id2, id0 = 0, prog_fd1, prog_fd2; + LIBBPF_OPTS(bpf_xdp_attach_opts, opts); struct bpf_link_info link_info; struct bpf_prog_info prog_info; struct bpf_link *link; @@ -41,12 +41,12 @@ void serial_test_xdp_link(void) id2 = prog_info.id; /* set initial prog attachment */ - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts); if (!ASSERT_OK(err, "fd_attach")) goto cleanup; /* validate prog ID */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val")) goto cleanup; @@ -55,14 +55,14 @@ void serial_test_xdp_link(void) if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { bpf_link__destroy(link); /* best-effort detach prog */ - opts.old_fd = prog_fd1; - bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts); + opts.old_prog_fd = prog_fd1; + bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_REPLACE, &opts); goto cleanup; } /* detach BPF program */ - opts.old_fd = prog_fd1; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts); + opts.old_prog_fd = prog_fd1; + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_REPLACE, &opts); if (!ASSERT_OK(err, "prog_detach")) goto cleanup; @@ -73,23 +73,23 @@ void serial_test_xdp_link(void) skel1->links.xdp_handler = link; /* validate prog ID */ - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val")) goto cleanup; /* BPF prog attach is not allowed to replace BPF link */ - opts.old_fd = prog_fd1; - err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts); + opts.old_prog_fd = prog_fd1; + err = bpf_xdp_attach(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts); if (!ASSERT_ERR(err, "prog_attach_fail")) goto cleanup; /* Can't force-update when BPF link is active */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd2, 0); + err = bpf_xdp_attach(IFINDEX_LO, prog_fd2, 0, NULL); if (!ASSERT_ERR(err, "prog_update_fail")) goto cleanup; /* Can't force-detach when BPF link is active */ - err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0); + err = bpf_xdp_detach(IFINDEX_LO, 0, NULL); if (!ASSERT_ERR(err, "prog_detach_fail")) goto cleanup; @@ -109,7 +109,7 @@ void serial_test_xdp_link(void) goto cleanup; skel2->links.xdp_handler = link; - err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0); + err = bpf_xdp_query_id(IFINDEX_LO, 0, &id0); if (!ASSERT_OK(err, "id2_check_err") || !ASSERT_EQ(id0, id2, "id2_check_val")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c index 0281095de266..92ef0aa50866 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_noinline.c @@ -25,43 +25,49 @@ void test_xdp_noinline(void) __u8 flags; } real_def = {.dst = MAGIC_VAL}; __u32 ch_key = 11, real_num = 3; - __u32 duration = 0, retval, size; int err, i; __u64 bytes = 0, pkts = 0; char buf[128]; u32 *magic = (u32 *)buf; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .data_out = buf, + .data_size_out = sizeof(buf), + .repeat = NUM_ITER, + ); skel = test_xdp_noinline__open_and_load(); - if (CHECK(!skel, "skel_open_and_load", "failed\n")) + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) return; bpf_map_update_elem(bpf_map__fd(skel->maps.vip_map), &key, &value, 0); bpf_map_update_elem(bpf_map__fd(skel->maps.ch_rings), &ch_key, &real_num, 0); bpf_map_update_elem(bpf_map__fd(skel->maps.reals), &real_num, &real_def, 0); - err = bpf_prog_test_run(bpf_program__fd(skel->progs.balancer_ingress_v4), - NUM_ITER, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - CHECK(err || retval != 1 || size != 54 || - *magic != MAGIC_VAL, "ipv4", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.balancer_ingress_v4), &topts); + ASSERT_OK(err, "ipv4 test_run"); + ASSERT_EQ(topts.retval, 1, "ipv4 test_run retval"); + ASSERT_EQ(topts.data_size_out, 54, "ipv4 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv4 test_run magic"); - err = bpf_prog_test_run(bpf_program__fd(skel->progs.balancer_ingress_v6), - NUM_ITER, &pkt_v6, sizeof(pkt_v6), - buf, &size, &retval, &duration); - CHECK(err || retval != 1 || size != 74 || - *magic != MAGIC_VAL, "ipv6", - "err %d errno %d retval %d size %d magic %x\n", - err, errno, retval, size, *magic); + topts.data_in = &pkt_v6; + topts.data_size_in = sizeof(pkt_v6); + topts.data_out = buf; + topts.data_size_out = sizeof(buf); + + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.balancer_ingress_v6), &topts); + ASSERT_OK(err, "ipv6 test_run"); + ASSERT_EQ(topts.retval, 1, "ipv6 test_run retval"); + ASSERT_EQ(topts.data_size_out, 74, "ipv6 test_run data_size_out"); + ASSERT_EQ(*magic, MAGIC_VAL, "ipv6 test_run magic"); bpf_map_lookup_elem(bpf_map__fd(skel->maps.stats), &stats_key, stats); for (i = 0; i < nr_cpus; i++) { bytes += stats[i].bytes; pkts += stats[i].pkts; } - CHECK(bytes != MAGIC_BYTES * NUM_ITER * 2 || pkts != NUM_ITER * 2, - "stats", "bytes %lld pkts %lld\n", - (unsigned long long)bytes, (unsigned long long)pkts); + ASSERT_EQ(bytes, MAGIC_BYTES * NUM_ITER * 2, "stats bytes"); + ASSERT_EQ(pkts, NUM_ITER * 2, "stats pkts"); test_xdp_noinline__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c index 15a3900e4370..f543d1bd21b8 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c @@ -4,22 +4,25 @@ void test_xdp_perf(void) { const char *file = "./xdp_dummy.o"; - __u32 duration, retval, size; struct bpf_object *obj; char in[128], out[128]; int err, prog_fd; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = in, + .data_size_in = sizeof(in), + .data_out = out, + .data_size_out = sizeof(out), + .repeat = 1000000, + ); err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - err = bpf_prog_test_run(prog_fd, 1000000, &in[0], 128, - out, &size, &retval, &duration); - - CHECK(err || retval != XDP_PASS || size != 128, - "xdp-perf", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, XDP_PASS, "test_run retval"); + ASSERT_EQ(topts.data_size_out, 128, "test_run data_size_out"); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/progs/atomics.c b/tools/testing/selftests/bpf/progs/atomics.c index 16e57313204a..f89c7f0cc53b 100644 --- a/tools/testing/selftests/bpf/progs/atomics.c +++ b/tools/testing/selftests/bpf/progs/atomics.c @@ -20,8 +20,8 @@ __u64 add_stack_value_copy = 0; __u64 add_stack_result = 0; __u64 add_noreturn_value = 1; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(add, int a) +SEC("raw_tp/sys_enter") +int add(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -46,8 +46,8 @@ __s64 sub_stack_value_copy = 0; __s64 sub_stack_result = 0; __s64 sub_noreturn_value = 1; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(sub, int a) +SEC("raw_tp/sys_enter") +int sub(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -70,8 +70,8 @@ __u32 and32_value = 0x110; __u32 and32_result = 0; __u64 and_noreturn_value = (0x110ull << 32); -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(and, int a) +SEC("raw_tp/sys_enter") +int and(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -91,8 +91,8 @@ __u32 or32_value = 0x110; __u32 or32_result = 0; __u64 or_noreturn_value = (0x110ull << 32); -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(or, int a) +SEC("raw_tp/sys_enter") +int or(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -111,8 +111,8 @@ __u32 xor32_value = 0x110; __u32 xor32_result = 0; __u64 xor_noreturn_value = (0x110ull << 32); -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(xor, int a) +SEC("raw_tp/sys_enter") +int xor(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -132,8 +132,8 @@ __u32 cmpxchg32_value = 1; __u32 cmpxchg32_result_fail = 0; __u32 cmpxchg32_result_succeed = 0; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(cmpxchg, int a) +SEC("raw_tp/sys_enter") +int cmpxchg(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; @@ -153,8 +153,8 @@ __u64 xchg64_result = 0; __u32 xchg32_value = 1; __u32 xchg32_result = 0; -SEC("fentry/bpf_fentry_test1") -int BPF_PROG(xchg, int a) +SEC("raw_tp/sys_enter") +int xchg(const void *ctx) { if (pid != (bpf_get_current_pid_tgid() >> 32)) return 0; diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_bench.c b/tools/testing/selftests/bpf/progs/bloom_filter_bench.c index d9a88dd1ea65..7efcbdbe772d 100644 --- a/tools/testing/selftests/bpf/progs/bloom_filter_bench.c +++ b/tools/testing/selftests/bpf/progs/bloom_filter_bench.c @@ -5,6 +5,7 @@ #include <linux/bpf.h> #include <stdbool.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -87,7 +88,7 @@ bloom_callback(struct bpf_map *map, __u32 *key, void *val, return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bloom_lookup(void *ctx) { struct callback_ctx data; @@ -100,7 +101,7 @@ int bloom_lookup(void *ctx) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bloom_update(void *ctx) { struct callback_ctx data; @@ -113,7 +114,7 @@ int bloom_update(void *ctx) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bloom_hashmap_lookup(void *ctx) { __u64 *result; diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_map.c b/tools/testing/selftests/bpf/progs/bloom_filter_map.c index 1316f3db79d9..f245fcfe0c61 100644 --- a/tools/testing/selftests/bpf/progs/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/progs/bloom_filter_map.c @@ -3,6 +3,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -51,7 +52,7 @@ check_elem(struct bpf_map *map, __u32 *key, __u32 *val, return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int inner_map(void *ctx) { struct bpf_map *inner_map; @@ -70,7 +71,7 @@ int inner_map(void *ctx) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int check_bloom(void *ctx) { struct callback_ctx data; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c new file mode 100644 index 000000000000..eafc877ea460 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <limits.h> + +#define AUTOBIND_LEN 6 +char sun_path[AUTOBIND_LEN]; + +#define NR_CASES 5 +int sndbuf_setsockopt[NR_CASES] = {-1, 0, 8192, INT_MAX / 2, INT_MAX}; +int sndbuf_getsockopt[NR_CASES] = {-1, -1, -1, -1, -1}; +int sndbuf_getsockopt_expected[NR_CASES]; + +static inline int cmpname(struct unix_sock *unix_sk) +{ + int i; + + for (i = 0; i < AUTOBIND_LEN; i++) { + if (unix_sk->addr->name->sun_path[i] != sun_path[i]) + return -1; + } + + return 0; +} + +SEC("iter/unix") +int change_sndbuf(struct bpf_iter__unix *ctx) +{ + struct unix_sock *unix_sk = ctx->unix_sk; + int i, err; + + if (!unix_sk || !unix_sk->addr) + return 0; + + if (unix_sk->addr->name->sun_path[0]) + return 0; + + if (cmpname(unix_sk)) + return 0; + + for (i = 0; i < NR_CASES; i++) { + err = bpf_setsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF, + &sndbuf_setsockopt[i], + sizeof(sndbuf_setsockopt[i])); + if (err) + break; + + err = bpf_getsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF, + &sndbuf_getsockopt[i], + sizeof(sndbuf_getsockopt[i])); + if (err) + break; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c index c86b93f33b32..d22741272692 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c @@ -2,6 +2,7 @@ /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> char _license[] SEC("license") = "GPL"; @@ -23,3 +24,56 @@ int dump_task(struct bpf_iter__task *ctx) BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid); return 0; } + +int num_expected_failure_copy_from_user_task = 0; +int num_success_copy_from_user_task = 0; + +SEC("iter.s/task") +int dump_task_sleepable(struct bpf_iter__task *ctx) +{ + struct seq_file *seq = ctx->meta->seq; + struct task_struct *task = ctx->task; + static const char info[] = " === END ==="; + struct pt_regs *regs; + void *ptr; + uint32_t user_data = 0; + int ret; + + if (task == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Read an invalid pointer and ensure we get an error */ + ptr = NULL; + ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0); + if (ret) { + ++num_expected_failure_copy_from_user_task; + } else { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + + /* Try to read the contents of the task's instruction pointer from the + * remote task's address space. + */ + regs = (struct pt_regs *)bpf_task_pt_regs(task); + if (regs == (void *)0) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + ptr = (void *)PT_REGS_IP(regs); + + ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0); + if (ret) { + BPF_SEQ_PRINTF(seq, "%s\n", info); + return 0; + } + ++num_success_copy_from_user_task; + + if (ctx->meta->seq_num == 0) + BPF_SEQ_PRINTF(seq, " tgid gid data\n"); + + BPF_SEQ_PRINTF(seq, "%8d %8d %8d\n", task->tgid, task->pid, user_data); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c index c21e3f545371..e6aefae38894 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c @@ -63,7 +63,7 @@ int dump_unix(struct bpf_iter__unix *ctx) BPF_SEQ_PRINTF(seq, " @"); for (i = 1; i < len; i++) { - /* unix_mkname() tests this upper bound. */ + /* unix_validate_addr() tests this upper bound. */ if (i >= sizeof(struct sockaddr_un)) break; diff --git a/tools/testing/selftests/bpf/progs/bpf_loop.c b/tools/testing/selftests/bpf/progs/bpf_loop.c index 12349e4601e8..e08565282759 100644 --- a/tools/testing/selftests/bpf/progs/bpf_loop.c +++ b/tools/testing/selftests/bpf/progs/bpf_loop.c @@ -3,6 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -53,7 +54,7 @@ static int nested_callback1(__u32 index, void *data) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int test_prog(void *ctx) { struct callback_ctx data = {}; @@ -71,7 +72,7 @@ int test_prog(void *ctx) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int prog_null_ctx(void *ctx) { if (bpf_get_current_pid_tgid() >> 32 != pid) @@ -82,7 +83,7 @@ int prog_null_ctx(void *ctx) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int prog_invalid_flags(void *ctx) { struct callback_ctx data = {}; @@ -95,7 +96,7 @@ int prog_invalid_flags(void *ctx) return 0; } -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int prog_nested_calls(void *ctx) { struct callback_ctx data = {}; diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c index 9dafdc244462..4ce76eb064c4 100644 --- a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c +++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c @@ -3,6 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -14,7 +15,7 @@ static int empty_callback(__u32 index, void *data) return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int benchmark(void *ctx) { for (int i = 0; i < 1000; i++) { diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h new file mode 100644 index 000000000000..5bb11fe595a4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __BPF_MISC_H__ +#define __BPF_MISC_H__ + +#if defined(__TARGET_ARCH_x86) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__x64_" +#elif defined(__TARGET_ARCH_s390) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__s390x_" +#elif defined(__TARGET_ARCH_arm64) +#define SYSCALL_WRAPPER 1 +#define SYS_PREFIX "__arm64_" +#else +#define SYSCALL_WRAPPER 0 +#define SYS_PREFIX "__se_" +#endif + +#endif diff --git a/tools/testing/selftests/bpf/progs/bpf_mod_race.c b/tools/testing/selftests/bpf/progs/bpf_mod_race.c new file mode 100644 index 000000000000..82a5c6c6ba83 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_mod_race.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile struct { + /* thread to activate trace programs for */ + pid_t tgid; + /* return error from __init function */ + int inject_error; + /* uffd monitored range start address */ + void *fault_addr; +} bpf_mod_race_config = { -1 }; + +int bpf_blocking = 0; +int res_try_get_module = -1; + +static __always_inline bool check_thread_id(void) +{ + struct task_struct *task = bpf_get_current_task_btf(); + + return task->tgid == bpf_mod_race_config.tgid; +} + +/* The trace of execution is something like this: + * + * finit_module() + * load_module() + * prepare_coming_module() + * notifier_call(MODULE_STATE_COMING) + * btf_parse_module() + * btf_alloc_id() // Visible to userspace at this point + * list_add(btf_mod->list, &btf_modules) + * do_init_module() + * freeinit = kmalloc() + * ret = mod->init() + * bpf_prog_widen_race() + * bpf_copy_from_user() + * ...<sleep>... + * if (ret < 0) + * ... + * free_module() + * return ret + * + * At this point, module loading thread is blocked, we now load the program: + * + * bpf_check + * add_kfunc_call/check_pseudo_btf_id + * btf_try_get_module + * try_get_module_live == false + * return -ENXIO + * + * Without the fix (try_get_module_live in btf_try_get_module): + * + * bpf_check + * add_kfunc_call/check_pseudo_btf_id + * btf_try_get_module + * try_get_module == true + * <store module reference in btf_kfunc_tab or used_btf array> + * ... + * return fd + * + * Now, if we inject an error in the blocked program, our module will be freed + * (going straight from MODULE_STATE_COMING to MODULE_STATE_GOING). + * Later, when bpf program is freed, it will try to module_put already freed + * module. This is why try_get_module_live returns false if mod->state is not + * MODULE_STATE_LIVE. + */ + +SEC("fmod_ret.s/bpf_fentry_test1") +int BPF_PROG(widen_race, int a, int ret) +{ + char dst; + + if (!check_thread_id()) + return 0; + /* Indicate that we will attempt to block */ + bpf_blocking = 1; + bpf_copy_from_user(&dst, 1, bpf_mod_race_config.fault_addr); + return bpf_mod_race_config.inject_error; +} + +SEC("fexit/do_init_module") +int BPF_PROG(fexit_init_module, struct module *mod, int ret) +{ + if (!check_thread_id()) + return 0; + /* Indicate that we finished blocking */ + bpf_blocking = 2; + return 0; +} + +SEC("fexit/btf_try_get_module") +int BPF_PROG(fexit_module_get, const struct btf *btf, struct module *mod) +{ + res_try_get_module = !!mod; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c new file mode 100644 index 000000000000..05838ed9b89c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2022 Sony Group Corporation */ +#include <vmlinux.h> + +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +int arg1 = 0; +unsigned long arg2 = 0; +unsigned long arg3 = 0; +unsigned long arg4_cx = 0; +unsigned long arg4 = 0; +unsigned long arg5 = 0; + +int arg1_core = 0; +unsigned long arg2_core = 0; +unsigned long arg3_core = 0; +unsigned long arg4_core_cx = 0; +unsigned long arg4_core = 0; +unsigned long arg5_core = 0; + +int option_syscall = 0; +unsigned long arg2_syscall = 0; +unsigned long arg3_syscall = 0; +unsigned long arg4_syscall = 0; +unsigned long arg5_syscall = 0; + +const volatile pid_t filter_pid = 0; + +SEC("kprobe/" SYS_PREFIX "sys_prctl") +int BPF_KPROBE(handle_sys_prctl) +{ + struct pt_regs *real_regs; + pid_t pid = bpf_get_current_pid_tgid() >> 32; + unsigned long tmp = 0; + + if (pid != filter_pid) + return 0; + + real_regs = PT_REGS_SYSCALL_REGS(ctx); + + /* test for PT_REGS_PARM */ + +#if !defined(bpf_target_arm64) && !defined(bpf_target_s390) + bpf_probe_read_kernel(&tmp, sizeof(tmp), &PT_REGS_PARM1_SYSCALL(real_regs)); +#endif + arg1 = tmp; + bpf_probe_read_kernel(&arg2, sizeof(arg2), &PT_REGS_PARM2_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg3, sizeof(arg3), &PT_REGS_PARM3_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg4_cx, sizeof(arg4_cx), &PT_REGS_PARM4(real_regs)); + bpf_probe_read_kernel(&arg4, sizeof(arg4), &PT_REGS_PARM4_SYSCALL(real_regs)); + bpf_probe_read_kernel(&arg5, sizeof(arg5), &PT_REGS_PARM5_SYSCALL(real_regs)); + + /* test for the CORE variant of PT_REGS_PARM */ + arg1_core = PT_REGS_PARM1_CORE_SYSCALL(real_regs); + arg2_core = PT_REGS_PARM2_CORE_SYSCALL(real_regs); + arg3_core = PT_REGS_PARM3_CORE_SYSCALL(real_regs); + arg4_core_cx = PT_REGS_PARM4_CORE(real_regs); + arg4_core = PT_REGS_PARM4_CORE_SYSCALL(real_regs); + arg5_core = PT_REGS_PARM5_CORE_SYSCALL(real_regs); + + return 0; +} + +SEC("kprobe/" SYS_PREFIX "sys_prctl") +int BPF_KPROBE_SYSCALL(prctl_enter, int option, unsigned long arg2, + unsigned long arg3, unsigned long arg4, unsigned long arg5) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + + if (pid != filter_pid) + return 0; + + option_syscall = option; + arg2_syscall = arg2; + arg3_syscall = arg3; + arg4_syscall = arg4; + arg5_syscall = arg5; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index e0f42601be9b..1c1289ba5fc5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -5,6 +5,8 @@ #define AF_INET 2 #define AF_INET6 10 +#define SOL_SOCKET 1 +#define SO_SNDBUF 7 #define __SO_ACCEPTCON (1 << 16) #define SOL_TCP 6 diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c new file mode 100644 index 000000000000..8feddb8289cf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Google */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 *p; +}; + +__u64 g; + +SEC("fentry/bpf_testmod_test_btf_type_tag_percpu_1") +int BPF_PROG(test_percpu1, struct bpf_testmod_btf_type_tag_1 *arg) +{ + g = arg->a; + return 0; +} + +SEC("fentry/bpf_testmod_test_btf_type_tag_percpu_2") +int BPF_PROG(test_percpu2, struct bpf_testmod_btf_type_tag_2 *arg) +{ + g = arg->p->a; + return 0; +} + +/* trace_cgroup_mkdir(struct cgroup *cgrp, const char *path) + * + * struct cgroup_rstat_cpu { + * ... + * struct cgroup *updated_children; + * ... + * }; + * + * struct cgroup { + * ... + * struct cgroup_rstat_cpu __percpu *rstat_cpu; + * ... + * }; + */ +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_percpu_load, struct cgroup *cgrp, const char *path) +{ + g = (__u64)cgrp->rstat_cpu->updated_children; + return 0; +} + +SEC("tp_btf/cgroup_mkdir") +int BPF_PROG(test_percpu_helper, struct cgroup *cgrp, const char *path) +{ + struct cgroup_rstat_cpu *rstat; + __u32 cpu; + + cpu = bpf_get_smp_processor_id(); + rstat = (struct cgroup_rstat_cpu *)bpf_per_cpu_ptr(cgrp->rstat_cpu, cpu); + if (rstat) { + /* READ_ONCE */ + *(volatile int *)rstat; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_user.c b/tools/testing/selftests/bpf/progs/btf_type_tag_user.c new file mode 100644 index 000000000000..5523f77c5a44 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/btf_type_tag_user.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +struct bpf_testmod_btf_type_tag_1 { + int a; +}; + +struct bpf_testmod_btf_type_tag_2 { + struct bpf_testmod_btf_type_tag_1 *p; +}; + +int g; + +SEC("fentry/bpf_testmod_test_btf_type_tag_user_1") +int BPF_PROG(test_user1, struct bpf_testmod_btf_type_tag_1 *arg) +{ + g = arg->a; + return 0; +} + +SEC("fentry/bpf_testmod_test_btf_type_tag_user_2") +int BPF_PROG(test_user2, struct bpf_testmod_btf_type_tag_2 *arg) +{ + g = arg->p->a; + return 0; +} + +/* int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, + * int __user *usockaddr_len); + */ +SEC("fentry/__sys_getsockname") +int BPF_PROG(test_sys_getsockname, int fd, struct sockaddr *usockaddr, + int *usockaddr_len) +{ + g = usockaddr->sa_family; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c new file mode 100644 index 000000000000..b2a409e6382a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 invocations = 0; +__u32 assertion_error = 0; +__u32 retval_value = 0; +__u32 ctx_retval_value = 0; + +SEC("cgroup/getsockopt") +int get_retval(struct bpf_sockopt *ctx) +{ + retval_value = bpf_get_retval(); + ctx_retval_value = ctx->retval; + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup/getsockopt") +int set_eisconn(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EISCONN)) + assertion_error = 1; + + return 1; +} + +SEC("cgroup/getsockopt") +int clear_retval(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + ctx->retval = 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c new file mode 100644 index 000000000000..d6e5903e06ba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 invocations = 0; +__u32 assertion_error = 0; +__u32 retval_value = 0; + +SEC("cgroup/setsockopt") +int get_retval(struct bpf_sockopt *ctx) +{ + retval_value = bpf_get_retval(); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup/setsockopt") +int set_eunatch(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EUNATCH)) + assertion_error = 1; + + return 0; +} + +SEC("cgroup/setsockopt") +int set_eisconn(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EISCONN)) + assertion_error = 1; + + return 0; +} + +SEC("cgroup/setsockopt") +int legacy_eperm(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/core_kern.c b/tools/testing/selftests/bpf/progs/core_kern.c index 13499cc15c7d..2715fe27d4cf 100644 --- a/tools/testing/selftests/bpf/progs/core_kern.c +++ b/tools/testing/selftests/bpf/progs/core_kern.c @@ -101,4 +101,20 @@ int balancer_ingress(struct __sk_buff *ctx) return 0; } +typedef int (*func_proto_typedef___match)(long); +typedef int (*func_proto_typedef___doesnt_match)(char *); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef___match); + +int proto_out[3]; + +SEC("raw_tracepoint/sys_enter") +int core_relo_proto(void *ctx) +{ + proto_out[0] = bpf_core_type_exists(func_proto_typedef___match); + proto_out[1] = bpf_core_type_exists(func_proto_typedef___doesnt_match); + proto_out[2] = bpf_core_type_exists(func_proto_typedef_nested1); + + return 0; +} + char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/core_kern_overflow.c b/tools/testing/selftests/bpf/progs/core_kern_overflow.c new file mode 100644 index 000000000000..f0d5652256ba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/core_kern_overflow.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +typedef int (*func_proto_typedef)(long); +typedef int (*func_proto_typedef_nested1)(func_proto_typedef); +typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1); + +int proto_out; + +SEC("raw_tracepoint/sys_enter") +int core_relo_proto(void *ctx) +{ + proto_out = bpf_core_type_exists(func_proto_typedef_nested2); + + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/fexit_sleep.c b/tools/testing/selftests/bpf/progs/fexit_sleep.c index bca92c9bd29a..106dc75efcc4 100644 --- a/tools/testing/selftests/bpf/progs/fexit_sleep.c +++ b/tools/testing/selftests/bpf/progs/fexit_sleep.c @@ -3,6 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char LICENSE[] SEC("license") = "GPL"; @@ -10,8 +11,8 @@ int pid = 0; int fentry_cnt = 0; int fexit_cnt = 0; -SEC("fentry/__x64_sys_nanosleep") -int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs) +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int nanosleep_fentry(void *ctx) { if (bpf_get_current_pid_tgid() >> 32 != pid) return 0; @@ -20,8 +21,8 @@ int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs) return 0; } -SEC("fexit/__x64_sys_nanosleep") -int BPF_PROG(nanosleep_fexit, const struct pt_regs *regs, int ret) +SEC("fexit/" SYS_PREFIX "sys_nanosleep") +int nanosleep_fexit(void *ctx) { if (bpf_get_current_pid_tgid() >> 32 != pid) return 0; diff --git a/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c index 68a5a9db928a..7e94412d47a5 100644 --- a/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c @@ -7,12 +7,12 @@ #include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") sock_map = { - .type = BPF_MAP_TYPE_SOCKMAP, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __type(key, int); + __type(value, int); + __uint(max_entries, 2); +} sock_map SEC(".maps"); SEC("freplace/cls_redirect") int freplace_cls_redirect_test(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/ima.c b/tools/testing/selftests/bpf/progs/ima.c index 96060ff4ffc6..e16a2c208481 100644 --- a/tools/testing/selftests/bpf/progs/ima.c +++ b/tools/testing/selftests/bpf/progs/ima.c @@ -18,8 +18,12 @@ struct { char _license[] SEC("license") = "GPL"; -SEC("lsm.s/bprm_committed_creds") -void BPF_PROG(ima, struct linux_binprm *bprm) +bool use_ima_file_hash; +bool enable_bprm_creds_for_exec; +bool enable_kernel_read_file; +bool test_deny; + +static void ima_test_common(struct file *file) { u64 ima_hash = 0; u64 *sample; @@ -28,8 +32,12 @@ void BPF_PROG(ima, struct linux_binprm *bprm) pid = bpf_get_current_pid_tgid() >> 32; if (pid == monitored_pid) { - ret = bpf_ima_inode_hash(bprm->file->f_inode, &ima_hash, - sizeof(ima_hash)); + if (!use_ima_file_hash) + ret = bpf_ima_inode_hash(file->f_inode, &ima_hash, + sizeof(ima_hash)); + else + ret = bpf_ima_file_hash(file, &ima_hash, + sizeof(ima_hash)); if (ret < 0 || ima_hash == 0) return; @@ -43,3 +51,53 @@ void BPF_PROG(ima, struct linux_binprm *bprm) return; } + +static int ima_test_deny(void) +{ + u32 pid; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid == monitored_pid && test_deny) + return -EPERM; + + return 0; +} + +SEC("lsm.s/bprm_committed_creds") +void BPF_PROG(bprm_committed_creds, struct linux_binprm *bprm) +{ + ima_test_common(bprm->file); +} + +SEC("lsm.s/bprm_creds_for_exec") +int BPF_PROG(bprm_creds_for_exec, struct linux_binprm *bprm) +{ + if (!enable_bprm_creds_for_exec) + return 0; + + ima_test_common(bprm->file); + return 0; +} + +SEC("lsm.s/kernel_read_file") +int BPF_PROG(kernel_read_file, struct file *file, enum kernel_read_file_id id, + bool contents) +{ + int ret; + + if (!enable_kernel_read_file) + return 0; + + if (!contents) + return 0; + + if (id != READING_POLICY) + return 0; + + ret = ima_test_deny(); + if (ret < 0) + return ret; + + ima_test_common(file); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c new file mode 100644 index 000000000000..4e8fed75a4e0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +extern void bpf_testmod_test_mod_kfunc(int i) __ksym; + +SEC("tc") +int kfunc_call_fail(struct __sk_buff *ctx) +{ + bpf_testmod_test_mod_kfunc(0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 8a8cf59017aa..5aecbb9fdc68 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -1,13 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "bpf_tcp_helpers.h" extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, __u32 c, __u64 d) __ksym; +extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; +extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; +extern void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; +extern void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; +extern void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; +extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; +extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; + SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) { @@ -44,4 +51,45 @@ int kfunc_call_test1(struct __sk_buff *skb) return ret; } +SEC("tc") +int kfunc_call_test_ref_btf_id(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + if (pt->a != 42 || pt->b != 108) + ret = -1; + bpf_kfunc_call_test_release(pt); + } + return ret; +} + +SEC("tc") +int kfunc_call_test_pass(struct __sk_buff *skb) +{ + struct prog_test_pass1 p1 = {}; + struct prog_test_pass2 p2 = {}; + short a = 0; + __u64 b = 0; + long c = 0; + char d = 0; + int e = 0; + + bpf_kfunc_call_test_pass_ctx(skb); + bpf_kfunc_call_test_pass1(&p1); + bpf_kfunc_call_test_pass2(&p2); + + bpf_kfunc_call_test_mem_len_pass1(&a, sizeof(a)); + bpf_kfunc_call_test_mem_len_pass1(&b, sizeof(b)); + bpf_kfunc_call_test_mem_len_pass1(&c, sizeof(c)); + bpf_kfunc_call_test_mem_len_pass1(&d, sizeof(d)); + bpf_kfunc_call_test_mem_len_pass1(&e, sizeof(e)); + bpf_kfunc_call_test_mem_len_fail2(&b, -1); + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi.c b/tools/testing/selftests/bpf/progs/kprobe_multi.c new file mode 100644 index 000000000000..600be50800f8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kprobe_multi.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <stdbool.h> + +char _license[] SEC("license") = "GPL"; + +extern const void bpf_fentry_test1 __ksym; +extern const void bpf_fentry_test2 __ksym; +extern const void bpf_fentry_test3 __ksym; +extern const void bpf_fentry_test4 __ksym; +extern const void bpf_fentry_test5 __ksym; +extern const void bpf_fentry_test6 __ksym; +extern const void bpf_fentry_test7 __ksym; +extern const void bpf_fentry_test8 __ksym; + +int pid = 0; +bool test_cookie = false; + +__u64 kprobe_test1_result = 0; +__u64 kprobe_test2_result = 0; +__u64 kprobe_test3_result = 0; +__u64 kprobe_test4_result = 0; +__u64 kprobe_test5_result = 0; +__u64 kprobe_test6_result = 0; +__u64 kprobe_test7_result = 0; +__u64 kprobe_test8_result = 0; + +__u64 kretprobe_test1_result = 0; +__u64 kretprobe_test2_result = 0; +__u64 kretprobe_test3_result = 0; +__u64 kretprobe_test4_result = 0; +__u64 kretprobe_test5_result = 0; +__u64 kretprobe_test6_result = 0; +__u64 kretprobe_test7_result = 0; +__u64 kretprobe_test8_result = 0; + +extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak; + +static void kprobe_multi_check(void *ctx, bool is_return) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; + __u64 addr = bpf_get_func_ip(ctx) - (CONFIG_X86_KERNEL_IBT ? 4 : 0); + +#define SET(__var, __addr, __cookie) ({ \ + if (((const void *) addr == __addr) && \ + (!test_cookie || (cookie == __cookie))) \ + __var = 1; \ +}) + + if (is_return) { + SET(kretprobe_test1_result, &bpf_fentry_test1, 8); + SET(kretprobe_test2_result, &bpf_fentry_test2, 7); + SET(kretprobe_test3_result, &bpf_fentry_test3, 6); + SET(kretprobe_test4_result, &bpf_fentry_test4, 5); + SET(kretprobe_test5_result, &bpf_fentry_test5, 4); + SET(kretprobe_test6_result, &bpf_fentry_test6, 3); + SET(kretprobe_test7_result, &bpf_fentry_test7, 2); + SET(kretprobe_test8_result, &bpf_fentry_test8, 1); + } else { + SET(kprobe_test1_result, &bpf_fentry_test1, 1); + SET(kprobe_test2_result, &bpf_fentry_test2, 2); + SET(kprobe_test3_result, &bpf_fentry_test3, 3); + SET(kprobe_test4_result, &bpf_fentry_test4, 4); + SET(kprobe_test5_result, &bpf_fentry_test5, 5); + SET(kprobe_test6_result, &bpf_fentry_test6, 6); + SET(kprobe_test7_result, &bpf_fentry_test7, 7); + SET(kprobe_test8_result, &bpf_fentry_test8, 8); + } + +#undef SET +} + +/* + * No tests in here, just to trigger 'bpf_fentry_test*' + * through tracing test_run + */ +SEC("fentry/bpf_modify_return_test") +int BPF_PROG(trigger) +{ + return 0; +} + +SEC("kprobe.multi/bpf_fentry_tes??") +int test_kprobe(struct pt_regs *ctx) +{ + kprobe_multi_check(ctx, false); + return 0; +} + +SEC("kretprobe.multi/bpf_fentry_test*") +int test_kretprobe(struct pt_regs *ctx) +{ + kprobe_multi_check(ctx, true); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/ksym_race.c b/tools/testing/selftests/bpf/progs/ksym_race.c new file mode 100644 index 000000000000..def97f2fed90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ksym_race.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +extern int bpf_testmod_ksym_percpu __ksym; + +SEC("tc") +int ksym_fail(struct __sk_buff *ctx) +{ + return *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c index 9b1f9b75d5c2..19423ed862e3 100644 --- a/tools/testing/selftests/bpf/progs/local_storage.c +++ b/tools/testing/selftests/bpf/progs/local_storage.c @@ -37,6 +37,13 @@ struct { } sk_storage_map SEC(".maps"); struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE); + __type(key, int); + __type(value, struct local_storage); +} sk_storage_map2 SEC(".maps"); + +struct { __uint(type, BPF_MAP_TYPE_TASK_STORAGE); __uint(map_flags, BPF_F_NO_PREALLOC); __type(key, int); @@ -115,7 +122,19 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address, if (storage->value != DUMMY_STORAGE_VALUE) sk_storage_result = -1; + /* This tests that we can associate multiple elements + * with the local storage. + */ + storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!storage) + return 0; + err = bpf_sk_storage_delete(&sk_storage_map, sock->sk); + if (err) + return 0; + + err = bpf_sk_storage_delete(&sk_storage_map2, sock->sk); if (!err) sk_storage_result = err; diff --git a/tools/testing/selftests/bpf/progs/perfbuf_bench.c b/tools/testing/selftests/bpf/progs/perfbuf_bench.c index e5ab4836a641..45204fe0c570 100644 --- a/tools/testing/selftests/bpf/progs/perfbuf_bench.c +++ b/tools/testing/selftests/bpf/progs/perfbuf_bench.c @@ -4,6 +4,7 @@ #include <linux/bpf.h> #include <stdint.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -18,7 +19,7 @@ const volatile int batch_cnt = 0; long sample_val = 42; long dropped __attribute__((aligned(128))) = 0; -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bench_perfbuf(void *ctx) { __u64 *sample; diff --git a/tools/testing/selftests/bpf/progs/ringbuf_bench.c b/tools/testing/selftests/bpf/progs/ringbuf_bench.c index 123607d314d6..6a468496f539 100644 --- a/tools/testing/selftests/bpf/progs/ringbuf_bench.c +++ b/tools/testing/selftests/bpf/progs/ringbuf_bench.c @@ -4,6 +4,7 @@ #include <linux/bpf.h> #include <stdint.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -30,7 +31,7 @@ static __always_inline long get_flags() return sz >= wakeup_data_size ? BPF_RB_FORCE_WAKEUP : BPF_RB_NO_WAKEUP; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bench_ringbuf(void *ctx) { long *sample, flags; diff --git a/tools/testing/selftests/bpf/progs/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c index 1612a32007b6..495990d355ef 100644 --- a/tools/testing/selftests/bpf/progs/sample_map_ret0.c +++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c @@ -2,19 +2,19 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") htab = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(long), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, long); + __uint(max_entries, 2); +} htab SEC(".maps"); -struct bpf_map_def SEC("maps") array = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(long), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, long); + __uint(max_entries, 2); +} array SEC(".maps"); /* Sample program which should always load for testing control paths. */ SEC(".text") int func() diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index 95d5b941bc1f..c9abfe3a11af 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -7,8 +7,6 @@ int bpf_prog1(struct __sk_buff *skb) { void *data_end = (void *)(long) skb->data_end; void *data = (void *)(long) skb->data; - __u32 lport = skb->local_port; - __u32 rport = skb->remote_port; __u8 *d = data; int err; diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 79c8139b63b8..c8d810010a94 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -72,18 +72,19 @@ int _getsockopt(struct bpf_sockopt *ctx) * reasons. */ - if (optval + sizeof(struct tcp_zerocopy_receive) > optval_end) - return 0; /* EPERM, bounds check */ + /* Check that optval contains address (__u64) */ + if (optval + sizeof(__u64) > optval_end) + return 0; /* bounds check */ if (((struct tcp_zerocopy_receive *)optval)->address != 0) - return 0; /* EPERM, unexpected data */ + return 0; /* unexpected data */ return 1; } if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ ctx->retval = 0; /* Reset system call return value to zero */ @@ -96,24 +97,24 @@ int _getsockopt(struct bpf_sockopt *ctx) * bytes of data. */ if (optval_end - optval != page_size) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ return 1; } if (ctx->level != SOL_CUSTOM) - return 0; /* EPERM, deny everything except custom level */ + return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); if (!storage) - return 0; /* EPERM, couldn't get sk storage */ + return 0; /* couldn't get sk storage */ if (!ctx->retval) - return 0; /* EPERM, kernel should not have handled + return 0; /* kernel should not have handled * SOL_CUSTOM, something is wrong! */ ctx->retval = 0; /* Reset system call return value to zero */ @@ -152,7 +153,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Overwrite SO_SNDBUF value */ if (optval + sizeof(__u32) > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ *(__u32 *)optval = 0x55AA; ctx->optlen = 4; @@ -164,7 +165,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Always use cubic */ if (optval + 5 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ memcpy(optval, "cubic", 5); ctx->optlen = 5; @@ -175,10 +176,10 @@ int _setsockopt(struct bpf_sockopt *ctx) if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { /* Original optlen is larger than PAGE_SIZE. */ if (ctx->optlen != page_size * 2) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ /* Make sure we can trim the buffer. */ optval[0] = 0; @@ -189,21 +190,21 @@ int _setsockopt(struct bpf_sockopt *ctx) * bytes of data. */ if (optval_end - optval != page_size) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ return 1; } if (ctx->level != SOL_CUSTOM) - return 0; /* EPERM, deny everything except custom level */ + return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); if (!storage) - return 0; /* EPERM, couldn't get sk storage */ + return 0; /* couldn't get sk storage */ storage->val = optval[0]; ctx->optlen = -1; /* BPF has consumed this option, don't call kernel diff --git a/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c b/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c new file mode 100644 index 000000000000..2eb297df3dd6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/stacktrace_map_skip.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define TEST_STACK_DEPTH 2 +#define TEST_MAX_ENTRIES 16384 + +typedef __u64 stack_trace_t[TEST_STACK_DEPTH]; + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, stack_trace_t); +} stackmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, __u32); +} stackid_hmap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, TEST_MAX_ENTRIES); + __type(key, __u32); + __type(value, stack_trace_t); +} stack_amap SEC(".maps"); + +int pid = 0; +int control = 0; +int failed = 0; + +SEC("tracepoint/sched/sched_switch") +int oncpu(struct trace_event_raw_sched_switch *ctx) +{ + __u32 max_len = TEST_STACK_DEPTH * sizeof(__u64); + __u32 key = 0, val = 0; + __u64 *stack_p; + + if (pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + if (control) + return 0; + + /* it should allow skipping whole buffer size entries */ + key = bpf_get_stackid(ctx, &stackmap, TEST_STACK_DEPTH); + if ((int)key >= 0) { + /* The size of stackmap and stack_amap should be the same */ + bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) { + bpf_get_stack(ctx, stack_p, max_len, TEST_STACK_DEPTH); + /* it wrongly skipped all the entries and filled zero */ + if (stack_p[0] == 0) + failed = 1; + } + } else { + /* old kernel doesn't support skipping that many entries */ + failed = 2; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c new file mode 100644 index 000000000000..f00a9731930e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define EAFNOSUPPORT 97 +#define EPROTO 71 +#define ENONET 64 +#define EINVAL 22 +#define ENOENT 2 + +int test_einval_bpf_tuple = 0; +int test_einval_reserved = 0; +int test_einval_netns_id = 0; +int test_einval_len_opts = 0; +int test_eproto_l4proto = 0; +int test_enonet_netns_id = 0; +int test_enoent_lookup = 0; +int test_eafnosupport = 0; + +struct nf_conn; + +struct bpf_ct_opts___local { + s32 netns_id; + s32 error; + u8 l4proto; + u8 reserved[3]; +} __attribute__((preserve_access_index)); + +struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +void bpf_ct_release(struct nf_conn *) __ksym; + +static __always_inline void +nf_ct_test(struct nf_conn *(*func)(void *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32), + void *ctx) +{ + struct bpf_ct_opts___local opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 }; + struct bpf_sock_tuple bpf_tuple; + struct nf_conn *ct; + + __builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4)); + + ct = func(ctx, NULL, 0, &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_einval_bpf_tuple = opts_def.error; + + opts_def.reserved[0] = 1; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.reserved[0] = 0; + opts_def.l4proto = IPPROTO_TCP; + if (ct) + bpf_ct_release(ct); + else + test_einval_reserved = opts_def.error; + + opts_def.netns_id = -2; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.netns_id = -1; + if (ct) + bpf_ct_release(ct); + else + test_einval_netns_id = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def) - 1); + if (ct) + bpf_ct_release(ct); + else + test_einval_len_opts = opts_def.error; + + opts_def.l4proto = IPPROTO_ICMP; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.l4proto = IPPROTO_TCP; + if (ct) + bpf_ct_release(ct); + else + test_eproto_l4proto = opts_def.error; + + opts_def.netns_id = 0xf00f; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.netns_id = -1; + if (ct) + bpf_ct_release(ct); + else + test_enonet_netns_id = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_enoent_lookup = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4) - 1, &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_eafnosupport = opts_def.error; +} + +SEC("xdp") +int nf_xdp_ct_test(struct xdp_md *ctx) +{ + nf_ct_test((void *)bpf_xdp_ct_lookup, ctx); + return 0; +} + +SEC("tc") +int nf_skb_ct_test(struct __sk_buff *ctx) +{ + nf_ct_test((void *)bpf_skb_ct_lookup, ctx); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/btf_decl_tag.c b/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c index c88ccc53529a..c88ccc53529a 100644 --- a/tools/testing/selftests/bpf/progs/btf_decl_tag.c +++ b/tools/testing/selftests/bpf/progs/test_btf_decl_tag.c diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c index 160ead6c67b2..07c94df13660 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c @@ -9,12 +9,15 @@ struct ipv_counts { unsigned int v6; }; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" struct bpf_map_def SEC("maps") btf_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(int), .value_size = sizeof(struct ipv_counts), .max_entries = 4, }; +#pragma GCC diagnostic pop BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts); diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c index 1884a5bd10f5..762671a2e90c 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -9,6 +9,8 @@ struct ipv_counts { unsigned int v6; }; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" /* just to validate we can handle maps in multiple sections */ struct bpf_map_def SEC("maps") btf_map_legacy = { .type = BPF_MAP_TYPE_ARRAY, @@ -16,6 +18,7 @@ struct bpf_map_def SEC("maps") btf_map_legacy = { .value_size = sizeof(long long), .max_entries = 4, }; +#pragma GCC diagnostic pop BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts); diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c index 15e0f9945fe4..1dabb88f8cb4 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c @@ -8,12 +8,12 @@ struct ipv_counts { unsigned int v6; }; -struct bpf_map_def SEC("maps") btf_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct ipv_counts), - .max_entries = 4, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(struct ipv_counts)); + __uint(max_entries, 4); +} btf_map SEC(".maps"); __attribute__((noinline)) int test_long_fname_2(void) diff --git a/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c b/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c new file mode 100644 index 000000000000..4061f701ca50 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_custom_sec_handlers.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile int my_pid; + +bool abc1_called; +bool abc2_called; +bool custom1_called; +bool custom2_called; +bool kprobe1_called; +bool xyz_called; + +SEC("abc") +int abc1(void *ctx) +{ + abc1_called = true; + return 0; +} + +SEC("abc/whatever") +int abc2(void *ctx) +{ + abc2_called = true; + return 0; +} + +SEC("custom") +int custom1(void *ctx) +{ + custom1_called = true; + return 0; +} + +SEC("custom/something") +int custom2(void *ctx) +{ + custom2_called = true; + return 0; +} + +SEC("kprobe") +int kprobe1(void *ctx) +{ + kprobe1_called = true; + return 0; +} + +SEC("xyz/blah") +int xyz(void *ctx) +{ + int whatever; + + /* use sleepable helper, custom handler should set sleepable flag */ + bpf_copy_from_user(&whatever, sizeof(whatever), NULL); + xyz_called = true; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c index 8812a90da4eb..702578a5e496 100644 --- a/tools/testing/selftests/bpf/progs/test_probe_user.c +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -7,20 +7,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> - -#if defined(__TARGET_ARCH_x86) -#define SYSCALL_WRAPPER 1 -#define SYS_PREFIX "__x64_" -#elif defined(__TARGET_ARCH_s390) -#define SYSCALL_WRAPPER 1 -#define SYS_PREFIX "__s390x_" -#elif defined(__TARGET_ARCH_arm64) -#define SYSCALL_WRAPPER 1 -#define SYS_PREFIX "__arm64_" -#else -#define SYSCALL_WRAPPER 0 -#define SYS_PREFIX "" -#endif +#include "bpf_misc.h" static struct sockaddr_in old; diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c index eaa7d9dba0be..5bdc0d38efc0 100644 --- a/tools/testing/selftests/bpf/progs/test_ringbuf.c +++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c @@ -3,6 +3,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -35,7 +36,7 @@ long prod_pos = 0; /* inner state */ long seq = 0; -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int test_ringbuf(void *ctx) { int cur_pid = bpf_get_current_pid_tgid() >> 32; diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c index b4233d3efac2..92354cd72044 100644 --- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -10,7 +10,7 @@ static __always_inline int bpf_send_signal_test(void *ctx) { int ret; - if (status != 0 || sig == 0 || pid == 0) + if (status != 0 || pid == 0) return 0; if ((bpf_get_current_pid_tgid() >> 32) == pid) { diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c index 83b0aaa52ef7..6058dcb11b36 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -392,6 +392,7 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; int err, family; + __u32 val_u32; bool v4; v4 = (ctx->family == AF_INET); @@ -412,12 +413,22 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) /* Narrow loads from remote_port field. Expect SRC_PORT. */ if (LSB(ctx->remote_port, 0) != ((SRC_PORT >> 0) & 0xff) || - LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff) || - LSB(ctx->remote_port, 2) != 0 || LSB(ctx->remote_port, 3) != 0) + LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff)) return SK_DROP; if (LSW(ctx->remote_port, 0) != SRC_PORT) return SK_DROP; + /* + * NOTE: 4-byte load from bpf_sk_lookup at remote_port offset + * is quirky. It gets rewritten by the access converter to a + * 2-byte load for backward compatibility. Treating the load + * result as a be16 value makes the code portable across + * little- and big-endian platforms. + */ + val_u32 = *(__u32 *)&ctx->remote_port; + if (val_u32 != SRC_PORT) + return SK_DROP; + /* Narrow loads from local_port field. Expect DST_PORT. */ if (LSB(ctx->local_port, 0) != ((DST_PORT >> 0) & 0xff) || LSB(ctx->local_port, 1) != ((DST_PORT >> 8) & 0xff) || diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c index c304cd5b8cad..37aacc66cd68 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c @@ -10,12 +10,12 @@ #define NUM_CGROUP_LEVELS 4 -struct bpf_map_def SEC("maps") cgroup_ids = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), - .max_entries = NUM_CGROUP_LEVELS, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u64); + __uint(max_entries, NUM_CGROUP_LEVELS); +} cgroup_ids SEC(".maps"); static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level) { diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index 81b57b9aaaea..9f4b8f9f1181 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -12,6 +12,7 @@ enum bpf_linum_array_idx { EGRESS_LINUM_IDX, INGRESS_LINUM_IDX, + READ_SK_DST_PORT_LINUM_IDX, __NR_BPF_LINUM_ARRAY_IDX, }; @@ -113,7 +114,7 @@ static void tpcpy(struct bpf_tcp_sock *dst, #define RET_LOG() ({ \ linum = __LINE__; \ - bpf_map_update_elem(&linum_map, &linum_idx, &linum, BPF_NOEXIST); \ + bpf_map_update_elem(&linum_map, &linum_idx, &linum, BPF_ANY); \ return CG_OK; \ }) @@ -133,11 +134,11 @@ int egress_read_sock_fields(struct __sk_buff *skb) if (!sk) RET_LOG(); - /* Not the testing egress traffic or - * TCP_LISTEN (10) socket will be copied at the ingress side. + /* Not testing the egress traffic or the listening socket, + * which are covered by the cgroup_skb/ingress test program. */ if (sk->family != AF_INET6 || !is_loopback6(sk->src_ip6) || - sk->state == 10) + sk->state == BPF_TCP_LISTEN) return CG_OK; if (sk->src_port == bpf_ntohs(srv_sa6.sin6_port)) { @@ -231,8 +232,8 @@ int ingress_read_sock_fields(struct __sk_buff *skb) sk->src_port != bpf_ntohs(srv_sa6.sin6_port)) return CG_OK; - /* Only interested in TCP_LISTEN */ - if (sk->state != 10) + /* Only interested in the listening socket */ + if (sk->state != BPF_TCP_LISTEN) return CG_OK; /* It must be a fullsock for cgroup_skb/ingress prog */ @@ -250,4 +251,54 @@ int ingress_read_sock_fields(struct __sk_buff *skb) return CG_OK; } +/* + * NOTE: 4-byte load from bpf_sock at dst_port offset is quirky. It + * gets rewritten by the access converter to a 2-byte load for + * backward compatibility. Treating the load result as a be16 value + * makes the code portable across little- and big-endian platforms. + */ +static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk) +{ + __u32 *word = (__u32 *)&sk->dst_port; + return word[0] == bpf_htons(0xcafe); +} + +static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk) +{ + __u16 *half = (__u16 *)&sk->dst_port; + return half[0] == bpf_htons(0xcafe); +} + +static __noinline bool sk_dst_port__load_byte(struct bpf_sock *sk) +{ + __u8 *byte = (__u8 *)&sk->dst_port; + return byte[0] == 0xca && byte[1] == 0xfe; +} + +SEC("cgroup_skb/egress") +int read_sk_dst_port(struct __sk_buff *skb) +{ + __u32 linum, linum_idx; + struct bpf_sock *sk; + + linum_idx = READ_SK_DST_PORT_LINUM_IDX; + + sk = skb->sk; + if (!sk) + RET_LOG(); + + /* Ignore everything but the SYN from the client socket */ + if (sk->state != BPF_TCP_SYN_SENT) + return CG_OK; + + if (!sk_dst_port__load_word(sk)) + RET_LOG(); + if (!sk_dst_port__load_half(sk)) + RET_LOG(); + if (!sk_dst_port__load_byte(sk)) + RET_LOG(); + + return CG_OK; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c b/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c new file mode 100644 index 000000000000..9d58d61c0dee --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +SEC("sk_msg") +int prog_skmsg_verdict(struct sk_msg_md *msg) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton.c b/tools/testing/selftests/bpf/progs/test_subskeleton.c new file mode 100644 index 000000000000..006417974372 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* volatile to force a read, compiler may assume 0 otherwise */ +const volatile int rovar1; +int out1; + +/* Override weak symbol in test_subskeleton_lib */ +int var5 = 5; + +extern volatile bool CONFIG_BPF_SYSCALL __kconfig; + +extern int lib_routine(void); + +SEC("raw_tp/sys_enter") +int handler1(const void *ctx) +{ + (void) CONFIG_BPF_SYSCALL; + + out1 = lib_routine() * rovar1; + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c b/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c new file mode 100644 index 000000000000..ecfafe812c36 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton_lib.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <stdbool.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +/* volatile to force a read */ +const volatile int var1; +volatile int var2 = 1; +struct { + int var3_1; + __s64 var3_2; +} var3; +int libout1; + +extern volatile bool CONFIG_BPF_SYSCALL __kconfig; + +int var4[4]; + +__weak int var5 SEC(".data"); + +/* Fully contained within library extern-and-definition */ +extern int var6; + +int var7 SEC(".data.custom"); + +int (*fn_ptr)(void); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map1 SEC(".maps"); + +extern struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map2 SEC(".maps"); + +int lib_routine(void) +{ + __u32 key = 1, value = 2; + + (void) CONFIG_BPF_SYSCALL; + bpf_map_update_elem(&map2, &key, &value, BPF_ANY); + + libout1 = var1 + var2 + var3.var3_1 + var3.var3_2 + var5 + var6; + return libout1; +} + +SEC("perf_event") +int lib_perf_handler(struct pt_regs *ctx) +{ + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c b/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c new file mode 100644 index 000000000000..80238486b7ce --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_subskeleton_lib2.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int var6 = 6; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 16); +} map2 SEC(".maps"); + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c new file mode 100644 index 000000000000..06f300d06dbd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2022 Meta + +#include <stddef.h> +#include <stdint.h> +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/stddef.h> +#include <linux/pkt_cls.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <sys/socket.h> + +/* veth_src --- veth_src_fwd --- veth_det_fwd --- veth_dst + * | | + * ns_src | ns_fwd | ns_dst + * + * ns_src and ns_dst: ENDHOST namespace + * ns_fwd: Fowarding namespace + */ + +#define ctx_ptr(field) (void *)(long)(field) + +#define ip4_src __bpf_htonl(0xac100164) /* 172.16.1.100 */ +#define ip4_dst __bpf_htonl(0xac100264) /* 172.16.2.100 */ + +#define ip6_src { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x01, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe } +#define ip6_dst { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \ + 0x00, 0x02, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe } + +#define v6_equal(a, b) (a.s6_addr32[0] == b.s6_addr32[0] && \ + a.s6_addr32[1] == b.s6_addr32[1] && \ + a.s6_addr32[2] == b.s6_addr32[2] && \ + a.s6_addr32[3] == b.s6_addr32[3]) + +volatile const __u32 IFINDEX_SRC; +volatile const __u32 IFINDEX_DST; + +#define EGRESS_ENDHOST_MAGIC 0x0b9fbeef +#define INGRESS_FWDNS_MAGIC 0x1b9fbeef +#define EGRESS_FWDNS_MAGIC 0x2b9fbeef + +enum { + INGRESS_FWDNS_P100, + INGRESS_FWDNS_P101, + EGRESS_FWDNS_P100, + EGRESS_FWDNS_P101, + INGRESS_ENDHOST, + EGRESS_ENDHOST, + SET_DTIME, + __MAX_CNT, +}; + +enum { + TCP_IP6_CLEAR_DTIME, + TCP_IP4, + TCP_IP6, + UDP_IP4, + UDP_IP6, + TCP_IP4_RT_FWD, + TCP_IP6_RT_FWD, + UDP_IP4_RT_FWD, + UDP_IP6_RT_FWD, + UKN_TEST, + __NR_TESTS, +}; + +enum { + SRC_NS = 1, + DST_NS, +}; + +__u32 dtimes[__NR_TESTS][__MAX_CNT] = {}; +__u32 errs[__NR_TESTS][__MAX_CNT] = {}; +__u32 test = 0; + +static void inc_dtimes(__u32 idx) +{ + if (test < __NR_TESTS) + dtimes[test][idx]++; + else + dtimes[UKN_TEST][idx]++; +} + +static void inc_errs(__u32 idx) +{ + if (test < __NR_TESTS) + errs[test][idx]++; + else + errs[UKN_TEST][idx]++; +} + +static int skb_proto(int type) +{ + return type & 0xff; +} + +static int skb_ns(int type) +{ + return (type >> 8) & 0xff; +} + +static bool fwdns_clear_dtime(void) +{ + return test == TCP_IP6_CLEAR_DTIME; +} + +static bool bpf_fwd(void) +{ + return test < TCP_IP4_RT_FWD; +} + +/* -1: parse error: TC_ACT_SHOT + * 0: not testing traffic: TC_ACT_OK + * >0: first byte is the inet_proto, second byte has the netns + * of the sender + */ +static int skb_get_type(struct __sk_buff *skb) +{ + void *data_end = ctx_ptr(skb->data_end); + void *data = ctx_ptr(skb->data); + __u8 inet_proto = 0, ns = 0; + struct ipv6hdr *ip6h; + struct iphdr *iph; + + switch (skb->protocol) { + case __bpf_htons(ETH_P_IP): + iph = data + sizeof(struct ethhdr); + if (iph + 1 > data_end) + return -1; + if (iph->saddr == ip4_src) + ns = SRC_NS; + else if (iph->saddr == ip4_dst) + ns = DST_NS; + inet_proto = iph->protocol; + break; + case __bpf_htons(ETH_P_IPV6): + ip6h = data + sizeof(struct ethhdr); + if (ip6h + 1 > data_end) + return -1; + if (v6_equal(ip6h->saddr, (struct in6_addr)ip6_src)) + ns = SRC_NS; + else if (v6_equal(ip6h->saddr, (struct in6_addr)ip6_dst)) + ns = DST_NS; + inet_proto = ip6h->nexthdr; + break; + default: + return 0; + } + + if ((inet_proto != IPPROTO_TCP && inet_proto != IPPROTO_UDP) || !ns) + return 0; + + return (ns << 8 | inet_proto); +} + +/* format: direction@iface@netns + * egress@veth_(src|dst)@ns_(src|dst) + */ +SEC("tc") +int egress_host(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + if (skb_proto(skb_type) == IPPROTO_TCP) { + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && + skb->tstamp) + inc_dtimes(EGRESS_ENDHOST); + else + inc_errs(EGRESS_ENDHOST); + } else { + if (skb->tstamp_type == BPF_SKB_TSTAMP_UNSPEC && + skb->tstamp) + inc_dtimes(EGRESS_ENDHOST); + else + inc_errs(EGRESS_ENDHOST); + } + + skb->tstamp = EGRESS_ENDHOST_MAGIC; + + return TC_ACT_OK; +} + +/* ingress@veth_(src|dst)@ns_(src|dst) */ +SEC("tc") +int ingress_host(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO && + skb->tstamp == EGRESS_FWDNS_MAGIC) + inc_dtimes(INGRESS_ENDHOST); + else + inc_errs(INGRESS_ENDHOST); + + return TC_ACT_OK; +} + +/* ingress@veth_(src|dst)_fwd@ns_fwd priority 100 */ +SEC("tc") +int ingress_fwdns_prio100(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + /* delivery_time is only available to the ingress + * if the tc-bpf checks the skb->tstamp_type. + */ + if (skb->tstamp == EGRESS_ENDHOST_MAGIC) + inc_errs(INGRESS_FWDNS_P100); + + if (fwdns_clear_dtime()) + skb->tstamp = 0; + + return TC_ACT_UNSPEC; +} + +/* egress@veth_(src|dst)_fwd@ns_fwd priority 100 */ +SEC("tc") +int egress_fwdns_prio100(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1) + return TC_ACT_SHOT; + if (!skb_type) + return TC_ACT_OK; + + /* delivery_time is always available to egress even + * the tc-bpf did not use the tstamp_type. + */ + if (skb->tstamp == INGRESS_FWDNS_MAGIC) + inc_dtimes(EGRESS_FWDNS_P100); + else + inc_errs(EGRESS_FWDNS_P100); + + if (fwdns_clear_dtime()) + skb->tstamp = 0; + + return TC_ACT_UNSPEC; +} + +/* ingress@veth_(src|dst)_fwd@ns_fwd priority 101 */ +SEC("tc") +int ingress_fwdns_prio101(struct __sk_buff *skb) +{ + __u64 expected_dtime = EGRESS_ENDHOST_MAGIC; + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1 || !skb_type) + /* Should have handled in prio100 */ + return TC_ACT_SHOT; + + if (skb_proto(skb_type) == IPPROTO_UDP) + expected_dtime = 0; + + if (skb->tstamp_type) { + if (fwdns_clear_dtime() || + skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || + skb->tstamp != expected_dtime) + inc_errs(INGRESS_FWDNS_P101); + else + inc_dtimes(INGRESS_FWDNS_P101); + } else { + if (!fwdns_clear_dtime() && expected_dtime) + inc_errs(INGRESS_FWDNS_P101); + } + + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { + skb->tstamp = INGRESS_FWDNS_MAGIC; + } else { + if (bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_DELIVERY_MONO)) + inc_errs(SET_DTIME); + if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_UNSPEC)) + inc_errs(SET_DTIME); + } + + if (skb_ns(skb_type) == SRC_NS) + return bpf_fwd() ? + bpf_redirect_neigh(IFINDEX_DST, NULL, 0, 0) : TC_ACT_OK; + else + return bpf_fwd() ? + bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0) : TC_ACT_OK; +} + +/* egress@veth_(src|dst)_fwd@ns_fwd priority 101 */ +SEC("tc") +int egress_fwdns_prio101(struct __sk_buff *skb) +{ + int skb_type; + + skb_type = skb_get_type(skb); + if (skb_type == -1 || !skb_type) + /* Should have handled in prio100 */ + return TC_ACT_SHOT; + + if (skb->tstamp_type) { + if (fwdns_clear_dtime() || + skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO || + skb->tstamp != INGRESS_FWDNS_MAGIC) + inc_errs(EGRESS_FWDNS_P101); + else + inc_dtimes(EGRESS_FWDNS_P101); + } else { + if (!fwdns_clear_dtime()) + inc_errs(EGRESS_FWDNS_P101); + } + + if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) { + skb->tstamp = EGRESS_FWDNS_MAGIC; + } else { + if (bpf_skb_set_tstamp(skb, EGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_DELIVERY_MONO)) + inc_errs(SET_DTIME); + if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC, + BPF_SKB_TSTAMP_UNSPEC)) + inc_errs(SET_DTIME); + } + + return TC_ACT_OK; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c index bf28814bfde5..950a70b61e74 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_edt.c +++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c @@ -17,12 +17,12 @@ #define THROTTLE_RATE_BPS (5 * 1000 * 1000) /* flow_key => last_tstamp timestamp used */ -struct bpf_map_def SEC("maps") flow_map = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(uint32_t), - .value_size = sizeof(uint64_t), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, uint32_t); + __type(value, uint64_t); + __uint(max_entries, 1); +} flow_map SEC(".maps"); static inline int throttle_flow(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index cd747cd93dbe..6edebce563b5 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -16,12 +16,12 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -struct bpf_map_def SEC("maps") results = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), - .max_entries = 3, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 3); +} results SEC(".maps"); static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk, void *iph, __u32 ip_size, diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 199c61b7d062..53b64c999450 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -7,11 +7,10 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; void *data = (void *)(long)xdp->data; - unsigned int data_len; + int data_len = bpf_xdp_get_buff_len(xdp); int offset = 0; /* Data length determine test case */ - data_len = data_end - data; if (data_len == 54) { /* sizeof(pkt_v4) */ offset = 4096; /* test too large offset */ @@ -20,7 +19,12 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) } else if (data_len == 64) { offset = 128; } else if (data_len == 128) { - offset = 4096 - 256 - 320 - data_len; /* Max tail grow 3520 */ + /* Max tail grow 3520 */ + offset = 4096 - 256 - 320 - data_len; + } else if (data_len == 9000) { + offset = 10; + } else if (data_len == 9001) { + offset = 4096; } else { return XDP_ABORTED; /* No matching test */ } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c index b7448253d135..ca68c038357c 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c @@ -12,14 +12,38 @@ SEC("xdp") int _xdp_adjust_tail_shrink(struct xdp_md *xdp) { - void *data_end = (void *)(long)xdp->data_end; - void *data = (void *)(long)xdp->data; + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; int offset = 0; - if (data_end - data == 54) /* sizeof(pkt_v4) */ + switch (bpf_xdp_get_buff_len(xdp)) { + case 54: + /* sizeof(pkt_v4) */ offset = 256; /* shrink too much */ - else + break; + case 9000: + /* non-linear buff test cases */ + if (data + 1 > data_end) + return XDP_DROP; + + switch (data[0]) { + case 0: + offset = 10; + break; + case 1: + offset = 4100; + break; + case 2: + offset = 8200; + break; + default: + return XDP_DROP; + } + break; + default: offset = 20; + break; + } if (bpf_xdp_adjust_tail(xdp, 0 - offset)) return XDP_DROP; return XDP_TX; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index 58cf4345f5cc..3379d303f41a 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -49,7 +49,7 @@ int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) void *data = (void *)(long)xdp->data; meta.ifindex = xdp->rxq->dev->ifindex; - meta.pkt_len = data_end - data; + meta.pkt_len = bpf_xdp_get_buff_len((struct xdp_md *)xdp); bpf_xdp_output(xdp, &perf_buf_map, ((__u64) meta.pkt_len << 32) | BPF_F_CURRENT_CPU, diff --git a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c new file mode 100644 index 000000000000..77a123071940 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define ETH_ALEN 6 +#define HDR_SZ (sizeof(struct ethhdr) + sizeof(struct ipv6hdr) + sizeof(struct udphdr)) +const volatile int ifindex_out; +const volatile int ifindex_in; +const volatile __u8 expect_dst[ETH_ALEN]; +volatile int pkts_seen_xdp = 0; +volatile int pkts_seen_zero = 0; +volatile int pkts_seen_tc = 0; +volatile int retcode = XDP_REDIRECT; + +SEC("xdp") +int xdp_redirect(struct xdp_md *xdp) +{ + __u32 *metadata = (void *)(long)xdp->data_meta; + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + + __u8 *payload = data + HDR_SZ; + int ret = retcode; + + if (payload + 1 > data_end) + return XDP_ABORTED; + + if (xdp->ingress_ifindex != ifindex_in) + return XDP_ABORTED; + + if (metadata + 1 > data) + return XDP_ABORTED; + + if (*metadata != 0x42) + return XDP_ABORTED; + + if (*payload == 0) { + *payload = 0x42; + pkts_seen_zero++; + } + + if (bpf_xdp_adjust_meta(xdp, 4)) + return XDP_ABORTED; + + if (retcode > XDP_PASS) + retcode--; + + if (ret == XDP_REDIRECT) + return bpf_redirect(ifindex_out, 0); + + return ret; +} + +static bool check_pkt(void *data, void *data_end) +{ + struct ipv6hdr *iph = data + sizeof(struct ethhdr); + __u8 *payload = data + HDR_SZ; + + if (payload + 1 > data_end) + return false; + + if (iph->nexthdr != IPPROTO_UDP || *payload != 0x42) + return false; + + /* reset the payload so the same packet doesn't get counted twice when + * it cycles back through the kernel path and out the dst veth + */ + *payload = 0; + return true; +} + +SEC("xdp") +int xdp_count_pkts(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + void *data_end = (void *)(long)xdp->data_end; + + if (check_pkt(data, data_end)) + pkts_seen_xdp++; + + /* Return XDP_DROP to make sure the data page is recycled, like when it + * exits a physical NIC. Recycled pages will be counted in the + * pkts_seen_zero counter above. + */ + return XDP_DROP; +} + +SEC("tc") +int tc_count_pkts(struct __sk_buff *skb) +{ + void *data = (void *)(long)skb->data; + void *data_end = (void *)(long)skb->data_end; + + if (check_pkt(data, data_end)) + pkts_seen_tc++; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c b/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c new file mode 100644 index 000000000000..2a3496d8e327 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <bpf/bpf_helpers.h> + +int _version SEC("version") = 1; + +SEC("xdp.frags") +int xdp_adjust_frags(struct xdp_md *xdp) +{ + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; + __u8 val[16] = {}; + __u32 offset; + int err; + + if (data + sizeof(__u32) > data_end) + return XDP_DROP; + + offset = *(__u32 *)data; + err = bpf_xdp_load_bytes(xdp, offset, val, sizeof(val)); + if (err < 0) + return XDP_DROP; + + if (val[0] != 0xaa || val[15] != 0xaa) /* marker */ + return XDP_DROP; + + val[0] = 0xbb; /* update the marker */ + val[15] = 0xbb; + err = bpf_xdp_store_bytes(xdp, offset, val, sizeof(val)); + if (err < 0) + return XDP_DROP; + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c new file mode 100644 index 000000000000..97ed625bb70a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define IFINDEX_LO 1 + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 4); +} cpu_map SEC(".maps"); + +SEC("xdp/cpumap") +int xdp_dummy_cm(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp.frags/cpumap") +int xdp_dummy_cm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c index 532025057711..20ec6723df18 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -24,7 +24,7 @@ int xdp_dummy_prog(struct xdp_md *ctx) return XDP_PASS; } -SEC("xdp_cpumap/dummy_cm") +SEC("xdp/cpumap") int xdp_dummy_cm(struct xdp_md *ctx) { if (ctx->ingress_ifindex == IFINDEX_LO) @@ -33,4 +33,10 @@ int xdp_dummy_cm(struct xdp_md *ctx) return XDP_PASS; } +SEC("xdp.frags/cpumap") +int xdp_dummy_cm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c new file mode 100644 index 000000000000..cdcf7de7ec8c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 4); +} dm_ports SEC(".maps"); + +/* valid program on DEVMAP entry via SEC name; + * has access to egress and ingress ifindex + */ +SEC("xdp/devmap") +int xdp_dummy_dm(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp.frags/devmap") +int xdp_dummy_dm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 1e6b9c38ea6d..4139a14f9996 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -27,7 +27,7 @@ int xdp_dummy_prog(struct xdp_md *ctx) /* valid program on DEVMAP entry via SEC name; * has access to egress and ingress ifindex */ -SEC("xdp_devmap/map_prog") +SEC("xdp/devmap") int xdp_dummy_dm(struct xdp_md *ctx) { char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; @@ -40,4 +40,11 @@ int xdp_dummy_dm(struct xdp_md *ctx) return XDP_PASS; } + +SEC("xdp.frags/devmap") +int xdp_dummy_dm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c index 119582aa105a..6695478c2b25 100644 --- a/tools/testing/selftests/bpf/progs/trace_printk.c +++ b/tools/testing/selftests/bpf/progs/trace_printk.c @@ -4,6 +4,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -12,7 +13,7 @@ int trace_printk_ran = 0; const char fmt[] = "Testing,testing %d\n"; -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int sys_enter(void *ctx) { trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt), diff --git a/tools/testing/selftests/bpf/progs/trace_vprintk.c b/tools/testing/selftests/bpf/progs/trace_vprintk.c index d327241ba047..969306cd4f33 100644 --- a/tools/testing/selftests/bpf/progs/trace_vprintk.c +++ b/tools/testing/selftests/bpf/progs/trace_vprintk.c @@ -4,6 +4,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -11,7 +12,7 @@ int null_data_vprintk_ret = 0; int trace_vprintk_ret = 0; int trace_vprintk_ran = 0; -SEC("fentry/__x64_sys_nanosleep") +SEC("fentry/" SYS_PREFIX "sys_nanosleep") int sys_enter(void *ctx) { static const char one[] = "1"; diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c index 2098f3f27f18..2ab049b54d6c 100644 --- a/tools/testing/selftests/bpf/progs/trigger_bench.c +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -5,6 +5,7 @@ #include <asm/unistd.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_misc.h" char _license[] SEC("license") = "GPL"; @@ -25,28 +26,28 @@ int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id) return 0; } -SEC("kprobe/__x64_sys_getpgid") +SEC("kprobe/" SYS_PREFIX "sys_getpgid") int bench_trigger_kprobe(void *ctx) { __sync_add_and_fetch(&hits, 1); return 0; } -SEC("fentry/__x64_sys_getpgid") +SEC("fentry/" SYS_PREFIX "sys_getpgid") int bench_trigger_fentry(void *ctx) { __sync_add_and_fetch(&hits, 1); return 0; } -SEC("fentry.s/__x64_sys_getpgid") +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") int bench_trigger_fentry_sleep(void *ctx) { __sync_add_and_fetch(&hits, 1); return 0; } -SEC("fmod_ret/__x64_sys_getpgid") +SEC("fmod_ret/" SYS_PREFIX "sys_getpgid") int bench_trigger_fmodret(void *ctx) { __sync_add_and_fetch(&hits, 1); diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c index 8395782b6e0a..97b26a30b59a 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c @@ -70,7 +70,7 @@ int xdp_redirect_map_all_prog(struct xdp_md *ctx) BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); } -SEC("xdp_devmap/map_prog") +SEC("xdp/devmap") int xdp_devmap_prog(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index 5b8314cd77fd..d6a1be4d8020 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -36,7 +36,7 @@ int main(int argc, char **argv) BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }; - size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + size_t insns_cnt = ARRAY_SIZE(prog); int error = EXIT_FAILURE; int map_fd, percpu_map_fd, prog_fd, cgroup_fd; struct bpf_cgroup_storage_key key; diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp index e00201de2890..19ad172036da 100644 --- a/tools/testing/selftests/bpf/test_cpp.cpp +++ b/tools/testing/selftests/bpf/test_cpp.cpp @@ -1,22 +1,107 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ #include <iostream> +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" #include <bpf/libbpf.h> +#pragma GCC diagnostic pop #include <bpf/bpf.h> #include <bpf/btf.h> #include "test_core_extern.skel.h" -/* do nothing, just make sure we can link successfully */ +template <typename T> +class Skeleton { +private: + T *skel; +public: + Skeleton(): skel(nullptr) { } + + ~Skeleton() { if (skel) T::destroy(skel); } + + int open(const struct bpf_object_open_opts *opts = nullptr) + { + int err; + + if (skel) + return -EBUSY; + + skel = T::open(opts); + err = libbpf_get_error(skel); + if (err) { + skel = nullptr; + return err; + } + + return 0; + } + + int load() { return T::load(skel); } + + int attach() { return T::attach(skel); } + + void detach() { return T::detach(skel); } + + const T* operator->() const { return skel; } + + T* operator->() { return skel; } + + const T *get() const { return skel; } +}; static void dump_printf(void *ctx, const char *fmt, va_list args) { } +static void try_skeleton_template() +{ + Skeleton<test_core_extern> skel; + std::string prog_name; + int err; + LIBBPF_OPTS(bpf_object_open_opts, opts); + + err = skel.open(&opts); + if (err) { + fprintf(stderr, "Skeleton open failed: %d\n", err); + return; + } + + skel->data->kern_ver = 123; + skel->data->int_val = skel->data->ushort_val; + + err = skel.load(); + if (err) { + fprintf(stderr, "Skeleton load failed: %d\n", err); + return; + } + + if (!skel->kconfig->CONFIG_BPF_SYSCALL) + fprintf(stderr, "Seems like CONFIG_BPF_SYSCALL isn't set?!\n"); + + err = skel.attach(); + if (err) { + fprintf(stderr, "Skeleton attach failed: %d\n", err); + return; + } + + prog_name = bpf_program__name(skel->progs.handle_sys_enter); + if (prog_name != "handle_sys_enter") + fprintf(stderr, "Unexpected program name: %s\n", prog_name.c_str()); + + bpf_link__destroy(skel->links.handle_sys_enter); + skel->links.handle_sys_enter = bpf_program__attach(skel->progs.handle_sys_enter); + + skel.detach(); + + /* destructor will destory underlying skeleton */ +} + int main(int argc, char *argv[]) { struct btf_dump_opts opts = { }; struct test_core_extern *skel; struct btf *btf; + try_skeleton_template(); + /* libbpf.h */ libbpf_set_print(NULL); @@ -25,7 +110,8 @@ int main(int argc, char *argv[]) /* btf.h */ btf = btf__new(NULL, 0); - btf_dump__new(btf, dump_printf, nullptr, &opts); + if (!libbpf_get_error(btf)) + btf_dump__new(btf, dump_printf, nullptr, &opts); /* BPF skeleton */ skel = test_core_extern__open_and_load(); diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh index ec4e15948e40..5252b91f48a1 100755 --- a/tools/testing/selftests/bpf/test_lirc_mode2.sh +++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh @@ -3,6 +3,7 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +ret=$ksft_skip msg="skip all tests:" if [ $UID != 0 ]; then @@ -25,7 +26,7 @@ do fi done -if [ -n $LIRCDEV ]; +if [ -n "$LIRCDEV" ]; then TYPE=lirc_mode2 ./test_lirc_mode2_user $LIRCDEV $INPUTDEV @@ -36,3 +37,5 @@ then echo -e ${GREEN}"PASS: $TYPE"${NC} fi fi + +exit $ret diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index b9f1bbbc8aba..563bbe18c172 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -61,7 +61,11 @@ static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, }; __u8 data[64] = {}; int mfd, pfd, ret, zero = 0; - __u32 retval = 0; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = data, + .data_size_in = sizeof(data), + .repeat = 1, + ); mfd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), sizeof(__u64), 1, NULL); if (mfd < 0) @@ -75,9 +79,8 @@ static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, return -1; } - ret = bpf_prog_test_run(pfd, 1, data, sizeof(data), - NULL, NULL, &retval, NULL); - if (ret < 0 || retval != 42) { + ret = bpf_prog_test_run_opts(pfd, &topts); + if (ret < 0 || topts.retval != 42) { ret = -1; } else { assert(!bpf_map_lookup_elem(mfd, &zero, value)); @@ -875,11 +878,11 @@ int main(int argc, char **argv) assert(nr_cpus != -1); printf("nr_cpus:%d\n\n", nr_cpus); - for (f = 0; f < sizeof(map_flags) / sizeof(*map_flags); f++) { + for (f = 0; f < ARRAY_SIZE(map_flags); f++) { unsigned int tgt_free = (map_flags[f] & BPF_F_NO_COMMON_LRU) ? PERCPU_FREE_TARGET : LOCAL_FREE_TARGET; - for (t = 0; t < sizeof(map_types) / sizeof(*map_types); t++) { + for (t = 0; t < ARRAY_SIZE(map_types); t++) { test_lru_sanity0(map_types[t], map_flags[f]); test_lru_sanity1(map_types[t], map_flags[f], tgt_free); test_lru_sanity2(map_types[t], map_flags[f], tgt_free); diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh index b497bb85b667..6c69c42b1d60 100755 --- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -120,6 +120,14 @@ setup() ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0 ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0 + # disable IPv6 DAD because it sometimes takes too long and fails tests + ip netns exec ${NS1} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${NS3} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${NS1} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip netns exec ${NS2} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip netns exec ${NS3} sysctl -wq net.ipv6.conf.default.accept_dad=0 + ip link add veth1 type veth peer name veth2 ip link add veth3 type veth peer name veth4 ip link add veth5 type veth peer name veth6 @@ -289,7 +297,7 @@ test_ping() ip netns exec ${NS1} ping -c 1 -W 1 -I veth1 ${IPv4_DST} 2>&1 > /dev/null RET=$? elif [ "${PROTO}" == "IPv6" ] ; then - ip netns exec ${NS1} ping6 -c 1 -W 6 -I veth1 ${IPv6_DST} 2>&1 > /dev/null + ip netns exec ${NS1} ping6 -c 1 -W 1 -I veth1 ${IPv6_DST} 2>&1 > /dev/null RET=$? else echo " test_ping: unknown PROTO: ${PROTO}" diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh index 5620919fde9e..826f4423ce02 100755 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -23,6 +23,12 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" +readonly NS3="ns3-$(mktemp -u XXXXXX)" +readonly NS4="ns4-$(mktemp -u XXXXXX)" +readonly NS5="ns5-$(mktemp -u XXXXXX)" +readonly NS6="ns6-$(mktemp -u XXXXXX)" msg="skip all tests:" if [ $UID != 0 ]; then @@ -41,23 +47,23 @@ cleanup() fi set +e - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null - ip netns del ns3 2> /dev/null - ip netns del ns4 2> /dev/null - ip netns del ns5 2> /dev/null - ip netns del ns6 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null + ip netns del ${NS3} 2> /dev/null + ip netns del ${NS4} 2> /dev/null + ip netns del ${NS5} 2> /dev/null + ip netns del ${NS6} 2> /dev/null rm -f $TMP_FILE } set -e -ip netns add ns1 -ip netns add ns2 -ip netns add ns3 -ip netns add ns4 -ip netns add ns5 -ip netns add ns6 +ip netns add ${NS1} +ip netns add ${NS2} +ip netns add ${NS3} +ip netns add ${NS4} +ip netns add ${NS5} +ip netns add ${NS6} trap cleanup 0 2 3 6 9 @@ -67,78 +73,78 @@ ip link add veth5 type veth peer name veth6 ip link add veth7 type veth peer name veth8 ip link add veth9 type veth peer name veth10 -ip link set veth1 netns ns1 -ip link set veth2 netns ns2 -ip link set veth3 netns ns2 -ip link set veth4 netns ns3 -ip link set veth5 netns ns3 -ip link set veth6 netns ns4 -ip link set veth7 netns ns4 -ip link set veth8 netns ns5 -ip link set veth9 netns ns5 -ip link set veth10 netns ns6 - -ip netns exec ns1 ip link set dev veth1 up -ip netns exec ns2 ip link set dev veth2 up -ip netns exec ns2 ip link set dev veth3 up -ip netns exec ns3 ip link set dev veth4 up -ip netns exec ns3 ip link set dev veth5 up -ip netns exec ns4 ip link set dev veth6 up -ip netns exec ns4 ip link set dev veth7 up -ip netns exec ns5 ip link set dev veth8 up -ip netns exec ns5 ip link set dev veth9 up -ip netns exec ns6 ip link set dev veth10 up -ip netns exec ns6 ip link set dev lo up +ip link set veth1 netns ${NS1} +ip link set veth2 netns ${NS2} +ip link set veth3 netns ${NS2} +ip link set veth4 netns ${NS3} +ip link set veth5 netns ${NS3} +ip link set veth6 netns ${NS4} +ip link set veth7 netns ${NS4} +ip link set veth8 netns ${NS5} +ip link set veth9 netns ${NS5} +ip link set veth10 netns ${NS6} + +ip netns exec ${NS1} ip link set dev veth1 up +ip netns exec ${NS2} ip link set dev veth2 up +ip netns exec ${NS2} ip link set dev veth3 up +ip netns exec ${NS3} ip link set dev veth4 up +ip netns exec ${NS3} ip link set dev veth5 up +ip netns exec ${NS4} ip link set dev veth6 up +ip netns exec ${NS4} ip link set dev veth7 up +ip netns exec ${NS5} ip link set dev veth8 up +ip netns exec ${NS5} ip link set dev veth9 up +ip netns exec ${NS6} ip link set dev veth10 up +ip netns exec ${NS6} ip link set dev lo up # All link scope addresses and routes required between veths -ip netns exec ns1 ip -6 addr add fb00::12/16 dev veth1 scope link -ip netns exec ns1 ip -6 route add fb00::21 dev veth1 scope link -ip netns exec ns2 ip -6 addr add fb00::21/16 dev veth2 scope link -ip netns exec ns2 ip -6 addr add fb00::34/16 dev veth3 scope link -ip netns exec ns2 ip -6 route add fb00::43 dev veth3 scope link -ip netns exec ns3 ip -6 route add fb00::65 dev veth5 scope link -ip netns exec ns3 ip -6 addr add fb00::43/16 dev veth4 scope link -ip netns exec ns3 ip -6 addr add fb00::56/16 dev veth5 scope link -ip netns exec ns4 ip -6 addr add fb00::65/16 dev veth6 scope link -ip netns exec ns4 ip -6 addr add fb00::78/16 dev veth7 scope link -ip netns exec ns4 ip -6 route add fb00::87 dev veth7 scope link -ip netns exec ns5 ip -6 addr add fb00::87/16 dev veth8 scope link -ip netns exec ns5 ip -6 addr add fb00::910/16 dev veth9 scope link -ip netns exec ns5 ip -6 route add fb00::109 dev veth9 scope link -ip netns exec ns5 ip -6 route add fb00::109 table 117 dev veth9 scope link -ip netns exec ns6 ip -6 addr add fb00::109/16 dev veth10 scope link - -ip netns exec ns1 ip -6 addr add fb00::1/16 dev lo -ip netns exec ns1 ip -6 route add fb00::6 dev veth1 via fb00::21 - -ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2 -ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link - -ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65 -ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4 - -ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6 -ip netns exec ns4 ip -6 addr add fc42::1 dev lo -ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87 - -ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 -ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8 - -ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo -ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo - -ip netns exec ns1 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns2 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns3 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns4 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null -ip netns exec ns5 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null - -ip netns exec ns6 sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null -ip netns exec ns6 sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null -ip netns exec ns6 sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null - -ip netns exec ns6 nc -l -6 -u -d 7330 > $TMP_FILE & -ip netns exec ns1 bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" +ip netns exec ${NS1} ip -6 addr add fb00::12/16 dev veth1 scope link +ip netns exec ${NS1} ip -6 route add fb00::21 dev veth1 scope link +ip netns exec ${NS2} ip -6 addr add fb00::21/16 dev veth2 scope link +ip netns exec ${NS2} ip -6 addr add fb00::34/16 dev veth3 scope link +ip netns exec ${NS2} ip -6 route add fb00::43 dev veth3 scope link +ip netns exec ${NS3} ip -6 route add fb00::65 dev veth5 scope link +ip netns exec ${NS3} ip -6 addr add fb00::43/16 dev veth4 scope link +ip netns exec ${NS3} ip -6 addr add fb00::56/16 dev veth5 scope link +ip netns exec ${NS4} ip -6 addr add fb00::65/16 dev veth6 scope link +ip netns exec ${NS4} ip -6 addr add fb00::78/16 dev veth7 scope link +ip netns exec ${NS4} ip -6 route add fb00::87 dev veth7 scope link +ip netns exec ${NS5} ip -6 addr add fb00::87/16 dev veth8 scope link +ip netns exec ${NS5} ip -6 addr add fb00::910/16 dev veth9 scope link +ip netns exec ${NS5} ip -6 route add fb00::109 dev veth9 scope link +ip netns exec ${NS5} ip -6 route add fb00::109 table 117 dev veth9 scope link +ip netns exec ${NS6} ip -6 addr add fb00::109/16 dev veth10 scope link + +ip netns exec ${NS1} ip -6 addr add fb00::1/16 dev lo +ip netns exec ${NS1} ip -6 route add fb00::6 dev veth1 via fb00::21 + +ip netns exec ${NS2} ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2 +ip netns exec ${NS2} ip -6 route add fd00::1 dev veth3 via fb00::43 scope link + +ip netns exec ${NS3} ip -6 route add fc42::1 dev veth5 via fb00::65 +ip netns exec ${NS3} ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4 + +ip netns exec ${NS4} ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6 +ip netns exec ${NS4} ip -6 addr add fc42::1 dev lo +ip netns exec ${NS4} ip -6 route add fd00::3 dev veth7 via fb00::87 + +ip netns exec ${NS5} ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 +ip netns exec ${NS5} ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8 + +ip netns exec ${NS6} ip -6 addr add fb00::6/16 dev lo +ip netns exec ${NS6} ip -6 addr add fd00::4/16 dev lo + +ip netns exec ${NS1} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS2} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS3} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS4} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec ${NS5} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + +ip netns exec ${NS6} sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null +ip netns exec ${NS6} sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null +ip netns exec ${NS6} sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null + +ip netns exec ${NS6} nc -l -6 -u -d 7330 > $TMP_FILE & +ip netns exec ${NS1} bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330" sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment kill -TERM $! diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 50f7e74ca0b9..cbebfaa7c1e8 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -738,7 +738,7 @@ static void test_sockmap(unsigned int tasks, void *data) sizeof(key), sizeof(value), 6, NULL); if (fd < 0) { - if (!bpf_probe_map_type(BPF_MAP_TYPE_SOCKMAP, 0)) { + if (!libbpf_probe_bpf_map_type(BPF_MAP_TYPE_SOCKMAP, NULL)) { printf("%s SKIP (unsupported map type BPF_MAP_TYPE_SOCKMAP)\n", __func__); skips++; diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index f0c8d05ba6d1..f3d5d7ac6505 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -723,7 +723,7 @@ static int xmsg_ret_only_prog_load(const struct sock_addr_test *test, BPF_MOV64_IMM(BPF_REG_0, rc), BPF_EXIT_INSN(), }; - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); + return load_insns(test, insns, ARRAY_SIZE(insns)); } static int sendmsg_allow_prog_load(const struct sock_addr_test *test) @@ -795,7 +795,7 @@ static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test) BPF_EXIT_INSN(), }; - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); + return load_insns(test, insns, ARRAY_SIZE(insns)); } static int recvmsg4_rw_c_prog_load(const struct sock_addr_test *test) @@ -858,7 +858,7 @@ static int sendmsg6_rw_dst_asm_prog_load(const struct sock_addr_test *test, BPF_EXIT_INSN(), }; - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); + return load_insns(test, insns, ARRAY_SIZE(insns)); } static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 1ba7e7346afb..dfb4f5c0fcb9 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1786,7 +1786,7 @@ static int populate_progs(char *bpf_file) i++; } - for (i = 0; i < sizeof(map_fd)/sizeof(int); i++) { + for (i = 0; i < ARRAY_SIZE(map_fd); i++) { maps[i] = bpf_object__find_map_by_name(obj, map_names[i]); map_fd[i] = bpf_map__fd(maps[i]); if (map_fd[i] < 0) { @@ -1867,7 +1867,7 @@ static int __test_selftests(int cg_fd, struct sockmap_options *opt) } /* Tests basic commands and APIs */ - for (i = 0; i < sizeof(test)/sizeof(struct _test); i++) { + for (i = 0; i < ARRAY_SIZE(test); i++) { struct _test t = test[i]; if (check_whitelist(&t, opt) != 0) diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index 6413c1472554..102e6588e2fe 100755 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -4,6 +4,7 @@ # Copyright (c) 2019 Cloudflare set -eu +readonly NS1="ns1-$(mktemp -u XXXXXX)" wait_for_ip() { @@ -28,12 +29,12 @@ get_prog_id() ns1_exec() { - ip netns exec ns1 "$@" + ip netns exec ${NS1} "$@" } setup() { - ip netns add ns1 + ip netns add ${NS1} ns1_exec ip link set lo up ns1_exec sysctl -w net.ipv4.tcp_syncookies=2 diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index ca1372924023..2817d9948d59 100755 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -39,7 +39,7 @@ # from root namespace, the following operations happen: # 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev. # 2) Tnl device's egress BPF program is triggered and set the tunnel metadata, -# with remote_ip=172.16.1.200 and others. +# with remote_ip=172.16.1.100 and others. # 3) Outer tunnel header is prepended and route the packet to veth1's egress # 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0 # 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 76cd903117af..a2cd236c32eb 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -22,8 +22,6 @@ #include <limits.h> #include <assert.h> -#include <sys/capability.h> - #include <linux/unistd.h> #include <linux/filter.h> #include <linux/bpf_perf_event.h> @@ -31,6 +29,7 @@ #include <linux/if_ether.h> #include <linux/btf.h> +#include <bpf/btf.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -41,6 +40,7 @@ # define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1 # endif #endif +#include "cap_helpers.h" #include "bpf_rand.h" #include "bpf_util.h" #include "test_btf.h" @@ -61,11 +61,20 @@ #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0) #define F_LOAD_WITH_STRICT_ALIGNMENT (1 << 1) +/* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */ +#define ADMIN_CAPS (1ULL << CAP_NET_ADMIN | \ + 1ULL << CAP_PERFMON | \ + 1ULL << CAP_BPF) #define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled" static bool unpriv_disabled = false; static int skips; static bool verbose = false; +struct kfunc_btf_id_pair { + const char *kfunc; + int insn_idx; +}; + struct bpf_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; @@ -92,6 +101,7 @@ struct bpf_test { int fixup_map_reuseport_array[MAX_FIXUPS]; int fixup_map_ringbuf[MAX_FIXUPS]; int fixup_map_timer[MAX_FIXUPS]; + struct kfunc_btf_id_pair fixup_kfunc_btf_id[MAX_FIXUPS]; /* Expected verifier log output for result REJECT or VERBOSE_ACCEPT. * Can be a tab-separated sequence of expected strings. An empty string * means no log verification. @@ -449,7 +459,7 @@ static int probe_filter_length(const struct bpf_insn *fp) static bool skip_unsupported_map(enum bpf_map_type map_type) { - if (!bpf_probe_map_type(map_type, 0)) { + if (!libbpf_probe_bpf_map_type(map_type, NULL)) { printf("SKIP (unsupported map type %d)\n", map_type); skips++; return true; @@ -744,6 +754,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; int *fixup_map_ringbuf = test->fixup_map_ringbuf; int *fixup_map_timer = test->fixup_map_timer; + struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -936,6 +947,26 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_timer++; } while (*fixup_map_timer); } + + /* Patch in kfunc BTF IDs */ + if (fixup_kfunc_btf_id->kfunc) { + struct btf *btf; + int btf_id; + + do { + btf_id = 0; + btf = btf__load_vmlinux_btf(); + if (btf) { + btf_id = btf__find_by_name_kind(btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + } + btf__free(btf); + prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; + fixup_kfunc_btf_id++; + } while (fixup_kfunc_btf_id->kfunc); + } } struct libcap { @@ -945,47 +976,19 @@ struct libcap { static int set_admin(bool admin) { - cap_t caps; - /* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */ - const cap_value_t cap_net_admin = CAP_NET_ADMIN; - const cap_value_t cap_sys_admin = CAP_SYS_ADMIN; - struct libcap *cap; - int ret = -1; - - caps = cap_get_proc(); - if (!caps) { - perror("cap_get_proc"); - return -1; - } - cap = (struct libcap *)caps; - if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_sys_admin, CAP_CLEAR)) { - perror("cap_set_flag clear admin"); - goto out; - } - if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_net_admin, - admin ? CAP_SET : CAP_CLEAR)) { - perror("cap_set_flag set_or_clear net"); - goto out; - } - /* libcap is likely old and simply ignores CAP_BPF and CAP_PERFMON, - * so update effective bits manually - */ + int err; + if (admin) { - cap->data[1].effective |= 1 << (38 /* CAP_PERFMON */ - 32); - cap->data[1].effective |= 1 << (39 /* CAP_BPF */ - 32); + err = cap_enable_effective(ADMIN_CAPS, NULL); + if (err) + perror("cap_enable_effective(ADMIN_CAPS)"); } else { - cap->data[1].effective &= ~(1 << (38 - 32)); - cap->data[1].effective &= ~(1 << (39 - 32)); + err = cap_disable_effective(ADMIN_CAPS, NULL); + if (err) + perror("cap_disable_effective(ADMIN_CAPS)"); } - if (cap_set_proc(caps)) { - perror("cap_set_proc"); - goto out; - } - ret = 0; -out: - if (cap_free(caps)) - perror("cap_free"); - return ret; + + return err; } static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, @@ -993,13 +996,18 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, { __u8 tmp[TEST_DATA_LEN << 2]; __u32 size_tmp = sizeof(tmp); - uint32_t retval; int err, saved_errno; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = data, + .data_size_in = size_data, + .data_out = tmp, + .data_size_out = size_tmp, + .repeat = 1, + ); if (unpriv) set_admin(true); - err = bpf_prog_test_run(fd_prog, 1, data, size_data, - tmp, &size_tmp, &retval, NULL); + err = bpf_prog_test_run_opts(fd_prog, &topts); saved_errno = errno; if (unpriv) @@ -1023,9 +1031,8 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val, } } - if (retval != expected_val && - expected_val != POINTER_VALUE) { - printf("FAIL retval %d != %d ", retval, expected_val); + if (topts.retval != expected_val && expected_val != POINTER_VALUE) { + printf("FAIL retval %d != %d ", topts.retval, expected_val); return 1; } @@ -1148,7 +1155,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, * bpf_probe_prog_type won't give correct answer */ if (fd_prog < 0 && prog_type != BPF_PROG_TYPE_TRACING && - !bpf_probe_prog_type(prog_type, 0)) { + !libbpf_probe_bpf_prog_type(prog_type, NULL)) { printf("SKIP (unsupported program type %d)\n", prog_type); skips++; goto close_fds; @@ -1259,31 +1266,18 @@ fail_log: static bool is_admin(void) { - cap_flag_value_t net_priv = CAP_CLEAR; - bool perfmon_priv = false; - bool bpf_priv = false; - struct libcap *cap; - cap_t caps; - -#ifdef CAP_IS_SUPPORTED - if (!CAP_IS_SUPPORTED(CAP_SETFCAP)) { - perror("cap_get_flag"); - return false; - } -#endif - caps = cap_get_proc(); - if (!caps) { - perror("cap_get_proc"); + __u64 caps; + + /* The test checks for finer cap as CAP_NET_ADMIN, + * CAP_PERFMON, and CAP_BPF instead of CAP_SYS_ADMIN. + * Thus, disable CAP_SYS_ADMIN at the beginning. + */ + if (cap_disable_effective(1ULL << CAP_SYS_ADMIN, &caps)) { + perror("cap_disable_effective(CAP_SYS_ADMIN)"); return false; } - cap = (struct libcap *)caps; - bpf_priv = cap->data[1].effective & (1 << (39/* CAP_BPF */ - 32)); - perfmon_priv = cap->data[1].effective & (1 << (38/* CAP_PERFMON */ - 32)); - if (cap_get_flag(caps, CAP_NET_ADMIN, CAP_EFFECTIVE, &net_priv)) - perror("cap_get_flag NET"); - if (cap_free(caps)) - perror("cap_free"); - return bpf_priv && perfmon_priv && net_priv == CAP_SET; + + return (caps & ADMIN_CAPS) == ADMIN_CAPS; } static void get_unpriv_disabled() diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh index d10cefd6eb09..ea69370caae3 100755 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -2,6 +2,8 @@ # Kselftest framework requirement - SKIP code is 4. readonly KSFT_SKIP=4 +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" cleanup() { @@ -13,8 +15,8 @@ cleanup() set +e ip link del veth1 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null } ip link set dev lo xdp off 2>/dev/null > /dev/null @@ -24,32 +26,32 @@ if [ $? -ne 0 ];then fi set -e -ip netns add ns1 -ip netns add ns2 +ip netns add ${NS1} +ip netns add ${NS2} trap cleanup 0 2 3 6 9 ip link add veth1 type veth peer name veth2 -ip link set veth1 netns ns1 -ip link set veth2 netns ns2 +ip link set veth1 netns ${NS1} +ip link set veth2 netns ${NS2} -ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth1 -ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth2 +ip netns exec ${NS1} ip addr add 10.1.1.11/24 dev veth1 +ip netns exec ${NS2} ip addr add 10.1.1.22/24 dev veth2 -ip netns exec ns1 tc qdisc add dev veth1 clsact -ip netns exec ns2 tc qdisc add dev veth2 clsact +ip netns exec ${NS1} tc qdisc add dev veth1 clsact +ip netns exec ${NS2} tc qdisc add dev veth2 clsact -ip netns exec ns1 tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t -ip netns exec ns2 tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t +ip netns exec ${NS1} tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t +ip netns exec ${NS2} tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t -ip netns exec ns1 ip link set dev veth1 xdp obj test_xdp_meta.o sec x -ip netns exec ns2 ip link set dev veth2 xdp obj test_xdp_meta.o sec x +ip netns exec ${NS1} ip link set dev veth1 xdp obj test_xdp_meta.o sec x +ip netns exec ${NS2} ip link set dev veth2 xdp obj test_xdp_meta.o sec x -ip netns exec ns1 ip link set dev veth1 up -ip netns exec ns2 ip link set dev veth2 up +ip netns exec ${NS1} ip link set dev veth1 up +ip netns exec ${NS2} ip link set dev veth2 up -ip netns exec ns1 ping -c 1 10.1.1.22 -ip netns exec ns2 ping -c 1 10.1.1.11 +ip netns exec ${NS1} ping -c 1 10.1.1.22 +ip netns exec ${NS2} ping -c 1 10.1.1.11 exit 0 diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh index 57c8db9972a6..1d79f31480ad 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -10,6 +10,8 @@ # | xdp forwarding | # ------------------ +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" ret=0 setup() @@ -17,27 +19,27 @@ setup() local xdpmode=$1 - ip netns add ns1 - ip netns add ns2 + ip netns add ${NS1} + ip netns add ${NS2} - ip link add veth1 index 111 type veth peer name veth11 netns ns1 - ip link add veth2 index 222 type veth peer name veth22 netns ns2 + ip link add veth1 index 111 type veth peer name veth11 netns ${NS1} + ip link add veth2 index 222 type veth peer name veth22 netns ${NS2} ip link set veth1 up ip link set veth2 up - ip -n ns1 link set dev veth11 up - ip -n ns2 link set dev veth22 up + ip -n ${NS1} link set dev veth11 up + ip -n ${NS2} link set dev veth22 up - ip -n ns1 addr add 10.1.1.11/24 dev veth11 - ip -n ns2 addr add 10.1.1.22/24 dev veth22 + ip -n ${NS1} addr add 10.1.1.11/24 dev veth11 + ip -n ${NS2} addr add 10.1.1.22/24 dev veth22 } cleanup() { ip link del veth1 2> /dev/null ip link del veth2 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null } test_xdp_redirect() @@ -52,13 +54,13 @@ test_xdp_redirect() return 0 fi - ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null - ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null + ip -n ${NS1} link set veth11 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null + ip -n ${NS2} link set veth22 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null ip link set dev veth1 $xdpmode obj test_xdp_redirect.o sec redirect_to_222 &> /dev/null ip link set dev veth2 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null - if ip netns exec ns1 ping -c 1 10.1.1.22 &> /dev/null && - ip netns exec ns2 ping -c 1 10.1.1.11 &> /dev/null; then + if ip netns exec ${NS1} ping -c 1 10.1.1.22 &> /dev/null && + ip netns exec ${NS2} ping -c 1 10.1.1.11 &> /dev/null; then echo "selftests: test_xdp_redirect $xdpmode [PASS]"; else ret=1 diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh index 05f872740999..cc57cb87e65f 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh @@ -32,6 +32,11 @@ DRV_MODE="xdpgeneric xdpdrv xdpegress" PASS=0 FAIL=0 LOG_DIR=$(mktemp -d) +declare -a NS +NS[0]="ns0-$(mktemp -u XXXXXX)" +NS[1]="ns1-$(mktemp -u XXXXXX)" +NS[2]="ns2-$(mktemp -u XXXXXX)" +NS[3]="ns3-$(mktemp -u XXXXXX)" test_pass() { @@ -47,11 +52,9 @@ test_fail() clean_up() { - for i in $(seq $NUM); do - ip link del veth$i 2> /dev/null - ip netns del ns$i 2> /dev/null + for i in $(seq 0 $NUM); do + ip netns del ${NS[$i]} 2> /dev/null done - ip netns del ns0 2> /dev/null } # Kselftest framework requirement - SKIP code is 4. @@ -79,23 +82,22 @@ setup_ns() mode="xdpdrv" fi - ip netns add ns0 + ip netns add ${NS[0]} for i in $(seq $NUM); do - ip netns add ns$i - ip -n ns$i link add veth0 index 2 type veth \ - peer name veth$i netns ns0 index $((1 + $i)) - ip -n ns0 link set veth$i up - ip -n ns$i link set veth0 up - - ip -n ns$i addr add 192.0.2.$i/24 dev veth0 - ip -n ns$i addr add 2001:db8::$i/64 dev veth0 + ip netns add ${NS[$i]} + ip -n ${NS[$i]} link add veth0 type veth peer name veth$i netns ${NS[0]} + ip -n ${NS[$i]} link set veth0 up + ip -n ${NS[0]} link set veth$i up + + ip -n ${NS[$i]} addr add 192.0.2.$i/24 dev veth0 + ip -n ${NS[$i]} addr add 2001:db8::$i/64 dev veth0 # Add a neigh entry for IPv4 ping test - ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 - ip -n ns$i link set veth0 $mode obj \ + ip -n ${NS[$i]} neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 + ip -n ${NS[$i]} link set veth0 $mode obj \ xdp_dummy.o sec xdp &> /dev/null || \ { test_fail "Unable to load dummy xdp" && exit 1; } IFACES="$IFACES veth$i" - veth_mac[$i]=$(ip -n ns0 link show veth$i | awk '/link\/ether/ {print $2}') + veth_mac[$i]=$(ip -n ${NS[0]} link show veth$i | awk '/link\/ether/ {print $2}') done } @@ -104,10 +106,10 @@ do_egress_tests() local mode=$1 # mac test - ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log & - ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log & + ip netns exec ${NS[2]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log & + ip netns exec ${NS[3]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log & sleep 0.5 - ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null + ip netns exec ${NS[1]} ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null sleep 0.5 pkill tcpdump @@ -123,18 +125,18 @@ do_ping_tests() local mode=$1 # ping6 test: echo request should be redirect back to itself, not others - ip netns exec ns1 ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02 + ip netns exec ${NS[1]} ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02 - ip netns exec ns1 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log & - ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log & - ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log & + ip netns exec ${NS[1]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log & + ip netns exec ${NS[2]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log & + ip netns exec ${NS[3]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log & sleep 0.5 # ARP test - ip netns exec ns1 arping -q -c 2 -I veth0 192.0.2.254 + ip netns exec ${NS[1]} arping -q -c 2 -I veth0 192.0.2.254 # IPv4 test - ip netns exec ns1 ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null + ip netns exec ${NS[1]} ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null # IPv6 test - ip netns exec ns1 ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null + ip netns exec ${NS[1]} ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null sleep 0.5 pkill tcpdump @@ -180,7 +182,7 @@ do_tests() xdpgeneric) drv_p="-S";; esac - ip netns exec ns0 ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log & + ip netns exec ${NS[0]} ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log & xdp_pid=$! sleep 1 if ! ps -p $xdp_pid > /dev/null; then @@ -197,10 +199,10 @@ do_tests() kill $xdp_pid } -trap clean_up EXIT - check_env +trap clean_up EXIT + for mode in ${DRV_MODE}; do setup_ns $mode do_tests $mode diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh index a3a1eaee26ea..392d28cc4e58 100755 --- a/tools/testing/selftests/bpf/test_xdp_veth.sh +++ b/tools/testing/selftests/bpf/test_xdp_veth.sh @@ -22,6 +22,9 @@ ksft_skip=4 TESTNAME=xdp_veth BPF_FS=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts) BPF_DIR=$BPF_FS/test_$TESTNAME +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" +readonly NS3="ns3-$(mktemp -u XXXXXX)" _cleanup() { @@ -29,9 +32,9 @@ _cleanup() ip link del veth1 2> /dev/null ip link del veth2 2> /dev/null ip link del veth3 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null - ip netns del ns3 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null + ip netns del ${NS3} 2> /dev/null rm -rf $BPF_DIR 2> /dev/null } @@ -77,24 +80,24 @@ set -e trap cleanup_skip EXIT -ip netns add ns1 -ip netns add ns2 -ip netns add ns3 +ip netns add ${NS1} +ip netns add ${NS2} +ip netns add ${NS3} -ip link add veth1 index 111 type veth peer name veth11 netns ns1 -ip link add veth2 index 122 type veth peer name veth22 netns ns2 -ip link add veth3 index 133 type veth peer name veth33 netns ns3 +ip link add veth1 index 111 type veth peer name veth11 netns ${NS1} +ip link add veth2 index 122 type veth peer name veth22 netns ${NS2} +ip link add veth3 index 133 type veth peer name veth33 netns ${NS3} ip link set veth1 up ip link set veth2 up ip link set veth3 up -ip -n ns1 addr add 10.1.1.11/24 dev veth11 -ip -n ns3 addr add 10.1.1.33/24 dev veth33 +ip -n ${NS1} addr add 10.1.1.11/24 dev veth11 +ip -n ${NS3} addr add 10.1.1.33/24 dev veth33 -ip -n ns1 link set dev veth11 up -ip -n ns2 link set dev veth22 up -ip -n ns3 link set dev veth33 up +ip -n ${NS1} link set dev veth11 up +ip -n ${NS2} link set dev veth22 up +ip -n ${NS3} link set dev veth33 up mkdir $BPF_DIR bpftool prog loadall \ @@ -107,12 +110,12 @@ ip link set dev veth1 xdp pinned $BPF_DIR/progs/redirect_map_0 ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1 ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2 -ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp -ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp -ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp +ip -n ${NS1} link set dev veth11 xdp obj xdp_dummy.o sec xdp +ip -n ${NS2} link set dev veth22 xdp obj xdp_tx.o sec xdp +ip -n ${NS3} link set dev veth33 xdp obj xdp_dummy.o sec xdp trap cleanup EXIT -ip netns exec ns1 ping -c 1 -W 1 10.1.1.33 +ip netns exec ${NS1} ping -c 1 -W 1 10.1.1.33 exit 0 diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index 0cbc7604a2f8..810c407e0286 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -4,6 +4,8 @@ # Kselftest framework requirement - SKIP code is 4. readonly KSFT_SKIP=4 +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" # Allow wrapper scripts to name test if [ -z "$TESTNAME" ]; then @@ -49,15 +51,15 @@ cleanup() if [ -n "$INTERACTIVE" ]; then echo "Namespace setup still active explore with:" - echo " ip netns exec ns1 bash" - echo " ip netns exec ns2 bash" + echo " ip netns exec ${NS1} bash" + echo " ip netns exec ${NS2} bash" exit $status fi set +e ip link del veth1 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null } # Using external program "getopt" to get --long-options @@ -126,8 +128,8 @@ fi # Interactive mode likely require us to cleanup netns if [ -n "$INTERACTIVE" ]; then ip link del veth1 2> /dev/null - ip netns del ns1 2> /dev/null - ip netns del ns2 2> /dev/null + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null fi # Exit on failure @@ -144,8 +146,8 @@ if [ -n "$VERBOSE" ]; then fi # Create two namespaces -ip netns add ns1 -ip netns add ns2 +ip netns add ${NS1} +ip netns add ${NS2} # Run cleanup if failing or on kill trap cleanup 0 2 3 6 9 @@ -154,44 +156,44 @@ trap cleanup 0 2 3 6 9 ip link add veth1 type veth peer name veth2 # Move veth1 and veth2 into the respective namespaces -ip link set veth1 netns ns1 -ip link set veth2 netns ns2 +ip link set veth1 netns ${NS1} +ip link set veth2 netns ${NS2} # NOTICE: XDP require VLAN header inside packet payload # - Thus, disable VLAN offloading driver features # - For veth REMEMBER TX side VLAN-offload # # Disable rx-vlan-offload (mostly needed on ns1) -ip netns exec ns1 ethtool -K veth1 rxvlan off -ip netns exec ns2 ethtool -K veth2 rxvlan off +ip netns exec ${NS1} ethtool -K veth1 rxvlan off +ip netns exec ${NS2} ethtool -K veth2 rxvlan off # # Disable tx-vlan-offload (mostly needed on ns2) -ip netns exec ns2 ethtool -K veth2 txvlan off -ip netns exec ns1 ethtool -K veth1 txvlan off +ip netns exec ${NS2} ethtool -K veth2 txvlan off +ip netns exec ${NS1} ethtool -K veth1 txvlan off export IPADDR1=100.64.41.1 export IPADDR2=100.64.41.2 # In ns1/veth1 add IP-addr on plain net_device -ip netns exec ns1 ip addr add ${IPADDR1}/24 dev veth1 -ip netns exec ns1 ip link set veth1 up +ip netns exec ${NS1} ip addr add ${IPADDR1}/24 dev veth1 +ip netns exec ${NS1} ip link set veth1 up # In ns2/veth2 create VLAN device export VLAN=4011 export DEVNS2=veth2 -ip netns exec ns2 ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN -ip netns exec ns2 ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN -ip netns exec ns2 ip link set $DEVNS2 up -ip netns exec ns2 ip link set $DEVNS2.$VLAN up +ip netns exec ${NS2} ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN +ip netns exec ${NS2} ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN +ip netns exec ${NS2} ip link set $DEVNS2 up +ip netns exec ${NS2} ip link set $DEVNS2.$VLAN up # Bringup lo in netns (to avoids confusing people using --interactive) -ip netns exec ns1 ip link set lo up -ip netns exec ns2 ip link set lo up +ip netns exec ${NS1} ip link set lo up +ip netns exec ${NS2} ip link set lo up # At this point, the hosts cannot reach each-other, # because ns2 are using VLAN tags on the packets. -ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"' +ip netns exec ${NS2} sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"' # Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags @@ -202,19 +204,19 @@ export FILE=test_xdp_vlan.o # First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change" export XDP_PROG=xdp_vlan_change -ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG +ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # In ns1: egress use TC to add back VLAN tag 4011 # (del cmd) # tc qdisc del dev $DEVNS1 clsact 2> /dev/null # -ip netns exec ns1 tc qdisc add dev $DEVNS1 clsact -ip netns exec ns1 tc filter add dev $DEVNS1 egress \ +ip netns exec ${NS1} tc qdisc add dev $DEVNS1 clsact +ip netns exec ${NS1} tc filter add dev $DEVNS1 egress \ prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push # Now the namespaces can reach each-other, test with ping: -ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 -ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 +ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2 # Second test: Replace xdp prog, that fully remove vlan header # @@ -223,9 +225,9 @@ ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 # ETH_P_8021Q indication, and this cause overwriting of our changes. # export XDP_PROG=xdp_vlan_remove_outer2 -ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off -ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG +ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE off +ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG # Now the namespaces should still be able reach each-other, test with ping: -ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1 -ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2 +ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1 +ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2 diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 7b7f918eda77..3d6217e3aff7 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -34,6 +34,13 @@ int load_kallsyms(void) if (!f) return -ENOENT; + /* + * This is called/used from multiplace places, + * load symbols just once. + */ + if (sym_cnt) + return 0; + while (fgets(buf, sizeof(buf), f)) { if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) break; @@ -138,6 +145,29 @@ void read_trace_pipe(void) } } +ssize_t get_uprobe_offset(const void *addr) +{ + size_t start, end, base; + char buf[256]; + bool found = false; + FILE *f; + + f = fopen("/proc/self/maps", "r"); + if (!f) + return -errno; + + while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) { + if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) { + found = true; + break; + } + } + + fclose(f); + + if (!found) + return -ESRCH; + #if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2 #define OP_RT_RA_MASK 0xffff0000UL @@ -145,10 +175,6 @@ void read_trace_pipe(void) #define ADDIS_R2_R12 0x3c4c0000UL #define ADDI_R2_R2 0x38420000UL -ssize_t get_uprobe_offset(const void *addr, ssize_t base) -{ - u32 *insn = (u32 *)(uintptr_t)addr; - /* * A PPC64 ABIv2 function may have a local and a global entry * point. We need to use the local entry point when patching @@ -165,43 +191,16 @@ ssize_t get_uprobe_offset(const void *addr, ssize_t base) * lis r2,XXXX * addi r2,r2,XXXX */ - if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) || - ((*insn & OP_RT_RA_MASK) == LIS_R2)) && - ((*(insn + 1) & OP_RT_RA_MASK) == ADDI_R2_R2)) - return (ssize_t)(insn + 2) - base; - else - return (uintptr_t)addr - base; -} + { + const u32 *insn = (const u32 *)(uintptr_t)addr; -#else - -ssize_t get_uprobe_offset(const void *addr, ssize_t base) -{ - return (uintptr_t)addr - base; -} - -#endif - -ssize_t get_base_addr(void) -{ - size_t start, offset; - char buf[256]; - FILE *f; - - f = fopen("/proc/self/maps", "r"); - if (!f) - return -errno; - - while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n", - &start, buf, &offset) == 3) { - if (strcmp(buf, "r-xp") == 0) { - fclose(f); - return start - offset; - } + if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) || + ((*insn & OP_RT_RA_MASK) == LIS_R2)) && + ((*(insn + 1) & OP_RT_RA_MASK) == ADDI_R2_R2)) + return (uintptr_t)(insn + 2) - start + base; } - - fclose(f); - return -EINVAL; +#endif + return (uintptr_t)addr - start + base; } ssize_t get_rel_offset(uintptr_t addr) diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index d907b445524d..238a9c98cde2 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -18,8 +18,7 @@ int kallsyms_find(const char *sym, unsigned long long *addr); void read_trace_pipe(void); -ssize_t get_uprobe_offset(const void *addr, ssize_t base); -ssize_t get_base_addr(void); +ssize_t get_uprobe_offset(const void *addr); ssize_t get_rel_offset(uintptr_t addr); #endif diff --git a/tools/testing/selftests/bpf/verifier/atomic_invalid.c b/tools/testing/selftests/bpf/verifier/atomic_invalid.c index 39272720b2f6..25f4ac1c69ab 100644 --- a/tools/testing/selftests/bpf/verifier/atomic_invalid.c +++ b/tools/testing/selftests/bpf/verifier/atomic_invalid.c @@ -1,6 +1,6 @@ -#define __INVALID_ATOMIC_ACCESS_TEST(op) \ +#define __INVALID_ATOMIC_ACCESS_TEST(op) \ { \ - "atomic " #op " access through non-pointer ", \ + "atomic " #op " access through non-pointer ", \ .insns = { \ BPF_MOV64_IMM(BPF_REG_0, 1), \ BPF_MOV64_IMM(BPF_REG_1, 0), \ @@ -9,7 +9,7 @@ BPF_EXIT_INSN(), \ }, \ .result = REJECT, \ - .errstr = "R1 invalid mem access 'inv'" \ + .errstr = "R1 invalid mem access 'scalar'" \ } __INVALID_ATOMIC_ACCESS_TEST(BPF_ADD), __INVALID_ATOMIC_ACCESS_TEST(BPF_ADD | BPF_FETCH), diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index e061e8799ce2..33125d5f6772 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -508,7 +508,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT }, @@ -530,7 +530,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT }, diff --git a/tools/testing/selftests/bpf/verifier/bounds_deduction.c b/tools/testing/selftests/bpf/verifier/bounds_deduction.c index 91869aea6d64..3931c481e30c 100644 --- a/tools/testing/selftests/bpf/verifier/bounds_deduction.c +++ b/tools/testing/selftests/bpf/verifier/bounds_deduction.c @@ -105,7 +105,7 @@ BPF_EXIT_INSN(), }, .errstr_unpriv = "R1 has pointer with unsupported alu operation", - .errstr = "dereference of modified ctx ptr", + .errstr = "negative offset ctx ptr R1 off=-1 disallowed", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index d7b74eb28333..2e03decb11b6 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -22,6 +22,183 @@ .result = ACCEPT, }, { + "calls: invalid kfunc call: ptr_to_mem to struct with non-scalar", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type STRUCT prog_test_fail1 must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail1", 2 }, + }, +}, +{ + "calls: invalid kfunc call: ptr_to_mem to struct with nesting depth > 4", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "max struct nesting depth exceeded\narg#0 pointer type STRUCT prog_test_fail2", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail2", 2 }, + }, +}, +{ + "calls: invalid kfunc call: ptr_to_mem to struct with FAM", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type STRUCT prog_test_fail3 must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail3", 2 }, + }, +}, +{ + "calls: invalid kfunc call: reg->type != PTR_TO_CTX", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 expected pointer to ctx, but got PTR", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_pass_ctx", 2 }, + }, +}, +{ + "calls: invalid kfunc call: void * not allowed in func proto without mem size arg", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type UNKNOWN must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_mem_len_fail1", 2 }, + }, +}, +{ + "calls: trigger reg2btf_ids[reg->type] for reg->type > __BPF_REG_TYPE_MAX", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type STRUCT prog_test_ref_kfunc must point", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_test_release", 5 }, + }, +}, +{ + "calls: invalid kfunc call: reg->off must be zero when passed to release kfunc", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "R1 must have zero offset when passed to release func", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_memb_release", 8 }, + }, +}, +{ + "calls: invalid kfunc call: PTR_TO_BTF_ID with negative offset", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 16), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_test_release", 9 }, + }, + .result_unpriv = REJECT, + .result = REJECT, + .errstr = "negative offset ptr_ ptr R1 off=-4 disallowed", +}, +{ + "calls: invalid kfunc call: PTR_TO_BTF_ID with variable offset", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4), + BPF_JMP_IMM(BPF_JLE, BPF_REG_2, 4, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_acquire", 3 }, + { "bpf_kfunc_call_test_release", 9 }, + { "bpf_kfunc_call_test_release", 13 }, + { "bpf_kfunc_call_test_release", 17 }, + }, + .result_unpriv = REJECT, + .result = REJECT, + .errstr = "variable ptr_ access var_off=(0x0; 0x7) disallowed", +}, +{ "calls: basic sanity", .insns = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), @@ -94,7 +271,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'scalar'", }, { "calls: multiple ret types in subprog 2", @@ -397,7 +574,7 @@ BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "R6 invalid mem access 'inv'", + .errstr = "R6 invalid mem access 'scalar'", .prog_type = BPF_PROG_TYPE_XDP, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -1603,7 +1780,7 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .fixup_map_hash_8b = { 12, 22 }, .result = REJECT, - .errstr = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'scalar'", }, { "calls: pkt_ptr spill into caller stack", diff --git a/tools/testing/selftests/bpf/verifier/ctx.c b/tools/testing/selftests/bpf/verifier/ctx.c index 23080862aafd..c8eaf0536c24 100644 --- a/tools/testing/selftests/bpf/verifier/ctx.c +++ b/tools/testing/selftests/bpf/verifier/ctx.c @@ -58,7 +58,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "dereference of modified ctx ptr", + .errstr = "negative offset ctx ptr R1 off=-612 disallowed", }, { "pass modified ctx pointer to helper, 2", @@ -71,8 +71,8 @@ }, .result_unpriv = REJECT, .result = REJECT, - .errstr_unpriv = "dereference of modified ctx ptr", - .errstr = "dereference of modified ctx ptr", + .errstr_unpriv = "negative offset ctx ptr R1 off=-612 disallowed", + .errstr = "negative offset ctx ptr R1 off=-612 disallowed", }, { "pass modified ctx pointer to helper, 3", @@ -127,7 +127,7 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, .result = REJECT, - .errstr = "R1 type=inv expected=ctx", + .errstr = "R1 type=scalar expected=ctx", }, { "pass ctx or null check, 4: ctx - const", @@ -141,7 +141,7 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, .result = REJECT, - .errstr = "dereference of modified ctx ptr", + .errstr = "negative offset ctx ptr R1 off=-612 disallowed", }, { "pass ctx or null check, 5: null (connect)", @@ -193,5 +193,5 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK, .expected_attach_type = BPF_CGROUP_INET4_POST_BIND, .result = REJECT, - .errstr = "R1 type=inv expected=ctx", + .errstr = "R1 type=scalar expected=ctx", }, diff --git a/tools/testing/selftests/bpf/verifier/direct_packet_access.c b/tools/testing/selftests/bpf/verifier/direct_packet_access.c index ac1e19d0f520..11acd1855acf 100644 --- a/tools/testing/selftests/bpf/verifier/direct_packet_access.c +++ b/tools/testing/selftests/bpf/verifier/direct_packet_access.c @@ -339,7 +339,7 @@ BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R2 invalid mem access 'inv'", + .errstr = "R2 invalid mem access 'scalar'", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, diff --git a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c index 0ab7f1dfc97a..a6c869a7319c 100644 --- a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c +++ b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c @@ -350,7 +350,7 @@ BPF_EMIT_CALL(BPF_FUNC_csum_diff), BPF_EXIT_INSN(), }, - .errstr = "R1 type=inv expected=fp", + .errstr = "R1 type=scalar expected=fp", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, @@ -471,7 +471,7 @@ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel), BPF_EXIT_INSN(), }, - .errstr = "R1 type=inv expected=fp", + .errstr = "R1 type=scalar expected=fp", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -484,7 +484,7 @@ BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel), BPF_EXIT_INSN(), }, - .errstr = "R1 type=inv expected=fp", + .errstr = "R1 type=scalar expected=fp", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c index 1c857b2fbdf0..6ddc418fdfaf 100644 --- a/tools/testing/selftests/bpf/verifier/jmp32.c +++ b/tools/testing/selftests/bpf/verifier/jmp32.c @@ -286,7 +286,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -356,7 +356,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -426,7 +426,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -496,7 +496,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -566,7 +566,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -636,7 +636,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -706,7 +706,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, @@ -776,7 +776,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 2, diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 6dc8003ffc70..9e754423fa8b 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -27,7 +27,7 @@ BPF_JMP_IMM(BPF_JLT, BPF_REG_2, 8, 1), BPF_EXIT_INSN(), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), /* R2=inv(umin=1, umax=8) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), /* R2=scalar(umin=1, umax=8) */ BPF_MOV64_REG(BPF_REG_1, BPF_REG_FP), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), BPF_MOV64_IMM(BPF_REG_3, 0), @@ -87,7 +87,7 @@ BPF_JMP_IMM(BPF_JLT, BPF_REG_2, 8, 1), BPF_EXIT_INSN(), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), /* R2=inv(umin=1, umax=8) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), /* R2=scalar(umin=1, umax=8) */ BPF_MOV64_REG(BPF_REG_1, BPF_REG_FP), BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), BPF_MOV64_IMM(BPF_REG_3, 0), diff --git a/tools/testing/selftests/bpf/verifier/raw_stack.c b/tools/testing/selftests/bpf/verifier/raw_stack.c index cc8e8c3cdc03..eb5ed936580b 100644 --- a/tools/testing/selftests/bpf/verifier/raw_stack.c +++ b/tools/testing/selftests/bpf/verifier/raw_stack.c @@ -132,7 +132,7 @@ BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'scalar'", .prog_type = BPF_PROG_TYPE_SCHED_CLS, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -162,7 +162,7 @@ BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "R3 invalid mem access 'inv'", + .errstr = "R3 invalid mem access 'scalar'", .prog_type = BPF_PROG_TYPE_SCHED_CLS, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index 3b6ee009c00b..fbd682520e47 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -162,7 +162,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, - .errstr = "type=inv expected=sock", + .errstr = "type=scalar expected=sock", .result = REJECT, }, { @@ -178,7 +178,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, - .errstr = "type=inv expected=sock", + .errstr = "type=scalar expected=sock", .result = REJECT, }, { @@ -274,7 +274,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, - .errstr = "type=inv expected=sock", + .errstr = "type=scalar expected=sock", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index 682519769fe3..68b14fdfebdb 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -104,7 +104,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - .errstr = "R6 invalid mem access 'inv'", + .errstr = "R6 invalid mem access 'scalar'", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index ce13ece08d51..86b24cad27a7 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -121,7 +121,25 @@ .result = ACCEPT, }, { - "sk_fullsock(skb->sk): sk->dst_port [narrow load]", + "sk_fullsock(skb->sk): sk->dst_port [word load] (backward compatibility)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [half load]", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), @@ -139,7 +157,64 @@ .result = ACCEPT, }, { - "sk_fullsock(skb->sk): sk->dst_port [load 2nd byte]", + "sk_fullsock(skb->sk): sk->dst_port [half load] (invalid)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [byte load]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [byte load] (invalid)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): past sk->dst_port [half load] (invalid)", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), @@ -149,7 +224,7 @@ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, dst_port)), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -427,7 +502,7 @@ .fixup_sk_storage_map = { 11 }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "R3 type=inv expected=fp", + .errstr = "R3 type=scalar expected=fp", }, { "sk_storage_get(map, skb->sk, &stack_value, 1): stack_value", diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 8cfc5349d2a8..e23f07175e1b 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -102,7 +102,7 @@ BPF_EXIT_INSN(), }, .errstr_unpriv = "attempt to corrupt spilled", - .errstr = "R0 invalid mem access 'inv", + .errstr = "R0 invalid mem access 'scalar'", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -147,11 +147,11 @@ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8), /* r0 = r2 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv20 */ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=20 */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), - /* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=inv20 */ + /* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), - /* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=inv20 */ + /* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=20 */ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -190,11 +190,11 @@ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8), /* r0 = r2 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), - /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), - /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -222,11 +222,11 @@ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8), /* r0 = r2 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), - /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), - /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -250,11 +250,11 @@ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -6), /* r0 = r2 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), - /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), - /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -280,11 +280,11 @@ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4), /* r0 = r2 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=U32_MAX */ + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=U32_MAX */ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), - /* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */ + /* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4= */ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), - /* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */ + /* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4= */ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -305,13 +305,13 @@ BPF_JMP_IMM(BPF_JLE, BPF_REG_4, 40, 2), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), - /* *(u32 *)(r10 -8) = r4 R4=inv,umax=40 */ + /* *(u32 *)(r10 -8) = r4 R4=umax=40 */ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), /* r4 = (*u32 *)(r10 - 8) */ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8), - /* r2 += r4 R2=pkt R4=inv,umax=40 */ + /* r2 += r4 R2=pkt R4=umax=40 */ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_4), - /* r0 = r2 R2=pkt,umax=40 R4=inv,umax=40 */ + /* r0 = r2 R2=pkt,umax=40 R4=umax=40 */ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), /* r2 += 20 R0=pkt,umax=40 R2=pkt,umax=40 */ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 20), diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c index 111801aea5e3..878ca26c3f0a 100644 --- a/tools/testing/selftests/bpf/verifier/unpriv.c +++ b/tools/testing/selftests/bpf/verifier/unpriv.c @@ -214,7 +214,7 @@ BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "R1 type=inv expected=ctx", + .errstr = "R1 type=scalar expected=ctx", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -420,7 +420,7 @@ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R7 invalid mem access 'inv'", + .errstr_unpriv = "R7 invalid mem access 'scalar'", .result_unpriv = REJECT, .result = ACCEPT, .retval = 0, diff --git a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c index 489062867218..d6f29eb4bd57 100644 --- a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c +++ b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c @@ -64,7 +64,7 @@ }, .fixup_map_hash_48b = { 3 }, .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "invalid mem access 'inv'", + .errstr = "invalid mem access 'scalar'", .result = REJECT, .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -89,7 +89,7 @@ }, .fixup_map_hash_48b = { 3 }, .errstr_unpriv = "leaking pointer from stack off -8", - .errstr = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'scalar'", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index 359f3e8f8b60..249187d3c530 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -397,7 +397,7 @@ .fixup_map_array_48b = { 1 }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 invalid mem access 'scalar'", .retval = 0, }, { @@ -1074,7 +1074,7 @@ }, .fixup_map_array_48b = { 3 }, .result = REJECT, - .errstr = "R0 invalid mem access 'inv'", + .errstr = "R0 invalid mem access 'scalar'", .errstr_unpriv = "R0 pointer -= pointer prohibited", }, { diff --git a/tools/testing/selftests/bpf/verifier/var_off.c b/tools/testing/selftests/bpf/verifier/var_off.c index eab1f7f56e2f..187c6f6e32bc 100644 --- a/tools/testing/selftests/bpf/verifier/var_off.c +++ b/tools/testing/selftests/bpf/verifier/var_off.c @@ -131,7 +131,7 @@ * write might have overwritten the spilled pointer (i.e. we lose track * of the spilled register when we analyze the write). */ - .errstr = "R2 invalid mem access 'inv'", + .errstr = "R2 invalid mem access 'scalar'", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh index b3afd43549fa..e0bb04a97e10 100755 --- a/tools/testing/selftests/bpf/vmtest.sh +++ b/tools/testing/selftests/bpf/vmtest.sh @@ -241,7 +241,7 @@ EOF -nodefaults \ -display none \ -serial mon:stdio \ - "${qemu_flags[@]}" \ + "${QEMU_FLAGS[@]}" \ -enable-kvm \ -m 4G \ -drive file="${rootfs_img}",format=raw,index=1,media=disk,if=virtio,cache=none \ diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c index 51c8224b4ccc..aaedbf4955c3 100644 --- a/tools/testing/selftests/bpf/xdp_redirect_multi.c +++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c @@ -32,12 +32,12 @@ static void int_exit(int sig) int i; for (i = 0; ifaces[i] > 0; i++) { - if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifaces[i], xdp_flags, &prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(1); } if (prog_id) - bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags); + bpf_xdp_detach(ifaces[i], xdp_flags, NULL); } exit(0); @@ -210,7 +210,7 @@ int main(int argc, char **argv) } /* bind prog_fd to each interface */ - ret = bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags); + ret = bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL); if (ret) { printf("Set xdp fd failed on %d\n", ifindex); goto err_out; diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index baa870a759a2..c567856fd1bc 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -29,7 +29,7 @@ static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; static void cleanup(int sig) { - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); if (sig) exit(1); } @@ -203,7 +203,7 @@ int main(int argc, char **argv) printf("XDP setup disrupts network connectivity, hit Ctrl+C to quit\n"); - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { fprintf(stderr, "Link set xdp fd failed for %s\n", ifname); goto done; } diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index 0a5d23da486d..5f8296d29e77 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -266,22 +266,24 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size } static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, - struct ifobject *ifobject, u32 qid) + struct ifobject *ifobject, bool shared) { - struct xsk_socket_config cfg; + struct xsk_socket_config cfg = {}; struct xsk_ring_cons *rxr; struct xsk_ring_prod *txr; xsk->umem = umem; cfg.rx_size = xsk->rxqsize; cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - cfg.libbpf_flags = 0; + cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD; cfg.xdp_flags = ifobject->xdp_flags; cfg.bind_flags = ifobject->bind_flags; + if (shared) + cfg.bind_flags |= XDP_SHARED_UMEM; txr = ifobject->tx_on ? &xsk->tx : NULL; rxr = ifobject->rx_on ? &xsk->rx : NULL; - return xsk_socket__create(&xsk->xsk, ifobject->ifname, qid, umem->umem, rxr, txr, &cfg); + return xsk_socket__create(&xsk->xsk, ifobject->ifname, 0, umem->umem, rxr, txr, &cfg); } static struct option long_options[] = { @@ -387,7 +389,6 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, for (i = 0; i < MAX_INTERFACES; i++) { struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; - ifobj->umem = &ifobj->umem_arr[0]; ifobj->xsk = &ifobj->xsk_arr[0]; ifobj->use_poll = false; ifobj->pacing_on = true; @@ -401,11 +402,12 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, ifobj->tx_on = false; } + memset(ifobj->umem, 0, sizeof(*ifobj->umem)); + ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; + ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; + for (j = 0; j < MAX_SOCKETS; j++) { - memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j])); memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); - ifobj->umem_arr[j].num_frames = DEFAULT_UMEM_BUFFERS; - ifobj->umem_arr[j].frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; } } @@ -906,7 +908,10 @@ static bool rx_stats_are_valid(struct ifobject *ifobject) return true; case STAT_TEST_RX_FULL: xsk_stat = stats.rx_ring_full; - expected_stat -= RX_FULL_RXQSIZE; + if (ifobject->umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) + expected_stat = ifobject->umem->num_frames - RX_FULL_RXQSIZE; + else + expected_stat = XSK_RING_PROD__DEFAULT_NUM_DESCS - RX_FULL_RXQSIZE; break; case STAT_TEST_RX_FILL_EMPTY: xsk_stat = stats.rx_fill_ring_empty_descs; @@ -947,7 +952,10 @@ static void tx_stats_validate(struct ifobject *ifobject) static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) { + u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; + int ret, ifindex; + void *bufs; u32 i; ifobject->ns_fd = switch_namespace(ifobject->nsname); @@ -955,23 +963,20 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) if (ifobject->umem->unaligned_mode) mmap_flags |= MAP_HUGETLB; - for (i = 0; i < test->nb_sockets; i++) { - u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; - u32 ctr = 0; - void *bufs; - int ret; + bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); + if (bufs == MAP_FAILED) + exit_with_error(errno); - bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); - if (bufs == MAP_FAILED) - exit_with_error(errno); + ret = xsk_configure_umem(ifobject->umem, bufs, umem_sz); + if (ret) + exit_with_error(-ret); - ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz); - if (ret) - exit_with_error(-ret); + for (i = 0; i < test->nb_sockets; i++) { + u32 ctr = 0; while (ctr++ < SOCK_RECONF_CTR) { - ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i], - ifobject, i); + ret = xsk_configure_socket(&ifobject->xsk_arr[i], ifobject->umem, + ifobject, !!i); if (!ret) break; @@ -982,8 +987,22 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) } } - ifobject->umem = &ifobject->umem_arr[0]; ifobject->xsk = &ifobject->xsk_arr[0]; + + if (!ifobject->rx_on) + return; + + ifindex = if_nametoindex(ifobject->ifname); + if (!ifindex) + exit_with_error(errno); + + ret = xsk_setup_xdp_prog(ifindex, &ifobject->xsk_map_fd); + if (ret) + exit_with_error(-ret); + + ret = xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd); + if (ret) + exit_with_error(-ret); } static void testapp_cleanup_xsk_res(struct ifobject *ifobj) @@ -1139,14 +1158,16 @@ static void testapp_bidi(struct test_spec *test) static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx) { + int ret; + xsk_socket__delete(ifobj_tx->xsk->xsk); - xsk_umem__delete(ifobj_tx->umem->umem); xsk_socket__delete(ifobj_rx->xsk->xsk); - xsk_umem__delete(ifobj_rx->umem->umem); - ifobj_tx->umem = &ifobj_tx->umem_arr[1]; ifobj_tx->xsk = &ifobj_tx->xsk_arr[1]; - ifobj_rx->umem = &ifobj_rx->umem_arr[1]; ifobj_rx->xsk = &ifobj_rx->xsk_arr[1]; + + ret = xsk_socket__update_xskmap(ifobj_rx->xsk->xsk, ifobj_rx->xsk_map_fd); + if (ret) + exit_with_error(-ret); } static void testapp_bpf_res(struct test_spec *test) @@ -1405,13 +1426,13 @@ static struct ifobject *ifobject_create(void) if (!ifobj->xsk_arr) goto out_xsk_arr; - ifobj->umem_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->umem_arr)); - if (!ifobj->umem_arr) - goto out_umem_arr; + ifobj->umem = calloc(1, sizeof(*ifobj->umem)); + if (!ifobj->umem) + goto out_umem; return ifobj; -out_umem_arr: +out_umem: free(ifobj->xsk_arr); out_xsk_arr: free(ifobj); @@ -1420,7 +1441,7 @@ out_xsk_arr: static void ifobject_delete(struct ifobject *ifobj) { - free(ifobj->umem_arr); + free(ifobj->umem); free(ifobj->xsk_arr); free(ifobj); } diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h index 2f705f44b748..62a3e6388632 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.h +++ b/tools/testing/selftests/bpf/xdpxceiver.h @@ -125,10 +125,10 @@ struct ifobject { struct xsk_socket_info *xsk; struct xsk_socket_info *xsk_arr; struct xsk_umem_info *umem; - struct xsk_umem_info *umem_arr; thread_func_t func_ptr; struct pkt_stream *pkt_stream; int ns_fd; + int xsk_map_fd; u32 dst_ip; u32 src_ip; u32 xdp_flags; diff --git a/tools/testing/selftests/drivers/net/mlxsw/hw_stats_l3.sh b/tools/testing/selftests/drivers/net/mlxsw/hw_stats_l3.sh new file mode 100755 index 000000000000..941ba4c485c9 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/hw_stats_l3.sh @@ -0,0 +1,31 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + l3_monitor_test +" +NUM_NETIFS=0 +source $lib_dir/lib.sh + +swp=$NETIF_NO_CABLE + +cleanup() +{ + pre_cleanup +} + +l3_monitor_test() +{ + hw_stats_monitor_test $swp l3 \ + "ip addr add dev $swp 192.0.2.1/28" \ + "ip addr del dev $swp 192.0.2.1/28" +} + +trap cleanup EXIT + +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/netdevsim/hw_stats_l3.sh b/tools/testing/selftests/drivers/net/netdevsim/hw_stats_l3.sh new file mode 100755 index 000000000000..fe1898402987 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/hw_stats_l3.sh @@ -0,0 +1,421 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + l3_reporting_test + l3_fail_next_test + l3_counter_test + l3_rollback_test + l3_monitor_test +" + +NETDEVSIM_PATH=/sys/bus/netdevsim/ +DEV_ADDR_1=1337 +DEV_ADDR_2=1057 +DEV_ADDR_3=5417 +NUM_NETIFS=0 +source $lib_dir/lib.sh + +DUMMY_IFINDEX= + +DEV_ADDR() +{ + local n=$1; shift + local var=DEV_ADDR_$n + + echo ${!var} +} + +DEV() +{ + echo netdevsim$(DEV_ADDR $1) +} + +DEVLINK_DEV() +{ + echo netdevsim/$(DEV $1) +} + +SYSFS_NET_DIR() +{ + echo /sys/bus/netdevsim/devices/$(DEV $1)/net/ +} + +DEBUGFS_DIR() +{ + echo /sys/kernel/debug/netdevsim/$(DEV $1)/ +} + +nsim_add() +{ + local n=$1; shift + + echo "$(DEV_ADDR $n) 1" > ${NETDEVSIM_PATH}/new_device + while [ ! -d $(SYSFS_NET_DIR $n) ] ; do :; done +} + +nsim_reload() +{ + local n=$1; shift + local ns=$1; shift + + devlink dev reload $(DEVLINK_DEV $n) netns $ns + + if [ $? -ne 0 ]; then + echo "Failed to reload $(DEV $n) into netns \"testns1\"" + exit 1 + fi + +} + +nsim_del() +{ + local n=$1; shift + + echo "$(DEV_ADDR $n)" > ${NETDEVSIM_PATH}/del_device +} + +nsim_hwstats_toggle() +{ + local action=$1; shift + local instance=$1; shift + local netdev=$1; shift + local type=$1; shift + + local ifindex=$($IP -j link show dev $netdev | jq '.[].ifindex') + + echo $ifindex > $(DEBUGFS_DIR $instance)/hwstats/$type/$action +} + +nsim_hwstats_enable() +{ + nsim_hwstats_toggle enable_ifindex "$@" +} + +nsim_hwstats_disable() +{ + nsim_hwstats_toggle disable_ifindex "$@" +} + +nsim_hwstats_fail_next_enable() +{ + nsim_hwstats_toggle fail_next_enable "$@" +} + +setup_prepare() +{ + modprobe netdevsim &> /dev/null + nsim_add 1 + nsim_add 2 + nsim_add 3 + + ip netns add testns1 + + if [ $? -ne 0 ]; then + echo "Failed to add netns \"testns1\"" + exit 1 + fi + + nsim_reload 1 testns1 + nsim_reload 2 testns1 + nsim_reload 3 testns1 + + IP="ip -n testns1" + + $IP link add name dummy1 type dummy + $IP link set dev dummy1 up + DUMMY_IFINDEX=$($IP -j link show dev dummy1 | jq '.[].ifindex') +} + +cleanup() +{ + pre_cleanup + + $IP link del name dummy1 + ip netns del testns1 + nsim_del 3 + nsim_del 2 + nsim_del 1 + modprobe -r netdevsim &> /dev/null +} + +netdev_hwstats_used() +{ + local netdev=$1; shift + local type=$1; shift + + $IP -j stats show dev "$netdev" group offload subgroup hw_stats_info | + jq '.[].info.l3_stats.used' +} + +netdev_check_used() +{ + local netdev=$1; shift + local type=$1; shift + + [[ $(netdev_hwstats_used $netdev $type) == "true" ]] +} + +netdev_check_unused() +{ + local netdev=$1; shift + local type=$1; shift + + [[ $(netdev_hwstats_used $netdev $type) == "false" ]] +} + +netdev_hwstats_request() +{ + local netdev=$1; shift + local type=$1; shift + + $IP -j stats show dev "$netdev" group offload subgroup hw_stats_info | + jq ".[].info.${type}_stats.request" +} + +netdev_check_requested() +{ + local netdev=$1; shift + local type=$1; shift + + [[ $(netdev_hwstats_request $netdev $type) == "true" ]] +} + +netdev_check_unrequested() +{ + local netdev=$1; shift + local type=$1; shift + + [[ $(netdev_hwstats_request $netdev $type) == "false" ]] +} + +reporting_test() +{ + local type=$1; shift + local instance=1 + + RET=0 + + [[ -n $(netdev_hwstats_used dummy1 $type) ]] + check_err $? "$type stats not reported" + + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used before either device or netdevsim request" + + nsim_hwstats_enable $instance dummy1 $type + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used before device request" + netdev_check_unrequested dummy1 $type + check_err $? "$type stats reported as requested before device request" + + $IP stats set dev dummy1 ${type}_stats on + netdev_check_used dummy1 $type + check_err $? "$type stats reported as not used after both device and netdevsim request" + netdev_check_requested dummy1 $type + check_err $? "$type stats reported as not requested after device request" + + nsim_hwstats_disable $instance dummy1 $type + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used after netdevsim request withdrawn" + + nsim_hwstats_enable $instance dummy1 $type + netdev_check_used dummy1 $type + check_err $? "$type stats reported as not used after netdevsim request reenabled" + + $IP stats set dev dummy1 ${type}_stats off + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used after device request withdrawn" + netdev_check_unrequested dummy1 $type + check_err $? "$type stats reported as requested after device request withdrawn" + + nsim_hwstats_disable $instance dummy1 $type + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used after both requests withdrawn" + + log_test "Reporting of $type stats usage" +} + +l3_reporting_test() +{ + reporting_test l3 +} + +__fail_next_test() +{ + local instance=$1; shift + local type=$1; shift + + RET=0 + + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used before either device or netdevsim request" + + nsim_hwstats_enable $instance dummy1 $type + nsim_hwstats_fail_next_enable $instance dummy1 $type + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used before device request" + netdev_check_unrequested dummy1 $type + check_err $? "$type stats reported as requested before device request" + + $IP stats set dev dummy1 ${type}_stats on 2>/dev/null + check_fail $? "$type stats request not bounced as it should have been" + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used after bounce" + netdev_check_unrequested dummy1 $type + check_err $? "$type stats reported as requested after bounce" + + $IP stats set dev dummy1 ${type}_stats on + check_err $? "$type stats request failed when it shouldn't have" + netdev_check_used dummy1 $type + check_err $? "$type stats reported as not used after both device and netdevsim request" + netdev_check_requested dummy1 $type + check_err $? "$type stats reported as not requested after device request" + + $IP stats set dev dummy1 ${type}_stats off + nsim_hwstats_disable $instance dummy1 $type + + log_test "Injected failure of $type stats enablement (netdevsim #$instance)" +} + +fail_next_test() +{ + __fail_next_test 1 "$@" + __fail_next_test 2 "$@" + __fail_next_test 3 "$@" +} + +l3_fail_next_test() +{ + fail_next_test l3 +} + +get_hwstat() +{ + local netdev=$1; shift + local type=$1; shift + local selector=$1; shift + + $IP -j stats show dev $netdev group offload subgroup ${type}_stats | + jq ".[0].stats64.${selector}" +} + +counter_test() +{ + local type=$1; shift + local instance=1 + + RET=0 + + nsim_hwstats_enable $instance dummy1 $type + $IP stats set dev dummy1 ${type}_stats on + netdev_check_used dummy1 $type + check_err $? "$type stats reported as not used after both device and netdevsim request" + + # Netdevsim counts 10pps on ingress. We should see maybe a couple + # packets, unless things take a reeealy long time. + local pkts=$(get_hwstat dummy1 l3 rx.packets) + ((pkts < 10)) + check_err $? "$type stats show >= 10 packets after first enablement" + + sleep 2 + + local pkts=$(get_hwstat dummy1 l3 rx.packets) + ((pkts >= 20)) + check_err $? "$type stats show < 20 packets after 2s passed" + + $IP stats set dev dummy1 ${type}_stats off + + sleep 2 + + $IP stats set dev dummy1 ${type}_stats on + local pkts=$(get_hwstat dummy1 l3 rx.packets) + ((pkts < 10)) + check_err $? "$type stats show >= 10 packets after second enablement" + + $IP stats set dev dummy1 ${type}_stats off + nsim_hwstats_fail_next_enable $instance dummy1 $type + $IP stats set dev dummy1 ${type}_stats on 2>/dev/null + check_fail $? "$type stats request not bounced as it should have been" + + sleep 2 + + $IP stats set dev dummy1 ${type}_stats on + local pkts=$(get_hwstat dummy1 l3 rx.packets) + ((pkts < 10)) + check_err $? "$type stats show >= 10 packets after post-fail enablement" + + $IP stats set dev dummy1 ${type}_stats off + + log_test "Counter values in $type stats" +} + +l3_counter_test() +{ + counter_test l3 +} + +rollback_test() +{ + local type=$1; shift + + RET=0 + + nsim_hwstats_enable 1 dummy1 l3 + nsim_hwstats_enable 2 dummy1 l3 + nsim_hwstats_enable 3 dummy1 l3 + + # The three netdevsim instances are registered in order of their number + # one after another. It is reasonable to expect that whatever + # notifications take place hit no. 2 in between hitting nos. 1 and 3, + # whatever the actual order. This allows us to test that a fail caused + # by no. 2 does not leave the system in a partial state, and rolls + # everything back. + + nsim_hwstats_fail_next_enable 2 dummy1 l3 + $IP stats set dev dummy1 ${type}_stats on 2>/dev/null + check_fail $? "$type stats request not bounced as it should have been" + + netdev_check_unused dummy1 $type + check_err $? "$type stats reported as used after bounce" + netdev_check_unrequested dummy1 $type + check_err $? "$type stats reported as requested after bounce" + + sleep 2 + + $IP stats set dev dummy1 ${type}_stats on + check_err $? "$type stats request not upheld as it should have been" + + local pkts=$(get_hwstat dummy1 l3 rx.packets) + ((pkts < 10)) + check_err $? "$type stats show $pkts packets after post-fail enablement" + + $IP stats set dev dummy1 ${type}_stats off + + nsim_hwstats_disable 3 dummy1 l3 + nsim_hwstats_disable 2 dummy1 l3 + nsim_hwstats_disable 1 dummy1 l3 + + log_test "Failure in $type stats enablement rolled back" +} + +l3_rollback_test() +{ + rollback_test l3 +} + +l3_monitor_test() +{ + hw_stats_monitor_test dummy1 l3 \ + "nsim_hwstats_enable 1 dummy1 l3" \ + "nsim_hwstats_disable 1 dummy1 l3" \ + "$IP" +} + +trap cleanup EXIT + +setup_prepare +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 7581a7348e1b..21a411b04890 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -35,4 +35,4 @@ test_unix_oob gro ioam6_parser toeplitz -cmsg_so_mark +cmsg_sender diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 0b1488616c55..3fe2515aa616 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -30,6 +30,7 @@ TEST_PROGS += ioam6.sh TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh +TEST_PROGS += cmsg_time.sh TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh @@ -52,7 +53,7 @@ TEST_GEN_FILES += gro TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls TEST_GEN_FILES += toeplitz -TEST_GEN_FILES += cmsg_so_mark +TEST_GEN_FILES += cmsg_sender TEST_FILES := settings diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c index 3dece8b29253..b57e91e1c3f2 100644 --- a/tools/testing/selftests/net/af_unix/test_unix_oob.c +++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c @@ -218,10 +218,10 @@ main(int argc, char **argv) /* Test 1: * veriyf that SIGURG is - * delivered and 63 bytes are - * read and oob is '@' + * delivered, 63 bytes are + * read, oob is '@', and POLLPRI works. */ - wait_for_data(pfd, POLLIN | POLLPRI); + wait_for_data(pfd, POLLPRI); read_oob(pfd, &oob); len = read_data(pfd, buf, 1024); if (!signal_recvd || len != 63 || oob != '@') { diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh new file mode 100755 index 000000000000..2d89cb0ad288 --- /dev/null +++ b/tools/testing/selftests/net/cmsg_ipv6.sh @@ -0,0 +1,156 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ksft_skip=4 + +NS=ns +IP6=2001:db8:1::1/64 +TGT6=2001:db8:1::2 +TMPF=`mktemp` + +cleanup() +{ + rm -f $TMPF + ip netns del $NS +} + +trap cleanup EXIT + +NSEXE="ip netns exec $NS" + +tcpdump -h | grep immediate-mode >> /dev/null +if [ $? -ne 0 ]; then + echo "SKIP - tcpdump with --immediate-mode option required" + exit $ksft_skip +fi + +# Namespaces +ip netns add $NS + +$NSEXE sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null + +# Connectivity +ip -netns $NS link add type dummy +ip -netns $NS link set dev dummy0 up +ip -netns $NS addr add $IP6 dev dummy0 + +# Test +BAD=0 +TOTAL=0 + +check_result() { + ((TOTAL++)) + if [ $1 -ne $2 ]; then + echo " Case $3 returned $1, expected $2" + ((BAD++)) + fi +} + +# IPV6_DONTFRAG +for ovr in setsock cmsg both diff; do + for df in 0 1; do + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-F $df" + [ $ovr == "cmsg" ] && m="-f $df" + [ $ovr == "both" ] && m="-F $df -f $df" + [ $ovr == "diff" ] && m="-F $((1 - df)) -f $df" + + $NSEXE ./cmsg_sender -s -S 2000 -6 -p $p $m $TGT6 1234 + check_result $? $df "DONTFRAG $prot $ovr" + done + done +done + +# IPV6_TCLASS +TOS=0x10 +TOS2=0x20 + +ip -6 -netns $NS rule add tos $TOS lookup 300 +ip -6 -netns $NS route add table 300 prohibit any + +for ovr in setsock cmsg both diff; do + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-C" + [ $ovr == "cmsg" ] && m="-c" + [ $ovr == "both" ] && m="-C $((TOS2)) -c" + [ $ovr == "diff" ] && m="-C $((TOS )) -c" + + $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null & + BG=$! + sleep 0.05 + + $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234 + check_result $? 0 "TCLASS $prot $ovr - pass" + + while [ -d /proc/$BG ]; do + $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + done + + tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null + check_result $? 0 "TCLASS $prot $ovr - packet data" + rm $TMPF + + [ $ovr == "both" ] && m="-C $((TOS )) -c" + [ $ovr == "diff" ] && m="-C $((TOS2)) -c" + + $NSEXE ./cmsg_sender -6 -p $p $m $((TOS)) -s $TGT6 1234 + check_result $? 1 "TCLASS $prot $ovr - rejection" + done +done + +# IPV6_HOPLIMIT +LIM=4 + +for ovr in setsock cmsg both diff; do + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-L" + [ $ovr == "cmsg" ] && m="-l" + [ $ovr == "both" ] && m="-L $LIM -l" + [ $ovr == "diff" ] && m="-L $((LIM + 1)) -l" + + $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null & + BG=$! + sleep 0.05 + + $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234 + check_result $? 0 "HOPLIMIT $prot $ovr - pass" + + while [ -d /proc/$BG ]; do + $NSEXE ./cmsg_sender -6 -p u $TGT6 1234 + done + + tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null + check_result $? 0 "HOPLIMIT $prot $ovr - packet data" + rm $TMPF + done +done + +# IPV6 exthdr +for p in u i r; do + # Very basic "does it crash" test + for h in h d r; do + $NSEXE ./cmsg_sender -p $p -6 -H $h $TGT6 1234 + check_result $? 0 "ExtHdr $prot $ovr - pass" + done +done + +# Summary +if [ $BAD -ne 0 ]; then + echo "FAIL - $BAD/$TOTAL cases failed" + exit 1 +else + echo "OK" + exit 0 +fi diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c new file mode 100644 index 000000000000..bc2162909a1a --- /dev/null +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -0,0 +1,506 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <errno.h> +#include <error.h> +#include <netdb.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <linux/errqueue.h> +#include <linux/icmp.h> +#include <linux/icmpv6.h> +#include <linux/net_tstamp.h> +#include <linux/types.h> +#include <linux/udp.h> +#include <sys/socket.h> + +#include "../kselftest.h" + +enum { + ERN_SUCCESS = 0, + /* Well defined errors, callers may depend on these */ + ERN_SEND = 1, + /* Informational, can reorder */ + ERN_HELP, + ERN_SEND_SHORT, + ERN_SOCK_CREATE, + ERN_RESOLVE, + ERN_CMSG_WR, + ERN_SOCKOPT, + ERN_GETTIME, + ERN_RECVERR, + ERN_CMSG_RD, + ERN_CMSG_RCV, +}; + +struct option_cmsg_u32 { + bool ena; + unsigned int val; +}; + +struct options { + bool silent_send; + const char *host; + const char *service; + unsigned int size; + struct { + unsigned int mark; + unsigned int dontfrag; + unsigned int tclass; + unsigned int hlimit; + } sockopt; + struct { + unsigned int family; + unsigned int type; + unsigned int proto; + } sock; + struct option_cmsg_u32 mark; + struct { + bool ena; + unsigned int delay; + } txtime; + struct { + bool ena; + } ts; + struct { + struct option_cmsg_u32 dontfrag; + struct option_cmsg_u32 tclass; + struct option_cmsg_u32 hlimit; + struct option_cmsg_u32 exthdr; + } v6; +} opt = { + .size = 13, + .sock = { + .family = AF_UNSPEC, + .type = SOCK_DGRAM, + .proto = IPPROTO_UDP, + }, +}; + +static struct timespec time_start_real; +static struct timespec time_start_mono; + +static void __attribute__((noreturn)) cs_usage(const char *bin) +{ + printf("Usage: %s [opts] <dst host> <dst port / service>\n", bin); + printf("Options:\n" + "\t\t-s Silent send() failures\n" + "\t\t-S send() size\n" + "\t\t-4/-6 Force IPv4 / IPv6 only\n" + "\t\t-p prot Socket protocol\n" + "\t\t (u = UDP (default); i = ICMP; r = RAW)\n" + "\n" + "\t\t-m val Set SO_MARK with given value\n" + "\t\t-M val Set SO_MARK via setsockopt\n" + "\t\t-d val Set SO_TXTIME with given delay (usec)\n" + "\t\t-t Enable time stamp reporting\n" + "\t\t-f val Set don't fragment via cmsg\n" + "\t\t-F val Set don't fragment via setsockopt\n" + "\t\t-c val Set TCLASS via cmsg\n" + "\t\t-C val Set TCLASS via setsockopt\n" + "\t\t-l val Set HOPLIMIT via cmsg\n" + "\t\t-L val Set HOPLIMIT via setsockopt\n" + "\t\t-H type Add an IPv6 header option\n" + "\t\t (h = HOP; d = DST; r = RTDST)" + ""); + exit(ERN_HELP); +} + +static void cs_parse_args(int argc, char *argv[]) +{ + char o; + + while ((o = getopt(argc, argv, "46sS:p:m:M:d:tf:F:c:C:l:L:H:")) != -1) { + switch (o) { + case 's': + opt.silent_send = true; + break; + case 'S': + opt.size = atoi(optarg); + break; + case '4': + opt.sock.family = AF_INET; + break; + case '6': + opt.sock.family = AF_INET6; + break; + case 'p': + if (*optarg == 'u' || *optarg == 'U') { + opt.sock.proto = IPPROTO_UDP; + } else if (*optarg == 'i' || *optarg == 'I') { + opt.sock.proto = IPPROTO_ICMP; + } else if (*optarg == 'r') { + opt.sock.type = SOCK_RAW; + } else { + printf("Error: unknown protocol: %s\n", optarg); + cs_usage(argv[0]); + } + break; + + case 'm': + opt.mark.ena = true; + opt.mark.val = atoi(optarg); + break; + case 'M': + opt.sockopt.mark = atoi(optarg); + break; + case 'd': + opt.txtime.ena = true; + opt.txtime.delay = atoi(optarg); + break; + case 't': + opt.ts.ena = true; + break; + case 'f': + opt.v6.dontfrag.ena = true; + opt.v6.dontfrag.val = atoi(optarg); + break; + case 'F': + opt.sockopt.dontfrag = atoi(optarg); + break; + case 'c': + opt.v6.tclass.ena = true; + opt.v6.tclass.val = atoi(optarg); + break; + case 'C': + opt.sockopt.tclass = atoi(optarg); + break; + case 'l': + opt.v6.hlimit.ena = true; + opt.v6.hlimit.val = atoi(optarg); + break; + case 'L': + opt.sockopt.hlimit = atoi(optarg); + break; + case 'H': + opt.v6.exthdr.ena = true; + switch (optarg[0]) { + case 'h': + opt.v6.exthdr.val = IPV6_HOPOPTS; + break; + case 'd': + opt.v6.exthdr.val = IPV6_DSTOPTS; + break; + case 'r': + opt.v6.exthdr.val = IPV6_RTHDRDSTOPTS; + break; + default: + printf("Error: hdr type: %s\n", optarg); + break; + } + break; + } + } + + if (optind != argc - 2) + cs_usage(argv[0]); + + opt.host = argv[optind]; + opt.service = argv[optind + 1]; +} + +static void memrnd(void *s, size_t n) +{ + int *dword = s; + char *byte; + + for (; n >= 4; n -= 4) + *dword++ = rand(); + byte = (void *)dword; + while (n--) + *byte++ = rand(); +} + +static void +ca_write_cmsg_u32(char *cbuf, size_t cbuf_sz, size_t *cmsg_len, + int level, int optname, struct option_cmsg_u32 *uopt) +{ + struct cmsghdr *cmsg; + + if (!uopt->ena) + return; + + cmsg = (struct cmsghdr *)(cbuf + *cmsg_len); + *cmsg_len += CMSG_SPACE(sizeof(__u32)); + if (cbuf_sz < *cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = level; + cmsg->cmsg_type = optname; + cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); + *(__u32 *)CMSG_DATA(cmsg) = uopt->val; +} + +static void +cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) +{ + struct cmsghdr *cmsg; + size_t cmsg_len; + + msg->msg_control = cbuf; + cmsg_len = 0; + + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_SOCKET, SO_MARK, &opt.mark); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_TCLASS, &opt.v6.tclass); + ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len, + SOL_IPV6, IPV6_HOPLIMIT, &opt.v6.hlimit); + + if (opt.txtime.ena) { + struct sock_txtime so_txtime = { + .clockid = CLOCK_MONOTONIC, + }; + __u64 txtime; + + if (setsockopt(fd, SOL_SOCKET, SO_TXTIME, + &so_txtime, sizeof(so_txtime))) + error(ERN_SOCKOPT, errno, "setsockopt TXTIME"); + + txtime = time_start_mono.tv_sec * (1000ULL * 1000 * 1000) + + time_start_mono.tv_nsec + + opt.txtime.delay * 1000; + + cmsg = (struct cmsghdr *)(cbuf + cmsg_len); + cmsg_len += CMSG_SPACE(sizeof(txtime)); + if (cbuf_sz < cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_TXTIME; + cmsg->cmsg_len = CMSG_LEN(sizeof(txtime)); + memcpy(CMSG_DATA(cmsg), &txtime, sizeof(txtime)); + } + if (opt.ts.ena) { + __u32 val = SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_OPT_TSONLY; + + if (setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, + &val, sizeof(val))) + error(ERN_SOCKOPT, errno, "setsockopt TIMESTAMPING"); + + cmsg = (struct cmsghdr *)(cbuf + cmsg_len); + cmsg_len += CMSG_SPACE(sizeof(__u32)); + if (cbuf_sz < cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SO_TIMESTAMPING; + cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); + *(__u32 *)CMSG_DATA(cmsg) = SOF_TIMESTAMPING_TX_SCHED | + SOF_TIMESTAMPING_TX_SOFTWARE; + } + if (opt.v6.exthdr.ena) { + cmsg = (struct cmsghdr *)(cbuf + cmsg_len); + cmsg_len += CMSG_SPACE(8); + if (cbuf_sz < cmsg_len) + error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small"); + + cmsg->cmsg_level = SOL_IPV6; + cmsg->cmsg_type = opt.v6.exthdr.val; + cmsg->cmsg_len = CMSG_LEN(8); + *(__u64 *)CMSG_DATA(cmsg) = 0; + } + + if (cmsg_len) + msg->msg_controllen = cmsg_len; + else + msg->msg_control = NULL; +} + +static const char *cs_ts_info2str(unsigned int info) +{ + static const char *names[] = { + [SCM_TSTAMP_SND] = "SND", + [SCM_TSTAMP_SCHED] = "SCHED", + [SCM_TSTAMP_ACK] = "ACK", + }; + + if (info < ARRAY_SIZE(names)) + return names[info]; + return "unknown"; +} + +static void +cs_read_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz) +{ + struct sock_extended_err *see; + struct scm_timestamping *ts; + struct cmsghdr *cmsg; + int i, err; + + if (!opt.ts.ena) + return; + msg->msg_control = cbuf; + msg->msg_controllen = cbuf_sz; + + while (true) { + ts = NULL; + see = NULL; + memset(cbuf, 0, cbuf_sz); + + err = recvmsg(fd, msg, MSG_ERRQUEUE); + if (err < 0) { + if (errno == EAGAIN) + break; + error(ERN_RECVERR, errno, "recvmsg ERRQ"); + } + + for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SO_TIMESTAMPING_OLD) { + if (cmsg->cmsg_len < sizeof(*ts)) + error(ERN_CMSG_RD, EINVAL, "TS cmsg"); + + ts = (void *)CMSG_DATA(cmsg); + } + if ((cmsg->cmsg_level == SOL_IP && + cmsg->cmsg_type == IP_RECVERR) || + (cmsg->cmsg_level == SOL_IPV6 && + cmsg->cmsg_type == IPV6_RECVERR)) { + if (cmsg->cmsg_len < sizeof(*see)) + error(ERN_CMSG_RD, EINVAL, "sock_err cmsg"); + + see = (void *)CMSG_DATA(cmsg); + } + } + + if (!ts) + error(ERN_CMSG_RCV, ENOENT, "TS cmsg not found"); + if (!see) + error(ERN_CMSG_RCV, ENOENT, "sock_err cmsg not found"); + + for (i = 0; i < 3; i++) { + unsigned long long rel_time; + + if (!ts->ts[i].tv_sec && !ts->ts[i].tv_nsec) + continue; + + rel_time = (ts->ts[i].tv_sec - time_start_real.tv_sec) * + (1000ULL * 1000) + + (ts->ts[i].tv_nsec - time_start_real.tv_nsec) / + 1000; + printf(" %5s ts%d %lluus\n", + cs_ts_info2str(see->ee_info), + i, rel_time); + } + } +} + +static void ca_set_sockopts(int fd) +{ + if (opt.sockopt.mark && + setsockopt(fd, SOL_SOCKET, SO_MARK, + &opt.sockopt.mark, sizeof(opt.sockopt.mark))) + error(ERN_SOCKOPT, errno, "setsockopt SO_MARK"); + if (opt.sockopt.dontfrag && + setsockopt(fd, SOL_IPV6, IPV6_DONTFRAG, + &opt.sockopt.dontfrag, sizeof(opt.sockopt.dontfrag))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_DONTFRAG"); + if (opt.sockopt.tclass && + setsockopt(fd, SOL_IPV6, IPV6_TCLASS, + &opt.sockopt.tclass, sizeof(opt.sockopt.tclass))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_TCLASS"); + if (opt.sockopt.hlimit && + setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS, + &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit))) + error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT"); +} + +int main(int argc, char *argv[]) +{ + struct addrinfo hints, *ai; + struct iovec iov[1]; + struct msghdr msg; + char cbuf[1024]; + char *buf; + int err; + int fd; + + cs_parse_args(argc, argv); + + buf = malloc(opt.size); + memrnd(buf, opt.size); + + memset(&hints, 0, sizeof(hints)); + hints.ai_family = opt.sock.family; + + ai = NULL; + err = getaddrinfo(opt.host, opt.service, &hints, &ai); + if (err) { + fprintf(stderr, "Can't resolve address [%s]:%s\n", + opt.host, opt.service); + return ERN_SOCK_CREATE; + } + + if (ai->ai_family == AF_INET6 && opt.sock.proto == IPPROTO_ICMP) + opt.sock.proto = IPPROTO_ICMPV6; + + fd = socket(ai->ai_family, opt.sock.type, opt.sock.proto); + if (fd < 0) { + fprintf(stderr, "Can't open socket: %s\n", strerror(errno)); + freeaddrinfo(ai); + return ERN_RESOLVE; + } + + if (opt.sock.proto == IPPROTO_ICMP) { + buf[0] = ICMP_ECHO; + buf[1] = 0; + } else if (opt.sock.proto == IPPROTO_ICMPV6) { + buf[0] = ICMPV6_ECHO_REQUEST; + buf[1] = 0; + } else if (opt.sock.type == SOCK_RAW) { + struct udphdr hdr = { 1, 2, htons(opt.size), 0 }; + struct sockaddr_in6 *sin6 = (void *)ai->ai_addr;; + + memcpy(buf, &hdr, sizeof(hdr)); + sin6->sin6_port = htons(opt.sock.proto); + } + + ca_set_sockopts(fd); + + if (clock_gettime(CLOCK_REALTIME, &time_start_real)) + error(ERN_GETTIME, errno, "gettime REALTIME"); + if (clock_gettime(CLOCK_MONOTONIC, &time_start_mono)) + error(ERN_GETTIME, errno, "gettime MONOTONIC"); + + iov[0].iov_base = buf; + iov[0].iov_len = opt.size; + + memset(&msg, 0, sizeof(msg)); + msg.msg_name = ai->ai_addr; + msg.msg_namelen = ai->ai_addrlen; + msg.msg_iov = iov; + msg.msg_iovlen = 1; + + cs_write_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + + err = sendmsg(fd, &msg, 0); + if (err < 0) { + if (!opt.silent_send) + fprintf(stderr, "send failed: %s\n", strerror(errno)); + err = ERN_SEND; + goto err_out; + } else if (err != (int)opt.size) { + fprintf(stderr, "short send\n"); + err = ERN_SEND_SHORT; + goto err_out; + } else { + err = ERN_SUCCESS; + } + + /* Make sure all timestamps have time to loop back */ + usleep(opt.txtime.delay); + + cs_read_cmsg(fd, &msg, cbuf, sizeof(cbuf)); + +err_out: + close(fd); + freeaddrinfo(ai); + return err; +} diff --git a/tools/testing/selftests/net/cmsg_so_mark.c b/tools/testing/selftests/net/cmsg_so_mark.c deleted file mode 100644 index 27f2804892a7..000000000000 --- a/tools/testing/selftests/net/cmsg_so_mark.c +++ /dev/null @@ -1,67 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -#include <errno.h> -#include <netdb.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <unistd.h> -#include <linux/types.h> -#include <sys/socket.h> - -int main(int argc, const char **argv) -{ - char cbuf[CMSG_SPACE(sizeof(__u32))]; - struct addrinfo hints, *ai; - struct cmsghdr *cmsg; - struct iovec iov[1]; - struct msghdr msg; - int mark; - int err; - int fd; - - if (argc != 4) { - fprintf(stderr, "Usage: %s <dst_ip> <port> <mark>\n", argv[0]); - return 1; - } - mark = atoi(argv[3]); - - memset(&hints, 0, sizeof(hints)); - hints.ai_family = AF_UNSPEC; - hints.ai_socktype = SOCK_DGRAM; - - ai = NULL; - err = getaddrinfo(argv[1], argv[2], &hints, &ai); - if (err) { - fprintf(stderr, "Can't resolve address: %s\n", strerror(errno)); - return 1; - } - - fd = socket(ai->ai_family, SOCK_DGRAM, IPPROTO_UDP); - if (fd < 0) { - fprintf(stderr, "Can't open socket: %s\n", strerror(errno)); - freeaddrinfo(ai); - return 1; - } - - iov[0].iov_base = "bla"; - iov[0].iov_len = 4; - - msg.msg_name = ai->ai_addr; - msg.msg_namelen = ai->ai_addrlen; - msg.msg_iov = iov; - msg.msg_iovlen = 1; - msg.msg_control = cbuf; - msg.msg_controllen = sizeof(cbuf); - - cmsg = CMSG_FIRSTHDR(&msg); - cmsg->cmsg_level = SOL_SOCKET; - cmsg->cmsg_type = SO_MARK; - cmsg->cmsg_len = CMSG_LEN(sizeof(__u32)); - *(__u32 *)CMSG_DATA(cmsg) = mark; - - err = sendmsg(fd, &msg, 0); - - close(fd); - freeaddrinfo(ai); - return err != 4; -} diff --git a/tools/testing/selftests/net/cmsg_so_mark.sh b/tools/testing/selftests/net/cmsg_so_mark.sh index 19c6aab8d0e9..1650b8622f2f 100755 --- a/tools/testing/selftests/net/cmsg_so_mark.sh +++ b/tools/testing/selftests/net/cmsg_so_mark.sh @@ -18,6 +18,8 @@ trap cleanup EXIT # Namespaces ip netns add $NS +ip netns exec $NS sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null + # Connectivity ip -netns $NS link add type dummy ip -netns $NS link set dev dummy0 up @@ -41,15 +43,29 @@ check_result() { fi } -ip netns exec $NS ./cmsg_so_mark $TGT4 1234 $((MARK + 1)) -check_result $? 0 "IPv4 pass" -ip netns exec $NS ./cmsg_so_mark $TGT6 1234 $((MARK + 1)) -check_result $? 0 "IPv6 pass" +for ovr in setsock cmsg both; do + for i in 4 6; do + [ $i == 4 ] && TGT=$TGT4 || TGT=$TGT6 + + for p in u i r; do + [ $p == "u" ] && prot=UDP + [ $p == "i" ] && prot=ICMP + [ $p == "r" ] && prot=RAW + + [ $ovr == "setsock" ] && m="-M" + [ $ovr == "cmsg" ] && m="-m" + [ $ovr == "both" ] && m="-M $MARK -m" + + ip netns exec $NS ./cmsg_sender -$i -p $p $m $((MARK + 1)) $TGT 1234 + check_result $? 0 "$prot $ovr - pass" + + [ $ovr == "diff" ] && m="-M $((MARK + 1)) -m" -ip netns exec $NS ./cmsg_so_mark $TGT4 1234 $MARK -check_result $? 1 "IPv4 rejection" -ip netns exec $NS ./cmsg_so_mark $TGT6 1234 $MARK -check_result $? 1 "IPv6 rejection" + ip netns exec $NS ./cmsg_sender -$i -p $p $m $MARK -s $TGT 1234 + check_result $? 1 "$prot $ovr - rejection" + done + done +done # Summary if [ $BAD -ne 0 ]; then diff --git a/tools/testing/selftests/net/cmsg_time.sh b/tools/testing/selftests/net/cmsg_time.sh new file mode 100755 index 000000000000..91161e1da734 --- /dev/null +++ b/tools/testing/selftests/net/cmsg_time.sh @@ -0,0 +1,83 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +NS=ns +IP4=172.16.0.1/24 +TGT4=172.16.0.2 +IP6=2001:db8:1::1/64 +TGT6=2001:db8:1::2 + +cleanup() +{ + ip netns del $NS +} + +trap cleanup EXIT + +# Namespaces +ip netns add $NS + +ip netns exec $NS sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null + +# Connectivity +ip -netns $NS link add type dummy +ip -netns $NS link set dev dummy0 up +ip -netns $NS addr add $IP4 dev dummy0 +ip -netns $NS addr add $IP6 dev dummy0 + +# Need FQ for TXTIME +ip netns exec $NS tc qdisc replace dev dummy0 root fq + +# Test +BAD=0 +TOTAL=0 + +check_result() { + ((TOTAL++)) + if [ $1 -ne 0 ]; then + echo " Case $4 returned $1, expected 0" + ((BAD++)) + elif [ "$2" != "$3" ]; then + echo " Case $4 returned '$2', expected '$3'" + ((BAD++)) + fi +} + +for i in "-4 $TGT4" "-6 $TGT6"; do + for p in u i r; do + [ $p == "u" ] && prot=UDPv${i:1:2} + [ $p == "i" ] && prot=ICMPv${i:1:2} + [ $p == "r" ] && prot=RAWv${i:1:2} + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234) + check_result $? "$ts" "" "$prot - no options" + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t | wc -l) + check_result $? "$ts" "2" "$prot - ts cnt" + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t | + sed -n "s/.*SCHED ts0 [0-9].*/OK/p") + check_result $? "$ts" "OK" "$prot - ts0 SCHED" + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t | + sed -n "s/.*SND ts0 [0-9].*/OK/p") + check_result $? "$ts" "OK" "$prot - ts0 SND" + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d 1000 | + awk '/SND/ { if ($3 > 1000) print "OK"; }') + check_result $? "$ts" "OK" "$prot - TXTIME abs" + + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d 1000 | + awk '/SND/ {snd=$3} + /SCHED/ {sch=$3} + END { if (snd - sch > 500) print "OK"; }') + check_result $? "$ts" "OK" "$prot - TXTIME rel" + done +done + +# Summary +if [ $BAD -ne 0 ]; then + echo "FAIL - $BAD/$TOTAL cases failed" + exit 1 +else + echo "OK" + exit 0 +fi diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 3f4c8cfe7aca..47c4d4b4a44a 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -750,7 +750,7 @@ ipv4_ping_vrf() log_start show_hint "Fails since address on vrf device is out of device scope" run_cmd ping -c1 -w1 -I ${NSA_DEV} ${a} - log_test_addr ${a} $? 1 "ping local, device bind" + log_test_addr ${a} $? 2 "ping local, device bind" done # diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 43ea8407a82e..4f70baad867d 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -96,7 +96,7 @@ fib_rule6_del() fib_rule6_del_by_pref() { - pref=$($IP -6 rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + pref=$($IP -6 rule show $1 table $RTABLE | cut -d ":" -f 1) $IP -6 rule del pref $pref } @@ -104,17 +104,36 @@ fib_rule6_test_match_n_redirect() { local match="$1" local getmatch="$2" + local description="$3" $IP -6 rule add $match table $RTABLE $IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE" - log_test $? 0 "rule6 check: $1" + log_test $? 0 "rule6 check: $description" fib_rule6_del_by_pref "$match" - log_test $? 0 "rule6 del by pref: $match" + log_test $? 0 "rule6 del by pref: $description" +} + +fib_rule6_test_reject() +{ + local match="$1" + local rc + + $IP -6 rule add $match table $RTABLE 2>/dev/null + rc=$? + log_test $rc 2 "rule6 check: $match" + + if [ $rc -eq 0 ]; then + $IP -6 rule del $match table $RTABLE + fi } fib_rule6_test() { + local getmatch + local match + local cnt + # setup the fib rule redirect route $IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink @@ -124,8 +143,21 @@ fib_rule6_test() match="from $SRC_IP6 iif $DEV" fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table" + # Reject dsfield (tos) options which have ECN bits set + for cnt in $(seq 1 3); do + match="dsfield $cnt" + fib_rule6_test_reject "$match" + done + + # Don't take ECN bits into account when matching on dsfield match="tos 0x10" - fib_rule6_test_match_n_redirect "$match" "$match" "tos redirect to table" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + # Using option 'tos' instead of 'dsfield' as old iproute2 + # versions don't support 'dsfield' in ip rule show. + getmatch="tos $cnt" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getmatch redirect to table" + done match="fwmark 0x64" getmatch="mark 0x64" @@ -165,7 +197,7 @@ fib_rule4_del() fib_rule4_del_by_pref() { - pref=$($IP rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + pref=$($IP rule show $1 table $RTABLE | cut -d ":" -f 1) $IP rule del pref $pref } @@ -173,17 +205,36 @@ fib_rule4_test_match_n_redirect() { local match="$1" local getmatch="$2" + local description="$3" $IP rule add $match table $RTABLE $IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE" - log_test $? 0 "rule4 check: $1" + log_test $? 0 "rule4 check: $description" fib_rule4_del_by_pref "$match" - log_test $? 0 "rule4 del by pref: $match" + log_test $? 0 "rule4 del by pref: $description" +} + +fib_rule4_test_reject() +{ + local match="$1" + local rc + + $IP rule add $match table $RTABLE 2>/dev/null + rc=$? + log_test $rc 2 "rule4 check: $match" + + if [ $rc -eq 0 ]; then + $IP rule del $match table $RTABLE + fi } fib_rule4_test() { + local getmatch + local match + local cnt + # setup the fib rule redirect route $IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink @@ -192,14 +243,27 @@ fib_rule4_test() # need enable forwarding and disable rp_filter temporarily as all the # addresses are in the same subnet and egress device == ingress device. - ip netns exec testns sysctl -w net.ipv4.ip_forward=1 - ip netns exec testns sysctl -w net.ipv4.conf.$DEV.rp_filter=0 + ip netns exec testns sysctl -qw net.ipv4.ip_forward=1 + ip netns exec testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0 match="from $SRC_IP iif $DEV" fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table" - ip netns exec testns sysctl -w net.ipv4.ip_forward=0 + ip netns exec testns sysctl -qw net.ipv4.ip_forward=0 + + # Reject dsfield (tos) options which have ECN bits set + for cnt in $(seq 1 3); do + match="dsfield $cnt" + fib_rule4_test_reject "$match" + done + # Don't take ECN bits into account when matching on dsfield match="tos 0x10" - fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + # Using option 'tos' instead of 'dsfield' as old iproute2 + # versions don't support 'dsfield' in ip rule show. + getmatch="tos $cnt" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getmatch redirect to table" + done match="fwmark 0x64" getmatch="mark 0x64" diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 996af1ae3d3d..2271a8727f62 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,7 +9,7 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle" +TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh" VERBOSE=0 PAUSE_ON_FAIL=no @@ -988,12 +988,25 @@ ipv6_rt_replace() ipv6_rt_replace_mpath } +ipv6_rt_dsfield() +{ + echo + echo "IPv6 route with dsfield tests" + + run_cmd "$IP -6 route flush 2001:db8:102::/64" + + # IPv6 doesn't support routing based on dsfield + run_cmd "$IP -6 route add 2001:db8:102::/64 dsfield 0x04 via 2001:db8:101::2" + log_test $? 2 "Reject route with dsfield" +} + ipv6_route_test() { route_setup ipv6_rt_add ipv6_rt_replace + ipv6_rt_dsfield route_cleanup } @@ -1447,6 +1460,81 @@ ipv4_local_rt_cache() log_test $? 0 "Cached route removed from VRF port device" } +ipv4_rt_dsfield() +{ + echo + echo "IPv4 route with dsfield tests" + + run_cmd "$IP route flush 172.16.102.0/24" + + # New routes should reject dsfield options that interfere with ECN + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x01 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x01" + + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x02 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x02" + + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x03 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x03" + + # A generic route that doesn't take DSCP into account + run_cmd "$IP route add 172.16.102.0/24 via 172.16.101.2" + + # A more specific route for DSCP 0x10 + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x10 via 172.16.103.2" + + # DSCP 0x10 should match the specific route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x10 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x11 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x12 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x13 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:CE" + + # Unknown DSCP should match the generic route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x14 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x15 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x16 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x17 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:CE" + + # Null DSCP should match the generic route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x00 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x01 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x02 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x03 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:CE" +} + ipv4_route_test() { route_setup @@ -1454,6 +1542,7 @@ ipv4_route_test() ipv4_rt_add ipv4_rt_replace ipv4_local_rt_cache + ipv4_rt_dsfield route_cleanup } @@ -1865,6 +1954,61 @@ ipv6_mangle_test() route_cleanup } +ip_neigh_get_check() +{ + ip neigh help 2>&1 | grep -q 'ip neigh get' + if [ $? -ne 0 ]; then + echo "iproute2 command does not support neigh get. Skipping test" + return 1 + fi + + return 0 +} + +ipv4_bcast_neigh_test() +{ + local rc + + echo + echo "IPv4 broadcast neighbour tests" + + ip_neigh_get_check || return 1 + + setup + + set -e + run_cmd "$IP neigh add 192.0.2.111 lladdr 00:11:22:33:44:55 nud perm dev dummy0" + run_cmd "$IP neigh add 192.0.2.255 lladdr 00:11:22:33:44:55 nud perm dev dummy0" + + run_cmd "$IP neigh get 192.0.2.111 dev dummy0" + run_cmd "$IP neigh get 192.0.2.255 dev dummy0" + + run_cmd "$IP address add 192.0.2.1/24 broadcast 192.0.2.111 dev dummy0" + + run_cmd "$IP neigh add 203.0.113.111 nud failed dev dummy0" + run_cmd "$IP neigh add 203.0.113.255 nud failed dev dummy0" + + run_cmd "$IP neigh get 203.0.113.111 dev dummy0" + run_cmd "$IP neigh get 203.0.113.255 dev dummy0" + + run_cmd "$IP address add 203.0.113.1/24 broadcast 203.0.113.111 dev dummy0" + set +e + + run_cmd "$IP neigh get 192.0.2.111 dev dummy0" + log_test $? 0 "Resolved neighbour for broadcast address" + + run_cmd "$IP neigh get 192.0.2.255 dev dummy0" + log_test $? 0 "Resolved neighbour for network broadcast address" + + run_cmd "$IP neigh get 203.0.113.111 dev dummy0" + log_test $? 2 "Unresolved neighbour for broadcast address" + + run_cmd "$IP neigh get 203.0.113.255 dev dummy0" + log_test $? 2 "Unresolved neighbour for network broadcast address" + + cleanup +} + ################################################################################ # usage @@ -1939,6 +2083,7 @@ do ipv4_route_v6_gw) ipv4_route_v6_gw_test;; ipv4_mangle) ipv4_mangle_test;; ipv6_mangle) ipv6_mangle_test;; + ipv4_bcast_neigh) ipv4_bcast_neigh_test;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 72ee644d47bf..8fa97ae9af9e 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0+ OR MIT TEST_PROGS = bridge_igmp.sh \ + bridge_locked_port.sh \ bridge_port_isolation.sh \ bridge_sticky_fdb.sh \ bridge_vlan_aware.sh \ diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh new file mode 100755 index 000000000000..5b02b6b60ce7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh @@ -0,0 +1,176 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="locked_port_ipv4 locked_port_ipv6 locked_port_vlan" +NUM_NETIFS=4 +CHECK_TC="no" +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64 + vlan_create $h1 100 v$h1 198.51.100.1/24 +} + +h1_destroy() +{ + vlan_destroy $h1 100 + simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/24 2001:db8:1::2/64 + vlan_create $h2 100 v$h2 198.51.100.2/24 +} + +h2_destroy() +{ + vlan_destroy $h2 100 + simple_if_fini $h2 192.0.2.2/24 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add dev br0 type bridge vlan_filtering 1 + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + bridge link set dev $swp1 learning off + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +locked_port_ipv4() +{ + RET=0 + + check_locked_port_support || return 0 + + ping_do $h1 192.0.2.2 + check_err $? "Ping did not work before locking port" + + bridge link set dev $swp1 locked on + + ping_do $h1 192.0.2.2 + check_fail $? "Ping worked after locking port, but before adding FDB entry" + + bridge fdb add `mac_get $h1` dev $swp1 master static + + ping_do $h1 192.0.2.2 + check_err $? "Ping did not work after locking port and adding FDB entry" + + bridge link set dev $swp1 locked off + bridge fdb del `mac_get $h1` dev $swp1 master static + + ping_do $h1 192.0.2.2 + check_err $? "Ping did not work after unlocking port and removing FDB entry." + + log_test "Locked port ipv4" +} + +locked_port_vlan() +{ + RET=0 + + check_locked_port_support || return 0 + + bridge vlan add vid 100 dev $swp1 + bridge vlan add vid 100 dev $swp2 + + ping_do $h1.100 198.51.100.2 + check_err $? "Ping through vlan did not work before locking port" + + bridge link set dev $swp1 locked on + ping_do $h1.100 198.51.100.2 + check_fail $? "Ping through vlan worked after locking port, but before adding FDB entry" + + bridge fdb add `mac_get $h1` dev $swp1 vlan 100 master static + + ping_do $h1.100 198.51.100.2 + check_err $? "Ping through vlan did not work after locking port and adding FDB entry" + + bridge link set dev $swp1 locked off + bridge fdb del `mac_get $h1` dev $swp1 vlan 100 master static + + ping_do $h1.100 198.51.100.2 + check_err $? "Ping through vlan did not work after unlocking port and removing FDB entry" + + bridge vlan del vid 100 dev $swp1 + bridge vlan del vid 100 dev $swp2 + log_test "Locked port vlan" +} + +locked_port_ipv6() +{ + RET=0 + check_locked_port_support || return 0 + + ping6_do $h1 2001:db8:1::2 + check_err $? "Ping6 did not work before locking port" + + bridge link set dev $swp1 locked on + + ping6_do $h1 2001:db8:1::2 + check_fail $? "Ping6 worked after locking port, but before adding FDB entry" + + bridge fdb add `mac_get $h1` dev $swp1 master static + ping6_do $h1 2001:db8:1::2 + check_err $? "Ping6 did not work after locking port and adding FDB entry" + + bridge link set dev $swp1 locked off + bridge fdb del `mac_get $h1` dev $swp1 master static + + ping6_do $h1 2001:db8:1::2 + check_err $? "Ping6 did not work after unlocking port and removing FDB entry" + + log_test "Locked port ipv6" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh index b90dff8d3a94..64bd00fe9a4f 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -28,8 +28,9 @@ h2_destroy() switch_create() { - # 10 Seconds ageing time. - ip link add dev br0 type bridge vlan_filtering 1 ageing_time 1000 \ + ip link add dev br0 type bridge \ + vlan_filtering 1 \ + ageing_time $LOW_AGEING_TIME \ mcast_snooping 0 ip link set dev $swp1 master br0 diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh index c15c6c85c984..1c8a26046589 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh @@ -27,8 +27,9 @@ h2_destroy() switch_create() { - # 10 Seconds ageing time. - ip link add dev br0 type bridge ageing_time 1000 mcast_snooping 0 + ip link add dev br0 type bridge \ + ageing_time $LOW_AGEING_TIME \ + mcast_snooping 0 ip link set dev $swp1 master br0 ip link set dev $swp2 master br0 diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh index e134a5f529c9..1b3b46292179 100644 --- a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh +++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh @@ -99,15 +99,15 @@ fib_ipv4_tos_test() fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false check_err $? "Route not in hardware when should" - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 2 metric 1024 - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 2 metric 1024" false + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 8 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 8 metric 1024" false check_err $? "Highest TOS route not in hardware when should" fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true check_err $? "Lowest TOS route still in hardware when should not" - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 metric 1024 - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1 metric 1024" true + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 4 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 4 metric 1024" true check_err $? "Middle TOS route in hardware when should not" log_test "IPv4 routes with TOS" @@ -277,11 +277,11 @@ fib_ipv4_replay_tos_test() ip -n $ns link set dev dummy1 up ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 4 devlink -N $ns dev reload $devlink_dev - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1" false + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 4" false check_err $? "Highest TOS route not in hardware when should" fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0" true diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index b0980a2efa31..4a546509de90 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -41,6 +41,8 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# Minimum ageing_time (in centiseconds) supported by hardware +LOW_AGEING_TIME=1000 # Flag for tc match, supposed to be skip_sw/skip_hw which means do not process # filter by software/hardware TC_FLAG=skip_hw diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh new file mode 100755 index 000000000000..1c11c4256d06 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3.sh @@ -0,0 +1,332 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +----------------------+ +# | H1 | | H2 | +# | | | | +# | $h1.200 + | | + $h2.200 | +# | 192.0.2.1/28 | | | | 192.0.2.18/28 | +# | 2001:db8:1::1/64 | | | | 2001:db8:2::1/64 | +# | | | | | | +# | $h1 + | | + $h2 | +# | | | | | | +# +------------------|-+ +-|--------------------+ +# | | +# +------------------|-------------------------|--------------------+ +# | SW | | | +# | | | | +# | $rp1 + + $rp2 | +# | | | | +# | $rp1.200 + + $rp2.200 | +# | 192.0.2.2/28 192.0.2.17/28 | +# | 2001:db8:1::2/64 2001:db8:2::2/64 | +# | | +# +-----------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + test_stats_rx_ipv4 + test_stats_tx_ipv4 + test_stats_rx_ipv6 + test_stats_tx_ipv6 + respin_enablement + test_stats_rx_ipv4 + test_stats_tx_ipv4 + test_stats_rx_ipv6 + test_stats_tx_ipv6 + reapply_config + ping_ipv4 + ping_ipv6 + test_stats_rx_ipv4 + test_stats_tx_ipv4 + test_stats_rx_ipv6 + test_stats_tx_ipv6 + test_stats_report_rx + test_stats_report_tx + test_destroy_enabled + test_double_enable +" +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 200 v$h1 192.0.2.1/28 2001:db8:1::1/64 + ip route add 192.0.2.16/28 vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2 + ip route del 192.0.2.16/28 vrf v$h1 nexthop via 192.0.2.2 + vlan_destroy $h1 200 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + vlan_create $h2 200 v$h2 192.0.2.18/28 2001:db8:2::1/64 + ip route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.17 + ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::2 +} + +h2_destroy() +{ + ip -6 route del 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::2 + ip route del 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.17 + vlan_destroy $h2 200 + simple_if_fini $h2 +} + +router_rp1_200_create() +{ + ip link add name $rp1.200 up \ + link $rp1 addrgenmode eui64 type vlan id 200 + ip address add dev $rp1.200 192.0.2.2/28 + ip address add dev $rp1.200 2001:db8:1::2/64 + ip stats set dev $rp1.200 l3_stats on +} + +router_rp1_200_destroy() +{ + ip stats set dev $rp1.200 l3_stats off + ip address del dev $rp1.200 2001:db8:1::2/64 + ip address del dev $rp1.200 192.0.2.2/28 + ip link del dev $rp1.200 +} + +router_create() +{ + ip link set dev $rp1 up + router_rp1_200_create + + ip link set dev $rp2 up + vlan_create $rp2 200 "" 192.0.2.17/28 2001:db8:2::2/64 +} + +router_destroy() +{ + vlan_destroy $rp2 200 + ip link set dev $rp2 down + + router_rp1_200_destroy + ip link set dev $rp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp1=${NETIFS[p2]} + + rp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + rp1mac=$(mac_get $rp1) + rp2mac=$(mac_get $rp2) + + vrf_prepare + + h1_create + h2_create + + router_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + router_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.200 192.0.2.18 " IPv4" +} + +ping_ipv6() +{ + ping_test $h1.200 2001:db8:2::1 " IPv6" +} + +get_l3_stat() +{ + local selector=$1; shift + + ip -j stats show dev $rp1.200 group offload subgroup l3_stats | + jq '.[0].stats64.'$selector +} + +send_packets_rx_ipv4() +{ + # Send 21 packets instead of 20, because the first one might trap and go + # through the SW datapath, which might not bump the HW counter. + $MZ $h1.200 -c 21 -d 20msec -p 100 \ + -a own -b $rp1mac -A 192.0.2.1 -B 192.0.2.18 \ + -q -t udp sp=54321,dp=12345 +} + +send_packets_rx_ipv6() +{ + $MZ $h1.200 -6 -c 21 -d 20msec -p 100 \ + -a own -b $rp1mac -A 2001:db8:1::1 -B 2001:db8:2::1 \ + -q -t udp sp=54321,dp=12345 +} + +send_packets_tx_ipv4() +{ + $MZ $h2.200 -c 21 -d 20msec -p 100 \ + -a own -b $rp2mac -A 192.0.2.18 -B 192.0.2.1 \ + -q -t udp sp=54321,dp=12345 +} + +send_packets_tx_ipv6() +{ + $MZ $h2.200 -6 -c 21 -d 20msec -p 100 \ + -a own -b $rp2mac -A 2001:db8:2::1 -B 2001:db8:1::1 \ + -q -t udp sp=54321,dp=12345 +} + +___test_stats() +{ + local dir=$1; shift + local prot=$1; shift + + local a + local b + + a=$(get_l3_stat ${dir}.packets) + send_packets_${dir}_${prot} + "$@" + b=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $a + 20" \ + get_l3_stat ${dir}.packets) + check_err $? "Traffic not reflected in the counter: $a -> $b" +} + +__test_stats() +{ + local dir=$1; shift + local prot=$1; shift + + RET=0 + ___test_stats "$dir" "$prot" + log_test "Test $dir packets: $prot" +} + +test_stats_rx_ipv4() +{ + __test_stats rx ipv4 +} + +test_stats_tx_ipv4() +{ + __test_stats tx ipv4 +} + +test_stats_rx_ipv6() +{ + __test_stats rx ipv6 +} + +test_stats_tx_ipv6() +{ + __test_stats tx ipv6 +} + +# Make sure everything works well even after stats have been disabled and +# reenabled on the same device without touching the L3 configuration. +respin_enablement() +{ + log_info "Turning stats off and on again" + ip stats set dev $rp1.200 l3_stats off + ip stats set dev $rp1.200 l3_stats on +} + +# For the initial run, l3_stats is enabled on a completely set up netdevice. Now +# do it the other way around: enabling the L3 stats on an L2 netdevice, and only +# then apply the L3 configuration. +reapply_config() +{ + log_info "Reapplying configuration" + + router_rp1_200_destroy + + ip link add name $rp1.200 link $rp1 addrgenmode none type vlan id 200 + ip stats set dev $rp1.200 l3_stats on + ip link set dev $rp1.200 up addrgenmode eui64 + ip address add dev $rp1.200 192.0.2.2/28 + ip address add dev $rp1.200 2001:db8:1::2/64 +} + +__test_stats_report() +{ + local dir=$1; shift + local prot=$1; shift + + local a + local b + + RET=0 + + a=$(get_l3_stat ${dir}.packets) + send_packets_${dir}_${prot} + ip address flush dev $rp1.200 + b=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $a + 20" \ + get_l3_stat ${dir}.packets) + check_err $? "Traffic not reflected in the counter: $a -> $b" + log_test "Test ${dir} packets: stats pushed on loss of L3" + + ip stats set dev $rp1.200 l3_stats off + ip link del dev $rp1.200 + router_rp1_200_create +} + +test_stats_report_rx() +{ + __test_stats_report rx ipv4 +} + +test_stats_report_tx() +{ + __test_stats_report tx ipv4 +} + +test_destroy_enabled() +{ + RET=0 + + ip link del dev $rp1.200 + router_rp1_200_create + + log_test "Destroy l3_stats-enabled netdev" +} + +test_double_enable() +{ + RET=0 + ___test_stats rx ipv4 \ + ip stats set dev $rp1.200 l3_stats on + log_test "Test stat retention across a spurious enablement" +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7da783d6f453..664b9ecaf228 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -24,6 +24,7 @@ PING_COUNT=${PING_COUNT:=10} PING_TIMEOUT=${PING_TIMEOUT:=5} WAIT_TIMEOUT=${WAIT_TIMEOUT:=20} INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600} +LOW_AGEING_TIME=${LOW_AGEING_TIME:=1000} REQUIRE_JQ=${REQUIRE_JQ:=yes} REQUIRE_MZ=${REQUIRE_MZ:=yes} @@ -125,6 +126,14 @@ check_ethtool_lanes_support() fi } +check_locked_port_support() +{ + if ! bridge -d link show | grep -q " locked"; then + echo "SKIP: iproute2 too old; Locked port feature not supported." + return $ksft_skip + fi +} + if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" exit $ksft_skip @@ -1489,3 +1498,63 @@ brmcast_check_sg_state() check_err_fail $should_fail $? "Entry $src has blocked flag" done } + +start_ip_monitor() +{ + local mtype=$1; shift + local ip=${1-ip}; shift + + # start the monitor in the background + tmpfile=`mktemp /var/run/nexthoptestXXX` + mpid=`($ip monitor $mtype > $tmpfile & echo $!) 2>/dev/null` + sleep 0.2 + echo "$mpid $tmpfile" +} + +stop_ip_monitor() +{ + local mpid=$1; shift + local tmpfile=$1; shift + local el=$1; shift + local what=$1; shift + + sleep 0.2 + kill $mpid + local lines=`grep '^\w' $tmpfile | wc -l` + test $lines -eq $el + check_err $? "$what: $lines lines of events, expected $el" + rm -rf $tmpfile +} + +hw_stats_monitor_test() +{ + local dev=$1; shift + local type=$1; shift + local make_suitable=$1; shift + local make_unsuitable=$1; shift + local ip=${1-ip}; shift + + RET=0 + + # Expect a notification about enablement. + local ipmout=$(start_ip_monitor stats "$ip") + $ip stats set dev $dev ${type}_stats on + stop_ip_monitor $ipmout 1 "${type}_stats enablement" + + # Expect a notification about offload. + local ipmout=$(start_ip_monitor stats "$ip") + $make_suitable + stop_ip_monitor $ipmout 1 "${type}_stats installation" + + # Expect a notification about loss of offload. + local ipmout=$(start_ip_monitor stats "$ip") + $make_unsuitable + stop_ip_monitor $ipmout 1 "${type}_stats deinstallation" + + # Expect a notification about disablement + local ipmout=$(start_ip_monitor stats "$ip") + $ip stats set dev $dev ${type}_stats off + stop_ip_monitor $ipmout 1 "${type}_stats disablement" + + log_test "${type}_stats notifications" +} diff --git a/tools/testing/selftests/net/forwarding/pedit_ip.sh b/tools/testing/selftests/net/forwarding/pedit_ip.sh new file mode 100755 index 000000000000..d14efb2d23b2 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/pedit_ip.sh @@ -0,0 +1,201 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test sends traffic from H1 to H2. Either on ingress of $swp1, or on +# egress of $swp2, the traffic is acted upon by a pedit action. An ingress +# filter installed on $h2 verifies that the packet looks like expected. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +----|-----------------+ +----------------|-----+ +# | | +# +----|----------------------------------------------------------------|-----+ +# | SW | | | +# | +-|----------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +--------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + test_ip4_src + test_ip4_dst + test_ip6_src + test_ip6_dst +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 up type bridge vlan_filtering 1 + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + tc qdisc del dev $swp1 clsact + + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h2mac=$(mac_get $h2) + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +do_test_pedit_ip() +{ + local pedit_locus=$1; shift + local pedit_action=$1; shift + local match_prot=$1; shift + local match_flower=$1; shift + local mz_flags=$1; shift + + tc filter add $pedit_locus handle 101 pref 1 \ + flower action pedit ex munge $pedit_action + tc filter add dev $h2 ingress handle 101 pref 1 prot $match_prot \ + flower skip_hw $match_flower action pass + + RET=0 + + $MZ $mz_flags $h1 -c 10 -d 20msec -p 100 -a own -b $h2mac -q -t ip + + local pkts + pkts=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= 10" \ + tc_rule_handle_stats_get "dev $h2 ingress" 101) + check_err $? "Expected to get 10 packets, but got $pkts." + + pkts=$(tc_rule_handle_stats_get "$pedit_locus" 101) + ((pkts >= 10)) + check_err $? "Expected to get 10 packets on pedit rule, but got $pkts." + + log_test "$pedit_locus pedit $pedit_action" + + tc filter del dev $h2 ingress pref 1 + tc filter del $pedit_locus pref 1 +} + +do_test_pedit_ip6() +{ + local locus=$1; shift + local pedit_addr=$1; shift + local flower_addr=$1; shift + + do_test_pedit_ip "$locus" "$pedit_addr set 2001:db8:2::1" ipv6 \ + "$flower_addr 2001:db8:2::1" \ + "-6 -A 2001:db8:1::1 -B 2001:db8:1::2" +} + +do_test_pedit_ip4() +{ + local locus=$1; shift + local pedit_addr=$1; shift + local flower_addr=$1; shift + + do_test_pedit_ip "$locus" "$pedit_addr set 198.51.100.1" ip \ + "$flower_addr 198.51.100.1" \ + "-A 192.0.2.1 -B 192.0.2.2" +} + +test_ip4_src() +{ + do_test_pedit_ip4 "dev $swp1 ingress" "ip src" src_ip + do_test_pedit_ip4 "dev $swp2 egress" "ip src" src_ip +} + +test_ip4_dst() +{ + do_test_pedit_ip4 "dev $swp1 ingress" "ip dst" dst_ip + do_test_pedit_ip4 "dev $swp2 egress" "ip dst" dst_ip +} + +test_ip6_src() +{ + do_test_pedit_ip6 "dev $swp1 ingress" "ip6 src" src_ip + do_test_pedit_ip6 "dev $swp2 egress" "ip6 src" src_ip +} + +test_ip6_dst() +{ + do_test_pedit_ip6 "dev $swp1 ingress" "ip6 dst" dst_ip + do_test_pedit_ip6 "dev $swp2 egress" "ip6 dst" dst_ip +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh index 4f9f17cb45d6..0a51eef21b9e 100755 --- a/tools/testing/selftests/net/forwarding/tc_police.sh +++ b/tools/testing/selftests/net/forwarding/tc_police.sh @@ -37,6 +37,8 @@ ALL_TESTS=" police_tx_mirror_test police_pps_rx_test police_pps_tx_test + police_mtu_rx_test + police_mtu_tx_test " NUM_NETIFS=6 source tc_common.sh @@ -346,6 +348,56 @@ police_pps_tx_test() tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower } +police_mtu_common_test() { + RET=0 + + local test_name=$1; shift + local dev=$1; shift + local direction=$1; shift + + tc filter add dev $dev $direction protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action police mtu 1042 conform-exceed drop/ok + + # to count "conform" packets + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ + action drop + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=54321 -p 1001 -c 10 -q + + mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ + -t udp sp=12345,dp=54321 -p 1000 -c 3 -q + + tc_check_packets "dev $dev $direction" 101 13 + check_err $? "wrong packet counter" + + # "exceed" packets + local overlimits_t0=$(tc_rule_stats_get ${dev} 1 ${direction} .overlimits) + test ${overlimits_t0} = 10 + check_err $? "wrong overlimits, expected 10 got ${overlimits_t0}" + + # "conform" packets + tc_check_packets "dev $h2 ingress" 101 3 + check_err $? "forwarding error" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $dev $direction protocol ip pref 1 handle 101 flower + + log_test "$test_name" +} + +police_mtu_rx_test() +{ + police_mtu_common_test "police mtu (rx)" $rp1 ingress +} + +police_mtu_tx_test() +{ + police_mtu_common_test "police mtu (tx)" $rp2 egress +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index f0f4ab96b8f3..621af6895f4d 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -432,6 +432,8 @@ do_transfer() local stat_ackrx_last_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") local stat_cookietx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent") local stat_cookierx_last=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv") + local stat_csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local stat_csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -524,6 +526,23 @@ do_transfer() fi fi + if $checksum; then + local csum_err_s=$(get_mib_counter "${listener_ns}" "MPTcpExtDataCsumErr") + local csum_err_c=$(get_mib_counter "${connector_ns}" "MPTcpExtDataCsumErr") + + local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) + if [ $csum_err_s_nr -gt 0 ]; then + printf "[ FAIL ]\nserver got $csum_err_s_nr data checksum error[s]" + rets=1 + fi + + local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) + if [ $csum_err_c_nr -gt 0 ]; then + printf "[ FAIL ]\nclient got $csum_err_c_nr data checksum error[s]" + retc=1 + fi + fi + if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then printf "[ OK ]" fi diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 0c8a2a20b96c..7314257d248a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1,6 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + ret=0 sin="" sinfail="" @@ -9,15 +14,28 @@ cin="" cinfail="" cinsent="" cout="" +capout="" +ns1="" +ns2="" ksft_skip=4 timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) -mptcp_connect="" capture=0 checksum=0 -do_all_tests=1 - +ip_mptcp=0 +check_invert=0 +validate_checksum=0 +init=0 + +declare -A all_tests +declare -a only_tests_ids +declare -a only_tests_names +declare -A failed_tests TEST_COUNT=0 +TEST_NAME="" +nr_blank=40 + +export FAILING_LINKS="" # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) || # (ip6 && (ip6[74] & 0xf0) == 0x30)'" @@ -37,16 +55,18 @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14, 6 0 0 65535, 6 0 0 0" -init() +init_partial() { capout=$(mktemp) - rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) + local rndh + rndh=$(mktemp -u XXXXXX) ns1="ns1-$rndh" ns2="ns2-$rndh" - for netns in "$ns1" "$ns2";do + local netns + for netns in "$ns1" "$ns2"; do ip netns add $netns || exit $ksft_skip ip -net $netns link set lo up ip netns exec $netns sysctl -q net.mptcp.enabled=1 @@ -57,13 +77,18 @@ init() fi done - # ns1 ns2 + check_invert=0 + validate_checksum=$checksum + FAILING_LINKS="" + + # ns1 ns2 # ns1eth1 ns2eth1 # ns1eth2 ns2eth2 # ns1eth3 ns2eth3 # ns1eth4 ns2eth4 - for i in `seq 1 4`; do + local i + for i in $(seq 1 4); do ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2" ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad @@ -81,7 +106,8 @@ init() init_shapers() { - for i in `seq 1 4`; do + local i + for i in $(seq 1 4); do tc -n $ns1 qdisc add dev ns1eth$i root netem rate 20mbit delay 1 tc -n $ns2 qdisc add dev ns2eth$i root netem rate 20mbit delay 1 done @@ -91,12 +117,48 @@ cleanup_partial() { rm -f "$capout" + local netns for netns in "$ns1" "$ns2"; do ip netns del $netns rm -f /tmp/$netns.{nstat,out} done } +check_tools() +{ + if ! ip -Version &> /dev/null; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip + fi + + if ! iptables -V &> /dev/null; then + echo "SKIP: Could not run all tests without iptables tool" + exit $ksft_skip + fi + + if ! ip6tables -V &> /dev/null; then + echo "SKIP: Could not run all tests without ip6tables tool" + exit $ksft_skip + fi +} + +init() { + init=1 + + check_tools + + sin=$(mktemp) + sout=$(mktemp) + cin=$(mktemp) + cinsent=$(mktemp) + cout=$(mktemp) + + trap cleanup EXIT + + make_file "$cin" "client" 1 + make_file "$sin" "server" 1 +} + cleanup() { rm -f "$cin" "$cout" "$sinfail" @@ -104,33 +166,73 @@ cleanup() cleanup_partial } +skip_test() +{ + if [ "${#only_tests_ids[@]}" -eq 0 ] && [ "${#only_tests_names[@]}" -eq 0 ]; then + return 1 + fi + + local i + for i in "${only_tests_ids[@]}"; do + if [ "${TEST_COUNT}" -eq "${i}" ]; then + return 1 + fi + done + for i in "${only_tests_names[@]}"; do + if [ "${TEST_NAME}" = "${i}" ]; then + return 1 + fi + done + + return 0 +} + +# $1: test name reset() { - cleanup_partial - init + TEST_NAME="${1}" + + TEST_COUNT=$((TEST_COUNT+1)) + + if skip_test; then + return 1 + fi + + if [ "${init}" != "1" ]; then + init + else + cleanup_partial + fi + + init_partial + + return 0 } +# $1: test name reset_with_cookies() { - reset + reset "${1}" || return 1 - for netns in "$ns1" "$ns2";do + local netns + for netns in "$ns1" "$ns2"; do ip netns exec $netns sysctl -q net.ipv4.tcp_syncookies=2 done } +# $1: test name reset_with_add_addr_timeout() { - local ip="${1:-4}" + local ip="${2:-4}" local tables + reset "${1}" || return 1 + tables="iptables" if [ $ip -eq 6 ]; then tables="ip6tables" fi - reset - ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 ip netns exec $ns2 $tables -A OUTPUT -p tcp \ -m tcp --tcp-option 30 \ @@ -139,45 +241,45 @@ reset_with_add_addr_timeout() -j DROP } +# $1: test name reset_with_checksum() { local ns1_enable=$1 local ns2_enable=$2 - reset + reset "checksum test ${1} ${2}" || return 1 ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=$ns1_enable ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=$ns2_enable + + validate_checksum=1 } reset_with_allow_join_id0() { - local ns1_enable=$1 - local ns2_enable=$2 + local ns1_enable=$2 + local ns2_enable=$3 - reset + reset "${1}" || return 1 ip netns exec $ns1 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns1_enable ip netns exec $ns2 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns2_enable } -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi - -iptables -V > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run all tests without iptables tool" - exit $ksft_skip -fi +fail_test() +{ + ret=1 + failed_tests[${TEST_COUNT}]="${TEST_NAME}" +} -ip6tables -V > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run all tests without ip6tables tool" - exit $ksft_skip -fi +get_failed_tests_ids() +{ + # sorted + local i + for i in "${!failed_tests[@]}"; do + echo "${i}" + done | sort -n +} print_file_err() { @@ -188,47 +290,53 @@ print_file_err() check_transfer() { - in=$1 - out=$2 - what=$3 - - cmp "$in" "$out" > /dev/null 2>&1 - if [ $? -ne 0 ] ;then - echo "[ FAIL ] $what does not match (in, out):" - print_file_err "$in" - print_file_err "$out" - ret=1 - - return 1 - fi + local in=$1 + local out=$2 + local what=$3 + local i a b + + local line + cmp -l "$in" "$out" | while read -r i a b; do + local sum=$((0${a} + 0${b})) + if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then + echo "[ FAIL ] $what does not match (in, out):" + print_file_err "$in" + print_file_err "$out" + fail_test + + return 1 + else + echo "$what has inverted byte at ${i}" + fi + done return 0 } do_ping() { - listener_ns="$1" - connector_ns="$2" - connect_addr="$3" + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" - ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null - if [ $? -ne 0 ] ; then + if ! ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null; then echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2 - ret=1 + fail_test fi } link_failure() { - ns="$1" + local ns="$1" if [ -z "$FAILING_LINKS" ]; then l=$((RANDOM%4)) FAILING_LINKS=$((l+1)) fi + local l for l in $FAILING_LINKS; do - veth="ns1eth$l" + local veth="ns1eth$l" ip -net "$ns" link set "$veth" down done } @@ -245,9 +353,10 @@ wait_local_port_listen() local listener_ns="${1}" local port="${2}" - local port_hex i - + local port_hex port_hex="$(printf "%04X" "${port}")" + + local i for i in $(seq 10); do ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && @@ -258,7 +367,7 @@ wait_local_port_listen() rm_addr_count() { - ns=${1} + local ns=${1} ip netns exec ${ns} nstat -as | grep MPTcpExtRmAddr | awk '{print $2}' } @@ -269,8 +378,8 @@ wait_rm_addr() local ns="${1}" local old_cnt="${2}" local cnt - local i + local i for i in $(seq 10); do cnt=$(rm_addr_count ${ns}) [ "$cnt" = "${old_cnt}" ] || break @@ -278,27 +387,227 @@ wait_rm_addr() done } +wait_mpj() +{ + local ns="${1}" + local cnt old_cnt + + old_cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + + local i + for i in $(seq 10); do + cnt=$(ip netns exec ${ns} nstat -as | grep MPJoinAckRx | awk '{print $2}') + [ "$cnt" = "${old_cnt}" ] || break + sleep 0.1 + done +} + +pm_nl_set_limits() +{ + local ns=$1 + local addrs=$2 + local subflows=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp limits set add_addr_accepted $addrs subflows $subflows + else + ip netns exec $ns ./pm_nl_ctl limits $addrs $subflows + fi +} + +pm_nl_add_endpoint() +{ + local ns=$1 + local addr=$2 + local flags _flags + local port _port + local dev _dev + local id _id + local nr=2 + + local p + for p in "${@}" + do + if [ $p = "flags" ]; then + eval _flags=\$"$nr" + [ -n "$_flags" ]; flags="flags $_flags" + fi + if [ $p = "dev" ]; then + eval _dev=\$"$nr" + [ -n "$_dev" ]; dev="dev $_dev" + fi + if [ $p = "id" ]; then + eval _id=\$"$nr" + [ -n "$_id" ]; id="id $_id" + fi + if [ $p = "port" ]; then + eval _port=\$"$nr" + [ -n "$_port" ]; port="port $_port" + fi + + nr=$((nr + 1)) + done + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint add $addr ${_flags//","/" "} $dev $id $port + else + ip netns exec $ns ./pm_nl_ctl add $addr $flags $dev $id $port + fi +} + +pm_nl_del_endpoint() +{ + local ns=$1 + local id=$2 + local addr=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint delete id $id $addr + else + ip netns exec $ns ./pm_nl_ctl del $id $addr + fi +} + +pm_nl_flush_endpoint() +{ + local ns=$1 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint flush + else + ip netns exec $ns ./pm_nl_ctl flush + fi +} + +pm_nl_show_endpoints() +{ + local ns=$1 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint show + else + ip netns exec $ns ./pm_nl_ctl dump + fi +} + +pm_nl_change_endpoint() +{ + local ns=$1 + local id=$2 + local flags=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint change id $id ${flags//","/" "} + else + ip netns exec $ns ./pm_nl_ctl set id $id flags $flags + fi +} + +pm_nl_check_endpoint() +{ + local line expected_line + local need_title=$1 + local msg="$2" + local ns=$3 + local addr=$4 + local _flags="" + local flags + local _port + local port + local dev + local _id + local id + + if [ "${need_title}" = 1 ]; then + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" + else + printf "%-${nr_blank}s %s" " " "${msg}" + fi + + shift 4 + while [ -n "$1" ]; do + if [ $1 = "flags" ]; then + _flags=$2 + [ -n "$_flags" ]; flags="flags $_flags" + shift + elif [ $1 = "dev" ]; then + [ -n "$2" ]; dev="dev $1" + shift + elif [ $1 = "id" ]; then + _id=$2 + [ -n "$_id" ]; id="id $_id" + shift + elif [ $1 = "port" ]; then + _port=$2 + [ -n "$_port" ]; port=" port $_port" + shift + fi + + shift + done + + if [ -z "$id" ]; then + echo "[skip] bad test - missing endpoint id" + return + fi + + if [ $ip_mptcp -eq 1 ]; then + line=$(ip -n $ns mptcp endpoint show $id) + # the dump order is: address id flags port dev + expected_line="$addr" + [ -n "$addr" ] && expected_line="$expected_line $addr" + expected_line="$expected_line $id" + [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" + [ -n "$dev" ] && expected_line="$expected_line $dev" + [ -n "$port" ] && expected_line="$expected_line $port" + else + line=$(ip netns exec $ns ./pm_nl_ctl get $_id) + # the dump order is: id flags dev address port + expected_line="$id" + [ -n "$flags" ] && expected_line="$expected_line $flags" + [ -n "$dev" ] && expected_line="$expected_line $dev" + [ -n "$addr" ] && expected_line="$expected_line $addr" + [ -n "$_port" ] && expected_line="$expected_line $_port" + fi + if [ "$line" = "$expected_line" ]; then + echo "[ ok ]" + else + echo "[fail] expected '$expected_line' found '$line'" + fail_test + fi +} + +filter_tcp_from() +{ + local ns="${1}" + local src="${2}" + local target="${3}" + + ip netns exec "${ns}" iptables -A INPUT -s "${src}" -p tcp -j "${target}" +} + do_transfer() { - listener_ns="$1" - connector_ns="$2" - cl_proto="$3" - srv_proto="$4" - connect_addr="$5" - test_link_fail="$6" - addr_nr_ns1="$7" - addr_nr_ns2="$8" - speed="$9" - bkup="${10}" - - port=$((10000+$TEST_COUNT)) - TEST_COUNT=$((TEST_COUNT+1)) + local listener_ns="$1" + local connector_ns="$2" + local cl_proto="$3" + local srv_proto="$4" + local connect_addr="$5" + local test_link_fail="$6" + local addr_nr_ns1="$7" + local addr_nr_ns2="$8" + local speed="$9" + local sflags="${10}" + + local port=$((10000 + TEST_COUNT - 1)) + local cappid :> "$cout" :> "$sout" :> "$capout" if [ $capture -eq 1 ]; then + local capuser if [ -z $SUDO_USER ] ; then capuser="" else @@ -319,12 +628,19 @@ do_transfer() NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ nstat -n + local extra_args if [ $speed = "fast" ]; then - mptcp_connect="./mptcp_connect -j" + extra_args="-j" elif [ $speed = "slow" ]; then - mptcp_connect="./mptcp_connect -r 50" - elif [ $speed = "least" ]; then - mptcp_connect="./mptcp_connect -r 10" + extra_args="-r 50" + elif [[ $speed = "speed_"* ]]; then + extra_args="-r ${speed:6}" + fi + + if [[ "${addr_nr_ns2}" = "fastclose_"* ]]; then + # disconnect + extra_args="$extra_args -I ${addr_nr_ns2:10}" + addr_nr_ns2=0 fi local local_addr @@ -334,43 +650,51 @@ do_transfer() local_addr="0.0.0.0" fi - if [ "$test_link_fail" -eq 2 ];then + if [ "$test_link_fail" -gt 1 ];then timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - ${local_addr} < "$sinfail" > "$sout" & + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_args ${local_addr} < "$sinfail" > "$sout" & else timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - ${local_addr} < "$sin" > "$sout" & + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_args ${local_addr} < "$sin" > "$sout" & fi - spid=$! + local spid=$! wait_local_port_listen "${listener_ns}" "${port}" if [ "$test_link_fail" -eq 0 ];then timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $connect_addr < "$cin" > "$cout" & - else + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_args $connect_addr < "$cin" > "$cout" & + elif [ "$test_link_fail" -eq 1 ] || [ "$test_link_fail" -eq 2 ];then ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ tee "$cinsent" | \ timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $connect_addr > "$cout" & + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_args $connect_addr > "$cout" & + else + tee "$cinsent" < "$cinfail" | \ + timeout ${timeout_test} \ + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_args $connect_addr > "$cout" & fi - cpid=$! + local cpid=$! # let the mptcp subflow be established in background before # do endpoint manipulation - [ $addr_nr_ns1 = "0" -a $addr_nr_ns2 = "0" ] || sleep 1 + if [ $addr_nr_ns1 != "0" ] || [ $addr_nr_ns2 != "0" ]; then + sleep 1 + fi if [ $addr_nr_ns1 -gt 0 ]; then - let add_nr_ns1=addr_nr_ns1 - counter=2 + local counter=2 + local add_nr_ns1=${addr_nr_ns1} while [ $add_nr_ns1 -gt 0 ]; do local addr if is_v6 "${connect_addr}"; then @@ -378,35 +702,43 @@ do_transfer() else addr="10.0.$counter.1" fi - ip netns exec $ns1 ./pm_nl_ctl add $addr flags signal - let counter+=1 - let add_nr_ns1-=1 + pm_nl_add_endpoint $ns1 $addr flags signal + counter=$((counter + 1)) + add_nr_ns1=$((add_nr_ns1 - 1)) done elif [ $addr_nr_ns1 -lt 0 ]; then - let rm_nr_ns1=-addr_nr_ns1 + local rm_nr_ns1=$((-addr_nr_ns1)) if [ $rm_nr_ns1 -lt 8 ]; then - counter=1 - pos=1 - dump=(`ip netns exec ${listener_ns} ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - while [ $counter -le $rm_nr_ns1 ] - do - id=${dump[$pos]} - rm_addr=$(rm_addr_count ${connector_ns}) - ip netns exec ${listener_ns} ./pm_nl_ctl del $id - wait_rm_addr ${connector_ns} ${rm_addr} - let counter+=1 - let pos+=5 + local counter=0 + local line + pm_nl_show_endpoints ${listener_ns} | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word + local arr=($line) + local nr=0 + + local i + for i in "${arr[@]}"; do + if [ $i = "id" ]; then + if [ $counter -eq $rm_nr_ns1 ]; then + break + fi + id=${arr[$nr+1]} + rm_addr=$(rm_addr_count ${connector_ns}) + pm_nl_del_endpoint ${listener_ns} $id + wait_rm_addr ${connector_ns} ${rm_addr} + counter=$((counter + 1)) + fi + nr=$((nr + 1)) done - fi + done elif [ $rm_nr_ns1 -eq 8 ]; then - ip netns exec ${listener_ns} ./pm_nl_ctl flush + pm_nl_flush_endpoint ${listener_ns} elif [ $rm_nr_ns1 -eq 9 ]; then - ip netns exec ${listener_ns} ./pm_nl_ctl del 0 ${connect_addr} + pm_nl_del_endpoint ${listener_ns} 0 ${connect_addr} fi fi - flags="subflow" + local flags="subflow" if [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then flags="${flags},fullmesh" addr_nr_ns2=${addr_nr_ns2:9} @@ -414,11 +746,11 @@ do_transfer() # if newly added endpoints must be deleted, give the background msk # some time to created them - [ $addr_nr_ns1 -gt 0 -a $addr_nr_ns2 -lt 0 ] && sleep 1 + [ $addr_nr_ns1 -gt 0 ] && [ $addr_nr_ns2 -lt 0 ] && sleep 1 if [ $addr_nr_ns2 -gt 0 ]; then - let add_nr_ns2=addr_nr_ns2 - counter=3 + local add_nr_ns2=${addr_nr_ns2} + local counter=3 while [ $add_nr_ns2 -gt 0 ]; do local addr if is_v6 "${connect_addr}"; then @@ -426,30 +758,40 @@ do_transfer() else addr="10.0.$counter.2" fi - ip netns exec $ns2 ./pm_nl_ctl add $addr flags $flags - let counter+=1 - let add_nr_ns2-=1 + pm_nl_add_endpoint $ns2 $addr flags $flags + counter=$((counter + 1)) + add_nr_ns2=$((add_nr_ns2 - 1)) done elif [ $addr_nr_ns2 -lt 0 ]; then - let rm_nr_ns2=-addr_nr_ns2 + local rm_nr_ns2=$((-addr_nr_ns2)) if [ $rm_nr_ns2 -lt 8 ]; then - counter=1 - pos=1 - dump=(`ip netns exec ${connector_ns} ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - while [ $counter -le $rm_nr_ns2 ] - do - # rm_addr are serialized, allow the previous one to complete - id=${dump[$pos]} - rm_addr=$(rm_addr_count ${listener_ns}) - ip netns exec ${connector_ns} ./pm_nl_ctl del $id - wait_rm_addr ${listener_ns} ${rm_addr} - let counter+=1 - let pos+=5 + local counter=0 + local line + pm_nl_show_endpoints ${connector_ns} | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word + local arr=($line) + local nr=0 + + local i + for i in "${arr[@]}"; do + if [ $i = "id" ]; then + if [ $counter -eq $rm_nr_ns2 ]; then + break + fi + local id rm_addr + # rm_addr are serialized, allow the previous one to + # complete + id=${arr[$nr+1]} + rm_addr=$(rm_addr_count ${listener_ns}) + pm_nl_del_endpoint ${connector_ns} $id + wait_rm_addr ${listener_ns} ${rm_addr} + counter=$((counter + 1)) + fi + nr=$((nr + 1)) done - fi + done elif [ $rm_nr_ns2 -eq 8 ]; then - ip netns exec ${connector_ns} ./pm_nl_ctl flush + pm_nl_flush_endpoint ${connector_ns} elif [ $rm_nr_ns2 -eq 9 ]; then local addr if is_v6 "${connect_addr}"; then @@ -457,26 +799,38 @@ do_transfer() else addr="10.0.1.2" fi - ip netns exec ${connector_ns} ./pm_nl_ctl del 0 $addr + pm_nl_del_endpoint ${connector_ns} 0 $addr fi fi - if [ ! -z $bkup ]; then + if [ -n "${sflags}" ]; then sleep 1 + + local netns for netns in "$ns1" "$ns2"; do - dump=(`ip netns exec $netns ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - addr=${dump[${#dump[@]} - 1]} - backup="ip netns exec $netns ./pm_nl_ctl set $addr flags $bkup" - $backup - fi + local line + pm_nl_show_endpoints $netns | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word + local arr=($line) + local nr=0 + local id + + local i + for i in "${arr[@]}"; do + if [ $i = "id" ]; then + id=${arr[$nr+1]} + fi + nr=$((nr + 1)) + done + pm_nl_change_endpoint $netns $id $sflags + done done fi wait $cpid - retc=$? + local retc=$? wait $spid - rets=$? + local rets=$? if [ $capture -eq 1 ]; then sleep 1 @@ -498,11 +852,11 @@ do_transfer() cat /tmp/${connector_ns}.out cat "$capout" - ret=1 + fail_test return 1 fi - if [ "$test_link_fail" -eq 2 ];then + if [ "$test_link_fail" -gt 1 ];then check_transfer $sinfail $cout "file received by client" else check_transfer $sin $cout "file received by client" @@ -526,9 +880,9 @@ do_transfer() make_file() { - name=$1 - who=$2 - size=$3 + local name=$1 + local who=$2 + local size=$3 dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" @@ -538,33 +892,49 @@ make_file() run_tests() { - listener_ns="$1" - connector_ns="$2" - connect_addr="$3" - test_linkfail="${4:-0}" - addr_nr_ns1="${5:-0}" - addr_nr_ns2="${6:-0}" - speed="${7:-fast}" - bkup="${8:-""}" - lret=0 - oldin="" - + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local test_linkfail="${4:-0}" + local addr_nr_ns1="${5:-0}" + local addr_nr_ns2="${6:-0}" + local speed="${7:-fast}" + local sflags="${8:-""}" + + local size + + # The values above 2 are reused to make test files + # with the given sizes (KB) + if [ "$test_linkfail" -gt 2 ]; then + size=$test_linkfail + + if [ -z "$cinfail" ]; then + cinfail=$(mktemp) + fi + make_file "$cinfail" "client" $size # create the input file for the failure test when # the first failure test run - if [ "$test_linkfail" -ne 0 -a -z "$cinfail" ]; then + elif [ "$test_linkfail" -ne 0 ] && [ -z "$cinfail" ]; then # the client file must be considerably larger # of the maximum expected cwin value, or the # link utilization will be not predicable size=$((RANDOM%2)) size=$((size+1)) size=$((size*8192)) - size=$((size + ( $RANDOM % 8192) )) + size=$((size + ( RANDOM % 8192) )) cinfail=$(mktemp) make_file "$cinfail" "client" $size fi - if [ "$test_linkfail" -eq 2 -a -z "$sinfail" ]; then + if [ "$test_linkfail" -gt 2 ]; then + size=$test_linkfail + + if [ -z "$sinfail" ]; then + sinfail=$(mktemp) + fi + make_file "$sinfail" "server" $size + elif [ "$test_linkfail" -eq 2 ] && [ -z "$sinfail" ]; then size=$((RANDOM%16)) size=$((size+1)) size=$((size*2048)) @@ -574,8 +944,7 @@ run_tests() fi do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ - ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${bkup} - lret=$? + ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${sflags} } dump_stats() @@ -588,31 +957,40 @@ dump_stats() chk_csum_nr() { - local msg=${1:-""} + local csum_ns1=${1:-0} + local csum_ns2=${2:-0} local count local dump_stats + local allow_multi_errors_ns1=0 + local allow_multi_errors_ns2=0 - if [ ! -z "$msg" ]; then - printf "%02u" "$TEST_COUNT" - else - echo -n " " + if [[ "${csum_ns1}" = "+"* ]]; then + allow_multi_errors_ns1=1 + csum_ns1=${csum_ns1:1} + fi + if [[ "${csum_ns2}" = "+"* ]]; then + allow_multi_errors_ns2=1 + csum_ns2=${csum_ns2:1} fi - printf " %-36s %s" "$msg" "sum" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}'` + + printf "%-${nr_blank}s %s" " " "sum" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != 0 ]; then - echo "[fail] got $count data checksum error[s] expected 0" - ret=1 + if { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || + { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then + echo "[fail] got $count data checksum error[s] expected $csum_ns1" + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - csum " - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != 0 ]; then - echo "[fail] got $count data checksum error[s] expected 0" - ret=1 + if { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || + { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then + echo "[fail] got $count data checksum error[s] expected $csum_ns2" + fail_test dump_stats=1 else echo "[ ok ]" @@ -622,28 +1000,28 @@ chk_csum_nr() chk_fail_nr() { - local mp_fail_nr_tx=$1 - local mp_fail_nr_rx=$2 + local fail_tx=$1 + local fail_rx=$2 local count local dump_stats - printf "%-39s %s" " " "ftx" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "ftx" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != "$mp_fail_nr_tx" ]; then - echo "[fail] got $count MP_FAIL[s] TX expected $mp_fail_nr_tx" - ret=1 + if [ "$count" != "$fail_tx" ]; then + echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" + fail_test dump_stats=1 else echo -n "[ ok ]" fi - echo -n " - frx " - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}'` + echo -n " - failrx" + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != "$mp_fail_nr_rx" ]; then - echo "[fail] got $count MP_FAIL[s] RX expected $mp_fail_nr_rx" - ret=1 + if [ "$count" != "$fail_rx" ]; then + echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" + fail_test dump_stats=1 else echo "[ ok ]" @@ -652,30 +1030,115 @@ chk_fail_nr() [ "${dump_stats}" = 1 ] && dump_stats } +chk_fclose_nr() +{ + local fclose_tx=$1 + local fclose_rx=$2 + local count + local dump_stats + + printf "%-${nr_blank}s %s" " " "ctx" + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPFastcloseTx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$fclose_tx" ]; then + echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - fclzrx" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPFastcloseRx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$fclose_rx" ]; then + echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" + fail_test + dump_stats=1 + else + echo "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && dump_stats +} + +chk_rst_nr() +{ + local rst_tx=$1 + local rst_rx=$2 + local ns_invert=${3:-""} + local count + local dump_stats + local ns_tx=$ns1 + local ns_rx=$ns2 + local extra_msg="" + + if [[ $ns_invert = "invert" ]]; then + ns_tx=$ns2 + ns_rx=$ns1 + extra_msg=" invert" + fi + + printf "%-${nr_blank}s %s" " " "rtx" + count=$(ip netns exec $ns_tx nstat -as | grep MPTcpExtMPRstTx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$rst_tx" ]; then + echo "[fail] got $count MP_RST[s] TX expected $rst_tx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - rstrx " + count=$(ip netns exec $ns_rx nstat -as | grep MPTcpExtMPRstRx | awk '{print $2}') + [ -z "$count" ] && count=0 + if [ "$count" != "$rst_rx" ]; then + echo "[fail] got $count MP_RST[s] RX expected $rst_rx" + fail_test + dump_stats=1 + else + echo -n "[ ok ]" + fi + + [ "${dump_stats}" = 1 ] && dump_stats + + echo "$extra_msg" +} + chk_join_nr() { - local msg="$1" - local syn_nr=$2 - local syn_ack_nr=$3 - local ack_nr=$4 + local syn_nr=$1 + local syn_ack_nr=$2 + local ack_nr=$3 + local csum_ns1=${4:-0} + local csum_ns2=${5:-0} + local fail_nr=${6:-0} + local rst_nr=${7:-0} + local corrupted_pkts=${8:-0} local count local dump_stats local with_cookie + local title="${TEST_NAME}" + + if [ "${corrupted_pkts}" -gt 0 ]; then + title+=": ${corrupted_pkts} corrupted pkts" + fi - printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'` + printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - synack" - with_cookie=`ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies` - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}'` + with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_ack_nr" ]; then # simult connections exceeding the limit with cookie enabled could go up to @@ -685,7 +1148,7 @@ chk_join_nr() echo -n "[ ok ]" else echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" - ret=1 + fail_test dump_stats=1 fi else @@ -693,19 +1156,20 @@ chk_join_nr() fi echo -n " - ack" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" fi [ "${dump_stats}" = 1 ] && dump_stats if [ $checksum -eq 1 ]; then - chk_csum_nr - chk_fail_nr 0 0 + chk_csum_nr $csum_ns1 $csum_ns2 + chk_fail_nr $fail_nr $fail_nr + chk_rst_nr $rst_nr $rst_nr fi } @@ -724,19 +1188,19 @@ chk_stale_nr() local stale_nr local recover_nr - printf "%-39s %-18s" " " "stale" - stale_nr=`ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}'` + printf "%-${nr_blank}s %-18s" " " "stale" + stale_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}') [ -z "$stale_nr" ] && stale_nr=0 - recover_nr=`ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}'` + recover_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}') [ -z "$recover_nr" ] && recover_nr=0 if [ $stale_nr -lt $stale_min ] || - [ $stale_max -gt 0 -a $stale_nr -gt $stale_max ] || - [ $((stale_nr - $recover_nr)) -ne $stale_delta ]; then + { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } || + [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \ " expected stale in range [$stale_min..$stale_max]," \ " stale-recover delta $stale_delta " - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -763,28 +1227,28 @@ chk_add_nr() local dump_stats local timeout - timeout=`ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout` + timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) - printf "%-39s %s" " " "add" - count=`ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "add" + count=$(ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}') [ -z "$count" ] && count=0 # if the test configured a short timeout tolerate greater then expected # add addrs options, due to retransmissions - if [ "$count" != "$add_nr" ] && [ "$timeout" -gt 1 -o "$count" -lt "$add_nr" ]; then + if [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - echo " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" @@ -792,76 +1256,76 @@ chk_add_nr() if [ $port_nr -gt 0 ]; then echo -n " - pt " - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$port_nr" ]; then echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" fi - printf "%-39s %s" " " "syn" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | - awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "syn" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a different \ port-number expected $syn_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - synack" - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | - awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_ack_nr" ]; then echo "[fail] got $count JOIN[s] synack with a different \ port-number expected $syn_ack_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - ack" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | - awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a different \ port-number expected $ack_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" fi - printf "%-39s %s" " " "syn" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | - awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "syn" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mis_syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a mismatched \ port-number expected $mis_syn_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - ack " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | - awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mis_ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a mismatched \ port-number expected $mis_ack_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -877,43 +1341,75 @@ chk_rm_nr() { local rm_addr_nr=$1 local rm_subflow_nr=$2 - local invert=${3:-""} + local invert + local simult local count local dump_stats - local addr_ns - local subflow_ns + local addr_ns=$ns1 + local subflow_ns=$ns2 + local extra_msg="" + + shift 2 + while [ -n "$1" ]; do + [ "$1" = "invert" ] && invert=true + [ "$1" = "simult" ] && simult=true + shift + done if [ -z $invert ]; then addr_ns=$ns1 subflow_ns=$ns2 - elif [ $invert = "invert" ]; then + elif [ $invert = "true" ]; then addr_ns=$ns2 subflow_ns=$ns1 + extra_msg=" invert" fi - printf "%-39s %s" " " "rm " - count=`ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "rm " + count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi - echo -n " - sf " - count=`ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}'` + echo -n " - rmsf " + count=$(ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') [ -z "$count" ] && count=0 + if [ -n "$simult" ]; then + local cnt suffix + + cnt=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') + + # in case of simult flush, the subflow removal count on each side is + # unreliable + [ -z "$cnt" ] && cnt=0 + count=$((count + cnt)) + [ "$count" != "$rm_subflow_nr" ] && suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" + if [ $count -ge "$rm_subflow_nr" ] && \ + [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then + echo "[ ok ] $suffix" + else + echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" + fail_test + dump_stats=1 + fi + return + fi if [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" - ret=1 + fail_test dump_stats=1 else - echo "[ ok ]" + echo -n "[ ok ]" fi [ "${dump_stats}" = 1 ] && dump_stats + + echo "$extra_msg" } chk_prio_nr() @@ -923,23 +1419,23 @@ chk_prio_nr() local count local dump_stats - printf "%-39s %s" " " "ptx" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "ptx" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mp_prio_nr_tx" ]; then echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - prx " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mp_prio_nr_rx" ]; then echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -954,29 +1450,33 @@ chk_link_usage() local link=$2 local out=$3 local expected_rate=$4 - local tx_link=`ip netns exec $ns cat /sys/class/net/$link/statistics/tx_bytes` - local tx_total=`ls -l $out | awk '{print $5}'` - local tx_rate=$((tx_link * 100 / $tx_total)) + + local tx_link tx_total + tx_link=$(ip netns exec $ns cat /sys/class/net/$link/statistics/tx_bytes) + tx_total=$(stat --format=%s $out) + local tx_rate=$((tx_link * 100 / tx_total)) local tolerance=5 - printf "%-39s %-18s" " " "link usage" - if [ $tx_rate -lt $((expected_rate - $tolerance)) -o \ - $tx_rate -gt $((expected_rate + $tolerance)) ]; then + printf "%-${nr_blank}s %-18s" " " "link usage" + if [ $tx_rate -lt $((expected_rate - tolerance)) ] || \ + [ $tx_rate -gt $((expected_rate + tolerance)) ]; then echo "[fail] got $tx_rate% usage, expected $expected_rate%" - ret=1 + fail_test else echo "[ ok ]" fi } -wait_for_tw() +wait_attempt_fail() { local timeout_ms=$((timeout_poll * 1000)) local time=0 local ns=$1 while [ $time -lt $timeout_ms ]; do - local cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') + local cnt + + cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') [ "$cnt" = 1 ] && return 1 time=$((time + 100)) @@ -987,877 +1487,968 @@ wait_for_tw() subflows_tests() { - reset - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "no JOIN" "0" "0" "0" + if reset "no JOIN"; then + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # subflow limited by client - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow, limited by client" 0 0 0 + if reset "single subflow, limited by client"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 0 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # subflow limited by server - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow, limited by server" 1 1 0 + if reset "single subflow, limited by server"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 0 + fi # subflow - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow" 1 1 1 + if reset "single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # multiple subflows - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows" 2 2 2 + if reset "multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi # multiple subflows limited by server - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows, limited by server" 2 2 1 + if reset "multiple subflows, limited by server"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 1 + fi # single subflow, dev - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow dev ns2eth3 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow, dev" 1 1 1 + if reset "single subflow, dev"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow dev ns2eth3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi } subflows_error_tests() { # If a single subflow is configured, and matches the MPC src # address, no additional subflow should be created - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.1.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "no MPC reuse with single endpoint" 0 0 0 + if reset "no MPC reuse with single endpoint"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 0 0 0 + fi # multiple subflows, with subflow creation error - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "multi subflows, with failing subflow" 1 1 1 + if reset "multi subflows, with failing subflow"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + filter_tcp_from $ns1 10.0.3.2 REJECT + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + fi # multiple subflows, with subflow timeout on MPJ - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j DROP - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "multi subflows, with subflow timeout" 1 1 1 + if reset "multi subflows, with subflow timeout"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + filter_tcp_from $ns1 10.0.3.2 DROP + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + fi # multiple subflows, check that the endpoint corresponding to # closed subflow (due to reset) is not reused if additional # subflows are added later - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & - - # updates in the child shell do not have any effect here, we - # need to bump the test counter for the above case - TEST_COUNT=$((TEST_COUNT+1)) - - # mpj subflow will be in TW after the reset - wait_for_tw $ns2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - wait - - # additional subflow could be created only if the PM select - # the later endpoint, skipping the already used one - chk_join_nr "multi subflows, fair usage on close" 1 1 1 + if reset "multi subflows, fair usage on close"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + filter_tcp_from $ns1 10.0.3.2 REJECT + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + + # mpj subflow will be in TW after the reset + wait_attempt_fail $ns2 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + wait + + # additional subflow could be created only if the PM select + # the later endpoint, skipping the already used one + chk_join_nr 1 1 1 + fi } signal_address_tests() { # add_address, unused - reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "unused signal address" 0 0 0 - chk_add_nr 1 1 + if reset "unused signal address"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi # accept and use add_addr - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address" 1 1 1 - chk_add_nr 1 1 + if reset "signal address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # accept and use add_addr with an additional subflow # note: signal address in server ns and local addresses in client ns must # belong to different subnets or one of the listed local address could be # used for 'add_addr' subflow - reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and signal" 2 2 2 - chk_add_nr 1 1 + if reset "subflow and signal"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + fi # accept and use add_addr with additional subflows - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows and signal" 3 3 3 - chk_add_nr 1 1 + if reset "multiple subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi # signal addresses - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal addresses" 3 3 3 - chk_add_nr 3 3 + if reset "signal addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 3 3 + fi # signal invalid addresses - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal invalid addresses" 1 1 1 - chk_add_nr 3 3 + if reset "signal invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 3 3 + fi # signal addresses race test - reset - ip netns exec $ns1 ./pm_nl_ctl limits 4 4 - ip netns exec $ns2 ./pm_nl_ctl limits 4 4 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.1.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal - - # the peer could possibly miss some addr notification, allow retransmission - ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "signal addresses race test" 3 3 3 - - # the server will not signal the address terminating - # the MPC subflow - chk_add_nr 3 3 + if reset "signal addresses race test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_add_endpoint $ns2 10.0.1.2 flags signal + pm_nl_add_endpoint $ns2 10.0.2.2 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags signal + pm_nl_add_endpoint $ns2 10.0.4.2 flags signal + + # the peer could possibly miss some addr notification, allow retransmission + ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 3 3 3 + + # the server will not signal the address terminating + # the MPC subflow + chk_add_nr 3 3 + fi } link_failure_tests() { # accept and use add_addr with additional subflows and link loss - reset - - # without any b/w limit each veth could spool the packets and get - # them acked at xmit time, so that the corresponding subflow will - # have almost always no outstanding pkts, the scheduler will pick - # always the first subflow and we will have hard time testing - # active backup and link switch-over. - # Let's set some arbitrary (low) virtual link limits. - init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 dev ns2eth4 flags subflow - run_tests $ns1 $ns2 10.0.1.1 1 - chk_join_nr "multiple flows, signal, link failure" 3 3 3 - chk_add_nr 1 1 - chk_stale_nr $ns2 1 5 1 + if reset "multiple flows, signal, link failure"; then + # without any b/w limit each veth could spool the packets and get + # them acked at xmit time, so that the corresponding subflow will + # have almost always no outstanding pkts, the scheduler will pick + # always the first subflow and we will have hard time testing + # active backup and link switch-over. + # Let's set some arbitrary (low) virtual link limits. + init_shapers + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 5 1 + fi # accept and use add_addr with additional subflows and link loss # for bidirectional transfer - reset - init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 dev ns2eth4 flags subflow - run_tests $ns1 $ns2 10.0.1.1 2 - chk_join_nr "multi flows, signal, bidi, link fail" 3 3 3 - chk_add_nr 1 1 - chk_stale_nr $ns2 1 -1 1 + if reset "multi flows, signal, bidi, link fail"; then + init_shapers + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow + run_tests $ns1 $ns2 10.0.1.1 2 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 -1 1 + fi # 2 subflows plus 1 backup subflow with a lossy link, backup # will never be used - reset - init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - export FAILING_LINKS="1" - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 1 - chk_join_nr "backup subflow unused, link failure" 2 2 2 - chk_add_nr 1 1 - chk_link_usage $ns2 ns2eth3 $cinsent 0 + if reset "backup subflow unused, link failure"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 + FAILING_LINKS="1" + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_link_usage $ns2 ns2eth3 $cinsent 0 + fi # 2 lossy links after half transfer, backup will get half of # the traffic - reset - init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup - export FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 1 - chk_join_nr "backup flow used, multi links fail" 2 2 2 - chk_add_nr 1 1 - chk_stale_nr $ns2 2 4 2 - chk_link_usage $ns2 ns2eth3 $cinsent 50 + if reset "backup flow used, multi links fail"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + FAILING_LINKS="1 2" + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_stale_nr $ns2 2 4 2 + chk_link_usage $ns2 ns2eth3 $cinsent 50 + fi # use a backup subflow with the first subflow on a lossy link # for bidirectional transfer - reset - init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 2 - chk_join_nr "backup flow used, bidi, link failure" 2 2 2 - chk_add_nr 1 1 - chk_stale_nr $ns2 1 -1 2 - chk_link_usage $ns2 ns2eth3 $cinsent 50 + if reset "backup flow used, bidi, link failure"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + FAILING_LINKS="1 2" + run_tests $ns1 $ns2 10.0.1.1 2 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 -1 2 + chk_link_usage $ns2 ns2eth3 $cinsent 50 + fi } add_addr_timeout_tests() { # add_addr timeout - reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "signal address, ADD_ADDR timeout" 1 1 1 - chk_add_nr 4 0 + if reset_with_add_addr_timeout "signal address, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 4 0 + fi # add_addr timeout IPv6 - reset_with_add_addr_timeout 6 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "signal address, ADD_ADDR6 timeout" 1 1 1 - chk_add_nr 4 0 + if reset_with_add_addr_timeout "signal address, ADD_ADDR6 timeout" 6; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 4 0 + fi # signal addresses timeout - reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 least - chk_join_nr "signal addresses, ADD_ADDR timeout" 2 2 2 - chk_add_nr 8 0 + if reset_with_add_addr_timeout "signal addresses, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + chk_join_nr 2 2 2 + chk_add_nr 8 0 + fi # signal invalid addresses timeout - reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 least - chk_join_nr "invalid address, ADD_ADDR timeout" 1 1 1 - chk_add_nr 8 0 + if reset_with_add_addr_timeout "invalid address, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + chk_join_nr 1 1 1 + chk_add_nr 8 0 + fi } remove_tests() { # single subflow, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow - chk_join_nr "remove single subflow" 1 1 1 - chk_rm_nr 1 1 + if reset "remove single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow + chk_join_nr 1 1 1 + chk_rm_nr 1 1 + fi # multiple subflows, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow - chk_join_nr "remove multiple subflows" 2 2 2 - chk_rm_nr 2 2 + if reset "remove multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow + chk_join_nr 2 2 2 + chk_rm_nr 2 2 + fi # single address, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow - chk_join_nr "remove single address" 1 1 1 - chk_add_nr 1 1 - chk_rm_nr 1 1 invert + if reset "remove single address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi # subflow and signal, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow - chk_join_nr "remove subflow and signal" 2 2 2 - chk_add_nr 1 1 - chk_rm_nr 1 1 + if reset "remove subflow and signal"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_rm_nr 1 1 + fi # subflows and signal, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow - chk_join_nr "remove subflows and signal" 3 3 3 - chk_add_nr 1 1 - chk_rm_nr 2 2 + if reset "remove subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 2 2 + fi # addresses remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow - chk_join_nr "remove addresses" 3 3 3 - chk_add_nr 3 3 - chk_rm_nr 3 3 invert + if reset "remove addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + chk_join_nr 3 3 3 + chk_add_nr 3 3 + chk_rm_nr 3 3 invert + fi # invalid addresses remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow - chk_join_nr "remove invalid addresses" 1 1 1 - chk_add_nr 3 3 - chk_rm_nr 3 1 invert + if reset "remove invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + chk_join_nr 1 1 1 + chk_add_nr 3 3 + chk_rm_nr 3 1 invert + fi # subflows and signal, flush - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow - chk_join_nr "flush subflows and signal" 3 3 3 - chk_add_nr 1 1 - chk_rm_nr 2 2 + if reset "flush subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 1 3 invert simult + fi # subflows flush - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow id 150 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow - chk_join_nr "flush subflows" 3 3 3 - chk_rm_nr 3 3 + if reset "flush subflows"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_set_limits $ns2 3 3 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_rm_nr 0 3 simult + fi # addresses flush - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow - chk_join_nr "flush addresses" 3 3 3 - chk_add_nr 3 3 - chk_rm_nr 3 3 invert + if reset "flush addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_add_nr 3 3 + chk_rm_nr 3 3 invert simult + fi # invalid addresses flush - reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow - chk_join_nr "flush invalid addresses" 1 1 1 - chk_add_nr 3 3 - chk_rm_nr 3 1 invert + if reset "flush invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow + chk_join_nr 1 1 1 + chk_add_nr 3 3 + chk_rm_nr 3 1 invert + fi # remove id 0 subflow - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow - chk_join_nr "remove id 0 subflow" 1 1 1 - chk_rm_nr 1 1 + if reset "remove id 0 subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow + chk_join_nr 1 1 1 + chk_rm_nr 1 1 + fi # remove id 0 address - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow - chk_join_nr "remove id 0 address" 1 1 1 - chk_add_nr 1 1 - chk_rm_nr 1 1 invert + if reset "remove id 0 address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi } add_tests() { # add single subflow - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow - chk_join_nr "add single subflow" 1 1 1 + if reset "add single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow + chk_join_nr 1 1 1 + fi # add signal address - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow - chk_join_nr "add signal address" 1 1 1 - chk_add_nr 1 1 + if reset "add signal address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # add multiple subflows - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow - chk_join_nr "add multiple subflows" 2 2 2 + if reset "add multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow + chk_join_nr 2 2 2 + fi # add multiple subflows IPv6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow - chk_join_nr "add multiple subflows IPv6" 2 2 2 + if reset "add multiple subflows IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow + chk_join_nr 2 2 2 + fi # add multiple addresses IPv6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow - chk_join_nr "add multiple addresses IPv6" 2 2 2 - chk_add_nr 2 2 + if reset "add multiple addresses IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow + chk_join_nr 2 2 2 + chk_add_nr 2 2 + fi } ipv6_tests() { # subflow IPv6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 dev ns2eth3 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "single subflow IPv6" 1 1 1 + if reset "single subflow IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + fi # add_address, unused IPv6 - reset - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "unused signal address IPv6" 0 0 0 - chk_add_nr 1 1 + if reset "unused signal address IPv6"; then + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi # signal address IPv6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "single address IPv6" 1 1 1 - chk_add_nr 1 1 + if reset "single address IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # single address IPv6, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow - chk_join_nr "remove single address IPv6" 1 1 1 - chk_add_nr 1 1 - chk_rm_nr 1 1 invert + if reset "remove single address IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi # subflow and signal IPv6, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 dev ns2eth3 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow - chk_join_nr "remove subflow and signal IPv6" 2 2 2 - chk_add_nr 1 1 - chk_rm_nr 1 1 + if reset "remove subflow and signal IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_rm_nr 1 1 + fi } v4mapped_tests() { # subflow IPv4-mapped to IPv4-mapped - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add "::ffff:10.0.3.2" flags subflow - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "single subflow IPv4-mapped" 1 1 1 + if reset "single subflow IPv4-mapped"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + fi # signal address IPv4-mapped with IPv4-mapped sk - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add "::ffff:10.0.2.1" flags signal - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "signal address IPv4-mapped" 1 1 1 - chk_add_nr 1 1 + if reset "signal address IPv4-mapped"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # subflow v4-map-v6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "single subflow v4-map-v6" 1 1 1 + if reset "single subflow v4-map-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + fi # signal address v4-map-v6 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "signal address v4-map-v6" 1 1 1 - chk_add_nr 1 1 + if reset "signal address v4-map-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # subflow v6-map-v4 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add "::ffff:10.0.3.2" flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow v6-map-v4" 1 1 1 + if reset "single subflow v6-map-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # signal address v6-map-v4 - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add "::ffff:10.0.2.1" flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address v6-map-v4" 1 1 1 - chk_add_nr 1 1 + if reset "signal address v6-map-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # no subflow IPv6 to v4 address - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:2::2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "no JOIN with diff families v4-v6" 0 0 0 + if reset "no JOIN with diff families v4-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # no subflow IPv6 to v4 address even if v6 has a valid v4 at the end - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:2::10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "no JOIN with diff families v4-v6-2" 0 0 0 + if reset "no JOIN with diff families v4-v6-2"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # no subflow IPv4 to v6 address, no need to slow down too then - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 - chk_join_nr "no JOIN with diff families v6-v4" 0 0 0 + if reset "no JOIN with diff families v6-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 + chk_join_nr 0 0 0 + fi } backup_tests() { # single subflow, backup - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup - chk_join_nr "single subflow, backup" 1 1 1 - chk_prio_nr 0 1 + if reset "single subflow, backup"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup + chk_join_nr 1 1 1 + chk_prio_nr 0 1 + fi # single address, backup - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup - chk_join_nr "single address, backup" 1 1 1 - chk_add_nr 1 1 - chk_prio_nr 1 0 + if reset "single address, backup"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 1 + fi + + # single address with port, backup + if reset "single address with port, backup"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 1 + fi } add_addr_ports_tests() { # signal address with port - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address with port" 1 1 1 - chk_add_nr 1 1 1 + if reset "signal address with port"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 1 + fi # subflow and signal with port - reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and signal with port" 2 2 2 - chk_add_nr 1 1 1 + if reset "subflow and signal with port"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 1 + fi # single address with port, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow - chk_join_nr "remove single address with port" 1 1 1 - chk_add_nr 1 1 1 - chk_rm_nr 1 1 invert + if reset "remove single address with port"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 1 + chk_rm_nr 1 1 invert + fi # subflow and signal with port, remove - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow - chk_join_nr "remove subflow and signal with port" 2 2 2 - chk_add_nr 1 1 1 - chk_rm_nr 1 1 + if reset "remove subflow and signal with port"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 1 + chk_rm_nr 1 1 + fi # subflows and signal with port, flush - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow - chk_join_nr "flush subflows and signal with port" 3 3 3 - chk_add_nr 1 1 - chk_rm_nr 2 2 + if reset "flush subflows and signal with port"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 1 3 invert simult + fi # multiple addresses with port - reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple addresses with port" 2 2 2 - chk_add_nr 2 2 2 + if reset "multiple addresses with port"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10100 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 2 2 2 + fi # multiple addresses with ports - reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal port 10101 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple addresses with ports" 2 2 2 - chk_add_nr 2 2 2 + if reset "multiple addresses with ports"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10101 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 2 2 2 + fi } syncookies_tests() { # single subflow, syncookies - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow with syn cookies" 1 1 1 + if reset_with_cookies "single subflow with syn cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # multiple subflows with syn cookies - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows with syn cookies" 2 2 2 + if reset_with_cookies "multiple subflows with syn cookies"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi # multiple subflows limited by server - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflows limited by server w cookies" 2 1 1 + if reset_with_cookies "subflows limited by server w cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 1 1 + fi # test signal address with cookies - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address with syn cookies" 1 1 1 - chk_add_nr 1 1 + if reset_with_cookies "signal address with syn cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # test cookie with subflow and signal - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and signal w cookies" 2 2 2 - chk_add_nr 1 1 + if reset_with_cookies "subflow and signal w cookies"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + fi # accept and use add_addr with additional subflows - reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflows and signal w. cookies" 3 3 3 - chk_add_nr 1 1 + if reset_with_cookies "subflows and signal w. cookies"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi } checksum_tests() { # checksum test 0 0 - reset_with_checksum 0 0 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 0 0" + if reset_with_checksum 0 0; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # checksum test 1 1 - reset_with_checksum 1 1 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 1 1" + if reset_with_checksum 1 1; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # checksum test 0 1 - reset_with_checksum 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 0 1" + if reset_with_checksum 0 1; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # checksum test 1 0 - reset_with_checksum 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 1 0" + if reset_with_checksum 1 0; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi } deny_join_id0_tests() { # subflow allow join id0 ns1 - reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow allow join id0 ns1" 1 1 1 + if reset_with_allow_join_id0 "single subflow allow join id0 ns1" 1 0; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # subflow allow join id0 ns2 - reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow allow join id0 ns2" 0 0 0 + if reset_with_allow_join_id0 "single subflow allow join id0 ns2" 0 1; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # signal address allow join id0 ns1 # ADD_ADDRs are not affected by allow_join_id0 value. - reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address allow join id0 ns1" 1 1 1 - chk_add_nr 1 1 + if reset_with_allow_join_id0 "signal address allow join id0 ns1" 1 0; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # signal address allow join id0 ns2 # ADD_ADDRs are not affected by allow_join_id0 value. - reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address allow join id0 ns2" 1 1 1 - chk_add_nr 1 1 + if reset_with_allow_join_id0 "signal address allow join id0 ns2" 0 1; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # subflow and address allow join id0 ns1 - reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and address allow join id0 1" 2 2 2 + if reset_with_allow_join_id0 "subflow and address allow join id0 1" 1 0; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi # subflow and address allow join id0 ns2 - reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and address allow join id0 2" 1 1 1 + if reset_with_allow_join_id0 "subflow and address allow join id0 2" 0 1; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi } fullmesh_tests() @@ -1865,177 +2456,237 @@ fullmesh_tests() # fullmesh 1 # 2 fullmesh addrs in ns2, added before the connection, # 1 non-fullmesh addr in ns1, added during the connection. - reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 4 - ip netns exec $ns2 ./pm_nl_ctl limits 1 4 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow,fullmesh - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow,fullmesh - run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow - chk_join_nr "fullmesh test 2x1" 4 4 4 - chk_add_nr 1 1 + if reset "fullmesh test 2x1"; then + pm_nl_set_limits $ns1 0 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + chk_join_nr 4 4 4 + chk_add_nr 1 1 + fi # fullmesh 2 # 1 non-fullmesh addr in ns1, added before the connection, # 1 fullmesh addr in ns2, added during the connection. - reset - ip netns exec $ns1 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow - chk_join_nr "fullmesh test 1x1" 3 3 3 - chk_add_nr 1 1 + if reset "fullmesh test 1x1"; then + pm_nl_set_limits $ns1 1 3 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi # fullmesh 3 # 1 non-fullmesh addr in ns1, added before the connection, # 2 fullmesh addrs in ns2, added during the connection. - reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 5 - ip netns exec $ns2 ./pm_nl_ctl limits 1 5 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow - chk_join_nr "fullmesh test 1x2" 5 5 5 - chk_add_nr 1 1 + if reset "fullmesh test 1x2"; then + pm_nl_set_limits $ns1 2 5 + pm_nl_set_limits $ns2 1 5 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + chk_join_nr 5 5 5 + chk_add_nr 1 1 + fi # fullmesh 4 # 1 non-fullmesh addr in ns1, added before the connection, # 2 fullmesh addrs in ns2, added during the connection, # limit max_subflows to 4. - reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 4 - ip netns exec $ns2 ./pm_nl_ctl limits 1 4 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow - chk_join_nr "fullmesh test 1x2, limited" 4 4 4 - chk_add_nr 1 1 + if reset "fullmesh test 1x2, limited"; then + pm_nl_set_limits $ns1 2 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + chk_join_nr 4 4 4 + chk_add_nr 1 1 + fi + + # set fullmesh flag + if reset "set fullmesh flag test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow fullmesh + chk_join_nr 2 2 2 + chk_rm_nr 0 1 + fi + + # set nofullmesh flag + if reset "set nofullmesh flag test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow nofullmesh + chk_join_nr 2 2 2 + chk_rm_nr 0 1 + fi + + # set backup,fullmesh flags + if reset "set backup,fullmesh flags test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow backup,fullmesh + chk_join_nr 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 + fi + + # set nobackup,nofullmesh flags + if reset "set nobackup,nofullmesh flags test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup,nofullmesh + chk_join_nr 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 + fi } -all_tests() +fastclose_tests() { - subflows_tests - subflows_error_tests - signal_address_tests - link_failure_tests - add_addr_timeout_tests - remove_tests - add_tests - ipv6_tests - v4mapped_tests - backup_tests - add_addr_ports_tests - syncookies_tests - checksum_tests - deny_join_id0_tests - fullmesh_tests + if reset "fastclose test"; then + run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_2 + chk_join_nr 0 0 0 + chk_fclose_nr 1 1 + chk_rst_nr 1 1 invert + fi +} + +implicit_tests() +{ + # userspace pm type prevents add_addr + if reset "implicit EP"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + + wait_mpj $ns1 + pm_nl_check_endpoint 1 "creation" \ + $ns2 10.0.2.2 id 1 flags implicit + + pm_nl_add_endpoint $ns2 10.0.2.2 id 33 + pm_nl_check_endpoint 0 "ID change is prevented" \ + $ns2 10.0.2.2 id 1 flags implicit + + pm_nl_add_endpoint $ns2 10.0.2.2 flags signal + pm_nl_check_endpoint 0 "modif is allowed" \ + $ns2 10.0.2.2 id 1 flags signal + wait + fi } +# [$1: error message] usage() { + if [ -n "${1}" ]; then + echo "${1}" + ret=1 + fi + echo "mptcp_join usage:" - echo " -f subflows_tests" - echo " -e subflows_error_tests" - echo " -s signal_address_tests" - echo " -l link_failure_tests" - echo " -t add_addr_timeout_tests" - echo " -r remove_tests" - echo " -a add_tests" - echo " -6 ipv6_tests" - echo " -4 v4mapped_tests" - echo " -b backup_tests" - echo " -p add_addr_ports_tests" - echo " -k syncookies_tests" - echo " -S checksum_tests" - echo " -d deny_join_id0_tests" - echo " -m fullmesh_tests" + + local key + for key in "${!all_tests[@]}"; do + echo " -${key} ${all_tests[${key}]}" + done + echo " -c capture pcap files" echo " -C enable data checksum" + echo " -i use ip mptcp" echo " -h help" -} -sin=$(mktemp) -sout=$(mktemp) -cin=$(mktemp) -cinsent=$(mktemp) -cout=$(mktemp) -init -make_file "$cin" "client" 1 -make_file "$sin" "server" 1 -trap cleanup EXIT + echo "[test ids|names]" -for arg in "$@"; do - # check for "capture/checksum" args before launching tests - if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"c"[0-9a-zA-Z]*$ ]]; then - capture=1 - fi - if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"C"[0-9a-zA-Z]*$ ]]; then - checksum=1 - fi + exit ${ret} +} - # exception for the capture/checksum options, the rest means: a part of the tests - if [ "${arg}" != "-c" ] && [ "${arg}" != "-C" ]; then - do_all_tests=0 - fi -done -if [ $do_all_tests -eq 1 ]; then - all_tests - exit $ret -fi +# Use a "simple" array to force an specific order we cannot have with an associative one +all_tests_sorted=( + f@subflows_tests + e@subflows_error_tests + s@signal_address_tests + l@link_failure_tests + t@add_addr_timeout_tests + r@remove_tests + a@add_tests + 6@ipv6_tests + 4@v4mapped_tests + b@backup_tests + p@add_addr_ports_tests + k@syncookies_tests + S@checksum_tests + d@deny_join_id0_tests + m@fullmesh_tests + z@fastclose_tests + I@implicit_tests +) + +all_tests_args="" +all_tests_names=() +for subtests in "${all_tests_sorted[@]}"; do + key="${subtests%@*}" + value="${subtests#*@}" + + all_tests_args+="${key}" + all_tests_names+=("${value}") + all_tests[${key}]="${value}" +done -while getopts 'fesltra64bpkdmchCS' opt; do +tests=() +while getopts "${all_tests_args}cCih" opt; do case $opt in - f) - subflows_tests - ;; - e) - subflows_error_tests - ;; - s) - signal_address_tests - ;; - l) - link_failure_tests - ;; - t) - add_addr_timeout_tests - ;; - r) - remove_tests - ;; - a) - add_tests - ;; - 6) - ipv6_tests - ;; - 4) - v4mapped_tests - ;; - b) - backup_tests - ;; - p) - add_addr_ports_tests - ;; - k) - syncookies_tests - ;; - S) - checksum_tests - ;; - d) - deny_join_id0_tests - ;; - m) - fullmesh_tests + ["${all_tests_args}"]) + tests+=("${all_tests[${opt}]}") ;; c) + capture=1 ;; C) + checksum=1 + ;; + i) + ip_mptcp=1 ;; - h | *) + h) usage ;; + *) + usage "Unknown option: -${opt}" + ;; esac done +shift $((OPTIND - 1)) + +for arg in "${@}"; do + if [[ "${arg}" =~ ^[0-9]+$ ]]; then + only_tests_ids+=("${arg}") + else + only_tests_names+=("${arg}") + fi +done + +if [ ${#tests[@]} -eq 0 ]; then + tests=("${all_tests_names[@]}") +fi + +for subtests in "${tests[@]}"; do + "${subtests}" +done + +if [ ${ret} -ne 0 ]; then + echo + echo "${#failed_tests[@]} failure(s) has(ve) been detected:" + for i in $(get_failed_tests_ids); do + echo -e "\t- ${i}: ${failed_tests[${i}]}" + done + echo +fi + exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index cbacf9f6538b..89839d1ff9d8 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -164,4 +164,22 @@ id 253 flags 10.0.0.5 id 254 flags 10.0.0.2 id 255 flags 10.0.0.3" "wrap-around ids" +ip netns exec $ns1 ./pm_nl_ctl flush +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 flags subflow +ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags backup +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,backup 10.0.1.1" "set flags (backup)" +ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags nobackup +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow 10.0.1.1" " (nobackup)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,fullmesh 10.0.1.1" " (fullmesh)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow 10.0.1.1" " (nofullmesh)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" + exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 354784512748..a75a68ad652e 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -28,7 +28,7 @@ static void syntax(char *argv[]) fprintf(stderr, "\tadd [flags signal|subflow|backup|fullmesh] [id <nr>] [dev <name>] <ip>\n"); fprintf(stderr, "\tdel <id> [<ip>]\n"); fprintf(stderr, "\tget <id>\n"); - fprintf(stderr, "\tset <ip> [flags backup|nobackup]\n"); + fprintf(stderr, "\tset [<ip>] [id <nr>] flags [no]backup|[no]fullmesh [port <nr>]\n"); fprintf(stderr, "\tflush\n"); fprintf(stderr, "\tdump\n"); fprintf(stderr, "\tlimits [<rcv addr max> <subflow max>]\n"); @@ -436,6 +436,13 @@ static void print_addr(struct rtattr *attrs, int len) printf(","); } + if (flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) { + printf("implicit"); + flags &= ~MPTCP_PM_ADDR_FLAG_IMPLICIT; + if (flags) + printf(","); + } + /* bump unknown flags, if any */ if (flags) printf("0x%x", flags); @@ -657,8 +664,10 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) u_int32_t flags = 0; u_int16_t family; int nest_start; + int use_id = 0; + u_int8_t id; int off = 0; - int arg; + int arg = 2; memset(data, 0, sizeof(data)); nh = (void *)data; @@ -674,29 +683,45 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) nest->rta_len = RTA_LENGTH(0); off += NLMSG_ALIGN(nest->rta_len); - /* addr data */ - rta = (void *)(data + off); - if (inet_pton(AF_INET, argv[2], RTA_DATA(rta))) { - family = AF_INET; - rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; - rta->rta_len = RTA_LENGTH(4); - } else if (inet_pton(AF_INET6, argv[2], RTA_DATA(rta))) { - family = AF_INET6; - rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; - rta->rta_len = RTA_LENGTH(16); + if (!strcmp(argv[arg], "id")) { + if (++arg >= argc) + error(1, 0, " missing id value"); + + use_id = 1; + id = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); } else { - error(1, errno, "can't parse ip %s", argv[2]); + /* addr data */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, argv[arg], RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, argv[arg], RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else { + error(1, errno, "can't parse ip %s", argv[arg]); + } + off += NLMSG_ALIGN(rta->rta_len); + + /* family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); } - off += NLMSG_ALIGN(rta->rta_len); - /* family */ - rta = (void *)(data + off); - rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; - rta->rta_len = RTA_LENGTH(2); - memcpy(RTA_DATA(rta), &family, 2); - off += NLMSG_ALIGN(rta->rta_len); + if (++arg >= argc) + error(1, 0, " missing flags keyword"); - for (arg = 3; arg < argc; arg++) { + for (; arg < argc; arg++) { if (!strcmp(argv[arg], "flags")) { char *tok, *str; @@ -704,12 +729,14 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) if (++arg >= argc) error(1, 0, " missing flags value"); - /* do not support flag list yet */ for (str = argv[arg]; (tok = strtok(str, ",")); str = NULL) { if (!strcmp(tok, "backup")) flags |= MPTCP_PM_ADDR_FLAG_BACKUP; - else if (strcmp(tok, "nobackup")) + else if (!strcmp(tok, "fullmesh")) + flags |= MPTCP_PM_ADDR_FLAG_FULLMESH; + else if (strcmp(tok, "nobackup") && + strcmp(tok, "nofullmesh")) error(1, errno, "unknown flag %s", argv[arg]); } @@ -719,6 +746,21 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) rta->rta_len = RTA_LENGTH(4); memcpy(RTA_DATA(rta), &flags, 4); off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "port")) { + u_int16_t port; + + if (use_id) + error(1, 0, " port can't be used with id"); + + if (++arg >= argc) + error(1, 0, " missing port value"); + + port = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &port, 2); + off += NLMSG_ALIGN(rta->rta_len); } else { error(1, 0, "unknown keyword %s", argv[arg]); } diff --git a/tools/testing/selftests/net/mptcp/settings b/tools/testing/selftests/net/mptcp/settings index a62d2fa1275c..79b65bdf05db 100644 --- a/tools/testing/selftests/net/mptcp/settings +++ b/tools/testing/selftests/net/mptcp/settings @@ -1 +1 @@ -timeout=600 +timeout=1200 diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 694732e4b344..736e358dc549 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -26,6 +26,15 @@ # - pmtu_ipv6 # Same as pmtu_ipv4, except for locked PMTU tests, using IPv6 # +# - pmtu_ipv4_dscp_icmp_exception +# Set up the same network topology as pmtu_ipv4, but use non-default +# routing table in A. A fib-rule is used to jump to this routing table +# based on DSCP. Send ICMPv4 packets with the expected DSCP value and +# verify that ECN doesn't interfere with the creation of PMTU exceptions. +# +# - pmtu_ipv4_dscp_udp_exception +# Same as pmtu_ipv4_dscp_icmp_exception, but use UDP instead of ICMP. +# # - pmtu_ipv4_vxlan4_exception # Set up the same network topology as pmtu_ipv4, create a VXLAN tunnel # over IPv4 between A and B, routed via R1. On the link between R1 and B, @@ -203,6 +212,8 @@ which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) tests=" pmtu_ipv4_exception ipv4: PMTU exceptions 1 pmtu_ipv6_exception ipv6: PMTU exceptions 1 + pmtu_ipv4_dscp_icmp_exception ICMPv4 with DSCP and ECN: PMTU exceptions 1 + pmtu_ipv4_dscp_udp_exception UDPv4 with DSCP and ECN: PMTU exceptions 1 pmtu_ipv4_vxlan4_exception IPv4 over vxlan4: PMTU exceptions 1 pmtu_ipv6_vxlan4_exception IPv6 over vxlan4: PMTU exceptions 1 pmtu_ipv4_vxlan6_exception IPv4 over vxlan6: PMTU exceptions 1 @@ -323,6 +334,9 @@ routes_nh=" B 6 default 61 " +policy_mark=0x04 +rt_table=main + veth4_a_addr="192.168.1.1" veth4_b_addr="192.168.1.2" veth4_c_addr="192.168.2.10" @@ -346,6 +360,7 @@ dummy6_mask="64" err_buf= tcpdump_pids= nettest_pids= +socat_pids= err() { err_buf="${err_buf}${1} @@ -723,7 +738,7 @@ setup_routing_old() { ns_name="$(nsname ${ns})" - ip -n ${ns_name} route add ${addr} via ${gw} + ip -n "${ns_name}" route add "${addr}" table "${rt_table}" via "${gw}" ns=""; addr=""; gw="" done @@ -753,7 +768,7 @@ setup_routing_new() { ns_name="$(nsname ${ns})" - ip -n ${ns_name} -${fam} route add ${addr} nhid ${nhid} + ip -n "${ns_name}" -"${fam}" route add "${addr}" table "${rt_table}" nhid "${nhid}" ns=""; fam=""; addr=""; nhid="" done @@ -798,6 +813,24 @@ setup_routing() { return 0 } +setup_policy_routing() { + setup_routing + + ip -netns "${NS_A}" -4 rule add dsfield "${policy_mark}" \ + table "${rt_table}" + + # Set the IPv4 Don't Fragment bit with tc, since socat doesn't seem to + # have an option do to it. + tc -netns "${NS_A}" qdisc replace dev veth_A-R1 root prio + tc -netns "${NS_A}" qdisc replace dev veth_A-R2 root prio + tc -netns "${NS_A}" filter add dev veth_A-R1 \ + protocol ipv4 flower ip_proto udp \ + action pedit ex munge ip df set 0x40 pipe csum ip and udp + tc -netns "${NS_A}" filter add dev veth_A-R2 \ + protocol ipv4 flower ip_proto udp \ + action pedit ex munge ip df set 0x40 pipe csum ip and udp +} + setup_bridge() { run_cmd ${ns_a} ip link add br0 type bridge || return $ksft_skip run_cmd ${ns_a} ip link set br0 up @@ -903,6 +936,11 @@ cleanup() { done nettest_pids= + for pid in ${socat_pids}; do + kill "${pid}" + done + socat_pids= + for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do ip netns del ${n} 2> /dev/null done @@ -950,15 +988,21 @@ link_get_mtu() { route_get_dst_exception() { ns_cmd="${1}" dst="${2}" + dsfield="${3}" - ${ns_cmd} ip route get "${dst}" + if [ -z "${dsfield}" ]; then + dsfield=0 + fi + + ${ns_cmd} ip route get "${dst}" dsfield "${dsfield}" } route_get_dst_pmtu_from_exception() { ns_cmd="${1}" dst="${2}" + dsfield="${3}" - mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})" + mtu_parse "$(route_get_dst_exception "${ns_cmd}" "${dst}" "${dsfield}")" } check_pmtu_value() { @@ -1068,6 +1112,95 @@ test_pmtu_ipv6_exception() { test_pmtu_ipvX 6 } +test_pmtu_ipv4_dscp_icmp_exception() { + rt_table=100 + + setup namespaces policy_routing || return $ksft_skip + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1400 + mtu "${ns_b}" veth_B-R1 1400 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + len=$((2000 - 20 - 8)) # Fills MTU of veth_A-R1 + + dst1="${prefix4}.${b_r1}.1" + dst2="${prefix4}.${b_r2}.1" + + # Create route exceptions + dsfield=${policy_mark} # No ECN bit set (Not-ECT) + run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst1}" + + dsfield=$(printf "%#x" $((policy_mark + 0x02))) # ECN=2 (ECT(0)) + run_cmd "${ns_a}" ping -q -M want -Q "${dsfield}" -c 1 -w 1 -s "${len}" "${dst2}" + + # Check that exceptions have been created with the correct PMTU + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 + + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 +} + +test_pmtu_ipv4_dscp_udp_exception() { + rt_table=100 + + if ! which socat > /dev/null 2>&1; then + echo "'socat' command not found; skipping tests" + return $ksft_skip + fi + + setup namespaces policy_routing || return $ksft_skip + trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \ + "${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \ + "${ns_r2}" veth_R2-B "${ns_b}" veth_B-R2 + + # Set up initial MTU values + mtu "${ns_a}" veth_A-R1 2000 + mtu "${ns_r1}" veth_R1-A 2000 + mtu "${ns_r1}" veth_R1-B 1400 + mtu "${ns_b}" veth_B-R1 1400 + + mtu "${ns_a}" veth_A-R2 2000 + mtu "${ns_r2}" veth_R2-A 2000 + mtu "${ns_r2}" veth_R2-B 1500 + mtu "${ns_b}" veth_B-R2 1500 + + len=$((2000 - 20 - 8)) # Fills MTU of veth_A-R1 + + dst1="${prefix4}.${b_r1}.1" + dst2="${prefix4}.${b_r2}.1" + + # Create route exceptions + run_cmd_bg "${ns_b}" socat UDP-LISTEN:50000 OPEN:/dev/null,wronly=1 + socat_pids="${socat_pids} $!" + + dsfield=${policy_mark} # No ECN bit set (Not-ECT) + run_cmd "${ns_a}" socat OPEN:/dev/zero,rdonly=1,readbytes="${len}" \ + UDP:"${dst1}":50000,tos="${dsfield}" + + dsfield=$(printf "%#x" $((policy_mark + 0x02))) # ECN=2 (ECT(0)) + run_cmd "${ns_a}" socat OPEN:/dev/zero,rdonly=1,readbytes="${len}" \ + UDP:"${dst2}":50000,tos="${dsfield}" + + # Check that exceptions have been created with the correct PMTU + pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst1}" "${policy_mark}")" + check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1 + pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" "${dst2}" "${policy_mark}")" + check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1 +} + test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() { type=${1} family=${2} diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 3653d6468c67..1a736f700be4 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -53,6 +53,7 @@ #include <unistd.h> #include "psock_lib.h" +#include "../kselftest.h" #define RING_NUM_FRAMES 20 @@ -117,7 +118,7 @@ static void sock_fanout_set_cbpf(int fd) struct sock_fprog bpf_prog; bpf_prog.filter = bpf_filter; - bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); + bpf_prog.len = ARRAY_SIZE(bpf_filter); if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &bpf_prog, sizeof(bpf_prog))) { @@ -162,7 +163,7 @@ static void sock_fanout_set_ebpf(int fd) memset(&attr, 0, sizeof(attr)); attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; attr.insns = (unsigned long) prog; - attr.insn_cnt = sizeof(prog) / sizeof(prog[0]); + attr.insn_cnt = ARRAY_SIZE(prog); attr.license = (unsigned long) "GPL"; attr.log_buf = (unsigned long) log_buf, attr.log_size = sizeof(log_buf), diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c index b2eebf669b8c..c9ba36aa688e 100644 --- a/tools/testing/selftests/net/reuseport_bpf_numa.c +++ b/tools/testing/selftests/net/reuseport_bpf_numa.c @@ -86,7 +86,7 @@ static void attach_bpf(int fd) memset(&attr, 0, sizeof(attr)); attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.insn_cnt = sizeof(prog) / sizeof(prog[0]); + attr.insn_cnt = ARRAY_SIZE(prog); attr.insns = (unsigned long) &prog; attr.license = (unsigned long) &bpf_license; attr.log_buf = (unsigned long) &bpf_log_buf; diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index c9ce3dfa42ee..0900c5438fbb 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -216,9 +216,9 @@ kci_test_route_get() check_err $? ip route get fe80::1 dev "$devdummy" > /dev/null check_err $? - ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x1 mark 0x1 > /dev/null + ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x10 mark 0x1 > /dev/null check_err $? - ip route get ::1 from ::1 iif lo oif lo tos 0x1 mark 0x1 > /dev/null + ip route get ::1 from ::1 iif lo oif lo tos 0x10 mark 0x1 > /dev/null check_err $? ip addr add dev "$devdummy" 10.23.7.11/24 check_err $? diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh new file mode 100755 index 000000000000..704997ffc244 --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh @@ -0,0 +1,579 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test is for checking the VXLAN vni filtering api and +# datapath. +# It simulates two hypervisors running two VMs each using four network +# six namespaces: two for the HVs, four for the VMs. Each VM is +# connected to a separate bridge. The VM's use overlapping vlans and +# hence the separate bridge domain. Each vxlan device is a collect +# metadata device with vni filtering and hence has the ability to +# terminate configured vni's only. + +# +--------------------------------+ +------------------------------------+ +# | vm-11 netns | | vm-21 netns | +# | | | | +# |+------------+ +-------------+ | |+-------------+ +----------------+ | +# ||veth-11.10 | |veth-11.20 | | ||veth-21.10 | | veth-21.20 | | +# ||10.0.10.11/24 |10.0.20.11/24| | ||10.0.10.21/24| | 10.0.20.21/24 | | +# |+------|-----+ +|------------+ | |+-----------|-+ +---|------------+ | +# | | | | | | | | +# | | | | | +------------+ | +# | +------------+ | | | veth-21 | | +# | | veth-11 | | | | | | +# | | | | | +-----|------+ | +# | +-----|------+ | | | | +# | | | | | | +# +------------|-------------------+ +---------------|--------------------+ +# +------------|-----------------------------------------|-------------------+ +# | +-----|------+ +-----|------+ | +# | |vethhv-11 | |vethhv-21 | | +# | +----|-------+ +-----|------+ | +# | +---|---+ +---|--+ | +# | | br1 | | br2 | | +# | +---|---+ +---|--+ | +# | +---|----+ +---|--+ | +# | | vxlan1| |vxlan2| | +# | +--|-----+ +--|---+ | +# | | | | +# | | +---------------------+ | | +# | | |veth0 | | | +# | +---------|172.16.0.1/24 -----------+ | +# | |2002:fee1::1/64 | | +# | hv-1 netns +--------|------------+ | +# +-----------------------------|--------------------------------------------+ +# | +# +-----------------------------|--------------------------------------------+ +# | hv-2 netns +--------|-------------+ | +# | | veth0 | | +# | +------| 172.16.0.2/24 |---+ | +# | | | 2002:fee1::2/64 | | | +# | | | | | | +# | | +----------------------+ | - | +# | | | | +# | +-|-------+ +--------|-+ | +# | | vxlan1 | | vxlan2 | | +# | +----|----+ +---|------+ | +# | +--|--+ +-|---+ | +# | | br1 | | br2 | | +# | +--|--+ +--|--+ | +# | +-----|-------+ +----|-------+ | +# | | vethhv-12 | |vethhv-22 | | +# | +------|------+ +-------|----+ | +# +-----------------|----------------------------|---------------------------+ +# | | +# +-----------------|-----------------+ +--------|---------------------------+ +# | +-------|---+ | | +--|---------+ | +# | | veth-12 | | | |veth-22 | | +# | +-|--------|+ | | +--|--------|+ | +# | | | | | | | | +# |+----------|--+ +---|-----------+ | |+-------|-----+ +|---------------+ | +# ||veth-12.10 | |veth-12.20 | | ||veth-22.10 | |veth-22.20 | | +# ||10.0.10.12/24| |10.0.20.12/24 | | ||10.0.10.22/24| |10.0.20.22/24 | | +# |+-------------+ +---------------+ | |+-------------+ +----------------+ | +# | | | | +# | | | | +# | vm-12 netns | |vm-22 netns | +# +-----------------------------------+ +------------------------------------+ +# +# +# This test tests the new vxlan vnifiltering api + +ret=0 +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# all tests in this script. Can be overridden with -t option +TESTS=" + vxlan_vnifilter_api + vxlan_vnifilter_datapath + vxlan_vnifilter_datapath_pervni + vxlan_vnifilter_datapath_mgroup + vxlan_vnifilter_datapath_mgroup_pervni + vxlan_vnifilter_metadata_and_traditional_mix +" +VERBOSE=0 +PAUSE_ON_FAIL=no +PAUSE=no + +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + printf " TEST: %-60s [ OK ]\n" "${msg}" + nsuccess=$((nsuccess+1)) + else + ret=1 + nfail=$((nfail+1)) + printf " TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi + + if [ "${PAUSE}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi +} + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + printf "COMMAND: $cmd\n" + stderr= + fi + + out=$(eval $cmd $stderr) + rc=$? + if [ "$VERBOSE" = "1" -a -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +check_hv_connectivity() { + ip netns exec hv-1 ping -c 1 -W 1 $1 &>/dev/null + sleep 1 + ip netns exec hv-1 ping -c 1 -W 1 $2 &>/dev/null + + return $? +} + +check_vm_connectivity() { + run_cmd "ip netns exec vm-11 ping -c 1 -W 1 10.0.10.12" + log_test $? 0 "VM connectivity over $1 (ipv4 default rdst)" + + run_cmd "ip netns exec vm-21 ping -c 1 -W 1 10.0.10.22" + log_test $? 0 "VM connectivity over $1 (ipv6 default rdst)" +} + +cleanup() { + ip link del veth-hv-1 2>/dev/null || true + ip link del vethhv-11 vethhv-12 vethhv-21 vethhv-22 2>/dev/null || true + + for ns in hv-1 hv-2 vm-11 vm-21 vm-12 vm-22 vm-31 vm-32; do + ip netns del $ns 2>/dev/null || true + done +} + +trap cleanup EXIT + +setup-hv-networking() { + hv=$1 + local1=$2 + mask1=$3 + local2=$4 + mask2=$5 + + ip netns add hv-$hv + ip link set veth-hv-$hv netns hv-$hv + ip -netns hv-$hv link set veth-hv-$hv name veth0 + ip -netns hv-$hv addr add $local1/$mask1 dev veth0 + ip -netns hv-$hv addr add $local2/$mask2 dev veth0 + ip -netns hv-$hv link set veth0 up +} + +# Setups a "VM" simulated by a netns an a veth pair +# example: setup-vm <hvid> <vmid> <brid> <VATTRS> <mcast_for_bum> +# VATTRS = comma separated "<vlan>-<v[46]>-<localip>-<remoteip>-<VTYPE>-<vxlandstport>" +# VTYPE = vxlan device type. "default = traditional device, metadata = metadata device +# vnifilter = vnifiltering device, +# vnifilterg = vnifiltering device with per vni group/remote" +# example: +# setup-vm 1 11 1 \ +# 10-v4-172.16.0.1-239.1.1.100-vnifilterg,20-v4-172.16.0.1-239.1.1.100-vnifilterg 1 +# +setup-vm() { + hvid=$1 + vmid=$2 + brid=$3 + vattrs=$4 + mcast=$5 + lastvxlandev="" + + # create bridge + ip -netns hv-$hvid link add br$brid type bridge vlan_filtering 1 vlan_default_pvid 0 \ + mcast_snooping 0 + ip -netns hv-$hvid link set br$brid up + + # create vm namespace and interfaces and connect to hypervisor + # namespace + ip netns add vm-$vmid + hvvethif="vethhv-$vmid" + vmvethif="veth-$vmid" + ip link add $hvvethif type veth peer name $vmvethif + ip link set $hvvethif netns hv-$hvid + ip link set $vmvethif netns vm-$vmid + ip -netns hv-$hvid link set $hvvethif up + ip -netns vm-$vmid link set $vmvethif up + ip -netns hv-$hvid link set $hvvethif master br$brid + + # configure VM vlan/vni filtering on hypervisor + for vmap in $(echo $vattrs | cut -d "," -f1- --output-delimiter=' ') + do + local vid=$(echo $vmap | awk -F'-' '{print ($1)}') + local family=$(echo $vmap | awk -F'-' '{print ($2)}') + local localip=$(echo $vmap | awk -F'-' '{print ($3)}') + local group=$(echo $vmap | awk -F'-' '{print ($4)}') + local vtype=$(echo $vmap | awk -F'-' '{print ($5)}') + local port=$(echo $vmap | awk -F'-' '{print ($6)}') + + ip -netns vm-$vmid link add name $vmvethif.$vid link $vmvethif type vlan id $vid + ip -netns vm-$vmid addr add 10.0.$vid.$vmid/24 dev $vmvethif.$vid + ip -netns vm-$vmid link set $vmvethif.$vid up + + tid=$vid + vxlandev="vxlan$brid" + vxlandevflags="" + + if [[ -n $vtype && $vtype == "metadata" ]]; then + vxlandevflags="$vxlandevflags external" + elif [[ -n $vtype && $vtype == "vnifilter" || $vtype == "vnifilterg" ]]; then + vxlandevflags="$vxlandevflags external vnifilter" + tid=$((vid+brid)) + else + vxlandevflags="$vxlandevflags id $tid" + vxlandev="vxlan$tid" + fi + + if [[ -n $vtype && $vtype != "vnifilterg" ]]; then + if [[ -n "$group" && "$group" != "null" ]]; then + if [ $mcast -eq 1 ]; then + vxlandevflags="$vxlandevflags group $group" + else + vxlandevflags="$vxlandevflags remote $group" + fi + fi + fi + + if [[ -n "$port" && "$port" != "default" ]]; then + vxlandevflags="$vxlandevflags dstport $port" + fi + + # create vxlan device + if [ "$vxlandev" != "$lastvxlandev" ]; then + ip -netns hv-$hvid link add $vxlandev type vxlan local $localip $vxlandevflags dev veth0 2>/dev/null + ip -netns hv-$hvid link set $vxlandev master br$brid + ip -netns hv-$hvid link set $vxlandev up + lastvxlandev=$vxlandev + fi + + # add vlan + bridge -netns hv-$hvid vlan add vid $vid dev $hvvethif + bridge -netns hv-$hvid vlan add vid $vid pvid dev $vxlandev + + # Add bridge vni filter for tx + if [[ -n $vtype && $vtype == "metadata" || $vtype == "vnifilter" || $vtype == "vnifilterg" ]]; then + bridge -netns hv-$hvid link set dev $vxlandev vlan_tunnel on + bridge -netns hv-$hvid vlan add dev $vxlandev vid $vid tunnel_info id $tid + fi + + if [[ -n $vtype && $vtype == "metadata" ]]; then + bridge -netns hv-$hvid fdb add 00:00:00:00:00:00 dev $vxlandev \ + src_vni $tid vni $tid dst $group self + elif [[ -n $vtype && $vtype == "vnifilter" ]]; then + # Add per vni rx filter with 'bridge vni' api + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid + elif [[ -n $vtype && $vtype == "vnifilterg" ]]; then + # Add per vni group config with 'bridge vni' api + if [ -n "$group" ]; then + if [ "$family" == "v4" ]; then + if [ $mcast -eq 1 ]; then + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group + else + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group + fi + else + if [ $mcast -eq 1 ]; then + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group6 $group + else + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote6 $group + fi + fi + fi + fi + done +} + +setup_vnifilter_api() +{ + ip link add veth-host type veth peer name veth-testns + ip netns add testns + ip link set veth-testns netns testns +} + +cleanup_vnifilter_api() +{ + ip link del veth-host 2>/dev/null || true + ip netns del testns 2>/dev/null || true +} + +# tests vxlan filtering api +vxlan_vnifilter_api() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + localip="172.16.0.1" + group="239.1.1.101" + + cleanup_vnifilter_api &>/dev/null + setup_vnifilter_api + + # Duplicate vni test + # create non-vnifiltering traditional vni device + run_cmd "ip -netns testns link add vxlan100 type vxlan id 100 local $localip dev veth-testns dstport 4789" + log_test $? 0 "Create traditional vxlan device" + + # create vni filtering device + run_cmd "ip -netns testns link add vxlan-ext1 type vxlan vnifilter local $localip dev veth-testns dstport 4789" + log_test $? 1 "Cannot create vnifilter device without external flag" + + run_cmd "ip -netns testns link add vxlan-ext1 type vxlan external vnifilter local $localip dev veth-testns dstport 4789" + log_test $? 0 "Creating external vxlan device with vnifilter flag" + + run_cmd "bridge -netns testns vni add dev vxlan-ext1 vni 100" + log_test $? 0 "Cannot set in-use vni id on vnifiltering device" + + run_cmd "bridge -netns testns vni add dev vxlan-ext1 vni 200" + log_test $? 0 "Set new vni id on vnifiltering device" + + run_cmd "ip -netns testns link add vxlan-ext2 type vxlan external vnifilter local $localip dev veth-testns dstport 4789" + log_test $? 0 "Create second external vxlan device with vnifilter flag" + + run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 200" + log_test $? 255 "Cannot set in-use vni id on vnifiltering device" + + run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 300" + log_test $? 0 "Set new vni id on vnifiltering device" + + # check in bridge vni show + run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 300" + log_test $? 0 "Update vni id on vnifiltering device" + + run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 400" + log_test $? 0 "Add new vni id on vnifiltering device" + + # add multicast group per vni + run_cmd "bridge -netns testns vni add dev vxlan-ext1 vni 200 group $group" + log_test $? 0 "Set multicast group on existing vni" + + # add multicast group per vni + run_cmd "bridge -netns testns vni add dev vxlan-ext2 vni 300 group $group" + log_test $? 0 "Set multicast group on existing vni" + + # set vnifilter on an existing external vxlan device + run_cmd "ip -netns testns link set dev vxlan-ext1 type vxlan external vnifilter" + log_test $? 2 "Cannot set vnifilter flag on a device" + + # change vxlan vnifilter flag + run_cmd "ip -netns testns link set dev vxlan-ext1 type vxlan external novnifilter" + log_test $? 2 "Cannot unset vnifilter flag on a device" +} + +# Sanity test vnifilter datapath +# vnifilter vnis inherit BUM group from +# vxlan device +vxlan_vnifilter_datapath() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + + ip link add veth-hv-1 type veth peer name veth-hv-2 + setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 $hv2addr1 $hv2addr2 + setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 $hv1addr1 $hv1addr2 + + check_hv_connectivity hv2addr1 hv2addr2 + + setup-vm 1 11 1 10-v4-$hv1addr1-$hv2addr1-vnifilter,20-v4-$hv1addr1-$hv2addr1-vnifilter 0 + setup-vm 1 21 2 10-v6-$hv1addr2-$hv2addr2-vnifilter,20-v6-$hv1addr2-$hv2addr2-vnifilter 0 + + setup-vm 2 12 1 10-v4-$hv2addr1-$hv1addr1-vnifilter,20-v4-$hv2addr1-$hv1addr1-vnifilter 0 + setup-vm 2 22 2 10-v6-$hv2addr2-$hv1addr2-vnifilter,20-v6-$hv2addr2-$hv1addr2-vnifilter 0 + + check_vm_connectivity "vnifiltering vxlan" +} + +# Sanity test vnifilter datapath +# with vnifilter per vni configured BUM +# group/remote +vxlan_vnifilter_datapath_pervni() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + + ip link add veth-hv-1 type veth peer name veth-hv-2 + setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 + setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 + + check_hv_connectivity hv2addr1 hv2addr2 + + setup-vm 1 11 1 10-v4-$hv1addr1-$hv2addr1-vnifilterg,20-v4-$hv1addr1-$hv2addr1-vnifilterg 0 + setup-vm 1 21 2 10-v6-$hv1addr2-$hv2addr2-vnifilterg,20-v6-$hv1addr2-$hv2addr2-vnifilterg 0 + + setup-vm 2 12 1 10-v4-$hv2addr1-$hv1addr1-vnifilterg,20-v4-$hv2addr1-$hv1addr1-vnifilterg 0 + setup-vm 2 22 2 10-v6-$hv2addr2-$hv1addr2-vnifilterg,20-v6-$hv2addr2-$hv1addr2-vnifilterg 0 + + check_vm_connectivity "vnifiltering vxlan pervni remote" +} + + +vxlan_vnifilter_datapath_mgroup() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + group="239.1.1.100" + group6="ff07::1" + + ip link add veth-hv-1 type veth peer name veth-hv-2 + setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 + setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 + + check_hv_connectivity hv2addr1 hv2addr2 + + setup-vm 1 11 1 10-v4-$hv1addr1-$group-vnifilter,20-v4-$hv1addr1-$group-vnifilter 1 + setup-vm 1 21 2 "10-v6-$hv1addr2-$group6-vnifilter,20-v6-$hv1addr2-$group6-vnifilter" 1 + + setup-vm 2 12 1 10-v4-$hv2addr1-$group-vnifilter,20-v4-$hv2addr1-$group-vnifilter 1 + setup-vm 2 22 2 10-v6-$hv2addr2-$group6-vnifilter,20-v6-$hv2addr2-$group6-vnifilter 1 + + check_vm_connectivity "vnifiltering vxlan mgroup" +} + +vxlan_vnifilter_datapath_mgroup_pervni() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + group="239.1.1.100" + group6="ff07::1" + + ip link add veth-hv-1 type veth peer name veth-hv-2 + setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 + setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 + + check_hv_connectivity hv2addr1 hv2addr2 + + setup-vm 1 11 1 10-v4-$hv1addr1-$group-vnifilterg,20-v4-$hv1addr1-$group-vnifilterg 1 + setup-vm 1 21 2 10-v6-$hv1addr2-$group6-vnifilterg,20-v6-$hv1addr2-$group6-vnifilterg 1 + + setup-vm 2 12 1 10-v4-$hv2addr1-$group-vnifilterg,20-v4-$hv2addr1-$group-vnifilterg 1 + setup-vm 2 22 2 10-v6-$hv2addr2-$group6-vnifilterg,20-v6-$hv2addr2-$group6-vnifilterg 1 + + check_vm_connectivity "vnifiltering vxlan pervni mgroup" +} + +vxlan_vnifilter_metadata_and_traditional_mix() +{ + hv1addr1="172.16.0.1" + hv2addr1="172.16.0.2" + hv1addr2="2002:fee1::1" + hv2addr2="2002:fee1::2" + + ip link add veth-hv-1 type veth peer name veth-hv-2 + setup-hv-networking 1 $hv1addr1 24 $hv1addr2 64 + setup-hv-networking 2 $hv2addr1 24 $hv2addr2 64 + + check_hv_connectivity hv2addr1 hv2addr2 + + setup-vm 1 11 1 10-v4-$hv1addr1-$hv2addr1-vnifilter,20-v4-$hv1addr1-$hv2addr1-vnifilter 0 + setup-vm 1 21 2 10-v6-$hv1addr2-$hv2addr2-vnifilter,20-v6-$hv1addr2-$hv2addr2-vnifilter 0 + setup-vm 1 31 3 30-v4-$hv1addr1-$hv2addr1-default-4790,40-v6-$hv1addr2-$hv2addr2-default-4790,50-v4-$hv1addr1-$hv2addr1-metadata-4791 0 + + + setup-vm 2 12 1 10-v4-$hv2addr1-$hv1addr1-vnifilter,20-v4-$hv2addr1-$hv1addr1-vnifilter 0 + setup-vm 2 22 2 10-v6-$hv2addr2-$hv1addr2-vnifilter,20-v6-$hv2addr2-$hv1addr2-vnifilter 0 + setup-vm 2 32 3 30-v4-$hv2addr1-$hv1addr1-default-4790,40-v6-$hv2addr2-$hv1addr2-default-4790,50-v4-$hv2addr1-$hv1addr1-metadata-4791 0 + + check_vm_connectivity "vnifiltering vxlan pervni remote mix" + + # check VM connectivity over traditional/non-vxlan filtering vxlan devices + run_cmd "ip netns exec vm-31 ping -c 1 -W 1 10.0.30.32" + log_test $? 0 "VM connectivity over traditional vxlan (ipv4 default rdst)" + + run_cmd "ip netns exec vm-31 ping -c 1 -W 1 10.0.40.32" + log_test $? 0 "VM connectivity over traditional vxlan (ipv6 default rdst)" + + run_cmd "ip netns exec vm-31 ping -c 1 -W 1 10.0.50.32" + log_test $? 0 "VM connectivity over metadata nonfiltering vxlan (ipv4 default rdst)" +} + +while getopts :t:pP46hv o +do + case $o in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + P) PAUSE=yes;; + v) VERBOSE=$(($VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +# make sure we don't pause twice +[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip; +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip link help vxlan 2>&1 | grep -q "vnifilter" +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 too old, missing vxlan dev vnifilter setting" + sync + exit $ksft_skip +fi + +bridge vni help 2>&1 | grep -q "Usage: bridge vni" +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 bridge lacks vxlan vnifiltering support" + exit $ksft_skip +fi + +# start clean +cleanup &> /dev/null + +for t in $TESTS +do + case $t in + none) setup; exit 0;; + *) $t; cleanup;; + esac +done + +if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} +fi + +exit $ret diff --git a/tools/testing/selftests/net/timestamping.c b/tools/testing/selftests/net/timestamping.c index aee631c5284e..044bc0e9ed81 100644 --- a/tools/testing/selftests/net/timestamping.c +++ b/tools/testing/selftests/net/timestamping.c @@ -325,8 +325,8 @@ int main(int argc, char **argv) struct ifreq device; struct ifreq hwtstamp; struct hwtstamp_config hwconfig, hwconfig_requested; - struct so_timestamping so_timestamping_get = { 0, -1 }; - struct so_timestamping so_timestamping = { 0, -1 }; + struct so_timestamping so_timestamping_get = { 0, 0 }; + struct so_timestamping so_timestamping = { 0, 0 }; struct sockaddr_in addr; struct ip_mreq imr; struct in_addr iaddr; diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c index c5489341cfb8..90026a27eac0 100644 --- a/tools/testing/selftests/net/toeplitz.c +++ b/tools/testing/selftests/net/toeplitz.c @@ -52,6 +52,8 @@ #include <sys/types.h> #include <unistd.h> +#include "../kselftest.h" + #define TOEPLITZ_KEY_MIN_LEN 40 #define TOEPLITZ_KEY_MAX_LEN 60 @@ -295,7 +297,7 @@ static void __set_filter(int fd, int off_proto, uint8_t proto, int off_dport) struct sock_fprog prog = {}; prog.filter = filter; - prog.len = sizeof(filter) / sizeof(struct sock_filter); + prog.len = ARRAY_SIZE(filter); if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prog, sizeof(prog))) error(1, errno, "setsockopt filter"); } @@ -324,7 +326,7 @@ static void set_filter_null(int fd) struct sock_fprog prog = {}; prog.filter = filter; - prog.len = sizeof(filter) / sizeof(struct sock_filter); + prog.len = ARRAY_SIZE(filter); if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prog, sizeof(prog))) error(1, errno, "setsockopt filter"); } diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index fabb1d555ee5..10f2fde3686b 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -161,7 +161,7 @@ static void validate_timestamp(struct timespec *cur, int min_delay) max_delay = min_delay + cfg_delay_tolerance_usec; if (cur64 < start64 + min_delay || cur64 > start64 + max_delay) { - fprintf(stderr, "ERROR: %lu us expected between %d and %d\n", + fprintf(stderr, "ERROR: %" PRId64 " us expected between %d and %d\n", cur64 - start64, min_delay, max_delay); test_failed = true; } @@ -170,9 +170,9 @@ static void validate_timestamp(struct timespec *cur, int min_delay) static void __print_ts_delta_formatted(int64_t ts_delta) { if (cfg_print_nsec) - fprintf(stderr, "%lu ns", ts_delta); + fprintf(stderr, "%" PRId64 " ns", ts_delta); else - fprintf(stderr, "%lu us", ts_delta / NSEC_PER_USEC); + fprintf(stderr, "%" PRId64 " us", ts_delta / NSEC_PER_USEC); } static void __print_timestamp(const char *name, struct timespec *cur, diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c index c0f6a062364d..198ad5f32187 100644 --- a/tools/testing/selftests/ptp/testptp.c +++ b/tools/testing/selftests/ptp/testptp.c @@ -133,6 +133,7 @@ static void usage(char *progname) " 0 - none\n" " 1 - external time stamp\n" " 2 - periodic output\n" + " -n val shift the ptp clock time by 'val' nanoseconds\n" " -p val enable output with a period of 'val' nanoseconds\n" " -H val set output phase to 'val' nanoseconds (requires -p)\n" " -w val set output pulse width to 'val' nanoseconds (requires -p)\n" @@ -165,6 +166,7 @@ int main(int argc, char *argv[]) clockid_t clkid; int adjfreq = 0x7fffffff; int adjtime = 0; + int adjns = 0; int capabilities = 0; int extts = 0; int flagtest = 0; @@ -186,7 +188,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:p:P:sSt:T:w:z"))) { + while (EOF != (c = getopt(argc, argv, "cd:e:f:ghH:i:k:lL:n:p:P:sSt:T:w:z"))) { switch (c) { case 'c': capabilities = 1; @@ -223,6 +225,9 @@ int main(int argc, char *argv[]) return -1; } break; + case 'n': + adjns = atoi(optarg); + break; case 'p': perout = atoll(optarg); break; @@ -305,11 +310,16 @@ int main(int argc, char *argv[]) } } - if (adjtime) { + if (adjtime || adjns) { memset(&tx, 0, sizeof(tx)); - tx.modes = ADJ_SETOFFSET; + tx.modes = ADJ_SETOFFSET | ADJ_NANO; tx.time.tv_sec = adjtime; - tx.time.tv_usec = 0; + tx.time.tv_usec = adjns; + while (tx.time.tv_usec < 0) { + tx.time.tv_sec -= 1; + tx.time.tv_usec += 1000000000; + } + if (clock_adjtime(clkid, &tx) < 0) { perror("clock_adjtime"); } else { diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py index ea04f04c173e..ccb0f06ef9e3 100644 --- a/tools/testing/selftests/tc-testing/tdc_config.py +++ b/tools/testing/selftests/tc-testing/tdc_config.py @@ -21,7 +21,7 @@ NAMES = { 'BATCH_FILE': './batch.txt', 'BATCH_DIR': 'tmp', # Length of time in seconds to wait before terminating a command - 'TIMEOUT': 12, + 'TIMEOUT': 24, # Name of the namespace to use 'NS': 'tcut', # Directory containing eBPF test programs diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 2a3638c0a008..dc577461afc2 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -16,6 +16,8 @@ #include <linux/kernel.h> #include <sys/types.h> #include <sys/socket.h> +#include <time.h> +#include <sys/mman.h> #include "timeout.h" #include "control.h" @@ -391,6 +393,209 @@ static void test_seqpacket_msg_trunc_server(const struct test_opts *opts) close(fd); } +static time_t current_nsec(void) +{ + struct timespec ts; + + if (clock_gettime(CLOCK_REALTIME, &ts)) { + perror("clock_gettime(3) failed"); + exit(EXIT_FAILURE); + } + + return (ts.tv_sec * 1000000000ULL) + ts.tv_nsec; +} + +#define RCVTIMEO_TIMEOUT_SEC 1 +#define READ_OVERHEAD_NSEC 250000000 /* 0.25 sec */ + +static void test_seqpacket_timeout_client(const struct test_opts *opts) +{ + int fd; + struct timeval tv; + char dummy; + time_t read_enter_ns; + time_t read_overhead_ns; + + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + tv.tv_sec = RCVTIMEO_TIMEOUT_SEC; + tv.tv_usec = 0; + + if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, (void *)&tv, sizeof(tv)) == -1) { + perror("setsockopt 'SO_RCVTIMEO'"); + exit(EXIT_FAILURE); + } + + read_enter_ns = current_nsec(); + + if (read(fd, &dummy, sizeof(dummy)) != -1) { + fprintf(stderr, + "expected 'dummy' read(2) failure\n"); + exit(EXIT_FAILURE); + } + + if (errno != EAGAIN) { + perror("EAGAIN expected"); + exit(EXIT_FAILURE); + } + + read_overhead_ns = current_nsec() - read_enter_ns - + 1000000000ULL * RCVTIMEO_TIMEOUT_SEC; + + if (read_overhead_ns > READ_OVERHEAD_NSEC) { + fprintf(stderr, + "too much time in read(2), %lu > %i ns\n", + read_overhead_ns, READ_OVERHEAD_NSEC); + exit(EXIT_FAILURE); + } + + control_writeln("WAITDONE"); + close(fd); +} + +static void test_seqpacket_timeout_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("WAITDONE"); + close(fd); +} + +#define BUF_PATTERN_1 'a' +#define BUF_PATTERN_2 'b' + +static void test_seqpacket_invalid_rec_buffer_client(const struct test_opts *opts) +{ + int fd; + unsigned char *buf1; + unsigned char *buf2; + int buf_size = getpagesize() * 3; + + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + buf1 = malloc(buf_size); + if (!buf1) { + perror("'malloc()' for 'buf1'"); + exit(EXIT_FAILURE); + } + + buf2 = malloc(buf_size); + if (!buf2) { + perror("'malloc()' for 'buf2'"); + exit(EXIT_FAILURE); + } + + memset(buf1, BUF_PATTERN_1, buf_size); + memset(buf2, BUF_PATTERN_2, buf_size); + + if (send(fd, buf1, buf_size, 0) != buf_size) { + perror("send failed"); + exit(EXIT_FAILURE); + } + + if (send(fd, buf2, buf_size, 0) != buf_size) { + perror("send failed"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_seqpacket_invalid_rec_buffer_server(const struct test_opts *opts) +{ + int fd; + unsigned char *broken_buf; + unsigned char *valid_buf; + int page_size = getpagesize(); + int buf_size = page_size * 3; + ssize_t res; + int prot = PROT_READ | PROT_WRITE; + int flags = MAP_PRIVATE | MAP_ANONYMOUS; + int i; + + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + /* Setup first buffer. */ + broken_buf = mmap(NULL, buf_size, prot, flags, -1, 0); + if (broken_buf == MAP_FAILED) { + perror("mmap for 'broken_buf'"); + exit(EXIT_FAILURE); + } + + /* Unmap "hole" in buffer. */ + if (munmap(broken_buf + page_size, page_size)) { + perror("'broken_buf' setup"); + exit(EXIT_FAILURE); + } + + valid_buf = mmap(NULL, buf_size, prot, flags, -1, 0); + if (valid_buf == MAP_FAILED) { + perror("mmap for 'valid_buf'"); + exit(EXIT_FAILURE); + } + + /* Try to fill buffer with unmapped middle. */ + res = read(fd, broken_buf, buf_size); + if (res != -1) { + fprintf(stderr, + "expected 'broken_buf' read(2) failure, got %zi\n", + res); + exit(EXIT_FAILURE); + } + + if (errno != ENOMEM) { + perror("unexpected errno of 'broken_buf'"); + exit(EXIT_FAILURE); + } + + /* Try to fill valid buffer. */ + res = read(fd, valid_buf, buf_size); + if (res < 0) { + perror("unexpected 'valid_buf' read(2) failure"); + exit(EXIT_FAILURE); + } + + if (res != buf_size) { + fprintf(stderr, + "invalid 'valid_buf' read(2), expected %i, got %zi\n", + buf_size, res); + exit(EXIT_FAILURE); + } + + for (i = 0; i < buf_size; i++) { + if (valid_buf[i] != BUF_PATTERN_2) { + fprintf(stderr, + "invalid pattern for 'valid_buf' at %i, expected %hhX, got %hhX\n", + i, BUF_PATTERN_2, valid_buf[i]); + exit(EXIT_FAILURE); + } + } + + /* Unmap buffers. */ + munmap(broken_buf, page_size); + munmap(broken_buf + page_size * 2, page_size); + munmap(valid_buf, buf_size); + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -431,6 +636,16 @@ static struct test_case test_cases[] = { .run_client = test_seqpacket_msg_trunc_client, .run_server = test_seqpacket_msg_trunc_server, }, + { + .name = "SOCK_SEQPACKET timeout", + .run_client = test_seqpacket_timeout_client, + .run_server = test_seqpacket_timeout_server, + }, + { + .name = "SOCK_SEQPACKET invalid receive buffer", + .run_client = test_seqpacket_invalid_rec_buffer_client, + .run_server = test_seqpacket_invalid_rec_buffer_server, + }, {}, }; |