diff options
Diffstat (limited to 'tools')
173 files changed, 6519 insertions, 1393 deletions
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index d73232be1e99..1fcf5b01a193 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -137,7 +137,10 @@ endif BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o) +$(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP) + OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o +$(OBJS): $(LIBBPF) VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index f7e5ff3586c9..49743ad96851 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -37,6 +37,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_TAG] = "TAG", }; struct btf_attach_table { @@ -347,6 +348,17 @@ static int dump_btf_type(const struct btf *btf, __u32 id, printf(" size=%u", t->size); break; } + case BTF_KIND_TAG: { + const struct btf_tag *tag = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_int_field(w, "component_idx", tag->component_idx); + } else { + printf(" type_id=%u component_idx=%d", t->type, tag->component_idx); + } + break; + } default: break; } diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index 7f36385aa9e2..ade44577688e 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -624,6 +624,7 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type, */ switch (id) { case BPF_FUNC_trace_printk: + case BPF_FUNC_trace_vprintk: case BPF_FUNC_probe_write_user: if (!full_mode) continue; diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index d40d92bbf0e4..cc835859465b 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -238,8 +238,8 @@ static void codegen(const char *template, ...) } else if (c == '\n') { break; } else { - p_err("unrecognized character at pos %td in template '%s'", - src - template - 1, template); + p_err("unrecognized character at pos %td in template '%s': '%c'", + src - template - 1, template, c); free(s); exit(-1); } @@ -406,7 +406,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) } bpf_object__for_each_map(map, obj) { - const char * ident; + const char *ident; ident = get_map_ident(map); if (!ident) @@ -803,7 +803,10 @@ static int do_skeleton(int argc, char **argv) } \n\ \n\ err = %1$s__create_skeleton(obj); \n\ - err = err ?: bpf_object__open_skeleton(obj->skeleton, opts);\n\ + if (err) \n\ + goto err_out; \n\ + \n\ + err = bpf_object__open_skeleton(obj->skeleton, opts);\n\ if (err) \n\ goto err_out; \n\ \n\ @@ -862,6 +865,8 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ \n\ + static inline const void *%1$s__elf_bytes(size_t *sz); \n\ + \n\ static inline int \n\ %1$s__create_skeleton(struct %1$s *obj) \n\ { \n\ @@ -943,10 +948,20 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ \n\ - s->data_sz = %d; \n\ - s->data = (void *)\"\\ \n\ - ", - file_sz); + s->data = (void *)%2$s__elf_bytes(&s->data_sz); \n\ + \n\ + return 0; \n\ + err: \n\ + bpf_object__destroy_skeleton(s); \n\ + return -ENOMEM; \n\ + } \n\ + \n\ + static inline const void *%2$s__elf_bytes(size_t *sz) \n\ + { \n\ + *sz = %1$d; \n\ + return (const void *)\"\\ \n\ + " + , file_sz, obj_name); /* embed contents of BPF object file */ print_hex(obj_data, file_sz); @@ -954,11 +969,6 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ \"; \n\ - \n\ - return 0; \n\ - err: \n\ - bpf_object__destroy_skeleton(s); \n\ - return -ENOMEM; \n\ } \n\ \n\ #endif /* %s */ \n\ diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index bb9fa8de7e62..08b75e314ae7 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -26,6 +26,7 @@ LIBBPF_SRC := $(srctree)/tools/lib/bpf/ SUBCMD_SRC := $(srctree)/tools/lib/subcmd/ BPFOBJ := $(OUTPUT)/libbpf/libbpf.a +LIBBPF_OUT := $(abspath $(dir $(BPFOBJ)))/ SUBCMDOBJ := $(OUTPUT)/libsubcmd/libsubcmd.a BINARY := $(OUTPUT)/resolve_btfids @@ -41,7 +42,7 @@ $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@) $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT)/libbpf - $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) $(abspath $@) CFLAGS := -g \ -I$(srctree)/tools/include \ @@ -54,7 +55,7 @@ LIBS = -lelf -lz export srctree OUTPUT CFLAGS Q include $(srctree)/tools/build/Makefile.include -$(BINARY_IN): fixdep FORCE | $(OUTPUT) +$(BINARY_IN): $(BPFOBJ) fixdep FORCE | $(OUTPUT) $(Q)$(MAKE) $(build)=resolve_btfids $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 791f31dd0abe..6fc59d61937a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1629,7 +1629,7 @@ union bpf_attr { * u32 bpf_get_smp_processor_id(void) * Description * Get the SMP (symmetric multiprocessing) processor id. Note that - * all programs run with preemption disabled, which means that the + * all programs run with migration disabled, which means that the * SMP processor id is stable during all the execution of the * program. * Return @@ -4046,7 +4046,7 @@ union bpf_attr { * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or @@ -4751,7 +4751,8 @@ union bpf_attr { * Each format specifier in **fmt** corresponds to one u64 element * in the **data** array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* - * array. The *data_len* is the size of *data* in bytes. + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. * * Formats **%s** and **%p{i,I}{4,6}** require to read kernel * memory. Reading kernel memory may fail due to either invalid @@ -4877,6 +4878,37 @@ union bpf_attr { * Get the struct pt_regs associated with **task**. * Return * A pointer to struct pt_regs. + * + * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags) + * Description + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5055,6 +5087,8 @@ union bpf_attr { FN(get_func_ip), \ FN(get_attach_cookie), \ FN(task_pt_regs), \ + FN(get_branch_snapshot), \ + FN(trace_vprintk), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5284,6 +5318,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; + __u32 :32; /* Padding, future use. */ + __u64 hwtstamp; }; struct bpf_tunnel_key { diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index d27b1708efe9..642b6ecb37d7 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and VAR. + * FUNC, FUNC_PROTO, VAR and TAG. * "type" is a type_id referring to another type. */ union { @@ -56,25 +56,29 @@ struct btf_type { #define BTF_INFO_VLEN(info) ((info) & 0xffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) -#define BTF_KIND_UNKN 0 /* Unknown */ -#define BTF_KIND_INT 1 /* Integer */ -#define BTF_KIND_PTR 2 /* Pointer */ -#define BTF_KIND_ARRAY 3 /* Array */ -#define BTF_KIND_STRUCT 4 /* Struct */ -#define BTF_KIND_UNION 5 /* Union */ -#define BTF_KIND_ENUM 6 /* Enumeration */ -#define BTF_KIND_FWD 7 /* Forward */ -#define BTF_KIND_TYPEDEF 8 /* Typedef */ -#define BTF_KIND_VOLATILE 9 /* Volatile */ -#define BTF_KIND_CONST 10 /* Const */ -#define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_FUNC 12 /* Function */ -#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_VAR 14 /* Variable */ -#define BTF_KIND_DATASEC 15 /* Section */ -#define BTF_KIND_FLOAT 16 /* Floating point */ -#define BTF_KIND_MAX BTF_KIND_FLOAT -#define NR_BTF_KINDS (BTF_KIND_MAX + 1) +enum { + BTF_KIND_UNKN = 0, /* Unknown */ + BTF_KIND_INT = 1, /* Integer */ + BTF_KIND_PTR = 2, /* Pointer */ + BTF_KIND_ARRAY = 3, /* Array */ + BTF_KIND_STRUCT = 4, /* Struct */ + BTF_KIND_UNION = 5, /* Union */ + BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_FWD = 7, /* Forward */ + BTF_KIND_TYPEDEF = 8, /* Typedef */ + BTF_KIND_VOLATILE = 9, /* Volatile */ + BTF_KIND_CONST = 10, /* Const */ + BTF_KIND_RESTRICT = 11, /* Restrict */ + BTF_KIND_FUNC = 12, /* Function */ + BTF_KIND_FUNC_PROTO = 13, /* Function Proto */ + BTF_KIND_VAR = 14, /* Variable */ + BTF_KIND_DATASEC = 15, /* Section */ + BTF_KIND_FLOAT = 16, /* Floating point */ + BTF_KIND_TAG = 17, /* Tag */ + + NR_BTF_KINDS, + BTF_KIND_MAX = NR_BTF_KINDS - 1, +}; /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. @@ -170,4 +174,15 @@ struct btf_var_secinfo { __u32 size; }; +/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe + * additional information related to the tag applied location. + * If component_idx == -1, the tag is applied to a struct, union, + * variable or function. Otherwise, it is applied to a struct/union + * member or a func argument, and component_idx indicates which member + * or argument (0 ... vlen-1). + */ +struct btf_tag { + __s32 component_idx; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 5d4cfac671d5..0da84cb9e66d 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -libbpf_version.h libbpf.pc libbpf.so.* TAGS diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 74c3b73a5fbe..0f766345506f 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -8,7 +8,8 @@ VERSION_SCRIPT := libbpf.map LIBBPF_VERSION := $(shell \ grep -oE '^LIBBPF_([0-9.]+)' $(VERSION_SCRIPT) | \ sort -rV | head -n1 | cut -d'_' -f2) -LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION))) +LIBBPF_MAJOR_VERSION := $(word 1,$(subst ., ,$(LIBBPF_VERSION))) +LIBBPF_MINOR_VERSION := $(word 2,$(subst ., ,$(LIBBPF_VERSION))) MAKEFLAGS += --no-print-directory @@ -59,7 +60,8 @@ ifndef VERBOSE VERBOSE = 0 endif -INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi +INCLUDES = -I$(if $(OUTPUT),$(OUTPUT),.) \ + -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi export prefix libdir src obj @@ -112,6 +114,7 @@ STATIC_OBJDIR := $(OUTPUT)staticobjs/ BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o BPF_HELPER_DEFS := $(OUTPUT)bpf_helper_defs.h +BPF_GENERATED := $(BPF_HELPER_DEFS) LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) @@ -136,7 +139,7 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force $(BPF_HELPER_DEFS) +$(BPF_IN_SHARED): force $(BPF_GENERATED) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -154,7 +157,7 @@ $(BPF_IN_SHARED): force $(BPF_HELPER_DEFS) echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force $(BPF_HELPER_DEFS) +$(BPF_IN_STATIC): force $(BPF_GENERATED) $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h @@ -179,7 +182,7 @@ $(OUTPUT)libbpf.pc: -e "s|@VERSION@|$(LIBBPF_VERSION)|" \ < libbpf.pc.template > $@ -check: check_abi +check: check_abi check_version check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) @if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then \ @@ -205,6 +208,21 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) exit 1; \ fi +HDR_MAJ_VERSION := $(shell grep -oE '^\#define LIBBPF_MAJOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3) +HDR_MIN_VERSION := $(shell grep -oE '^\#define LIBBPF_MINOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3) + +check_version: $(VERSION_SCRIPT) libbpf_version.h + @if [ "$(HDR_MAJ_VERSION)" != "$(LIBBPF_MAJOR_VERSION)" ]; then \ + echo "Error: libbpf major version mismatch detected: " \ + "'$(HDR_MAJ_VERSION)' != '$(LIBBPF_MAJOR_VERSION)'" >&2; \ + exit 1; \ + fi + @if [ "$(HDR_MIN_VERSION)" != "$(LIBBPF_MINOR_VERSION)" ]; then \ + echo "Error: libbpf minor version mismatch detected: " \ + "'$(HDR_MIN_VERSION)' != '$(LIBBPF_MINOR_VERSION)'" >&2; \ + exit 1; \ + fi + define do_install_mkdir if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ @@ -224,10 +242,11 @@ install_lib: all_cmd cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \ - bpf_helpers.h $(BPF_HELPER_DEFS) bpf_tracing.h \ - bpf_endian.h bpf_core_read.h skel_internal.h + bpf_helpers.h $(BPF_GENERATED) bpf_tracing.h \ + bpf_endian.h bpf_core_read.h skel_internal.h \ + libbpf_version.h -install_headers: $(BPF_HELPER_DEFS) +install_headers: $(BPF_GENERATED) $(call QUIET_INSTALL, headers) \ $(foreach hdr,$(INSTALL_HEADERS), \ $(call do_install,$(hdr),$(prefix)/include/bpf,644);) @@ -240,12 +259,12 @@ install: install_lib install_pkgconfig install_headers clean: $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ - *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ + *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED) \ $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ $(addprefix $(OUTPUT), \ *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc) -PHONY += force cscope tags +PHONY += force cscope tags check check_abi check_version force: cscope: diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index b9987c3efa3c..963b1060d944 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -14,14 +14,6 @@ #define __type(name, val) typeof(val) *name #define __array(name, val) typeof(val) *name[] -/* Helper macro to print out debug messages */ -#define bpf_printk(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) - /* * Helper macro to place programs, maps, license in * different sections in elf_bpf file. Section names @@ -224,4 +216,47 @@ enum libbpf_tristate { ___param, sizeof(___param)); \ }) +#ifdef BPF_NO_GLOBAL_DATA +#define BPF_PRINTK_FMT_MOD +#else +#define BPF_PRINTK_FMT_MOD static const +#endif + +#define __bpf_printk(fmt, ...) \ +({ \ + BPF_PRINTK_FMT_MOD char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +/* + * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments + * instead of an array of u64. + */ +#define __bpf_vprintk(fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_trace_vprintk(___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ +}) + +/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args + * Otherwise use __bpf_vprintk + */ +#define ___bpf_pick_printk(...) \ + ___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, \ + __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\ + __bpf_printk /*1*/, __bpf_printk /*0*/) + +/* Helper macro to print out debug messages */ +#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args) + #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 77dc24d58302..6ad63e4d418a 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -304,6 +304,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); + case BTF_KIND_TAG: + return base_size + sizeof(struct btf_tag); default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; @@ -376,6 +378,9 @@ static int btf_bswap_type_rest(struct btf_type *t) v->size = bswap_32(v->size); } return 0; + case BTF_KIND_TAG: + btf_tag(t)->component_idx = bswap_32(btf_tag(t)->component_idx); + return 0; default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; @@ -586,6 +591,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_VAR: + case BTF_KIND_TAG: type_id = t->type; break; case BTF_KIND_ARRAY: @@ -2440,6 +2446,48 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ return 0; } +/* + * Append new BTF_KIND_TAG type with: + * - *value* - non-empty/non-NULL string; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * - *component_idx* - -1 for tagging reference type, otherwise struct/union + * member or function argument index; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx) +{ + struct btf_type *t; + int sz, value_off; + + if (!value || !value[0] || component_idx < -1) + return libbpf_err(-EINVAL); + + if (validate_type_id(ref_type_id)) + return libbpf_err(-EINVAL); + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type) + sizeof(struct btf_tag); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + value_off = btf__add_str(btf, value); + if (value_off < 0) + return value_off; + + t->name_off = value_off; + t->info = btf_type_info(BTF_KIND_TAG, 0, false); + t->type = ref_type_id; + btf_tag(t)->component_idx = component_idx; + + return btf_commit_type(btf, sz); +} + struct btf_ext_sec_setup_param { __u32 off; __u32 len; @@ -3256,8 +3304,8 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) t1->size == t2->size; } -/* Calculate type signature hash of INT. */ -static long btf_hash_int(struct btf_type *t) +/* Calculate type signature hash of INT or TAG. */ +static long btf_hash_int_tag(struct btf_type *t) { __u32 info = *(__u32 *)(t + 1); long h; @@ -3267,8 +3315,8 @@ static long btf_hash_int(struct btf_type *t) return h; } -/* Check structural equality of two INTs. */ -static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2) +/* Check structural equality of two INTs or TAGs. */ +static bool btf_equal_int_tag(struct btf_type *t1, struct btf_type *t2) { __u32 info1, info2; @@ -3535,7 +3583,8 @@ static int btf_dedup_prep(struct btf_dedup *d) h = btf_hash_common(t); break; case BTF_KIND_INT: - h = btf_hash_int(t); + case BTF_KIND_TAG: + h = btf_hash_int_tag(t); break; case BTF_KIND_ENUM: h = btf_hash_enum(t); @@ -3590,14 +3639,15 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_FUNC_PROTO: case BTF_KIND_VAR: case BTF_KIND_DATASEC: + case BTF_KIND_TAG: return 0; case BTF_KIND_INT: - h = btf_hash_int(t); + h = btf_hash_int_tag(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; cand = btf_type_by_id(d->btf, cand_id); - if (btf_equal_int(t, cand)) { + if (btf_equal_int_tag(t, cand)) { new_id = cand_id; break; } @@ -3881,7 +3931,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, switch (cand_kind) { case BTF_KIND_INT: - return btf_equal_int(cand_type, canon_type); + return btf_equal_int_tag(cand_type, canon_type); case BTF_KIND_ENUM: if (d->opts.dont_resolve_fwds) @@ -4210,6 +4260,23 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) } break; + case BTF_KIND_TAG: + ref_type_id = btf_dedup_ref_type(d, t->type); + if (ref_type_id < 0) + return ref_type_id; + t->type = ref_type_id; + + h = btf_hash_int_tag(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_int_tag(t, cand)) { + new_id = cand_id; + break; + } + } + break; + case BTF_KIND_ARRAY: { struct btf_array *info = btf_array(t); @@ -4482,6 +4549,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: + case BTF_KIND_TAG: return visit(&t->type, ctx); case BTF_KIND_ARRAY: { diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 4a711f990904..2cfe31327920 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ /* Copyright (c) 2018 Facebook */ +/*! \file */ #ifndef __LIBBPF_BTF_H #define __LIBBPF_BTF_H @@ -30,11 +31,80 @@ enum btf_endianness { BTF_BIG_ENDIAN = 1, }; +/** + * @brief **btf__free()** frees all data of a BTF object + * @param btf BTF object to free + */ LIBBPF_API void btf__free(struct btf *btf); +/** + * @brief **btf__new()** creates a new instance of a BTF object from the raw + * bytes of an ELF's BTF section + * @param data raw bytes + * @param size number of bytes passed in `data` + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new(const void *data, __u32 size); + +/** + * @brief **btf__new_split()** create a new instance of a BTF object from the + * provided raw data bytes. It takes another BTF instance, **base_btf**, which + * serves as a base BTF, which is extended by types in a newly created BTF + * instance + * @param data raw bytes + * @param size length of raw bytes + * @param base_btf the base BTF object + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * If *base_btf* is NULL, `btf__new_split()` is equivalent to `btf__new()` and + * creates non-split BTF. + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf); + +/** + * @brief **btf__new_empty()** creates an empty BTF object. Use + * `btf__add_*()` to populate such BTF object. + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new_empty(void); + +/** + * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an + * ELF BTF section except with a base BTF on top of which split BTF should be + * based + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * If *base_btf* is NULL, `btf__new_empty_split()` is equivalent to + * `btf__new_empty()` and creates non-split BTF. + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf); LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext); @@ -50,9 +120,11 @@ LIBBPF_API struct btf *libbpf_find_kernel_btf(void); LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id); LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf); +LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead") LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf); LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf); +LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead") LIBBPF_API int btf__load(struct btf *btf); LIBBPF_API int btf__load_into_kernel(struct btf *btf); LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, @@ -141,6 +213,10 @@ LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __u32 byte_sz); +/* tag construction API */ +LIBBPF_API int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx); + struct btf_dedup_opts { unsigned int dedup_table_size; bool dont_resolve_fwds; @@ -328,6 +404,11 @@ static inline bool btf_is_float(const struct btf_type *t) return btf_kind(t) == BTF_KIND_FLOAT; } +static inline bool btf_is_tag(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_TAG; +} + static inline __u8 btf_int_encoding(const struct btf_type *t) { return BTF_INT_ENCODING(*(__u32 *)(t + 1)); @@ -396,6 +477,12 @@ btf_var_secinfos(const struct btf_type *t) return (struct btf_var_secinfo *)(t + 1); } +struct btf_tag; +static inline struct btf_tag *btf_tag(const struct btf_type *t) +{ + return (struct btf_tag *)(t + 1); +} + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index e4b483f15fb9..ad6df97295ae 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -316,6 +316,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: + case BTF_KIND_TAG: d->type_states[t->type].referenced = 1; break; @@ -583,6 +584,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) case BTF_KIND_FUNC: case BTF_KIND_VAR: case BTF_KIND_DATASEC: + case BTF_KIND_TAG: d->type_states[id].order_state = ORDERED; return 0; @@ -2215,6 +2217,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, case BTF_KIND_FWD: case BTF_KIND_FUNC: case BTF_KIND_FUNC_PROTO: + case BTF_KIND_TAG: err = btf_dump_unsupported_data(d, t, id); break; case BTF_KIND_INT: diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 8df718a6b142..80087b13877f 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -5,6 +5,7 @@ #include <string.h> #include <errno.h> #include <linux/filter.h> +#include <sys/param.h> #include "btf.h" #include "bpf.h" #include "libbpf.h" @@ -135,13 +136,17 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level) static int add_data(struct bpf_gen *gen, const void *data, __u32 size) { + __u32 size8 = roundup(size, 8); + __u64 zero = 0; void *prev; - if (realloc_data_buf(gen, size)) + if (realloc_data_buf(gen, size8)) return 0; prev = gen->data_cur; memcpy(gen->data_cur, data, size); gen->data_cur += size; + memcpy(gen->data_cur, &zero, size8 - size); + gen->data_cur += size8 - size; return prev - gen->data_start; } diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e4f83c304ec9..8892f2f1bbcc 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -195,6 +195,8 @@ enum kern_feature_id { FEAT_BTF_FLOAT, /* BPF perf link support */ FEAT_PERF_LINK, + /* BTF_KIND_TAG support */ + FEAT_BTF_TAG, __FEAT_CNT, }; @@ -218,18 +220,40 @@ struct reloc_desc { struct bpf_sec_def; -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec, - struct bpf_program *prog); +typedef int (*init_fn_t)(struct bpf_program *prog, long cookie); +typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_params *attr, 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, + /* expected_attach_type is optional, if kernel doesn't support that */ + SEC_EXP_ATTACH_OPT = 1, + /* legacy, only used by libbpf_get_type_names() and + * libbpf_attach_type_by_name(), not used by libbpf itself at all. + * This used to be associated with cgroup (and few other) BPF programs + * that were attachable through BPF_PROG_ATTACH command. Pretty + * meaningless nowadays, though. + */ + SEC_ATTACHABLE = 2, + SEC_ATTACHABLE_OPT = SEC_ATTACHABLE | SEC_EXP_ATTACH_OPT, + /* attachment target is specified through BTF ID in either kernel or + * other BPF program's BTF object */ + SEC_ATTACH_BTF = 4, + /* BPF program type allows sleeping/blocking in kernel */ + SEC_SLEEPABLE = 8, + /* allow non-strict prefix matching */ + SEC_SLOPPY_PFX = 16, +}; struct bpf_sec_def { const char *sec; - size_t len; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; - bool is_exp_attach_type_optional; - bool is_attachable; - bool is_attach_btf; - bool is_sleepable; + long cookie; + + init_fn_t init_fn; + preload_fn_t preload_fn; attach_fn_t attach_fn; }; @@ -1664,7 +1688,7 @@ static int bpf_object__process_kconfig_line(struct bpf_object *obj, void *ext_val; __u64 num; - if (strncmp(buf, "CONFIG_", 7)) + if (!str_has_pfx(buf, "CONFIG_")) return 0; sep = strchr(buf, '='); @@ -1844,6 +1868,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) + continue; nr_maps++; } /* Assume equally sized map definitions */ @@ -1868,6 +1894,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION) + continue; map = bpf_object__add_map(obj); if (IS_ERR(map)) @@ -1880,8 +1908,7 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return -LIBBPF_ERRNO__FORMAT; } - if (GELF_ST_TYPE(sym.st_info) == STT_SECTION - || GELF_ST_BIND(sym.st_info) == STB_LOCAL) { + if (GELF_ST_BIND(sym.st_info) == STB_LOCAL) { pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); return -ENOTSUP; } @@ -1987,6 +2014,7 @@ static const char *__btf_kind_str(__u16 kind) case BTF_KIND_VAR: return "var"; case BTF_KIND_DATASEC: return "datasec"; case BTF_KIND_FLOAT: return "float"; + case BTF_KIND_TAG: return "tag"; default: return "unknown"; } } @@ -2486,8 +2514,9 @@ static bool btf_needs_sanitization(struct bpf_object *obj) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); + bool has_tag = kernel_supports(obj, FEAT_BTF_TAG); - return !has_func || !has_datasec || !has_func_global || !has_float; + return !has_func || !has_datasec || !has_func_global || !has_float || !has_tag; } static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) @@ -2496,14 +2525,15 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); + bool has_tag = kernel_supports(obj, FEAT_BTF_TAG); struct btf_type *t; int i, j, vlen; for (i = 1; i <= btf__get_nr_types(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); - if (!has_datasec && btf_is_var(t)) { - /* replace VAR with INT */ + if ((!has_datasec && btf_is_var(t)) || (!has_tag && btf_is_tag(t))) { + /* replace VAR/TAG with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); /* * using size = 1 is the safest choice, 4 will be too @@ -2909,7 +2939,7 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn) static bool is_sec_name_dwarf(const char *name) { /* approximation, but the actual list is too long */ - return strncmp(name, ".debug_", sizeof(".debug_") - 1) == 0; + return str_has_pfx(name, ".debug_"); } static bool ignore_elf_section(GElf_Shdr *hdr, const char *name) @@ -2931,7 +2961,7 @@ static bool ignore_elf_section(GElf_Shdr *hdr, const char *name) if (is_sec_name_dwarf(name)) return true; - if (strncmp(name, ".rel", sizeof(".rel") - 1) == 0) { + if (str_has_pfx(name, ".rel")) { name += sizeof(".rel") - 1; /* DWARF section relocations */ if (is_sec_name_dwarf(name)) @@ -2993,6 +3023,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } } + if (!obj->efile.symbols) { + pr_warn("elf: couldn't find symbol table in %s, stripped object file?\n", + obj->path); + return -ENOENT; + } + scn = NULL; while ((scn = elf_nextscn(elf, scn)) != NULL) { idx++; @@ -4207,6 +4243,23 @@ static int probe_kern_btf_float(void) strs, sizeof(strs))); } +static int probe_kern_btf_tag(void) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* attr */ + BTF_TYPE_TAG_ENC(1, 2, -1), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + static int probe_kern_array_mmap(void) { struct bpf_create_map_attr attr = { @@ -4423,6 +4476,9 @@ static struct kern_feature_desc { [FEAT_PERF_LINK] = { "BPF perf link support", probe_perf_link, }, + [FEAT_BTF_TAG] = { + "BTF_KIND_TAG support", probe_kern_btf_tag, + }, }; static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) @@ -4613,6 +4669,30 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.inner_map_fd = map->inner_map_fd; } + switch (def->type) { + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + case BPF_MAP_TYPE_CGROUP_ARRAY: + case BPF_MAP_TYPE_STACK_TRACE: + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: + case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_SOCKHASH: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_RINGBUF: + create_attr.btf_fd = 0; + create_attr.btf_key_type_id = 0; + create_attr.btf_value_type_id = 0; + map->btf_key_type_id = 0; + map->btf_value_type_id = 0; + default: + break; + } + if (obj->gen_loader) { bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps); /* Pretend to have valid FD to pass various fd >= 0 checks. @@ -6064,6 +6144,48 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program return 0; } +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_params *attr, long cookie) +{ + enum sec_def_flags def = cookie; + + /* old kernels might not support specifying expected_attach_type */ + if ((def & SEC_EXP_ATTACH_OPT) && !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE)) + attr->expected_attach_type = 0; + + if (def & SEC_SLEEPABLE) + attr->prog_flags |= BPF_F_SLEEPABLE; + + if ((prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_LSM || + prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { + int btf_obj_fd = 0, btf_type_id = 0, err; + const char *attach_name; + + attach_name = strchr(prog->sec_name, '/') + 1; + err = libbpf_find_attach_btf_id(prog, attach_name, &btf_obj_fd, &btf_type_id); + if (err) + return err; + + /* cache resolved BTF FD and BTF type ID in the prog */ + prog->attach_btf_obj_fd = btf_obj_fd; + prog->attach_btf_id = btf_type_id; + + /* but by now libbpf common logic is not utilizing + * prog->atach_btf_obj_fd/prog->attach_btf_id anymore because + * this callback is called after attrs were populated by + * libbpf, so this callback has to update attr explicitly here + */ + attr->attach_btf_obj_fd = btf_obj_fd; + attr->attach_btf_id = btf_type_id; + } + return 0; +} + static int load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, char *license, __u32 kern_version, int *pfd) @@ -6072,7 +6194,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; char *log_buf = NULL; - int btf_fd, ret; + int btf_fd, ret, err; if (prog->type == BPF_PROG_TYPE_UNSPEC) { /* @@ -6088,22 +6210,15 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, return -EINVAL; load_attr.prog_type = prog->type; - /* old kernels might not support specifying expected_attach_type */ - if (!kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE) && prog->sec_def && - prog->sec_def->is_exp_attach_type_optional) - load_attr.expected_attach_type = 0; - else - load_attr.expected_attach_type = prog->expected_attach_type; + load_attr.expected_attach_type = prog->expected_attach_type; if (kernel_supports(prog->obj, FEAT_PROG_NAME)) load_attr.name = prog->name; load_attr.insns = insns; load_attr.insn_cnt = insns_cnt; load_attr.license = license; load_attr.attach_btf_id = prog->attach_btf_id; - if (prog->attach_prog_fd) - load_attr.attach_prog_fd = prog->attach_prog_fd; - else - load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; + load_attr.attach_prog_fd = prog->attach_prog_fd; + load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; load_attr.attach_btf_id = prog->attach_btf_id; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; @@ -6122,6 +6237,16 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.log_level = prog->log_level; load_attr.prog_flags = prog->prog_flags; + /* 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 (err < 0) { + pr_warn("prog '%s': failed to prepare load attributes: %d\n", + prog->name, err); + return err; + } + } + if (prog->obj->gen_loader) { bpf_gen__prog_load(prog->obj->gen_loader, &load_attr, prog - prog->obj->programs); @@ -6237,8 +6362,6 @@ static int bpf_program__record_externs(struct bpf_program *prog) return 0; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id); - int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) { int err = 0, fd, i; @@ -6248,19 +6371,6 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) return libbpf_err(-EINVAL); } - if ((prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_LSM || - prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { - int btf_obj_fd = 0, btf_type_id = 0; - - err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id); - if (err) - return libbpf_err(err); - - prog->attach_btf_obj_fd = btf_obj_fd; - prog->attach_btf_id = btf_type_id; - } - if (prog->instances.nr < 0 || !prog->instances.fds) { if (prog->preprocessor) { pr_warn("Internal error: can't load program '%s'\n", @@ -6367,12 +6477,51 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) static const struct bpf_sec_def *find_sec_def(const char *sec_name); +static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts) +{ + struct bpf_program *prog; + int err; + + bpf_object__for_each_program(prog, obj) { + prog->sec_def = find_sec_def(prog->sec_name); + if (!prog->sec_def) { + /* couldn't guess, but user might manually specify */ + pr_debug("prog '%s': unrecognized ELF section name '%s'\n", + prog->name, prog->sec_name); + continue; + } + + bpf_program__set_type(prog, prog->sec_def->prog_type); + bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type); + +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING || + prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) + prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); +#pragma GCC diagnostic pop + + /* 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 (err < 0) { + pr_warn("prog '%s': failed to initialize: %d\n", + prog->name, err); + return err; + } + } + } + + return 0; +} + static struct bpf_object * __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts) { const char *obj_name, *kconfig, *btf_tmp_path; - struct bpf_program *prog; struct bpf_object *obj; char tmp_name[64]; int err; @@ -6430,30 +6579,12 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, err = err ? : bpf_object__collect_externs(obj); err = err ? : bpf_object__finalize_btf(obj); err = err ? : bpf_object__init_maps(obj, opts); + err = err ? : bpf_object_init_progs(obj, opts); err = err ? : bpf_object__collect_relos(obj); if (err) goto out; - bpf_object__elf_finish(obj); - - bpf_object__for_each_program(prog, obj) { - prog->sec_def = find_sec_def(prog->sec_name); - if (!prog->sec_def) { - /* couldn't guess, but user might manually specify */ - pr_debug("prog '%s': unrecognized ELF section name '%s'\n", - prog->name, prog->sec_name); - continue; - } - if (prog->sec_def->is_sleepable) - prog->prog_flags |= BPF_F_SLEEPABLE; - bpf_program__set_type(prog, prog->sec_def->prog_type); - bpf_program__set_expected_attach_type(prog, - prog->sec_def->expected_attach_type); - - if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING || - prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) - prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); - } + bpf_object__elf_finish(obj); return obj; out: @@ -6807,8 +6938,7 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, if (err) return err; pr_debug("extern (kcfg) %s=0x%x\n", ext->name, kver); - } else if (ext->type == EXT_KCFG && - strncmp(ext->name, "CONFIG_", 7) == 0) { + } else if (ext->type == EXT_KCFG && str_has_pfx(ext->name, "CONFIG_")) { need_config = true; } else if (ext->type == EXT_KSYM) { if (ext->ksym.type_id) @@ -7869,223 +7999,143 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, prog->expected_attach_type = type; } -#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional, \ - attachable, attach_btf) \ - { \ - .sec = string, \ - .len = sizeof(string) - 1, \ - .prog_type = ptype, \ - .expected_attach_type = eatype, \ - .is_exp_attach_type_optional = eatype_optional, \ - .is_attachable = attachable, \ - .is_attach_btf = attach_btf, \ - } - -/* Programs that can NOT be attached. */ -#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0) - -/* Programs that can be attached. */ -#define BPF_APROG_SEC(string, ptype, atype) \ - BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0) - -/* Programs that must specify expected attach type at load time. */ -#define BPF_EAPROG_SEC(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0) - -/* Programs that use BTF to identify attach point */ -#define BPF_PROG_BTF(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1) - -/* Programs that can be attached but attach type can't be identified by section - * name. Kept for backward compatibility. - */ -#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype) - -#define SEC_DEF(sec_pfx, ptype, ...) { \ +#define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ .sec = sec_pfx, \ - .len = sizeof(sec_pfx) - 1, \ .prog_type = BPF_PROG_TYPE_##ptype, \ + .expected_attach_type = atype, \ + .cookie = (long)(flags), \ + .preload_fn = libbpf_preload_prog, \ __VA_ARGS__ \ } -static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, - struct bpf_program *prog); +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 const struct bpf_sec_def section_defs[] = { - BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), - BPF_EAPROG_SEC("sk_reuseport/migrate", BPF_PROG_TYPE_SK_REUSEPORT, - BPF_SK_REUSEPORT_SELECT_OR_MIGRATE), - BPF_EAPROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT, - BPF_SK_REUSEPORT_SELECT), - SEC_DEF("kprobe/", KPROBE, - .attach_fn = attach_kprobe), - BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), - SEC_DEF("kretprobe/", KPROBE, - .attach_fn = attach_kprobe), - BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), - BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), - BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), - SEC_DEF("tracepoint/", TRACEPOINT, - .attach_fn = attach_tp), - SEC_DEF("tp/", TRACEPOINT, - .attach_fn = attach_tp), - SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, - .attach_fn = attach_raw_tp), - SEC_DEF("raw_tp/", RAW_TRACEPOINT, - .attach_fn = attach_raw_tp), - SEC_DEF("tp_btf/", TRACING, - .expected_attach_type = BPF_TRACE_RAW_TP, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fentry/", TRACING, - .expected_attach_type = BPF_TRACE_FENTRY, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fmod_ret/", TRACING, - .expected_attach_type = BPF_MODIFY_RETURN, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fexit/", TRACING, - .expected_attach_type = BPF_TRACE_FEXIT, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("fentry.s/", TRACING, - .expected_attach_type = BPF_TRACE_FENTRY, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("fmod_ret.s/", TRACING, - .expected_attach_type = BPF_MODIFY_RETURN, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("fexit.s/", TRACING, - .expected_attach_type = BPF_TRACE_FEXIT, - .is_attach_btf = true, - .is_sleepable = true, - .attach_fn = attach_trace), - SEC_DEF("freplace/", EXT, - .is_attach_btf = true, - .attach_fn = attach_trace), - SEC_DEF("lsm/", LSM, - .is_attach_btf = true, - .expected_attach_type = BPF_LSM_MAC, - .attach_fn = attach_lsm), - SEC_DEF("lsm.s/", LSM, - .is_attach_btf = true, - .is_sleepable = true, - .expected_attach_type = BPF_LSM_MAC, - .attach_fn = attach_lsm), - SEC_DEF("iter/", TRACING, - .expected_attach_type = BPF_TRACE_ITER, - .is_attach_btf = true, - .attach_fn = attach_iter), - SEC_DEF("syscall", SYSCALL, - .is_sleepable = true), - BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, - BPF_XDP_DEVMAP), - BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, - BPF_XDP_CPUMAP), - BPF_APROG_SEC("xdp", BPF_PROG_TYPE_XDP, - BPF_XDP), - BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), - BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), - BPF_PROG_SEC("lwt_out", BPF_PROG_TYPE_LWT_OUT), - BPF_PROG_SEC("lwt_xmit", BPF_PROG_TYPE_LWT_XMIT), - BPF_PROG_SEC("lwt_seg6local", BPF_PROG_TYPE_LWT_SEG6LOCAL), - BPF_APROG_SEC("cgroup_skb/ingress", BPF_PROG_TYPE_CGROUP_SKB, - BPF_CGROUP_INET_INGRESS), - BPF_APROG_SEC("cgroup_skb/egress", BPF_PROG_TYPE_CGROUP_SKB, - BPF_CGROUP_INET_EGRESS), - BPF_APROG_COMPAT("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), - BPF_EAPROG_SEC("cgroup/sock_create", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_CREATE), - BPF_EAPROG_SEC("cgroup/sock_release", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_RELEASE), - BPF_APROG_SEC("cgroup/sock", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET_SOCK_CREATE), - BPF_EAPROG_SEC("cgroup/post_bind4", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET4_POST_BIND), - BPF_EAPROG_SEC("cgroup/post_bind6", BPF_PROG_TYPE_CGROUP_SOCK, - BPF_CGROUP_INET6_POST_BIND), - BPF_APROG_SEC("cgroup/dev", BPF_PROG_TYPE_CGROUP_DEVICE, - BPF_CGROUP_DEVICE), - BPF_APROG_SEC("sockops", BPF_PROG_TYPE_SOCK_OPS, - BPF_CGROUP_SOCK_OPS), - BPF_APROG_SEC("sk_skb/stream_parser", BPF_PROG_TYPE_SK_SKB, - BPF_SK_SKB_STREAM_PARSER), - BPF_APROG_SEC("sk_skb/stream_verdict", BPF_PROG_TYPE_SK_SKB, - BPF_SK_SKB_STREAM_VERDICT), - BPF_APROG_COMPAT("sk_skb", BPF_PROG_TYPE_SK_SKB), - BPF_APROG_SEC("sk_msg", BPF_PROG_TYPE_SK_MSG, - BPF_SK_MSG_VERDICT), - BPF_APROG_SEC("lirc_mode2", BPF_PROG_TYPE_LIRC_MODE2, - BPF_LIRC_MODE2), - BPF_APROG_SEC("flow_dissector", BPF_PROG_TYPE_FLOW_DISSECTOR, - BPF_FLOW_DISSECTOR), - BPF_EAPROG_SEC("cgroup/bind4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_BIND), - BPF_EAPROG_SEC("cgroup/bind6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_BIND), - BPF_EAPROG_SEC("cgroup/connect4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_CONNECT), - BPF_EAPROG_SEC("cgroup/connect6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_CONNECT), - BPF_EAPROG_SEC("cgroup/sendmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP4_SENDMSG), - BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP6_SENDMSG), - BPF_EAPROG_SEC("cgroup/recvmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP4_RECVMSG), - BPF_EAPROG_SEC("cgroup/recvmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_UDP6_RECVMSG), - BPF_EAPROG_SEC("cgroup/getpeername4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_GETPEERNAME), - BPF_EAPROG_SEC("cgroup/getpeername6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_GETPEERNAME), - BPF_EAPROG_SEC("cgroup/getsockname4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET4_GETSOCKNAME), - BPF_EAPROG_SEC("cgroup/getsockname6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - BPF_CGROUP_INET6_GETSOCKNAME), - BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL, - BPF_CGROUP_SYSCTL), - BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, - BPF_CGROUP_GETSOCKOPT), - BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, - BPF_CGROUP_SETSOCKOPT), - BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS), - BPF_EAPROG_SEC("sk_lookup/", BPF_PROG_TYPE_SK_LOOKUP, - BPF_SK_LOOKUP), + SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("kprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), + 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("tc", SCHED_CLS, 0, SEC_NONE), + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX), + 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), + SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tp/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("tp_btf/", TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry/", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fmod_ret/", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fexit/", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry.s/", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fmod_ret.s/", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fexit.s/", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("freplace/", EXT, 0, SEC_ATTACH_BTF, attach_trace), + 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("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", 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), + SEC_DEF("lwt_out", LWT_OUT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_xmit", LWT_XMIT, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("lwt_seg6local", LWT_SEG6LOCAL, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/skb", CGROUP_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), + SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE | SEC_SLOPPY_PFX), }; -#undef BPF_PROG_SEC_IMPL -#undef BPF_PROG_SEC -#undef BPF_APROG_SEC -#undef BPF_EAPROG_SEC -#undef BPF_APROG_COMPAT -#undef SEC_DEF - #define MAX_TYPE_NAME_SIZE 32 static const struct bpf_sec_def *find_sec_def(const char *sec_name) { - int i, n = ARRAY_SIZE(section_defs); + 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; for (i = 0; i < n; i++) { - if (strncmp(sec_name, - section_defs[i].sec, section_defs[i].len)) + sec_def = §ion_defs[i]; + sec_flags = sec_def->cookie; + 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 sec_def; + continue; + } + + /* "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; - return §ion_defs[i]; + } + + /* 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; + } + + /* Definitions not marked SEC_SLOPPY_PFX (e.g., + * SEC("syscall")) are exact matches in both modes. + */ + if (strcmp(sec_name, sec_def->sec) == 0) + return sec_def; } return NULL; } @@ -8102,8 +8152,15 @@ static char *libbpf_get_type_names(bool attach_type) buf[0] = '\0'; /* Forge string buf with all available names */ for (i = 0; i < ARRAY_SIZE(section_defs); i++) { - if (attach_type && !section_defs[i].is_attachable) - continue; + const struct bpf_sec_def *sec_def = §ion_defs[i]; + + if (attach_type) { + if (sec_def->preload_fn != libbpf_preload_prog) + continue; + + if (!(sec_def->cookie & SEC_ATTACHABLE)) + continue; + } if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) { free(buf); @@ -8245,35 +8302,37 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, return -EINVAL; } - if (prog->type == BPF_PROG_TYPE_UNSPEC) { - const struct bpf_sec_def *sec_def; - - sec_def = find_sec_def(prog->sec_name); - if (sec_def && - sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) { - /* for pr_warn */ - prog->type = sec_def->prog_type; - goto invalid_prog; - } + /* prevent the use of BPF prog with invalid type */ + if (prog->type != BPF_PROG_TYPE_STRUCT_OPS) { + pr_warn("struct_ops reloc %s: prog %s is not struct_ops BPF program\n", + map->name, prog->name); + return -EINVAL; + } - prog->type = BPF_PROG_TYPE_STRUCT_OPS; + /* if we haven't yet processed this BPF program, record proper + * attach_btf_id and member_idx + */ + if (!prog->attach_btf_id) { prog->attach_btf_id = st_ops->type_id; prog->expected_attach_type = member_idx; - } else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || - prog->attach_btf_id != st_ops->type_id || - prog->expected_attach_type != member_idx) { - goto invalid_prog; } + + /* struct_ops BPF prog can be re-used between multiple + * .struct_ops as long as it's the same struct_ops struct + * definition and the same function pointer field + */ + if (prog->attach_btf_id != st_ops->type_id || + prog->expected_attach_type != member_idx) { + pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", + map->name, prog->name, prog->sec_name, prog->type, + prog->attach_btf_id, prog->expected_attach_type, name); + return -EINVAL; + } + st_ops->progs[member_idx] = prog; } return 0; - -invalid_prog: - pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", - map->name, prog->name, prog->sec_name, prog->type, - prog->attach_btf_id, prog->expected_attach_type, name); - return -EINVAL; } #define BTF_TRACE_PREFIX "btf_trace_" @@ -8425,32 +8484,12 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, return -ESRCH; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id) +static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, + int *btf_obj_fd, int *btf_type_id) { enum bpf_attach_type attach_type = prog->expected_attach_type; __u32 attach_prog_fd = prog->attach_prog_fd; - const char *name = prog->sec_name, *attach_name; - const struct bpf_sec_def *sec = NULL; - int i, err = 0; - - if (!name) - return -EINVAL; - - for (i = 0; i < ARRAY_SIZE(section_defs); i++) { - if (!section_defs[i].is_attach_btf) - continue; - if (strncmp(name, section_defs[i].sec, section_defs[i].len)) - continue; - - sec = §ion_defs[i]; - break; - } - - if (!sec) { - pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", name); - return -ESRCH; - } - attach_name = name + sec->len; + int err = 0; /* BPF program's BTF ID */ if (attach_prog_fd) { @@ -8484,27 +8523,30 @@ int libbpf_attach_type_by_name(const char *name, enum bpf_attach_type *attach_type) { char *type_names; - int i; + const struct bpf_sec_def *sec_def; if (!name) return libbpf_err(-EINVAL); - for (i = 0; i < ARRAY_SIZE(section_defs); i++) { - if (strncmp(name, section_defs[i].sec, section_defs[i].len)) - continue; - if (!section_defs[i].is_attachable) - return libbpf_err(-EINVAL); - *attach_type = section_defs[i].expected_attach_type; - return 0; - } - pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); - type_names = libbpf_get_type_names(true); - if (type_names != NULL) { - pr_debug("attachable section(type) names are:%s\n", type_names); - free(type_names); + sec_def = find_sec_def(name); + if (!sec_def) { + pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); + type_names = libbpf_get_type_names(true); + if (type_names != NULL) { + pr_debug("attachable section(type) names are:%s\n", type_names); + free(type_names); + } + + return libbpf_err(-EINVAL); } - return libbpf_err(-EINVAL); + if (sec_def->preload_fn != libbpf_preload_prog) + return libbpf_err(-EINVAL); + if (!(sec_def->cookie & SEC_ATTACHABLE)) + return libbpf_err(-EINVAL); + + *attach_type = sec_def->expected_attach_type; + return 0; } int bpf_map__fd(const struct bpf_map *map) @@ -8991,8 +9033,15 @@ int bpf_link__unpin(struct bpf_link *link) struct bpf_link_perf { struct bpf_link link; int perf_event_fd; + /* legacy kprobe support: keep track of probe identifier and type */ + char *legacy_probe_name; + bool legacy_is_kprobe; + bool legacy_is_retprobe; }; +static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe); +static int remove_uprobe_event_legacy(const char *probe_name, bool retprobe); + static int bpf_link_perf_detach(struct bpf_link *link) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); @@ -9005,17 +9054,29 @@ static int bpf_link_perf_detach(struct bpf_link *link) close(perf_link->perf_event_fd); close(link->fd); - return libbpf_err(err); + /* legacy uprobe/kprobe needs to be removed after perf event fd closure */ + if (perf_link->legacy_probe_name) { + if (perf_link->legacy_is_kprobe) { + err = remove_kprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); + } else { + err = remove_uprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); + } + } + + return err; } static void bpf_link_perf_dealloc(struct bpf_link *link) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + free(perf_link->legacy_probe_name); free(perf_link); } -struct bpf_link *bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd, +struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, const struct bpf_perf_event_opts *opts) { char errmsg[STRERR_BUFSIZE]; @@ -9090,7 +9151,7 @@ err_out: return libbpf_err_ptr(err); } -struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd) +struct bpf_link *bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd) { return bpf_program__attach_perf_event_opts(prog, pfd, NULL); } @@ -9207,16 +9268,110 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, return pfd; } +static int append_to_file(const char *file, const char *fmt, ...) +{ + int fd, n, err = 0; + va_list ap; + + fd = open(file, O_WRONLY | O_APPEND, 0); + if (fd < 0) + return -errno; + + va_start(ap, fmt); + n = vdprintf(fd, fmt, ap); + va_end(ap); + + if (n < 0) + err = -errno; + + close(fd); + return err; +} + +static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, + const char *kfunc_name, size_t offset) +{ + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), kfunc_name, offset); +} + +static int add_kprobe_event_legacy(const char *probe_name, bool retprobe, + const char *kfunc_name, size_t offset) +{ + const char *file = "/sys/kernel/debug/tracing/kprobe_events"; + + return append_to_file(file, "%c:%s/%s %s+0x%zx", + retprobe ? 'r' : 'p', + retprobe ? "kretprobes" : "kprobes", + probe_name, kfunc_name, offset); +} + +static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe) +{ + const char *file = "/sys/kernel/debug/tracing/kprobe_events"; + + return append_to_file(file, "-:%s/%s", retprobe ? "kretprobes" : "kprobes", probe_name); +} + +static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retprobe) +{ + char file[256]; + + snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + retprobe ? "kretprobes" : "kprobes", probe_name); + + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, + const char *kfunc_name, size_t offset, int pid) +{ + struct perf_event_attr attr = {}; + char errmsg[STRERR_BUFSIZE]; + int type, pfd, err; + + err = add_kprobe_event_legacy(probe_name, retprobe, kfunc_name, offset); + if (err < 0) { + pr_warn("failed to add legacy kprobe event for '%s+0x%zx': %s\n", + kfunc_name, offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + type = determine_kprobe_perf_type_legacy(probe_name, retprobe); + if (type < 0) { + pr_warn("failed to determine legacy kprobe event id for '%s+0x%zx': %s\n", + kfunc_name, offset, + libbpf_strerror_r(type, errmsg, sizeof(errmsg))); + return type; + } + attr.size = sizeof(attr); + attr.config = type; + attr.type = PERF_TYPE_TRACEPOINT; + + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid, /* pid */ + pid == -1 ? 0 : -1, /* cpu */ + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("legacy kprobe perf_event_open() failed: %s\n", + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + return pfd; +} + struct bpf_link * -bpf_program__attach_kprobe_opts(struct bpf_program *prog, +bpf_program__attach_kprobe_opts(const struct bpf_program *prog, const char *func_name, const struct bpf_kprobe_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); char errmsg[STRERR_BUFSIZE]; + char *legacy_probe = NULL; struct bpf_link *link; - unsigned long offset; - bool retprobe; + size_t offset; + bool retprobe, legacy; int pfd, err; if (!OPTS_VALID(opts, bpf_kprobe_opts)) @@ -9226,27 +9381,57 @@ bpf_program__attach_kprobe_opts(struct bpf_program *prog, offset = OPTS_GET(opts, offset, 0); pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); - pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name, - offset, -1 /* pid */, 0 /* ref_ctr_off */); + legacy = determine_kprobe_perf_type() < 0; + if (!legacy) { + pfd = perf_event_open_probe(false /* uprobe */, retprobe, + func_name, offset, + -1 /* pid */, 0 /* ref_ctr_off */); + } else { + char probe_name[256]; + + gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), + func_name, offset); + + legacy_probe = strdup(func_name); + if (!legacy_probe) + return libbpf_err_ptr(-ENOMEM); + + pfd = perf_event_kprobe_open_legacy(legacy_probe, retprobe, func_name, + offset, -1 /* pid */); + } if (pfd < 0) { - pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n", - prog->name, retprobe ? "kretprobe" : "kprobe", func_name, - libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(pfd); + err = -errno; + pr_warn("prog '%s': failed to create %s '%s+0x%zx' perf event: %s\n", + prog->name, retprobe ? "kretprobe" : "kprobe", + func_name, offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; } link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); err = libbpf_get_error(link); if (err) { close(pfd); - pr_warn("prog '%s': failed to attach to %s '%s': %s\n", - prog->name, retprobe ? "kretprobe" : "kprobe", func_name, + pr_warn("prog '%s': failed to attach to %s '%s+0x%zx': %s\n", + prog->name, retprobe ? "kretprobe" : "kprobe", + func_name, offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(err); + goto err_out; } + if (legacy) { + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + + perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_kprobe = true; + perf_link->legacy_is_retprobe = retprobe; + } + return link; +err_out: + free(legacy_probe); + return libbpf_err_ptr(err); } -struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe, const char *func_name) { @@ -9257,8 +9442,7 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, return bpf_program__attach_kprobe_opts(prog, func_name, &opts); } -static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie) { DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts); unsigned long offset = 0; @@ -9267,8 +9451,11 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, char *func; int n, err; - func_name = prog->sec_name + sec->len; - opts.retprobe = strcmp(sec->sec, "kretprobe/") == 0; + opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/"); + if (opts.retprobe) + func_name = prog->sec_name + sizeof("kretprobe/") - 1; + else + func_name = prog->sec_name + sizeof("kprobe/") - 1; n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset); if (n < 1) { @@ -9289,17 +9476,96 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, return link; } +static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, + const char *binary_path, uint64_t offset) +{ + int i; + + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), binary_path, (size_t)offset); + + /* sanitize binary_path in the probe name */ + for (i = 0; buf[i]; i++) { + if (!isalnum(buf[i])) + buf[i] = '_'; + } +} + +static inline int add_uprobe_event_legacy(const char *probe_name, bool retprobe, + const char *binary_path, size_t offset) +{ + const char *file = "/sys/kernel/debug/tracing/uprobe_events"; + + return append_to_file(file, "%c:%s/%s %s:0x%zx", + retprobe ? 'r' : 'p', + retprobe ? "uretprobes" : "uprobes", + probe_name, binary_path, offset); +} + +static inline int remove_uprobe_event_legacy(const char *probe_name, bool retprobe) +{ + const char *file = "/sys/kernel/debug/tracing/uprobe_events"; + + return append_to_file(file, "-:%s/%s", retprobe ? "uretprobes" : "uprobes", probe_name); +} + +static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retprobe) +{ + char file[512]; + + snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + retprobe ? "uretprobes" : "uprobes", probe_name); + + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, + const char *binary_path, size_t offset, int pid) +{ + struct perf_event_attr attr; + int type, pfd, err; + + err = add_uprobe_event_legacy(probe_name, retprobe, binary_path, offset); + if (err < 0) { + pr_warn("failed to add legacy uprobe event for %s:0x%zx: %d\n", + binary_path, (size_t)offset, err); + return err; + } + type = determine_uprobe_perf_type_legacy(probe_name, retprobe); + if (type < 0) { + pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %d\n", + binary_path, offset, err); + return type; + } + + memset(&attr, 0, sizeof(attr)); + attr.size = sizeof(attr); + attr.config = type; + attr.type = PERF_TYPE_TRACEPOINT; + + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid, /* pid */ + pid == -1 ? 0 : -1, /* cpu */ + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("legacy uprobe perf_event_open() failed: %d\n", err); + return err; + } + return pfd; +} + LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, +bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, const struct bpf_uprobe_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); - char errmsg[STRERR_BUFSIZE]; + char errmsg[STRERR_BUFSIZE], *legacy_probe = NULL; struct bpf_link *link; size_t ref_ctr_off; int pfd, err; - bool retprobe; + bool retprobe, legacy; if (!OPTS_VALID(opts, bpf_uprobe_opts)) return libbpf_err_ptr(-EINVAL); @@ -9308,15 +9574,35 @@ bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0); pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); - pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, - func_offset, pid, ref_ctr_off); + legacy = determine_uprobe_perf_type() < 0; + if (!legacy) { + pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, + func_offset, pid, ref_ctr_off); + } else { + char probe_name[512]; + + if (ref_ctr_off) + return libbpf_err_ptr(-EINVAL); + + gen_uprobe_legacy_event_name(probe_name, sizeof(probe_name), + binary_path, func_offset); + + legacy_probe = strdup(probe_name); + if (!legacy_probe) + return libbpf_err_ptr(-ENOMEM); + + pfd = perf_event_uprobe_open_legacy(legacy_probe, retprobe, + binary_path, func_offset, pid); + } if (pfd < 0) { + err = -errno; pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n", prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, - libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(pfd); + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_out; } + link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); err = libbpf_get_error(link); if (err) { @@ -9325,12 +9611,23 @@ bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return libbpf_err_ptr(err); + goto err_out; + } + if (legacy) { + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + + perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_kprobe = false; + perf_link->legacy_is_retprobe = retprobe; } return link; +err_out: + free(legacy_probe); + return libbpf_err_ptr(err); + } -struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, size_t func_offset) @@ -9390,7 +9687,7 @@ static int perf_event_open_tracepoint(const char *tp_category, return pfd; } -struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, const char *tp_category, const char *tp_name, const struct bpf_tracepoint_opts *opts) @@ -9424,15 +9721,14 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog, return link; } -struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog, const char *tp_category, const char *tp_name) { return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL); } -static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) { char *sec_name, *tp_cat, *tp_name; struct bpf_link *link; @@ -9441,8 +9737,11 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, if (!sec_name) return libbpf_err_ptr(-ENOMEM); - /* extract "tp/<category>/<name>" */ - tp_cat = sec_name + sec->len; + /* extract "tp/<category>/<name>" or "tracepoint/<category>/<name>" */ + if (str_has_pfx(prog->sec_name, "tp/")) + tp_cat = sec_name + sizeof("tp/") - 1; + else + tp_cat = sec_name + sizeof("tracepoint/") - 1; tp_name = strchr(tp_cat, '/'); if (!tp_name) { free(sec_name); @@ -9456,7 +9755,7 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, return link; } -struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, const char *tp_name) { char errmsg[STRERR_BUFSIZE]; @@ -9486,16 +9785,20 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, return link; } -static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie) { - const char *tp_name = prog->sec_name + sec->len; + const char *tp_name; + + if (str_has_pfx(prog->sec_name, "raw_tp/")) + tp_name = prog->sec_name + sizeof("raw_tp/") - 1; + else + tp_name = prog->sec_name + sizeof("raw_tracepoint/") - 1; return bpf_program__attach_raw_tracepoint(prog, tp_name); } /* Common logic for all BPF program types that attach to a btf_id */ -static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog) +static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *prog) { char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; @@ -9524,30 +9827,28 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog) return (struct bpf_link *)link; } -struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) +struct bpf_link *bpf_program__attach_trace(const struct bpf_program *prog) { return bpf_program__attach_btf_id(prog); } -struct bpf_link *bpf_program__attach_lsm(struct bpf_program *prog) +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_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie) { return bpf_program__attach_trace(prog); } -static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie) { return bpf_program__attach_lsm(prog); } static struct bpf_link * -bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id, +bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id, const char *target_name) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts, @@ -9583,24 +9884,24 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id, } struct bpf_link * -bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) +bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd) { return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup"); } struct bpf_link * -bpf_program__attach_netns(struct bpf_program *prog, int netns_fd) +bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd) { return bpf_program__attach_fd(prog, netns_fd, 0, "netns"); } -struct bpf_link *bpf_program__attach_xdp(struct bpf_program *prog, int ifindex) +struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex) { /* target_fd/target_ifindex use the same field in LINK_CREATE */ return bpf_program__attach_fd(prog, ifindex, 0, "xdp"); } -struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, int target_fd, const char *attach_func_name) { @@ -9633,7 +9934,7 @@ struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog, } struct bpf_link * -bpf_program__attach_iter(struct bpf_program *prog, +bpf_program__attach_iter(const struct bpf_program *prog, const struct bpf_iter_attach_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); @@ -9672,21 +9973,17 @@ bpf_program__attach_iter(struct bpf_program *prog, return link; } -static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie) { return bpf_program__attach_iter(prog, NULL); } -struct bpf_link *bpf_program__attach(struct bpf_program *prog) +struct bpf_link *bpf_program__attach(const struct bpf_program *prog) { - const struct bpf_sec_def *sec_def; - - sec_def = find_sec_def(prog->sec_name); - if (!sec_def || !sec_def->attach_fn) + if (!prog->sec_def || !prog->sec_def->attach_fn) return libbpf_err_ptr(-ESRCH); - return sec_def->attach_fn(sec_def, prog); + return prog->sec_def->attach_fn(prog, prog->sec_def->cookie); } static int bpf_link__detach_struct_ops(struct bpf_link *link) @@ -9699,7 +9996,7 @@ static int bpf_link__detach_struct_ops(struct bpf_link *link) return 0; } -struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) +struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) { struct bpf_struct_ops *st_ops; struct bpf_link *link; @@ -10512,18 +10809,29 @@ int bpf_program__set_attach_target(struct bpf_program *prog, { int btf_obj_fd = 0, btf_id = 0, err; - if (!prog || attach_prog_fd < 0 || !attach_func_name) + if (!prog || attach_prog_fd < 0) return libbpf_err(-EINVAL); if (prog->obj->loaded) return libbpf_err(-EINVAL); + if (attach_prog_fd && !attach_func_name) { + /* remember attach_prog_fd and let bpf_program__load() find + * BTF ID during the program load + */ + prog->attach_prog_fd = attach_prog_fd; + return 0; + } + if (attach_prog_fd) { btf_id = libbpf_find_prog_btf_id(attach_func_name, attach_prog_fd); if (btf_id < 0) return libbpf_err(btf_id); } else { + if (!attach_func_name) + return libbpf_err(-EINVAL); + /* load btf_vmlinux, if not yet */ err = bpf_object__load_vmlinux_btf(prog->obj, true); if (err) @@ -10765,16 +11073,15 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) for (i = 0; i < s->prog_cnt; i++) { struct bpf_program *prog = *s->progs[i].prog; struct bpf_link **link = s->progs[i].link; - const struct bpf_sec_def *sec_def; if (!prog->load) continue; - sec_def = find_sec_def(prog->sec_name); - if (!sec_def || !sec_def->attach_fn) + /* auto-attaching not supported for this program */ + if (!prog->sec_def || !prog->sec_def->attach_fn) continue; - *link = sec_def->attach_fn(sec_def, prog); + *link = bpf_program__attach(prog); err = libbpf_get_error(*link); if (err) { pr_warn("failed to auto-attach program '%s': %d\n", diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index f177d897c5f7..e35490c54eb3 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -83,12 +83,15 @@ struct bpf_object_open_opts { * Non-relocatable instructions are replaced with invalid ones to * prevent accidental errors. * */ + LIBBPF_DEPRECATED_SINCE(0, 6, "field has no effect") bool relaxed_core_relocs; /* maps that set the 'pinning' attribute in their definition will have * their pin_path attribute set to a file in this directory, and be * auto-pinned to that path on load; defaults to "/sys/fs/bpf". */ const char *pin_root_path; + + LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__set_attach_target() on each individual bpf_program") __u32 attach_prog_fd; /* Additional kernel config content that augments and overrides * system Kconfig for CONFIG_xxx externs. @@ -243,7 +246,7 @@ LIBBPF_API int bpf_link__detach(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); LIBBPF_API struct bpf_link * -bpf_program__attach(struct bpf_program *prog); +bpf_program__attach(const struct bpf_program *prog); struct bpf_perf_event_opts { /* size of this struct, for forward/backward compatiblity */ @@ -254,10 +257,10 @@ struct bpf_perf_event_opts { #define bpf_perf_event_opts__last_field bpf_cookie LIBBPF_API struct bpf_link * -bpf_program__attach_perf_event(struct bpf_program *prog, int pfd); +bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd); LIBBPF_API struct bpf_link * -bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd, +bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, const struct bpf_perf_event_opts *opts); struct bpf_kprobe_opts { @@ -266,7 +269,7 @@ struct bpf_kprobe_opts { /* custom user-provided value fetchable through bpf_get_attach_cookie() */ __u64 bpf_cookie; /* function's offset to install kprobe to */ - unsigned long offset; + size_t offset; /* kprobe is return probe */ bool retprobe; size_t :0; @@ -274,10 +277,10 @@ struct bpf_kprobe_opts { #define bpf_kprobe_opts__last_field retprobe LIBBPF_API struct bpf_link * -bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe, +bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe, const char *func_name); LIBBPF_API struct bpf_link * -bpf_program__attach_kprobe_opts(struct bpf_program *prog, +bpf_program__attach_kprobe_opts(const struct bpf_program *prog, const char *func_name, const struct bpf_kprobe_opts *opts); @@ -297,11 +300,11 @@ struct bpf_uprobe_opts { #define bpf_uprobe_opts__last_field retprobe LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe, +bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, size_t func_offset); LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, +bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, const struct bpf_uprobe_opts *opts); @@ -314,35 +317,35 @@ struct bpf_tracepoint_opts { #define bpf_tracepoint_opts__last_field bpf_cookie LIBBPF_API struct bpf_link * -bpf_program__attach_tracepoint(struct bpf_program *prog, +bpf_program__attach_tracepoint(const struct bpf_program *prog, const char *tp_category, const char *tp_name); LIBBPF_API struct bpf_link * -bpf_program__attach_tracepoint_opts(struct bpf_program *prog, +bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, const char *tp_category, const char *tp_name, const struct bpf_tracepoint_opts *opts); LIBBPF_API struct bpf_link * -bpf_program__attach_raw_tracepoint(struct bpf_program *prog, +bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, const char *tp_name); LIBBPF_API struct bpf_link * -bpf_program__attach_trace(struct bpf_program *prog); +bpf_program__attach_trace(const struct bpf_program *prog); LIBBPF_API struct bpf_link * -bpf_program__attach_lsm(struct bpf_program *prog); +bpf_program__attach_lsm(const struct bpf_program *prog); LIBBPF_API struct bpf_link * -bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd); +bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd); LIBBPF_API struct bpf_link * -bpf_program__attach_netns(struct bpf_program *prog, int netns_fd); +bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd); LIBBPF_API struct bpf_link * -bpf_program__attach_xdp(struct bpf_program *prog, int ifindex); +bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex); LIBBPF_API struct bpf_link * -bpf_program__attach_freplace(struct bpf_program *prog, +bpf_program__attach_freplace(const struct bpf_program *prog, int target_fd, const char *attach_func_name); struct bpf_map; -LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map); +LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map); struct bpf_iter_attach_opts { size_t sz; /* size of this struct for forward/backward compatibility */ @@ -352,7 +355,7 @@ struct bpf_iter_attach_opts { #define bpf_iter_attach_opts__last_field link_info_len LIBBPF_API struct bpf_link * -bpf_program__attach_iter(struct bpf_program *prog, +bpf_program__attach_iter(const struct bpf_program *prog, const struct bpf_iter_attach_opts *opts); struct bpf_insn; @@ -478,9 +481,13 @@ struct bpf_map_def { unsigned int map_flags; }; -/* - * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, - * so no need to worry about a name clash. +/** + * @brief **bpf_object__find_map_by_name()** returns BPF map of + * the given name, if it exists within the passed BPF object + * @param obj BPF object + * @param name name of the BPF map + * @return BPF map instance, if such map exists within the BPF object; + * or NULL otherwise. */ LIBBPF_API struct bpf_map * bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); @@ -506,7 +513,12 @@ bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); LIBBPF_API struct bpf_map * bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); -/* get/set map FD */ +/** + * @brief **bpf_map__fd()** gets the file descriptor of the passed + * BPF map + * @param map the BPF map instance + * @return the file descriptor; or -EINVAL in case of an error + */ 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 */ @@ -547,6 +559,14 @@ LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); + +/** + * @brief **bpf_map__is_internal()** tells the caller whether or not the + * passed map is a special map created by libbpf automatically for things like + * global variables, __ksym externs, Kconfig values, etc + * @param map the bpf_map + * @return true, if the map is an internal map; false, otherwise + */ 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); @@ -558,6 +578,38 @@ LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); +/** + * @brief **libbpf_get_error()** extracts the error code from the passed + * pointer + * @param ptr pointer returned from libbpf API function + * @return error code; or 0 if no error occured + * + * Many libbpf API functions which return pointers have logic to encode error + * codes as pointers, and do not return NULL. Meaning **libbpf_get_error()** + * should be used on the return value from these functions immediately after + * calling the API function, with no intervening calls that could clobber the + * `errno` variable. Consult the individual functions documentation to verify + * if this logic applies should be used. + * + * For these API functions, if `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` + * is enabled, NULL is returned on error instead. + * + * If ptr is NULL, then errno should be already set by the failing + * API, because libbpf never returns NULL on success and it now always + * sets errno on error. + * + * Example usage: + * + * struct perf_buffer *pb; + * + * pb = perf_buffer__new(bpf_map__fd(obj->maps.events), PERF_BUFFER_PAGES, &opts); + * err = libbpf_get_error(pb); + * if (err) { + * pb = NULL; + * fprintf(stderr, "failed to open perf buffer: %d\n", err); + * goto cleanup; + * } + */ LIBBPF_API long libbpf_get_error(const void *ptr); struct bpf_prog_load_attr { @@ -822,9 +874,10 @@ bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); LIBBPF_API void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); -/* - * A helper function to get the number of possible CPUs before looking up - * per-CPU maps. Negative errno is returned on failure. +/** + * @brief **libbpf_num_possible_cpus()** is a helper function to get the + * number of possible CPUs that the host kernel supports and expects. + * @return number of possible CPUs; or error code on failure * * Example usage: * @@ -834,7 +887,6 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); * } * long values[ncpus]; * bpf_map_lookup_elem(per_cpu_map_fd, key, values); - * */ LIBBPF_API int libbpf_num_possible_cpus(void); @@ -854,7 +906,7 @@ struct bpf_object_skeleton { size_t sz; /* size of this struct, for forward/backward compatibility */ const char *name; - void *data; + const void *data; size_t data_sz; struct bpf_object **obj; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index bbc53bb25f68..9e649cf9e771 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -386,3 +386,8 @@ LIBBPF_0.5.0 { btf_dump__dump_type_data; libbpf_set_strict_mode; } LIBBPF_0.4.0; + +LIBBPF_0.6.0 { + global: + btf__add_tag; +} LIBBPF_0.5.0; diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h index 947d8bd8a7bb..aaa1efbf6f51 100644 --- a/tools/lib/bpf/libbpf_common.h +++ b/tools/lib/bpf/libbpf_common.h @@ -10,6 +10,7 @@ #define __LIBBPF_LIBBPF_COMMON_H #include <string.h> +#include "libbpf_version.h" #ifndef LIBBPF_API #define LIBBPF_API __attribute__((visibility("default"))) @@ -17,6 +18,29 @@ #define LIBBPF_DEPRECATED(msg) __attribute__((deprecated(msg))) +/* Mark a symbol as deprecated when libbpf version is >= {major}.{minor} */ +#define LIBBPF_DEPRECATED_SINCE(major, minor, msg) \ + __LIBBPF_MARK_DEPRECATED_ ## major ## _ ## minor \ + (LIBBPF_DEPRECATED("libbpf v" # major "." # minor "+: " msg)) + +#define __LIBBPF_CURRENT_VERSION_GEQ(major, minor) \ + (LIBBPF_MAJOR_VERSION > (major) || \ + (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor))) + +/* Add checks for other versions below when planning deprecation of API symbols + * with the LIBBPF_DEPRECATED_SINCE macro. + */ +#if __LIBBPF_CURRENT_VERSION_GEQ(0, 6) +#define __LIBBPF_MARK_DEPRECATED_0_6(X) X +#else +#define __LIBBPF_MARK_DEPRECATED_0_6(X) +#endif +#if __LIBBPF_CURRENT_VERSION_GEQ(0, 7) +#define __LIBBPF_MARK_DEPRECATED_0_7(X) X +#else +#define __LIBBPF_MARK_DEPRECATED_0_7(X) +#endif + /* Helper macro to declare and initialize libbpf options struct * * This dance with uninitialized declaration, followed by memset to zero, diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 533b0211f40a..ec79400517d4 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -69,6 +69,8 @@ #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) +#define BTF_TYPE_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx) #ifndef likely #define likely(x) __builtin_expect(!!(x), 1) @@ -87,20 +89,40 @@ (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) #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 + * runtime. + */ +#define str_has_pfx(str, pfx) \ + (strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0) + /* Symbol versioning is different between static and shared library. * Properly versioned symbols are needed for shared library, but * only the symbol of the new version is needed for static library. + * Starting with GNU C 10, use symver attribute instead of .symver assembler + * directive, which works better with GCC LTO builds. */ -#ifdef SHARED -# define COMPAT_VERSION(internal_name, api_name, version) \ +#if defined(SHARED) && defined(__GNUC__) && __GNUC__ >= 10 + +#define DEFAULT_VERSION(internal_name, api_name, version) \ + __attribute__((symver(#api_name "@@" #version))) +#define COMPAT_VERSION(internal_name, api_name, version) \ + __attribute__((symver(#api_name "@" #version))) + +#elif defined(SHARED) + +#define COMPAT_VERSION(internal_name, api_name, version) \ asm(".symver " #internal_name "," #api_name "@" #version); -# define DEFAULT_VERSION(internal_name, api_name, version) \ +#define DEFAULT_VERSION(internal_name, api_name, version) \ asm(".symver " #internal_name "," #api_name "@@" #version); -#else -# define COMPAT_VERSION(internal_name, api_name, version) -# define DEFAULT_VERSION(internal_name, api_name, version) \ + +#else /* !SHARED */ + +#define COMPAT_VERSION(internal_name, api_name, version) +#define DEFAULT_VERSION(internal_name, api_name, version) \ extern typeof(internal_name) api_name \ __attribute__((alias(#internal_name))); + #endif extern void libbpf_print(enum libbpf_print_level level, diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index df0d03dcffab..74e6f860f703 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -46,6 +46,15 @@ enum libbpf_strict_mode { */ LIBBPF_STRICT_DIRECT_ERRS = 0x02, + /* + * Enforce strict BPF program section (SEC()) names. + * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were + * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become + * unrecognized by libbpf and would have to be just SEC("xdp") and + * SEC("xdp") and SEC("perf_event"). + */ + LIBBPF_STRICT_SEC_NAME = 0x04, + __LIBBPF_STRICT_LAST, }; diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h new file mode 100644 index 000000000000..dd56d76f291c --- /dev/null +++ b/tools/lib/bpf/libbpf_version.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (C) 2021 Facebook */ +#ifndef __LIBBPF_VERSION_H +#define __LIBBPF_VERSION_H + +#define LIBBPF_MAJOR_VERSION 0 +#define LIBBPF_MINOR_VERSION 6 + +#endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index b22b50c1b173..9cf66702fa8d 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -105,10 +105,12 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr)); if (err < 0 || (int)attr.test.retval < 0) { opts->errstr = "failed to execute loader prog"; - if (err < 0) + if (err < 0) { err = -errno; - else + } else { err = (int)attr.test.retval; + errno = -err; + } goto out; } err = 0; diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index e9b619aa0cdf..a2111696ba91 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -281,6 +281,7 @@ out_mmap: return err; } +DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, @@ -345,6 +346,7 @@ struct xsk_umem_config_v1 { __u32 frame_headroom; }; +COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, @@ -358,8 +360,6 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp, &config); } -COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) -DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) static enum xsk_prog get_xsk_prog(void) { diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 433f8bef261e..1dad8d617da8 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -9,8 +9,9 @@ test_tag FEATURE-DUMP.libbpf fixdep test_dev_cgroup -/test_progs* -!test_progs.h +/test_progs +/test_progs-no_alu32 +/test_progs-bpf_gcc test_verifier_log feature test_sock diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 799b88152e9e..aa94739a1835 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -315,7 +315,8 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ linked_vars.skel.h linked_maps.skel.h LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ - test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c + test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c \ + trace_vprintk.c SKEL_BLACKLIST += $$(LSKELS) test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o @@ -513,14 +514,14 @@ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ # Benchmark runner -$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h +$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ) $(call msg,CC,,$@) $(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@ $(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \ $(OUTPUT)/perfbuf_bench.skel.h -$(OUTPUT)/bench.o: bench.h testing_helpers.h +$(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ $(OUTPUT)/bench_count.o \ diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 9b17f2867488..554553acc6d9 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -201,6 +201,20 @@ Without it, the error from compiling bpf selftests looks like: __ https://reviews.llvm.org/D93563 +btf_tag test and Clang version +============================== + +The btf_tag selftest require LLVM support to recognize the btf_tag attribute. +It was introduced in `Clang 14`__. + +Without it, the btf_tag selftest will be skipped and you will observe: + +.. code-block:: console + + #<test_num> btf_tag:SKIP + +__ https://reviews.llvm.org/D106614 + Clang dependencies for static linking tests =========================================== @@ -228,3 +242,16 @@ To fix this issue, user newer libbpf. .. Links .. _clang reloc patch: https://reviews.llvm.org/D102712 .. _kernel llvm reloc: /Documentation/bpf/llvm_reloc.rst + +Clang dependencies for the u32 spill test (xdpwall) +=================================================== +The xdpwall selftest requires a change in `Clang 14`__. + +Without it, the xdpwall selftest will fail and the error message +from running test_progs will look like: + +.. code-block:: console + + test_xdpwall:FAIL:Does LLVM have https://reviews.llvm.org/D109073? unexpected error: -4007 + +__ https://reviews.llvm.org/D109073 diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 141d8da687d2..50fc5561110a 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -13,6 +13,18 @@ DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123; +noinline int bpf_testmod_loop_test(int n) +{ + int i, sum = 0; + + /* the primary goal of this test is to test LBR. Create a lot of + * branches in the function, so we can catch it easily. + */ + for (i = 0; i < n; i++) + sum += i; + return sum; +} + noinline ssize_t bpf_testmod_test_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, @@ -24,7 +36,11 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, .len = len, }; - trace_bpf_testmod_test_read(current, &ctx); + /* This is always true. Use the check to make sure the compiler + * doesn't remove bpf_testmod_loop_test. + */ + if (bpf_testmod_loop_test(101) > 100) + trace_bpf_testmod_test_read(current, &ctx); return -EIO; /* always fail */ } @@ -71,4 +87,3 @@ module_exit(bpf_testmod_exit); MODULE_AUTHOR("Andrii Nakryiko"); MODULE_DESCRIPTION("BPF selftests module"); MODULE_LICENSE("Dual BSD/GPL"); - diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c index b692e6ead9b5..ce103fb0ad1b 100644 --- a/tools/testing/selftests/bpf/btf_helpers.c +++ b/tools/testing/selftests/bpf/btf_helpers.c @@ -24,11 +24,12 @@ static const char * const btf_kind_str_mapping[] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_TAG] = "TAG", }; static const char *btf_kind_str(__u16 kind) { - if (kind > BTF_KIND_DATASEC) + if (kind > BTF_KIND_TAG) return "UNKNOWN"; return btf_kind_str_mapping[kind]; } @@ -177,6 +178,10 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id) case BTF_KIND_FLOAT: fprintf(out, " size=%u", t->size); break; + case BTF_KIND_TAG: + fprintf(out, " type_id=%u component_idx=%d", + t->type, btf_tag(t)->component_idx); + break; default: break; } diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index bf307bb9e446..6c511dcd1465 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -14,6 +14,20 @@ void test_attach_probe(void) struct test_attach_probe* skel; size_t uprobe_offset; ssize_t base_addr, ref_ctr_offset; + bool legacy; + + /* Check if new-style kprobe/uprobe API is supported. + * Kernels that support new FD-based kprobe and uprobe BPF attachment + * through perf_event_open() syscall expose + * /sys/bus/event_source/devices/kprobe/type and + * /sys/bus/event_source/devices/uprobe/type files, respectively. They + * contain magic numbers that are passed as "type" field of + * perf_event_attr. Lack of such file in the system indicates legacy + * kernel with old-style kprobe/uprobe attach interface through + * creating per-probe event through tracefs. For such cases + * ref_ctr_offset feature is not supported, so we don't test it. + */ + 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", @@ -45,10 +59,11 @@ void test_attach_probe(void) goto cleanup; skel->links.handle_kretprobe = kretprobe_link; - ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before"); + if (!legacy) + ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before"); uprobe_opts.retprobe = false; - uprobe_opts.ref_ctr_offset = ref_ctr_offset; + uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset; uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe, 0 /* self pid */, "/proc/self/exe", @@ -58,11 +73,12 @@ void test_attach_probe(void) goto cleanup; skel->links.handle_uprobe = uprobe_link; - ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after"); + if (!legacy) + ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after"); /* if uprobe uses ref_ctr, uretprobe has to use ref_ctr as well */ uprobe_opts.retprobe = true; - uprobe_opts.ref_ctr_offset = ref_ctr_offset; + uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset; uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe, -1 /* any pid */, "/proc/self/exe", diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 77ac24b191d4..9454331aaf85 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -589,7 +589,7 @@ out: static void test_bpf_hash_map(void) { - __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0; + __u32 expected_key_a = 0, expected_key_b = 0; DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); struct bpf_iter_bpf_hash_map *skel; int err, i, len, map_fd, iter_fd; @@ -638,7 +638,6 @@ static void test_bpf_hash_map(void) val = i + 4; expected_key_a += key.a; expected_key_b += key.b; - expected_key_c += key.c; expected_val += val; err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY); @@ -685,7 +684,7 @@ out: static void test_bpf_percpu_hash_map(void) { - __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0; + __u32 expected_key_a = 0, expected_key_b = 0; DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); struct bpf_iter_bpf_percpu_hash_map *skel; int err, i, j, len, map_fd, iter_fd; @@ -722,7 +721,6 @@ static void test_bpf_percpu_hash_map(void) key.c = i + 3; expected_key_a += key.a; expected_key_b += key.b; - expected_key_c += key.c; for (j = 0; j < bpf_num_possible_cpus(); j++) { *(__u32 *)(val + j * 8) = i + j; diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 649f87382c8d..9c85d7d27409 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -39,8 +39,8 @@ static bool always_log; #define BTF_END_RAW 0xdeadbeef #define NAME_TBD 0xdeadb33f -#define NAME_NTH(N) (0xffff0000 | N) -#define IS_NAME_NTH(X) ((X & 0xffff0000) == 0xffff0000) +#define NAME_NTH(N) (0xfffe0000 | N) +#define IS_NAME_NTH(X) ((X & 0xffff0000) == 0xfffe0000) #define GET_NAME_NTH_IDX(X) (X & 0x0000ffff) #define MAX_NR_RAW_U32 1024 @@ -3661,6 +3661,249 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid type_size", }, +{ + .descr = "tag test #1, struct/member, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(0, 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 32), + BTF_TAG_ENC(NAME_TBD, 2, -1), + BTF_TAG_ENC(NAME_TBD, 2, 0), + BTF_TAG_ENC(NAME_TBD, 2, 1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0m1\0m2\0tag1\0tag2\0tag3"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 8, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 1, +}, +{ + .descr = "tag test #2, union/member, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_UNION_ENC(NAME_TBD, 2, 4), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_TAG_ENC(NAME_TBD, 2, -1), + BTF_TAG_ENC(NAME_TBD, 2, 0), + BTF_TAG_ENC(NAME_TBD, 2, 1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), + .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 = 2, + .max_entries = 1, +}, +{ + .descr = "tag test #3, variable, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_VAR_ENC(NAME_TBD, 1, 1), /* [3] */ + BTF_TAG_ENC(NAME_TBD, 2, -1), + BTF_TAG_ENC(NAME_TBD, 3, -1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0global\0tag1\0tag2"), + .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, +}, +{ + .descr = "tag test #4, func/parameter, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ + BTF_TAG_ENC(NAME_TBD, 3, -1), + BTF_TAG_ENC(NAME_TBD, 3, 0), + BTF_TAG_ENC(NAME_TBD, 3, 1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0arg1\0arg2\0f\0tag1\0tag2\0tag3"), + .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, +}, +{ + .descr = "tag test #5, invalid value", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TAG_ENC(0, 2, -1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag"), + .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 value", +}, +{ + .descr = "tag test #6, invalid target type", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TAG_ENC(NAME_TBD, 1, -1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1"), + .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", +}, +{ + .descr = "tag test #7, invalid vlen", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 0, 1), 2), (0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag1"), + .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 = "vlen != 0", +}, +{ + .descr = "tag test #8, invalid kflag", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 1, 0), 2), (-1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag1"), + .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 btf_info kind_flag", +}, +{ + .descr = "tag test #9, var, invalid component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TAG_ENC(NAME_TBD, 2, 0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag"), + .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 component_idx", +}, +{ + .descr = "tag test #10, struct member, invalid component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(0, 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 32), + BTF_TAG_ENC(NAME_TBD, 2, 2), + BTF_END_RAW, + }, + BTF_STR_SEC("\0m1\0m2\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 8, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid component_idx", +}, +{ + .descr = "tag test #11, func parameter, invalid component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ + BTF_TAG_ENC(NAME_TBD, 3, 2), + BTF_END_RAW, + }, + BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), + .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 component_idx", +}, +{ + .descr = "tag test #12, < -1 component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ + BTF_TAG_ENC(NAME_TBD, 3, -2), + BTF_END_RAW, + }, + BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), + .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 component_idx", +}, + }; /* struct btf_raw_test raw_tests[] */ static const char *get_next_str(const char *start, const char *end) @@ -6421,27 +6664,33 @@ const struct btf_dedup_test dedup_tests[] = { BTF_MEMBER_ENC(NAME_NTH(4), 5, 64), /* const int *a; */ BTF_MEMBER_ENC(NAME_NTH(5), 2, 128), /* int b[16]; */ BTF_MEMBER_ENC(NAME_NTH(6), 1, 640), /* int c; */ - BTF_MEMBER_ENC(NAME_NTH(8), 13, 672), /* float d; */ + BTF_MEMBER_ENC(NAME_NTH(8), 15, 672), /* float d; */ /* ptr -> [3] struct s */ BTF_PTR_ENC(3), /* [4] */ /* ptr -> [6] const int */ BTF_PTR_ENC(6), /* [5] */ /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ + /* tag -> [3] struct s */ + BTF_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + /* tag -> [3] struct s, member 1 */ + BTF_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ /* full copy of the above */ - BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [7] */ - BTF_TYPE_ARRAY_ENC(7, 7, 16), /* [8] */ - BTF_STRUCT_ENC(NAME_NTH(2), 5, 88), /* [9] */ - BTF_MEMBER_ENC(NAME_NTH(3), 10, 0), - BTF_MEMBER_ENC(NAME_NTH(4), 11, 64), - BTF_MEMBER_ENC(NAME_NTH(5), 8, 128), - BTF_MEMBER_ENC(NAME_NTH(6), 7, 640), - BTF_MEMBER_ENC(NAME_NTH(8), 13, 672), - BTF_PTR_ENC(9), /* [10] */ - BTF_PTR_ENC(12), /* [11] */ - BTF_CONST_ENC(7), /* [12] */ - BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [13] */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [9] */ + BTF_TYPE_ARRAY_ENC(9, 9, 16), /* [10] */ + BTF_STRUCT_ENC(NAME_NTH(2), 5, 88), /* [11] */ + BTF_MEMBER_ENC(NAME_NTH(3), 12, 0), + BTF_MEMBER_ENC(NAME_NTH(4), 13, 64), + BTF_MEMBER_ENC(NAME_NTH(5), 10, 128), + BTF_MEMBER_ENC(NAME_NTH(6), 9, 640), + BTF_MEMBER_ENC(NAME_NTH(8), 15, 672), + BTF_PTR_ENC(11), /* [12] */ + BTF_PTR_ENC(14), /* [13] */ + BTF_CONST_ENC(9), /* [14] */ + BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [15] */ + BTF_TAG_ENC(NAME_NTH(2), 11, -1), /* [16] */ + BTF_TAG_ENC(NAME_NTH(2), 11, 1), /* [17] */ BTF_END_RAW, }, BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0float\0d"), @@ -6458,14 +6707,16 @@ const struct btf_dedup_test dedup_tests[] = { BTF_MEMBER_ENC(NAME_NTH(1), 5, 64), /* const int *a; */ BTF_MEMBER_ENC(NAME_NTH(2), 2, 128), /* int b[16]; */ BTF_MEMBER_ENC(NAME_NTH(3), 1, 640), /* int c; */ - BTF_MEMBER_ENC(NAME_NTH(4), 7, 672), /* float d; */ + BTF_MEMBER_ENC(NAME_NTH(4), 9, 672), /* float d; */ /* ptr -> [3] struct s */ BTF_PTR_ENC(3), /* [4] */ /* ptr -> [6] const int */ BTF_PTR_ENC(6), /* [5] */ /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ - BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [7] */ + BTF_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + BTF_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ + BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [9] */ BTF_END_RAW, }, BTF_STR_SEC("\0a\0b\0c\0d\0int\0float\0next\0s"), @@ -6590,9 +6841,11 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ + BTF_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ + BTF_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ BTF_END_RAW, }, - BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N"), + BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"), }, .expect = { .raw_types = { @@ -6616,9 +6869,11 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ + BTF_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ + BTF_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ BTF_END_RAW, }, - BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N"), + BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"), }, .opts = { .dont_resolve_fwds = false, @@ -6767,6 +7022,152 @@ const struct btf_dedup_test dedup_tests[] = { .dedup_table_size = 1 }, }, +{ + .descr = "dedup: func/func_arg/var tags", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* static int t */ + BTF_VAR_ENC(NAME_NTH(1), 1, 0), /* [2] */ + /* void f(int a1, int a2) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), + BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ + /* tag -> t */ + BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [6] */ + /* tag -> func */ + BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [7] */ + BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [8] */ + /* tag -> func arg a1 */ + BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [9] */ + BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [10] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_NTH(1), 1, 0), /* [2] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), + BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ + BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [6] */ + BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [7] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, +{ + .descr = "dedup: func/func_param tags", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* void f(int a1, int a2) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_ENC(NAME_NTH(3), 2), /* [3] */ + /* void f(int a1, int a2) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [4] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_ENC(NAME_NTH(3), 4), /* [5] */ + /* tag -> f: tag1, tag2 */ + BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [6] */ + BTF_TAG_ENC(NAME_NTH(5), 3, -1), /* [7] */ + /* tag -> f/a2: tag1, tag2 */ + BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [8] */ + BTF_TAG_ENC(NAME_NTH(5), 3, 1), /* [9] */ + /* tag -> f: tag1, tag3 */ + BTF_TAG_ENC(NAME_NTH(4), 5, -1), /* [10] */ + BTF_TAG_ENC(NAME_NTH(6), 5, -1), /* [11] */ + /* tag -> f/a2: tag1, tag3 */ + BTF_TAG_ENC(NAME_NTH(4), 5, 1), /* [12] */ + BTF_TAG_ENC(NAME_NTH(6), 5, 1), /* [13] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_ENC(NAME_NTH(3), 2), /* [3] */ + BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [4] */ + BTF_TAG_ENC(NAME_NTH(5), 3, -1), /* [5] */ + BTF_TAG_ENC(NAME_NTH(6), 3, -1), /* [6] */ + BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [7] */ + BTF_TAG_ENC(NAME_NTH(5), 3, 1), /* [8] */ + BTF_TAG_ENC(NAME_NTH(6), 3, 1), /* [9] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, +{ + .descr = "dedup: struct/struct_member tags", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), + BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), + BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [3] */ + BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), + BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), + /* tag -> t: tag1, tag2 */ + BTF_TAG_ENC(NAME_NTH(4), 2, -1), /* [4] */ + BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + /* tag -> t/m2: tag1, tag2 */ + BTF_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + /* tag -> t: tag1, tag3 */ + BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [8] */ + BTF_TAG_ENC(NAME_NTH(6), 3, -1), /* [9] */ + /* tag -> t/m2: tag1, tag3 */ + BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [10] */ + BTF_TAG_ENC(NAME_NTH(6), 3, 1), /* [11] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), + BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), + BTF_TAG_ENC(NAME_NTH(4), 2, -1), /* [3] */ + BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [4] */ + BTF_TAG_ENC(NAME_NTH(6), 2, -1), /* [5] */ + BTF_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + BTF_TAG_ENC(NAME_NTH(6), 2, 1), /* [8] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, }; @@ -6801,6 +7202,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); + case BTF_KIND_TAG: + return base_size + sizeof(struct btf_tag); default: fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind); return -EINVAL; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index 52ccf0cf35e1..87f9df653e4e 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -358,12 +358,27 @@ static void test_btf_dump_int_data(struct btf *btf, struct btf_dump *d, TEST_BTF_DUMP_DATA_OVER(btf, d, NULL, str, int, sizeof(int)-1, "", 1); #ifdef __SIZEOF_INT128__ - TEST_BTF_DUMP_DATA(btf, d, NULL, str, __int128, BTF_F_COMPACT, - "(__int128)0xffffffffffffffff", - 0xffffffffffffffff); - ASSERT_OK(btf_dump_data(btf, d, "__int128", NULL, 0, &i, 16, str, - "(__int128)0xfffffffffffffffffffffffffffffffe"), - "dump __int128"); + /* gcc encode unsigned __int128 type with name "__int128 unsigned" in dwarf, + * and clang encode it with name "unsigned __int128" in dwarf. + * Do an availability test for either variant before doing actual test. + */ + if (btf__find_by_name(btf, "unsigned __int128") > 0) { + TEST_BTF_DUMP_DATA(btf, d, NULL, str, unsigned __int128, BTF_F_COMPACT, + "(unsigned __int128)0xffffffffffffffff", + 0xffffffffffffffff); + ASSERT_OK(btf_dump_data(btf, d, "unsigned __int128", NULL, 0, &i, 16, str, + "(unsigned __int128)0xfffffffffffffffffffffffffffffffe"), + "dump unsigned __int128"); + } else if (btf__find_by_name(btf, "__int128 unsigned") > 0) { + TEST_BTF_DUMP_DATA(btf, d, NULL, str, __int128 unsigned, BTF_F_COMPACT, + "(__int128 unsigned)0xffffffffffffffff", + 0xffffffffffffffff); + ASSERT_OK(btf_dump_data(btf, d, "__int128 unsigned", NULL, 0, &i, 16, str, + "(__int128 unsigned)0xfffffffffffffffffffffffffffffffe"), + "dump unsigned __int128"); + } else { + ASSERT_TRUE(false, "unsigned_int128_not_found"); + } #endif } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_tag.c b/tools/testing/selftests/bpf/prog_tests/btf_tag.c new file mode 100644 index 000000000000..91821f42714d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/btf_tag.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <test_progs.h> +#include "tag.skel.h" + +void test_btf_tag(void) +{ + struct tag *skel; + + skel = tag__open_and_load(); + if (!ASSERT_OK_PTR(skel, "btf_tag")) + return; + + if (skel->rodata->skip_tests) { + printf("%s:SKIP: btf_tag attribute not supported", __func__); + test__skip(); + } + + tag__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c index 022c7d89d6f4..76548eecce2c 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_write.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c @@ -281,5 +281,26 @@ void test_btf_write() { "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", "raw_dump"); + /* TAG */ + id = btf__add_tag(btf, "tag1", 16, -1); + ASSERT_EQ(id, 18, "tag_id"); + t = btf__type_by_id(btf, 18); + ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag1", "tag_value"); + ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind"); + ASSERT_EQ(t->type, 16, "tag_type"); + ASSERT_EQ(btf_tag(t)->component_idx, -1, "tag_component_idx"); + ASSERT_STREQ(btf_type_raw_dump(btf, 18), + "[18] TAG 'tag1' type_id=16 component_idx=-1", "raw_dump"); + + id = btf__add_tag(btf, "tag2", 14, 1); + ASSERT_EQ(id, 19, "tag_id"); + t = btf__type_by_id(btf, 19); + ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag2", "tag_value"); + ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind"); + ASSERT_EQ(t->type, 14, "tag_type"); + ASSERT_EQ(btf_tag(t)->component_idx, 1, "tag_component_idx"); + ASSERT_STREQ(btf_type_raw_dump(btf, 19), + "[19] TAG 'tag2' type_id=14 component_idx=1", "raw_dump"); + btf__free(btf); } diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 4739b15b2a97..763302e63a29 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -30,7 +30,7 @@ static int duration = 0; .output_len = sizeof(struct core_reloc_module_output), \ .prog_sec_name = sec_name, \ .raw_tp_name = tp_name, \ - .trigger = trigger_module_test_read, \ + .trigger = __trigger_module_test_read, \ .needs_testmod = true, \ } @@ -249,8 +249,7 @@ static int duration = 0; #define SIZE_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_size.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o", \ - .relaxed_core_relocs = true + .btf_src_file = "btf__core_reloc_" #name ".o" #define SIZE_OUTPUT_DATA(type) \ STRUCT_TO_CHAR_PTR(core_reloc_size_output) { \ @@ -475,19 +474,11 @@ static int setup_type_id_case_failure(struct core_reloc_test_case *test) return 0; } -static int trigger_module_test_read(const struct core_reloc_test_case *test) +static int __trigger_module_test_read(const struct core_reloc_test_case *test) { struct core_reloc_module_output *exp = (void *)test->output; - int fd, err; - - fd = open("/sys/kernel/bpf_testmod", O_RDONLY); - err = -errno; - if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) - return err; - - read(fd, NULL, exp->len); /* request expected number of bytes */ - close(fd); + trigger_module_test_read(exp->len); return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index 73b4c76e6b86..c7c1816899bf 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -60,7 +60,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, struct bpf_object *obj = NULL, *tgt_obj; __u32 retval, tgt_prog_id, info_len; struct bpf_prog_info prog_info = {}; - struct bpf_program **prog = NULL; + struct bpf_program **prog = NULL, *p; struct bpf_link **link = NULL; int err, tgt_fd, i; struct btf *btf; @@ -69,9 +69,6 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, &tgt_obj, &tgt_fd); if (!ASSERT_OK(err, "tgt_prog_load")) return; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, - .attach_prog_fd = tgt_fd, - ); info_len = sizeof(prog_info); err = bpf_obj_get_info_by_fd(tgt_fd, &prog_info, &info_len); @@ -89,10 +86,15 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, if (!ASSERT_OK_PTR(prog, "prog_ptr")) goto close_prog; - obj = bpf_object__open_file(obj_file, &opts); + obj = bpf_object__open_file(obj_file, NULL); if (!ASSERT_OK_PTR(obj, "obj_open")) goto close_prog; + bpf_object__for_each_program(p, obj) { + err = bpf_program__set_attach_target(p, tgt_fd, NULL); + ASSERT_OK(err, "set_attach_target"); + } + err = bpf_object__load(obj); if (!ASSERT_OK(err, "obj_load")) goto close_prog; @@ -270,7 +272,7 @@ static void test_fmod_ret_freplace(void) struct bpf_link *freplace_link = NULL; struct bpf_program *prog; __u32 duration = 0; - int err, pkt_fd; + int err, pkt_fd, attach_prog_fd; err = bpf_prog_load(tgt_name, BPF_PROG_TYPE_UNSPEC, &pkt_obj, &pkt_fd); @@ -278,26 +280,32 @@ static void test_fmod_ret_freplace(void) if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n", tgt_name, err, errno)) return; - opts.attach_prog_fd = pkt_fd; - freplace_obj = bpf_object__open_file(freplace_name, &opts); + freplace_obj = bpf_object__open_file(freplace_name, NULL); if (!ASSERT_OK_PTR(freplace_obj, "freplace_obj_open")) goto out; + prog = bpf_program__next(NULL, freplace_obj); + err = bpf_program__set_attach_target(prog, pkt_fd, NULL); + ASSERT_OK(err, "freplace__set_attach_target"); + err = bpf_object__load(freplace_obj); if (CHECK(err, "freplace_obj_load", "err %d\n", err)) goto out; - prog = bpf_program__next(NULL, freplace_obj); freplace_link = bpf_program__attach_trace(prog); if (!ASSERT_OK_PTR(freplace_link, "freplace_attach_trace")) goto out; - opts.attach_prog_fd = bpf_program__fd(prog); - fmod_obj = bpf_object__open_file(fmod_ret_name, &opts); + fmod_obj = bpf_object__open_file(fmod_ret_name, NULL); if (!ASSERT_OK_PTR(fmod_obj, "fmod_obj_open")) goto out; + attach_prog_fd = bpf_program__fd(prog); + prog = bpf_program__next(NULL, fmod_obj); + err = bpf_program__set_attach_target(prog, attach_prog_fd, NULL); + ASSERT_OK(err, "fmod_ret_set_attach_target"); + err = bpf_object__load(fmod_obj); if (CHECK(!err, "fmod_obj_load", "loading fmod_ret should fail\n")) goto out; @@ -322,14 +330,14 @@ static void test_func_sockmap_update(void) } static void test_obj_load_failure_common(const char *obj_file, - const char *target_obj_file) - + const char *target_obj_file) { /* * standalone test that asserts failure to load freplace prog * because of invalid return code. */ struct bpf_object *obj = NULL, *pkt_obj; + struct bpf_program *prog; int err, pkt_fd; __u32 duration = 0; @@ -339,14 +347,15 @@ static void test_obj_load_failure_common(const char *obj_file, if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n", target_obj_file, err, errno)) return; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, - .attach_prog_fd = pkt_fd, - ); - obj = bpf_object__open_file(obj_file, &opts); + obj = bpf_object__open_file(obj_file, NULL); if (!ASSERT_OK_PTR(obj, "obj_open")) goto close_prog; + prog = bpf_program__next(NULL, obj); + err = bpf_program__set_attach_target(prog, pkt_fd, NULL); + ASSERT_OK(err, "set_attach_target"); + /* It should fail to load the program */ err = bpf_object__load(obj); if (CHECK(!err, "bpf_obj_load should fail", "err %d\n", err)) diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 225714f71ac6..ac54e3f91d42 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -458,9 +458,9 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) return -1; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "flow_dissector/%i", i); + snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (!prog) return -1; diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c new file mode 100644 index 000000000000..67e86f8d8677 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <test_progs.h> +#include "get_branch_snapshot.skel.h" + +static int *pfd_array; +static int cpu_cnt; + +static int create_perf_events(void) +{ + struct perf_event_attr attr = {0}; + int cpu; + + /* create perf event */ + attr.size = sizeof(attr); + attr.type = PERF_TYPE_RAW; + attr.config = 0x1b00; + attr.sample_type = PERF_SAMPLE_BRANCH_STACK; + attr.branch_sample_type = PERF_SAMPLE_BRANCH_KERNEL | + PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY; + + cpu_cnt = libbpf_num_possible_cpus(); + pfd_array = malloc(sizeof(int) * cpu_cnt); + if (!pfd_array) { + cpu_cnt = 0; + return 1; + } + + for (cpu = 0; cpu < cpu_cnt; cpu++) { + pfd_array[cpu] = syscall(__NR_perf_event_open, &attr, + -1, cpu, -1, PERF_FLAG_FD_CLOEXEC); + if (pfd_array[cpu] < 0) + break; + } + + return cpu == 0; +} + +static void close_perf_events(void) +{ + int cpu, fd; + + for (cpu = 0; cpu < cpu_cnt; cpu++) { + fd = pfd_array[cpu]; + if (fd < 0) + break; + close(fd); + } + free(pfd_array); +} + +void test_get_branch_snapshot(void) +{ + struct get_branch_snapshot *skel = NULL; + int err; + + if (create_perf_events()) { + test__skip(); /* system doesn't support LBR */ + goto cleanup; + } + + skel = get_branch_snapshot__open_and_load(); + if (!ASSERT_OK_PTR(skel, "get_branch_snapshot__open_and_load")) + goto cleanup; + + err = kallsyms_find("bpf_testmod_loop_test", &skel->bss->address_low); + if (!ASSERT_OK(err, "kallsyms_find")) + goto cleanup; + + err = kallsyms_find_next("bpf_testmod_loop_test", &skel->bss->address_high); + if (!ASSERT_OK(err, "kallsyms_find_next")) + goto cleanup; + + err = get_branch_snapshot__attach(skel); + if (!ASSERT_OK(err, "get_branch_snapshot__attach")) + goto cleanup; + + trigger_module_test_read(100); + + if (skel->bss->total_entries < 16) { + /* too few entries for the hit/waste test */ + test__skip(); + goto cleanup; + } + + ASSERT_GT(skel->bss->test1_hits, 6, "find_looptest_in_lbr"); + + /* Given we stop LBR in software, we will waste a few entries. + * But we should try to waste as few as possible entries. We are at + * about 7 on x86_64 systems. + * Add a check for < 10 so that we get heads-up when something + * changes and wastes too many entries. + */ + ASSERT_LT(skel->bss->wasted_entries, 10, "check_wasted_entries"); + +cleanup: + get_branch_snapshot__destroy(skel); + close_perf_events(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c index d85a69b7ce44..1797a6e4d6d8 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c @@ -6,45 +6,6 @@ static int duration; -static int trigger_module_test_read(int read_sz) -{ - int fd, err; - - fd = open("/sys/kernel/bpf_testmod", O_RDONLY); - err = -errno; - if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) - return err; - - read(fd, NULL, read_sz); - close(fd); - - return 0; -} - -static int trigger_module_test_write(int write_sz) -{ - int fd, err; - char *buf = malloc(write_sz); - - if (!buf) - return -ENOMEM; - - memset(buf, 'a', write_sz); - buf[write_sz-1] = '\0'; - - fd = open("/sys/kernel/bpf_testmod", O_WRONLY); - err = -errno; - if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) { - free(buf); - return err; - } - - write(fd, buf, write_sz); - close(fd); - free(buf); - return 0; -} - static int delete_module(const char *name, int flags) { return syscall(__NR_delete_module, name, flags); diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c index 95bd12097358..52fe157e2a90 100644 --- a/tools/testing/selftests/bpf/prog_tests/probe_user.c +++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c @@ -3,7 +3,7 @@ void test_probe_user(void) { - const char *prog_name = "kprobe/__sys_connect"; + const char *prog_name = "handle_sys_connect"; const char *obj_file = "./test_probe_user.o"; DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, ); int err, results_map_fd, sock_fd, duration = 0; @@ -18,7 +18,7 @@ void test_probe_user(void) if (!ASSERT_OK_PTR(obj, "obj_open_file")) return; - kprobe_prog = bpf_object__find_program_by_title(obj, prog_name); + kprobe_prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK(!kprobe_prog, "find_probe", "prog '%s' not found\n", prog_name)) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c index 4e91f4d6466c..873323fb18ba 100644 --- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c +++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c @@ -1,6 +1,21 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +static void toggle_object_autoload_progs(const struct bpf_object *obj, + const char *name_load) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + const char *name = bpf_program__name(prog); + + if (!strcmp(name_load, name)) + bpf_program__set_autoload(prog, true); + else + bpf_program__set_autoload(prog, false); + } +} + void test_reference_tracking(void) { const char *file = "test_sk_lookup_kern.o"; @@ -9,44 +24,49 @@ void test_reference_tracking(void) .object_name = obj_name, .relaxed_maps = true, ); - struct bpf_object *obj; + struct bpf_object *obj_iter, *obj = NULL; struct bpf_program *prog; __u32 duration = 0; int err = 0; - obj = bpf_object__open_file(file, &open_opts); - if (!ASSERT_OK_PTR(obj, "obj_open_file")) + obj_iter = bpf_object__open_file(file, &open_opts); + if (!ASSERT_OK_PTR(obj_iter, "obj_iter_open_file")) return; - if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name", + if (CHECK(strcmp(bpf_object__name(obj_iter), obj_name), "obj_name", "wrong obj name '%s', expected '%s'\n", - bpf_object__name(obj), obj_name)) + bpf_object__name(obj_iter), obj_name)) goto cleanup; - bpf_object__for_each_program(prog, obj) { - const char *title; + bpf_object__for_each_program(prog, obj_iter) { + const char *name; - /* Ignore .text sections */ - title = bpf_program__section_name(prog); - if (strstr(title, ".text") != NULL) + name = bpf_program__name(prog); + if (!test__start_subtest(name)) continue; - if (!test__start_subtest(title)) - continue; + obj = bpf_object__open_file(file, &open_opts); + if (!ASSERT_OK_PTR(obj, "obj_open_file")) + goto cleanup; + toggle_object_autoload_progs(obj, name); /* Expect verifier failure if test name has 'err' */ - if (strstr(title, "err_") != NULL) { + if (strncmp(name, "err_", sizeof("err_") - 1) == 0) { libbpf_print_fn_t old_print_fn; old_print_fn = libbpf_set_print(NULL); - err = !bpf_program__load(prog, "GPL", 0); + err = !bpf_object__load(obj); libbpf_set_print(old_print_fn); } else { - err = bpf_program__load(prog, "GPL", 0); + err = bpf_object__load(obj); } - CHECK(err, title, "\n"); + ASSERT_OK(err, name); + + bpf_object__close(obj); + obj = NULL; } cleanup: bpf_object__close(obj); + bpf_object__close(obj_iter); } diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index 3a469099f30d..1d272e05188e 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -48,7 +48,7 @@ configure_stack(void) return false; sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf", "direct-action object-file ./test_sk_assign.o", - "section classifier/sk_assign_test", + "section tc", (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose"); if (CHECK(system(tc_cmd), "BPF load failed;", "run with -vv for more info\n")) diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index fafeddaad6a9..c437e6ba8fe2 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -11,12 +11,14 @@ void test_skb_ctx(void) .cb[3] = 4, .cb[4] = 5, .priority = 6, + .ingress_ifindex = 11, .ifindex = 1, .tstamp = 7, .wire_len = 100, .gso_segs = 8, .mark = 9, .gso_size = 10, + .hwtstamp = 11, }; struct bpf_prog_test_run_attr tattr = { .data_in = &pkt_v4, @@ -97,6 +99,10 @@ void test_skb_ctx(void) "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", diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c index f6f130c99b8c..fe1e204a65c6 100644 --- a/tools/testing/selftests/bpf/prog_tests/skeleton.c +++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c @@ -18,6 +18,8 @@ void test_skeleton(void) struct test_skeleton__data *data; struct test_skeleton__rodata *rodata; struct test_skeleton__kconfig *kcfg; + const void *elf_bytes; + size_t elf_bytes_sz = 0; skel = test_skeleton__open(); if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) @@ -91,6 +93,10 @@ void test_skeleton(void) CHECK(bss->kern_ver != kcfg->LINUX_KERNEL_VERSION, "ext2", "got %d != exp %d\n", bss->kern_ver, kcfg->LINUX_KERNEL_VERSION); + elf_bytes = test_skeleton__elf_bytes(&elf_bytes_sz); + ASSERT_OK_PTR(elf_bytes, "elf_bytes"); + ASSERT_GE(elf_bytes_sz, 0, "elf_bytes_sz"); + cleanup: test_skeleton__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index 51fac975b316..bc34f7773444 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -2,7 +2,7 @@ #include <test_progs.h> #include "cgroup_helpers.h" -static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) +static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) { enum bpf_attach_type attach_type; enum bpf_prog_type prog_type; @@ -15,23 +15,23 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) return -1; } - prog = bpf_object__find_program_by_title(obj, title); + prog = bpf_object__find_program_by_name(obj, name); if (!prog) { - log_err("Failed to find %s BPF program", title); + log_err("Failed to find %s BPF program", name); return -1; } err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, attach_type, BPF_F_ALLOW_MULTI); if (err) { - log_err("Failed to attach %s BPF program", title); + log_err("Failed to attach %s BPF program", name); return -1; } return 0; } -static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title) +static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name) { enum bpf_attach_type attach_type; enum bpf_prog_type prog_type; @@ -42,7 +42,7 @@ static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title) if (err) return -1; - prog = bpf_object__find_program_by_title(obj, title); + prog = bpf_object__find_program_by_name(obj, name); if (!prog) return -1; @@ -89,7 +89,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - child: 0x80 -> 0x90 */ - err = prog_attach(obj, cg_child, "cgroup/getsockopt/child"); + err = prog_attach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); if (err) goto detach; @@ -113,7 +113,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: 0x90 -> 0xA0 */ - err = prog_attach(obj, cg_parent, "cgroup/getsockopt/parent"); + err = prog_attach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); if (err) goto detach; @@ -157,7 +157,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, * - parent: unexpected 0x40, EPERM */ - err = prog_detach(obj, cg_child, "cgroup/getsockopt/child"); + err = prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); if (err) { log_err("Failed to detach child program"); goto detach; @@ -198,8 +198,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/getsockopt/child"); - prog_detach(obj, cg_parent, "cgroup/getsockopt/parent"); + prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child"); + prog_detach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent"); return err; } @@ -236,7 +236,7 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach child program and make sure it adds 0x10. */ - err = prog_attach(obj, cg_child, "cgroup/setsockopt"); + err = prog_attach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); if (err) goto detach; @@ -263,7 +263,7 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, /* Attach parent program and make sure it adds another 0x10. */ - err = prog_attach(obj, cg_parent, "cgroup/setsockopt"); + err = prog_attach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); if (err) goto detach; @@ -289,8 +289,8 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, } detach: - prog_detach(obj, cg_child, "cgroup/setsockopt"); - prog_detach(obj, cg_parent, "cgroup/setsockopt"); + prog_detach(obj, cg_child, "cgroup/setsockopt", "_setsockopt"); + prog_detach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt"); return err; } diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index b5940e6ca67c..9825f1f7bfcc 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -21,7 +21,7 @@ static void test_tailcall_1(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -38,9 +38,9 @@ static void test_tailcall_1(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -70,9 +70,9 @@ static void test_tailcall_1(void) err, errno, retval); for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -92,9 +92,9 @@ static void test_tailcall_1(void) for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { j = bpf_map__def(prog_array)->max_entries - 1 - i; - snprintf(prog_name, sizeof(prog_name), "classifier/%i", j); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", j); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -159,7 +159,7 @@ static void test_tailcall_2(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -176,9 +176,9 @@ static void test_tailcall_2(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -219,10 +219,7 @@ out: bpf_object__close(obj); } -/* test_tailcall_3 checks that the count value of the tail call limit - * enforcement matches with expectations. - */ -static void test_tailcall_3(void) +static void test_tailcall_count(const char *which) { int err, map_fd, prog_fd, main_fd, data_fd, i, val; struct bpf_map *prog_array, *data_map; @@ -231,12 +228,12 @@ static void test_tailcall_3(void) __u32 retval, duration; char buff[128] = {}; - err = bpf_prog_load("tailcall3.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + err = bpf_prog_load(which, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -252,7 +249,7 @@ static void test_tailcall_3(void) if (CHECK_FAIL(map_fd < 0)) goto out; - prog = bpf_object__find_program_by_title(obj, "classifier/0"); + prog = bpf_object__find_program_by_name(obj, "classifier_0"); if (CHECK_FAIL(!prog)) goto out; @@ -296,6 +293,22 @@ out: bpf_object__close(obj); } +/* test_tailcall_3 checks that the count value of the tail call limit + * enforcement matches with expectations. JIT uses direct jump. + */ +static void test_tailcall_3(void) +{ + test_tailcall_count("tailcall3.o"); +} + +/* test_tailcall_6 checks that the count value of the tail call limit + * enforcement matches with expectations. JIT uses indirect jump. + */ +static void test_tailcall_6(void) +{ + test_tailcall_count("tailcall6.o"); +} + /* test_tailcall_4 checks that the kernel properly selects indirect jump * for the case where the key is not known. Latter is passed via global * data to select different targets we can compare return value of. @@ -316,7 +329,7 @@ static void test_tailcall_4(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -341,9 +354,9 @@ static void test_tailcall_4(void) return; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -404,7 +417,7 @@ static void test_tailcall_5(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -429,9 +442,9 @@ static void test_tailcall_5(void) return; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -490,7 +503,7 @@ static void test_tailcall_bpf2bpf_1(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -508,9 +521,9 @@ static void test_tailcall_bpf2bpf_1(void) /* nop -> jmp */ for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -574,7 +587,7 @@ static void test_tailcall_bpf2bpf_2(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -590,7 +603,7 @@ static void test_tailcall_bpf2bpf_2(void) if (CHECK_FAIL(map_fd < 0)) goto out; - prog = bpf_object__find_program_by_title(obj, "classifier/0"); + prog = bpf_object__find_program_by_name(obj, "classifier_0"); if (CHECK_FAIL(!prog)) goto out; @@ -652,7 +665,7 @@ static void test_tailcall_bpf2bpf_3(void) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -669,9 +682,9 @@ static void test_tailcall_bpf2bpf_3(void) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -749,7 +762,7 @@ static void test_tailcall_bpf2bpf_4(bool noise) if (CHECK_FAIL(err)) return; - prog = bpf_object__find_program_by_title(obj, "classifier"); + prog = bpf_object__find_program_by_name(obj, "entry"); if (CHECK_FAIL(!prog)) goto out; @@ -766,9 +779,9 @@ static void test_tailcall_bpf2bpf_4(bool noise) goto out; for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - snprintf(prog_name, sizeof(prog_name), "classifier/%i", i); + snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); - prog = bpf_object__find_program_by_title(obj, prog_name); + prog = bpf_object__find_program_by_name(obj, prog_name); if (CHECK_FAIL(!prog)) goto out; @@ -822,6 +835,8 @@ void test_tailcalls(void) test_tailcall_4(); if (test__start_subtest("tailcall_5")) test_tailcall_5(); + if (test__start_subtest("tailcall_6")) + test_tailcall_6(); if (test__start_subtest("tailcall_bpf2bpf_1")) test_tailcall_bpf2bpf_1(); if (test__start_subtest("tailcall_bpf2bpf_2")) diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index e7201ba29ccd..e87bc4466d9a 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -633,7 +633,7 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) struct nstoken *nstoken = NULL; int err; int tunnel_pid = -1; - int src_fd, target_fd; + int src_fd, target_fd = -1; int ifindex; /* Start a L3 TUN/TAP tunnel between the src and dst namespaces. diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c index d39bc00feb45..e47835f0a674 100644 --- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c +++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c @@ -10,7 +10,7 @@ void test_trace_printk(void) { - int err, iter = 0, duration = 0, found = 0; + int err = 0, iter = 0, found = 0; struct trace_printk__bss *bss; struct trace_printk *skel; char *buf = NULL; @@ -18,25 +18,24 @@ void test_trace_printk(void) size_t buflen; skel = trace_printk__open(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!ASSERT_OK_PTR(skel, "trace_printk__open")) return; - ASSERT_EQ(skel->rodata->fmt[0], 'T', "invalid printk fmt string"); + ASSERT_EQ(skel->rodata->fmt[0], 'T', "skel->rodata->fmt[0]"); skel->rodata->fmt[0] = 't'; err = trace_printk__load(skel); - if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) + if (!ASSERT_OK(err, "trace_printk__load")) goto cleanup; bss = skel->bss; err = trace_printk__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + if (!ASSERT_OK(err, "trace_printk__attach")) goto cleanup; fp = fopen(TRACEBUF, "r"); - if (CHECK(fp == NULL, "could not open trace buffer", - "error %d opening %s", errno, TRACEBUF)) + if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)")) goto cleanup; /* We do not want to wait forever if this test fails... */ @@ -46,14 +45,10 @@ void test_trace_printk(void) usleep(1); trace_printk__detach(skel); - if (CHECK(bss->trace_printk_ran == 0, - "bpf_trace_printk never ran", - "ran == %d", bss->trace_printk_ran)) + if (!ASSERT_GT(bss->trace_printk_ran, 0, "bss->trace_printk_ran")) goto cleanup; - if (CHECK(bss->trace_printk_ret <= 0, - "bpf_trace_printk returned <= 0 value", - "got %d", bss->trace_printk_ret)) + if (!ASSERT_GT(bss->trace_printk_ret, 0, "bss->trace_printk_ret")) goto cleanup; /* verify our search string is in the trace buffer */ @@ -66,8 +61,7 @@ void test_trace_printk(void) break; } - if (CHECK(!found, "message from bpf_trace_printk not found", - "no instance of %s in %s", SEARCHMSG, TRACEBUF)) + if (!ASSERT_EQ(found, bss->trace_printk_ran, "found")) goto cleanup; cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c new file mode 100644 index 000000000000..61a24e62e1a0 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <test_progs.h> + +#include "trace_vprintk.lskel.h" + +#define TRACEBUF "/sys/kernel/debug/tracing/trace_pipe" +#define SEARCHMSG "1,2,3,4,5,6,7,8,9,10" + +void test_trace_vprintk(void) +{ + int err = 0, iter = 0, found = 0; + struct trace_vprintk__bss *bss; + struct trace_vprintk *skel; + char *buf = NULL; + FILE *fp = NULL; + size_t buflen; + + skel = trace_vprintk__open_and_load(); + if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load")) + goto cleanup; + + bss = skel->bss; + + err = trace_vprintk__attach(skel); + if (!ASSERT_OK(err, "trace_vprintk__attach")) + goto cleanup; + + fp = fopen(TRACEBUF, "r"); + if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)")) + goto cleanup; + + /* We do not want to wait forever if this test fails... */ + fcntl(fileno(fp), F_SETFL, O_NONBLOCK); + + /* wait for tracepoint to trigger */ + usleep(1); + trace_vprintk__detach(skel); + + if (!ASSERT_GT(bss->trace_vprintk_ran, 0, "bss->trace_vprintk_ran")) + goto cleanup; + + if (!ASSERT_GT(bss->trace_vprintk_ret, 0, "bss->trace_vprintk_ret")) + goto cleanup; + + /* verify our search string is in the trace buffer */ + while (getline(&buf, &buflen, fp) >= 0 || errno == EAGAIN) { + if (strstr(buf, SEARCHMSG) != NULL) + found++; + if (found == bss->trace_vprintk_ran) + break; + if (++iter > 1000) + break; + } + + if (!ASSERT_EQ(found, bss->trace_vprintk_ran, "found")) + goto cleanup; + + if (!ASSERT_LT(bss->null_data_vprintk_ret, 0, "bss->null_data_vprintk_ret")) + goto cleanup; + +cleanup: + trace_vprintk__destroy(skel); + free(buf); + if (fp) + fclose(fp); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdpwall.c b/tools/testing/selftests/bpf/prog_tests/xdpwall.c new file mode 100644 index 000000000000..f3927829a55a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdpwall.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "test_progs.h" +#include "xdpwall.skel.h" + +void test_xdpwall(void) +{ + struct xdpwall *skel; + + skel = xdpwall__open_and_load(); + ASSERT_OK_PTR(skel, "Does LLMV have https://reviews.llvm.org/D109073?"); + + xdpwall__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index f62df4d023f9..d9660e7200e2 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -169,11 +169,7 @@ static __always_inline void bictcp_hystart_reset(struct sock *sk) ca->sample_cnt = 0; } -/* "struct_ops/" prefix is not a requirement - * It will be recognized as BPF_PROG_TYPE_STRUCT_OPS - * as long as it is used in one of the func ptr - * under SEC(".struct_ops"). - */ +/* "struct_ops/" prefix is a requirement */ SEC("struct_ops/bpf_cubic_init") void BPF_PROG(bpf_cubic_init, struct sock *sk) { @@ -188,10 +184,8 @@ void BPF_PROG(bpf_cubic_init, struct sock *sk) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } -/* No prefix in SEC will also work. - * The remaining tcp-cubic functions have an easier way. - */ -SEC("no-sec-prefix-bictcp_cwnd_event") +/* "struct_ops" prefix is a requirement */ +SEC("struct_ops/bpf_cubic_cwnd_event") void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 95a5a0778ed7..f266c757b3df 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -19,9 +19,8 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -int _version SEC("version") = 1; #define PROG(F) PROG_(F, _##F) -#define PROG_(NUM, NAME) SEC("flow_dissector/"#NUM) int bpf_func##NAME +#define PROG_(NUM, NAME) SEC("flow_dissector") int flow_dissector_##NUM /* These are the identifiers of the BPF programs that will be used in tail * calls. Name is limited to 16 characters, with the terminating character and diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c index a25373002055..3f81ff92184c 100644 --- a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c @@ -20,7 +20,7 @@ struct { __u32 invocations = 0; -SEC("cgroup_skb/egress/1") +SEC("cgroup_skb/egress") int egress1(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = @@ -32,7 +32,7 @@ int egress1(struct __sk_buff *skb) return 1; } -SEC("cgroup_skb/egress/2") +SEC("cgroup_skb/egress") int egress2(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c index a149f33bc533..d662db27fe4a 100644 --- a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c +++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c @@ -20,7 +20,7 @@ struct { __u32 invocations = 0; -SEC("cgroup_skb/egress/1") +SEC("cgroup_skb/egress") int egress1(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = @@ -32,7 +32,7 @@ int egress1(struct __sk_buff *skb) return 1; } -SEC("cgroup_skb/egress/2") +SEC("cgroup_skb/egress") int egress2(struct __sk_buff *skb) { struct cgroup_value *ptr_cg_storage = diff --git a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c index 75e8e1069fe7..df918b2469da 100644 --- a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c +++ b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c @@ -47,7 +47,7 @@ check_percpu_elem(struct bpf_map *map, __u32 *key, __u64 *val, u32 arraymap_output = 0; -SEC("classifier") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { struct callback_ctx data; diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c index 913dd91aafff..276994d5c0c7 100644 --- a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c +++ b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c @@ -78,7 +78,7 @@ int hashmap_output = 0; int hashmap_elems = 0; int percpu_map_elems = 0; -SEC("classifier") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { struct callback_ctx data; diff --git a/tools/testing/selftests/bpf/progs/get_branch_snapshot.c b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c new file mode 100644 index 000000000000..a1b139888048 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +__u64 test1_hits = 0; +__u64 address_low = 0; +__u64 address_high = 0; +int wasted_entries = 0; +long total_entries = 0; + +#define ENTRY_CNT 32 +struct perf_branch_entry entries[ENTRY_CNT] = {}; + +static inline bool in_range(__u64 val) +{ + return (val >= address_low) && (val < address_high); +} + +SEC("fexit/bpf_testmod_loop_test") +int BPF_PROG(test1, int n, int ret) +{ + long i; + + total_entries = bpf_get_branch_snapshot(entries, sizeof(entries), 0); + total_entries /= sizeof(struct perf_branch_entry); + + for (i = 0; i < ENTRY_CNT; i++) { + if (i >= total_entries) + break; + if (in_range(entries[i].from) && in_range(entries[i].to)) + test1_hits++; + else if (!test1_hits) + wasted_entries++; + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c index 55e283050cab..7236da72ce80 100644 --- a/tools/testing/selftests/bpf/progs/kfree_skb.c +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c @@ -9,8 +9,8 @@ char _license[] SEC("license") = "GPL"; struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); #define _(P) (__builtin_preserve_access_index(P)) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 470f8723e463..8a8cf59017aa 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -8,7 +8,7 @@ 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; -SEC("classifier") +SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) { struct bpf_sock *sk = skb->sk; @@ -23,7 +23,7 @@ int kfunc_call_test2(struct __sk_buff *skb) return bpf_kfunc_call_test2((struct sock *)sk, 1, 2); } -SEC("classifier") +SEC("tc") int kfunc_call_test1(struct __sk_buff *skb) { struct bpf_sock *sk = skb->sk; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c index 5fbd9e232d44..c1fdecabeabf 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -33,7 +33,7 @@ int __noinline f1(struct __sk_buff *skb) return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4); } -SEC("classifier") +SEC("tc") int kfunc_call_test1(struct __sk_buff *skb) { return f1(skb); diff --git a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c index 25467d13c356..b3fcb5274ee0 100644 --- a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c +++ b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c @@ -11,8 +11,8 @@ typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 16384); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c index 7f2eaa2f89f8..992b7861003a 100644 --- a/tools/testing/selftests/bpf/progs/skb_pkt_end.c +++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c @@ -25,7 +25,7 @@ out: return ip; } -SEC("classifier/cls") +SEC("tc") int main_prog(struct __sk_buff *skb) { struct iphdr *ip = NULL; diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c index 4797dc985064..73872c535cbb 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c @@ -7,22 +7,22 @@ int _version SEC("version") = 1; struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_rx SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_tx SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_SOCKMAP); __uint(max_entries, 20); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } sock_map_msg SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c index 9d8c212dde9f..177a59069dae 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_multi.c +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -4,9 +4,8 @@ #include <bpf/bpf_helpers.h> char _license[] SEC("license") = "GPL"; -__u32 _version SEC("version") = 1; -SEC("cgroup/getsockopt/child") +SEC("cgroup/getsockopt") int _getsockopt_child(struct bpf_sockopt *ctx) { __u8 *optval_end = ctx->optval_end; @@ -29,7 +28,7 @@ int _getsockopt_child(struct bpf_sockopt *ctx) return 1; } -SEC("cgroup/getsockopt/parent") +SEC("cgroup/getsockopt") int _getsockopt_parent(struct bpf_sockopt *ctx) { __u8 *optval_end = ctx->optval_end; diff --git a/tools/testing/selftests/bpf/progs/tag.c b/tools/testing/selftests/bpf/progs/tag.c new file mode 100644 index 000000000000..b46b1bfac7da --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tag.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#ifndef __has_attribute +#define __has_attribute(x) 0 +#endif + +#if __has_attribute(btf_tag) +#define __tag1 __attribute__((btf_tag("tag1"))) +#define __tag2 __attribute__((btf_tag("tag2"))) +volatile const bool skip_tests __tag1 __tag2 = false; +#else +#define __tag1 +#define __tag2 +volatile const bool skip_tests = true; +#endif + +struct key_t { + int a; + int b __tag1 __tag2; + int c; +} __tag1 __tag2; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u64); +} hashmap1 SEC(".maps"); + + +static __noinline int foo(int x __tag1 __tag2) __tag1 __tag2 +{ + struct key_t key; + __u64 val = 1; + + key.a = key.b = key.c = x; + bpf_map_update_elem(&hashmap1, &key, &val, 0); + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(sub, int x) +{ + return foo(x); +} diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c index 7115bcefbe8a..8159a0b4a69a 100644 --- a/tools/testing/selftests/bpf/progs/tailcall1.c +++ b/tools/testing/selftests/bpf/progs/tailcall1.c @@ -11,8 +11,8 @@ struct { } jmp_table SEC(".maps"); #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -20,7 +20,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { /* Multiple locations to make sure we patch @@ -45,4 +45,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c index 0431e4fe7efd..a5ff53e61702 100644 --- a/tools/testing/selftests/bpf/progs/tailcall2.c +++ b/tools/testing/selftests/bpf/progs/tailcall2.c @@ -10,41 +10,41 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 1); return 0; } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 2); return 1; } -SEC("classifier/2") -int bpf_func_2(struct __sk_buff *skb) +SEC("tc") +int classifier_2(struct __sk_buff *skb) { return 2; } -SEC("classifier/3") -int bpf_func_3(struct __sk_buff *skb) +SEC("tc") +int classifier_3(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 4); return 3; } -SEC("classifier/4") -int bpf_func_4(struct __sk_buff *skb) +SEC("tc") +int classifier_4(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 3); return 4; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -56,4 +56,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c index 910858fe078a..f60bcd7b8d4b 100644 --- a/tools/testing/selftests/bpf/progs/tailcall3.c +++ b/tools/testing/selftests/bpf/progs/tailcall3.c @@ -12,15 +12,15 @@ struct { int count = 0; -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { count++; bpf_tail_call_static(skb, &jmp_table, 0); return 1; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -28,4 +28,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c index bd4be135c39d..a56bbc2313ca 100644 --- a/tools/testing/selftests/bpf/progs/tailcall4.c +++ b/tools/testing/selftests/bpf/progs/tailcall4.c @@ -13,8 +13,8 @@ struct { int selector = 0; #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -22,7 +22,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call(skb, &jmp_table, selector); @@ -30,4 +30,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c index adf30a33064e..8d03496eb6ca 100644 --- a/tools/testing/selftests/bpf/progs/tailcall5.c +++ b/tools/testing/selftests/bpf/progs/tailcall5.c @@ -13,8 +13,8 @@ struct { int selector = 0; #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -22,7 +22,7 @@ TAIL_FUNC(0) TAIL_FUNC(1) TAIL_FUNC(2) -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { int idx = 0; @@ -37,4 +37,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall6.c b/tools/testing/selftests/bpf/progs/tailcall6.c new file mode 100644 index 000000000000..d77b8abd62f3 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall6.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +int count, which; + +SEC("tc") +int classifier_0(struct __sk_buff *skb) +{ + count++; + if (__builtin_constant_p(which)) + __bpf_unreachable(); + bpf_tail_call(skb, &jmp_table, which); + return 1; +} + +SEC("tc") +int entry(struct __sk_buff *skb) +{ + if (__builtin_constant_p(which)) + __bpf_unreachable(); + bpf_tail_call(skb, &jmp_table, which); + return 0; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c index 0103f3dd9f02..8c91428deb90 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c @@ -10,8 +10,8 @@ struct { } jmp_table SEC(".maps"); #define TAIL_FUNC(x) \ - SEC("classifier/" #x) \ - int bpf_func_##x(struct __sk_buff *skb) \ + SEC("tc") \ + int classifier_##x(struct __sk_buff *skb) \ { \ return x; \ } @@ -26,7 +26,7 @@ int subprog_tail(struct __sk_buff *skb) return skb->len * 2; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 1); @@ -35,4 +35,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c index 3cc4c12817b5..ce97d141daee 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c @@ -22,14 +22,14 @@ int subprog_tail(struct __sk_buff *skb) int count = 0; -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { count++; return subprog_tail(skb); } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { bpf_tail_call_static(skb, &jmp_table, 0); @@ -38,4 +38,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c index 0d5482bea6c9..7fab39a3bb12 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c @@ -33,23 +33,23 @@ int subprog_tail(struct __sk_buff *skb) return skb->len * 2; } -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { volatile char arr[128] = {}; return subprog_tail2(skb); } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { volatile char arr[128] = {}; return skb->len * 3; } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { volatile char arr[128] = {}; @@ -58,4 +58,3 @@ int entry(struct __sk_buff *skb) } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c index e89368a50b97..b67e8022d500 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c @@ -50,30 +50,29 @@ int subprog_tail(struct __sk_buff *skb) return skb->len; } -SEC("classifier/1") -int bpf_func_1(struct __sk_buff *skb) +SEC("tc") +int classifier_1(struct __sk_buff *skb) { return subprog_tail_2(skb); } -SEC("classifier/2") -int bpf_func_2(struct __sk_buff *skb) +SEC("tc") +int classifier_2(struct __sk_buff *skb) { count++; return subprog_tail_2(skb); } -SEC("classifier/0") -int bpf_func_0(struct __sk_buff *skb) +SEC("tc") +int classifier_0(struct __sk_buff *skb) { return subprog_tail_1(skb); } -SEC("classifier") +SEC("tc") int entry(struct __sk_buff *skb) { return subprog_tail(skb); } char __license[] SEC("license") = "GPL"; -int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c index c1e0c8c7c55f..c218cf8989a9 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c @@ -21,8 +21,8 @@ struct inner_map_sz2 { struct outer_arr { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 3); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); /* it's possible to use anonymous struct as inner map definition here */ __array(values, struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -61,8 +61,8 @@ struct inner_map_sz4 { struct outer_arr_dyn { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 3); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __array(values, struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(map_flags, BPF_F_INNER_MAP); @@ -81,7 +81,7 @@ struct outer_arr_dyn { struct outer_hash { __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); __uint(max_entries, 5); - __uint(key_size, sizeof(int)); + __type(key, int); /* Here everything works flawlessly due to reuse of struct inner_map * and compiler will complain at the attempt to use non-inner_map * references below. This is great experience. @@ -111,8 +111,8 @@ struct sockarr_sz2 { struct outer_sockarr_sz1 { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __array(values, struct sockarr_sz1); } outer_sockarr SEC(".maps") = { .values = { (void *)&sockarr_sz1 }, diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c index 9a6b85dd52d2..e2bea4da194b 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c +++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c @@ -145,7 +145,7 @@ release: return TC_ACT_OK; } -SEC("classifier/ingress") +SEC("tc") int cls_ingress(struct __sk_buff *skb) { struct ipv6hdr *ip6h; diff --git a/tools/testing/selftests/bpf/progs/test_cgroup_link.c b/tools/testing/selftests/bpf/progs/test_cgroup_link.c index 77e47b9e4446..4faba88e45a5 100644 --- a/tools/testing/selftests/bpf/progs/test_cgroup_link.c +++ b/tools/testing/selftests/bpf/progs/test_cgroup_link.c @@ -6,14 +6,14 @@ int calls = 0; int alt_calls = 0; -SEC("cgroup_skb/egress1") +SEC("cgroup_skb/egress") int egress(struct __sk_buff *skb) { __sync_fetch_and_add(&calls, 1); return 1; } -SEC("cgroup_skb/egress2") +SEC("cgroup_skb/egress") int egress_alt(struct __sk_buff *skb) { __sync_fetch_and_add(&alt_calls, 1); diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c index 71184af57749..2ec1de11a3ae 100644 --- a/tools/testing/selftests/bpf/progs/test_check_mtu.c +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -153,7 +153,7 @@ int xdp_input_len_exceed(struct xdp_md *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_use_helper(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -172,7 +172,7 @@ out: return retval; } -SEC("classifier") +SEC("tc") int tc_exceed_mtu(struct __sk_buff *ctx) { __u32 ifindex = GLOBAL_USER_IFINDEX; @@ -196,7 +196,7 @@ int tc_exceed_mtu(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_exceed_mtu_da(struct __sk_buff *ctx) { /* SKB Direct-Access variant */ @@ -223,7 +223,7 @@ int tc_exceed_mtu_da(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_minus_delta(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -245,7 +245,7 @@ int tc_minus_delta(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_input_len(struct __sk_buff *ctx) { int retval = BPF_OK; /* Expected retval on successful test */ @@ -265,7 +265,7 @@ int tc_input_len(struct __sk_buff *ctx) return retval; } -SEC("classifier") +SEC("tc") int tc_input_len_exceed(struct __sk_buff *ctx) { int retval = BPF_DROP; /* Fail */ diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index e2a5acc4785c..2833ad722cb7 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -928,7 +928,7 @@ static INLINING verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics) } } -SEC("classifier/cls_redirect") +SEC("tc") int cls_redirect(struct __sk_buff *skb) { metrics_t *metrics = get_global_metrics(); diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c index 1319be1c54ba..719e314ef3e4 100644 --- a/tools/testing/selftests/bpf/progs/test_global_data.c +++ b/tools/testing/selftests/bpf/progs/test_global_data.c @@ -68,7 +68,7 @@ static struct foo struct3 = { bpf_map_update_elem(&result_##map, &key, var, 0); \ } while (0) -SEC("classifier/static_data_load") +SEC("tc") int load_static_data(struct __sk_buff *skb) { static const __u64 bar = ~0; diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c index 880260f6d536..7b42dad187b8 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func1.c +++ b/tools/testing/selftests/bpf/progs/test_global_func1.c @@ -38,7 +38,7 @@ int f3(int val, struct __sk_buff *skb, int var) return skb->ifindex * val * var; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4); diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c index 86f0ecb304fc..01bf8275dfd6 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func3.c +++ b/tools/testing/selftests/bpf/progs/test_global_func3.c @@ -54,7 +54,7 @@ int f8(struct __sk_buff *skb) } #endif -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { #ifndef NO_FN8 diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c index 260c25b827ef..9248d03e0d06 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func5.c +++ b/tools/testing/selftests/bpf/progs/test_global_func5.c @@ -24,7 +24,7 @@ int f3(int val, struct __sk_buff *skb) return skb->ifindex * val; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { return f1(skb) + f2(2, skb) + f3(3, skb); diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c index 69e19c64e10b..af8c78bdfb25 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func6.c +++ b/tools/testing/selftests/bpf/progs/test_global_func6.c @@ -24,7 +24,7 @@ int f3(int val, struct __sk_buff *skb) return skb->ifindex * val; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { return f1(skb) + f2(2, skb) + f3(3, skb); diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c index 309b3f6136bd..6cb8e2f5254c 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func7.c +++ b/tools/testing/selftests/bpf/progs/test_global_func7.c @@ -10,7 +10,7 @@ void foo(struct __sk_buff *skb) skb->tc_index = 0; } -SEC("classifier/test") +SEC("tc") int test_cls(struct __sk_buff *skb) { foo(skb); diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index 1cfeb940cf9f..a6d91932dcd5 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c @@ -9,21 +9,19 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); __uint(map_flags, 0); - __uint(key_size, sizeof(__u32)); - /* must be sizeof(__u32) for map in map */ - __uint(value_size, sizeof(__u32)); + __type(key, __u32); + __type(value, __u32); } mim_array SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); __uint(max_entries, 1); __uint(map_flags, 0); - __uint(key_size, sizeof(int)); - /* must be sizeof(__u32) for map in map */ - __uint(value_size, sizeof(__u32)); + __type(key, int); + __type(value, __u32); } mim_hash SEC(".maps"); -SEC("xdp_mimtest") +SEC("xdp") int xdp_mimtest0(struct xdp_md *ctx) { int value = 123; diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c index 703c08e06442..9c7d75cf0bd6 100644 --- a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c @@ -13,7 +13,7 @@ struct inner { struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 0); /* This will make map creation to fail */ - __uint(key_size, sizeof(__u32)); + __type(key, __u32); __array(values, struct inner); } mim SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c index 6077a025092c..2c121c5d66a7 100644 --- a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c @@ -293,7 +293,7 @@ static int handle_passive_estab(struct bpf_sock_ops *skops) return check_active_hdr_in(skops); } -SEC("sockops/misc_estab") +SEC("sockops") int misc_estab(struct bpf_sock_ops *skops) { int true_val = 1; diff --git a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c index fb22de7c365d..1249a945699f 100644 --- a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c +++ b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c @@ -7,15 +7,15 @@ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } array_1 SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 1); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); __uint(map_flags, BPF_F_PRESERVE_ELEMS); } array_2 SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c index 8207a2dc2f9d..d37ce29fd393 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c +++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c @@ -8,8 +8,8 @@ struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); SEC("tp/raw_syscalls/sys_enter") diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c index 852051064507..3cfd88141ddc 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c @@ -97,7 +97,7 @@ int test_pkt_write_access_subprog(struct __sk_buff *skb, __u32 off) return 0; } -SEC("classifier/test_pkt_access") +SEC("tc") int test_pkt_access(struct __sk_buff *skb) { void *data_end = (void *)(long)skb->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c index 610c74ea9f64..d1839366f3e1 100644 --- a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c @@ -7,8 +7,6 @@ #include <linux/pkt_cls.h> #include <bpf/bpf_helpers.h> -int _version SEC("version") = 1; - #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ #define TEST_FIELD(TYPE, FIELD, MASK) \ { \ @@ -27,7 +25,7 @@ int _version SEC("version") = 1; } #endif -SEC("classifier/test_pkt_md_access") +SEC("tc") int test_pkt_md_access(struct __sk_buff *skb) { TEST_FIELD(__u8, len, 0xFF); diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c index 89b3532ccc75..8812a90da4eb 100644 --- a/tools/testing/selftests/bpf/progs/test_probe_user.c +++ b/tools/testing/selftests/bpf/progs/test_probe_user.c @@ -8,13 +8,37 @@ #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 + static struct sockaddr_in old; -SEC("kprobe/__sys_connect") +SEC("kprobe/" SYS_PREFIX "sys_connect") int BPF_KPROBE(handle_sys_connect) { - void *ptr = (void *)PT_REGS_PARM2(ctx); +#if SYSCALL_WRAPPER == 1 + struct pt_regs *real_regs; +#endif struct sockaddr_in new; + void *ptr; + +#if SYSCALL_WRAPPER == 0 + ptr = (void *)PT_REGS_PARM2(ctx); +#else + real_regs = (struct pt_regs *)PT_REGS_PARM1(ctx); + bpf_probe_read_kernel(&ptr, sizeof(ptr), &PT_REGS_PARM2(real_regs)); +#endif bpf_probe_read_user(&old, sizeof(old), ptr); __builtin_memset(&new, 0xab, sizeof(new)); diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index 26e77dcc7e91..0f9bc258225e 100644 --- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c @@ -24,8 +24,8 @@ int _version SEC("version") = 1; struct { __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); __uint(max_entries, 1); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(__u32)); + __type(key, __u32); + __type(value, __u32); } outer_map SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c index 1ecd987005d2..02f79356d5eb 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_assign.c +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -36,7 +36,6 @@ struct { .pinning = PIN_GLOBAL_NS, }; -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; /* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ @@ -159,7 +158,7 @@ assign: return ret; } -SEC("classifier/sk_assign_test") +SEC("tc") int bpf_sk_assign_test(struct __sk_buff *skb) { struct bpf_sock_tuple *tuple, ln = {0}; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c index ac6f7f205e25..48534d810391 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c @@ -72,32 +72,32 @@ static const __u16 DST_PORT = 7007; /* Host byte order */ static const __u32 DST_IP4 = IP4(127, 0, 0, 1); static const __u32 DST_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000001); -SEC("sk_lookup/lookup_pass") +SEC("sk_lookup") int lookup_pass(struct bpf_sk_lookup *ctx) { return SK_PASS; } -SEC("sk_lookup/lookup_drop") +SEC("sk_lookup") int lookup_drop(struct bpf_sk_lookup *ctx) { return SK_DROP; } -SEC("sk_reuseport/reuse_pass") +SEC("sk_reuseport") int reuseport_pass(struct sk_reuseport_md *ctx) { return SK_PASS; } -SEC("sk_reuseport/reuse_drop") +SEC("sk_reuseport") int reuseport_drop(struct sk_reuseport_md *ctx) { return SK_DROP; } /* Redirect packets destined for port DST_PORT to socket at redir_map[0]. */ -SEC("sk_lookup/redir_port") +SEC("sk_lookup") int redir_port(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -116,7 +116,7 @@ int redir_port(struct bpf_sk_lookup *ctx) } /* Redirect packets destined for DST_IP4 address to socket at redir_map[0]. */ -SEC("sk_lookup/redir_ip4") +SEC("sk_lookup") int redir_ip4(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -139,7 +139,7 @@ int redir_ip4(struct bpf_sk_lookup *ctx) } /* Redirect packets destined for DST_IP6 address to socket at redir_map[0]. */ -SEC("sk_lookup/redir_ip6") +SEC("sk_lookup") int redir_ip6(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -164,7 +164,7 @@ int redir_ip6(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_lookup/select_sock_a") +SEC("sk_lookup") int select_sock_a(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -179,7 +179,7 @@ int select_sock_a(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_lookup/select_sock_a_no_reuseport") +SEC("sk_lookup") int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -194,7 +194,7 @@ int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx) return err ? SK_DROP : SK_PASS; } -SEC("sk_reuseport/select_sock_b") +SEC("sk_reuseport") int select_sock_b(struct sk_reuseport_md *ctx) { __u32 key = KEY_SERVER_B; @@ -205,7 +205,7 @@ int select_sock_b(struct sk_reuseport_md *ctx) } /* Check that bpf_sk_assign() returns -EEXIST if socket already selected. */ -SEC("sk_lookup/sk_assign_eexist") +SEC("sk_lookup") int sk_assign_eexist(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -238,7 +238,7 @@ out: } /* Check that bpf_sk_assign(BPF_SK_LOOKUP_F_REPLACE) can override selection. */ -SEC("sk_lookup/sk_assign_replace_flag") +SEC("sk_lookup") int sk_assign_replace_flag(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -270,7 +270,7 @@ out: } /* Check that bpf_sk_assign(sk=NULL) is accepted. */ -SEC("sk_lookup/sk_assign_null") +SEC("sk_lookup") int sk_assign_null(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk = NULL; @@ -313,7 +313,7 @@ out: } /* Check that selected sk is accessible through context. */ -SEC("sk_lookup/access_ctx_sk") +SEC("sk_lookup") int access_ctx_sk(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk1 = NULL, *sk2 = NULL; @@ -379,7 +379,7 @@ out: * are not covered because they give bogus results, that is the * verifier ignores the offset. */ -SEC("sk_lookup/ctx_narrow_access") +SEC("sk_lookup") int ctx_narrow_access(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -553,7 +553,7 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx) } /* Check that sk_assign rejects SERVER_A socket with -ESOCKNOSUPPORT */ -SEC("sk_lookup/sk_assign_esocknosupport") +SEC("sk_lookup") int sk_assign_esocknosupport(struct bpf_sk_lookup *ctx) { struct bpf_sock *sk; @@ -578,28 +578,28 @@ out: return ret; } -SEC("sk_lookup/multi_prog_pass1") +SEC("sk_lookup") int multi_prog_pass1(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); return SK_PASS; } -SEC("sk_lookup/multi_prog_pass2") +SEC("sk_lookup") int multi_prog_pass2(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); return SK_PASS; } -SEC("sk_lookup/multi_prog_drop1") +SEC("sk_lookup") int multi_prog_drop1(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY); return SK_DROP; } -SEC("sk_lookup/multi_prog_drop2") +SEC("sk_lookup") int multi_prog_drop2(struct bpf_sk_lookup *ctx) { bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY); @@ -623,7 +623,7 @@ static __always_inline int select_server_a(struct bpf_sk_lookup *ctx) return SK_PASS; } -SEC("sk_lookup/multi_prog_redir1") +SEC("sk_lookup") int multi_prog_redir1(struct bpf_sk_lookup *ctx) { int ret; @@ -633,7 +633,7 @@ int multi_prog_redir1(struct bpf_sk_lookup *ctx) return SK_PASS; } -SEC("sk_lookup/multi_prog_redir2") +SEC("sk_lookup") int multi_prog_redir2(struct bpf_sk_lookup *ctx) { int ret; diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c index 8249075f088f..40f161480a2f 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c @@ -15,7 +15,6 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; /* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */ @@ -53,8 +52,8 @@ static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off, return result; } -SEC("classifier/sk_lookup_success") -int bpf_sk_lookup_test0(struct __sk_buff *skb) +SEC("tc") +int sk_lookup_success(struct __sk_buff *skb) { void *data_end = (void *)(long)skb->data_end; void *data = (void *)(long)skb->data; @@ -79,8 +78,8 @@ int bpf_sk_lookup_test0(struct __sk_buff *skb) return sk ? TC_ACT_OK : TC_ACT_UNSPEC; } -SEC("classifier/sk_lookup_success_simple") -int bpf_sk_lookup_test1(struct __sk_buff *skb) +SEC("tc") +int sk_lookup_success_simple(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -91,8 +90,8 @@ int bpf_sk_lookup_test1(struct __sk_buff *skb) return 0; } -SEC("classifier/err_use_after_free") -int bpf_sk_lookup_uaf(struct __sk_buff *skb) +SEC("tc") +int err_use_after_free(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -106,8 +105,8 @@ int bpf_sk_lookup_uaf(struct __sk_buff *skb) return family; } -SEC("classifier/err_modify_sk_pointer") -int bpf_sk_lookup_modptr(struct __sk_buff *skb) +SEC("tc") +int err_modify_sk_pointer(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -121,8 +120,8 @@ int bpf_sk_lookup_modptr(struct __sk_buff *skb) return 0; } -SEC("classifier/err_modify_sk_or_null_pointer") -int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb) +SEC("tc") +int err_modify_sk_or_null_pointer(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -135,8 +134,8 @@ int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb) return 0; } -SEC("classifier/err_no_release") -int bpf_sk_lookup_test2(struct __sk_buff *skb) +SEC("tc") +int err_no_release(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; @@ -144,8 +143,8 @@ int bpf_sk_lookup_test2(struct __sk_buff *skb) return 0; } -SEC("classifier/err_release_twice") -int bpf_sk_lookup_test3(struct __sk_buff *skb) +SEC("tc") +int err_release_twice(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -156,8 +155,8 @@ int bpf_sk_lookup_test3(struct __sk_buff *skb) return 0; } -SEC("classifier/err_release_unchecked") -int bpf_sk_lookup_test4(struct __sk_buff *skb) +SEC("tc") +int err_release_unchecked(struct __sk_buff *skb) { struct bpf_sock_tuple tuple = {}; struct bpf_sock *sk; @@ -173,8 +172,8 @@ void lookup_no_release(struct __sk_buff *skb) bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0); } -SEC("classifier/err_no_release_subcall") -int bpf_sk_lookup_test5(struct __sk_buff *skb) +SEC("tc") +int err_no_release_subcall(struct __sk_buff *skb) { lookup_no_release(skb); return 0; diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c index b02ea589ce7e..ba4dab09d19c 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c +++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c @@ -25,6 +25,12 @@ int process(struct __sk_buff *skb) return 1; if (skb->gso_size != 10) return 1; + if (skb->ingress_ifindex != 11) + return 1; + if (skb->ifindex != 1) + return 1; + if (skb->hwtstamp != 11) + return 1; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_skb_helpers.c b/tools/testing/selftests/bpf/progs/test_skb_helpers.c index bb3fbf1a29e3..507215791c5b 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_skb_helpers.c @@ -14,7 +14,7 @@ struct { char _license[] SEC("license") = "GPL"; -SEC("classifier/test_skb_helpers") +SEC("tc") int test_skb_helpers(struct __sk_buff *skb) { struct task_struct *task; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c index a1cc58b10c7c..00f1456aaeda 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -56,7 +56,7 @@ int prog_stream_verdict(struct __sk_buff *skb) return verdict; } -SEC("sk_skb/skb_verdict") +SEC("sk_skb") int prog_skb_verdict(struct __sk_buff *skb) { unsigned int *count; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c index 2d31f66e4f23..3c69aa971738 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c @@ -9,7 +9,7 @@ struct { __type(value, __u64); } sock_map SEC(".maps"); -SEC("sk_skb/skb_verdict") +SEC("sk_skb") int prog_skb_verdict(struct __sk_buff *skb) { return SK_DROP; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_update.c b/tools/testing/selftests/bpf/progs/test_sockmap_update.c index 9d0c9f28cab2..6d64ea536e3d 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_update.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_update.c @@ -24,7 +24,7 @@ struct { __type(value, __u64); } dst_sock_hash SEC(".maps"); -SEC("classifier/copy_sock_map") +SEC("tc") int copy_sock_map(void *ctx) { struct bpf_sock *sk; diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index 0cf0134631b4..7449fdb1763b 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -28,8 +28,8 @@ struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 128); __uint(map_flags, BPF_F_STACK_BUILD_ID); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index 00ed48672620..a8233e7f173b 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -27,8 +27,8 @@ typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; struct { __uint(type, BPF_MAP_TYPE_STACK_TRACE); __uint(max_entries, 16384); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(stack_trace_t)); + __type(key, __u32); + __type(value, stack_trace_t); } stackmap SEC(".maps"); struct { diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c index 18a3a7ed924a..d28ca8d1f3d0 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_bpf.c +++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c @@ -5,7 +5,7 @@ /* Dummy prog to test TC-BPF API */ -SEC("classifier") +SEC("tc") int cls(struct __sk_buff *skb) { return 0; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c index 0c93d326a663..3e32ea375ab4 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c @@ -70,7 +70,7 @@ static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb, return v6_equal(ip6h->daddr, addr); } -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); @@ -83,7 +83,7 @@ int tc_chk(struct __sk_buff *skb) return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK; } -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; @@ -108,7 +108,7 @@ int tc_dst(struct __sk_buff *skb) return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { __u8 zero[ETH_ALEN * 2]; diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c index f7ab69cf018e..ec4cce19362d 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c +++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c @@ -75,7 +75,7 @@ static __always_inline int fill_fib_params_v6(struct __sk_buff *skb, return 0; } -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { void *data_end = ctx_ptr(skb->data_end); @@ -143,13 +143,13 @@ static __always_inline int tc_redir(struct __sk_buff *skb) /* these are identical, but keep them separate for compatibility with the * section names expected by test_tc_redirect.sh */ -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { return tc_redir(skb); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { return tc_redir(skb); diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c index fe818cd5f010..365eacb5dc34 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_peer.c +++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c @@ -16,31 +16,31 @@ volatile const __u32 IFINDEX_DST; static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}; static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66}; -SEC("classifier/chk_egress") +SEC("tc") int tc_chk(struct __sk_buff *skb) { return TC_ACT_SHOT; } -SEC("classifier/dst_ingress") +SEC("tc") int tc_dst(struct __sk_buff *skb) { return bpf_redirect_peer(IFINDEX_SRC, 0); } -SEC("classifier/src_ingress") +SEC("tc") int tc_src(struct __sk_buff *skb) { return bpf_redirect_peer(IFINDEX_DST, 0); } -SEC("classifier/dst_ingress_l3") +SEC("tc") int tc_dst_l3(struct __sk_buff *skb) { return bpf_redirect(IFINDEX_SRC, 0); } -SEC("classifier/src_ingress_l3") +SEC("tc") int tc_src_l3(struct __sk_buff *skb) { __u16 proto = skb->protocol; 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 47cbe2eeae43..cd747cd93dbe 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 @@ -148,7 +148,7 @@ release: bpf_sk_release(sk); } -SEC("clsact/check_syncookie") +SEC("tc") int check_syncookie_clsact(struct __sk_buff *skb) { check_syncookie(skb, (void *)(long)skb->data, @@ -156,7 +156,7 @@ int check_syncookie_clsact(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("xdp/check_syncookie") +SEC("xdp") int check_syncookie_xdp(struct xdp_md *ctx) { check_syncookie(ctx, (void *)(long)ctx->data, diff --git a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c index 678bd0fad29e..5f4e87ee949a 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c @@ -594,7 +594,7 @@ static int handle_parse_hdr(struct bpf_sock_ops *skops) return CG_OK; } -SEC("sockops/estab") +SEC("sockops") int estab(struct bpf_sock_ops *skops) { int true_val = 1; diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index ac63410bb541..24e9344994ef 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c @@ -24,8 +24,8 @@ struct { struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); __uint(max_entries, 2); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(__u32)); + __type(key, int); + __type(value, __u32); } perf_event_map SEC(".maps"); int _version SEC("version") = 1; diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 31f9bce37491..e6aa2fc6ce6b 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c @@ -210,7 +210,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp) return XDP_TX; } -SEC("xdp_tx_iptunnel") +SEC("xdp") int _xdp_tx_iptunnel(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; 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 3d66599eee2e..199c61b7d062 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 @@ -2,7 +2,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -SEC("xdp_adjust_tail_grow") +SEC("xdp") int _xdp_adjust_tail_grow(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; 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 22065a9cfb25..b7448253d135 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 @@ -9,9 +9,7 @@ #include <linux/if_ether.h> #include <bpf/bpf_helpers.h> -int _version SEC("version") = 1; - -SEC("xdp_adjust_tail_shrink") +SEC("xdp") int _xdp_adjust_tail_shrink(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index a038e827f850..58cf4345f5cc 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -36,8 +36,8 @@ struct meta { struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __type(key, int); + __type(value, int); } perf_buf_map SEC(".maps"); __u64 test_result_fentry = 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c index b360ba2bd441..807bf895f42c 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c @@ -5,7 +5,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -SEC("xdp_dm_log") +SEC("xdp") int xdpdm_devlog(struct xdp_md *ctx) { char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c index eb93ea95d1d8..ee7d6ac0f615 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_link.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c @@ -5,7 +5,7 @@ char LICENSE[] SEC("license") = "GPL"; -SEC("xdp/handler") +SEC("xdp") int xdp_handler(struct xdp_md *xdp) { return 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c index fcabcda30ba3..27eb52dda92c 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c @@ -206,7 +206,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp) return XDP_TX; } -SEC("xdp_tx_iptunnel") +SEC("xdp") int _xdp_tx_iptunnel(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index 3a67921f62b5..596c4e71bf3a 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -797,7 +797,7 @@ out: return XDP_DROP; } -SEC("xdp-test-v4") +SEC("xdp") int balancer_ingress_v4(struct xdp_md *ctx) { void *data = (void *)(long)ctx->data; @@ -816,7 +816,7 @@ int balancer_ingress_v4(struct xdp_md *ctx) return XDP_DROP; } -SEC("xdp-test-v6") +SEC("xdp") int balancer_ingress_v6(struct xdp_md *ctx) { void *data = (void *)(long)ctx->data; 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 59ee4f182ff8..532025057711 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 @@ -12,13 +12,13 @@ struct { __uint(max_entries, 4); } cpu_map SEC(".maps"); -SEC("xdp_redir") +SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { return bpf_redirect_map(&cpu_map, 1, 0); } -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; 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 0ac086497722..1e6b9c38ea6d 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 @@ -9,7 +9,7 @@ struct { __uint(max_entries, 4); } dm_ports SEC(".maps"); -SEC("xdp_redir") +SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { return bpf_redirect_map(&dm_ports, 1, 0); @@ -18,7 +18,7 @@ int xdp_redir_prog(struct xdp_md *ctx) /* invalid program on DEVMAP entry; * SEC name means expected attach type not set */ -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; diff --git a/tools/testing/selftests/bpf/progs/trace_vprintk.c b/tools/testing/selftests/bpf/progs/trace_vprintk.c new file mode 100644 index 000000000000..d327241ba047 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_vprintk.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +int null_data_vprintk_ret = 0; +int trace_vprintk_ret = 0; +int trace_vprintk_ran = 0; + +SEC("fentry/__x64_sys_nanosleep") +int sys_enter(void *ctx) +{ + static const char one[] = "1"; + static const char three[] = "3"; + static const char five[] = "5"; + static const char seven[] = "7"; + static const char nine[] = "9"; + static const char f[] = "%pS\n"; + + /* runner doesn't search for \t, just ensure it compiles */ + bpf_printk("\t"); + + trace_vprintk_ret = __bpf_vprintk("%s,%d,%s,%d,%s,%d,%s,%d,%s,%d %d\n", + one, 2, three, 4, five, 6, seven, 8, nine, 10, ++trace_vprintk_ran); + + /* non-NULL fmt w/ NULL data should result in error */ + null_data_vprintk_ret = bpf_trace_vprintk(f, sizeof(f), NULL, 0); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c index ea25e8881992..d988b2e0cee8 100644 --- a/tools/testing/selftests/bpf/progs/xdp_dummy.c +++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c @@ -4,7 +4,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -SEC("xdp_dummy") +SEC("xdp") int xdp_dummy_prog(struct xdp_md *ctx) { return XDP_PASS; 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 880debcbcd65..8395782b6e0a 100644 --- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c @@ -34,7 +34,7 @@ struct { __uint(max_entries, 128); } mac_map SEC(".maps"); -SEC("xdp_redirect_map_multi") +SEC("xdp") int xdp_redirect_map_multi_prog(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; @@ -63,7 +63,7 @@ int xdp_redirect_map_multi_prog(struct xdp_md *ctx) } /* The following 2 progs are for 2nd devmap prog testing */ -SEC("xdp_redirect_map_ingress") +SEC("xdp") int xdp_redirect_map_all_prog(struct xdp_md *ctx) { return bpf_redirect_map(&map_egress, 0, diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c index 6b9ca40bd1f4..4ad73847b8a5 100644 --- a/tools/testing/selftests/bpf/progs/xdping_kern.c +++ b/tools/testing/selftests/bpf/progs/xdping_kern.c @@ -86,7 +86,7 @@ static __always_inline int icmp_check(struct xdp_md *ctx, int type) return XDP_TX; } -SEC("xdpclient") +SEC("xdp") int xdping_client(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; @@ -150,7 +150,7 @@ int xdping_client(struct xdp_md *ctx) return XDP_TX; } -SEC("xdpserver") +SEC("xdp") int xdping_server(struct xdp_md *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/progs/xdpwall.c b/tools/testing/selftests/bpf/progs/xdpwall.c new file mode 100644 index 000000000000..7a891a0c3a39 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdpwall.c @@ -0,0 +1,365 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <stdbool.h> +#include <stdint.h> +#include <linux/stddef.h> +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +enum pkt_parse_err { + NO_ERR, + BAD_IP6_HDR, + BAD_IP4GUE_HDR, + BAD_IP6GUE_HDR, +}; + +enum pkt_flag { + TUNNEL = 0x1, + TCP_SYN = 0x2, + QUIC_INITIAL_FLAG = 0x4, + TCP_ACK = 0x8, + TCP_RST = 0x10 +}; + +struct v4_lpm_key { + __u32 prefixlen; + __u32 src; +}; + +struct v4_lpm_val { + struct v4_lpm_key key; + __u8 val; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16); + __type(key, struct in6_addr); + __type(value, bool); +} v6_addr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 16); + __type(key, __u32); + __type(value, bool); +} v4_addr_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __uint(max_entries, 16); + __uint(key_size, sizeof(struct v4_lpm_key)); + __uint(value_size, sizeof(struct v4_lpm_val)); + __uint(map_flags, BPF_F_NO_PREALLOC); +} v4_lpm_val_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 16); + __type(key, int); + __type(value, __u8); +} tcp_port_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 16); + __type(key, int); + __type(value, __u16); +} udp_port_map SEC(".maps"); + +enum ip_type { V4 = 1, V6 = 2 }; + +struct fw_match_info { + __u8 v4_src_ip_match; + __u8 v6_src_ip_match; + __u8 v4_src_prefix_match; + __u8 v4_dst_prefix_match; + __u8 tcp_dp_match; + __u16 udp_sp_match; + __u16 udp_dp_match; + bool is_tcp; + bool is_tcp_syn; +}; + +struct pkt_info { + enum ip_type type; + union { + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + } ip; + int sport; + int dport; + __u16 trans_hdr_offset; + __u8 proto; + __u8 flags; +}; + +static __always_inline struct ethhdr *parse_ethhdr(void *data, void *data_end) +{ + struct ethhdr *eth = data; + + if (eth + 1 > data_end) + return NULL; + + return eth; +} + +static __always_inline __u8 filter_ipv6_addr(const struct in6_addr *ipv6addr) +{ + __u8 *leaf; + + leaf = bpf_map_lookup_elem(&v6_addr_map, ipv6addr); + + return leaf ? *leaf : 0; +} + +static __always_inline __u8 filter_ipv4_addr(const __u32 ipaddr) +{ + __u8 *leaf; + + leaf = bpf_map_lookup_elem(&v4_addr_map, &ipaddr); + + return leaf ? *leaf : 0; +} + +static __always_inline __u8 filter_ipv4_lpm(const __u32 ipaddr) +{ + struct v4_lpm_key v4_key = {}; + struct v4_lpm_val *lpm_val; + + v4_key.src = ipaddr; + v4_key.prefixlen = 32; + + lpm_val = bpf_map_lookup_elem(&v4_lpm_val_map, &v4_key); + + return lpm_val ? lpm_val->val : 0; +} + + +static __always_inline void +filter_src_dst_ip(struct pkt_info* info, struct fw_match_info* match_info) +{ + if (info->type == V6) { + match_info->v6_src_ip_match = + filter_ipv6_addr(&info->ip.ipv6->saddr); + } else if (info->type == V4) { + match_info->v4_src_ip_match = + filter_ipv4_addr(info->ip.ipv4->saddr); + match_info->v4_src_prefix_match = + filter_ipv4_lpm(info->ip.ipv4->saddr); + match_info->v4_dst_prefix_match = + filter_ipv4_lpm(info->ip.ipv4->daddr); + } +} + +static __always_inline void * +get_transport_hdr(__u16 offset, void *data, void *data_end) +{ + if (offset > 255 || data + offset > data_end) + return NULL; + + return data + offset; +} + +static __always_inline bool tcphdr_only_contains_flag(struct tcphdr *tcp, + __u32 FLAG) +{ + return (tcp_flag_word(tcp) & + (TCP_FLAG_ACK | TCP_FLAG_RST | TCP_FLAG_SYN | TCP_FLAG_FIN)) == FLAG; +} + +static __always_inline void set_tcp_flags(struct pkt_info *info, + struct tcphdr *tcp) { + if (tcphdr_only_contains_flag(tcp, TCP_FLAG_SYN)) + info->flags |= TCP_SYN; + else if (tcphdr_only_contains_flag(tcp, TCP_FLAG_ACK)) + info->flags |= TCP_ACK; + else if (tcphdr_only_contains_flag(tcp, TCP_FLAG_RST)) + info->flags |= TCP_RST; +} + +static __always_inline bool +parse_tcp(struct pkt_info *info, void *transport_hdr, void *data_end) +{ + struct tcphdr *tcp = transport_hdr; + + if (tcp + 1 > data_end) + return false; + + info->sport = bpf_ntohs(tcp->source); + info->dport = bpf_ntohs(tcp->dest); + set_tcp_flags(info, tcp); + + return true; +} + +static __always_inline bool +parse_udp(struct pkt_info *info, void *transport_hdr, void *data_end) +{ + struct udphdr *udp = transport_hdr; + + if (udp + 1 > data_end) + return false; + + info->sport = bpf_ntohs(udp->source); + info->dport = bpf_ntohs(udp->dest); + + return true; +} + +static __always_inline __u8 filter_tcp_port(int port) +{ + __u8 *leaf = bpf_map_lookup_elem(&tcp_port_map, &port); + + return leaf ? *leaf : 0; +} + +static __always_inline __u16 filter_udp_port(int port) +{ + __u16 *leaf = bpf_map_lookup_elem(&udp_port_map, &port); + + return leaf ? *leaf : 0; +} + +static __always_inline bool +filter_transport_hdr(void *transport_hdr, void *data_end, + struct pkt_info *info, struct fw_match_info *match_info) +{ + if (info->proto == IPPROTO_TCP) { + if (!parse_tcp(info, transport_hdr, data_end)) + return false; + + match_info->is_tcp = true; + match_info->is_tcp_syn = (info->flags & TCP_SYN) > 0; + + match_info->tcp_dp_match = filter_tcp_port(info->dport); + } else if (info->proto == IPPROTO_UDP) { + if (!parse_udp(info, transport_hdr, data_end)) + return false; + + match_info->udp_dp_match = filter_udp_port(info->dport); + match_info->udp_sp_match = filter_udp_port(info->sport); + } + + return true; +} + +static __always_inline __u8 +parse_gue_v6(struct pkt_info *info, struct ipv6hdr *ip6h, void *data_end) +{ + struct udphdr *udp = (struct udphdr *)(ip6h + 1); + void *encap_data = udp + 1; + + if (udp + 1 > data_end) + return BAD_IP6_HDR; + + if (udp->dest != bpf_htons(6666)) + return NO_ERR; + + info->flags |= TUNNEL; + + if (encap_data + 1 > data_end) + return BAD_IP6GUE_HDR; + + if (*(__u8 *)encap_data & 0x30) { + struct ipv6hdr *inner_ip6h = encap_data; + + if (inner_ip6h + 1 > data_end) + return BAD_IP6GUE_HDR; + + info->type = V6; + info->proto = inner_ip6h->nexthdr; + info->ip.ipv6 = inner_ip6h; + info->trans_hdr_offset += sizeof(struct ipv6hdr) + sizeof(struct udphdr); + } else { + struct iphdr *inner_ip4h = encap_data; + + if (inner_ip4h + 1 > data_end) + return BAD_IP6GUE_HDR; + + info->type = V4; + info->proto = inner_ip4h->protocol; + info->ip.ipv4 = inner_ip4h; + info->trans_hdr_offset += sizeof(struct iphdr) + sizeof(struct udphdr); + } + + return NO_ERR; +} + +static __always_inline __u8 parse_ipv6_gue(struct pkt_info *info, + void *data, void *data_end) +{ + struct ipv6hdr *ip6h = data + sizeof(struct ethhdr); + + if (ip6h + 1 > data_end) + return BAD_IP6_HDR; + + info->proto = ip6h->nexthdr; + info->ip.ipv6 = ip6h; + info->type = V6; + info->trans_hdr_offset = sizeof(struct ethhdr) + sizeof(struct ipv6hdr); + + if (info->proto == IPPROTO_UDP) + return parse_gue_v6(info, ip6h, data_end); + + return NO_ERR; +} + +SEC("xdp") +int edgewall(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)(ctx->data_end); + void *data = (void *)(long)(ctx->data); + struct fw_match_info match_info = {}; + struct pkt_info info = {}; + __u8 parse_err = NO_ERR; + void *transport_hdr; + struct ethhdr *eth; + bool filter_res; + __u32 proto; + + eth = parse_ethhdr(data, data_end); + if (!eth) + return XDP_DROP; + + proto = eth->h_proto; + if (proto != bpf_htons(ETH_P_IPV6)) + return XDP_DROP; + + if (parse_ipv6_gue(&info, data, data_end)) + return XDP_DROP; + + if (info.proto == IPPROTO_ICMPV6) + return XDP_PASS; + + if (info.proto != IPPROTO_TCP && info.proto != IPPROTO_UDP) + return XDP_DROP; + + filter_src_dst_ip(&info, &match_info); + + transport_hdr = get_transport_hdr(info.trans_hdr_offset, data, + data_end); + if (!transport_hdr) + return XDP_DROP; + + filter_res = filter_transport_hdr(transport_hdr, data_end, + &info, &match_info); + if (!filter_res) + return XDP_DROP; + + if (match_info.is_tcp && !match_info.is_tcp_syn) + return XDP_PASS; + + return XDP_DROP; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_bpftool.py b/tools/testing/selftests/bpf/test_bpftool.py index 4fed2dc25c0a..1c2408ee1f5d 100644 --- a/tools/testing/selftests/bpf/test_bpftool.py +++ b/tools/testing/selftests/bpf/test_bpftool.py @@ -57,6 +57,11 @@ def default_iface(f): return f(*args, iface, **kwargs) return wrapper +DMESG_EMITTING_HELPERS = [ + "bpf_probe_write_user", + "bpf_trace_printk", + "bpf_trace_vprintk", + ] class TestBpftool(unittest.TestCase): @classmethod @@ -67,10 +72,7 @@ class TestBpftool(unittest.TestCase): @default_iface def test_feature_dev_json(self, iface): - unexpected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + unexpected_helpers = DMESG_EMITTING_HELPERS expected_keys = [ "syscall_config", "program_types", @@ -94,10 +96,7 @@ class TestBpftool(unittest.TestCase): bpftool_json(["feature", "probe"]), bpftool_json(["feature"]), ] - unexpected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + unexpected_helpers = DMESG_EMITTING_HELPERS expected_keys = [ "syscall_config", "system_config", @@ -121,10 +120,7 @@ class TestBpftool(unittest.TestCase): bpftool_json(["feature", "probe", "kernel", "full"]), bpftool_json(["feature", "probe", "full"]), ] - expected_helpers = [ - "bpf_probe_write_user", - "bpf_trace_printk", - ] + expected_helpers = DMESG_EMITTING_HELPERS for tc in test_cases: # Check if expected helpers are included at least once in any @@ -157,7 +153,7 @@ class TestBpftool(unittest.TestCase): not_full_set.add(helper) self.assertCountEqual(full_set - not_full_set, - {"bpf_probe_write_user", "bpf_trace_printk"}) + set(DMESG_EMITTING_HELPERS)) self.assertCountEqual(not_full_set - full_set, set()) def test_feature_macros(self): diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h index e2394eea4b7f..0619e06d745e 100644 --- a/tools/testing/selftests/bpf/test_btf.h +++ b/tools/testing/selftests/bpf/test_btf.h @@ -69,4 +69,7 @@ #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) +#define BTF_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx) + #endif /* _TEST_BTF_H */ diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index cc1cd240445d..2ed01f615d20 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -743,6 +743,45 @@ int cd_flavor_subdir(const char *exec_name) return chdir(flavor); } +int trigger_module_test_read(int read_sz) +{ + int fd, err; + + fd = open("/sys/kernel/bpf_testmod", O_RDONLY); + err = -errno; + if (!ASSERT_GE(fd, 0, "testmod_file_open")) + return err; + + read(fd, NULL, read_sz); + close(fd); + + return 0; +} + +int trigger_module_test_write(int write_sz) +{ + int fd, err; + char *buf = malloc(write_sz); + + if (!buf) + return -ENOMEM; + + memset(buf, 'a', write_sz); + buf[write_sz-1] = '\0'; + + fd = open("/sys/kernel/bpf_testmod", O_WRONLY); + err = -errno; + if (!ASSERT_GE(fd, 0, "testmod_file_open")) { + free(buf); + return err; + } + + write(fd, buf, write_sz); + close(fd); + free(buf); + return 0; +} + #define MAX_BACKTRACE_SZ 128 void crash_handler(int signum) { diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index c8c2bf878f67..94bef0aa74cf 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -291,6 +291,8 @@ int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); int extract_build_id(char *build_id, size_t size); int kern_sync_rcu(void); +int trigger_module_test_read(int read_sz); +int trigger_module_test_write(int write_sz); #ifdef __x86_64__ #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep" diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh index 9b3617d770a5..6413c1472554 100755 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh @@ -76,8 +76,8 @@ DIR=$(dirname $0) TEST_IF=lo MAX_PING_TRIES=5 BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.o" -CLSACT_SECTION="clsact/check_syncookie" -XDP_SECTION="xdp/check_syncookie" +CLSACT_SECTION="tc" +XDP_SECTION="xdp" BPF_PROG_ID=0 PROG="${DIR}/test_tcp_check_syncookie_user" diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index 1ccbe804e8e1..ca1372924023 100755 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -168,14 +168,15 @@ add_vxlan_tunnel() ip netns exec at_ns0 \ ip link set dev $DEV_NS address 52:54:00:d9:01:00 up ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00 + ip netns exec at_ns0 \ + ip neigh add 10.1.1.200 lladdr 52:54:00:d9:02:00 dev $DEV_NS ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF # root namespace ip link add dev $DEV type $TYPE external gbp dstport 4789 ip link set dev $DEV address 52:54:00:d9:02:00 up ip addr add dev $DEV 10.1.1.200/24 - arp -s 10.1.1.100 52:54:00:d9:01:00 + ip neigh add 10.1.1.100 lladdr 52:54:00:d9:01:00 dev $DEV } add_ip6vxlan_tunnel() diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh index 637fcf4fe4e3..d10cefd6eb09 100755 --- a/tools/testing/selftests/bpf/test_xdp_meta.sh +++ b/tools/testing/selftests/bpf/test_xdp_meta.sh @@ -1,5 +1,8 @@ #!/bin/sh +# Kselftest framework requirement - SKIP code is 4. +readonly KSFT_SKIP=4 + cleanup() { if [ "$?" = "0" ]; then @@ -17,7 +20,7 @@ cleanup() ip link set dev lo xdp off 2>/dev/null > /dev/null if [ $? -ne 0 ];then echo "selftests: [SKIP] Could not run test without the ip xdp support" - exit 0 + exit $KSFT_SKIP fi set -e diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh index c033850886f4..57c8db9972a6 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -52,8 +52,8 @@ test_xdp_redirect() return 0 fi - ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null - ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /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 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh index 1538373157e3..351955c2bdfd 100755 --- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh +++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh @@ -88,7 +88,7 @@ setup_ns() # Add a neigh entry for IPv4 ping test ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 ip -n ns$i link set veth0 $mode obj \ - xdp_dummy.o sec xdp_dummy &> /dev/null || \ + xdp_dummy.o sec xdp &> /dev/null || \ { test_fail "Unable to load dummy xdp" && exit 1; } IFACES="$IFACES veth$i" veth_mac[$i]=$(ip link show veth$i | awk '/link\/ether/ {print $2}') diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh index 995278e684b6..a3a1eaee26ea 100755 --- a/tools/testing/selftests/bpf/test_xdp_veth.sh +++ b/tools/testing/selftests/bpf/test_xdp_veth.sh @@ -107,9 +107,9 @@ 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 $BPF_DIR/progs/redirect_map_2 -ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp_dummy +ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp -ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp_dummy +ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp trap cleanup EXIT diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh index bb8b0da91686..0cbc7604a2f8 100755 --- a/tools/testing/selftests/bpf/test_xdp_vlan.sh +++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh @@ -2,6 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 # Author: Jesper Dangaard Brouer <hawk@kernel.org> +# Kselftest framework requirement - SKIP code is 4. +readonly KSFT_SKIP=4 + # Allow wrapper scripts to name test if [ -z "$TESTNAME" ]; then TESTNAME=xdp_vlan @@ -94,7 +97,7 @@ while true; do -h | --help ) usage; echo "selftests: $TESTNAME [SKIP] usage help info requested" - exit 0 + exit $KSFT_SKIP ;; * ) shift @@ -117,7 +120,7 @@ fi ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null if [ $? -ne 0 ]; then echo "selftests: $TESTNAME [SKIP] need ip xdp support" - exit 0 + exit $KSFT_SKIP fi # Interactive mode likely require us to cleanup netns diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index e7a19b04d4ea..5100a169b72b 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <ctype.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -117,6 +118,42 @@ out: return err; } +/* find the address of the next symbol of the same type, this can be used + * to determine the end of a function. + */ +int kallsyms_find_next(const char *sym, unsigned long long *addr) +{ + char type, found_type, name[500]; + unsigned long long value; + bool found = false; + int err = 0; + FILE *f; + + f = fopen("/proc/kallsyms", "r"); + if (!f) + return -EINVAL; + + while (fscanf(f, "%llx %c %499s%*[^\n]\n", &value, &type, name) > 0) { + /* Different types of symbols in kernel modules are mixed + * in /proc/kallsyms. Only return the next matching type. + * Use tolower() for type so that 'T' matches 't'. + */ + if (found && found_type == tolower(type)) { + *addr = value; + goto out; + } + if (strcmp(name, sym) == 0) { + found = true; + found_type = tolower(type); + } + } + err = -ENOENT; + +out: + fclose(f); + return err; +} + void read_trace_pipe(void) { int trace_fd; diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index d907b445524d..bc8ed86105d9 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -16,6 +16,11 @@ long ksym_get_addr(const char *name); /* open kallsyms and find addresses on the fly, faster than load + search. */ int kallsyms_find(const char *sym, unsigned long long *addr); +/* find the address of the next symbol, this can be used to determine the + * end of a function + */ +int kallsyms_find_next(const char *sym, unsigned long long *addr); + void read_trace_pipe(void); ssize_t get_uprobe_offset(const void *addr, ssize_t base); diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c index 2022c0f2cd75..9e1a30b94197 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_skb.c +++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c @@ -1058,6 +1058,66 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { + "padding after gso_size is not accessible", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetofend(struct __sk_buff, gso_size)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .result_unpriv = REJECT, + .errstr = "invalid bpf_context access off=180 size=4", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "read hwtstamp from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "read hwtstamp from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "write hwtstamp from CGROUP_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .result_unpriv = REJECT, + .errstr = "invalid bpf_context access off=184 size=8", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "read hwtstamp from CLS", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ "check wire_len is not readable by sockets", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, diff --git a/tools/testing/selftests/bpf/verifier/jit.c b/tools/testing/selftests/bpf/verifier/jit.c index df215e004566..eedcb752bf70 100644 --- a/tools/testing/selftests/bpf/verifier/jit.c +++ b/tools/testing/selftests/bpf/verifier/jit.c @@ -62,6 +62,11 @@ BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 0xefefef), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), BPF_MOV32_REG(BPF_REG_2, BPF_REG_2), BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL), BPF_ALU32_REG(BPF_MUL, BPF_REG_0, BPF_REG_1), @@ -73,11 +78,22 @@ BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL), + BPF_ALU32_IMM(BPF_MUL, BPF_REG_3, 0xefefef), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL), + BPF_LD_IMM64(BPF_REG_2, 0x2ad4d4aaULL), + BPF_ALU32_IMM(BPF_MUL, BPF_REG_0, 0x2b), + BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), BPF_LD_IMM64(BPF_REG_0, 0x952a7bbcULL), BPF_LD_IMM64(BPF_REG_1, 0xfefefeULL), - BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL), - BPF_ALU32_REG(BPF_MUL, BPF_REG_2, BPF_REG_1), - BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_0, 2), + BPF_LD_IMM64(BPF_REG_5, 0xeeff0d413122ULL), + BPF_ALU32_REG(BPF_MUL, BPF_REG_5, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_5, BPF_REG_0, 2), BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), BPF_MOV64_IMM(BPF_REG_0, 2), diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 0b943897aaf6..c9991c3f3bd2 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -104,3 +104,164 @@ .result = ACCEPT, .retval = POINTER_VALUE, }, +{ + "Spill and refill a u32 const scalar. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + 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), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv20 */ + 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 */ + 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 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const, refill from another half of the uninit u32 from the stack", + .insns = { + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u32 *)(r10 -4) fp-8=????rrrr*/ + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid read from stack off -4+0 size 4", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const scalar. Refill as u16. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u16 *)(r10 -8) */ + 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 */ + 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 */ + 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 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill a u32 const scalar. Refill as u16 from fp-6. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* r4 = *(u16 *)(r10 -6) */ + 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 */ + 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 */ + 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 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill and refill a u32 const scalar at non 8byte aligned stack addr. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r4 = 20 */ + BPF_MOV32_IMM(BPF_REG_4, 20), + /* *(u32 *)(r10 -8) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8), + /* *(u32 *)(r10 -4) = r4 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -4), + /* r4 = *(u32 *)(r10 -4), */ + 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 */ + 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 */ + 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 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "Spill and refill a umax=40 bounded scalar. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, + offsetof(struct __sk_buff, tstamp)), + 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 */ + 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 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_4), + /* r0 = r2 R2=pkt,umax=40 R4=inv,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), + /* if (r2 > r3) R0=pkt,umax=40 R2=pkt,off=20,umax=40 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_3, 1), + /* r0 = *(u32 *)r0 R0=pkt,r=20,umax=40 R2=pkt,off=20,r=20,umax=40 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c index 842d9155d36c..79a3453dab25 100644 --- a/tools/testing/selftests/bpf/xdping.c +++ b/tools/testing/selftests/bpf/xdping.c @@ -178,9 +178,8 @@ int main(int argc, char **argv) return 1; } - main_prog = bpf_object__find_program_by_title(obj, - server ? "xdpserver" : - "xdpclient"); + main_prog = bpf_object__find_program_by_name(obj, + server ? "xdping_server" : "xdping_client"); if (main_prog) prog_fd = bpf_program__fd(main_prog); if (!main_prog || prog_fd < 0) { diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index f53ce2683f8d..6c7cf8aadc79 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -19,7 +19,7 @@ * Virtual Ethernet interfaces. * * For each mode, the following tests are run: - * a. nopoll - soft-irq processing + * a. nopoll - soft-irq processing in run-to-completion mode * b. poll - using poll() syscall * c. Socket Teardown * Create a Tx and a Rx socket, Tx from one socket, Rx on another. Destroy @@ -45,6 +45,10 @@ * Configure sockets at indexes 0 and 1, run a traffic on queue ids 0, * then remove xsk sockets from queue 0 on both veth interfaces and * finally run a traffic on queues ids 1 + * g. unaligned mode + * h. tests for invalid and corner case Tx descriptors so that the correct ones + * are discarded and let through, respectively. + * i. 2K frame size tests * * Total tests: 12 * @@ -112,13 +116,10 @@ static void __exit_with_error(int error, const char *file, const char *func, int #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__) -#define print_ksft_result(void)\ - (ksft_test_result_pass("PASS: %s %s %s%s%s%s\n", configured_mode ? "DRV" : "SKB",\ - test_type == TEST_TYPE_POLL ? "POLL" : "NOPOLL",\ - test_type == TEST_TYPE_TEARDOWN ? "Socket Teardown" : "",\ - test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : "",\ - test_type == TEST_TYPE_STATS ? "Stats" : "",\ - test_type == TEST_TYPE_BPF_RES ? "BPF RES" : "")) +#define mode_string(test) (test)->ifobj_tx->xdp_flags & XDP_FLAGS_SKB_MODE ? "SKB" : "DRV" + +#define print_ksft_result(test) \ + (ksft_test_result_pass("PASS: %s %s\n", mode_string(test), (test)->name)) static void memset32_htonl(void *dest, u32 val, u32 size) { @@ -235,80 +236,46 @@ static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr) udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr); } -static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size, int idx) +static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size) { struct xsk_umem_config cfg = { .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, - .frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE, - .frame_headroom = frame_headroom, + .frame_size = umem->frame_size, + .frame_headroom = umem->frame_headroom, .flags = XSK_UMEM__DEFAULT_FLAGS }; - struct xsk_umem_info *umem; int ret; - umem = calloc(1, sizeof(struct xsk_umem_info)); - if (!umem) - exit_with_error(errno); + if (umem->unaligned_mode) + cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG; ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq, &cfg); if (ret) - exit_with_error(-ret); + return ret; umem->buffer = buffer; - - data->umem_arr[idx] = umem; -} - -static void xsk_populate_fill_ring(struct xsk_umem_info *umem) -{ - int ret, i; - u32 idx = 0; - - ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx); - if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) - exit_with_error(-ret); - for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) - *xsk_ring_prod__fill_addr(&umem->fq, idx++) = i * XSK_UMEM__DEFAULT_FRAME_SIZE; - xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS); + return 0; } -static int xsk_configure_socket(struct ifobject *ifobject, int idx) +static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, + struct ifobject *ifobject, u32 qid) { struct xsk_socket_config cfg; - struct xsk_socket_info *xsk; struct xsk_ring_cons *rxr; struct xsk_ring_prod *txr; - int ret; - - xsk = calloc(1, sizeof(struct xsk_socket_info)); - if (!xsk) - exit_with_error(errno); - xsk->umem = ifobject->umem; - cfg.rx_size = rxqsize; + xsk->umem = umem; + cfg.rx_size = xsk->rxqsize; cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; cfg.libbpf_flags = 0; - cfg.xdp_flags = xdp_flags; - cfg.bind_flags = xdp_bind_flags; - - if (test_type != TEST_TYPE_BIDI) { - rxr = (ifobject->fv.vector == rx) ? &xsk->rx : NULL; - txr = (ifobject->fv.vector == tx) ? &xsk->tx : NULL; - } else { - rxr = &xsk->rx; - txr = &xsk->tx; - } - - ret = xsk_socket__create(&xsk->xsk, ifobject->ifname, idx, - ifobject->umem->umem, rxr, txr, &cfg); - if (ret) - return 1; + cfg.xdp_flags = ifobject->xdp_flags; + cfg.bind_flags = ifobject->bind_flags; - ifobject->xsk_arr[idx] = xsk; - - return 0; + 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); } static struct option long_options[] = { @@ -354,45 +321,44 @@ static int switch_namespace(const char *nsname) return nsfd; } -static int validate_interfaces(void) +static bool validate_interface(struct ifobject *ifobj) { - bool ret = true; - - for (int i = 0; i < MAX_INTERFACES; i++) { - if (!strcmp(ifdict[i]->ifname, "")) { - ret = false; - ksft_test_result_fail("ERROR: interfaces: -i <int>,<ns> -i <int>,<ns>."); - } - } - return ret; + if (!strcmp(ifobj->ifname, "")) + return false; + return true; } -static void parse_command_line(int argc, char **argv) +static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx, int argc, + char **argv) { - int option_index, interface_index = 0, c; + struct ifobject *ifobj; + u32 interface_nb = 0; + int option_index, c; opterr = 0; for (;;) { - c = getopt_long(argc, argv, "i:Dv", long_options, &option_index); + char *sptr, *token; + c = getopt_long(argc, argv, "i:Dv", long_options, &option_index); if (c == -1) break; switch (c) { case 'i': - if (interface_index == MAX_INTERFACES) + if (interface_nb == 0) + ifobj = ifobj_tx; + else if (interface_nb == 1) + ifobj = ifobj_rx; + else break; - char *sptr, *token; sptr = strndupa(optarg, strlen(optarg)); - memcpy(ifdict[interface_index]->ifname, - strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS); + memcpy(ifobj->ifname, strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS); token = strsep(&sptr, ","); if (token) - memcpy(ifdict[interface_index]->nsname, token, - MAX_INTERFACES_NAMESPACE_CHARS); - interface_index++; + memcpy(ifobj->nsname, token, MAX_INTERFACES_NAMESPACE_CHARS); + interface_nb++; break; case 'D': opt_pkt_dump = true; @@ -405,11 +371,85 @@ static void parse_command_line(int argc, char **argv) ksft_exit_xfail(); } } +} - if (!validate_interfaces()) { - usage(basename(argv[0])); - ksft_exit_xfail(); +static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx) +{ + u32 i, j; + + 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; + ifobj->pkt_stream = test->pkt_stream_default; + + if (i == 0) { + ifobj->rx_on = false; + ifobj->tx_on = true; + } else { + ifobj->rx_on = true; + ifobj->tx_on = false; + } + + 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; + } + } + + test->ifobj_tx = ifobj_tx; + test->ifobj_rx = ifobj_rx; + test->current_step = 0; + test->total_steps = 1; + test->nb_sockets = 1; +} + +static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx, enum test_mode mode) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = test->pkt_stream_default; + memset(test, 0, sizeof(*test)); + test->pkt_stream_default = pkt_stream; + + for (i = 0; i < MAX_INTERFACES; i++) { + struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; + + ifobj->xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; + if (mode == TEST_MODE_SKB) + ifobj->xdp_flags |= XDP_FLAGS_SKB_MODE; + else + ifobj->xdp_flags |= XDP_FLAGS_DRV_MODE; + + ifobj->bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY; } + + __test_spec_init(test, ifobj_tx, ifobj_rx); +} + +static void test_spec_reset(struct test_spec *test) +{ + __test_spec_init(test, test->ifobj_tx, test->ifobj_rx); +} + +static void test_spec_set_name(struct test_spec *test, const char *name) +{ + strncpy(test->name, name, MAX_TEST_NAME_SIZE); +} + +static void pkt_stream_reset(struct pkt_stream *pkt_stream) +{ + if (pkt_stream) + pkt_stream->rx_pkt_nb = 0; } static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) @@ -420,29 +460,104 @@ static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) return &pkt_stream->pkts[pkt_nb]; } -static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len) +static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream) +{ + while (pkt_stream->rx_pkt_nb < pkt_stream->nb_pkts) { + if (pkt_stream->pkts[pkt_stream->rx_pkt_nb].valid) + return &pkt_stream->pkts[pkt_stream->rx_pkt_nb++]; + pkt_stream->rx_pkt_nb++; + } + return NULL; +} + +static void pkt_stream_delete(struct pkt_stream *pkt_stream) +{ + free(pkt_stream->pkts); + free(pkt_stream); +} + +static void pkt_stream_restore_default(struct test_spec *test) +{ + if (test->ifobj_tx->pkt_stream != test->pkt_stream_default) { + pkt_stream_delete(test->ifobj_tx->pkt_stream); + test->ifobj_tx->pkt_stream = test->pkt_stream_default; + } + test->ifobj_rx->pkt_stream = test->pkt_stream_default; +} + +static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) { struct pkt_stream *pkt_stream; - u32 i; - pkt_stream = malloc(sizeof(*pkt_stream)); + pkt_stream = calloc(1, sizeof(*pkt_stream)); if (!pkt_stream) - exit_with_error(ENOMEM); + return NULL; pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts)); - if (!pkt_stream->pkts) + if (!pkt_stream->pkts) { + free(pkt_stream); + return NULL; + } + + pkt_stream->nb_pkts = nb_pkts; + return pkt_stream; +} + +static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = __pkt_stream_alloc(nb_pkts); + if (!pkt_stream) exit_with_error(ENOMEM); pkt_stream->nb_pkts = nb_pkts; for (i = 0; i < nb_pkts; i++) { - pkt_stream->pkts[i].addr = (i % num_frames) * XSK_UMEM__DEFAULT_FRAME_SIZE; + pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size; pkt_stream->pkts[i].len = pkt_len; pkt_stream->pkts[i].payload = i; + + if (pkt_len > umem->frame_size) + pkt_stream->pkts[i].valid = false; + else + pkt_stream->pkts[i].valid = true; } return pkt_stream; } +static struct pkt_stream *pkt_stream_clone(struct xsk_umem_info *umem, + struct pkt_stream *pkt_stream) +{ + return pkt_stream_generate(umem, pkt_stream->nb_pkts, pkt_stream->pkts[0].len); +} + +static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) +{ + struct pkt_stream *pkt_stream; + + pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, nb_pkts, pkt_len); + test->ifobj_tx->pkt_stream = pkt_stream; + test->ifobj_rx->pkt_stream = pkt_stream; +} + +static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset) +{ + struct xsk_umem_info *umem = test->ifobj_tx->umem; + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = pkt_stream_clone(umem, test->pkt_stream_default); + for (i = 1; i < test->pkt_stream_default->nb_pkts; i += 2) { + pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + offset; + pkt_stream->pkts[i].len = pkt_len; + } + + test->ifobj_tx->pkt_stream = pkt_stream; + test->ifobj_rx->pkt_stream = pkt_stream; +} + static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) { struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb); @@ -453,6 +568,8 @@ static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) if (!pkt) return NULL; + if (!pkt->valid || pkt->len < PKT_SIZE) + return pkt; data = xsk_umem__get_data(ifobject->umem->buffer, pkt->addr); udp_hdr = (struct udphdr *)(data + sizeof(struct ethhdr) + sizeof(struct iphdr)); @@ -467,6 +584,26 @@ static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) return pkt; } +static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = __pkt_stream_alloc(nb_pkts); + if (!pkt_stream) + exit_with_error(ENOMEM); + + test->ifobj_tx->pkt_stream = pkt_stream; + test->ifobj_rx->pkt_stream = pkt_stream; + + for (i = 0; i < nb_pkts; i++) { + pkt_stream->pkts[i].addr = pkts[i].addr; + pkt_stream->pkts[i].len = pkts[i].len; + pkt_stream->pkts[i].payload = i; + pkt_stream->pkts[i].valid = pkts[i].valid; + } +} + static void pkt_dump(void *pkt, u32 len) { char s[INET_ADDRSTRLEN]; @@ -504,9 +641,28 @@ static void pkt_dump(void *pkt, u32 len) fprintf(stdout, "---------------------------------------\n"); } -static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *desc) +static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, u64 addr, + u64 pkt_stream_addr) { - void *data = xsk_umem__get_data(buffer, desc->addr); + u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; + u32 offset = addr % umem->frame_size, expected_offset = 0; + + if (!pkt_stream->use_addr_for_fill) + pkt_stream_addr = 0; + + expected_offset += (pkt_stream_addr + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; + + if (offset == expected_offset) + return true; + + ksft_test_result_fail("ERROR: [%s] expected [%u], got [%u]\n", __func__, expected_offset, + offset); + return false; +} + +static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) +{ + void *data = xsk_umem__get_data(buffer, addr); struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr)); if (!pkt) { @@ -514,19 +670,24 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *d return false; } + if (len < PKT_SIZE) { + /*Do not try to verify packets that are smaller than minimum size. */ + return true; + } + + if (pkt->len != len) { + ksft_test_result_fail + ("ERROR: [%s] expected length [%d], got length [%d]\n", + __func__, pkt->len, len); + return false; + } + if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) { u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); - if (opt_pkt_dump && test_type != TEST_TYPE_STATS) + if (opt_pkt_dump) pkt_dump(data, PKT_SIZE); - if (pkt->len != desc->len) { - ksft_test_result_fail - ("ERROR: [%s] expected length [%d], got length [%d]\n", - __func__, pkt->len, desc->len); - return false; - } - if (pkt->payload != seqnum) { ksft_test_result_fail ("ERROR: [%s] expected seqnum [%d], got seqnum [%d]\n", @@ -558,14 +719,20 @@ static void complete_pkts(struct xsk_socket_info *xsk, int batch_size) unsigned int rcvd; u32 idx; - if (!xsk->outstanding_tx) - return; - if (xsk_ring_prod__needs_wakeup(&xsk->tx)) kick_tx(xsk); rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx); if (rcvd) { + if (rcvd > xsk->outstanding_tx) { + u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1); + + ksft_test_result_fail("ERROR: [%s] Too many packets completed\n", + __func__); + ksft_print_msg("Last completion address: %llx\n", addr); + return; + } + xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; } @@ -574,15 +741,16 @@ static void complete_pkts(struct xsk_socket_info *xsk, int batch_size) static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *xsk, struct pollfd *fds) { - u32 idx_rx = 0, idx_fq = 0, rcvd, i, pkt_count = 0; - struct pkt *pkt; + struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream); + struct xsk_umem_info *umem = xsk->umem; + u32 idx_rx = 0, idx_fq = 0, rcvd, i; + u32 total = 0; int ret; - pkt = pkt_stream_get_pkt(pkt_stream, pkt_count++); while (pkt) { rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { ret = poll(fds, 1, POLL_TMOUT); if (ret < 0) exit_with_error(-ret); @@ -590,40 +758,58 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * continue; } - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { ret = poll(fds, 1, POLL_TMOUT); if (ret < 0) exit_with_error(-ret); } - ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); } for (i = 0; i < rcvd; i++) { const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++); u64 addr = desc->addr, orig; + if (!pkt) { + ksft_test_result_fail("ERROR: [%s] Received too many packets.\n", + __func__); + ksft_print_msg("Last packet has addr: %llx len: %u\n", + addr, desc->len); + return; + } + orig = xsk_umem__extract_addr(addr); addr = xsk_umem__add_offset_to_addr(addr); - if (!is_pkt_valid(pkt, xsk->umem->buffer, desc)) + + if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len)) + return; + if (!is_offset_correct(umem, pkt_stream, addr, pkt->addr)) return; - *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig; - pkt = pkt_stream_get_pkt(pkt_stream, pkt_count++); + *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig; + pkt = pkt_stream_get_next_rx_pkt(pkt_stream); } - xsk_ring_prod__submit(&xsk->umem->fq, rcvd); + xsk_ring_prod__submit(&umem->fq, rcvd); xsk_ring_cons__release(&xsk->rx, rcvd); + + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight -= rcvd; + total += rcvd; + if (pkts_in_flight < umem->num_frames) + pthread_cond_signal(&pacing_cond); + pthread_mutex_unlock(&pacing_mutex); } } static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb) { struct xsk_socket_info *xsk = ifobject->xsk; - u32 i, idx; + u32 i, idx, valid_pkts = 0; while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) complete_pkts(xsk, BATCH_SIZE); @@ -638,15 +824,23 @@ static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb) tx_desc->addr = pkt->addr; tx_desc->len = pkt->len; pkt_nb++; + if (pkt->valid) + valid_pkts++; } - xsk_ring_prod__submit(&xsk->tx, i); - if (stat_test_type != STAT_TEST_TX_INVALID) - xsk->outstanding_tx += i; - else if (xsk_ring_prod__needs_wakeup(&xsk->tx)) + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight += valid_pkts; + if (ifobject->pacing_on && pkts_in_flight >= ifobject->umem->num_frames - BATCH_SIZE) { kick_tx(xsk); + pthread_cond_wait(&pacing_cond, &pacing_mutex); + } + pthread_mutex_unlock(&pacing_mutex); + + xsk_ring_prod__submit(&xsk->tx, i); + xsk->outstanding_tx += valid_pkts; complete_pkts(xsk, i); + usleep(10); return i; } @@ -658,29 +852,25 @@ static void wait_for_tx_completion(struct xsk_socket_info *xsk) static void send_pkts(struct ifobject *ifobject) { - struct pollfd fds[MAX_SOCKS] = { }; + struct pollfd fds = { }; u32 pkt_cnt = 0; - fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk); - fds[0].events = POLLOUT; + fds.fd = xsk_socket__fd(ifobject->xsk->xsk); + fds.events = POLLOUT; while (pkt_cnt < ifobject->pkt_stream->nb_pkts) { - u32 sent; - - if (test_type == TEST_TYPE_POLL) { + if (ifobject->use_poll) { int ret; - ret = poll(fds, 1, POLL_TMOUT); + ret = poll(&fds, 1, POLL_TMOUT); if (ret <= 0) continue; - if (!(fds[0].revents & POLLOUT)) + if (!(fds.revents & POLLOUT)) continue; } - sent = __send_pkts(ifobject, pkt_cnt); - pkt_cnt += sent; - usleep(10); + pkt_cnt += __send_pkts(ifobject, pkt_cnt); } wait_for_tx_completion(ifobject->xsk); @@ -698,7 +888,7 @@ static bool rx_stats_are_valid(struct ifobject *ifobject) optlen = sizeof(stats); err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); if (err) { - ksft_test_result_fail("ERROR: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", + ksft_test_result_fail("ERROR Rx: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", __func__, -err, strerror(-err)); return true; } @@ -739,7 +929,7 @@ static void tx_stats_validate(struct ifobject *ifobject) optlen = sizeof(stats); err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); if (err) { - ksft_test_result_fail("ERROR: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", + ksft_test_result_fail("ERROR Tx: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", __func__, -err, strerror(-err)); return; } @@ -751,71 +941,62 @@ static void tx_stats_validate(struct ifobject *ifobject) __func__, stats.tx_invalid_descs, ifobject->pkt_stream->nb_pkts); } -static void thread_common_ops(struct ifobject *ifobject, void *bufs) +static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) { - u64 umem_sz = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE; int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; - size_t mmap_sz = umem_sz; - int ctr = 0; - int ret; + u32 i; ifobject->ns_fd = switch_namespace(ifobject->nsname); - if (test_type == TEST_TYPE_BPF_RES) - mmap_sz *= 2; + if (ifobject->umem->unaligned_mode) + mmap_flags |= MAP_HUGETLB; - bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); - if (bufs == MAP_FAILED) - exit_with_error(errno); + 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; - while (ctr++ < SOCK_RECONF_CTR) { - xsk_configure_umem(ifobject, bufs, umem_sz, 0); - ifobject->umem = ifobject->umem_arr[0]; - ret = xsk_configure_socket(ifobject, 0); - if (!ret) - break; + bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); + if (bufs == MAP_FAILED) + exit_with_error(errno); - /* Retry Create Socket if it fails as xsk_socket__create() is asynchronous */ - usleep(USLEEP_MAX); - if (ctr >= SOCK_RECONF_CTR) + ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz); + if (ret) exit_with_error(-ret); - } - ifobject->umem = ifobject->umem_arr[0]; - ifobject->xsk = ifobject->xsk_arr[0]; + while (ctr++ < SOCK_RECONF_CTR) { + ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i], + ifobject, i); + if (!ret) + break; - if (test_type == TEST_TYPE_BPF_RES) { - xsk_configure_umem(ifobject, (u8 *)bufs + umem_sz, umem_sz, 1); - ifobject->umem = ifobject->umem_arr[1]; - ret = xsk_configure_socket(ifobject, 1); + /* Retry if it fails as xsk_socket__create() is asynchronous */ + if (ctr >= SOCK_RECONF_CTR) + exit_with_error(-ret); + usleep(USLEEP_MAX); + } } - ifobject->umem = ifobject->umem_arr[0]; - ifobject->xsk = ifobject->xsk_arr[0]; - print_verbose("Interface [%s] vector [%s]\n", - ifobject->ifname, ifobject->fv.vector == tx ? "Tx" : "Rx"); -} - -static bool testapp_is_test_two_stepped(void) -{ - return (test_type != TEST_TYPE_BIDI && test_type != TEST_TYPE_BPF_RES) || second_step; + ifobject->umem = &ifobject->umem_arr[0]; + ifobject->xsk = &ifobject->xsk_arr[0]; } static void testapp_cleanup_xsk_res(struct ifobject *ifobj) { - if (testapp_is_test_two_stepped()) { - xsk_socket__delete(ifobj->xsk->xsk); - (void)xsk_umem__delete(ifobj->umem->umem); - } + print_verbose("Destroying socket\n"); + xsk_socket__delete(ifobj->xsk->xsk); + munmap(ifobj->umem->buffer, ifobj->umem->num_frames * ifobj->umem->frame_size); + xsk_umem__delete(ifobj->umem->umem); } static void *worker_testapp_validate_tx(void *arg) { - struct ifobject *ifobject = (struct ifobject *)arg; - void *bufs = NULL; + struct test_spec *test = (struct test_spec *)arg; + struct ifobject *ifobject = test->ifobj_tx; - if (!second_step) - thread_common_ops(ifobject, bufs); + if (test->current_step == 1) + thread_common_ops(test, ifobject); print_verbose("Sending %d packets on interface %s\n", ifobject->pkt_stream->nb_pkts, ifobject->ifname); @@ -824,24 +1005,55 @@ static void *worker_testapp_validate_tx(void *arg) if (stat_test_type == STAT_TEST_TX_INVALID) tx_stats_validate(ifobject); - testapp_cleanup_xsk_res(ifobject); + if (test->total_steps == test->current_step) + testapp_cleanup_xsk_res(ifobject); pthread_exit(NULL); } +static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream) +{ + u32 idx = 0, i, buffers_to_fill; + int ret; + + if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) + buffers_to_fill = umem->num_frames; + else + buffers_to_fill = XSK_RING_PROD__DEFAULT_NUM_DESCS; + + ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); + if (ret != buffers_to_fill) + exit_with_error(ENOSPC); + for (i = 0; i < buffers_to_fill; i++) { + u64 addr; + + if (pkt_stream->use_addr_for_fill) { + struct pkt *pkt = pkt_stream_get_pkt(pkt_stream, i); + + if (!pkt) + break; + addr = pkt->addr; + } else { + addr = i * umem->frame_size; + } + + *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; + } + xsk_ring_prod__submit(&umem->fq, buffers_to_fill); +} + static void *worker_testapp_validate_rx(void *arg) { - struct ifobject *ifobject = (struct ifobject *)arg; - struct pollfd fds[MAX_SOCKS] = { }; - void *bufs = NULL; + struct test_spec *test = (struct test_spec *)arg; + struct ifobject *ifobject = test->ifobj_rx; + struct pollfd fds = { }; - if (!second_step) - thread_common_ops(ifobject, bufs); + if (test->current_step == 1) + thread_common_ops(test, ifobject); - if (stat_test_type != STAT_TEST_RX_FILL_EMPTY) - xsk_populate_fill_ring(ifobject->umem); + xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream); - fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk); - fds[0].events = POLLIN; + fds.fd = xsk_socket__fd(ifobject->xsk->xsk); + fds.events = POLLIN; pthread_barrier_wait(&barr); @@ -849,151 +1061,239 @@ static void *worker_testapp_validate_rx(void *arg) while (!rx_stats_are_valid(ifobject)) continue; else - receive_pkts(ifobject->pkt_stream, ifobject->xsk, fds); + receive_pkts(ifobject->pkt_stream, ifobject->xsk, &fds); - if (test_type == TEST_TYPE_TEARDOWN) - print_verbose("Destroying socket\n"); - - testapp_cleanup_xsk_res(ifobject); + if (test->total_steps == test->current_step) + testapp_cleanup_xsk_res(ifobject); pthread_exit(NULL); } -static void testapp_validate(void) +static void testapp_validate_traffic(struct test_spec *test) { - bool bidi = test_type == TEST_TYPE_BIDI; - bool bpf = test_type == TEST_TYPE_BPF_RES; - struct pkt_stream *pkt_stream; + struct ifobject *ifobj_tx = test->ifobj_tx; + struct ifobject *ifobj_rx = test->ifobj_rx; + pthread_t t0, t1; if (pthread_barrier_init(&barr, NULL, 2)) exit_with_error(errno); - if (stat_test_type == STAT_TEST_TX_INVALID) - pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, XSK_UMEM__INVALID_FRAME_SIZE); - else - pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, PKT_SIZE); - ifdict_tx->pkt_stream = pkt_stream; - ifdict_rx->pkt_stream = pkt_stream; + test->current_step++; + pkt_stream_reset(ifobj_rx->pkt_stream); + pkts_in_flight = 0; /*Spawn RX thread */ - pthread_create(&t0, NULL, ifdict_rx->func_ptr, ifdict_rx); + pthread_create(&t0, NULL, ifobj_rx->func_ptr, test); pthread_barrier_wait(&barr); if (pthread_barrier_destroy(&barr)) exit_with_error(errno); /*Spawn TX thread */ - pthread_create(&t1, NULL, ifdict_tx->func_ptr, ifdict_tx); + pthread_create(&t1, NULL, ifobj_tx->func_ptr, test); pthread_join(t1, NULL); pthread_join(t0, NULL); - - if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !bpf && !(test_type == TEST_TYPE_STATS)) - print_ksft_result(); } -static void testapp_teardown(void) +static void testapp_teardown(struct test_spec *test) { int i; + test_spec_set_name(test, "TEARDOWN"); for (i = 0; i < MAX_TEARDOWN_ITER; i++) { - print_verbose("Creating socket\n"); - testapp_validate(); + testapp_validate_traffic(test); + test_spec_reset(test); } - - print_ksft_result(); } -static void swap_vectors(struct ifobject *ifobj1, struct ifobject *ifobj2) +static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) { - void *(*tmp_func_ptr)(void *) = ifobj1->func_ptr; - enum fvector tmp_vector = ifobj1->fv.vector; + thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr; + struct ifobject *tmp_ifobj = (*ifobj1); - ifobj1->func_ptr = ifobj2->func_ptr; - ifobj1->fv.vector = ifobj2->fv.vector; + (*ifobj1)->func_ptr = (*ifobj2)->func_ptr; + (*ifobj2)->func_ptr = tmp_func_ptr; - ifobj2->func_ptr = tmp_func_ptr; - ifobj2->fv.vector = tmp_vector; - - ifdict_tx = ifobj1; - ifdict_rx = ifobj2; + *ifobj1 = *ifobj2; + *ifobj2 = tmp_ifobj; } -static void testapp_bidi(void) +static void testapp_bidi(struct test_spec *test) { - for (int i = 0; i < MAX_BIDI_ITER; i++) { - print_verbose("Creating socket\n"); - testapp_validate(); - if (!second_step) { - print_verbose("Switching Tx/Rx vectors\n"); - swap_vectors(ifdict[1], ifdict[0]); - } - second_step = true; - } + test_spec_set_name(test, "BIDIRECTIONAL"); + test->ifobj_tx->rx_on = true; + test->ifobj_rx->tx_on = true; + test->total_steps = 2; + testapp_validate_traffic(test); - swap_vectors(ifdict[0], ifdict[1]); + print_verbose("Switching Tx/Rx vectors\n"); + swap_directions(&test->ifobj_rx, &test->ifobj_tx); + testapp_validate_traffic(test); - print_ksft_result(); + swap_directions(&test->ifobj_rx, &test->ifobj_tx); } -static void swap_xsk_res(void) +static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx) { - xsk_socket__delete(ifdict_tx->xsk->xsk); - xsk_umem__delete(ifdict_tx->umem->umem); - xsk_socket__delete(ifdict_rx->xsk->xsk); - xsk_umem__delete(ifdict_rx->umem->umem); - ifdict_tx->umem = ifdict_tx->umem_arr[1]; - ifdict_tx->xsk = ifdict_tx->xsk_arr[1]; - ifdict_rx->umem = ifdict_rx->umem_arr[1]; - ifdict_rx->xsk = ifdict_rx->xsk_arr[1]; + 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]; } -static void testapp_bpf_res(void) +static void testapp_bpf_res(struct test_spec *test) { - int i; + test_spec_set_name(test, "BPF_RES"); + test->total_steps = 2; + test->nb_sockets = 2; + testapp_validate_traffic(test); - for (i = 0; i < MAX_BPF_ITER; i++) { - print_verbose("Creating socket\n"); - testapp_validate(); - if (!second_step) - swap_xsk_res(); - second_step = true; - } + swap_xsk_resources(test->ifobj_tx, test->ifobj_rx); + testapp_validate_traffic(test); +} - print_ksft_result(); +static void testapp_headroom(struct test_spec *test) +{ + test_spec_set_name(test, "UMEM_HEADROOM"); + test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; + testapp_validate_traffic(test); } -static void testapp_stats(void) +static void testapp_stats(struct test_spec *test) { - for (int i = 0; i < STAT_TEST_TYPE_MAX; i++) { - stat_test_type = i; + int i; - /* reset defaults */ - rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; - frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; + for (i = 0; i < STAT_TEST_TYPE_MAX; i++) { + test_spec_reset(test); + stat_test_type = i; + /* No or few packets will be received so cannot pace packets */ + test->ifobj_tx->pacing_on = false; switch (stat_test_type) { case STAT_TEST_RX_DROPPED: - frame_headroom = XSK_UMEM__DEFAULT_FRAME_SIZE - - XDP_PACKET_HEADROOM - 1; + test_spec_set_name(test, "STAT_RX_DROPPED"); + test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - + XDP_PACKET_HEADROOM - 1; + testapp_validate_traffic(test); break; case STAT_TEST_RX_FULL: - rxqsize = RX_FULL_RXQSIZE; + test_spec_set_name(test, "STAT_RX_FULL"); + test->ifobj_rx->xsk->rxqsize = RX_FULL_RXQSIZE; + testapp_validate_traffic(test); break; case STAT_TEST_TX_INVALID: - continue; + test_spec_set_name(test, "STAT_TX_INVALID"); + pkt_stream_replace(test, DEFAULT_PKT_CNT, XSK_UMEM__INVALID_FRAME_SIZE); + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + break; + case STAT_TEST_RX_FILL_EMPTY: + test_spec_set_name(test, "STAT_RX_FILL_EMPTY"); + test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, 0, + MIN_PKT_SIZE); + if (!test->ifobj_rx->pkt_stream) + exit_with_error(ENOMEM); + test->ifobj_rx->pkt_stream->use_addr_for_fill = true; + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + break; default: break; } - testapp_validate(); } - print_ksft_result(); + /* To only see the whole stat set being completed unless an individual test fails. */ + test_spec_set_name(test, "STATS"); +} + +/* Simple test */ +static bool hugepages_present(struct ifobject *ifobject) +{ + const size_t mmap_sz = 2 * ifobject->umem->num_frames * ifobject->umem->frame_size; + void *bufs; + + bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE | MAP_HUGETLB, -1, 0); + if (bufs == MAP_FAILED) + return false; + + munmap(bufs, mmap_sz); + return true; +} + +static bool testapp_unaligned(struct test_spec *test) +{ + if (!hugepages_present(test->ifobj_tx)) { + ksft_test_result_skip("No 2M huge pages present.\n"); + return false; + } + + test_spec_set_name(test, "UNALIGNED_MODE"); + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + /* Let half of the packets straddle a buffer boundrary */ + pkt_stream_replace_half(test, PKT_SIZE, -PKT_SIZE / 2); + test->ifobj_rx->pkt_stream->use_addr_for_fill = true; + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + return true; +} + +static void testapp_single_pkt(struct test_spec *test) +{ + struct pkt pkts[] = {{0x1000, PKT_SIZE, 0, true}}; + + pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); + testapp_validate_traffic(test); + pkt_stream_restore_default(test); } -static void init_iface(struct ifobject *ifobj, const char *dst_mac, - const char *src_mac, const char *dst_ip, - const char *src_ip, const u16 dst_port, - const u16 src_port, enum fvector vector) +static void testapp_invalid_desc(struct test_spec *test) +{ + struct pkt pkts[] = { + /* Zero packet length at address zero allowed */ + {0, 0, 0, true}, + /* Zero packet length allowed */ + {0x1000, 0, 0, true}, + /* Straddling the start of umem */ + {-2, PKT_SIZE, 0, false}, + /* Packet too large */ + {0x2000, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, + /* After umem ends */ + {UMEM_SIZE, PKT_SIZE, 0, false}, + /* Straddle the end of umem */ + {UMEM_SIZE - PKT_SIZE / 2, PKT_SIZE, 0, false}, + /* Straddle a page boundrary */ + {0x3000 - PKT_SIZE / 2, PKT_SIZE, 0, false}, + /* Straddle a 2K boundrary */ + {0x3800 - PKT_SIZE / 2, PKT_SIZE, 0, true}, + /* Valid packet for synch so that something is received */ + {0x4000, PKT_SIZE, 0, true}}; + + if (test->ifobj_tx->umem->unaligned_mode) { + /* Crossing a page boundrary allowed */ + pkts[6].valid = true; + } + if (test->ifobj_tx->umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { + /* Crossing a 2K frame size boundrary not allowed */ + pkts[7].valid = false; + } + + pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); + testapp_validate_traffic(test); + pkt_stream_restore_default(test); +} + +static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac, + const char *dst_ip, const char *src_ip, const u16 dst_port, + const u16 src_port, thread_func_t func_ptr) { struct in_addr ip; @@ -1009,58 +1309,80 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, ifobj->dst_port = dst_port; ifobj->src_port = src_port; - if (vector == tx) { - ifobj->fv.vector = tx; - ifobj->func_ptr = worker_testapp_validate_tx; - ifdict_tx = ifobj; - } else { - ifobj->fv.vector = rx; - ifobj->func_ptr = worker_testapp_validate_rx; - ifdict_rx = ifobj; - } + ifobj->func_ptr = func_ptr; } -static void run_pkt_test(int mode, int type) +static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type) { test_type = type; /* reset defaults after potential previous test */ - xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; - second_step = 0; stat_test_type = -1; - rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; - frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; - - configured_mode = mode; - - switch (mode) { - case (TEST_MODE_SKB): - xdp_flags |= XDP_FLAGS_SKB_MODE; - break; - case (TEST_MODE_DRV): - xdp_flags |= XDP_FLAGS_DRV_MODE; - break; - default: - break; - } switch (test_type) { case TEST_TYPE_STATS: - testapp_stats(); + testapp_stats(test); break; case TEST_TYPE_TEARDOWN: - testapp_teardown(); + testapp_teardown(test); break; case TEST_TYPE_BIDI: - testapp_bidi(); + testapp_bidi(test); break; case TEST_TYPE_BPF_RES: - testapp_bpf_res(); + testapp_bpf_res(test); + break; + case TEST_TYPE_RUN_TO_COMPLETION: + test_spec_set_name(test, "RUN_TO_COMPLETION"); + testapp_validate_traffic(test); + break; + case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT: + test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT"); + testapp_single_pkt(test); + break; + case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME: + test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE"); + test->ifobj_tx->umem->frame_size = 2048; + test->ifobj_rx->umem->frame_size = 2048; + pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + break; + case TEST_TYPE_POLL: + test->ifobj_tx->use_poll = true; + test->ifobj_rx->use_poll = true; + test_spec_set_name(test, "POLL"); + testapp_validate_traffic(test); + break; + case TEST_TYPE_ALIGNED_INV_DESC: + test_spec_set_name(test, "ALIGNED_INV_DESC"); + testapp_invalid_desc(test); + break; + case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME: + test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE"); + test->ifobj_tx->umem->frame_size = 2048; + test->ifobj_rx->umem->frame_size = 2048; + testapp_invalid_desc(test); + break; + case TEST_TYPE_UNALIGNED_INV_DESC: + test_spec_set_name(test, "UNALIGNED_INV_DESC"); + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + testapp_invalid_desc(test); + break; + case TEST_TYPE_UNALIGNED: + if (!testapp_unaligned(test)) + return; + break; + case TEST_TYPE_HEADROOM: + testapp_headroom(test); break; default: - testapp_validate(); break; } + + print_ksft_result(test); } static struct ifobject *ifobject_create(void) @@ -1071,11 +1393,11 @@ static struct ifobject *ifobject_create(void) if (!ifobj) return NULL; - ifobj->xsk_arr = calloc(2, sizeof(struct xsk_socket_info *)); + ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr)); if (!ifobj->xsk_arr) goto out_xsk_arr; - ifobj->umem_arr = calloc(2, sizeof(struct xsk_umem_info *)); + ifobj->umem_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->umem_arr)); if (!ifobj->umem_arr) goto out_umem_arr; @@ -1098,34 +1420,53 @@ static void ifobject_delete(struct ifobject *ifobj) int main(int argc, char **argv) { struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY }; - int i, j; + struct pkt_stream *pkt_stream_default; + struct ifobject *ifobj_tx, *ifobj_rx; + struct test_spec test; + u32 i, j; if (setrlimit(RLIMIT_MEMLOCK, &_rlim)) exit_with_error(errno); - for (i = 0; i < MAX_INTERFACES; i++) { - ifdict[i] = ifobject_create(); - if (!ifdict[i]) - exit_with_error(ENOMEM); - } + ifobj_tx = ifobject_create(); + if (!ifobj_tx) + exit_with_error(ENOMEM); + ifobj_rx = ifobject_create(); + if (!ifobj_rx) + exit_with_error(ENOMEM); setlocale(LC_ALL, ""); - parse_command_line(argc, argv); + parse_command_line(ifobj_tx, ifobj_rx, argc, argv); - init_iface(ifdict[tx], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx); - init_iface(ifdict[rx], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx); + if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx)) { + usage(basename(argv[0])); + ksft_exit_xfail(); + } + + init_iface(ifobj_tx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, + worker_testapp_validate_tx); + init_iface(ifobj_rx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, + worker_testapp_validate_rx); + + test_spec_init(&test, ifobj_tx, ifobj_rx, 0); + pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE); + if (!pkt_stream_default) + exit_with_error(ENOMEM); + test.pkt_stream_default = pkt_stream_default; ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX); for (i = 0; i < TEST_MODE_MAX; i++) for (j = 0; j < TEST_TYPE_MAX; j++) { - run_pkt_test(i, j); + test_spec_init(&test, ifobj_tx, ifobj_rx, i); + run_pkt_test(&test, i, j); usleep(USLEEP_MAX); } - for (i = 0; i < MAX_INTERFACES; i++) - ifobject_delete(ifdict[i]); + pkt_stream_delete(pkt_stream_default); + ifobject_delete(ifobj_tx); + ifobject_delete(ifobj_rx); ksft_exit_pass(); return 0; diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h index 7e49b9fbe25e..2f705f44b748 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.h +++ b/tools/testing/selftests/bpf/xdpxceiver.h @@ -20,10 +20,9 @@ #define MAX_INTERFACES 2 #define MAX_INTERFACE_NAME_CHARS 7 #define MAX_INTERFACES_NAMESPACE_CHARS 10 -#define MAX_SOCKS 1 +#define MAX_SOCKETS 2 +#define MAX_TEST_NAME_SIZE 32 #define MAX_TEARDOWN_ITER 10 -#define MAX_BIDI_ITER 2 -#define MAX_BPF_ITER 2 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ sizeof(struct udphdr)) #define MIN_PKT_SIZE 64 @@ -36,10 +35,13 @@ #define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr)) #define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 -#define BATCH_SIZE 8 +#define BATCH_SIZE 64 #define POLL_TMOUT 1000 #define DEFAULT_PKT_CNT (4 * 1024) +#define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) +#define UMEM_SIZE (DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE) #define RX_FULL_RXQSIZE 32 +#define UMEM_HEADROOM_TEST_SIZE 128 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1) #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) @@ -51,8 +53,15 @@ enum test_mode { }; enum test_type { - TEST_TYPE_NOPOLL, + TEST_TYPE_RUN_TO_COMPLETION, + TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME, + TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT, TEST_TYPE_POLL, + TEST_TYPE_UNALIGNED, + TEST_TYPE_ALIGNED_INV_DESC, + TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME, + TEST_TYPE_UNALIGNED_INV_DESC, + TEST_TYPE_HEADROOM, TEST_TYPE_TEARDOWN, TEST_TYPE_BIDI, TEST_TYPE_STATS, @@ -68,25 +77,21 @@ enum stat_test_type { STAT_TEST_TYPE_MAX }; -static int configured_mode; static bool opt_pkt_dump; -static u32 num_frames = DEFAULT_PKT_CNT / 4; -static bool second_step; static int test_type; static bool opt_verbose; - -static u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; -static u32 xdp_bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY; static int stat_test_type; -static u32 rxqsize; -static u32 frame_headroom; struct xsk_umem_info { struct xsk_ring_prod fq; struct xsk_ring_cons cq; struct xsk_umem *umem; + u32 num_frames; + u32 frame_headroom; void *buffer; + u32 frame_size; + bool unaligned_mode; }; struct xsk_socket_info { @@ -95,51 +100,63 @@ struct xsk_socket_info { struct xsk_umem_info *umem; struct xsk_socket *xsk; u32 outstanding_tx; -}; - -struct flow_vector { - enum fvector { - tx, - rx, - } vector; + u32 rxqsize; }; struct pkt { u64 addr; u32 len; u32 payload; + bool valid; }; struct pkt_stream { u32 nb_pkts; + u32 rx_pkt_nb; struct pkt *pkts; + bool use_addr_for_fill; }; +typedef void *(*thread_func_t)(void *arg); + struct ifobject { char ifname[MAX_INTERFACE_NAME_CHARS]; char nsname[MAX_INTERFACES_NAMESPACE_CHARS]; struct xsk_socket_info *xsk; - struct xsk_socket_info **xsk_arr; - struct xsk_umem_info **umem_arr; + struct xsk_socket_info *xsk_arr; struct xsk_umem_info *umem; - void *(*func_ptr)(void *arg); - struct flow_vector fv; + struct xsk_umem_info *umem_arr; + thread_func_t func_ptr; struct pkt_stream *pkt_stream; int ns_fd; u32 dst_ip; u32 src_ip; + u32 xdp_flags; + u32 bind_flags; u16 src_port; u16 dst_port; + bool tx_on; + bool rx_on; + bool use_poll; + bool pacing_on; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; }; -static struct ifobject *ifdict[MAX_INTERFACES]; -static struct ifobject *ifdict_rx; -static struct ifobject *ifdict_tx; +struct test_spec { + struct ifobject *ifobj_tx; + struct ifobject *ifobj_rx; + struct pkt_stream *pkt_stream_default; + u16 total_steps; + u16 current_step; + u16 nb_sockets; + char name[MAX_TEST_NAME_SIZE]; +}; -/*threads*/ pthread_barrier_t barr; -pthread_t t0, t1; +pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; +pthread_cond_t pacing_cond = PTHREAD_COND_INITIALIZER; + +u32 pkts_in_flight; #endif /* XDPXCEIVER_H */ diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh index 8817851da7a9..e9a82cae8c9a 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -13,7 +13,7 @@ # | # +-------------------|-----+ # | SW1 | | -# | $swp1 + | +# | $swp1 + | # | 192.0.2.2/28 | # | | # | + g1a (gre) | @@ -27,8 +27,8 @@ # | # +--|----------------------+ # | | VRF2 | -# | + $rp2 | -# | 198.51.100.2/28 | +# | + $rp2 | +# | 198.51.100.2/28 | # +-------------------------+ lib_dir=$(dirname $0)/../../../net/forwarding @@ -116,12 +116,16 @@ cleanup() forwarding_restore } -ecn_payload_get() +ipip_payload_get() { + local flags=$1; shift + local key=$1; shift + p=$(: - )"0"$( : GRE flags + )"$flags"$( : GRE flags )"0:00:"$( : Reserved + version )"08:00:"$( : ETH protocol type + )"$key"$( : Key )"4"$( : IP version )"5:"$( : IHL )"00:"$( : IP TOS @@ -137,6 +141,11 @@ ecn_payload_get() echo $p } +ecn_payload_get() +{ + echo $(ipip_payload_get "0") +} + ecn_decap_test() { local trap_name="decap_error" @@ -171,31 +180,6 @@ ecn_decap_test() tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } -ipip_payload_get() -{ - local flags=$1; shift - local key=$1; shift - - p=$(: - )"$flags"$( : GRE flags - )"0:00:"$( : Reserved + version - )"08:00:"$( : ETH protocol type - )"$key"$( : Key - )"4"$( : IP version - )"5:"$( : IHL - )"00:"$( : IP TOS - )"00:14:"$( : IP total length - )"00:00:"$( : IP identification - )"20:00:"$( : IP flags + frag off - )"30:"$( : IP TTL - )"01:"$( : IP proto - )"E7:E6:"$( : IP header csum - )"C0:00:01:01:"$( : IP saddr : 192.0.1.1 - )"C0:00:02:01:"$( : IP daddr : 192.0.2.1 - ) - echo $p -} - no_matching_tunnel_test() { local trap_name="decap_error" @@ -239,7 +223,8 @@ decap_error_test() no_matching_tunnel_test "Decap error: Source IP check failed" \ 192.0.2.68 "0" no_matching_tunnel_test \ - "Decap error: Key exists but was not expected" $sip "2" ":E9:" + "Decap error: Key exists but was not expected" $sip "2" \ + "00:00:00:E9:" # Destroy the tunnel and create new one with key __addr_add_del g1 del 192.0.2.65/32 @@ -251,7 +236,8 @@ decap_error_test() no_matching_tunnel_test \ "Decap error: Key does not exist but was expected" $sip "0" no_matching_tunnel_test \ - "Decap error: Packet has a wrong key field" $sip "2" "E8:" + "Decap error: Packet has a wrong key field" $sip "2" \ + "00:00:00:E8:" } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh new file mode 100755 index 000000000000..ade79ef08de3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh @@ -0,0 +1,276 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test qdisc offload indication + + +ALL_TESTS=" + test_root + test_etsprio +" +NUM_NETIFS=1 +lib_dir=$(dirname $0)/../../../net/forwarding +source $lib_dir/lib.sh + +check_not_offloaded() +{ + local handle=$1; shift + local h + local offloaded + + h=$(qdisc_stats_get $h1 "$handle" .handle) + [[ $h == '"'$handle'"' ]] + check_err $? "Qdisc with handle $handle does not exist" + + offloaded=$(qdisc_stats_get $h1 "$handle" .offloaded) + [[ $offloaded == true ]] + check_fail $? "Qdisc with handle $handle offloaded, but should not be" +} + +check_all_offloaded() +{ + local handle=$1; shift + + if [[ ! -z $handle ]]; then + local offloaded=$(qdisc_stats_get $h1 "$handle" .offloaded) + [[ $offloaded == true ]] + check_err $? "Qdisc with handle $handle not offloaded" + fi + + local unoffloaded=$(tc q sh dev $h1 invisible | + grep -v offloaded | + sed s/root/parent\ root/ | + cut -d' ' -f 5) + [[ -z $unoffloaded ]] + check_err $? "Qdiscs with following parents not offloaded: $unoffloaded" + + pre_cleanup +} + +with_ets() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + ets bands 8 priomap 7 6 5 4 3 2 1 0 + "$@" + tc qdisc del dev $h1 $locus +} + +with_prio() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + prio bands 8 priomap 7 6 5 4 3 2 1 0 + "$@" + tc qdisc del dev $h1 $locus +} + +with_red() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + red limit 1000000 min 200000 max 300000 probability 0.5 avpkt 1500 + "$@" + tc qdisc del dev $h1 $locus +} + +with_tbf() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle \ + tbf rate 400Mbit burst 128K limit 1M + "$@" + tc qdisc del dev $h1 $locus +} + +with_pfifo() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle pfifo limit 100K + "$@" + tc qdisc del dev $h1 $locus +} + +with_bfifo() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle bfifo limit 100K + "$@" + tc qdisc del dev $h1 $locus +} + +with_drr() +{ + local handle=$1; shift + local locus=$1; shift + + tc qdisc add dev $h1 $locus handle $handle drr + "$@" + tc qdisc del dev $h1 $locus +} + +with_qdiscs() +{ + local handle=$1; shift + local parent=$1; shift + local kind=$1; shift + local next_handle=$((handle * 2)) + local locus; + + if [[ $kind == "--" ]]; then + local cmd=$1; shift + $cmd $(printf %x: $parent) "$@" + else + if ((parent == 0)); then + locus=root + else + locus=$(printf "parent %x:1" $parent) + fi + + with_$kind $(printf %x: $handle) "$locus" \ + with_qdiscs $next_handle $handle "$@" + fi +} + +get_name() +{ + local parent=$1; shift + local name=$(echo "" "${@^^}" | tr ' ' -) + + if ((parent != 0)); then + kind=$(qdisc_stats_get $h1 $parent: .kind) + kind=${kind%\"} + kind=${kind#\"} + name="-${kind^^}$name" + fi + + echo root$name +} + +do_test_offloaded() +{ + local handle=$1; shift + local parent=$1; shift + + RET=0 + with_qdiscs $handle $parent "$@" -- check_all_offloaded + log_test $(get_name $parent "$@")" offloaded" +} + +do_test_nooffload() +{ + local handle=$1; shift + local parent=$1; shift + + local name=$(echo "${@^^}" | tr ' ' -) + local kind + + RET=0 + with_qdiscs $handle $parent "$@" -- check_not_offloaded + log_test $(get_name $parent "$@")" not offloaded" +} + +do_test_combinations() +{ + local handle=$1; shift + local parent=$1; shift + + local cont + local leaf + local fifo + + for cont in "" ets prio; do + for leaf in "" red tbf "red tbf" "tbf red"; do + for fifo in "" pfifo bfifo; do + if [[ -z "$cont$leaf$fifo" ]]; then + continue + fi + do_test_offloaded $handle $parent \ + $cont $leaf $fifo + done + done + done + + for cont in ets prio; do + for leaf in red tbf; do + do_test_nooffload $handle $parent $cont red tbf $leaf + do_test_nooffload $handle $parent $cont tbf red $leaf + done + for leaf in "red red" "tbf tbf"; do + do_test_nooffload $handle $parent $cont $leaf + done + done + + do_test_nooffload $handle $parent drr +} + +test_root() +{ + do_test_combinations 1 0 +} + +do_test_etsprio() +{ + local parent=$1; shift + local tbfpfx=$1; shift + local cont + + for cont in ets prio; do + RET=0 + with_$cont 8: "$parent" \ + with_red 11: "parent 8:1" \ + with_red 12: "parent 8:2" \ + with_tbf 13: "parent 8:3" \ + with_tbf 14: "parent 8:4" \ + check_all_offloaded + log_test "root$tbfpfx-ETS-{RED,TBF} offloaded" + + RET=0 + with_$cont 8: "$parent" \ + with_red 81: "parent 8:1" \ + with_tbf 811: "parent 81:1" \ + with_tbf 84: "parent 8:4" \ + with_red 841: "parent 84:1" \ + check_all_offloaded + log_test "root$tbfpfx-ETS-{RED-TBF,TBF-RED} offloaded" + + RET=0 + with_$cont 8: "$parent" \ + with_red 81: "parent 8:1" \ + with_tbf 811: "parent 81:1" \ + with_bfifo 8111: "parent 811:1" \ + with_tbf 82: "parent 8:2" \ + with_red 821: "parent 82:1" \ + with_bfifo 8211: "parent 821:1" \ + check_all_offloaded + log_test "root$tbfpfx-ETS-{RED-TBF-bFIFO,TBF-RED-bFIFO} offloaded" + done +} + +test_etsprio() +{ + do_test_etsprio root "" +} + +cleanup() +{ + tc qdisc del dev $h1 root &>/dev/null +} + +trap cleanup EXIT +h1=${NETIFS[p1]} +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh index 33ddd01689be..dd90cd87d4f9 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -331,6 +331,14 @@ get_nmarked() ethtool_stats_get $swp3 ecn_marked } +get_qdisc_nmarked() +{ + local vlan=$1; shift + + busywait_for_counter 1100 +1 \ + qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .marked +} + get_qdisc_npackets() { local vlan=$1; shift @@ -384,14 +392,15 @@ build_backlog() check_marking() { + local get_nmarked=$1; shift local vlan=$1; shift local cond=$1; shift local npackets_0=$(get_qdisc_npackets $vlan) - local nmarked_0=$(get_nmarked $vlan) + local nmarked_0=$($get_nmarked $vlan) sleep 5 local npackets_1=$(get_qdisc_npackets $vlan) - local nmarked_1=$(get_nmarked $vlan) + local nmarked_1=$($get_nmarked $vlan) local nmarked_d=$((nmarked_1 - nmarked_0)) local npackets_d=$((npackets_1 - npackets_0)) @@ -404,6 +413,7 @@ check_marking() ecn_test_common() { local name=$1; shift + local get_nmarked=$1; shift local vlan=$1; shift local limit=$1; shift local backlog @@ -416,7 +426,7 @@ ecn_test_common() RET=0 backlog=$(build_backlog $vlan $((2 * limit / 3)) udp) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking "$get_nmarked" $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." log_test "TC $((vlan - 10)): $name backlog < limit" @@ -426,22 +436,23 @@ ecn_test_common() RET=0 backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan ">= 95") + pct=$(check_marking "$get_nmarked" $vlan ">= 95") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95." log_test "TC $((vlan - 10)): $name backlog > limit" } -do_ecn_test() +__do_ecn_test() { + local get_nmarked=$1; shift local vlan=$1; shift local limit=$1; shift - local name=ECN + local name=${1-ECN}; shift start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ $h3_mac tos=0x01 sleep 1 - ecn_test_common "$name" $vlan $limit + ecn_test_common "$name" "$get_nmarked" $vlan $limit # Up there we saw that UDP gets accepted when backlog is below the # limit. Now that it is above, it should all get dropped, and backlog @@ -455,6 +466,26 @@ do_ecn_test() sleep 1 } +do_ecn_test() +{ + local vlan=$1; shift + local limit=$1; shift + + __do_ecn_test get_nmarked "$vlan" "$limit" +} + +do_ecn_test_perband() +{ + local vlan=$1; shift + local limit=$1; shift + + # Per-band ECN counters are not supported on Spectrum-1 and Spectrum-2. + [[ "$DEVLINK_VIDDID" == "15b3:cb84" || + "$DEVLINK_VIDDID" == "15b3:cf6c" ]] && return + + __do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN" +} + do_ecn_nodrop_test() { local vlan=$1; shift @@ -465,7 +496,7 @@ do_ecn_nodrop_test() $h3_mac tos=0x01 sleep 1 - ecn_test_common "$name" $vlan $limit + ecn_test_common "$name" get_nmarked $vlan $limit # Up there we saw that UDP gets accepted when backlog is below the # limit. Now that it is above, in nodrop mode, make sure it goes to @@ -495,7 +526,7 @@ do_red_test() RET=0 backlog=$(build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01) check_err $? "Could not build the requested backlog" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." log_test "TC $((vlan - 10)): RED backlog < limit" @@ -503,7 +534,7 @@ do_red_test() RET=0 backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) check_fail $? "Traffic went into backlog instead of being early-dropped" - pct=$(check_marking $vlan "== 0") + pct=$(check_marking get_nmarked $vlan "== 0") check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." local diff=$((limit - backlog)) pct=$((100 * diff / limit)) @@ -544,6 +575,53 @@ do_mc_backlog_test() log_test "TC $((vlan - 10)): Qdisc reports MC backlog" } +do_mark_test() +{ + local vlan=$1; shift + local limit=$1; shift + local subtest=$1; shift + local fetch_counter=$1; shift + local should_fail=$1; shift + local base + + RET=0 + + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ + $h3_mac tos=0x01 + + # Create a bit of a backlog and observe no mirroring due to marks. + qevent_rule_install_$subtest + + build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01 >/dev/null + + base=$($fetch_counter) + count=$(busywait 1100 until_counter_is ">= $((base + 1))" \ + $fetch_counter) + check_fail $? "Spurious packets ($base -> $count) observed without buffer pressure" + + # Above limit, everything should be mirrored, we should see lots of + # packets. + build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01 >/dev/null + busywait_for_counter 1100 +10000 \ + $fetch_counter > /dev/null + check_err_fail "$should_fail" $? "ECN-marked packets $subtest'd" + + # When the rule is uninstalled, there should be no mirroring. + qevent_rule_uninstall_$subtest + busywait_for_counter 1100 +10 \ + $fetch_counter > /dev/null + check_fail $? "Spurious packets observed after uninstall" + + if ((should_fail)); then + log_test "TC $((vlan - 10)): marked packets not $subtest'd" + else + log_test "TC $((vlan - 10)): marked packets $subtest'd" + fi + + stop_traffic + sleep 1 +} + do_drop_test() { local vlan=$1; shift @@ -551,10 +629,8 @@ do_drop_test() local trigger=$1; shift local subtest=$1; shift local fetch_counter=$1; shift - local backlog local base local now - local pct RET=0 @@ -628,6 +704,22 @@ do_drop_mirror_test() tc filter del dev $h2 ingress pref 1 handle 101 flower } +do_mark_mirror_test() +{ + local vlan=$1; shift + local limit=$1; shift + + tc filter add dev $h2 ingress pref 1 handle 101 prot ip \ + flower skip_sw ip_proto tcp \ + action drop + + do_mark_test "$vlan" "$limit" mirror \ + qevent_counter_fetch_mirror \ + $(: should_fail=)0 + + tc filter del dev $h2 ingress pref 1 handle 101 flower +} + qevent_rule_install_trap() { tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ @@ -655,3 +747,14 @@ do_drop_trap_test() do_drop_test "$vlan" "$limit" "$trap_name" trap \ "qevent_counter_fetch_trap $trap_name" } + +qevent_rule_install_trap_fwd() +{ + tc filter add block 10 pref 1234 handle 102 matchall skip_sw \ + action trap_fwd hw_stats disabled +} + +qevent_rule_uninstall_trap_fwd() +{ + tc filter del block 10 pref 1234 handle 102 matchall +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh index f3ef3274f9b3..1e5ad3209436 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -4,11 +4,13 @@ ALL_TESTS=" ping_ipv4 ecn_test + ecn_test_perband ecn_nodrop_test red_test mc_backlog_test red_mirror_test red_trap_test + ecn_mirror_test " : ${QDISC:=ets} source sch_red_core.sh @@ -21,28 +23,60 @@ source sch_red_core.sh BACKLOG1=200000 BACKLOG2=500000 -install_qdisc() +install_root_qdisc() { - local -a args=("$@") - tc qdisc add dev $swp3 root handle 10: $QDISC \ bands 8 priomap 7 6 5 4 3 2 1 0 +} + +install_qdisc_tc0() +{ + local -a args=("$@") + tc qdisc add dev $swp3 parent 10:8 handle 108: red \ limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \ probability 1.0 avpkt 8000 burst 38 "${args[@]}" +} + +install_qdisc_tc1() +{ + local -a args=("$@") + tc qdisc add dev $swp3 parent 10:7 handle 107: red \ limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \ probability 1.0 avpkt 8000 burst 63 "${args[@]}" +} + +install_qdisc() +{ + install_root_qdisc + install_qdisc_tc0 "$@" + install_qdisc_tc1 "$@" sleep 1 } -uninstall_qdisc() +uninstall_qdisc_tc0() { - tc qdisc del dev $swp3 parent 10:7 tc qdisc del dev $swp3 parent 10:8 +} + +uninstall_qdisc_tc1() +{ + tc qdisc del dev $swp3 parent 10:7 +} + +uninstall_root_qdisc() +{ tc qdisc del dev $swp3 root } +uninstall_qdisc() +{ + uninstall_qdisc_tc0 + uninstall_qdisc_tc1 + uninstall_root_qdisc +} + ecn_test() { install_qdisc ecn @@ -53,6 +87,16 @@ ecn_test() uninstall_qdisc } +ecn_test_perband() +{ + install_qdisc ecn + + do_ecn_test_perband 10 $BACKLOG1 + do_ecn_test_perband 11 $BACKLOG2 + + uninstall_qdisc +} + ecn_nodrop_test() { install_qdisc ecn nodrop @@ -112,6 +156,16 @@ red_trap_test() uninstall_qdisc } +ecn_mirror_test() +{ + install_qdisc ecn qevent mark block 10 + + do_mark_mirror_test 10 $BACKLOG1 + do_mark_mirror_test 11 $BACKLOG2 + + uninstall_qdisc +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh index ede9c38d3eff..d79a82f317d2 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh @@ -4,6 +4,7 @@ ALL_TESTS=" ping_ipv4 ecn_test + ecn_test_perband ecn_nodrop_test red_test mc_backlog_test @@ -35,6 +36,13 @@ ecn_test() uninstall_qdisc } +ecn_test_perband() +{ + install_qdisc ecn + do_ecn_test_perband 10 $BACKLOG + uninstall_qdisc +} + ecn_nodrop_test() { install_qdisc ecn nodrop diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh new file mode 100755 index 000000000000..f62ce479c266 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh @@ -0,0 +1,250 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap tunnel exceptions functionality over mlxsw. +# Check all exception traps to make sure they are triggered under the right +# conditions. + +# +-------------------------+ +# | H1 | +# | $h1 + | +# | 2001:db8:1::1/64 | | +# +-------------------|-----+ +# | +# +-------------------|-----+ +# | SW1 | | +# | $swp1 + | +# | 2001:db8:1::2/64 | +# | | +# | + g1 (ip6gre) | +# | loc=2001:db8:3::1 | +# | rem=2001:db8:3::2 | +# | tos=inherit | +# | | +# | + $rp1 | +# | | 2001:db8:10::1/64 | +# +--|----------------------+ +# | +# +--|----------------------+ +# | | VRF2 | +# | + $rp2 | +# | 2001:db8:10::2/64 | +# +-------------------------+ + +lib_dir=$(dirname $0)/../../../../net/forwarding + +ALL_TESTS=" + decap_error_test +" + +NUM_NETIFS=4 +source $lib_dir/lib.sh +source $lib_dir/tc_common.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 2001:db8:1::1/64 +} + +vrf2_create() +{ + simple_if_init $rp2 2001:db8:10::2/64 +} + +vrf2_destroy() +{ + simple_if_fini $rp2 2001:db8:10::2/64 +} + +switch_create() +{ + ip link set dev $swp1 up + __addr_add_del $swp1 add 2001:db8:1::2/64 + tc qdisc add dev $swp1 clsact + + tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit + ip link set dev g1 up + __addr_add_del g1 add 2001:db8:3::1/128 + + ip link set dev $rp1 up + __addr_add_del $rp1 add 2001:db8:10::1/64 +} + +switch_destroy() +{ + __addr_add_del $rp1 del 2001:db8:10::1/64 + ip link set dev $rp1 down + + __addr_add_del g1 del 2001:db8:3::1/128 + ip link set dev g1 down + tunnel_destroy g1 + + tc qdisc del dev $swp1 clsact + __addr_add_del $swp1 del 2001:db8:1::2/64 + ip link set dev $swp1 down +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + forwarding_enable + vrf_prepare + h1_create + switch_create + vrf2_create +} + +cleanup() +{ + pre_cleanup + + vrf2_destroy + switch_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +ipip_payload_get() +{ + local saddr="20:01:0d:b8:00:02:00:00:00:00:00:00:00:00:00:01" + local daddr="20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01" + local flags=$1; shift + local key=$1; shift + + p=$(: + )"$flags"$( : GRE flags + )"0:00:"$( : Reserved + version + )"86:dd:"$( : ETH protocol type + )"$key"$( : Key + )"6"$( : IP version + )"0:0"$( : Traffic class + )"0:00:00:"$( : Flow label + )"00:00:"$( : Payload length + )"3a:"$( : Next header + )"04:"$( : Hop limit + )"$saddr:"$( : IP saddr + )"$daddr:"$( : IP daddr + ) + echo $p +} + +ecn_payload_get() +{ + echo $(ipip_payload_get "0") +} + +ecn_decap_test() +{ + local trap_name="decap_error" + local desc=$1; shift + local ecn_desc=$1; shift + local outer_tos=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::1 dst_ip 2001:db8:1::1 skip_sw \ + action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ecn_payload_get) + + ip vrf exec v$rp2 $MZ -6 $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A 2001:db8:3::2 -B 2001:db8:3::1 -t ip \ + tos=$outer_tos,next=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower +} + +no_matching_tunnel_test() +{ + local trap_name="decap_error" + local desc=$1; shift + local sip=$1; shift + local mz_pid + + RET=0 + + tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \ + flower src_ip 2001:db8:2::1 dst_ip 2001:db8:1::1 action pass + + rp1_mac=$(mac_get $rp1) + rp2_mac=$(mac_get $rp2) + payload=$(ipip_payload_get "$@") + + ip vrf exec v$rp2 $MZ -6 $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \ + -A $sip -B 2001:db8:3::1 -t ip next=47,p=$payload -q & + mz_pid=$! + + devlink_trap_exception_test $trap_name + + tc_check_packets "dev $swp1 egress" 101 0 + check_err $? "Packets were not dropped" + + log_test "$desc" + + kill $mz_pid && wait $mz_pid &> /dev/null + tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower +} + +decap_error_test() +{ + # Correct source IP - the remote address + local sip=2001:db8:3::2 + + ecn_decap_test "Decap error" "ECT(1)" 01 + ecn_decap_test "Decap error" "ECT(0)" 02 + ecn_decap_test "Decap error" "CE" 03 + + no_matching_tunnel_test "Decap error: Source IP check failed" \ + 2001:db8:4::2 "0" + no_matching_tunnel_test \ + "Decap error: Key exists but was not expected" $sip "2" \ + "00:00:00:E9:" + + # Destroy the tunnel and create new one with key + __addr_add_del g1 del 2001:db8:3::1/128 + tunnel_destroy g1 + + tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit key 233 + __addr_add_del g1 add 2001:db8:3::1/128 + + no_matching_tunnel_test \ + "Decap error: Key does not exist but was expected" $sip "0" + no_matching_tunnel_test \ + "Decap error: Packet has a wrong key field" $sip "2" \ + "00:00:00:E8:" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh index 7ca1f030d209..922744059aaa 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh @@ -50,7 +50,7 @@ function make_netdev { modprobe netdevsim fi - echo $NSIM_ID > /sys/bus/netdevsim/new_device + echo $NSIM_ID $@ > /sys/bus/netdevsim/new_device # get new device name ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/ } diff --git a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh new file mode 100755 index 000000000000..fd13c8cfb7a8 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh @@ -0,0 +1,77 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only + +source ethtool-common.sh + +set -o pipefail + +n_children() { + n=$(tc qdisc show dev $NDEV | grep '^qdisc' | wc -l) + echo $((n - 1)) +} + +tcq() { + tc qdisc $1 dev $NDEV ${@:2} +} + +n_child_assert() { + n=$(n_children) + if [ $n -ne $1 ]; then + echo "ERROR ($root): ${@:2}, expected $1 have $n" + ((num_errors++)) + else + ((num_passes++)) + fi +} + + +for root in mq mqprio; do + NDEV=$(make_netdev 1 4) + + opts= + [ $root == "mqprio" ] && opts='hw 0 num_tc 1 map 0 0 0 0 queues 1@0' + + tcq add root handle 100: $root $opts + n_child_assert 4 'Init' + + # All defaults + + for n in 3 2 1 2 3 4 1 4; do + ethtool -L $NDEV combined $n + n_child_assert $n "Change queues to $n while down" + done + + ip link set dev $NDEV up + + for n in 3 2 1 2 3 4 1 4; do + ethtool -L $NDEV combined $n + n_child_assert $n "Change queues to $n while up" + done + + # One real one + tcq replace parent 100:4 handle 204: pfifo_fast + n_child_assert 4 "One real queue" + + ethtool -L $NDEV combined 1 + n_child_assert 2 "One real queue, one default" + + ethtool -L $NDEV combined 4 + n_child_assert 4 "One real queue, rest default" + + # Graft some + tcq replace parent 100:1 handle 204: + n_child_assert 3 "Grafted" + + ethtool -L $NDEV combined 1 + n_child_assert 1 "Grafted, one" + + cleanup_nsim +done + +if [ $num_errors -eq 0 ]; then + echo "PASSED all $((num_passes)) checks" + exit 0 +else + echo "FAILED $num_errors/$((num_errors+num_passes)) checks" + exit 1 +fi diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index f7d84549cc3e..eaf8a04a7ca5 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -156,6 +156,11 @@ create_tcam_skeleton() setup_prepare() { + ip link set $eth0 up + ip link set $eth1 up + ip link set $eth2 up + ip link set $eth3 up + create_tcam_skeleton $eth0 ip link add br0 type bridge @@ -242,9 +247,9 @@ test_vlan_push() tcpdump_cleanup } -test_vlan_modify() +test_vlan_ingress_modify() { - printf "Testing VLAN modification.. " + printf "Testing ingress VLAN modification.. " ip link set br0 type bridge vlan_filtering 1 bridge vlan add dev $eth0 vid 200 @@ -280,6 +285,44 @@ test_vlan_modify() ip link set br0 type bridge vlan_filtering 0 } +test_vlan_egress_modify() +{ + printf "Testing egress VLAN modification.. " + + tc qdisc add dev $eth1 clsact + + ip link set br0 type bridge vlan_filtering 1 + bridge vlan add dev $eth0 vid 200 + bridge vlan add dev $eth1 vid 200 + + tc filter add dev $eth1 egress chain $(ES0) pref 3 \ + protocol 802.1Q flower skip_sw vlan_id 200 vlan_prio 0 \ + action vlan modify id 300 priority 7 + + tcpdump_start $eth2 + + $MZ $eth3.200 -q -c 1 -p 64 -a $eth3_mac -b $eth2_mac -t ip + + sleep 1 + + tcpdump_stop + + if tcpdump_show | grep -q "$eth3_mac > $eth2_mac, .* vlan 300"; then + echo "OK" + else + echo "FAIL" + fi + + tcpdump_cleanup + + tc filter del dev $eth1 egress chain $(ES0) pref 3 + tc qdisc del dev $eth1 clsact + + bridge vlan del dev $eth0 vid 200 + bridge vlan del dev $eth1 vid 200 + ip link set br0 type bridge vlan_filtering 0 +} + test_skbedit_priority() { local num_pkts=100 @@ -304,7 +347,8 @@ trap cleanup EXIT ALL_TESTS=" test_vlan_pop test_vlan_push - test_vlan_modify + test_vlan_ingress_modify + test_vlan_egress_modify test_skbedit_priority " diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 0d293391e9a4..b5a69ad191b0 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2078,6 +2078,7 @@ basic_res() "id 101 index 0 nhid 2 id 101 index 1 nhid 2 id 101 index 2 nhid 1 id 101 index 3 nhid 1" log_test $? 0 "Dump all nexthop buckets in a group" + sleep 0.1 (( $($IP -j nexthop bucket list id 101 | jq '[.[] | select(.bucket.idle_time > 0 and .bucket.idle_time < 2)] | length') == 4 )) diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index e5e2fbeca22e..bf17e485684f 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -39,5 +39,9 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# Flag for tc match, supposed to be skip_sw/skip_hw which means do not process +# filter by software/hardware +TC_FLAG=skip_hw # IPv6 traceroute utility name. TROUTE6=traceroute6 + diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh new file mode 100755 index 000000000000..96c97064f2d3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel without key. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 + sw2_flat_create $ol2 $ul2 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6" +} + +gre_mtu_change() +{ + test_mtu_change +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh new file mode 100755 index 000000000000..ff9fb0db9bd1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel with key. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 key 233 + sw2_flat_create $ol2 $ul2 key 233 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key" +} + +gre_mtu_change() +{ + test_mtu_change +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh new file mode 100755 index 000000000000..12c138785242 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnel with keys. +# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for +# more details. + +ALL_TESTS=" + gre_flat + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_flat_create $ol1 $ul1 ikey 111 okey 222 + sw2_flat_create $ol2 $ul2 ikey 222 okey 111 +} + +gre_flat() +{ + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_flat_destroy $ol2 $ul2 + sw1_flat_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh new file mode 100755 index 000000000000..83b55c30a5c3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 + sw2_hierarchical_create $ol2 $ul2 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh new file mode 100755 index 000000000000..256607916d92 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 key 22 + sw2_hierarchical_create $ol2 $ul2 key 22 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh new file mode 100755 index 000000000000..ad1bcd6334a8 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh @@ -0,0 +1,65 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test IP-in-IP GRE tunnels without key. +# This test uses hierarchical topology for IP tunneling tests. See +# ip6gre_lib.sh for more details. + +ALL_TESTS=" + gre_hier + gre_mtu_change +" + +NUM_NETIFS=6 +source lib.sh +source ip6gre_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + ol1=${NETIFS[p2]} + + ul1=${NETIFS[p3]} + ul2=${NETIFS[p4]} + + ol2=${NETIFS[p5]} + h2=${NETIFS[p6]} + + forwarding_enable + vrf_prepare + h1_create + h2_create + sw1_hierarchical_create $ol1 $ul1 ikey 111 okey 222 + sw2_hierarchical_create $ol2 $ul2 ikey 222 okey 111 +} + +gre_hier() +{ + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey" +} + +gre_mtu_change() +{ + test_mtu_change gre +} + +cleanup() +{ + pre_cleanup + + sw2_hierarchical_destroy $ol2 $ul2 + sw1_hierarchical_destroy $ol1 $ul1 + h2_destroy + h1_destroy + vrf_cleanup + forwarding_restore +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh new file mode 100644 index 000000000000..58a3597037b1 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh @@ -0,0 +1,438 @@ +# SPDX-License-Identifier: GPL-2.0 +#!/bin/bash + +# Handles creation and destruction of IP-in-IP or GRE tunnels over the given +# topology. Supports both flat and hierarchical models. +# +# Flat Model: +# Overlay and underlay share the same VRF. +# SW1 uses default VRF so tunnel has no bound dev. +# SW2 uses non-default VRF tunnel has a bound dev. +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.1/24 | | +# | 2001:db8:1::1/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------+ +# | SW1 | | +# | $ol1 + | +# | 198.51.100.2/24 | +# | 2001:db8:1::2/64 | +# | | +# | + g1a (ip6gre) | +# | loc=2001:db8:3::1 | +# | rem=2001:db8:3::2 --. | +# | tos=inherit | | +# | . | +# | .--------------------- | +# | | | +# | v | +# | + $ul1.111 (vlan) | +# | | 2001:db8:10::1/64 | +# | \ | +# | \____________ | +# | | | +# | VRF default + $ul1 | +# +---------------------|-----------------------+ +# | +# +---------------------|-----------------------+ +# | SW2 | | +# | $ul2 + | +# | ___________| | +# | / | +# | / | +# | + $ul2.111 (vlan) | +# | ^ 2001:db8:10::2/64 | +# | | | +# | | | +# | '----------------------. | +# | + g2a (ip6gre) | | +# | loc=2001:db8:3::2 | | +# | rem=2001:db8:3::1 --' | +# | tos=inherit | +# | | +# | + $ol2 | +# | | 203.0.113.2/24 | +# | VRF v$ol2 | 2001:db8:2::2/64 | +# +---------------------|-----------------------+ +# +---------------------|----------+ +# | H2 | | +# | $h2 + | +# | 203.0.113.1/24 | +# | 2001:db8:2::1/64 | +# +--------------------------------+ +# +# Hierarchical model: +# The tunnel is bound to a device in a different VRF +# +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.1/24 | | +# | 2001:db8:1::1/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------+ +# | SW1 | | +# | +-----------------------|-----------------+ | +# | | $ol1 + | | +# | | 198.51.100.2/24 | | +# | | 2001:db8:1::2/64 | | +# | | | | +# | | + g1a (ip6gre) | | +# | | loc=2001:db8:3::1 | | +# | | rem=2001:db8:3::2 | | +# | | tos=inherit | | +# | | ^ | | +# | | VRF v$ol1 | | | +# | +--------------------|--------------------+ | +# | | | +# | +--------------------|--------------------+ | +# | | VRF v$ul1 | | | +# | | | | | +# | | v | | +# | | dummy1 + | | +# | | 2001:db8:3::1/64 | | +# | | .-----------' | | +# | | | | | +# | | v | | +# | | + $ul1.111 (vlan) | | +# | | | 2001:db8:10::1/64 | | +# | | \ | | +# | | \__________ | | +# | | | | | +# | | + $ul1 | | +# | +---------------------|-------------------+ | +# +-----------------------|---------------------+ +# | +# +-----------------------|---------------------+ +# | SW2 | | +# | +---------------------|-------------------+ | +# | | + $ul2 | | +# | | _____| | | +# | | / | | +# | | / | | +# | | | $ul2.111 (vlan) | | +# | | + 2001:db8:10::2/64 | | +# | | ^ | | +# | | | | | +# | | '------. | | +# | | dummy2 + | | +# | | 2001:db8:3::2/64 | | +# | | ^ | | +# | | | | | +# | | | | | +# | | VRF v$ul2 | | | +# | +---------------------|-------------------+ | +# | | | +# | +---------------------|-------------------+ | +# | | VRF v$ol2 | | | +# | | | | | +# | | v | | +# | | g2a (ip6gre) + | | +# | | loc=2001:db8:3::2 | | +# | | rem=2001:db8:3::1 | | +# | | tos=inherit | | +# | | | | +# | | $ol2 + | | +# | | 203.0.113.2/24 | | | +# | | 2001:db8:2::2/64 | | | +# | +---------------------|-------------------+ | +# +-----------------------|---------------------+ +# | +# +-----------------------|--------+ +# | H2 | | +# | $h2 + | +# | 203.0.113.1/24 | +# | 2001:db8:2::1/64 | +# +--------------------------------+ + +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 198.51.100.1/24 2001:db8:1::1/64 + ip route add vrf v$h1 203.0.113.0/24 via 198.51.100.2 + ip -6 route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2 + ip route del vrf v$h1 203.0.113.0/24 via 198.51.100.2 + simple_if_fini $h1 198.51.100.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 203.0.113.1/24 2001:db8:2::1/64 + ip route add vrf v$h2 198.51.100.0/24 via 203.0.113.2 + ip -6 route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::2 +} + +h2_destroy() +{ + ip -6 route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::2 + ip route del vrf v$h2 198.51.100.0/24 via 203.0.113.2 + simple_if_fini $h2 203.0.113.1/24 2001:db8:2::1/64 +} + +sw1_flat_create() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip link set dev $ol1 up + __addr_add_del $ol1 add 198.51.100.2/24 2001:db8:1::2/64 + + ip link set dev $ul1 up + vlan_create $ul1 111 "" 2001:db8:10::1/64 + + tunnel_create g1a ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit "$@" + ip link set dev g1a up + __addr_add_del g1a add "2001:db8:3::1/128" + + ip -6 route add 2001:db8:3::2/128 via 2001:db8:10::2 + ip route add 203.0.113.0/24 dev g1a + ip -6 route add 2001:db8:2::/64 dev g1a +} + +sw1_flat_destroy() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip -6 route del 2001:db8:2::/64 + ip route del 203.0.113.0/24 + ip -6 route del 2001:db8:3::2/128 via 2001:db8:10::2 + + __simple_if_fini g1a 2001:db8:3::1/128 + tunnel_destroy g1a + + vlan_destroy $ul1 111 + __simple_if_fini $ul1 + __simple_if_fini $ol1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw2_flat_create() +{ + local ol2=$1; shift + local ul2=$1; shift + + simple_if_init $ol2 203.0.113.2/24 2001:db8:2::2/64 + __simple_if_init $ul2 v$ol2 + vlan_create $ul2 111 v$ol2 2001:db8:10::2/64 + + tunnel_create g2a ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \ + ttl inherit dev v$ol2 "$@" + __simple_if_init g2a v$ol2 2001:db8:3::2/128 + + # Replace neighbor to avoid 1 dropped packet due to "unresolved neigh" + ip neigh replace dev $ol2 203.0.113.1 lladdr $(mac_get $h2) + ip -6 neigh replace dev $ol2 2001:db8:2::1 lladdr $(mac_get $h2) + + ip -6 route add vrf v$ol2 2001:db8:3::1/128 via 2001:db8:10::1 + ip route add vrf v$ol2 198.51.100.0/24 dev g2a + ip -6 route add vrf v$ol2 2001:db8:1::/64 dev g2a +} + +sw2_flat_destroy() +{ + local ol2=$1; shift + local ul2=$1; shift + + ip -6 route del vrf v$ol2 2001:db8:2::/64 + ip route del vrf v$ol2 198.51.100.0/24 + ip -6 route del vrf v$ol2 2001:db8:3::1/128 via 2001:db8:10::1 + + __simple_if_fini g2a 2001:db8:3::2/128 + tunnel_destroy g2a + + vlan_destroy $ul2 111 + __simple_if_fini $ul2 + simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64 +} + +sw1_hierarchical_create() +{ + local ol1=$1; shift + local ul1=$1; shift + + simple_if_init $ol1 198.51.100.2/24 2001:db8:1::2/64 + simple_if_init $ul1 + ip link add name dummy1 type dummy + __simple_if_init dummy1 v$ul1 2001:db8:3::1/64 + + vlan_create $ul1 111 v$ul1 2001:db8:10::1/64 + tunnel_create g1a ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + ttl inherit dev dummy1 "$@" + ip link set dev g1a master v$ol1 + + ip -6 route add vrf v$ul1 2001:db8:3::2/128 via 2001:db8:10::2 + ip route add vrf v$ol1 203.0.113.0/24 dev g1a + ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1a +} + +sw1_hierarchical_destroy() +{ + local ol1=$1; shift + local ul1=$1; shift + + ip -6 route del vrf v$ol1 2001:db8:2::/64 + ip route del vrf v$ol1 203.0.113.0/24 + ip -6 route del vrf v$ul1 2001:db8:3::2/128 + + tunnel_destroy g1a + vlan_destroy $ul1 111 + + __simple_if_fini dummy1 2001:db8:3::1/64 + ip link del dev dummy1 + + simple_if_fini $ul1 + simple_if_fini $ol1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw2_hierarchical_create() +{ + local ol2=$1; shift + local ul2=$1; shift + + simple_if_init $ol2 203.0.113.2/24 2001:db8:2::2/64 + simple_if_init $ul2 + + ip link add name dummy2 type dummy + __simple_if_init dummy2 v$ul2 2001:db8:3::2/64 + + vlan_create $ul2 111 v$ul2 2001:db8:10::2/64 + tunnel_create g2a ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \ + ttl inherit dev dummy2 "$@" + ip link set dev g2a master v$ol2 + + # Replace neighbor to avoid 1 dropped packet due to "unresolved neigh" + ip neigh replace dev $ol2 203.0.113.1 lladdr $(mac_get $h2) + ip -6 neigh replace dev $ol2 2001:db8:2::1 lladdr $(mac_get $h2) + + ip -6 route add vrf v$ul2 2001:db8:3::1/128 via 2001:db8:10::1 + ip route add vrf v$ol2 198.51.100.0/24 dev g2a + ip -6 route add vrf v$ol2 2001:db8:1::/64 dev g2a +} + +sw2_hierarchical_destroy() +{ + local ol2=$1; shift + local ul2=$1; shift + + ip -6 route del vrf v$ol2 2001:db8:2::/64 + ip route del vrf v$ol2 198.51.100.0/24 + ip -6 route del vrf v$ul2 2001:db8:3::1/128 + + tunnel_destroy g2a + vlan_destroy $ul2 111 + + __simple_if_fini dummy2 2001:db8:3::2/64 + ip link del dev dummy2 + + simple_if_fini $ul2 + simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64 +} + +test_traffic_ip4ip6() +{ + RET=0 + + h1mac=$(mac_get $h1) + ol1mac=$(mac_get $ol1) + + tc qdisc add dev $ul1 clsact + tc filter add dev $ul1 egress proto all pref 1 handle 101 \ + flower $TC_FLAG action pass + + tc qdisc add dev $ol2 clsact + tc filter add dev $ol2 egress protocol ipv4 pref 1 handle 101 \ + flower $TC_FLAG dst_ip 203.0.113.1 action pass + + $MZ $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 198.51.100.1 \ + -B 203.0.113.1 -t ip -q -d 1msec + + # Check ports after encap and after decap. + tc_check_at_least_x_packets "dev $ul1 egress" 101 1000 + check_err $? "Packets did not go through $ul1, tc_flag = $TC_FLAG" + + tc_check_at_least_x_packets "dev $ol2 egress" 101 1000 + check_err $? "Packets did not go through $ol2, tc_flag = $TC_FLAG" + + log_test "$@" + + tc filter del dev $ol2 egress protocol ipv4 pref 1 handle 101 flower + tc qdisc del dev $ol2 clsact + tc filter del dev $ul1 egress proto all pref 1 handle 101 flower + tc qdisc del dev $ul1 clsact +} + +test_traffic_ip6ip6() +{ + RET=0 + + h1mac=$(mac_get $h1) + ol1mac=$(mac_get $ol1) + + tc qdisc add dev $ul1 clsact + tc filter add dev $ul1 egress proto all pref 1 handle 101 \ + flower $TC_FLAG action pass + + tc qdisc add dev $ol2 clsact + tc filter add dev $ol2 egress protocol ipv6 pref 1 handle 101 \ + flower $TC_FLAG dst_ip 2001:db8:2::1 action pass + + $MZ -6 $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 2001:db8:1::1 \ + -B 2001:db8:2::1 -t ip -q -d 1msec + + # Check ports after encap and after decap. + tc_check_at_least_x_packets "dev $ul1 egress" 101 1000 + check_err $? "Packets did not go through $ul1, tc_flag = $TC_FLAG" + + tc_check_at_least_x_packets "dev $ol2 egress" 101 1000 + check_err $? "Packets did not go through $ol2, tc_flag = $TC_FLAG" + + log_test "$@" + + tc filter del dev $ol2 egress protocol ipv6 pref 1 handle 101 flower + tc qdisc del dev $ol2 clsact + tc filter del dev $ul1 egress proto all pref 1 handle 101 flower + tc qdisc del dev $ul1 clsact +} + +topo_mtu_change() +{ + local mtu=$1 + + ip link set mtu $mtu dev $h1 + ip link set mtu $mtu dev $ol1 + ip link set mtu $mtu dev g1a + ip link set mtu $mtu dev $ul1 + ip link set mtu $mtu dev $ul1.111 + ip link set mtu $mtu dev $h2 + ip link set mtu $mtu dev $ol2 + ip link set mtu $mtu dev g2a + ip link set mtu $mtu dev $ul2 + ip link set mtu $mtu dev $ul2.111 +} + +test_mtu_change() +{ + RET=0 + + ping6_do $h1 2001:db8:2::1 "-s 1800 -w 3" + check_fail $? "ping GRE IPv6 should not pass with packet size 1800" + + RET=0 + + topo_mtu_change 2000 + ping6_do $h1 2001:db8:2::1 "-s 1800 -w 3" + check_err $? + log_test "ping GRE IPv6, packet size 1800 after MTU change" +} diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh index 0e18e8be6e2a..bce8bb8d2b6f 100644 --- a/tools/testing/selftests/net/forwarding/tc_common.sh +++ b/tools/testing/selftests/net/forwarding/tc_common.sh @@ -16,6 +16,16 @@ tc_check_packets() tc_rule_handle_stats_get "$id" "$handle" > /dev/null } +tc_check_at_least_x_packets() +{ + local id=$1 + local handle=$2 + local count=$3 + + busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $count" \ + tc_rule_handle_stats_get "$id" "$handle" > /dev/null +} + tc_check_packets_hitting() { local id=$1 diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index a2489ec398fe..a2b9fad5a9a6 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -6,7 +6,7 @@ # This script evaluates the IOAM insertion for IPv6 by checking the IOAM data # consistency directly inside packets on the receiver side. Tests are divided # into three categories: OUTPUT (evaluates the IOAM processing by the sender), -# INPUT (evaluates the IOAM processing by the receiver) and GLOBAL (evaluates +# INPUT (evaluates the IOAM processing by a receiver) and GLOBAL (evaluates # wider use cases that do not fall into the other two categories). Both OUTPUT # and INPUT tests only use a two-node topology (alpha and beta), while GLOBAL # tests use the entire three-node topology (alpha, beta, gamma). Each test is @@ -200,7 +200,7 @@ check_kernel_compatibility() ip -netns ioam-tmp-node link set veth0 up ip -netns ioam-tmp-node link set veth1 up - ip -netns ioam-tmp-node ioam namespace add 0 &>/dev/null + ip -netns ioam-tmp-node ioam namespace add 0 ns_ad=$? ip -netns ioam-tmp-node ioam namespace show | grep -q "namespace 0" @@ -214,11 +214,11 @@ check_kernel_compatibility() exit 1 fi - ip -netns ioam-tmp-node route add db02::/64 encap ioam6 trace prealloc \ - type 0x800000 ns 0 size 4 dev veth0 &>/dev/null + ip -netns ioam-tmp-node route add db02::/64 encap ioam6 mode inline \ + trace prealloc type 0x800000 ns 0 size 4 dev veth0 tr_ad=$? - ip -netns ioam-tmp-node -6 route | grep -q "encap ioam6 trace" + ip -netns ioam-tmp-node -6 route | grep -q "encap ioam6" tr_sh=$? if [[ $tr_ad != 0 || $tr_sh != 0 ]] @@ -232,6 +232,30 @@ check_kernel_compatibility() ip link del veth0 2>/dev/null || true ip netns del ioam-tmp-node || true + + lsmod | grep -q "ip6_tunnel" + ip6tnl_loaded=$? + + if [ $ip6tnl_loaded = 0 ] + then + encap_tests=0 + else + modprobe ip6_tunnel &>/dev/null + lsmod | grep -q "ip6_tunnel" + encap_tests=$? + + if [ $encap_tests != 0 ] + then + ip a | grep -q "ip6tnl0" + encap_tests=$? + + if [ $encap_tests != 0 ] + then + echo "Note: ip6_tunnel not found neither as a module nor inside the" \ + "kernel, tests that require it (encap mode) will be omitted" + fi + fi + fi } cleanup() @@ -242,6 +266,11 @@ cleanup() ip netns del ioam-node-alpha || true ip netns del ioam-node-beta || true ip netns del ioam-node-gamma || true + + if [ $ip6tnl_loaded != 0 ] + then + modprobe -r ip6_tunnel 2>/dev/null || true + fi } setup() @@ -329,6 +358,12 @@ log_test_failed() printf "TEST: %-60s [FAIL]\n" "${desc}" } +log_results() +{ + echo "- Tests passed: ${npassed}" + echo "- Tests failed: ${nfailed}" +} + run_test() { local name=$1 @@ -349,17 +384,27 @@ run_test() ip netns exec $node_src ping6 -t 64 -c 1 -W 1 $ip6_dst &>/dev/null if [ $? != 0 ] then + nfailed=$((nfailed+1)) log_test_failed "${desc}" kill -2 $spid &>/dev/null else wait $spid - [ $? = 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}" + if [ $? = 0 ] + then + npassed=$((npassed+1)) + log_test_passed "${desc}" + else + nfailed=$((nfailed+1)) + log_test_failed "${desc}" + fi fi } run() { echo + printf "%0.s-" {1..74} + echo echo "OUTPUT tests" printf "%0.s-" {1..74} echo @@ -369,7 +414,8 @@ run() for t in $TESTS_OUTPUT do - $t + $t "inline" + [ $encap_tests = 0 ] && $t "encap" done # clean OUTPUT settings @@ -378,6 +424,8 @@ run() echo + printf "%0.s-" {1..74} + echo echo "INPUT tests" printf "%0.s-" {1..74} echo @@ -387,7 +435,8 @@ run() for t in $TESTS_INPUT do - $t + $t "inline" + [ $encap_tests = 0 ] && $t "encap" done # clean INPUT settings @@ -396,7 +445,8 @@ run() ip -netns ioam-node-alpha ioam namespace set 123 schema ${ALPHA[8]} ip -netns ioam-node-alpha route change db01::/64 dev veth0 - + echo + printf "%0.s-" {1..74} echo echo "GLOBAL tests" printf "%0.s-" {1..74} @@ -404,8 +454,12 @@ run() for t in $TESTS_GLOBAL do - $t + $t "inline" + [ $encap_tests = 0 ] && $t "encap" done + + echo + log_results } bit2type=( @@ -431,11 +485,16 @@ out_undef_ns() ############################################################################## local desc="Unknown IOAM namespace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0x800000 ns 0 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0x800000 0 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0x800000 ns 0 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0x800000 0 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } out_no_room() @@ -446,11 +505,16 @@ out_no_room() ############################################################################## local desc="Missing trace room" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xc00000 ns 123 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xc00000 ns 123 size 4 dev veth0 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xc00000 123 + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xc00000 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } out_bits() @@ -465,10 +529,13 @@ out_bits() local tmp=${bit2size[22]} bit2size[22]=$(( $tmp + ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) )) + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + for i in {0..22} do - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ - prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ dev veth0 &>/dev/null local cmd_res=$? @@ -485,11 +552,13 @@ out_bits() log_test_failed "$descr" fi else - run_test "out_bit$i" "$descr" ioam-node-alpha ioam-node-beta \ - db01::2 db01::1 veth0 ${bit2type[$i]} 123 + run_test "out_bit$i" "$descr ($1 mode)" ioam-node-alpha \ + ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 fi done + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down + bit2size[22]=$tmp } @@ -501,11 +570,16 @@ out_full_supp_trace() ############################################################################## local desc="Full supported trace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xfff002 ns 123 size 100 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xfff002 123 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xfff002 ns 123 size 100 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xfff002 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } @@ -526,11 +600,16 @@ in_undef_ns() ############################################################################## local desc="Unknown IOAM namespace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0x800000 ns 0 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0x800000 ns 0 size 4 dev veth0 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0x800000 0 + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0x800000 0 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } in_no_room() @@ -541,11 +620,16 @@ in_no_room() ############################################################################## local desc="Missing trace room" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xc00000 ns 123 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xc00000 ns 123 size 4 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xc00000 123 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xc00000 123 + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } in_bits() @@ -560,15 +644,21 @@ in_bits() local tmp=${bit2size[22]} bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) )) + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + for i in {0..11} {22..22} do - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \ - prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0 + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \ + dev veth0 - run_test "in_bit$i" "${desc/<n>/$i}" ioam-node-alpha ioam-node-beta \ - db01::2 db01::1 veth0 ${bit2type[$i]} 123 + run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" ioam-node-alpha \ + ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 done + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down + bit2size[22]=$tmp } @@ -585,11 +675,16 @@ in_oflag() # back the IOAM namespace that was previously configured on the sender. ip -netns ioam-node-alpha ioam namespace add 123 - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xc00000 ns 123 size 4 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xc00000 ns 123 size 4 dev veth0 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xc00000 123 + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xc00000 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down # And we clean the exception for this test to get things back to normal for # other INPUT tests @@ -604,11 +699,16 @@ in_full_supp_trace() ############################################################################## local desc="Full supported trace" - ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \ - type 0xfff002 ns 123 size 80 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up + + ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \ + trace prealloc type 0xfff002 ns 123 size 80 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \ + db01::2 db01::1 veth0 0xfff002 123 - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \ - db01::1 veth0 0xfff002 123 + [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down } @@ -627,11 +727,16 @@ fwd_full_supp_trace() ############################################################################## local desc="Forward - Full supported trace" - ip -netns ioam-node-alpha route change db02::/64 encap ioam6 trace prealloc \ - type 0xfff002 ns 123 size 244 via db01::1 dev veth0 + [ "$1" = "encap" ] && mode="$1 tundst db02::2" || mode="$1" + [ "$1" = "encap" ] && ip -netns ioam-node-gamma link set ip6tnl0 up - run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-gamma db01::2 \ - db02::2 veth0 0xfff002 123 + ip -netns ioam-node-alpha route change db02::/64 encap ioam6 mode $mode \ + trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0 + + run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-gamma \ + db01::2 db02::2 veth0 0xfff002 123 + + [ "$1" = "encap" ] && ip -netns ioam-node-gamma link set ip6tnl0 down } @@ -641,6 +746,9 @@ fwd_full_supp_trace() # # ################################################################################ +npassed=0 +nfailed=0 + if [ "$(id -u)" -ne 0 ] then echo "SKIP: Need root privileges" diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore index 260336d5f0b1..7569d892967a 100644 --- a/tools/testing/selftests/net/mptcp/.gitignore +++ b/tools/testing/selftests/net/mptcp/.gitignore @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only mptcp_connect +mptcp_sockopt pm_nl_ctl *.pcap diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index f1464f09b080..bbf4e448bad9 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -8,7 +8,7 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh -TEST_GEN_FILES = mptcp_connect pm_nl_ctl +TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt TEST_FILES := settings diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 255793c5ac4f..293d349e21fe 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -945,12 +945,15 @@ subflows_tests() # 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 # 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 @@ -973,7 +976,7 @@ subflows_tests() run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows" 2 2 2 - # multiple subflows limited by serverf + # 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 diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c new file mode 100644 index 000000000000..417b11cafafe --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -0,0 +1,683 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <assert.h> +#include <errno.h> +#include <limits.h> +#include <string.h> +#include <stdarg.h> +#include <stdbool.h> +#include <stdint.h> +#include <inttypes.h> +#include <stdio.h> +#include <stdlib.h> +#include <strings.h> +#include <unistd.h> + +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include <netdb.h> +#include <netinet/in.h> + +#include <linux/tcp.h> + +static int pf = AF_INET; + +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif +#ifndef SOL_MPTCP +#define SOL_MPTCP 284 +#endif + +#ifndef MPTCP_INFO +struct mptcp_info { + __u8 mptcpi_subflows; + __u8 mptcpi_add_addr_signal; + __u8 mptcpi_add_addr_accepted; + __u8 mptcpi_subflows_max; + __u8 mptcpi_add_addr_signal_max; + __u8 mptcpi_add_addr_accepted_max; + __u32 mptcpi_flags; + __u32 mptcpi_token; + __u64 mptcpi_write_seq; + __u64 mptcpi_snd_una; + __u64 mptcpi_rcv_nxt; + __u8 mptcpi_local_addr_used; + __u8 mptcpi_local_addr_max; + __u8 mptcpi_csum_enabled; +}; + +struct mptcp_subflow_data { + __u32 size_subflow_data; /* size of this structure in userspace */ + __u32 num_subflows; /* must be 0, set by kernel */ + __u32 size_kernel; /* must be 0, set by kernel */ + __u32 size_user; /* size of one element in data[] */ +} __attribute__((aligned(8))); + +struct mptcp_subflow_addrs { + union { + __kernel_sa_family_t sa_family; + struct sockaddr sa_local; + struct sockaddr_in sin_local; + struct sockaddr_in6 sin6_local; + struct __kernel_sockaddr_storage ss_local; + }; + union { + struct sockaddr sa_remote; + struct sockaddr_in sin_remote; + struct sockaddr_in6 sin6_remote; + struct __kernel_sockaddr_storage ss_remote; + }; +}; + +#define MPTCP_INFO 1 +#define MPTCP_TCPINFO 2 +#define MPTCP_SUBFLOW_ADDRS 3 +#endif + +struct so_state { + struct mptcp_info mi; + uint64_t mptcpi_rcv_delta; + uint64_t tcpi_rcv_delta; +}; + +static void die_perror(const char *msg) +{ + perror(msg); + exit(1); +} + +static void die_usage(int r) +{ + fprintf(stderr, "Usage: mptcp_sockopt [-6]\n"); + exit(r); +} + +static void xerror(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + fputc('\n', stderr); + exit(1); +} + +static const char *getxinfo_strerr(int err) +{ + if (err == EAI_SYSTEM) + return strerror(errno); + + return gai_strerror(err); +} + +static void xgetaddrinfo(const char *node, const char *service, + const struct addrinfo *hints, + struct addrinfo **res) +{ + int err = getaddrinfo(node, service, hints, res); + + if (err) { + const char *errstr = getxinfo_strerr(err); + + fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n", + node ? node : "", service ? service : "", errstr); + exit(1); + } +} + +static int sock_listen_mptcp(const char * const listenaddr, + const char * const port) +{ + int sock; + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + .ai_flags = AI_PASSIVE | AI_NUMERICHOST + }; + + hints.ai_family = pf; + + struct addrinfo *a, *addr; + int one = 1; + + xgetaddrinfo(listenaddr, port, &hints, &addr); + hints.ai_family = pf; + + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, IPPROTO_MPTCP); + if (sock < 0) + continue; + + if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one, + sizeof(one))) + perror("setsockopt"); + + if (bind(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + perror("bind"); + close(sock); + sock = -1; + } + + freeaddrinfo(addr); + + if (sock < 0) + xerror("could not create listen socket"); + + if (listen(sock, 20)) + die_perror("listen"); + + return sock; +} + +static int sock_connect_mptcp(const char * const remoteaddr, + const char * const port, int proto) +{ + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + }; + struct addrinfo *a, *addr; + int sock = -1; + + hints.ai_family = pf; + + xgetaddrinfo(remoteaddr, port, &hints, &addr); + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, proto); + if (sock < 0) + continue; + + if (connect(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + die_perror("connect"); + } + + if (sock < 0) + xerror("could not create connect socket"); + + freeaddrinfo(addr); + return sock; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "h6")) != -1) { + switch (c) { + case 'h': + die_usage(0); + break; + case '6': + pf = AF_INET6; + break; + default: + die_usage(1); + break; + } + } +} + +static void do_getsockopt_bogus_sf_data(int fd, int optname) +{ + struct mptcp_subflow_data good_data; + struct bogus_data { + struct mptcp_subflow_data d; + char buf[2]; + } bd; + socklen_t olen, _olen; + int ret; + + memset(&bd, 0, sizeof(bd)); + memset(&good_data, 0, sizeof(good_data)); + + olen = sizeof(good_data); + good_data.size_subflow_data = olen; + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* 0 size_subflow_data */ + assert(olen == sizeof(good_data)); + + bd.d = good_data; + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret == 0); + assert(olen == sizeof(good_data)); + assert(bd.d.num_subflows == 1); + assert(bd.d.size_kernel > 0); + assert(bd.d.size_user == 0); + + bd.d = good_data; + _olen = rand() % olen; + olen = _olen; + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* bogus olen */ + assert(olen == _olen); /* must be unchanged */ + + bd.d = good_data; + olen = sizeof(good_data); + bd.d.size_kernel = 1; + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* size_kernel not 0 */ + + bd.d = good_data; + olen = sizeof(good_data); + bd.d.num_subflows = 1; + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* num_subflows not 0 */ + + /* forward compat check: larger struct mptcp_subflow_data on 'old' kernel */ + bd.d = good_data; + olen = sizeof(bd); + bd.d.size_subflow_data = sizeof(bd); + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret == 0); + + /* olen must be truncated to real data size filled by kernel: */ + assert(olen == sizeof(good_data)); + + assert(bd.d.size_subflow_data == sizeof(bd)); + + bd.d = good_data; + bd.d.size_subflow_data += 1; + bd.d.size_user = 1; + olen = bd.d.size_subflow_data + 1; + _olen = olen; + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &_olen); + assert(ret == 0); + + /* no truncation, kernel should have filled 1 byte of optname payload in buf[1]: */ + assert(olen == _olen); + + assert(bd.d.size_subflow_data == sizeof(good_data) + 1); + assert(bd.buf[0] == 0); +} + +static void do_getsockopt_mptcp_info(struct so_state *s, int fd, size_t w) +{ + struct mptcp_info i; + socklen_t olen; + int ret; + + olen = sizeof(i); + ret = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &i, &olen); + + if (ret < 0) + die_perror("getsockopt MPTCP_INFO"); + + assert(olen == sizeof(i)); + + if (s->mi.mptcpi_write_seq == 0) + s->mi = i; + + assert(s->mi.mptcpi_write_seq + w == i.mptcpi_write_seq); + + s->mptcpi_rcv_delta = i.mptcpi_rcv_nxt - s->mi.mptcpi_rcv_nxt; +} + +static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t w) +{ + struct my_tcp_info { + struct mptcp_subflow_data d; + struct tcp_info ti[2]; + } ti; + int ret, tries = 5; + socklen_t olen; + + do { + memset(&ti, 0, sizeof(ti)); + + ti.d.size_subflow_data = sizeof(struct mptcp_subflow_data); + ti.d.size_user = sizeof(struct tcp_info); + olen = sizeof(ti); + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_TCPINFO, &ti, &olen); + if (ret < 0) + xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)"); + + assert(olen <= sizeof(ti)); + assert(ti.d.size_user == ti.d.size_kernel); + assert(ti.d.size_user == sizeof(struct tcp_info)); + assert(ti.d.num_subflows == 1); + + assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); + olen -= sizeof(struct mptcp_subflow_data); + assert(olen == sizeof(struct tcp_info)); + + if (ti.ti[0].tcpi_bytes_sent == w && + ti.ti[0].tcpi_bytes_received == r) + goto done; + + if (r == 0 && ti.ti[0].tcpi_bytes_sent == w && + ti.ti[0].tcpi_bytes_received) { + s->tcpi_rcv_delta = ti.ti[0].tcpi_bytes_received; + goto done; + } + + /* wait and repeat, might be that tx is still ongoing */ + sleep(1); + } while (tries-- > 0); + + xerror("tcpi_bytes_sent %" PRIu64 ", want %zu. tcpi_bytes_received %" PRIu64 ", want %zu", + ti.ti[0].tcpi_bytes_sent, w, ti.ti[0].tcpi_bytes_received, r); + +done: + do_getsockopt_bogus_sf_data(fd, MPTCP_TCPINFO); +} + +static void do_getsockopt_subflow_addrs(int fd) +{ + struct sockaddr_storage remote, local; + socklen_t olen, rlen, llen; + int ret; + struct my_addrs { + struct mptcp_subflow_data d; + struct mptcp_subflow_addrs addr[2]; + } addrs; + + memset(&addrs, 0, sizeof(addrs)); + memset(&local, 0, sizeof(local)); + memset(&remote, 0, sizeof(remote)); + + addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data); + addrs.d.size_user = sizeof(struct mptcp_subflow_addrs); + olen = sizeof(addrs); + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen); + if (ret < 0) + die_perror("getsockopt MPTCP_SUBFLOW_ADDRS"); + + assert(olen <= sizeof(addrs)); + assert(addrs.d.size_user == addrs.d.size_kernel); + assert(addrs.d.size_user == sizeof(struct mptcp_subflow_addrs)); + assert(addrs.d.num_subflows == 1); + + assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); + olen -= sizeof(struct mptcp_subflow_data); + assert(olen == sizeof(struct mptcp_subflow_addrs)); + + llen = sizeof(local); + ret = getsockname(fd, (struct sockaddr *)&local, &llen); + if (ret < 0) + die_perror("getsockname"); + rlen = sizeof(remote); + ret = getpeername(fd, (struct sockaddr *)&remote, &rlen); + if (ret < 0) + die_perror("getpeername"); + + assert(rlen > 0); + assert(rlen == llen); + + assert(remote.ss_family == local.ss_family); + + assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) == 0); + assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) == 0); + + memset(&addrs, 0, sizeof(addrs)); + + addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data); + addrs.d.size_user = sizeof(sa_family_t); + olen = sizeof(addrs.d) + sizeof(sa_family_t); + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen); + assert(ret == 0); + assert(olen == sizeof(addrs.d) + sizeof(sa_family_t)); + + assert(addrs.addr[0].sa_family == pf); + assert(addrs.addr[0].sa_family == local.ss_family); + + assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) != 0); + assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) != 0); + + do_getsockopt_bogus_sf_data(fd, MPTCP_SUBFLOW_ADDRS); +} + +static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w) +{ + do_getsockopt_mptcp_info(s, fd, w); + + do_getsockopt_tcp_info(s, fd, r, w); + + do_getsockopt_subflow_addrs(fd); +} + +static void connect_one_server(int fd, int pipefd) +{ + char buf[4096], buf2[4096]; + size_t len, i, total; + struct so_state s; + bool eof = false; + ssize_t ret; + + memset(&s, 0, sizeof(s)); + + len = rand() % (sizeof(buf) - 1); + + if (len < 128) + len = 128; + + for (i = 0; i < len ; i++) { + buf[i] = rand() % 26; + buf[i] += 'A'; + } + + buf[i] = '\n'; + + do_getsockopts(&s, fd, 0, 0); + + /* un-block server */ + ret = read(pipefd, buf2, 4); + assert(ret == 4); + close(pipefd); + + assert(strncmp(buf2, "xmit", 4) == 0); + + ret = write(fd, buf, len); + if (ret < 0) + die_perror("write"); + + if (ret != (ssize_t)len) + xerror("short write"); + + total = 0; + do { + ret = read(fd, buf2 + total, sizeof(buf2) - total); + if (ret < 0) + die_perror("read"); + if (ret == 0) { + eof = true; + break; + } + + total += ret; + } while (total < len); + + if (total != len) + xerror("total %lu, len %lu eof %d\n", total, len, eof); + + if (memcmp(buf, buf2, len)) + xerror("data corruption"); + + if (s.tcpi_rcv_delta) + assert(s.tcpi_rcv_delta <= total); + + do_getsockopts(&s, fd, ret, ret); + + if (eof) + total += 1; /* sequence advances due to FIN */ + + assert(s.mptcpi_rcv_delta == (uint64_t)total); + close(fd); +} + +static void process_one_client(int fd, int pipefd) +{ + ssize_t ret, ret2, ret3; + struct so_state s; + char buf[4096]; + + memset(&s, 0, sizeof(s)); + do_getsockopts(&s, fd, 0, 0); + + ret = write(pipefd, "xmit", 4); + assert(ret == 4); + + ret = read(fd, buf, sizeof(buf)); + if (ret < 0) + die_perror("read"); + + assert(s.mptcpi_rcv_delta <= (uint64_t)ret); + + if (s.tcpi_rcv_delta) + assert(s.tcpi_rcv_delta == (uint64_t)ret); + + ret2 = write(fd, buf, ret); + if (ret2 < 0) + die_perror("write"); + + /* wait for hangup */ + ret3 = read(fd, buf, 1); + if (ret3 != 0) + xerror("expected EOF, got %lu", ret3); + + do_getsockopts(&s, fd, ret, ret2); + if (s.mptcpi_rcv_delta != (uint64_t)ret + 1) + xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret); + close(fd); +} + +static int xaccept(int s) +{ + int fd = accept(s, NULL, 0); + + if (fd < 0) + die_perror("accept"); + + return fd; +} + +static int server(int pipefd) +{ + int fd = -1, r; + + switch (pf) { + case AF_INET: + fd = sock_listen_mptcp("127.0.0.1", "15432"); + break; + case AF_INET6: + fd = sock_listen_mptcp("::1", "15432"); + break; + default: + xerror("Unknown pf %d\n", pf); + break; + } + + r = write(pipefd, "conn", 4); + assert(r == 4); + + alarm(15); + r = xaccept(fd); + + process_one_client(r, pipefd); + + return 0; +} + +static int client(int pipefd) +{ + int fd = -1; + + alarm(15); + + switch (pf) { + case AF_INET: + fd = sock_connect_mptcp("127.0.0.1", "15432", IPPROTO_MPTCP); + break; + case AF_INET6: + fd = sock_connect_mptcp("::1", "15432", IPPROTO_MPTCP); + break; + default: + xerror("Unknown pf %d\n", pf); + } + + connect_one_server(fd, pipefd); + + return 0; +} + +static pid_t xfork(void) +{ + pid_t p = fork(); + + if (p < 0) + die_perror("fork"); + + return p; +} + +static int rcheck(int wstatus, const char *what) +{ + if (WIFEXITED(wstatus)) { + if (WEXITSTATUS(wstatus) == 0) + return 0; + fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus)); + return WEXITSTATUS(wstatus); + } else if (WIFSIGNALED(wstatus)) { + xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus)); + } else if (WIFSTOPPED(wstatus)) { + xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus)); + } + + return 111; +} + +int main(int argc, char *argv[]) +{ + int e1, e2, wstatus; + pid_t s, c, ret; + int pipefds[2]; + + parse_opts(argc, argv); + + e1 = pipe(pipefds); + if (e1 < 0) + die_perror("pipe"); + + s = xfork(); + if (s == 0) + return server(pipefds[1]); + + close(pipefds[1]); + + /* wait until server bound a socket */ + e1 = read(pipefds[0], &e1, 4); + assert(e1 == 4); + + c = xfork(); + if (c == 0) + return client(pipefds[0]); + + close(pipefds[0]); + + ret = waitpid(s, &wstatus, 0); + if (ret == -1) + die_perror("waitpid"); + e1 = rcheck(wstatus, "server"); + ret = waitpid(c, &wstatus, 0); + if (ret == -1) + die_perror("waitpid"); + e2 = rcheck(wstatus, "client"); + + return e1 ? e1 : e2; +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 1579e471a5e7..41de643788b8 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -239,12 +239,35 @@ make_file() echo "Created $name (size $size KB) containing data sent by $who" } +do_mptcp_sockopt_tests() +{ + local lret=0 + + ./mptcp_sockopt + lret=$? + + if [ $lret -ne 0 ]; then + echo "FAIL: SOL_MPTCP getsockopt" 1>&2 + ret=$lret + return + fi + + ./mptcp_sockopt -6 + lret=$? + + if [ $lret -ne 0 ]; then + echo "FAIL: SOL_MPTCP getsockopt (ipv6)" 1>&2 + ret=$lret + return + fi +} + run_tests() { listener_ns="$1" connector_ns="$2" connect_addr="$3" - lret=0 + local lret=0 do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} @@ -268,9 +291,13 @@ trap cleanup EXIT run_tests $ns1 $ns2 10.0.1.1 run_tests $ns1 $ns2 dead:beef:1::1 - if [ $ret -eq 0 ];then echo "PASS: all packets had packet mark set" fi +do_mptcp_sockopt_tests +if [ $ret -eq 0 ];then + echo "PASS: SOL_MPTCP getsockopt has expected information" +fi + exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 3c741abe034e..cbacf9f6538b 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -70,7 +70,7 @@ check() check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list" check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "defaults limits" +subflows 2" "defaults limits" ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo @@ -118,11 +118,11 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs" ip netns exec $ns1 ./pm_nl_ctl limits 9 1 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "rcv addrs above hard limit" +subflows 2" "rcv addrs above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 1 9 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0 -subflows 0" "subflows above hard limit" +subflows 2" "subflows above hard limit" ip netns exec $ns1 ./pm_nl_ctl limits 8 8 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8 diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 97fceb9be9ed..d3047e251fe9 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -29,6 +29,8 @@ struct tls_crypto_info_keys { union { struct tls12_crypto_info_aes_gcm_128 aes128; struct tls12_crypto_info_chacha20_poly1305 chacha20; + struct tls12_crypto_info_sm4_gcm sm4gcm; + struct tls12_crypto_info_sm4_ccm sm4ccm; }; size_t len; }; @@ -49,6 +51,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, tls12->aes128.info.version = tls_version; tls12->aes128.info.cipher_type = cipher_type; break; + case TLS_CIPHER_SM4_GCM: + tls12->len = sizeof(struct tls12_crypto_info_sm4_gcm); + tls12->sm4gcm.info.version = tls_version; + tls12->sm4gcm.info.cipher_type = cipher_type; + break; + case TLS_CIPHER_SM4_CCM: + tls12->len = sizeof(struct tls12_crypto_info_sm4_ccm); + tls12->sm4ccm.info.version = tls_version; + tls12->sm4ccm.info.cipher_type = cipher_type; + break; default: break; } @@ -148,13 +160,13 @@ FIXTURE_VARIANT(tls) uint16_t cipher_type; }; -FIXTURE_VARIANT_ADD(tls, 12_gcm) +FIXTURE_VARIANT_ADD(tls, 12_aes_gcm) { .tls_version = TLS_1_2_VERSION, .cipher_type = TLS_CIPHER_AES_GCM_128, }; -FIXTURE_VARIANT_ADD(tls, 13_gcm) +FIXTURE_VARIANT_ADD(tls, 13_aes_gcm) { .tls_version = TLS_1_3_VERSION, .cipher_type = TLS_CIPHER_AES_GCM_128, @@ -172,6 +184,18 @@ FIXTURE_VARIANT_ADD(tls, 13_chacha) .cipher_type = TLS_CIPHER_CHACHA20_POLY1305, }; +FIXTURE_VARIANT_ADD(tls, 13_sm4_gcm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_SM4_GCM, +}; + +FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_SM4_CCM, +}; + FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; |