diff options
Diffstat (limited to 'tools/lib/bpf')
37 files changed, 3048 insertions, 1112 deletions
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 0da84cb9e66d..f02725b123b3 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -5,3 +5,4 @@ TAGS tags cscope.* /bpf_helper_defs.h +fixdep diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index e2cd558ca0b4..c80204bb72a2 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,4 +1,4 @@ -libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ +libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_utils.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ usdt.o zip.o elf.o features.o btf_iter.o btf_relocate.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 2cf892774346..168140f8e646 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -53,15 +53,9 @@ include $(srctree)/tools/scripts/Makefile.include # copy a bit from Linux kbuild -ifeq ("$(origin V)", "command line") - VERBOSE = $(V) -endif -ifndef VERBOSE - VERBOSE = 0 -endif - INCLUDES = -I$(or $(OUTPUT),.) \ - -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi + -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/arch/$(SRCARCH)/include export prefix libdir src obj @@ -95,12 +89,6 @@ override CFLAGS += $(CLANG_CROSS_FLAGS) # flags specific for shared library SHLIB_FLAGS := -DSHARED -fPIC -ifeq ($(VERBOSE),1) - Q = -else - Q = @ -endif - # Disable command line variables (CFLAGS) override from top # level Makefile (perf), otherwise build Makefile will get # the same command line setup. @@ -108,6 +96,8 @@ MAKEOVERRIDES= all: +OUTPUT ?= ./ +OUTPUT := $(abspath $(OUTPUT))/ export srctree OUTPUT CC LD CFLAGS V include $(srctree)/tools/build/Makefile.include @@ -141,7 +131,10 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force $(BPF_GENERATED) +$(SHARED_OBJDIR) $(STATIC_OBJDIR): + $(Q)mkdir -p $@ + +$(BPF_IN_SHARED): force $(BPF_GENERATED) | $(SHARED_OBJDIR) @(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 @@ -151,9 +144,11 @@ $(BPF_IN_SHARED): force $(BPF_GENERATED) @(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \ (diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \ 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 + $(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= OUTPUT=$(SHARED_OBJDIR) $(SHARED_OBJDIR)fixdep $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force $(BPF_GENERATED) +$(BPF_IN_STATIC): force $(BPF_GENERATED) | $(STATIC_OBJDIR) + $(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= OUTPUT=$(STATIC_OBJDIR) $(STATIC_OBJDIR)fixdep $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h @@ -263,7 +258,7 @@ install_pkgconfig: $(PC_FILE) install: install_lib install_pkgconfig install_headers -clean: +clean: fixdep-clean $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED) \ $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 2a4c71501a17..b66f5fbfbbb2 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -154,7 +154,7 @@ int bump_rlimit_memlock(void) memlock_bumped = true; - /* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */ + /* zero memlock_rlim disables auto-bumping RLIMIT_MEMLOCK */ if (memlock_rlim == 0) return 0; @@ -172,7 +172,7 @@ int bpf_map_create(enum bpf_map_type map_type, __u32 max_entries, const struct bpf_map_create_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd); + const size_t attr_sz = offsetofend(union bpf_attr, excl_prog_hash_size); union bpf_attr attr; int fd; @@ -203,6 +203,8 @@ int bpf_map_create(enum bpf_map_type map_type, attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); attr.map_token_fd = OPTS_GET(opts, token_fd, 0); + attr.excl_prog_hash = ptr_to_u64(OPTS_GET(opts, excl_prog_hash, NULL)); + attr.excl_prog_hash_size = OPTS_GET(opts, excl_prog_hash_size, 0); fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); @@ -238,7 +240,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd); + const size_t attr_sz = offsetofend(union bpf_attr, keyring_id); void *finfo = NULL, *linfo = NULL; const char *func_info, *line_info; __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; @@ -311,6 +313,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.line_info_cnt = OPTS_GET(opts, line_info_cnt, 0); attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL)); + attr.fd_array_cnt = OPTS_GET(opts, fd_array_cnt, 0); if (log_level) { attr.log_buf = ptr_to_u64(log_buf); @@ -776,6 +779,7 @@ int bpf_link_create(int prog_fd, int target_fd, return libbpf_err(-EINVAL); break; case BPF_TRACE_UPROBE_MULTI: + case BPF_TRACE_UPROBE_SESSION: attr.link_create.uprobe_multi.flags = OPTS_GET(opts, uprobe_multi.flags, 0); attr.link_create.uprobe_multi.cnt = OPTS_GET(opts, uprobe_multi.cnt, 0); attr.link_create.uprobe_multi.path = ptr_to_u64(OPTS_GET(opts, uprobe_multi.path, 0)); @@ -835,6 +839,50 @@ int bpf_link_create(int prog_fd, int target_fd, if (!OPTS_ZEROED(opts, netkit)) return libbpf_err(-EINVAL); break; + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_INET_SOCK_RELEASE: + case BPF_CGROUP_INET4_BIND: + case BPF_CGROUP_INET6_BIND: + case BPF_CGROUP_INET4_POST_BIND: + case BPF_CGROUP_INET6_POST_BIND: + case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: + case BPF_CGROUP_UDP4_RECVMSG: + case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: + case BPF_CGROUP_SOCK_OPS: + case BPF_CGROUP_DEVICE: + case BPF_CGROUP_SYSCTL: + case BPF_CGROUP_GETSOCKOPT: + case BPF_CGROUP_SETSOCKOPT: + case BPF_LSM_CGROUP: + relative_fd = OPTS_GET(opts, cgroup.relative_fd, 0); + relative_id = OPTS_GET(opts, cgroup.relative_id, 0); + if (relative_fd && relative_id) + return libbpf_err(-EINVAL); + if (relative_id) { + attr.link_create.cgroup.relative_id = relative_id; + attr.link_create.flags |= BPF_F_ID; + } else { + attr.link_create.cgroup.relative_fd = relative_fd; + } + attr.link_create.cgroup.expected_revision = + OPTS_GET(opts, cgroup.expected_revision, 0); + if (!OPTS_ZEROED(opts, cgroup)) + return libbpf_err(-EINVAL); + break; default: if (!OPTS_ZEROED(opts, flags)) return libbpf_err(-EINVAL); @@ -1095,7 +1143,7 @@ int bpf_map_get_fd_by_id(__u32 id) int bpf_btf_get_fd_by_id_opts(__u32 id, const struct bpf_get_fd_by_id_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, open_flags); + const size_t attr_sz = offsetofend(union bpf_attr, fd_by_id_token_fd); union bpf_attr attr; int fd; @@ -1105,6 +1153,7 @@ int bpf_btf_get_fd_by_id_opts(__u32 id, memset(&attr, 0, attr_sz); attr.btf_id = id; attr.open_flags = OPTS_GET(opts, open_flags, 0); + attr.fd_by_id_token_fd = OPTS_GET(opts, token_fd, 0); fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); @@ -1328,3 +1377,23 @@ int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts) fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } + +int bpf_prog_stream_read(int prog_fd, __u32 stream_id, void *buf, __u32 buf_len, + struct bpf_prog_stream_read_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, prog_stream_read); + union bpf_attr attr; + int err; + + if (!OPTS_VALID(opts, bpf_prog_stream_read_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.prog_stream_read.stream_buf = ptr_to_u64(buf); + attr.prog_stream_read.stream_buf_len = buf_len; + attr.prog_stream_read.stream_id = stream_id; + attr.prog_stream_read.prog_fd = prog_fd; + + err = sys_bpf(BPF_PROG_STREAM_READ_BY_FD, &attr, attr_sz); + return libbpf_err_errno(err); +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 972e17ec0c09..e983a3e40d61 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -54,9 +54,12 @@ struct bpf_map_create_opts { __s32 value_type_btf_obj_fd; __u32 token_fd; + + const void *excl_prog_hash; + __u32 excl_prog_hash_size; size_t :0; }; -#define bpf_map_create_opts__last_field token_fd +#define bpf_map_create_opts__last_field excl_prog_hash_size LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, const char *map_name, @@ -100,16 +103,19 @@ struct bpf_prog_load_opts { __u32 log_level; __u32 log_size; char *log_buf; - /* output: actual total log contents size (including termintaing zero). + /* output: actual total log contents size (including terminating zero). * It could be both larger than original log_size (if log was * truncated), or smaller (if log buffer wasn't filled completely). * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; __u32 token_fd; + + /* if set, provides the length of fd_array */ + __u32 fd_array_cnt; size_t :0; }; -#define bpf_prog_load_opts__last_field token_fd +#define bpf_prog_load_opts__last_field fd_array_cnt LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name, const char *license, @@ -129,7 +135,7 @@ struct bpf_btf_load_opts { char *log_buf; __u32 log_level; __u32 log_size; - /* output: actual total log contents size (including termintaing zero). + /* output: actual total log contents size (including terminating zero). * It could be both larger than original log_size (if log was * truncated), or smaller (if log buffer wasn't filled completely). * If kernel doesn't support this feature, log_size is left unchanged. @@ -435,6 +441,11 @@ struct bpf_link_create_opts { __u32 relative_id; __u64 expected_revision; } netkit; + struct { + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + } cgroup; }; size_t :0; }; @@ -484,9 +495,10 @@ LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id); struct bpf_get_fd_by_id_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 open_flags; /* permissions requested for the operation on fd */ + __u32 token_fd; size_t :0; }; -#define bpf_get_fd_by_id_opts__last_field open_flags +#define bpf_get_fd_by_id_opts__last_field token_fd LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id); LIBBPF_API int bpf_prog_get_fd_by_id_opts(__u32 id, @@ -700,6 +712,27 @@ struct bpf_token_create_opts { LIBBPF_API int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts); +struct bpf_prog_stream_read_opts { + size_t sz; + size_t :0; +}; +#define bpf_prog_stream_read_opts__last_field sz +/** + * @brief **bpf_prog_stream_read** reads data from the BPF stream of a given BPF + * program. + * + * @param prog_fd FD for the BPF program whose BPF stream is to be read. + * @param stream_id ID of the BPF stream to be read. + * @param buf Buffer to read data into from the BPF stream. + * @param buf_len Maximum number of bytes to read from the BPF stream. + * @param opts optional options, can be NULL + * + * @return The number of bytes read, on success; negative error code, otherwise + * (errno is also set to the error code) + */ +LIBBPF_API int bpf_prog_stream_read(int prog_fd, __u32 stream_id, void *buf, __u32 buf_len, + struct bpf_prog_stream_read_opts *opts); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index c0e13cdf9660..b997c68bd945 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -388,7 +388,13 @@ extern void *bpf_rdonly_cast(const void *obj, __u32 btf_id) __ksym __weak; #define ___arrow10(a, b, c, d, e, f, g, h, i, j) a->b->c->d->e->f->g->h->i->j #define ___arrow(...) ___apply(___arrow, ___narg(__VA_ARGS__))(__VA_ARGS__) +#if defined(__clang__) && (__clang_major__ >= 19) +#define ___type(...) __typeof_unqual__(___arrow(__VA_ARGS__)) +#elif defined(__GNUC__) && (__GNUC__ >= 14) +#define ___type(...) __typeof_unqual__(___arrow(__VA_ARGS__)) +#else #define ___type(...) typeof(___arrow(__VA_ARGS__)) +#endif #define ___read(read_fn, dst, src_type, src, accessor) \ read_fn((void *)(dst), sizeof(*(dst)), &((src_type)(src))->accessor) diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index fdf44403ff36..49af4260b8e6 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -4,6 +4,7 @@ #define __BPF_GEN_INTERNAL_H #include "bpf.h" +#include "libbpf_internal.h" struct ksym_relo_desc { const char *name; @@ -34,6 +35,7 @@ struct bpf_gen { void *data_cur; void *insn_start; void *insn_cur; + bool swapped_endian; ssize_t cleanup_label; __u32 nr_progs; __u32 nr_maps; @@ -49,6 +51,7 @@ struct bpf_gen { __u32 nr_ksyms; int fd_array; int nr_fd_array; + int hash_insn_offset[SHA256_DWORD_SIZE]; }; void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 305c62817dd3..d4e4e388e625 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -15,6 +15,14 @@ #define __array(name, val) typeof(val) *name[] #define __ulong(name, val) enum { ___bpf_concat(__unique_value, __COUNTER__) = val } name +#ifndef likely +#define likely(x) (__builtin_expect(!!(x), 1)) +#endif + +#ifndef unlikely +#define unlikely(x) (__builtin_expect(!!(x), 0)) +#endif + /* * Helper macro to place programs, maps, license in * different sections in elf_bpf file. Section names @@ -185,6 +193,7 @@ enum libbpf_tristate { #define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted"))) #define __kptr __attribute__((btf_type_tag("kptr"))) #define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr"))) +#define __uptr __attribute__((btf_type_tag("uptr"))) #if defined (__clang__) #define bpf_ksym_exists(sym) ({ \ @@ -206,6 +215,7 @@ enum libbpf_tristate { #define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull"))) #define __arg_nullable __attribute((btf_decl_tag("arg:nullable"))) #define __arg_trusted __attribute((btf_decl_tag("arg:trusted"))) +#define __arg_untrusted __attribute((btf_decl_tag("arg:untrusted"))) #define __arg_arena __attribute((btf_decl_tag("arg:arena"))) #ifndef ___bpf_concat @@ -305,6 +315,22 @@ enum libbpf_tristate { ___param, sizeof(___param)); \ }) +extern int bpf_stream_vprintk_impl(int stream_id, const char *fmt__str, const void *args, + __u32 len__sz, void *aux__prog) __weak __ksym; + +#define bpf_stream_printk(stream_id, 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_stream_vprintk_impl(stream_id, ___fmt, ___param, sizeof(___param), NULL); \ +}) + /* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args * Otherwise use __bpf_vprintk */ @@ -341,7 +367,7 @@ extern void bpf_iter_num_destroy(struct bpf_iter_num *it) __weak __ksym; * I.e., it looks almost like high-level for each loop in other languages, * supports continue/break, and is verifiable by BPF verifier. * - * For iterating integers, the difference betwen bpf_for_each(num, i, N, M) + * For iterating integers, the difference between bpf_for_each(num, i, N, M) * and bpf_for(i, N, M) is in that bpf_for() provides additional proof to * verifier that i is in [N, M) range, and in bpf_for_each() case i is `int * *`, not just `int`. So for integers bpf_for() is more convenient. diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 9314fa95f04e..dbe32a5d02cd 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -163,7 +163,7 @@ struct pt_regs___s390 { unsigned long orig_gpr2; -}; +} __attribute__((preserve_access_index)); /* s390 provides user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const user_pt_regs *)(x)) @@ -179,7 +179,7 @@ struct pt_regs___s390 { #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG #define __PT_PARM6_SYSCALL_REG gprs[7] -#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) +#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___s390 *)(x))->__PT_PARM1_SYSCALL_REG) #define PT_REGS_PARM1_CORE_SYSCALL(x) \ BPF_CORE_READ((const struct pt_regs___s390 *)(x), __PT_PARM1_SYSCALL_REG) @@ -222,7 +222,7 @@ struct pt_regs___s390 { struct pt_regs___arm64 { unsigned long orig_x0; -}; +} __attribute__((preserve_access_index)); /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) @@ -241,7 +241,7 @@ struct pt_regs___arm64 { #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG #define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG -#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) +#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___arm64 *)(x))->__PT_PARM1_SYSCALL_REG) #define PT_REGS_PARM1_CORE_SYSCALL(x) \ BPF_CORE_READ((const struct pt_regs___arm64 *)(x), __PT_PARM1_SYSCALL_REG) @@ -311,7 +311,7 @@ struct pt_regs___arm64 { #define __PT_RET_REG regs[31] #define __PT_FP_REG __unsupported__ #define __PT_RC_REG gpr[3] -#define __PT_SP_REG sp +#define __PT_SP_REG gpr[1] #define __PT_IP_REG nip #elif defined(bpf_target_sparc) @@ -351,6 +351,10 @@ struct pt_regs___arm64 { * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions */ +struct pt_regs___riscv { + unsigned long orig_a0; +} __attribute__((preserve_access_index)); + /* riscv provides struct user_regs_struct instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG a0 @@ -362,12 +366,15 @@ struct pt_regs___arm64 { #define __PT_PARM7_REG a6 #define __PT_PARM8_REG a7 -#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM1_SYSCALL_REG orig_a0 #define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG #define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG #define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG #define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG #define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG +#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___riscv *)(x))->__PT_PARM1_SYSCALL_REG) +#define PT_REGS_PARM1_CORE_SYSCALL(x) \ + BPF_CORE_READ((const struct pt_regs___riscv *)(x), __PT_PARM1_SYSCALL_REG) #define __PT_RET_REG ra #define __PT_FP_REG s0 @@ -473,7 +480,7 @@ struct pt_regs; #endif /* * Similarly, syscall-specific conventions might differ between function call - * conventions within each architecutre. All supported architectures pass + * conventions within each architecture. All supported architectures pass * either 6 or 7 syscall arguments in registers. * * See syscall(2) manpage for succinct table with information on each arch. @@ -515,7 +522,7 @@ struct pt_regs; #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP -#elif defined(bpf_target_sparc) +#elif defined(bpf_target_sparc) || defined(bpf_target_arm64) #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP @@ -651,7 +658,7 @@ struct pt_regs; * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and * similar kinds of BPF programs, that accept input arguments as a single * pointer to untyped u64 array, where each u64 can actually be a typed - * pointer or integer of different size. Instead of requring user to write + * pointer or integer of different size. Instead of requiring user to write * manual casts and work with array elements by index, BPF_PROG macro * allows user to declare a list of named and typed input arguments in the * same syntax as for normal C function. All the casting is hidden and @@ -801,7 +808,7 @@ struct pt_regs; * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific * low-level way of getting kprobe input arguments from struct pt_regs, and * provides a familiar typed and named function arguments syntax and - * semantics of accessing kprobe input paremeters. + * semantics of accessing kprobe input parameters. * * Original struct pt_regs* context is preserved as 'ctx' argument. This might * be necessary when using BPF helpers like bpf_perf_event_output(). diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 32c00db3b91b..84a4b0abc8be 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -12,6 +12,7 @@ #include <sys/utsname.h> #include <sys/param.h> #include <sys/stat.h> +#include <sys/mman.h> #include <linux/kernel.h> #include <linux/err.h> #include <linux/btf.h> @@ -119,6 +120,9 @@ struct btf { /* whether base_btf should be freed in btf_free for this instance */ bool owns_base; + /* whether raw_data is a (read-only) mmap */ + bool raw_data_is_mmap; + /* BTF object FD, if loaded into kernel */ int fd; @@ -282,7 +286,7 @@ static int btf_parse_str_sec(struct btf *btf) return -EINVAL; } if (!btf->base_btf && start[0]) { - pr_debug("Invalid BTF string section\n"); + pr_debug("Malformed BTF string section, did you forget to provide base BTF?\n"); return -EINVAL; } return 0; @@ -950,6 +954,17 @@ static bool btf_is_modifiable(const struct btf *btf) return (void *)btf->hdr != btf->raw_data; } +static void btf_free_raw_data(struct btf *btf) +{ + if (btf->raw_data_is_mmap) { + munmap(btf->raw_data, btf->raw_size); + btf->raw_data_is_mmap = false; + } else { + free(btf->raw_data); + } + btf->raw_data = NULL; +} + void btf__free(struct btf *btf) { if (IS_ERR_OR_NULL(btf)) @@ -969,7 +984,7 @@ void btf__free(struct btf *btf) free(btf->types_data); strset__free(btf->strs_set); } - free(btf->raw_data); + btf_free_raw_data(btf); free(btf->raw_data_swapped); free(btf->type_offs); if (btf->owns_base) @@ -995,7 +1010,8 @@ static struct btf *btf_new_empty(struct btf *base_btf) if (base_btf) { btf->base_btf = base_btf; btf->start_id = btf__type_cnt(base_btf); - btf->start_str_off = base_btf->hdr->str_len; + btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off; + btf->swapped_endian = base_btf->swapped_endian; } /* +1 for empty string at offset 0 */ @@ -1028,7 +1044,7 @@ struct btf *btf__new_empty_split(struct btf *base_btf) return libbpf_ptr(btf_new_empty(base_btf)); } -static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) +static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf, bool is_mmap) { struct btf *btf; int err; @@ -1045,15 +1061,21 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) if (base_btf) { btf->base_btf = base_btf; btf->start_id = btf__type_cnt(base_btf); - btf->start_str_off = base_btf->hdr->str_len; + btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off; } - btf->raw_data = malloc(size); - if (!btf->raw_data) { - err = -ENOMEM; - goto done; + if (is_mmap) { + btf->raw_data = (void *)data; + btf->raw_data_is_mmap = true; + } else { + btf->raw_data = malloc(size); + if (!btf->raw_data) { + err = -ENOMEM; + goto done; + } + memcpy(btf->raw_data, data, size); } - memcpy(btf->raw_data, data, size); + btf->raw_size = size; btf->hdr = btf->raw_data; @@ -1081,12 +1103,12 @@ done: struct btf *btf__new(const void *data, __u32 size) { - return libbpf_ptr(btf_new(data, size, NULL)); + return libbpf_ptr(btf_new(data, size, NULL, false)); } struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf) { - return libbpf_ptr(btf_new(data, size, base_btf)); + return libbpf_ptr(btf_new(data, size, base_btf, false)); } struct btf_elf_secs { @@ -1146,6 +1168,12 @@ static int btf_find_elf_sections(Elf *elf, const char *path, struct btf_elf_secs else continue; + if (sh.sh_type != SHT_PROGBITS) { + pr_warn("unexpected section type (%d) of section(%d, %s) from %s\n", + sh.sh_type, idx, name, path); + goto err; + } + data = elf_getdata(scn, 0); if (!data) { pr_warn("failed to get section(%d, %s) data from %s\n", @@ -1178,12 +1206,13 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, fd = open(path, O_RDONLY | O_CLOEXEC); if (fd < 0) { err = -errno; - pr_warn("failed to open %s: %s\n", path, strerror(errno)); + pr_warn("failed to open %s: %s\n", path, errstr(err)); return ERR_PTR(err); } elf = elf_begin(fd, ELF_C_READ, NULL); if (!elf) { + err = -LIBBPF_ERRNO__FORMAT; pr_warn("failed to open %s as ELF file\n", path); goto done; } @@ -1200,7 +1229,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, if (secs.btf_base_data) { dist_base_btf = btf_new(secs.btf_base_data->d_buf, secs.btf_base_data->d_size, - NULL); + NULL, false); if (IS_ERR(dist_base_btf)) { err = PTR_ERR(dist_base_btf); dist_base_btf = NULL; @@ -1209,7 +1238,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, } btf = btf_new(secs.btf_data->d_buf, secs.btf_data->d_size, - dist_base_btf ?: base_btf); + dist_base_btf ?: base_btf, false); if (IS_ERR(btf)) { err = PTR_ERR(btf); goto done; @@ -1326,7 +1355,7 @@ static struct btf *btf_parse_raw(const char *path, struct btf *base_btf) } /* finally parse BTF data */ - btf = btf_new(data, sz, base_btf); + btf = btf_new(data, sz, base_btf, false); err_out: free(data); @@ -1345,6 +1374,37 @@ struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf) return libbpf_ptr(btf_parse_raw(path, base_btf)); } +static struct btf *btf_parse_raw_mmap(const char *path, struct btf *base_btf) +{ + struct stat st; + void *data; + struct btf *btf; + int fd, err; + + fd = open(path, O_RDONLY); + if (fd < 0) + return ERR_PTR(-errno); + + if (fstat(fd, &st) < 0) { + err = -errno; + close(fd); + return ERR_PTR(err); + } + + data = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0); + err = -errno; + close(fd); + + if (data == MAP_FAILED) + return ERR_PTR(err); + + btf = btf_new(data, st.st_size, base_btf, true); + if (IS_ERR(btf)) + munmap(data, st.st_size); + + return btf; +} + static struct btf *btf_parse(const char *path, struct btf *base_btf, struct btf_ext **btf_ext) { struct btf *btf; @@ -1444,7 +1504,7 @@ retry_load: goto retry_load; err = -errno; - pr_warn("BTF loading error: %d\n", err); + pr_warn("BTF loading error: %s\n", errstr(err)); /* don't print out contents of custom log_buf */ if (!log_buf && buf[0]) pr_warn("-- BEGIN BTF LOAD LOG ---\n%s\n-- END BTF LOAD LOG --\n", buf); @@ -1609,19 +1669,25 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) goto exit_free; } - btf = btf_new(ptr, btf_info.btf_size, base_btf); + btf = btf_new(ptr, btf_info.btf_size, base_btf, false); exit_free: free(ptr); return btf; } -struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf) +struct btf *btf_load_from_kernel(__u32 id, struct btf *base_btf, int token_fd) { struct btf *btf; int btf_fd; + LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts); + + if (token_fd) { + opts.open_flags |= BPF_F_TOKEN_FD; + opts.token_fd = token_fd; + } - btf_fd = bpf_btf_get_fd_by_id(id); + btf_fd = bpf_btf_get_fd_by_id_opts(id, &opts); if (btf_fd < 0) return libbpf_err_ptr(-errno); @@ -1631,6 +1697,11 @@ struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf) return libbpf_ptr(btf); } +struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf) +{ + return btf_load_from_kernel(id, base_btf, 0); +} + struct btf *btf__load_from_kernel_by_id(__u32 id) { return btf__load_from_kernel_by_id_split(id, NULL); @@ -1638,10 +1709,8 @@ struct btf *btf__load_from_kernel_by_id(__u32 id) static void btf_invalidate_raw_data(struct btf *btf) { - if (btf->raw_data) { - free(btf->raw_data); - btf->raw_data = NULL; - } + if (btf->raw_data) + btf_free_raw_data(btf); if (btf->raw_data_swapped) { free(btf->raw_data_swapped); btf->raw_data_swapped = NULL; @@ -2087,7 +2156,7 @@ static int validate_type_id(int id) } /* generic append function for PTR, TYPEDEF, CONST/VOLATILE/RESTRICT */ -static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id) +static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id, int kflag) { struct btf_type *t; int sz, name_off = 0; @@ -2110,7 +2179,7 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref } t->name_off = name_off; - t->info = btf_type_info(kind, 0, 0); + t->info = btf_type_info(kind, 0, kflag); t->type = ref_type_id; return btf_commit_type(btf, sz); @@ -2125,7 +2194,7 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref */ int btf__add_ptr(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id, 0); } /* @@ -2503,7 +2572,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind) struct btf_type *t; int id; - id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0); + id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0, 0); if (id <= 0) return id; t = btf_type_by_id(btf, id); @@ -2533,7 +2602,7 @@ int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id) if (!name || !name[0]) return libbpf_err(-EINVAL); - return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id, 0); } /* @@ -2545,7 +2614,7 @@ int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id) */ int btf__add_volatile(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id, 0); } /* @@ -2557,7 +2626,7 @@ int btf__add_volatile(struct btf *btf, int ref_type_id) */ int btf__add_const(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id, 0); } /* @@ -2569,7 +2638,7 @@ int btf__add_const(struct btf *btf, int ref_type_id) */ int btf__add_restrict(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id, 0); } /* @@ -2585,7 +2654,24 @@ int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id) if (!value || !value[0]) return libbpf_err(-EINVAL); - return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id, 0); +} + +/* + * Append new BTF_KIND_TYPE_TAG type with: + * - *value*, non-empty/non-NULL tag value; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Set info->kflag to 1, indicating this tag is an __attribute__ + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_type_attr(struct btf *btf, const char *value, int ref_type_id) +{ + if (!value || !value[0]) + return libbpf_err(-EINVAL); + + return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id, 1); } /* @@ -2607,7 +2693,7 @@ int btf__add_func(struct btf *btf, const char *name, linkage != BTF_FUNC_EXTERN) return libbpf_err(-EINVAL); - id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id); + id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id, 0); if (id > 0) { struct btf_type *t = btf_type_by_id(btf, id); @@ -2842,18 +2928,8 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ return 0; } -/* - * Append new BTF_KIND_DECL_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_decl_tag(struct btf *btf, const char *value, int ref_type_id, - int component_idx) +static int btf_add_decl_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx, int kflag) { struct btf_type *t; int sz, value_off; @@ -2877,14 +2953,47 @@ int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, return value_off; t->name_off = value_off; - t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false); + t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, kflag); t->type = ref_type_id; btf_decl_tag(t)->component_idx = component_idx; return btf_commit_type(btf, sz); } -struct btf_ext_sec_setup_param { +/* + * Append new BTF_KIND_DECL_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_decl_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx) +{ + return btf_add_decl_tag(btf, value, ref_type_id, component_idx, 0); +} + +/* + * Append new BTF_KIND_DECL_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; + * Set info->kflag to 1, indicating this tag is an __attribute__ + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_decl_attr(struct btf *btf, const char *value, int ref_type_id, + int component_idx) +{ + return btf_add_decl_tag(btf, value, ref_type_id, component_idx, 1); +} + +struct btf_ext_sec_info_param { __u32 off; __u32 len; __u32 min_rec_size; @@ -2892,14 +3001,20 @@ struct btf_ext_sec_setup_param { const char *desc; }; -static int btf_ext_setup_info(struct btf_ext *btf_ext, - struct btf_ext_sec_setup_param *ext_sec) +/* + * Parse a single info subsection of the BTF.ext info data: + * - validate subsection structure and elements + * - save info subsection start and sizing details in struct btf_ext + * - endian-independent operation, for calling before byte-swapping + */ +static int btf_ext_parse_sec_info(struct btf_ext *btf_ext, + struct btf_ext_sec_info_param *ext_sec, + bool is_native) { const struct btf_ext_info_sec *sinfo; struct btf_ext_info *ext_info; __u32 info_left, record_size; size_t sec_cnt = 0; - /* The start of the info sec (including the __u32 record_size). */ void *info; if (ext_sec->len == 0) @@ -2911,6 +3026,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return -EINVAL; } + /* The start of the info sec (including the __u32 record_size). */ info = btf_ext->data + btf_ext->hdr->hdr_len + ext_sec->off; info_left = ext_sec->len; @@ -2926,9 +3042,13 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return -EINVAL; } - /* The record size needs to meet the minimum standard */ - record_size = *(__u32 *)info; + /* The record size needs to meet either the minimum standard or, when + * handling non-native endianness data, the exact standard so as + * to allow safe byte-swapping. + */ + record_size = is_native ? *(__u32 *)info : bswap_32(*(__u32 *)info); if (record_size < ext_sec->min_rec_size || + (!is_native && record_size != ext_sec->min_rec_size) || record_size & 0x03) { pr_debug("%s section in .BTF.ext has invalid record size %u\n", ext_sec->desc, record_size); @@ -2940,7 +3060,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, /* If no records, return failure now so .BTF.ext won't be used. */ if (!info_left) { - pr_debug("%s section in .BTF.ext has no records", ext_sec->desc); + pr_debug("%s section in .BTF.ext has no records\n", ext_sec->desc); return -EINVAL; } @@ -2955,7 +3075,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return -EINVAL; } - num_records = sinfo->num_info; + num_records = is_native ? sinfo->num_info : bswap_32(sinfo->num_info); if (num_records == 0) { pr_debug("%s section has incorrect num_records in .BTF.ext\n", ext_sec->desc); @@ -2983,64 +3103,157 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return 0; } -static int btf_ext_setup_func_info(struct btf_ext *btf_ext) +/* Parse all info secs in the BTF.ext info data */ +static int btf_ext_parse_info(struct btf_ext *btf_ext, bool is_native) { - struct btf_ext_sec_setup_param param = { + struct btf_ext_sec_info_param func_info = { .off = btf_ext->hdr->func_info_off, .len = btf_ext->hdr->func_info_len, .min_rec_size = sizeof(struct bpf_func_info_min), .ext_info = &btf_ext->func_info, .desc = "func_info" }; - - return btf_ext_setup_info(btf_ext, ¶m); -} - -static int btf_ext_setup_line_info(struct btf_ext *btf_ext) -{ - struct btf_ext_sec_setup_param param = { + struct btf_ext_sec_info_param line_info = { .off = btf_ext->hdr->line_info_off, .len = btf_ext->hdr->line_info_len, .min_rec_size = sizeof(struct bpf_line_info_min), .ext_info = &btf_ext->line_info, .desc = "line_info", }; - - return btf_ext_setup_info(btf_ext, ¶m); -} - -static int btf_ext_setup_core_relos(struct btf_ext *btf_ext) -{ - struct btf_ext_sec_setup_param param = { - .off = btf_ext->hdr->core_relo_off, - .len = btf_ext->hdr->core_relo_len, + struct btf_ext_sec_info_param core_relo = { .min_rec_size = sizeof(struct bpf_core_relo), .ext_info = &btf_ext->core_relo_info, .desc = "core_relo", }; + int err; - return btf_ext_setup_info(btf_ext, ¶m); + err = btf_ext_parse_sec_info(btf_ext, &func_info, is_native); + if (err) + return err; + + err = btf_ext_parse_sec_info(btf_ext, &line_info, is_native); + if (err) + return err; + + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + return 0; /* skip core relos parsing */ + + core_relo.off = btf_ext->hdr->core_relo_off; + core_relo.len = btf_ext->hdr->core_relo_len; + err = btf_ext_parse_sec_info(btf_ext, &core_relo, is_native); + if (err) + return err; + + return 0; } -static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) +/* Swap byte-order of BTF.ext header with any endianness */ +static void btf_ext_bswap_hdr(struct btf_ext_header *h) { - const struct btf_ext_header *hdr = (struct btf_ext_header *)data; + bool is_native = h->magic == BTF_MAGIC; + __u32 hdr_len; + + hdr_len = is_native ? h->hdr_len : bswap_32(h->hdr_len); + + h->magic = bswap_16(h->magic); + h->hdr_len = bswap_32(h->hdr_len); + h->func_info_off = bswap_32(h->func_info_off); + h->func_info_len = bswap_32(h->func_info_len); + h->line_info_off = bswap_32(h->line_info_off); + h->line_info_len = bswap_32(h->line_info_len); + + if (hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + return; + + h->core_relo_off = bswap_32(h->core_relo_off); + h->core_relo_len = bswap_32(h->core_relo_len); +} + +/* Swap byte-order of generic info subsection */ +static void btf_ext_bswap_info_sec(void *info, __u32 len, bool is_native, + info_rec_bswap_fn bswap_fn) +{ + struct btf_ext_info_sec *sec; + __u32 info_left, rec_size, *rs; + + if (len == 0) + return; + + rs = info; /* info record size */ + rec_size = is_native ? *rs : bswap_32(*rs); + *rs = bswap_32(*rs); + + sec = info + sizeof(__u32); /* info sec #1 */ + info_left = len - sizeof(__u32); + while (info_left) { + unsigned int sec_hdrlen = sizeof(struct btf_ext_info_sec); + __u32 i, num_recs; + void *p; + + num_recs = is_native ? sec->num_info : bswap_32(sec->num_info); + sec->sec_name_off = bswap_32(sec->sec_name_off); + sec->num_info = bswap_32(sec->num_info); + p = sec->data; /* info rec #1 */ + for (i = 0; i < num_recs; i++, p += rec_size) + bswap_fn(p); + sec = p; + info_left -= sec_hdrlen + (__u64)rec_size * num_recs; + } +} + +/* + * Swap byte-order of all info data in a BTF.ext section + * - requires BTF.ext hdr in native endianness + */ +static void btf_ext_bswap_info(struct btf_ext *btf_ext, void *data) +{ + const bool is_native = btf_ext->swapped_endian; + const struct btf_ext_header *h = data; + void *info; - if (data_size < offsetofend(struct btf_ext_header, hdr_len) || - data_size < hdr->hdr_len) { - pr_debug("BTF.ext header not found"); + /* Swap func_info subsection byte-order */ + info = data + h->hdr_len + h->func_info_off; + btf_ext_bswap_info_sec(info, h->func_info_len, is_native, + (info_rec_bswap_fn)bpf_func_info_bswap); + + /* Swap line_info subsection byte-order */ + info = data + h->hdr_len + h->line_info_off; + btf_ext_bswap_info_sec(info, h->line_info_len, is_native, + (info_rec_bswap_fn)bpf_line_info_bswap); + + /* Swap core_relo subsection byte-order (if present) */ + if (h->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + return; + + info = data + h->hdr_len + h->core_relo_off; + btf_ext_bswap_info_sec(info, h->core_relo_len, is_native, + (info_rec_bswap_fn)bpf_core_relo_bswap); +} + +/* Parse hdr data and info sections: check and convert to native endianness */ +static int btf_ext_parse(struct btf_ext *btf_ext) +{ + __u32 hdr_len, data_size = btf_ext->data_size; + struct btf_ext_header *hdr = btf_ext->hdr; + bool swapped_endian = false; + int err; + + if (data_size < offsetofend(struct btf_ext_header, hdr_len)) { + pr_debug("BTF.ext header too short\n"); return -EINVAL; } + hdr_len = hdr->hdr_len; if (hdr->magic == bswap_16(BTF_MAGIC)) { - pr_warn("BTF.ext in non-native endianness is not supported\n"); - return -ENOTSUP; + swapped_endian = true; + hdr_len = bswap_32(hdr_len); } else if (hdr->magic != BTF_MAGIC) { pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic); return -EINVAL; } - if (hdr->version != BTF_VERSION) { + /* Ensure known version of structs, current BTF_VERSION == 1 */ + if (hdr->version != 1) { pr_debug("Unsupported BTF.ext version:%u\n", hdr->version); return -ENOTSUP; } @@ -3050,11 +3263,39 @@ static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) return -ENOTSUP; } - if (data_size == hdr->hdr_len) { + if (data_size < hdr_len) { + pr_debug("BTF.ext header not found\n"); + return -EINVAL; + } else if (data_size == hdr_len) { pr_debug("BTF.ext has no data\n"); return -EINVAL; } + /* Verify mandatory hdr info details present */ + if (hdr_len < offsetofend(struct btf_ext_header, line_info_len)) { + pr_warn("BTF.ext header missing func_info, line_info\n"); + return -EINVAL; + } + + /* Keep hdr native byte-order in memory for introspection */ + if (swapped_endian) + btf_ext_bswap_hdr(btf_ext->hdr); + + /* Validate info subsections and cache key metadata */ + err = btf_ext_parse_info(btf_ext, !swapped_endian); + if (err) + return err; + + /* Keep infos native byte-order in memory for introspection */ + if (swapped_endian) + btf_ext_bswap_info(btf_ext, btf_ext->data); + + /* + * Set btf_ext->swapped_endian only after all header and info data has + * been swapped, helping bswap functions determine if their data are + * in native byte-order when called. + */ + btf_ext->swapped_endian = swapped_endian; return 0; } @@ -3066,6 +3307,7 @@ void btf_ext__free(struct btf_ext *btf_ext) free(btf_ext->line_info.sec_idxs); free(btf_ext->core_relo_info.sec_idxs); free(btf_ext->data); + free(btf_ext->data_swapped); free(btf_ext); } @@ -3086,29 +3328,7 @@ struct btf_ext *btf_ext__new(const __u8 *data, __u32 size) } memcpy(btf_ext->data, data, size); - err = btf_ext_parse_hdr(btf_ext->data, size); - if (err) - goto done; - - if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) { - err = -EINVAL; - goto done; - } - - err = btf_ext_setup_func_info(btf_ext); - if (err) - goto done; - - err = btf_ext_setup_line_info(btf_ext); - if (err) - goto done; - - if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) - goto done; /* skip core relos parsing */ - - err = btf_ext_setup_core_relos(btf_ext); - if (err) - goto done; + err = btf_ext_parse(btf_ext); done: if (err) { @@ -3119,15 +3339,66 @@ done: return btf_ext; } +static void *btf_ext_raw_data(const struct btf_ext *btf_ext_ro, bool swap_endian) +{ + struct btf_ext *btf_ext = (struct btf_ext *)btf_ext_ro; + const __u32 data_sz = btf_ext->data_size; + void *data; + + /* Return native data (always present) or swapped data if present */ + if (!swap_endian) + return btf_ext->data; + else if (btf_ext->data_swapped) + return btf_ext->data_swapped; + + /* Recreate missing swapped data, then cache and return */ + data = calloc(1, data_sz); + if (!data) + return NULL; + memcpy(data, btf_ext->data, data_sz); + + btf_ext_bswap_info(btf_ext, data); + btf_ext_bswap_hdr(data); + btf_ext->data_swapped = data; + return data; +} + const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size) { + void *data; + + data = btf_ext_raw_data(btf_ext, btf_ext->swapped_endian); + if (!data) + return errno = ENOMEM, NULL; + *size = btf_ext->data_size; - return btf_ext->data; + return data; } __attribute__((alias("btf_ext__raw_data"))) const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size); +enum btf_endianness btf_ext__endianness(const struct btf_ext *btf_ext) +{ + if (is_host_big_endian()) + return btf_ext->swapped_endian ? BTF_LITTLE_ENDIAN : BTF_BIG_ENDIAN; + else + return btf_ext->swapped_endian ? BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN; +} + +int btf_ext__set_endianness(struct btf_ext *btf_ext, enum btf_endianness endian) +{ + if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN) + return libbpf_err(-EINVAL); + + btf_ext->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN); + + if (!btf_ext->swapped_endian) { + free(btf_ext->data_swapped); + btf_ext->data_swapped = NULL; + } + return 0; +} struct btf_dedup; @@ -3290,7 +3561,7 @@ int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts) d = btf_dedup_new(btf, opts); if (IS_ERR(d)) { - pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d)); + pr_debug("btf_dedup_new failed: %ld\n", PTR_ERR(d)); return libbpf_err(-EINVAL); } @@ -3301,42 +3572,42 @@ int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts) err = btf_dedup_prep(d); if (err) { - pr_debug("btf_dedup_prep failed:%d\n", err); + pr_debug("btf_dedup_prep failed: %s\n", errstr(err)); goto done; } err = btf_dedup_strings(d); if (err < 0) { - pr_debug("btf_dedup_strings failed:%d\n", err); + pr_debug("btf_dedup_strings failed: %s\n", errstr(err)); goto done; } err = btf_dedup_prim_types(d); if (err < 0) { - pr_debug("btf_dedup_prim_types failed:%d\n", err); + pr_debug("btf_dedup_prim_types failed: %s\n", errstr(err)); goto done; } err = btf_dedup_struct_types(d); if (err < 0) { - pr_debug("btf_dedup_struct_types failed:%d\n", err); + pr_debug("btf_dedup_struct_types failed: %s\n", errstr(err)); goto done; } err = btf_dedup_resolve_fwds(d); if (err < 0) { - pr_debug("btf_dedup_resolve_fwds failed:%d\n", err); + pr_debug("btf_dedup_resolve_fwds failed: %s\n", errstr(err)); goto done; } err = btf_dedup_ref_types(d); if (err < 0) { - pr_debug("btf_dedup_ref_types failed:%d\n", err); + pr_debug("btf_dedup_ref_types failed: %s\n", errstr(err)); goto done; } err = btf_dedup_compact_types(d); if (err < 0) { - pr_debug("btf_dedup_compact_types failed:%d\n", err); + pr_debug("btf_dedup_compact_types failed: %s\n", errstr(err)); goto done; } err = btf_dedup_remap_types(d); if (err < 0) { - pr_debug("btf_dedup_remap_types failed:%d\n", err); + pr_debug("btf_dedup_remap_types failed: %s\n", errstr(err)); goto done; } @@ -3384,7 +3655,7 @@ struct btf_dedup { struct strset *strs_set; }; -static long hash_combine(long h, long value) +static unsigned long hash_combine(unsigned long h, unsigned long value) { return h * 31 + value; } @@ -3630,6 +3901,20 @@ err_out: return err; } +/* + * Calculate type signature hash of TYPEDEF, ignoring referenced type IDs, + * as referenced type IDs equivalence is established separately during type + * graph equivalence check algorithm. + */ +static long btf_hash_typedef(struct btf_type *t) +{ + long h; + + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info); + return h; +} + static long btf_hash_common(struct btf_type *t) { long h; @@ -3647,6 +3932,13 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) t1->size == t2->size; } +/* Check structural compatibility of two TYPEDEF. */ +static bool btf_equal_typedef(struct btf_type *t1, struct btf_type *t2) +{ + return t1->name_off == t2->name_off && + t1->info == t2->info; +} + /* Calculate type signature hash of INT or TAG. */ static long btf_hash_int_decl_tag(struct btf_type *t) { @@ -4134,46 +4426,109 @@ static inline __u16 btf_fwd_kind(struct btf_type *t) return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT; } -/* Check if given two types are identical ARRAY definitions */ -static bool btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2) +static bool btf_dedup_identical_types(struct btf_dedup *d, __u32 id1, __u32 id2, int depth) { struct btf_type *t1, *t2; + int k1, k2; +recur: + if (depth <= 0) + return false; t1 = btf_type_by_id(d->btf, id1); t2 = btf_type_by_id(d->btf, id2); - if (!btf_is_array(t1) || !btf_is_array(t2)) + + k1 = btf_kind(t1); + k2 = btf_kind(t2); + if (k1 != k2) return false; - return btf_equal_array(t1, t2); -} + switch (k1) { + case BTF_KIND_UNKN: /* VOID */ + return true; + case BTF_KIND_INT: + return btf_equal_int_tag(t1, t2); + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + return btf_compat_enum(t1, t2); + case BTF_KIND_FWD: + case BTF_KIND_FLOAT: + return btf_equal_common(t1, t2); + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_TYPE_TAG: + if (t1->info != t2->info || t1->name_off != t2->name_off) + return false; + id1 = t1->type; + id2 = t2->type; + goto recur; + case BTF_KIND_ARRAY: { + struct btf_array *a1, *a2; -/* Check if given two types are identical STRUCT/UNION definitions */ -static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id2) -{ - const struct btf_member *m1, *m2; - struct btf_type *t1, *t2; - int n, i; + if (!btf_compat_array(t1, t2)) + return false; - t1 = btf_type_by_id(d->btf, id1); - t2 = btf_type_by_id(d->btf, id2); + a1 = btf_array(t1); + a2 = btf_array(t1); - if (!btf_is_composite(t1) || btf_kind(t1) != btf_kind(t2)) - return false; + if (a1->index_type != a2->index_type && + !btf_dedup_identical_types(d, a1->index_type, a2->index_type, depth - 1)) + return false; - if (!btf_shallow_equal_struct(t1, t2)) - return false; + if (a1->type != a2->type && + !btf_dedup_identical_types(d, a1->type, a2->type, depth - 1)) + return false; - m1 = btf_members(t1); - m2 = btf_members(t2); - for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) { - if (m1->type != m2->type && - !btf_dedup_identical_arrays(d, m1->type, m2->type) && - !btf_dedup_identical_structs(d, m1->type, m2->type)) + return true; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m1, *m2; + int i, n; + + if (!btf_shallow_equal_struct(t1, t2)) return false; + + m1 = btf_members(t1); + m2 = btf_members(t2); + for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) { + if (m1->type == m2->type) + continue; + if (!btf_dedup_identical_types(d, m1->type, m2->type, depth - 1)) + return false; + } + return true; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p1, *p2; + int i, n; + + if (!btf_compat_fnproto(t1, t2)) + return false; + + if (t1->type != t2->type && + !btf_dedup_identical_types(d, t1->type, t2->type, depth - 1)) + return false; + + p1 = btf_params(t1); + p2 = btf_params(t2); + for (i = 0, n = btf_vlen(t1); i < n; i++, p1++, p2++) { + if (p1->type == p2->type) + continue; + if (!btf_dedup_identical_types(d, p1->type, p2->type, depth - 1)) + return false; + } + return true; + } + default: + return false; } - return true; } + /* * Check equivalence of BTF type graph formed by candidate struct/union (we'll * call it "candidate graph" in this description for brevity) to a type graph @@ -4191,7 +4546,7 @@ static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id * and canonical graphs are not compatible structurally, whole graphs are * incompatible. If types are structurally equivalent (i.e., all information * except referenced type IDs is exactly the same), a mapping from `canon_id` to - * a `cand_id` is recored in hypothetical mapping (`btf_dedup->hypot_map`). + * a `cand_id` is recoded in hypothetical mapping (`btf_dedup->hypot_map`). * If a type references other types, then those referenced types are checked * for equivalence recursively. * @@ -4229,7 +4584,7 @@ static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id * consists of portions of the graph that come from multiple compilation units. * This is due to the fact that types within single compilation unit are always * deduplicated and FWDs are already resolved, if referenced struct/union - * definiton is available. So, if we had unresolved FWD and found corresponding + * definition is available. So, if we had unresolved FWD and found corresponding * STRUCT/UNION, they will be from different compilation units. This * consequently means that when we "link" FWD to corresponding STRUCT/UNION, * type graph will likely have at least two different BTF types that describe @@ -4292,19 +4647,13 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, * different fields within the *same* struct. This breaks type * equivalence check, which makes an assumption that candidate * types sub-graph has a consistent and deduped-by-compiler - * types within a single CU. So work around that by explicitly - * allowing identical array types here. + * types within a single CU. And similar situation can happen + * with struct/union sometimes, and event with pointers. + * So accommodate cases like this doing a structural + * comparison recursively, but avoiding being stuck in endless + * loops by limiting the depth up to which we check. */ - if (btf_dedup_identical_arrays(d, hypot_type_id, cand_id)) - return 1; - /* It turns out that similar situation can happen with - * struct/union sometimes, sigh... Handle the case where - * structs/unions are exactly the same, down to the referenced - * type IDs. Anything more complicated (e.g., if referenced - * types are different, but equivalent) is *way more* - * complicated and requires a many-to-many equivalence mapping. - */ - if (btf_dedup_identical_structs(d, hypot_type_id, cand_id)) + if (btf_dedup_identical_types(d, hypot_type_id, cand_id, 16)) return 1; return 0; } @@ -4516,13 +4865,30 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d) } } +static inline long btf_hash_by_kind(struct btf_type *t, __u16 kind) +{ + if (kind == BTF_KIND_TYPEDEF) + return btf_hash_typedef(t); + else + return btf_hash_struct(t); +} + +static inline bool btf_equal_by_kind(struct btf_type *t1, struct btf_type *t2, __u16 kind) +{ + if (kind == BTF_KIND_TYPEDEF) + return btf_equal_typedef(t1, t2); + else + return btf_shallow_equal_struct(t1, t2); +} + /* - * Deduplicate struct/union types. + * Deduplicate struct/union and typedef types. * * For each struct/union type its type signature hash is calculated, taking * into account type's name, size, number, order and names of fields, but * ignoring type ID's referenced from fields, because they might not be deduped - * completely until after reference types deduplication phase. This type hash + * completely until after reference types deduplication phase. For each typedef + * type, the hash is computed based on the type’s name and size. This type hash * is used to iterate over all potential canonical types, sharing same hash. * For each canonical candidate we check whether type graphs that they form * (through referenced types in fields and so on) are equivalent using algorithm @@ -4554,18 +4920,20 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) t = btf_type_by_id(d->btf, type_id); kind = btf_kind(t); - if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) + if (kind != BTF_KIND_STRUCT && + kind != BTF_KIND_UNION && + kind != BTF_KIND_TYPEDEF) return 0; - h = btf_hash_struct(t); + h = btf_hash_by_kind(t, kind); for_each_dedup_cand(d, hash_entry, h) { __u32 cand_id = hash_entry->value; int eq; /* * Even though btf_dedup_is_equiv() checks for - * btf_shallow_equal_struct() internally when checking two - * structs (unions) for equivalence, we need to guard here + * btf_equal_by_kind() internally when checking two + * structs (unions) or typedefs for equivalence, we need to guard here * from picking matching FWD type as a dedup candidate. * This can happen due to hash collision. In such case just * relying on btf_dedup_is_equiv() would lead to potentially @@ -4573,7 +4941,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) * FWD and compatible STRUCT/UNION are considered equivalent. */ cand_type = btf_type_by_id(d->btf, cand_id); - if (!btf_shallow_equal_struct(t, cand_type)) + if (!btf_equal_by_kind(t, cand_type, kind)) continue; btf_dedup_clear_hypot_map(d); @@ -4611,18 +4979,18 @@ static int btf_dedup_struct_types(struct btf_dedup *d) /* * Deduplicate reference type. * - * Once all primitive and struct/union types got deduplicated, we can easily + * Once all primitive, struct/union and typedef types got deduplicated, we can easily * deduplicate all other (reference) BTF types. This is done in two steps: * * 1. Resolve all referenced type IDs into their canonical type IDs. This - * resolution can be done either immediately for primitive or struct/union types - * (because they were deduped in previous two phases) or recursively for + * resolution can be done either immediately for primitive, struct/union, and typedef + * types (because they were deduped in previous two phases) or recursively for * reference types. Recursion will always terminate at either primitive or - * struct/union type, at which point we can "unwind" chain of reference types - * one by one. There is no danger of encountering cycles because in C type - * system the only way to form type cycle is through struct/union, so any chain - * of reference types, even those taking part in a type cycle, will inevitably - * reach struct/union at some point. + * struct/union and typedef types, at which point we can "unwind" chain of reference + * types one by one. There is no danger of encountering cycles in C, as the only way to + * form a type cycle is through struct or union types. Go can form such cycles through + * typedef. Thus, any chain of reference types, even those taking part in a type cycle, + * will inevitably reach a struct/union or typedef type at some point. * * 2. Once all referenced type IDs are resolved into canonical ones, BTF type * becomes "stable", in the sense that no further deduplication will cause @@ -4654,7 +5022,6 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: case BTF_KIND_PTR: - case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_TYPE_TAG: ref_type_id = btf_dedup_ref_type(d, t->type); @@ -5052,10 +5419,14 @@ struct btf *btf__load_vmlinux_btf(void) pr_warn("kernel BTF is missing at '%s', was CONFIG_DEBUG_INFO_BTF enabled?\n", sysfs_btf_path); } else { - btf = btf__parse(sysfs_btf_path, NULL); + btf = btf_parse_raw_mmap(sysfs_btf_path, NULL); + if (IS_ERR(btf)) + btf = btf__parse(sysfs_btf_path, NULL); + if (!btf) { err = -errno; - pr_warn("failed to read kernel BTF from '%s': %d\n", sysfs_btf_path, err); + pr_warn("failed to read kernel BTF from '%s': %s\n", + sysfs_btf_path, errstr(err)); return libbpf_err_ptr(err); } pr_debug("loaded kernel BTF from '%s'\n", sysfs_btf_path); @@ -5072,7 +5443,7 @@ struct btf *btf__load_vmlinux_btf(void) btf = btf__parse(path, NULL); err = libbpf_get_error(btf); - pr_debug("loading kernel BTF '%s': %d\n", path, err); + pr_debug("loading kernel BTF '%s': %s\n", path, errstr(err)); if (err) continue; @@ -5394,6 +5765,9 @@ int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf, new_base = btf__new_empty(); if (!new_base) return libbpf_err(-ENOMEM); + + btf__set_endianness(new_base, btf__endianness(src_btf)); + dist.id_map = calloc(n, sizeof(*dist.id_map)); if (!dist.id_map) { err = -ENOMEM; @@ -5483,7 +5857,7 @@ void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) { btf->base_btf = (struct btf *)base_btf; btf->start_id = btf__type_cnt(base_btf); - btf->start_str_off = base_btf->hdr->str_len; + btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off; } int btf__relocate(struct btf *btf, const struct btf *base_btf) diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index b68d216837a9..cc01494d6210 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -94,6 +94,7 @@ 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 + * @param base_btf base BTF object * @return new BTF object instance which has to be eventually freed with * **btf__free()** * @@ -115,6 +116,10 @@ LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf); * When that split BTF is loaded against a (possibly changed) base, this * distilled base BTF will help update references to that (possibly changed) * base BTF. + * @param src_btf source split BTF object + * @param new_base_btf pointer to where the new base BTF object pointer will be stored + * @param new_split_btf pointer to where the new split BTF object pointer will be stored + * @return 0 on success; negative error code, otherwise * * Both the new split and its associated new base BTF must be freed by * the caller. @@ -167,6 +172,9 @@ LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset); LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size); LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size); +LIBBPF_API enum btf_endianness btf_ext__endianness(const struct btf_ext *btf_ext); +LIBBPF_API int btf_ext__set_endianness(struct btf_ext *btf_ext, + enum btf_endianness endian); LIBBPF_API int btf__find_str(struct btf *btf, const char *s); LIBBPF_API int btf__add_str(struct btf *btf, const char *s); @@ -224,6 +232,7 @@ LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id); +LIBBPF_API int btf__add_type_attr(struct btf *btf, const char *value, int ref_type_id); /* func and func_proto construction APIs */ LIBBPF_API int btf__add_func(struct btf *btf, const char *name, @@ -240,6 +249,8 @@ LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, /* tag construction API */ LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, int component_idx); +LIBBPF_API int btf__add_decl_attr(struct btf *btf, const char *value, int ref_type_id, + int component_idx); struct btf_dedup_opts { size_t sz; @@ -258,6 +269,9 @@ LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts); * to base BTF kinds, and verify those references are compatible with * *base_btf*; if they are, *btf* is adjusted such that is re-parented to * *base_btf* and type ids and strings are adjusted to accommodate this. + * @param btf split BTF object to relocate + * @param base_btf base BTF object + * @return 0 on success; negative error code, otherwise * * If successful, 0 is returned and **btf** now has **base_btf** as its * base. @@ -286,7 +300,7 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); struct btf_dump_emit_type_decl_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; /* optional field name for type declaration, e.g.: * - struct my_struct <FNAME> @@ -320,9 +334,10 @@ struct btf_dump_type_data_opts { bool compact; /* no newlines/indentation */ bool skip_names; /* skip member/type names */ bool emit_zeroes; /* show 0-valued fields */ + bool emit_strings; /* print char arrays as strings */ size_t :0; }; -#define btf_dump_type_data_opts__last_field emit_zeroes +#define btf_dump_type_data_opts__last_field emit_strings LIBBPF_API int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 5dbca76b953f..6388392f49a0 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -67,6 +67,7 @@ struct btf_dump_data { bool compact; bool skip_names; bool emit_zeroes; + bool emit_strings; __u8 indent_lvl; /* base indent level */ char indent_str[BTF_DATA_INDENT_STR_LEN]; /* below are used during iteration */ @@ -225,6 +226,9 @@ static void btf_dump_free_names(struct hashmap *map) size_t bkt; struct hashmap_entry *cur; + if (!map) + return; + hashmap__for_each_entry(map, cur, bkt) free((void *)cur->pkey); @@ -304,7 +308,7 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id) * definition, in which case they have to be declared inline as part of field * type declaration; or as a top-level anonymous enum, typically used for * declaring global constants. It's impossible to distinguish between two - * without knowning whether given enum type was referenced from other type: + * without knowing whether given enum type was referenced from other type: * top-level anonymous enum won't be referenced by anything, while embedded * one will. */ @@ -867,8 +871,8 @@ static void btf_dump_emit_bit_padding(const struct btf_dump *d, } pads[] = { {"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8} }; - int new_off, pad_bits, bits, i; - const char *pad_type; + int new_off = 0, pad_bits = 0, bits, i; + const char *pad_type = NULL; if (cur_off >= next_off) return; /* no gap */ @@ -1304,7 +1308,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, * chain, restore stack, emit warning, and try to * proceed nevertheless */ - pr_warn("not enough memory for decl stack:%d", err); + pr_warn("not enough memory for decl stack: %s\n", errstr(err)); d->decl_stack_cnt = stack_start; return; } @@ -1493,7 +1497,10 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, case BTF_KIND_TYPE_TAG: btf_dump_emit_mods(d, decls); name = btf_name_of(d, t->name_off); - btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name); + if (btf_kflag(t)) + btf_dump_printf(d, " __attribute__((%s))", name); + else + btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name); break; case BTF_KIND_ARRAY: { const struct btf_array *a = btf_array(t); @@ -1559,10 +1566,12 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, * Clang for BPF target generates func_proto with no * args as a func_proto with a single void arg (e.g., * `int (*f)(void)` vs just `int (*f)()`). We are - * going to pretend there are no args for such case. + * going to emit valid empty args (void) syntax for + * such case. Similarly and conveniently, valid + * no args case can be special-cased here as well. */ - if (vlen == 1 && p->type == 0) { - btf_dump_printf(d, ")"); + if (vlen == 0 || (vlen == 1 && p->type == 0)) { + btf_dump_printf(d, "void)"); return; } @@ -2022,6 +2031,52 @@ static int btf_dump_var_data(struct btf_dump *d, return btf_dump_dump_type_data(d, NULL, t, type_id, data, 0, 0); } +static int btf_dump_string_data(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data) +{ + const struct btf_array *array = btf_array(t); + const char *chars = data; + __u32 i; + + /* Make sure it is a NUL-terminated string. */ + for (i = 0; i < array->nelems; i++) { + if ((void *)(chars + i) >= d->typed_dump->data_end) + return -E2BIG; + if (chars[i] == '\0') + break; + } + if (i == array->nelems) { + /* The caller will print this as a regular array. */ + return -EINVAL; + } + + btf_dump_data_pfx(d); + btf_dump_printf(d, "\""); + + for (i = 0; i < array->nelems; i++) { + char c = chars[i]; + + if (c == '\0') { + /* + * When printing character arrays as strings, NUL bytes + * are always treated as string terminators; they are + * never printed. + */ + break; + } + if (isprint(c)) + btf_dump_printf(d, "%c", c); + else + btf_dump_printf(d, "\\x%02x", (__u8)c); + } + + btf_dump_printf(d, "\""); + + return 0; +} + static int btf_dump_array_data(struct btf_dump *d, const struct btf_type *t, __u32 id, @@ -2049,8 +2104,13 @@ static int btf_dump_array_data(struct btf_dump *d, * char arrays, so if size is 1 and element is * printable as a char, we'll do that. */ - if (elem_size == 1) + if (elem_size == 1) { + if (d->typed_dump->emit_strings && + btf_dump_string_data(d, t, id, data) == 0) { + return 0; + } d->typed_dump->is_array_char = true; + } } /* note that we increment depth before calling btf_dump_print() below; @@ -2538,6 +2598,7 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, d->typed_dump->compact = OPTS_GET(opts, compact, false); d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false); d->typed_dump->emit_zeroes = OPTS_GET(opts, emit_zeroes, false); + d->typed_dump->emit_strings = OPTS_GET(opts, emit_strings, false); ret = btf_dump_dump_type_data(d, NULL, t, id, data, 0, 0); diff --git a/tools/lib/bpf/btf_relocate.c b/tools/lib/bpf/btf_relocate.c index 17f8b32f94a0..53d1f3541bce 100644 --- a/tools/lib/bpf/btf_relocate.c +++ b/tools/lib/bpf/btf_relocate.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2024, Oracle and/or its affiliates. */ #ifndef _GNU_SOURCE @@ -212,7 +212,7 @@ static int btf_relocate_map_distilled_base(struct btf_relocate *r) * need to match both name and size, otherwise embedding the base * struct/union in the split type is invalid. */ - for (id = r->nr_dist_base_types; id < r->nr_split_types; id++) { + for (id = r->nr_dist_base_types; id < r->nr_dist_base_types + r->nr_split_types; id++) { err = btf_mark_embedded_composite_type_ids(r, id); if (err) goto done; @@ -428,7 +428,7 @@ static int btf_relocate_rewrite_strs(struct btf_relocate *r, __u32 i) } else { off = r->str_map[*str_off]; if (!off) { - pr_warn("string '%s' [offset %u] is not mapped to base BTF", + pr_warn("string '%s' [offset %u] is not mapped to base BTF\n", btf__str_by_offset(r->btf, off), *str_off); return -ENOENT; } diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c index c92e02394159..295dbda24580 100644 --- a/tools/lib/bpf/elf.c +++ b/tools/lib/bpf/elf.c @@ -9,7 +9,6 @@ #include <linux/kernel.h> #include "libbpf_internal.h" -#include "str_error.h" /* A SHT_GNU_versym section holds 16-bit words. This bit is set if * the symbol is hidden and can only be seen when referenced using an @@ -24,10 +23,12 @@ int elf_open(const char *binary_path, struct elf_fd *elf_fd) { - char errmsg[STRERR_BUFSIZE]; int fd, ret; Elf *elf; + elf_fd->elf = NULL; + elf_fd->fd = -1; + if (elf_version(EV_CURRENT) == EV_NONE) { pr_warn("elf: failed to init libelf for %s\n", binary_path); return -LIBBPF_ERRNO__LIBELF; @@ -35,8 +36,7 @@ int elf_open(const char *binary_path, struct elf_fd *elf_fd) fd = open(binary_path, O_RDONLY | O_CLOEXEC); if (fd < 0) { ret = -errno; - pr_warn("elf: failed to open %s: %s\n", binary_path, - libbpf_strerror_r(ret, errmsg, sizeof(errmsg))); + pr_warn("elf: failed to open %s: %s\n", binary_path, errstr(ret)); return ret; } elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c index 50befe125ddc..b842b83e2480 100644 --- a/tools/lib/bpf/features.c +++ b/tools/lib/bpf/features.c @@ -6,7 +6,6 @@ #include "libbpf.h" #include "libbpf_common.h" #include "libbpf_internal.h" -#include "str_error.h" static inline __u64 ptr_to_u64(const void *ptr) { @@ -47,7 +46,6 @@ static int probe_kern_prog_name(int token_fd) static int probe_kern_global_data(int token_fd) { - char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), @@ -67,9 +65,8 @@ static int probe_kern_global_data(int token_fd) map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts); if (map < 0) { ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); + pr_warn("Error in %s(): %s. Couldn't create simple array map.\n", + __func__, errstr(ret)); return ret; } @@ -267,7 +264,6 @@ static int probe_kern_probe_read_kernel(int token_fd) static int probe_prog_bind_map(int token_fd) { - char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -285,9 +281,8 @@ static int probe_prog_bind_map(int token_fd) map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts); if (map < 0) { ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); + pr_warn("Error in %s(): %s. Couldn't create simple array map.\n", + __func__, errstr(ret)); return ret; } @@ -604,7 +599,8 @@ bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_ } else if (ret == 0) { WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); } else { - pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); + pr_warn("Detection of kernel %s support failed: %s\n", + feat->desc, errstr(ret)); WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); } } diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index cf3323fd47b8..cd5c2543f54d 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -4,6 +4,7 @@ #include <stdlib.h> #include <string.h> #include <errno.h> +#include <asm/byteorder.h> #include <linux/filter.h> #include <sys/param.h> #include "btf.h" @@ -13,7 +14,6 @@ #include "hashmap.h" #include "bpf_gen_internal.h" #include "skel_internal.h" -#include <asm/byteorder.h> #define MAX_USED_MAPS 64 #define MAX_USED_PROGS 32 @@ -109,6 +109,7 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in static int add_data(struct bpf_gen *gen, const void *data, __u32 size); static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off); +static void emit_signature_match(struct bpf_gen *gen); void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps) { @@ -151,6 +152,8 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps /* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */ emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); emit(gen, BPF_EXIT_INSN()); + if (OPTS_GET(gen->opts, gen_hash, false)) + emit_signature_match(gen); } static int add_data(struct bpf_gen *gen, const void *data, __u32 size) @@ -367,6 +370,8 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off) __emit_sys_close(gen); } +static void compute_sha_update_offsets(struct bpf_gen *gen); + int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) { int i; @@ -393,7 +398,10 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) blob_fd_array_off(gen, i)); emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0)); emit(gen, BPF_EXIT_INSN()); - pr_debug("gen: finish %d\n", gen->error); + if (OPTS_GET(gen->opts, gen_hash, false)) + compute_sha_update_offsets(gen); + + pr_debug("gen: finish %s\n", errstr(gen->error)); if (!gen->error) { struct gen_loader_opts *opts = gen->opts; @@ -401,6 +409,15 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) opts->insns_sz = gen->insn_cur - gen->insn_start; opts->data = gen->data_start; opts->data_sz = gen->data_cur - gen->data_start; + + /* use target endianness for embedded loader */ + if (gen->swapped_endian) { + struct bpf_insn *insn = (struct bpf_insn *)opts->insns; + int insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); + + for (i = 0; i < insn_cnt; i++) + bpf_insn_bswap(insn++); + } } return gen->error; } @@ -414,6 +431,44 @@ void bpf_gen__free(struct bpf_gen *gen) free(gen); } +/* + * Fields of bpf_attr are set to values in native byte-order before being + * written to the target-bound data blob, and may need endian conversion. + * This macro allows providing the correct value in situ more simply than + * writing a separate converter for *all fields* of *all records* included + * in union bpf_attr. Note that sizeof(rval) should match the assignment + * target to avoid runtime problems. + */ +#define tgt_endian(rval) ({ \ + typeof(rval) _val = (rval); \ + if (gen->swapped_endian) { \ + switch (sizeof(_val)) { \ + case 1: break; \ + case 2: _val = bswap_16(_val); break; \ + case 4: _val = bswap_32(_val); break; \ + case 8: _val = bswap_64(_val); break; \ + default: pr_warn("unsupported bswap size!\n"); \ + } \ + } \ + _val; \ +}) + +static void compute_sha_update_offsets(struct bpf_gen *gen) +{ + __u64 sha[SHA256_DWORD_SIZE]; + __u64 sha_dw; + int i; + + libbpf_sha256(gen->data_start, gen->data_cur - gen->data_start, (__u8 *)sha); + for (i = 0; i < SHA256_DWORD_SIZE; i++) { + struct bpf_insn *insn = + (struct bpf_insn *)(gen->insn_start + gen->hash_insn_offset[i]); + sha_dw = tgt_endian(sha[i]); + insn[0].imm = (__u32)sha_dw; + insn[1].imm = sha_dw >> 32; + } +} + void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, __u32 btf_raw_size) { @@ -422,11 +477,12 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: load_btf: size %d\n", btf_raw_size); btf_data = add_data(gen, btf_raw_data, btf_raw_size); - attr.btf_size = btf_raw_size; + attr.btf_size = tgt_endian(btf_raw_size); btf_load_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: load_btf: off %d size %d, attr: off %d size %d\n", + btf_data, btf_raw_size, btf_load_attr, attr_size); /* populate union bpf_attr with user provided log details */ move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_level), 4, @@ -457,28 +513,29 @@ void bpf_gen__map_create(struct bpf_gen *gen, union bpf_attr attr; memset(&attr, 0, attr_size); - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = value_size; - attr.map_flags = map_attr->map_flags; - attr.map_extra = map_attr->map_extra; + attr.map_type = tgt_endian(map_type); + attr.key_size = tgt_endian(key_size); + attr.value_size = tgt_endian(value_size); + attr.map_flags = tgt_endian(map_attr->map_flags); + attr.map_extra = tgt_endian(map_attr->map_extra); if (map_name) libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); - attr.numa_node = map_attr->numa_node; - attr.map_ifindex = map_attr->map_ifindex; - attr.max_entries = max_entries; - attr.btf_key_type_id = map_attr->btf_key_type_id; - attr.btf_value_type_id = map_attr->btf_value_type_id; - - pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n", - attr.map_name, map_idx, map_type, attr.btf_value_type_id); + attr.numa_node = tgt_endian(map_attr->numa_node); + attr.map_ifindex = tgt_endian(map_attr->map_ifindex); + attr.max_entries = tgt_endian(max_entries); + attr.btf_key_type_id = tgt_endian(map_attr->btf_key_type_id); + attr.btf_value_type_id = tgt_endian(map_attr->btf_value_type_id); map_create_attr = add_data(gen, &attr, attr_size); - if (attr.btf_value_type_id) + pr_debug("gen: map_create: %s idx %d type %d value_type_id %d, attr: off %d size %d\n", + map_name, map_idx, map_type, map_attr->btf_value_type_id, + map_create_attr, attr_size); + + if (map_attr->btf_value_type_id) /* populate union bpf_attr with btf_fd saved in the stack earlier */ move_stack2blob(gen, attr_field(map_create_attr, btf_fd), 4, stack_off(btf_fd)); - switch (attr.map_type) { + switch (map_type) { case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: move_stack2blob(gen, attr_field(map_create_attr, inner_map_fd), 4, @@ -498,8 +555,8 @@ void bpf_gen__map_create(struct bpf_gen *gen, /* emit MAP_CREATE command */ emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size); debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d", - attr.map_name, map_idx, map_type, value_size, - attr.btf_value_type_id); + map_name, map_idx, map_type, value_size, + map_attr->btf_value_type_id); emit_check_err(gen); /* remember map_fd in the stack, if successful */ if (map_idx < 0) { @@ -523,6 +580,29 @@ void bpf_gen__map_create(struct bpf_gen *gen, emit_sys_close_stack(gen, stack_off(inner_map_fd)); } +static void emit_signature_match(struct bpf_gen *gen) +{ + __s64 off; + int i; + + for (i = 0; i < SHA256_DWORD_SIZE; i++) { + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX, + 0, 0, 0, 0)); + emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, i * sizeof(__u64))); + gen->hash_insn_offset[i] = gen->insn_cur - gen->insn_start; + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_3, 0, 0, 0, 0, 0)); + + off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1; + if (is_simm16(off)) { + emit(gen, BPF_MOV64_IMM(BPF_REG_7, -EINVAL)); + emit(gen, BPF_JMP_REG(BPF_JNE, BPF_REG_2, BPF_REG_3, off)); + } else { + gen->error = -ERANGE; + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1)); + } + } +} + void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name, enum bpf_attach_type type) { @@ -784,12 +864,12 @@ log: emit_ksym_relo_log(gen, relo, kdesc->ref); } -static __u32 src_reg_mask(void) +static __u32 src_reg_mask(struct bpf_gen *gen) { -#if defined(__LITTLE_ENDIAN_BITFIELD) - return 0x0f; /* src_reg,dst_reg,... */ -#elif defined(__BIG_ENDIAN_BITFIELD) - return 0xf0; /* dst_reg,src_reg,... */ +#if defined(__LITTLE_ENDIAN_BITFIELD) /* src_reg,dst_reg,... */ + return gen->swapped_endian ? 0xf0 : 0x0f; +#elif defined(__BIG_ENDIAN_BITFIELD) /* dst_reg,src_reg,... */ + return gen->swapped_endian ? 0x0f : 0xf0; #else #error "Unsupported bit endianness, cannot proceed" #endif @@ -840,7 +920,7 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 3)); clear_src_reg: /* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */ - reg_mask = src_reg_mask(); + reg_mask = src_reg_mask(gen); emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code))); emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask)); emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code))); @@ -931,48 +1011,94 @@ static void cleanup_relos(struct bpf_gen *gen, int insns) cleanup_core_relo(gen); } +/* Convert func, line, and core relo info blobs to target endianness */ +static void info_blob_bswap(struct bpf_gen *gen, int func_info, int line_info, + int core_relos, struct bpf_prog_load_opts *load_attr) +{ + struct bpf_func_info *fi = gen->data_start + func_info; + struct bpf_line_info *li = gen->data_start + line_info; + struct bpf_core_relo *cr = gen->data_start + core_relos; + int i; + + for (i = 0; i < load_attr->func_info_cnt; i++) + bpf_func_info_bswap(fi++); + + for (i = 0; i < load_attr->line_info_cnt; i++) + bpf_line_info_bswap(li++); + + for (i = 0; i < gen->core_relo_cnt; i++) + bpf_core_relo_bswap(cr++); +} + void bpf_gen__prog_load(struct bpf_gen *gen, enum bpf_prog_type prog_type, const char *prog_name, const char *license, struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *load_attr, int prog_idx) { + int func_info_tot_sz = load_attr->func_info_cnt * + load_attr->func_info_rec_size; + int line_info_tot_sz = load_attr->line_info_cnt * + load_attr->line_info_rec_size; + int core_relo_tot_sz = gen->core_relo_cnt * + sizeof(struct bpf_core_relo); int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos; int attr_size = offsetofend(union bpf_attr, core_relo_rec_size); union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n", - prog_type, insn_cnt, prog_idx); /* add license string to blob of bytes */ license_off = add_data(gen, license, strlen(license) + 1); /* add insns to blob of bytes */ insns_off = add_data(gen, insns, insn_cnt * sizeof(struct bpf_insn)); + pr_debug("gen: prog_load: prog_idx %d type %d insn off %d insns_cnt %zd license off %d\n", + prog_idx, prog_type, insns_off, insn_cnt, license_off); - attr.prog_type = prog_type; - attr.expected_attach_type = load_attr->expected_attach_type; - attr.attach_btf_id = load_attr->attach_btf_id; - attr.prog_ifindex = load_attr->prog_ifindex; - attr.kern_version = 0; - attr.insn_cnt = (__u32)insn_cnt; - attr.prog_flags = load_attr->prog_flags; - - attr.func_info_rec_size = load_attr->func_info_rec_size; - attr.func_info_cnt = load_attr->func_info_cnt; - func_info = add_data(gen, load_attr->func_info, - attr.func_info_cnt * attr.func_info_rec_size); + /* convert blob insns to target endianness */ + if (gen->swapped_endian) { + struct bpf_insn *insn = gen->data_start + insns_off; + int i; - attr.line_info_rec_size = load_attr->line_info_rec_size; - attr.line_info_cnt = load_attr->line_info_cnt; - line_info = add_data(gen, load_attr->line_info, - attr.line_info_cnt * attr.line_info_rec_size); + for (i = 0; i < insn_cnt; i++, insn++) + bpf_insn_bswap(insn); + } - attr.core_relo_rec_size = sizeof(struct bpf_core_relo); - attr.core_relo_cnt = gen->core_relo_cnt; - core_relos = add_data(gen, gen->core_relos, - attr.core_relo_cnt * attr.core_relo_rec_size); + attr.prog_type = tgt_endian(prog_type); + attr.expected_attach_type = tgt_endian(load_attr->expected_attach_type); + attr.attach_btf_id = tgt_endian(load_attr->attach_btf_id); + attr.prog_ifindex = tgt_endian(load_attr->prog_ifindex); + attr.kern_version = 0; + attr.insn_cnt = tgt_endian((__u32)insn_cnt); + attr.prog_flags = tgt_endian(load_attr->prog_flags); + + attr.func_info_rec_size = tgt_endian(load_attr->func_info_rec_size); + attr.func_info_cnt = tgt_endian(load_attr->func_info_cnt); + func_info = add_data(gen, load_attr->func_info, func_info_tot_sz); + pr_debug("gen: prog_load: func_info: off %d cnt %d rec size %d\n", + func_info, load_attr->func_info_cnt, + load_attr->func_info_rec_size); + + attr.line_info_rec_size = tgt_endian(load_attr->line_info_rec_size); + attr.line_info_cnt = tgt_endian(load_attr->line_info_cnt); + line_info = add_data(gen, load_attr->line_info, line_info_tot_sz); + pr_debug("gen: prog_load: line_info: off %d cnt %d rec size %d\n", + line_info, load_attr->line_info_cnt, + load_attr->line_info_rec_size); + + attr.core_relo_rec_size = tgt_endian((__u32)sizeof(struct bpf_core_relo)); + attr.core_relo_cnt = tgt_endian(gen->core_relo_cnt); + core_relos = add_data(gen, gen->core_relos, core_relo_tot_sz); + pr_debug("gen: prog_load: core_relos: off %d cnt %d rec size %zd\n", + core_relos, gen->core_relo_cnt, + sizeof(struct bpf_core_relo)); + + /* convert all info blobs to target endianness */ + if (gen->swapped_endian) + info_blob_bswap(gen, func_info, line_info, core_relos, load_attr); libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); prog_load_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: prog_load: attr: off %d size %d\n", + prog_load_attr, attr_size); /* populate union bpf_attr with a pointer to license */ emit_rel_store(gen, attr_field(prog_load_attr, license), license_off); @@ -1040,7 +1166,6 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, int zero = 0; memset(&attr, 0, attr_size); - pr_debug("gen: map_update_elem: idx %d\n", map_idx); value = add_data(gen, pvalue, value_size); key = add_data(gen, &zero, sizeof(zero)); @@ -1068,6 +1193,8 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); map_update_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: map_update_elem: idx %d, value: off %d size %d, attr: off %d size %d\n", + map_idx, value, value_size, map_update_attr, attr_size); move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, blob_fd_array_off(gen, map_idx)); emit_rel_store(gen, attr_field(map_update_attr, key), key); @@ -1084,14 +1211,16 @@ void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slo int attr_size = offsetofend(union bpf_attr, flags); int map_update_attr, key; union bpf_attr attr; + int tgt_slot; memset(&attr, 0, attr_size); - pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n", - outer_map_idx, slot, inner_map_idx); - key = add_data(gen, &slot, sizeof(slot)); + tgt_slot = tgt_endian(slot); + key = add_data(gen, &tgt_slot, sizeof(tgt_slot)); map_update_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: populate_outer_map: outer %d key %d inner %d, attr: off %d size %d\n", + outer_map_idx, slot, inner_map_idx, map_update_attr, attr_size); move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, blob_fd_array_off(gen, outer_map_idx)); emit_rel_store(gen, attr_field(map_update_attr, key), key); @@ -1112,8 +1241,9 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx) union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: map_freeze: idx %d\n", map_idx); map_freeze_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: map_freeze: idx %d, attr: off %d size %d\n", + map_idx, map_freeze_attr, attr_size); move_blob2blob(gen, attr_field(map_freeze_attr, map_fd), 4, blob_fd_array_off(gen, map_idx)); /* emit MAP_FREEZE command */ diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index c12f8320e668..0c4f155e8eb7 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -166,8 +166,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value); * @bkt: integer used as a bucket loop cursor */ #define hashmap__for_each_entry(map, cur, bkt) \ - for (bkt = 0; bkt < map->cap; bkt++) \ - for (cur = map->buckets[bkt]; cur; cur = cur->next) + for (bkt = 0; bkt < (map)->cap; bkt++) \ + for (cur = (map)->buckets[bkt]; cur; cur = cur->next) /* * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe @@ -178,8 +178,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value); * @bkt: integer used as a bucket loop cursor */ #define hashmap__for_each_entry_safe(map, cur, tmp, bkt) \ - for (bkt = 0; bkt < map->cap; bkt++) \ - for (cur = map->buckets[bkt]; \ + for (bkt = 0; bkt < (map)->cap; bkt++) \ + for (cur = (map)->buckets[bkt]; \ cur && ({tmp = cur->next; true; }); \ cur = tmp) @@ -190,19 +190,19 @@ bool hashmap_find(const struct hashmap *map, long key, long *value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = map->buckets \ - ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + for (cur = (map)->buckets \ + ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \ : NULL; \ cur; \ cur = cur->next) \ - if (map->equal_fn(cur->key, (_key), map->ctx)) + if ((map)->equal_fn(cur->key, (_key), (map)->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = map->buckets \ - ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + for (cur = (map)->buckets \ + ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \ : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ - if (map->equal_fn(cur->key, (_key), map->ctx)) + if ((map)->equal_fn(cur->key, (_key), (map)->ctx)) #endif /* __LIBBPF_HASHMAP_H */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a3be6f8fac09..3dc8a8078815 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -50,7 +50,6 @@ #include "libbpf.h" #include "bpf.h" #include "btf.h" -#include "str_error.h" #include "libbpf_internal.h" #include "hashmap.h" #include "bpf_gen_internal.h" @@ -60,6 +59,8 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif +#define MAX_EVENT_NAME_LEN 64 + #define BPF_FS_DEFAULT_PATH "/sys/fs/bpf" #define BPF_INSN_SZ (sizeof(struct bpf_insn)) @@ -133,6 +134,7 @@ static const char * const attach_type_name[] = { [BPF_NETKIT_PRIMARY] = "netkit_primary", [BPF_NETKIT_PEER] = "netkit_peer", [BPF_TRACE_KPROBE_SESSION] = "trace_kprobe_session", + [BPF_TRACE_UPROBE_SESSION] = "trace_uprobe_session", }; static const char * const link_type_name[] = { @@ -188,6 +190,7 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_USER_RINGBUF] = "user_ringbuf", [BPF_MAP_TYPE_CGRP_STORAGE] = "cgrp_storage", [BPF_MAP_TYPE_ARENA] = "arena", + [BPF_MAP_TYPE_INSN_ARRAY] = "insn_array", }; static const char * const prog_type_name[] = { @@ -283,7 +286,7 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...) old_errno = errno; va_start(args, format); - __libbpf_pr(level, format, args); + print_fn(level, format, args); va_end(args); errno = old_errno; @@ -315,8 +318,6 @@ static void pr_perm_msg(int err) buf); } -#define STRERR_BUFSIZE 128 - /* Copied from tools/perf/util/util.h */ #ifndef zfree # define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) @@ -369,6 +370,7 @@ enum reloc_type { RELO_EXTERN_CALL, RELO_SUBPROG_ADDR, RELO_CORE, + RELO_INSN_ARRAY, }; struct reloc_desc { @@ -379,7 +381,16 @@ struct reloc_desc { struct { int map_idx; int sym_off; - int ext_idx; + /* + * The following two fields can be unionized, as the + * ext_idx field is used for extern symbols, and the + * sym_size is used for jump tables, which are never + * extern + */ + union { + int ext_idx; + int sym_size; + }; }; }; }; @@ -421,6 +432,11 @@ struct bpf_sec_def { libbpf_prog_attach_fn_t prog_attach_fn; }; +struct bpf_light_subprog { + __u32 sec_insn_off; + __u32 sub_insn_off; +}; + /* * bpf_prog should be a better name but it has been used in * linux/filter.h. @@ -493,11 +509,13 @@ struct bpf_program { __u32 line_info_rec_size; __u32 line_info_cnt; __u32 prog_flags; + __u8 hash[SHA256_DIGEST_LENGTH]; + + struct bpf_light_subprog *subprogs; + __u32 subprog_cnt; }; struct bpf_struct_ops { - const char *tname; - const struct btf_type *type; struct bpf_program **progs; __u32 *kern_func_off; /* e.g. struct tcp_congestion_ops in bpf_prog's btf format */ @@ -574,6 +592,7 @@ struct bpf_map { bool autocreate; bool autoattach; __u64 map_extra; + struct bpf_program *excl_prog; }; enum extern_type { @@ -596,7 +615,7 @@ struct extern_desc { int sym_idx; int btf_id; int sec_btf_id; - const char *name; + char *name; char *essent_name; bool is_set; bool is_weak; @@ -667,15 +686,23 @@ struct elf_state { int symbols_shndx; bool has_st_ops; int arena_data_shndx; + int jumptables_data_shndx; }; struct usdt_manager; +enum bpf_object_state { + OBJ_OPEN, + OBJ_PREPARED, + OBJ_LOADED, +}; + struct bpf_object { char name[BPF_OBJ_NAME_LEN]; char license[64]; __u32 kern_version; + enum bpf_object_state state; struct bpf_program *programs; size_t nr_programs; struct bpf_map *maps; @@ -687,7 +714,6 @@ struct bpf_object { int nr_extern; int kconfig_map_idx; - bool loaded; bool has_subcalls; bool has_rodata; @@ -696,6 +722,8 @@ struct bpf_object { /* Information when doing ELF related work. Only valid if efile.elf is not NULL */ struct elf_state efile; + unsigned char byteorder; + struct btf *btf; struct btf_ext *btf_ext; @@ -726,10 +754,20 @@ struct bpf_object { struct usdt_manager *usdt_man; - struct bpf_map *arena_map; + int arena_map_idx; void *arena_data; size_t arena_data_sz; + void *jumptables_data; + size_t jumptables_data_sz; + + struct { + struct bpf_program *prog; + int sym_off; + int fd; + } *jumptable_maps; + size_t jumptable_map_cnt; + struct kern_feature_cache *feat_cache; char *token_path; int token_fd; @@ -756,6 +794,7 @@ void bpf_program__unload(struct bpf_program *prog) zfree(&prog->func_info); zfree(&prog->line_info); + zfree(&prog->subprogs); } static void bpf_program__exit(struct bpf_program *prog) @@ -889,7 +928,7 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return -LIBBPF_ERRNO__FORMAT; } - if (sec_off + prog_sz > sec_sz) { + if (sec_off + prog_sz > sec_sz || sec_off + prog_sz < sec_off) { pr_warn("sec '%s': program at offset %zu crosses section boundary\n", sec_name, sec_off); return -LIBBPF_ERRNO__FORMAT; @@ -942,6 +981,20 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return 0; } +static void bpf_object_bswap_progs(struct bpf_object *obj) +{ + struct bpf_program *prog = obj->programs; + struct bpf_insn *insn; + int p, i; + + for (p = 0; p < obj->nr_programs; p++, prog++) { + insn = prog->insns; + for (i = 0; i < prog->insns_cnt; i++, insn++) + bpf_insn_bswap(insn); + } + pr_debug("converted %zu BPF programs to native byte order\n", obj->nr_programs); +} + static const struct btf_member * find_member_by_offset(const struct btf_type *t, __u32 bit_offset) { @@ -988,37 +1041,35 @@ find_struct_ops_kern_types(struct bpf_object *obj, const char *tname_raw, { const struct btf_type *kern_type, *kern_vtype; const struct btf_member *kern_data_member; - struct btf *btf; + struct btf *btf = NULL; __s32 kern_vtype_id, kern_type_id; - char tname[256]; + char tname[192], stname[256]; __u32 i; snprintf(tname, sizeof(tname), "%.*s", (int)bpf_core_essential_name_len(tname_raw), tname_raw); - kern_type_id = find_ksym_btf_id(obj, tname, BTF_KIND_STRUCT, - &btf, mod_btf); - if (kern_type_id < 0) { - pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", - tname); - return kern_type_id; - } - kern_type = btf__type_by_id(btf, kern_type_id); + snprintf(stname, sizeof(stname), "%s%s", STRUCT_OPS_VALUE_PREFIX, tname); - /* Find the corresponding "map_value" type that will be used - * in map_update(BPF_MAP_TYPE_STRUCT_OPS). For example, - * find "struct bpf_struct_ops_tcp_congestion_ops" from the - * btf_vmlinux. + /* Look for the corresponding "map_value" type that will be used + * in map_update(BPF_MAP_TYPE_STRUCT_OPS) first, figure out the btf + * and the mod_btf. + * For example, find "struct bpf_struct_ops_tcp_congestion_ops". */ - kern_vtype_id = find_btf_by_prefix_kind(btf, STRUCT_OPS_VALUE_PREFIX, - tname, BTF_KIND_STRUCT); + kern_vtype_id = find_ksym_btf_id(obj, stname, BTF_KIND_STRUCT, &btf, mod_btf); if (kern_vtype_id < 0) { - pr_warn("struct_ops init_kern: struct %s%s is not found in kernel BTF\n", - STRUCT_OPS_VALUE_PREFIX, tname); + pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", stname); return kern_vtype_id; } kern_vtype = btf__type_by_id(btf, kern_vtype_id); + kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); + if (kern_type_id < 0) { + pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", tname); + return kern_type_id; + } + kern_type = btf__type_by_id(btf, kern_type_id); + /* Find "struct tcp_congestion_ops" from * struct bpf_struct_ops_tcp_congestion_ops { * [ ... ] @@ -1031,8 +1082,8 @@ find_struct_ops_kern_types(struct bpf_object *obj, const char *tname_raw, break; } if (i == btf_vlen(kern_vtype)) { - pr_warn("struct_ops init_kern: struct %s data is not found in struct %s%s\n", - tname, STRUCT_OPS_VALUE_PREFIX, tname); + pr_warn("struct_ops init_kern: struct %s data is not found in struct %s\n", + tname, stname); return -EINVAL; } @@ -1083,11 +1134,14 @@ static int bpf_object_adjust_struct_ops_autoload(struct bpf_object *obj) continue; for (j = 0; j < obj->nr_maps; ++j) { + const struct btf_type *type; + map = &obj->maps[j]; if (!bpf_map__is_struct_ops(map)) continue; - vlen = btf_vlen(map->st_ops->type); + type = btf__type_by_id(obj->btf, map->st_ops->type_id); + vlen = btf_vlen(type); for (k = 0; k < vlen; ++k) { slot_prog = map->st_ops->progs[k]; if (prog != slot_prog) @@ -1115,14 +1169,14 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map) const struct btf *btf = obj->btf; struct bpf_struct_ops *st_ops; const struct btf *kern_btf; - struct module_btf *mod_btf; + struct module_btf *mod_btf = NULL; void *data, *kern_data; const char *tname; int err; st_ops = map->st_ops; - type = st_ops->type; - tname = st_ops->tname; + type = btf__type_by_id(btf, st_ops->type_id); + tname = btf__name_by_offset(btf, type->name_off); err = find_struct_ops_kern_types(obj, tname, &mod_btf, &kern_type, &kern_type_id, &kern_vtype, &kern_vtype_id, @@ -1423,8 +1477,6 @@ static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name, memcpy(st_ops->data, data->d_buf + vsi->offset, type->size); - st_ops->tname = tname; - st_ops->type = type; st_ops->type_id = type_id; pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n", @@ -1493,9 +1545,10 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.btf_maps_shndx = -1; obj->kconfig_map_idx = -1; + obj->arena_map_idx = -1; obj->kern_version = get_kernel_version(); - obj->loaded = false; + obj->state = OBJ_OPEN; return obj; } @@ -1507,6 +1560,7 @@ static void bpf_object__elf_finish(struct bpf_object *obj) elf_end(obj->efile.elf); obj->efile.elf = NULL; + obj->efile.ehdr = NULL; obj->efile.symbols = NULL; obj->efile.arena_data = NULL; @@ -1534,11 +1588,8 @@ static int bpf_object__elf_init(struct bpf_object *obj) } else { obj->efile.fd = open(obj->path, O_RDONLY | O_CLOEXEC); if (obj->efile.fd < 0) { - char errmsg[STRERR_BUFSIZE], *cp; - err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("elf: failed to open %s: %s\n", obj->path, cp); + pr_warn("elf: failed to open %s: %s\n", obj->path, errstr(err)); return err; } @@ -1572,6 +1623,16 @@ static int bpf_object__elf_init(struct bpf_object *obj) goto errout; } + /* Validate ELF object endianness... */ + if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB && + ehdr->e_ident[EI_DATA] != ELFDATA2MSB) { + err = -LIBBPF_ERRNO__ENDIAN; + pr_warn("elf: '%s' has unknown byte order\n", obj->path); + goto errout; + } + /* and save after bpf_object_open() frees ELF data */ + obj->byteorder = ehdr->e_ident[EI_DATA]; + if (elf_getshdrstrndx(elf, &obj->efile.shstrndx)) { pr_warn("elf: failed to get section names section index for %s: %s\n", obj->path, elf_errmsg(-1)); @@ -1600,19 +1661,15 @@ errout: return err; } -static int bpf_object__check_endianness(struct bpf_object *obj) +static bool is_native_endianness(struct bpf_object *obj) { #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ - if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2LSB) - return 0; + return obj->byteorder == ELFDATA2LSB; #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2MSB) - return 0; + return obj->byteorder == ELFDATA2MSB; #else # error "Unrecognized __BYTE_ORDER__" #endif - pr_warn("elf: endianness mismatch in %s.\n", obj->path); - return -LIBBPF_ERRNO__ENDIAN; } static int @@ -1699,24 +1756,27 @@ static Elf64_Sym *find_elf_var_sym(const struct bpf_object *obj, const char *nam return ERR_PTR(-ENOENT); } -/* Some versions of Android don't provide memfd_create() in their libc - * implementation, so avoid complications and just go straight to Linux - * syscall. - */ -static int sys_memfd_create(const char *name, unsigned flags) -{ - return syscall(__NR_memfd_create, name, flags); -} - #ifndef MFD_CLOEXEC #define MFD_CLOEXEC 0x0001U #endif +#ifndef MFD_NOEXEC_SEAL +#define MFD_NOEXEC_SEAL 0x0008U +#endif static int create_placeholder_fd(void) { + unsigned int flags = MFD_CLOEXEC | MFD_NOEXEC_SEAL; + const char *name = "libbpf-placeholder-fd"; int fd; - fd = ensure_good_fd(sys_memfd_create("libbpf-placeholder-fd", MFD_CLOEXEC)); + fd = ensure_good_fd(sys_memfd_create(name, flags)); + if (fd >= 0) + return fd; + else if (errno != EINVAL) + return -errno; + + /* Possibly running on kernel without MFD_NOEXEC_SEAL */ + fd = ensure_good_fd(sys_memfd_create(name, flags & ~MFD_NOEXEC_SEAL)); if (fd < 0) return -errno; return fd; @@ -1849,7 +1909,7 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name) snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name, sfx_len, real_name); - /* sanitise map name to characters allowed by kernel */ + /* sanities map name to characters allowed by kernel */ for (p = map_name; *p && p < map_name + sizeof(map_name); p++) if (!isalnum(*p) && *p != '_' && *p != '.') *p = '_'; @@ -1938,8 +1998,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, if (map->mmaped == MAP_FAILED) { err = -errno; map->mmaped = NULL; - pr_warn("failed to alloc map '%s' content buffer: %d\n", - map->name, err); + pr_warn("failed to alloc map '%s' content buffer: %s\n", map->name, errstr(err)); zfree(&map->real_name); zfree(&map->name); return err; @@ -2075,7 +2134,7 @@ static int set_kcfg_value_str(struct extern_desc *ext, char *ext_val, } len = strlen(value); - if (value[len - 1] != '"') { + if (len < 2 || value[len - 1] != '"') { pr_warn("extern (kcfg) '%s': invalid string config '%s'\n", ext->name, value); return -EINVAL; @@ -2103,7 +2162,7 @@ static int parse_u64(const char *value, __u64 *res) *res = strtoull(value, &value_end, 0); if (errno) { err = -errno; - pr_warn("failed to parse '%s' as integer: %d\n", value, err); + pr_warn("failed to parse '%s': %s\n", value, errstr(err)); return err; } if (*value_end) { @@ -2269,8 +2328,8 @@ static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data) while (gzgets(file, buf, sizeof(buf))) { err = bpf_object__process_kconfig_line(obj, buf, data); if (err) { - pr_warn("error parsing system Kconfig line '%s': %d\n", - buf, err); + pr_warn("error parsing system Kconfig line '%s': %s\n", + buf, errstr(err)); goto out; } } @@ -2290,15 +2349,15 @@ static int bpf_object__read_kconfig_mem(struct bpf_object *obj, file = fmemopen((void *)config, strlen(config), "r"); if (!file) { err = -errno; - pr_warn("failed to open in-memory Kconfig: %d\n", err); + pr_warn("failed to open in-memory Kconfig: %s\n", errstr(err)); return err; } while (fgets(buf, sizeof(buf), file)) { err = bpf_object__process_kconfig_line(obj, buf, data); if (err) { - pr_warn("error parsing in-memory Kconfig line '%s': %d\n", - buf, err); + pr_warn("error parsing in-memory Kconfig line '%s': %s\n", + buf, errstr(err)); break; } } @@ -2934,7 +2993,7 @@ static int init_arena_map_data(struct bpf_object *obj, struct bpf_map *map, const long page_sz = sysconf(_SC_PAGE_SIZE); size_t mmap_sz; - mmap_sz = bpf_map_mmap_sz(obj->arena_map); + mmap_sz = bpf_map_mmap_sz(map); if (roundup(data_sz, page_sz) > mmap_sz) { pr_warn("elf: sec '%s': declared ARENA map size (%zu) is too small to hold global __arena variables of size %zu\n", sec_name, mmap_sz, data_sz); @@ -2968,7 +3027,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, scn = elf_sec_by_idx(obj, obj->efile.btf_maps_shndx); data = elf_sec_data(obj, scn); - if (!scn || !data) { + if (!data) { pr_warn("elf: failed to get %s map definitions for %s\n", MAPS_ELF_SEC, obj->path); return -EINVAL; @@ -3008,12 +3067,12 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, if (map->def.type != BPF_MAP_TYPE_ARENA) continue; - if (obj->arena_map) { + if (obj->arena_map_idx >= 0) { pr_warn("map '%s': only single ARENA map is supported (map '%s' is also ARENA)\n", - map->name, obj->arena_map->name); + map->name, obj->maps[obj->arena_map_idx].name); return -EINVAL; } - obj->arena_map = map; + obj->arena_map_idx = i; if (obj->efile.arena_data) { err = init_arena_map_data(obj, map, ARENA_SEC, obj->efile.arena_data_shndx, @@ -3023,7 +3082,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, return err; } } - if (obj->efile.arena_data && !obj->arena_map) { + if (obj->efile.arena_data && obj->arena_map_idx < 0) { pr_warn("elf: sec '%s': to use global __arena variables the ARENA map should be explicitly declared in SEC(\".maps\")\n", ARENA_SEC); return -ENOENT; @@ -3213,7 +3272,7 @@ static int bpf_object__init_btf(struct bpf_object *obj, err = libbpf_get_error(obj->btf); if (err) { obj->btf = NULL; - pr_warn("Error loading ELF section %s: %d.\n", BTF_ELF_SEC, err); + pr_warn("Error loading ELF section %s: %s.\n", BTF_ELF_SEC, errstr(err)); goto out; } /* enforce 8-byte pointers for BPF-targeted BTFs */ @@ -3231,8 +3290,8 @@ static int bpf_object__init_btf(struct bpf_object *obj, obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); err = libbpf_get_error(obj->btf_ext); if (err) { - pr_warn("Error loading ELF section %s: %d. Ignored and continue.\n", - BTF_EXT_ELF_SEC, err); + pr_warn("Error loading ELF section %s: %s. Ignored and continue.\n", + BTF_EXT_ELF_SEC, errstr(err)); obj->btf_ext = NULL; goto out; } @@ -3324,8 +3383,8 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, if (t->size == 0) { err = find_elf_sec_sz(obj, sec_name, &size); if (err || !size) { - pr_debug("sec '%s': failed to determine size from ELF: size %u, err %d\n", - sec_name, size, err); + pr_debug("sec '%s': failed to determine size from ELF: size %u, err %s\n", + sec_name, size, errstr(err)); return -ENOENT; } @@ -3479,7 +3538,7 @@ static int bpf_object__load_vmlinux_btf(struct bpf_object *obj, bool force) obj->btf_vmlinux = btf__load_vmlinux_btf(); err = libbpf_get_error(obj->btf_vmlinux); if (err) { - pr_warn("Error loading vmlinux BTF: %d\n", err); + pr_warn("Error loading vmlinux BTF: %s\n", errstr(err)); obj->btf_vmlinux = NULL; return err; } @@ -3582,11 +3641,14 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) report: if (err) { btf_mandatory = kernel_needs_btf(obj); - pr_warn("Error loading .BTF into kernel: %d. %s\n", err, - btf_mandatory ? "BTF is mandatory, can't proceed." - : "BTF is optional, ignoring."); - if (!btf_mandatory) + if (btf_mandatory) { + pr_warn("Error loading .BTF into kernel: %s. BTF is mandatory, can't proceed.\n", + errstr(err)); + } else { + pr_info("Error loading .BTF into kernel: %s. BTF is optional, ignoring.\n", + errstr(err)); err = 0; + } } return err; } @@ -3911,6 +3973,13 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } else if (strcmp(name, ARENA_SEC) == 0) { obj->efile.arena_data = data; obj->efile.arena_data_shndx = idx; + } else if (strcmp(name, JUMPTABLES_SEC) == 0) { + obj->jumptables_data = malloc(data->d_size); + if (!obj->jumptables_data) + return -ENOMEM; + memcpy(obj->jumptables_data, data->d_buf, data->d_size); + obj->jumptables_data_sz = data->d_size; + obj->efile.jumptables_data_shndx = idx; } else { pr_info("elf: skipping unrecognized data section(%d) %s\n", idx, name); @@ -3954,6 +4023,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj) return -LIBBPF_ERRNO__FORMAT; } + /* change BPF program insns to native endianness for introspection */ + if (!is_native_endianness(obj)) + bpf_object_bswap_progs(obj); + /* sort BPF programs by section name and in-section instruction offset * for faster search */ @@ -3986,7 +4059,7 @@ static bool sym_is_subprog(const Elf64_Sym *sym, int text_shndx) return true; /* global function */ - return bind == STB_GLOBAL && type == STT_FUNC; + return (bind == STB_GLOBAL || bind == STB_WEAK) && type == STT_FUNC; } static int find_extern_btf_id(const struct btf *btf, const char *ext_name) @@ -4222,7 +4295,9 @@ static int bpf_object__collect_externs(struct bpf_object *obj) return ext->btf_id; } t = btf__type_by_id(obj->btf, ext->btf_id); - ext->name = btf__name_by_offset(obj->btf, t->name_off); + ext->name = strdup(btf__name_by_offset(obj->btf, t->name_off)); + if (!ext->name) + return -ENOMEM; ext->sym_idx = i; ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK; @@ -4390,7 +4465,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj) static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog) { - return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; + return prog->sec_idx == obj->efile.text_shndx; } struct bpf_program * @@ -4445,6 +4520,44 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) } } +static int bpf_prog_compute_hash(struct bpf_program *prog) +{ + struct bpf_insn *purged; + int i, err = 0; + + purged = calloc(prog->insns_cnt, BPF_INSN_SZ); + if (!purged) + return -ENOMEM; + + /* If relocations have been done, the map_fd needs to be + * discarded for the digest calculation. + */ + for (i = 0; i < prog->insns_cnt; i++) { + purged[i] = prog->insns[i]; + if (purged[i].code == (BPF_LD | BPF_IMM | BPF_DW) && + (purged[i].src_reg == BPF_PSEUDO_MAP_FD || + purged[i].src_reg == BPF_PSEUDO_MAP_VALUE)) { + purged[i].imm = 0; + i++; + if (i >= prog->insns_cnt || + prog->insns[i].code != 0 || + prog->insns[i].dst_reg != 0 || + prog->insns[i].src_reg != 0 || + prog->insns[i].off != 0) { + err = -EINVAL; + goto out; + } + purged[i] = prog->insns[i]; + purged[i].imm = 0; + } + } + libbpf_sha256(purged, prog->insns_cnt * sizeof(struct bpf_insn), + prog->hash); +out: + free(purged); + return err; +} + static int bpf_program__record_reloc(struct bpf_program *prog, struct reloc_desc *reloc_desc, __u32 insn_idx, const char *sym_name, @@ -4542,10 +4655,30 @@ static int bpf_program__record_reloc(struct bpf_program *prog, /* arena data relocation */ if (shdr_idx == obj->efile.arena_data_shndx) { + if (obj->arena_map_idx < 0) { + pr_warn("prog '%s': bad arena data relocation at insn %u, no arena maps defined\n", + prog->name, insn_idx); + return -LIBBPF_ERRNO__RELOC; + } reloc_desc->type = RELO_DATA; reloc_desc->insn_idx = insn_idx; - reloc_desc->map_idx = obj->arena_map - obj->maps; + reloc_desc->map_idx = obj->arena_map_idx; + reloc_desc->sym_off = sym->st_value; + + map = &obj->maps[obj->arena_map_idx]; + pr_debug("prog '%s': found arena map %d (%s, sec %d, off %zu) for insn %u\n", + prog->name, obj->arena_map_idx, map->name, map->sec_idx, + map->sec_offset, insn_idx); + return 0; + } + + /* jump table data relocation */ + if (shdr_idx == obj->efile.jumptables_data_shndx) { + reloc_desc->type = RELO_INSN_ARRAY; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = -1; reloc_desc->sym_off = sym->st_value; + reloc_desc->sym_size = sym->st_size; return 0; } @@ -4784,8 +4917,8 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) fp = fopen(file, "re"); if (!fp) { err = -errno; - pr_warn("failed to open %s: %d. No procfs support?\n", file, - err); + pr_warn("failed to open %s: %s. No procfs support?\n", file, + errstr(err)); return err; } @@ -4807,6 +4940,11 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) return 0; } +static bool map_is_created(const struct bpf_map *map) +{ + return map->obj->state >= OBJ_PREPARED || map->reused; +} + bool bpf_map__autocreate(const struct bpf_map *map) { return map->autocreate; @@ -4814,7 +4952,7 @@ bool bpf_map__autocreate(const struct bpf_map *map) int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate) { - if (map->obj->loaded) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->autocreate = autocreate; @@ -4908,7 +5046,7 @@ struct bpf_map *bpf_map__inner_map(struct bpf_map *map) int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) { - if (map->obj->loaded) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->def.max_entries = max_entries; @@ -4940,8 +5078,8 @@ static int bpf_object_prepare_token(struct bpf_object *obj) bpffs_fd = open(bpffs_path, O_DIRECTORY, O_RDWR); if (bpffs_fd < 0) { err = -errno; - __pr(level, "object '%s': failed (%d) to open BPF FS mount at '%s'%s\n", - obj->name, err, bpffs_path, + __pr(level, "object '%s': failed (%s) to open BPF FS mount at '%s'%s\n", + obj->name, errstr(err), bpffs_path, mandatory ? "" : ", skipping optional step..."); return mandatory ? err : 0; } @@ -4975,7 +5113,6 @@ static int bpf_object_prepare_token(struct bpf_object *obj) static int bpf_object__probe_loading(struct bpf_object *obj) { - char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), @@ -4991,7 +5128,8 @@ bpf_object__probe_loading(struct bpf_object *obj) ret = bump_rlimit_memlock(); if (ret) - pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret); + pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %s), you might need to do it explicitly!\n", + errstr(ret)); /* make sure basic loading works */ ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &opts); @@ -4999,11 +5137,8 @@ bpf_object__probe_loading(struct bpf_object *obj) ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); if (ret < 0) { ret = errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't load trivial BPF " - "program. Make sure your kernel supports BPF " - "(CONFIG_BPF_SYSCALL=y) and/or that RLIMIT_MEMLOCK is " - "set to big enough value.\n", __func__, cp, ret); + pr_warn("Error in %s(): %s. Couldn't load trivial BPF program. Make sure your kernel supports BPF (CONFIG_BPF_SYSCALL=y) and/or that RLIMIT_MEMLOCK is set to big enough value.\n", + __func__, errstr(ret)); return -ret; } close(ret); @@ -5028,7 +5163,6 @@ bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) { struct bpf_map_info map_info; - char msg[STRERR_BUFSIZE]; __u32 map_info_len = sizeof(map_info); int err; @@ -5038,10 +5172,20 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) err = bpf_get_map_info_from_fdinfo(map_fd, &map_info); if (err) { pr_warn("failed to get map info for map FD %d: %s\n", map_fd, - libbpf_strerror_r(errno, msg, sizeof(msg))); + errstr(err)); return false; } + /* + * bpf_get_map_info_by_fd() for DEVMAP will always return flags with + * BPF_F_RDONLY_PROG set, but it generally is not set at map creation time. + * Thus, ignore the BPF_F_RDONLY_PROG flag in the flags returned from + * bpf_get_map_info_by_fd() when checking for compatibility with an + * existing DEVMAP. + */ + if (map->def.type == BPF_MAP_TYPE_DEVMAP || map->def.type == BPF_MAP_TYPE_DEVMAP_HASH) + map_info.map_flags &= ~BPF_F_RDONLY_PROG; + return (map_info.type == map->def.type && map_info.key_size == map->def.key_size && map_info.value_size == map->def.value_size && @@ -5053,7 +5197,6 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) static int bpf_object__reuse_map(struct bpf_map *map) { - char *cp, errmsg[STRERR_BUFSIZE]; int err, pin_fd; pin_fd = bpf_obj_get(map->pin_path); @@ -5065,9 +5208,8 @@ bpf_object__reuse_map(struct bpf_map *map) return 0; } - cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); pr_warn("couldn't retrieve pinned map '%s': %s\n", - map->pin_path, cp); + map->pin_path, errstr(err)); return err; } @@ -5093,8 +5235,8 @@ static int bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) { enum libbpf_map_type map_type = map->libbpf_type; - char *cp, errmsg[STRERR_BUFSIZE]; int err, zero = 0; + size_t mmap_sz; if (obj->gen_loader) { bpf_gen__map_update_elem(obj->gen_loader, map - obj->maps, @@ -5107,9 +5249,8 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0); if (err) { err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("Error setting initial map(%s) contents: %s\n", - map->name, cp); + pr_warn("map '%s': failed to set initial contents: %s\n", + bpf_map__name(map), errstr(err)); return err; } @@ -5118,22 +5259,48 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) err = bpf_map_freeze(map->fd); if (err) { err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("Error freezing map(%s) as read-only: %s\n", - map->name, cp); + pr_warn("map '%s': failed to freeze as read-only: %s\n", + bpf_map__name(map), errstr(err)); return err; } } + + /* Remap anonymous mmap()-ed "map initialization image" as + * a BPF map-backed mmap()-ed memory, but preserving the same + * memory address. This will cause kernel to change process' + * page table to point to a different piece of kernel memory, + * but from userspace point of view memory address (and its + * contents, being identical at this point) will stay the + * same. This mapping will be released by bpf_object__close() + * as per normal clean up procedure. + */ + mmap_sz = bpf_map_mmap_sz(map); + if (map->def.map_flags & BPF_F_MMAPABLE) { + void *mmaped; + int prot; + + if (map->def.map_flags & BPF_F_RDONLY_PROG) + prot = PROT_READ; + else + prot = PROT_READ | PROT_WRITE; + mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map->fd, 0); + if (mmaped == MAP_FAILED) { + err = -errno; + pr_warn("map '%s': failed to re-mmap() contents: %s\n", + bpf_map__name(map), errstr(err)); + return err; + } + map->mmaped = mmaped; + } else if (map->mmaped) { + munmap(map->mmaped, mmap_sz); + map->mmaped = NULL; + } + return 0; } static void bpf_map__destroy(struct bpf_map *map); -static bool map_is_created(const struct bpf_map *map) -{ - return map->obj->loaded || map->reused; -} - static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner) { LIBBPF_OPTS(bpf_map_create_opts, create_attr); @@ -5150,6 +5317,14 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.token_fd = obj->token_fd; if (obj->token_fd) create_attr.map_flags |= BPF_F_TOKEN_FD; + if (map->excl_prog) { + err = bpf_prog_compute_hash(map->excl_prog); + if (err) + return err; + + create_attr.excl_prog_hash = map->excl_prog->hash; + create_attr.excl_prog_hash_size = SHA256_DIGEST_LENGTH; + } if (bpf_map__is_struct_ops(map)) { create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; @@ -5172,8 +5347,8 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b return err; err = bpf_object__create_map(obj, map->inner_map, true); if (err) { - pr_warn("map '%s': failed to create inner map: %d\n", - map->name, err); + pr_warn("map '%s': failed to create inner map: %s\n", + map->name, errstr(err)); return err; } map->inner_map_fd = map->inner_map->fd; @@ -5227,12 +5402,9 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b def->max_entries, &create_attr); } if (map_fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { - char *cp, errmsg[STRERR_BUFSIZE]; - err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", - map->name, cp, err); + pr_warn("Error in bpf_create_map_xattr(%s): %s. Retrying without BTF.\n", + map->name, errstr(err)); create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; @@ -5287,8 +5459,8 @@ static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map) } if (err) { err = -errno; - pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", - map->name, i, targ_map->name, fd, err); + pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %s\n", + map->name, i, targ_map->name, fd, errstr(err)); return err; } pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n", @@ -5320,8 +5492,8 @@ static int init_prog_array_slots(struct bpf_object *obj, struct bpf_map *map) err = bpf_map_update_elem(map->fd, &i, &fd, 0); if (err) { err = -errno; - pr_warn("map '%s': failed to initialize slot [%d] to prog '%s' fd=%d: %d\n", - map->name, i, targ_prog->name, fd, err); + pr_warn("map '%s': failed to initialize slot [%d] to prog '%s' fd=%d: %s\n", + map->name, i, targ_prog->name, fd, errstr(err)); return err; } pr_debug("map '%s': slot [%d] set to prog '%s' fd=%d\n", @@ -5374,7 +5546,6 @@ static int bpf_object__create_maps(struct bpf_object *obj) { struct bpf_map *map; - char *cp, errmsg[STRERR_BUFSIZE]; unsigned int i, j; int err; bool retried; @@ -5440,8 +5611,7 @@ retry: err = bpf_object__populate_internal_map(obj, map); if (err < 0) goto err_out; - } - if (map->def.type == BPF_MAP_TYPE_ARENA) { + } else if (map->def.type == BPF_MAP_TYPE_ARENA) { map->mmaped = mmap((void *)(long)map->map_extra, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, map->map_extra ? MAP_SHARED | MAP_FIXED : MAP_SHARED, @@ -5449,8 +5619,8 @@ retry: if (map->mmaped == MAP_FAILED) { err = -errno; map->mmaped = NULL; - pr_warn("map '%s': failed to mmap arena: %d\n", - map->name, err); + pr_warn("map '%s': failed to mmap arena: %s\n", + map->name, errstr(err)); return err; } if (obj->arena_data) { @@ -5472,8 +5642,8 @@ retry: retried = true; goto retry; } - pr_warn("map '%s': failed to auto-pin at '%s': %d\n", - map->name, map->pin_path, err); + pr_warn("map '%s': failed to auto-pin at '%s': %s\n", + map->name, map->pin_path, errstr(err)); goto err_out; } } @@ -5482,8 +5652,7 @@ retry: return 0; err_out: - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("map '%s': failed to create: %s(%d)\n", map->name, cp, err); + pr_warn("map '%s': failed to create: %s\n", map->name, errstr(err)); pr_perm_msg(err); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); @@ -5607,7 +5776,7 @@ static int load_module_btfs(struct bpf_object *obj) } if (err) { err = -errno; - pr_warn("failed to iterate BTF objects: %d\n", err); + pr_warn("failed to iterate BTF objects: %s\n", errstr(err)); return err; } @@ -5616,7 +5785,7 @@ static int load_module_btfs(struct bpf_object *obj) if (errno == ENOENT) continue; /* expected race: BTF was unloaded */ err = -errno; - pr_warn("failed to get BTF object #%d FD: %d\n", id, err); + pr_warn("failed to get BTF object #%d FD: %s\n", id, errstr(err)); return err; } @@ -5628,7 +5797,7 @@ static int load_module_btfs(struct bpf_object *obj) err = bpf_btf_get_info_by_fd(fd, &info, &len); if (err) { err = -errno; - pr_warn("failed to get BTF object #%d info: %d\n", id, err); + pr_warn("failed to get BTF object #%d info: %s\n", id, errstr(err)); goto err_out; } @@ -5641,8 +5810,8 @@ static int load_module_btfs(struct bpf_object *obj) btf = btf_get_from_fd(fd, obj->btf_vmlinux); err = libbpf_get_error(btf); if (err) { - pr_warn("failed to load module [%s]'s BTF object #%d: %d\n", - name, id, err); + pr_warn("failed to load module [%s]'s BTF object #%d: %s\n", + name, id, errstr(err)); goto err_out; } @@ -5871,7 +6040,7 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) obj->btf_vmlinux_override = btf__parse(targ_btf_path, NULL); err = libbpf_get_error(obj->btf_vmlinux_override); if (err) { - pr_warn("failed to parse target BTF: %d\n", err); + pr_warn("failed to parse target BTF: %s\n", errstr(err)); return err; } } @@ -5931,8 +6100,8 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) err = record_relo_core(prog, rec, insn_idx); if (err) { - pr_warn("prog '%s': relo #%d: failed to record relocation: %d\n", - prog->name, i, err); + pr_warn("prog '%s': relo #%d: failed to record relocation: %s\n", + prog->name, i, errstr(err)); goto out; } @@ -5941,15 +6110,15 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) err = bpf_core_resolve_relo(prog, rec, i, obj->btf, cand_cache, &targ_res); if (err) { - pr_warn("prog '%s': relo #%d: failed to relocate: %d\n", - prog->name, i, err); + pr_warn("prog '%s': relo #%d: failed to relocate: %s\n", + prog->name, i, errstr(err)); goto out; } err = bpf_core_patch_insn(prog->name, insn, insn_idx, rec, i, &targ_res); if (err) { - pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n", - prog->name, i, insn_idx, err); + pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %s\n", + prog->name, i, insn_idx, errstr(err)); goto out; } } @@ -6023,6 +6192,157 @@ static void poison_kfunc_call(struct bpf_program *prog, int relo_idx, insn->imm = POISON_CALL_KFUNC_BASE + ext_idx; } +static int find_jt_map(struct bpf_object *obj, struct bpf_program *prog, int sym_off) +{ + size_t i; + + for (i = 0; i < obj->jumptable_map_cnt; i++) { + /* + * This might happen that same offset is used for two different + * programs (as jump tables can be the same). However, for + * different programs different maps should be created. + */ + if (obj->jumptable_maps[i].sym_off == sym_off && + obj->jumptable_maps[i].prog == prog) + return obj->jumptable_maps[i].fd; + } + + return -ENOENT; +} + +static int add_jt_map(struct bpf_object *obj, struct bpf_program *prog, int sym_off, int map_fd) +{ + size_t cnt = obj->jumptable_map_cnt; + size_t size = sizeof(obj->jumptable_maps[0]); + void *tmp; + + tmp = libbpf_reallocarray(obj->jumptable_maps, cnt + 1, size); + if (!tmp) + return -ENOMEM; + + obj->jumptable_maps = tmp; + obj->jumptable_maps[cnt].prog = prog; + obj->jumptable_maps[cnt].sym_off = sym_off; + obj->jumptable_maps[cnt].fd = map_fd; + obj->jumptable_map_cnt++; + + return 0; +} + +static int find_subprog_idx(struct bpf_program *prog, int insn_idx) +{ + int i; + + for (i = prog->subprog_cnt - 1; i >= 0; i--) { + if (insn_idx >= prog->subprogs[i].sub_insn_off) + return i; + } + + return -1; +} + +static int create_jt_map(struct bpf_object *obj, struct bpf_program *prog, struct reloc_desc *relo) +{ + const __u32 jt_entry_size = 8; + int sym_off = relo->sym_off; + int jt_size = relo->sym_size; + __u32 max_entries = jt_size / jt_entry_size; + __u32 value_size = sizeof(struct bpf_insn_array_value); + struct bpf_insn_array_value val = {}; + int subprog_idx; + int map_fd, err; + __u64 insn_off; + __u64 *jt; + __u32 i; + + map_fd = find_jt_map(obj, prog, sym_off); + if (map_fd >= 0) + return map_fd; + + if (sym_off % jt_entry_size) { + pr_warn("map '.jumptables': jumptable start %d should be multiple of %u\n", + sym_off, jt_entry_size); + return -EINVAL; + } + + if (jt_size % jt_entry_size) { + pr_warn("map '.jumptables': jumptable size %d should be multiple of %u\n", + jt_size, jt_entry_size); + return -EINVAL; + } + + map_fd = bpf_map_create(BPF_MAP_TYPE_INSN_ARRAY, ".jumptables", + 4, value_size, max_entries, NULL); + if (map_fd < 0) + return map_fd; + + if (!obj->jumptables_data) { + pr_warn("map '.jumptables': ELF file is missing jump table data\n"); + err = -EINVAL; + goto err_close; + } + if (sym_off + jt_size > obj->jumptables_data_sz) { + pr_warn("map '.jumptables': jumptables_data size is %zd, trying to access %d\n", + obj->jumptables_data_sz, sym_off + jt_size); + err = -EINVAL; + goto err_close; + } + + subprog_idx = -1; /* main program */ + if (relo->insn_idx < 0 || relo->insn_idx >= prog->insns_cnt) { + pr_warn("map '.jumptables': invalid instruction index %d\n", relo->insn_idx); + err = -EINVAL; + goto err_close; + } + if (prog->subprogs) + subprog_idx = find_subprog_idx(prog, relo->insn_idx); + + jt = (__u64 *)(obj->jumptables_data + sym_off); + for (i = 0; i < max_entries; i++) { + /* + * The offset should be made to be relative to the beginning of + * the main function, not the subfunction. + */ + insn_off = jt[i]/sizeof(struct bpf_insn); + if (subprog_idx >= 0) { + insn_off -= prog->subprogs[subprog_idx].sec_insn_off; + insn_off += prog->subprogs[subprog_idx].sub_insn_off; + } else { + insn_off -= prog->sec_insn_off; + } + + /* + * LLVM-generated jump tables contain u64 records, however + * should contain values that fit in u32. + */ + if (insn_off > UINT32_MAX) { + pr_warn("map '.jumptables': invalid jump table value 0x%llx at offset %d\n", + (long long)jt[i], sym_off + i * jt_entry_size); + err = -EINVAL; + goto err_close; + } + + val.orig_off = insn_off; + err = bpf_map_update_elem(map_fd, &i, &val, 0); + if (err) + goto err_close; + } + + err = bpf_map_freeze(map_fd); + if (err) + goto err_close; + + err = add_jt_map(obj, prog, sym_off, map_fd); + if (err) + goto err_close; + + return map_fd; + +err_close: + close(map_fd); + return err; +} + /* Relocate data references within program code: * - map references; * - global variable references; @@ -6114,6 +6434,20 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) case RELO_CORE: /* will be handled by bpf_program_record_relos() */ break; + case RELO_INSN_ARRAY: { + int map_fd; + + map_fd = create_jt_map(obj, prog, relo); + if (map_fd < 0) { + pr_warn("prog '%s': relo #%d: can't create jump table: sym_off %u\n", + prog->name, i, relo->sym_off); + return map_fd; + } + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn->imm = map_fd; + insn->off = 0; + } + break; default: pr_warn("prog '%s': relo #%d: bad relo type %d\n", prog->name, i, relo->type); @@ -6217,8 +6551,8 @@ reloc_prog_func_and_line_info(const struct bpf_object *obj, &main_prog->func_info_rec_size); if (err) { if (err != -ENOENT) { - pr_warn("prog '%s': error relocating .BTF.ext function info: %d\n", - prog->name, err); + pr_warn("prog '%s': error relocating .BTF.ext function info: %s\n", + prog->name, errstr(err)); return err; } if (main_prog->func_info) { @@ -6245,8 +6579,8 @@ line_info: &main_prog->line_info_rec_size); if (err) { if (err != -ENOENT) { - pr_warn("prog '%s': error relocating .BTF.ext line info: %d\n", - prog->name, err); + pr_warn("prog '%s': error relocating .BTF.ext line info: %s\n", + prog->name, errstr(err)); return err; } if (main_prog->line_info) { @@ -6311,36 +6645,62 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra return 0; } +static int save_subprog_offsets(struct bpf_program *main_prog, struct bpf_program *subprog) +{ + size_t size = sizeof(main_prog->subprogs[0]); + int cnt = main_prog->subprog_cnt; + void *tmp; + + tmp = libbpf_reallocarray(main_prog->subprogs, cnt + 1, size); + if (!tmp) + return -ENOMEM; + + main_prog->subprogs = tmp; + main_prog->subprogs[cnt].sec_insn_off = subprog->sec_insn_off; + main_prog->subprogs[cnt].sub_insn_off = subprog->sub_insn_off; + main_prog->subprog_cnt++; + + return 0; +} + static int bpf_object__append_subprog_code(struct bpf_object *obj, struct bpf_program *main_prog, struct bpf_program *subprog) { - struct bpf_insn *insns; - size_t new_cnt; - int err; + struct bpf_insn *insns; + size_t new_cnt; + int err; + + subprog->sub_insn_off = main_prog->insns_cnt; - subprog->sub_insn_off = main_prog->insns_cnt; + new_cnt = main_prog->insns_cnt + subprog->insns_cnt; + insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns)); + if (!insns) { + pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name); + return -ENOMEM; + } + main_prog->insns = insns; + main_prog->insns_cnt = new_cnt; - new_cnt = main_prog->insns_cnt + subprog->insns_cnt; - insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns)); - if (!insns) { - pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name); - return -ENOMEM; - } - main_prog->insns = insns; - main_prog->insns_cnt = new_cnt; + memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns, + subprog->insns_cnt * sizeof(*insns)); - memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns, - subprog->insns_cnt * sizeof(*insns)); + pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", + main_prog->name, subprog->insns_cnt, subprog->name); - pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", - main_prog->name, subprog->insns_cnt, subprog->name); + /* The subprog insns are now appended. Append its relos too. */ + err = append_subprog_relos(main_prog, subprog); + if (err) + return err; - /* The subprog insns are now appended. Append its relos too. */ - err = append_subprog_relos(main_prog, subprog); - if (err) - return err; - return 0; + err = save_subprog_offsets(main_prog, subprog); + if (err) { + pr_warn("prog '%s': failed to add subprog offsets: %s\n", + main_prog->name, errstr(err)); + return err; + } + + return 0; } static int @@ -7010,8 +7370,8 @@ static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_pat if (obj->btf_ext) { err = bpf_object__relocate_core(obj, targ_btf_path); if (err) { - pr_warn("failed to perform CO-RE relocations: %d\n", - err); + pr_warn("failed to perform CO-RE relocations: %s\n", + errstr(err)); return err; } bpf_object__sort_relos(obj); @@ -7055,8 +7415,8 @@ static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_pat err = bpf_object__relocate_calls(obj, prog); if (err) { - pr_warn("prog '%s': failed to relocate calls: %d\n", - prog->name, err); + pr_warn("prog '%s': failed to relocate calls: %s\n", + prog->name, errstr(err)); return err; } @@ -7092,16 +7452,16 @@ static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_pat /* Process data relos for main programs */ err = bpf_object__relocate_data(obj, prog); if (err) { - pr_warn("prog '%s': failed to relocate data references: %d\n", - prog->name, err); + pr_warn("prog '%s': failed to relocate data references: %s\n", + prog->name, errstr(err)); return err; } /* Fix up .BTF.ext information, if necessary */ err = bpf_program_fixup_func_info(obj, prog); if (err) { - pr_warn("prog '%s': failed to perform .BTF.ext fix ups: %d\n", - prog->name, err); + pr_warn("prog '%s': failed to perform .BTF.ext fix ups: %s\n", + prog->name, errstr(err)); return err; } } @@ -7353,8 +7713,14 @@ static int libbpf_prepare_prog_load(struct bpf_program *prog, opts->prog_flags |= BPF_F_XDP_HAS_FRAGS; /* special check for usdt to use uprobe_multi link */ - if ((def & SEC_USDT) && kernel_supports(prog->obj, FEAT_UPROBE_MULTI_LINK)) + if ((def & SEC_USDT) && kernel_supports(prog->obj, FEAT_UPROBE_MULTI_LINK)) { + /* for BPF_TRACE_UPROBE_MULTI, user might want to query expected_attach_type + * in prog, and expected_attach_type we set in kernel is from opts, so we + * update both. + */ prog->expected_attach_type = BPF_TRACE_UPROBE_MULTI; + opts->expected_attach_type = BPF_TRACE_UPROBE_MULTI; + } if ((def & SEC_ATTACH_BTF) && !prog->attach_btf_id) { int btf_obj_fd = 0, btf_type_id = 0, err; @@ -7404,7 +7770,6 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog { LIBBPF_OPTS(bpf_prog_load_opts, load_attr); const char *prog_name = NULL; - char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; char *log_buf = NULL, *tmp; bool own_log_buf = true; @@ -7444,6 +7809,7 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog load_attr.attach_btf_id = prog->attach_btf_id; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; + load_attr.expected_attach_type = prog->expected_attach_type; /* specify func_info/line_info only if kernel supports them */ if (obj->btf && btf__fd(obj->btf) >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) { @@ -7467,17 +7833,14 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog if (prog->sec_def && prog->sec_def->prog_prepare_load_fn) { err = prog->sec_def->prog_prepare_load_fn(prog, &load_attr, prog->sec_def->cookie); if (err < 0) { - pr_warn("prog '%s': failed to prepare load attributes: %d\n", - prog->name, err); + pr_warn("prog '%s': failed to prepare load attributes: %s\n", + prog->name, errstr(err)); return err; } insns = prog->insns; insns_cnt = prog->insns_cnt; } - /* allow prog_prepare_load_fn to change expected_attach_type */ - load_attr.expected_attach_type = prog->expected_attach_type; - if (obj->gen_loader) { bpf_gen__prog_load(obj->gen_loader, prog->type, prog->name, license, insns, insns_cnt, &load_attr, @@ -7535,9 +7898,8 @@ retry_load: continue; if (bpf_prog_bind_map(ret, map->fd, NULL)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); pr_warn("prog '%s': failed to bind map '%s': %s\n", - prog->name, map->real_name, cp); + prog->name, map->real_name, errstr(errno)); /* Don't fail hard if can't bind rodata. */ } } @@ -7567,8 +7929,7 @@ retry_load: /* post-process verifier log to improve error descriptions */ fixup_verifier_log(prog, log_buf, log_buf_size); - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("prog '%s': BPF program load failed: %s\n", prog->name, cp); + pr_warn("prog '%s': BPF program load failed: %s\n", prog->name, errstr(errno)); pr_perm_msg(ret); if (own_log_buf && log_buf && log_buf[0] != '\0') { @@ -7840,13 +8201,6 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; - err = bpf_object__sanitize_prog(obj, prog); - if (err) - return err; - } - - for (i = 0; i < obj->nr_programs; i++) { - prog = &obj->programs[i]; if (prog_is_subprog(obj, prog)) continue; if (!prog->autoload) { @@ -7861,7 +8215,7 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) err = bpf_object_load_prog(obj, prog, prog->insns, prog->insns_cnt, obj->license, obj->kern_version, &prog->fd); if (err) { - pr_warn("prog '%s': failed to load: %d\n", prog->name, err); + pr_warn("prog '%s': failed to load: %s\n", prog->name, errstr(err)); return err; } } @@ -7870,6 +8224,21 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) return 0; } +static int bpf_object_prepare_progs(struct bpf_object *obj) +{ + struct bpf_program *prog; + size_t i; + int err; + + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + err = bpf_object__sanitize_prog(obj, prog); + if (err) + return err; + } + return 0; +} + 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) @@ -7895,8 +8264,8 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object if (prog->sec_def->prog_setup_fn) { err = prog->sec_def->prog_setup_fn(prog, prog->sec_def->cookie); if (err < 0) { - pr_warn("prog '%s': failed to initialize: %d\n", - prog->name, err); + pr_warn("prog '%s': failed to initialize: %s\n", + prog->name, errstr(err)); return err; } } @@ -7906,16 +8275,19 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object } static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz, + const char *obj_name, const struct bpf_object_open_opts *opts) { - const char *obj_name, *kconfig, *btf_tmp_path, *token_path; + const char *kconfig, *btf_tmp_path, *token_path; struct bpf_object *obj; - char tmp_name[64]; int err; char *log_buf; size_t log_size; __u32 log_level; + if (obj_buf && !obj_name) + return ERR_PTR(-EINVAL); + if (elf_version(EV_CURRENT) == EV_NONE) { pr_warn("failed to init libelf for %s\n", path ? : "(mem buf)"); @@ -7925,16 +8297,12 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, if (!OPTS_VALID(opts, bpf_object_open_opts)) return ERR_PTR(-EINVAL); - obj_name = OPTS_GET(opts, object_name, NULL); + obj_name = OPTS_GET(opts, object_name, NULL) ?: obj_name; if (obj_buf) { - if (!obj_name) { - snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx", - (unsigned long)obj_buf, - (unsigned long)obj_buf_sz); - obj_name = tmp_name; - } path = obj_name; pr_debug("loading object '%s' from buffer\n", obj_name); + } else { + pr_debug("loading object from %s\n", path); } log_buf = OPTS_GET(opts, kernel_log_buf, NULL); @@ -7994,7 +8362,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, } err = bpf_object__elf_init(obj); - err = err ? : bpf_object__check_endianness(obj); err = err ? : bpf_object__elf_collect(obj); err = err ? : bpf_object__collect_externs(obj); err = err ? : bpf_object_fixup_btf(obj); @@ -8018,9 +8385,7 @@ bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) if (!path) return libbpf_err_ptr(-EINVAL); - pr_debug("loading %s\n", path); - - return libbpf_ptr(bpf_object_open(path, NULL, 0, opts)); + return libbpf_ptr(bpf_object_open(path, NULL, 0, NULL, opts)); } struct bpf_object *bpf_object__open(const char *path) @@ -8032,10 +8397,15 @@ struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts) { + char tmp_name[64]; + if (!obj_buf || obj_buf_sz == 0) return libbpf_err_ptr(-EINVAL); - return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, opts)); + /* create a (quite useless) default "name" for this memory buffer object */ + snprintf(tmp_name, sizeof(tmp_name), "%lx-%zx", (unsigned long)obj_buf, obj_buf_sz); + + return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, tmp_name, opts)); } static int bpf_object_unload(struct bpf_object *obj) @@ -8084,7 +8454,7 @@ static int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) f = fopen("/proc/kallsyms", "re"); if (!f) { err = -errno; - pr_warn("failed to open /proc/kallsyms: %d\n", err); + pr_warn("failed to open /proc/kallsyms: %s\n", errstr(err)); return err; } @@ -8445,11 +8815,13 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, static void bpf_map_prepare_vdata(const struct bpf_map *map) { + const struct btf_type *type; struct bpf_struct_ops *st_ops; __u32 i; st_ops = map->st_ops; - for (i = 0; i < btf_vlen(st_ops->type); i++) { + type = btf__type_by_id(map->obj->btf, st_ops->type_id); + for (i = 0; i < btf_vlen(type); i++) { struct bpf_program *prog = st_ops->progs[i]; void *kern_data; int prog_fd; @@ -8483,20 +8855,45 @@ static int bpf_object_prepare_struct_ops(struct bpf_object *obj) return 0; } -static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path) +static void bpf_object_unpin(struct bpf_object *obj) { - int err, i; + int i; - if (!obj) - return libbpf_err(-EINVAL); + /* unpin any maps that were auto-pinned during load */ + for (i = 0; i < obj->nr_maps; i++) + if (obj->maps[i].pinned && !obj->maps[i].reused) + bpf_map__unpin(&obj->maps[i], NULL); +} - if (obj->loaded) { - pr_warn("object '%s': load can't be attempted twice\n", obj->name); - return libbpf_err(-EINVAL); +static void bpf_object_post_load_cleanup(struct bpf_object *obj) +{ + int i; + + /* clean up fd_array */ + zfree(&obj->fd_array); + + /* clean up module BTFs */ + for (i = 0; i < obj->btf_module_cnt; i++) { + close(obj->btf_modules[i].fd); + btf__free(obj->btf_modules[i].btf); + free(obj->btf_modules[i].name); } + obj->btf_module_cnt = 0; + zfree(&obj->btf_modules); - if (obj->gen_loader) - bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); + /* clean up vmlinux BTF */ + btf__free(obj->btf_vmlinux); + obj->btf_vmlinux = NULL; +} + +static int bpf_object_prepare(struct bpf_object *obj, const char *target_btf_path) +{ + int err; + + if (obj->state >= OBJ_PREPARED) { + pr_warn("object '%s': prepare loading can't be attempted twice\n", obj->name); + return -EINVAL; + } err = bpf_object_prepare_token(obj); err = err ? : bpf_object__probe_loading(obj); @@ -8508,7 +8905,47 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path); err = err ? : bpf_object__sanitize_and_load_btf(obj); err = err ? : bpf_object__create_maps(obj); - err = err ? : bpf_object__load_progs(obj, extra_log_level); + err = err ? : bpf_object_prepare_progs(obj); + + if (err) { + bpf_object_unpin(obj); + bpf_object_unload(obj); + obj->state = OBJ_LOADED; + return err; + } + + obj->state = OBJ_PREPARED; + return 0; +} + +static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path) +{ + int err; + + if (!obj) + return libbpf_err(-EINVAL); + + if (obj->state >= OBJ_LOADED) { + pr_warn("object '%s': load can't be attempted twice\n", obj->name); + return libbpf_err(-EINVAL); + } + + /* Disallow kernel loading programs of non-native endianness but + * permit cross-endian creation of "light skeleton". + */ + if (obj->gen_loader) { + bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); + } else if (!is_native_endianness(obj)) { + pr_warn("object '%s': loading non-native endianness is unsupported\n", obj->name); + return libbpf_err(-LIBBPF_ERRNO__ENDIAN); + } + + if (obj->state < OBJ_PREPARED) { + err = bpf_object_prepare(obj, target_btf_path); + if (err) + return libbpf_err(err); + } + err = bpf_object__load_progs(obj, extra_log_level); err = err ? : bpf_object_init_prog_arrays(obj); err = err ? : bpf_object_prepare_struct_ops(obj); @@ -8520,36 +8957,22 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps); } - /* clean up fd_array */ - zfree(&obj->fd_array); + bpf_object_post_load_cleanup(obj); + obj->state = OBJ_LOADED; /* doesn't matter if successfully or not */ - /* clean up module BTFs */ - for (i = 0; i < obj->btf_module_cnt; i++) { - close(obj->btf_modules[i].fd); - btf__free(obj->btf_modules[i].btf); - free(obj->btf_modules[i].name); + if (err) { + bpf_object_unpin(obj); + bpf_object_unload(obj); + pr_warn("failed to load object '%s'\n", obj->path); + return libbpf_err(err); } - free(obj->btf_modules); - - /* clean up vmlinux BTF */ - btf__free(obj->btf_vmlinux); - obj->btf_vmlinux = NULL; - - obj->loaded = true; /* doesn't matter if successfully or not */ - - if (err) - goto out; return 0; -out: - /* unpin any maps that were auto-pinned during load */ - for (i = 0; i < obj->nr_maps; i++) - if (obj->maps[i].pinned && !obj->maps[i].reused) - bpf_map__unpin(&obj->maps[i], NULL); +} - bpf_object_unload(obj); - pr_warn("failed to load object '%s'\n", obj->path); - return libbpf_err(err); +int bpf_object__prepare(struct bpf_object *obj) +{ + return libbpf_err(bpf_object_prepare(obj, NULL)); } int bpf_object__load(struct bpf_object *obj) @@ -8559,7 +8982,6 @@ int bpf_object__load(struct bpf_object *obj) static int make_parent_dir(const char *path) { - char *cp, errmsg[STRERR_BUFSIZE]; char *dname, *dir; int err = 0; @@ -8573,15 +8995,13 @@ static int make_parent_dir(const char *path) free(dname); if (err) { - cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); - pr_warn("failed to mkdir %s: %s\n", path, cp); + pr_warn("failed to mkdir %s: %s\n", path, errstr(err)); } return err; } static int check_path(const char *path) { - char *cp, errmsg[STRERR_BUFSIZE]; struct statfs st_fs; char *dname, *dir; int err = 0; @@ -8595,8 +9015,7 @@ static int check_path(const char *path) dir = dirname(dname); if (statfs(dir, &st_fs)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("failed to statfs %s: %s\n", dir, cp); + pr_warn("failed to statfs %s: %s\n", dir, errstr(errno)); err = -errno; } free(dname); @@ -8611,7 +9030,6 @@ static int check_path(const char *path) int bpf_program__pin(struct bpf_program *prog, const char *path) { - char *cp, errmsg[STRERR_BUFSIZE]; int err; if (prog->fd < 0) { @@ -8629,8 +9047,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path) if (bpf_obj_pin(prog->fd, path)) { err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("prog '%s': failed to pin at '%s': %s\n", prog->name, path, cp); + pr_warn("prog '%s': failed to pin at '%s': %s\n", prog->name, path, errstr(err)); return libbpf_err(err); } @@ -8661,7 +9078,6 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path) int bpf_map__pin(struct bpf_map *map, const char *path) { - char *cp, errmsg[STRERR_BUFSIZE]; int err; if (map == NULL) { @@ -8720,8 +9136,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path) return 0; out_err: - cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); - pr_warn("failed to pin map: %s\n", cp); + pr_warn("failed to pin map: %s\n", errstr(err)); return libbpf_err(err); } @@ -8807,7 +9222,7 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) if (!obj) return libbpf_err(-ENOENT); - if (!obj->loaded) { + if (obj->state < OBJ_PREPARED) { pr_warn("object not yet loaded; load it first\n"); return libbpf_err(-ENOENT); } @@ -8886,7 +9301,7 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) if (!obj) return libbpf_err(-ENOENT); - if (!obj->loaded) { + if (obj->state < OBJ_LOADED) { pr_warn("object not yet loaded; load it first\n"); return libbpf_err(-ENOENT); } @@ -9005,6 +9420,13 @@ void bpf_object__close(struct bpf_object *obj) if (IS_ERR_OR_NULL(obj)) return; + /* + * if user called bpf_object__prepare() without ever getting to + * bpf_object__load(), we need to clean up stuff that is normally + * cleaned up at the end of loading step + */ + bpf_object_post_load_cleanup(obj); + usdt_manager_free(obj->usdt_man); obj->usdt_man = NULL; @@ -9021,8 +9443,10 @@ void bpf_object__close(struct bpf_object *obj) zfree(&obj->btf_custom_path); zfree(&obj->kconfig); - for (i = 0; i < obj->nr_extern; i++) + for (i = 0; i < obj->nr_extern; i++) { + zfree(&obj->externs[i].name); zfree(&obj->externs[i].essent_name); + } zfree(&obj->externs); obj->nr_extern = 0; @@ -9043,6 +9467,13 @@ void bpf_object__close(struct bpf_object *obj) zfree(&obj->arena_data); + zfree(&obj->jumptables_data); + obj->jumptables_data_sz = 0; + + for (i = 0; i < obj->jumptable_map_cnt; i++) + close(obj->jumptable_maps[i].fd); + zfree(&obj->jumptable_maps); + free(obj); } @@ -9056,6 +9487,11 @@ unsigned int bpf_object__kversion(const struct bpf_object *obj) return obj ? obj->kern_version : 0; } +int bpf_object__token_fd(const struct bpf_object *obj) +{ + return obj->token_fd ?: -1; +} + struct btf *bpf_object__btf(const struct bpf_object *obj) { return obj ? obj->btf : NULL; @@ -9068,7 +9504,7 @@ int bpf_object__btf_fd(const struct bpf_object *obj) int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version) { - if (obj->loaded) + if (obj->state >= OBJ_LOADED) return libbpf_err(-EINVAL); obj->kern_version = kern_version; @@ -9081,13 +9517,14 @@ int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts) struct bpf_gen *gen; if (!opts) - return -EFAULT; + return libbpf_err(-EFAULT); if (!OPTS_VALID(opts, gen_loader_opts)) - return -EINVAL; - gen = calloc(sizeof(*gen), 1); + return libbpf_err(-EINVAL); + gen = calloc(1, sizeof(*gen)); if (!gen) - return -ENOMEM; + return libbpf_err(-ENOMEM); gen->opts = opts; + gen->swapped_endian = !is_native_endianness(obj); obj->gen_loader = gen; return 0; } @@ -9164,7 +9601,7 @@ bool bpf_program__autoload(const struct bpf_program *prog) int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EINVAL); prog->autoload = autoload; @@ -9196,14 +9633,14 @@ int bpf_program__set_insns(struct bpf_program *prog, { struct bpf_insn *insns; - if (prog->obj->loaded) - return -EBUSY; + if (prog->obj->state >= OBJ_LOADED) + return libbpf_err(-EBUSY); insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns)); /* NULL is a valid return from reallocarray if the new count is zero */ if (!insns && new_insn_cnt) { pr_warn("prog '%s': failed to realloc prog code\n", prog->name); - return -ENOMEM; + return libbpf_err(-ENOMEM); } memcpy(insns, new_insns, new_insn_cnt * sizeof(*insns)); @@ -9239,7 +9676,7 @@ static int last_custom_sec_def_handler_id; int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); /* if type is not changed, do nothing */ @@ -9270,7 +9707,7 @@ enum bpf_attach_type bpf_program__expected_attach_type(const struct bpf_program int bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); prog->expected_attach_type = type; @@ -9284,7 +9721,7 @@ __u32 bpf_program__flags(const struct bpf_program *prog) int bpf_program__set_flags(struct bpf_program *prog, __u32 flags) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); prog->prog_flags = flags; @@ -9298,7 +9735,7 @@ __u32 bpf_program__log_level(const struct bpf_program *prog) int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); prog->log_level = log_level; @@ -9314,17 +9751,41 @@ const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_siz int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size) { if (log_size && !log_buf) - return -EINVAL; + return libbpf_err(-EINVAL); if (prog->log_size > UINT_MAX) - return -EINVAL; - if (prog->obj->loaded) - return -EBUSY; + return libbpf_err(-EINVAL); + if (prog->obj->state >= OBJ_LOADED) + return libbpf_err(-EBUSY); prog->log_buf = log_buf; prog->log_size = log_size; return 0; } +struct bpf_func_info *bpf_program__func_info(const struct bpf_program *prog) +{ + if (prog->func_info_rec_size != sizeof(struct bpf_func_info)) + return libbpf_err_ptr(-EOPNOTSUPP); + return prog->func_info; +} + +__u32 bpf_program__func_info_cnt(const struct bpf_program *prog) +{ + return prog->func_info_cnt; +} + +struct bpf_line_info *bpf_program__line_info(const struct bpf_program *prog) +{ + if (prog->line_info_rec_size != sizeof(struct bpf_line_info)) + return libbpf_err_ptr(-EOPNOTSUPP); + return prog->line_info; +} + +__u32 bpf_program__line_info_cnt(const struct bpf_program *prog) +{ + return prog->line_info_cnt; +} + #define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ .sec = (char *)sec_pfx, \ .prog_type = BPF_PROG_TYPE_##ptype, \ @@ -9362,8 +9823,10 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("kprobe.session+", KPROBE, BPF_TRACE_KPROBE_SESSION, SEC_NONE, attach_kprobe_session), SEC_DEF("uprobe.multi+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi), SEC_DEF("uretprobe.multi+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi), + SEC_DEF("uprobe.session+", KPROBE, BPF_TRACE_UPROBE_SESSION, SEC_NONE, attach_uprobe_multi), SEC_DEF("uprobe.multi.s+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi), SEC_DEF("uretprobe.multi.s+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi), + SEC_DEF("uprobe.session.s+", KPROBE, BPF_TRACE_UPROBE_SESSION, SEC_SLEEPABLE, attach_uprobe_multi), SEC_DEF("ksyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), SEC_DEF("kretsyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), SEC_DEF("usdt+", KPROBE, 0, SEC_USDT, attach_usdt), @@ -9712,6 +10175,7 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Data *data) { + const struct btf_type *type; const struct btf_member *member; struct bpf_struct_ops *st_ops; struct bpf_program *prog; @@ -9771,13 +10235,14 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, } insn_idx = sym->st_value / BPF_INSN_SZ; - member = find_member_by_offset(st_ops->type, moff * 8); + type = btf__type_by_id(btf, st_ops->type_id); + member = find_member_by_offset(type, moff * 8); if (!member) { pr_warn("struct_ops reloc %s: cannot find member at moff %u\n", map->name, moff); return -EINVAL; } - member_idx = member - btf_members(st_ops->type); + member_idx = member - btf_members(type); name = btf__name_by_offset(btf, member->name_off); if (!resolve_func_ptr(btf, member->type, NULL)) { @@ -9890,7 +10355,7 @@ int libbpf_find_vmlinux_btf_id(const char *name, return libbpf_err(err); } -static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) +static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd, int token_fd) { struct bpf_prog_info info; __u32 info_len = sizeof(info); @@ -9900,8 +10365,8 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) memset(&info, 0, info_len); err = bpf_prog_get_info_by_fd(attach_prog_fd, &info, &info_len); if (err) { - pr_warn("failed bpf_prog_get_info_by_fd for FD %d: %d\n", - attach_prog_fd, err); + pr_warn("failed bpf_prog_get_info_by_fd for FD %d: %s\n", + attach_prog_fd, errstr(err)); return err; } @@ -9910,10 +10375,10 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) pr_warn("The target program doesn't have BTF\n"); goto out; } - btf = btf__load_from_kernel_by_id(info.btf_id); + btf = btf_load_from_kernel(info.btf_id, NULL, token_fd); err = libbpf_get_error(btf); if (err) { - pr_warn("Failed to get BTF %d of the program: %d\n", info.btf_id, err); + pr_warn("Failed to get BTF %d of the program: %s\n", info.btf_id, errstr(err)); goto out; } err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); @@ -9930,7 +10395,7 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, enum bpf_attach_type attach_type, int *btf_obj_fd, int *btf_type_id) { - int ret, i, mod_len; + int ret, i, mod_len = 0; const char *fn_name, *mod_name = NULL; fn_name = strchr(attach_name, ':'); @@ -9993,10 +10458,10 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac pr_warn("prog '%s': attach program FD is not set\n", prog->name); return -EINVAL; } - err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd); + err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd, prog->obj->token_fd); if (err < 0) { - pr_warn("prog '%s': failed to find BPF program (FD %d) BTF ID for '%s': %d\n", - prog->name, attach_prog_fd, attach_name, err); + pr_warn("prog '%s': failed to find BPF program (FD %d) BTF ID for '%s': %s\n", + prog->name, attach_prog_fd, attach_name, errstr(err)); return err; } *btf_obj_fd = 0; @@ -10015,8 +10480,8 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac btf_type_id); } if (err) { - pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %d\n", - prog->name, attach_name, err); + pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %s\n", + prog->name, attach_name, errstr(err)); return err; } return 0; @@ -10230,7 +10695,7 @@ static int map_btf_datasec_resize(struct bpf_map *map, __u32 size) int bpf_map__set_value_size(struct bpf_map *map, __u32 size) { - if (map->obj->loaded || map->reused) + if (map_is_created(map)) return libbpf_err(-EBUSY); if (map->mmaped) { @@ -10238,20 +10703,20 @@ int bpf_map__set_value_size(struct bpf_map *map, __u32 size) int err; if (map->def.type != BPF_MAP_TYPE_ARRAY) - return -EOPNOTSUPP; + return libbpf_err(-EOPNOTSUPP); mmap_old_sz = bpf_map_mmap_sz(map); mmap_new_sz = array_map_mmap_sz(size, map->def.max_entries); err = bpf_map_mmap_resize(map, mmap_old_sz, mmap_new_sz); if (err) { - pr_warn("map '%s': failed to resize memory-mapped region: %d\n", - bpf_map__name(map), err); - return err; + pr_warn("map '%s': failed to resize memory-mapped region: %s\n", + bpf_map__name(map), errstr(err)); + return libbpf_err(err); } err = map_btf_datasec_resize(map, size); if (err && err != -ENOENT) { - pr_warn("map '%s': failed to adjust resized BTF, clearing BTF key/value info: %d\n", - bpf_map__name(map), err); + pr_warn("map '%s': failed to adjust resized BTF, clearing BTF key/value info: %s\n", + bpf_map__name(map), errstr(err)); map->btf_value_type_id = 0; map->btf_key_type_id = 0; } @@ -10276,7 +10741,7 @@ int bpf_map__set_initial_value(struct bpf_map *map, { size_t actual_sz; - if (map->obj->loaded || map->reused) + if (map_is_created(map)) return libbpf_err(-EBUSY); if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG) @@ -10348,6 +10813,27 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) return 0; } +int bpf_map__set_exclusive_program(struct bpf_map *map, struct bpf_program *prog) +{ + if (map_is_created(map)) { + pr_warn("exclusive programs must be set before map creation\n"); + return libbpf_err(-EINVAL); + } + + if (map->obj != prog->obj) { + pr_warn("excl_prog and map must be from the same bpf object\n"); + return libbpf_err(-EINVAL); + } + + map->excl_prog = prog; + return 0; +} + +struct bpf_program *bpf_map__exclusive_program(struct bpf_map *map) +{ + return map->excl_prog; +} + static struct bpf_map * __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) { @@ -10742,7 +11228,6 @@ static void bpf_link_perf_dealloc(struct bpf_link *link) 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]; struct bpf_link_perf *link; int prog_fd, link_fd = -1, err; bool force_ioctl_attach; @@ -10777,9 +11262,8 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p link_fd = bpf_link_create(prog_fd, pfd, BPF_PERF_EVENT, &link_opts); if (link_fd < 0) { err = -errno; - pr_warn("prog '%s': failed to create BPF link for perf_event FD %d: %d (%s)\n", - prog->name, pfd, - err, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + pr_warn("prog '%s': failed to create BPF link for perf_event FD %d: %s\n", + prog->name, pfd, errstr(err)); goto err_out; } link->link.fd = link_fd; @@ -10793,7 +11277,7 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { err = -errno; pr_warn("prog '%s': failed to attach to perf_event FD %d: %s\n", - prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + prog->name, pfd, errstr(err)); if (err == -EPROTO) pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n", prog->name, pfd); @@ -10801,11 +11285,14 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p } link->link.fd = pfd; } - if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) { - err = -errno; - pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n", - prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - goto err_out; + + if (!OPTS_GET(opts, dont_enable, false)) { + if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) { + err = -errno; + pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n", + prog->name, pfd, errstr(err)); + goto err_out; + } } return &link->link; @@ -10828,22 +11315,19 @@ struct bpf_link *bpf_program__attach_perf_event(const struct bpf_program *prog, */ static int parse_uint_from_file(const char *file, const char *fmt) { - char buf[STRERR_BUFSIZE]; int err, ret; FILE *f; f = fopen(file, "re"); if (!f) { err = -errno; - pr_debug("failed to open '%s': %s\n", file, - libbpf_strerror_r(err, buf, sizeof(buf))); + pr_debug("failed to open '%s': %s\n", file, errstr(err)); return err; } err = fscanf(f, fmt, &ret); if (err != 1) { err = err == EOF ? -EIO : -errno; - pr_debug("failed to parse '%s': %s\n", file, - libbpf_strerror_r(err, buf, sizeof(buf))); + pr_debug("failed to parse '%s': %s\n", file, errstr(err)); fclose(f); return err; } @@ -10887,7 +11371,6 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, { const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_event_attr attr; - char errmsg[STRERR_BUFSIZE]; int type, pfd; if ((__u64)ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS)) @@ -10900,7 +11383,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, if (type < 0) { pr_warn("failed to determine %s perf type: %s\n", uprobe ? "uprobe" : "kprobe", - libbpf_strerror_r(type, errmsg, sizeof(errmsg))); + errstr(type)); return type; } if (retprobe) { @@ -10910,7 +11393,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, if (bit < 0) { pr_warn("failed to determine %s retprobe bit: %s\n", uprobe ? "uprobe" : "kprobe", - libbpf_strerror_r(bit, errmsg, sizeof(errmsg))); + errstr(bit)); return bit; } attr.config |= 1 << bit; @@ -10993,16 +11476,16 @@ static const char *tracefs_available_filter_functions_addrs(void) : TRACEFS"/available_filter_functions_addrs"; } -static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, - const char *kfunc_name, size_t offset) +static void gen_probe_legacy_event_name(char *buf, size_t buf_sz, + const char *name, size_t offset) { static int index = 0; int i; - snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx_%d", getpid(), kfunc_name, offset, - __sync_fetch_and_add(&index, 1)); + snprintf(buf, buf_sz, "libbpf_%u_%d_%s_0x%zx", getpid(), + __sync_fetch_and_add(&index, 1), name, offset); - /* sanitize binary_path in the probe name */ + /* sanitize name in the probe name */ for (i = 0; buf[i]; i++) { if (!isalnum(buf[i])) buf[i] = '_'; @@ -11039,14 +11522,13 @@ static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, { const size_t attr_sz = sizeof(struct perf_event_attr); 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))); + errstr(err)); return err; } type = determine_kprobe_perf_type_legacy(probe_name, retprobe); @@ -11054,7 +11536,7 @@ static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, err = type; pr_warn("failed to determine legacy kprobe event id for '%s+0x%zx': %s\n", kfunc_name, offset, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); goto err_clean_legacy; } @@ -11070,7 +11552,7 @@ static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, if (pfd < 0) { err = -errno; pr_warn("legacy kprobe perf_event_open() failed: %s\n", - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); goto err_clean_legacy; } return pfd; @@ -11089,8 +11571,6 @@ static const char *arch_specific_syscall_pfx(void) return "ia32"; #elif defined(__s390x__) return "s390x"; -#elif defined(__s390__) - return "s390"; #elif defined(__arm__) return "arm"; #elif defined(__aarch64__) @@ -11128,9 +11608,9 @@ int probe_kern_syscall_wrapper(int token_fd) return pfd >= 0 ? 1 : 0; } else { /* legacy mode */ - char probe_name[128]; + char probe_name[MAX_EVENT_NAME_LEN]; - gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0); + gen_probe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0); if (add_kprobe_event_legacy(probe_name, false, syscall_name, 0) < 0) return 0; @@ -11146,7 +11626,6 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); enum probe_attach_mode attach_mode; - char errmsg[STRERR_BUFSIZE]; char *legacy_probe = NULL; struct bpf_link *link; size_t offset; @@ -11187,10 +11666,10 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, func_name, offset, -1 /* pid */, 0 /* ref_ctr_off */); } else { - char probe_name[256]; + char probe_name[MAX_EVENT_NAME_LEN]; - gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), - func_name, offset); + gen_probe_legacy_event_name(probe_name, sizeof(probe_name), + func_name, offset); legacy_probe = strdup(probe_name); if (!legacy_probe) @@ -11204,7 +11683,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, 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))); + errstr(err)); goto err_out; } link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); @@ -11214,7 +11693,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, 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))); + errstr(err)); goto err_clean_legacy; } if (legacy) { @@ -11326,9 +11805,33 @@ static int avail_kallsyms_cb(unsigned long long sym_addr, char sym_type, struct kprobe_multi_resolve *res = data->res; int err; - if (!bsearch(&sym_name, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp)) + if (!glob_match(sym_name, res->pattern)) return 0; + if (!bsearch(&sym_name, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp)) { + /* Some versions of kernel strip out .llvm.<hash> suffix from + * function names reported in available_filter_functions, but + * don't do so for kallsyms. While this is clearly a kernel + * bug (fixed by [0]) we try to accommodate that in libbpf to + * make multi-kprobe usability a bit better: if no match is + * found, we will strip .llvm. suffix and try one more time. + * + * [0] fb6a421fb615 ("kallsyms: Match symbols exactly with CONFIG_LTO_CLANG") + */ + char sym_trim[256], *psym_trim = sym_trim, *sym_sfx; + + if (!(sym_sfx = strstr(sym_name, ".llvm."))) + return 0; + + /* psym_trim vs sym_trim dance is done to avoid pointer vs array + * coercion differences and get proper `const char **` pointer + * which avail_func_cmp() expects + */ + snprintf(sym_trim, sizeof(sym_trim), "%.*s", (int)(sym_sfx - sym_name), sym_name); + if (!bsearch(&psym_trim, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp)) + return 0; + } + err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, sizeof(*res->addrs), res->cnt + 1); if (err) return err; @@ -11350,7 +11853,7 @@ static int libbpf_available_kallsyms_parse(struct kprobe_multi_resolve *res) f = fopen(available_functions_file, "re"); if (!f) { err = -errno; - pr_warn("failed to open %s: %d\n", available_functions_file, err); + pr_warn("failed to open %s: %s\n", available_functions_file, errstr(err)); return err; } @@ -11425,7 +11928,7 @@ static int libbpf_available_kprobes_parse(struct kprobe_multi_resolve *res) f = fopen(available_path, "re"); if (!f) { err = -errno; - pr_warn("failed to open %s: %d\n", available_path, err); + pr_warn("failed to open %s: %s\n", available_path, errstr(err)); return err; } @@ -11471,10 +11974,9 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, }; enum bpf_attach_type attach_type; struct bpf_link *link = NULL; - char errmsg[STRERR_BUFSIZE]; const unsigned long *addrs; int err, link_fd, prog_fd; - bool retprobe, session; + bool retprobe, session, unique_match; const __u64 *cookies; const char **syms; size_t cnt; @@ -11493,6 +11995,7 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, addrs = OPTS_GET(opts, addrs, false); cnt = OPTS_GET(opts, cnt, false); cookies = OPTS_GET(opts, cookies, false); + unique_match = OPTS_GET(opts, unique_match, false); if (!pattern && !addrs && !syms) return libbpf_err_ptr(-EINVAL); @@ -11500,6 +12003,8 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, return libbpf_err_ptr(-EINVAL); if (!pattern && !cnt) return libbpf_err_ptr(-EINVAL); + if (!pattern && unique_match) + return libbpf_err_ptr(-EINVAL); if (addrs && syms) return libbpf_err_ptr(-EINVAL); @@ -11510,6 +12015,14 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, err = libbpf_available_kallsyms_parse(&res); if (err) goto error; + + if (unique_match && res.cnt != 1) { + pr_warn("prog '%s': failed to find a unique match for '%s' (%zu matches)\n", + prog->name, pattern, res.cnt); + err = -EINVAL; + goto error; + } + addrs = res.addrs; cnt = res.cnt; } @@ -11539,7 +12052,7 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, if (link_fd < 0) { err = -errno; pr_warn("prog '%s': failed to attach: %s\n", - prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + prog->name, errstr(err)); goto error; } link->fd = link_fd; @@ -11683,7 +12196,9 @@ static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, stru ret = 0; break; case 3: - opts.retprobe = strcmp(probe_type, "uretprobe.multi") == 0; + opts.session = str_has_pfx(probe_type, "uprobe.session"); + opts.retprobe = str_has_pfx(probe_type, "uretprobe.multi"); + *link = bpf_program__attach_uprobe_multi(prog, -1, binary_path, func_name, &opts); ret = libbpf_get_error(*link); break; @@ -11698,20 +12213,6 @@ static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, stru return ret; } -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) { @@ -11746,15 +12247,15 @@ static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, 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); + pr_warn("failed to add legacy uprobe event for %s:0x%zx: %s\n", + binary_path, (size_t)offset, errstr(err)); return err; } type = determine_uprobe_perf_type_legacy(probe_name, retprobe); if (type < 0) { err = type; - pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %d\n", - binary_path, offset, err); + pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %s\n", + binary_path, offset, errstr(err)); goto err_clean_legacy; } @@ -11769,7 +12270,7 @@ static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); if (pfd < 0) { err = -errno; - pr_warn("legacy uprobe perf_event_open() failed: %d\n", err); + pr_warn("legacy uprobe perf_event_open() failed: %s\n", errstr(err)); goto err_clean_legacy; } return pfd; @@ -11856,8 +12357,6 @@ static const char *arch_specific_lib_paths(void) return "/lib/i386-linux-gnu"; #elif defined(__s390x__) return "/lib/s390x-linux-gnu"; -#elif defined(__s390__) - return "/lib/s390-linux-gnu"; #elif defined(__arm__) && defined(__SOFTFP__) return "/lib/arm-linux-gnueabi"; #elif defined(__arm__) && !defined(__SOFTFP__) @@ -11932,10 +12431,11 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog, const unsigned long *ref_ctr_offsets = NULL, *offsets = NULL; LIBBPF_OPTS(bpf_link_create_opts, lopts); unsigned long *resolved_offsets = NULL; + enum bpf_attach_type attach_type; int err = 0, link_fd, prog_fd; struct bpf_link *link = NULL; - char errmsg[STRERR_BUFSIZE]; char full_path[PATH_MAX]; + bool retprobe, session; const __u64 *cookies; const char **syms; size_t cnt; @@ -11955,6 +12455,8 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog, ref_ctr_offsets = OPTS_GET(opts, ref_ctr_offsets, NULL); cookies = OPTS_GET(opts, cookies, NULL); cnt = OPTS_GET(opts, cnt, 0); + retprobe = OPTS_GET(opts, retprobe, false); + session = OPTS_GET(opts, session, false); /* * User can specify 2 mutually exclusive set of inputs: @@ -11983,12 +12485,15 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog, return libbpf_err_ptr(-EINVAL); } + if (retprobe && session) + return libbpf_err_ptr(-EINVAL); + if (func_pattern) { if (!strchr(path, '/')) { err = resolve_full_path(path, full_path, sizeof(full_path)); if (err) { - pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", - prog->name, path, err); + pr_warn("prog '%s': failed to resolve full path for '%s': %s\n", + prog->name, path, errstr(err)); return libbpf_err_ptr(err); } path = full_path; @@ -12006,12 +12511,14 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog, offsets = resolved_offsets; } + attach_type = session ? BPF_TRACE_UPROBE_SESSION : BPF_TRACE_UPROBE_MULTI; + lopts.uprobe_multi.path = path; lopts.uprobe_multi.offsets = offsets; lopts.uprobe_multi.ref_ctr_offsets = ref_ctr_offsets; lopts.uprobe_multi.cookies = cookies; lopts.uprobe_multi.cnt = cnt; - lopts.uprobe_multi.flags = OPTS_GET(opts, retprobe, false) ? BPF_F_UPROBE_MULTI_RETURN : 0; + lopts.uprobe_multi.flags = retprobe ? BPF_F_UPROBE_MULTI_RETURN : 0; if (pid == 0) pid = getpid(); @@ -12025,11 +12532,11 @@ bpf_program__attach_uprobe_multi(const struct bpf_program *prog, } link->detach = &bpf_link__detach_fd; - link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &lopts); + link_fd = bpf_link_create(prog_fd, 0, attach_type, &lopts); if (link_fd < 0) { err = -errno; pr_warn("prog '%s': failed to attach multi-uprobe: %s\n", - prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + prog->name, errstr(err)); goto error; } link->fd = link_fd; @@ -12048,7 +12555,7 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const struct bpf_uprobe_opts *opts) { const char *archive_path = NULL, *archive_sep = NULL; - char errmsg[STRERR_BUFSIZE], *legacy_probe = NULL; + char *legacy_probe = NULL; DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); enum probe_attach_mode attach_mode; char full_path[PATH_MAX]; @@ -12080,8 +12587,8 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, } else if (!strchr(binary_path, '/')) { err = resolve_full_path(binary_path, full_path, sizeof(full_path)); if (err) { - pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", - prog->name, binary_path, err); + pr_warn("prog '%s': failed to resolve full path for '%s': %s\n", + prog->name, binary_path, errstr(err)); return libbpf_err_ptr(err); } binary_path = full_path; @@ -12127,13 +12634,14 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, func_offset, pid, ref_ctr_off); } else { - char probe_name[PATH_MAX + 64]; + char probe_name[MAX_EVENT_NAME_LEN]; if (ref_ctr_off) return libbpf_err_ptr(-EINVAL); - gen_uprobe_legacy_event_name(probe_name, sizeof(probe_name), - binary_path, func_offset); + gen_probe_legacy_event_name(probe_name, sizeof(probe_name), + strrchr(binary_path, '/') ? : binary_path, + func_offset); legacy_probe = strdup(probe_name); if (!legacy_probe) @@ -12147,7 +12655,7 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, 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(err, errmsg, sizeof(errmsg))); + errstr(err)); goto err_out; } @@ -12158,7 +12666,7 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, pr_warn("prog '%s': failed to attach to %s '%s:0x%zx': %s\n", prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); goto err_clean_legacy; } if (legacy) { @@ -12279,8 +12787,8 @@ struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog, if (!strchr(binary_path, '/')) { err = resolve_full_path(binary_path, resolved_path, sizeof(resolved_path)); if (err) { - pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", - prog->name, binary_path, err); + pr_warn("prog '%s': failed to resolve full path for '%s': %s\n", + prog->name, binary_path, errstr(err)); return libbpf_err_ptr(err); } binary_path = resolved_path; @@ -12358,14 +12866,13 @@ static int perf_event_open_tracepoint(const char *tp_category, { const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_event_attr attr; - char errmsg[STRERR_BUFSIZE]; int tp_id, pfd, err; tp_id = determine_tracepoint_id(tp_category, tp_name); if (tp_id < 0) { pr_warn("failed to determine tracepoint '%s/%s' perf event ID: %s\n", tp_category, tp_name, - libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg))); + errstr(tp_id)); return tp_id; } @@ -12380,7 +12887,7 @@ static int perf_event_open_tracepoint(const char *tp_category, err = -errno; pr_warn("tracepoint '%s/%s' perf_event_open() failed: %s\n", tp_category, tp_name, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); return err; } return pfd; @@ -12392,7 +12899,6 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *p const struct bpf_tracepoint_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); - char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int pfd, err; @@ -12405,7 +12911,7 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *p if (pfd < 0) { pr_warn("prog '%s': failed to create tracepoint '%s/%s' perf event: %s\n", prog->name, tp_category, tp_name, - libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + errstr(pfd)); return libbpf_err_ptr(pfd); } link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); @@ -12414,7 +12920,7 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *p close(pfd); pr_warn("prog '%s': failed to attach to tracepoint '%s/%s': %s\n", prog->name, tp_category, tp_name, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); return libbpf_err_ptr(err); } return link; @@ -12465,7 +12971,6 @@ bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog, struct bpf_raw_tracepoint_opts *opts) { LIBBPF_OPTS(bpf_raw_tp_opts, raw_opts); - char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int prog_fd, pfd; @@ -12490,7 +12995,7 @@ bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog, pfd = -errno; free(link); pr_warn("prog '%s': failed to attach to raw tracepoint '%s': %s\n", - prog->name, tp_name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + prog->name, tp_name, errstr(pfd)); return libbpf_err_ptr(pfd); } link->fd = pfd; @@ -12549,7 +13054,6 @@ static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *pro const struct bpf_trace_opts *opts) { LIBBPF_OPTS(bpf_link_create_opts, link_opts); - char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int prog_fd, pfd; @@ -12574,7 +13078,7 @@ static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *pro pfd = -errno; free(link); pr_warn("prog '%s': failed to attach: %s\n", - prog->name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + prog->name, errstr(pfd)); return libbpf_err_ptr(pfd); } link->fd = pfd; @@ -12615,7 +13119,6 @@ bpf_program_attach_fd(const struct bpf_program *prog, const struct bpf_link_create_opts *opts) { enum bpf_attach_type attach_type; - char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int prog_fd, link_fd; @@ -12637,7 +13140,7 @@ bpf_program_attach_fd(const struct bpf_program *prog, free(link); pr_warn("prog '%s': failed to attach to %s: %s\n", prog->name, target_name, - libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + errstr(link_fd)); return libbpf_err_ptr(link_fd); } link->fd = link_fd; @@ -12669,6 +13172,34 @@ struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifi } struct bpf_link * +bpf_program__attach_cgroup_opts(const struct bpf_program *prog, int cgroup_fd, + const struct bpf_cgroup_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); + __u32 relative_id; + int relative_fd; + + if (!OPTS_VALID(opts, bpf_cgroup_opts)) + return libbpf_err_ptr(-EINVAL); + + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + + if (relative_fd && relative_id) { + pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link_create_opts.cgroup.expected_revision = OPTS_GET(opts, expected_revision, 0); + link_create_opts.cgroup.relative_fd = relative_fd; + link_create_opts.cgroup.relative_id = relative_id; + link_create_opts.flags = OPTS_GET(opts, flags, 0); + + return bpf_program_attach_fd(prog, cgroup_fd, "cgroup", &link_create_opts); +} + +struct bpf_link * bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex, const struct bpf_tcx_opts *opts) { @@ -12750,7 +13281,7 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, } if (prog->type != BPF_PROG_TYPE_EXT) { - pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace", + pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace\n", prog->name); return libbpf_err_ptr(-EINVAL); } @@ -12758,7 +13289,7 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, if (target_fd) { LIBBPF_OPTS(bpf_link_create_opts, target_opts); - btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd); + btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd, prog->obj->token_fd); if (btf_id < 0) return libbpf_err_ptr(btf_id); @@ -12779,7 +13310,6 @@ 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); - char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int prog_fd, link_fd; __u32 target_fd = 0; @@ -12807,7 +13337,7 @@ bpf_program__attach_iter(const struct bpf_program *prog, link_fd = -errno; free(link); pr_warn("prog '%s': failed to attach to iterator: %s\n", - prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + prog->name, errstr(link_fd)); return libbpf_err_ptr(link_fd); } link->fd = link_fd; @@ -12849,12 +13379,10 @@ struct bpf_link *bpf_program__attach_netfilter(const struct bpf_program *prog, link_fd = bpf_link_create(prog_fd, 0, BPF_NETFILTER, &lopts); if (link_fd < 0) { - char errmsg[STRERR_BUFSIZE]; - link_fd = -errno; free(link); pr_warn("prog '%s': failed to attach to netfilter: %s\n", - prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + prog->name, errstr(link_fd)); return libbpf_err_ptr(link_fd); } link->fd = link_fd; @@ -12973,17 +13501,17 @@ int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map) int err; if (!bpf_map__is_struct_ops(map)) - return -EINVAL; + return libbpf_err(-EINVAL); if (map->fd < 0) { pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name); - return -EINVAL; + return libbpf_err(-EINVAL); } st_ops_link = container_of(link, struct bpf_link_struct_ops, link); /* Ensure the type of a link is correct */ if (st_ops_link->map_fd < 0) - return -EINVAL; + return libbpf_err(-EINVAL); err = bpf_map_update_elem(map->fd, &zero, map->st_ops->kern_vdata, 0); /* It can be EBUSY if the map has been used to create or @@ -13139,7 +13667,6 @@ perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, int cpu, int map_key) { struct perf_cpu_buf *cpu_buf; - char msg[STRERR_BUFSIZE]; int err; cpu_buf = calloc(1, sizeof(*cpu_buf)); @@ -13155,7 +13682,7 @@ perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, if (cpu_buf->fd < 0) { err = -errno; pr_warn("failed to open perf buffer event on cpu #%d: %s\n", - cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + cpu, errstr(err)); goto error; } @@ -13166,14 +13693,14 @@ perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, cpu_buf->base = NULL; err = -errno; pr_warn("failed to mmap perf buffer on cpu #%d: %s\n", - cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + cpu, errstr(err)); goto error; } if (ioctl(cpu_buf->fd, PERF_EVENT_IOC_ENABLE, 0) < 0) { err = -errno; pr_warn("failed to enable perf buffer event on cpu #%d: %s\n", - cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + cpu, errstr(err)); goto error; } @@ -13210,7 +13737,6 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; attr.sample_type = PERF_SAMPLE_RAW; - attr.sample_period = sample_period; attr.wakeup_events = sample_period; p.attr = &attr; @@ -13249,7 +13775,6 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, { const char *online_cpus_file = "/sys/devices/system/cpu/online"; struct bpf_map_info map; - char msg[STRERR_BUFSIZE]; struct perf_buffer *pb; bool *online = NULL; __u32 map_info_len; @@ -13272,7 +13797,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, */ if (err != -EINVAL) { pr_warn("failed to get map info for map FD %d: %s\n", - map_fd, libbpf_strerror_r(err, msg, sizeof(msg))); + map_fd, errstr(err)); return ERR_PTR(err); } pr_debug("failed to get map info for FD %d; API not supported? Ignoring...\n", @@ -13302,7 +13827,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, if (pb->epoll_fd < 0) { err = -errno; pr_warn("failed to create epoll instance: %s\n", - libbpf_strerror_r(err, msg, sizeof(msg))); + errstr(err)); goto error; } @@ -13333,7 +13858,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, err = parse_cpu_mask_file(online_cpus_file, &online, &n); if (err) { - pr_warn("failed to get online CPU mask: %d\n", err); + pr_warn("failed to get online CPU mask: %s\n", errstr(err)); goto error; } @@ -13364,7 +13889,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, err = -errno; pr_warn("failed to set cpu #%d, key %d -> perf FD %d: %s\n", cpu, map_key, cpu_buf->fd, - libbpf_strerror_r(err, msg, sizeof(msg))); + errstr(err)); goto error; } @@ -13375,7 +13900,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, err = -errno; pr_warn("failed to epoll_ctl cpu #%d perf FD %d: %s\n", cpu, cpu_buf->fd, - libbpf_strerror_r(err, msg, sizeof(msg))); + errstr(err)); goto error; } j++; @@ -13470,7 +13995,7 @@ int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) err = perf_buffer__process_records(pb, cpu_buf); if (err) { - pr_warn("error while processing records: %d\n", err); + pr_warn("error while processing records: %s\n", errstr(err)); return libbpf_err(err); } } @@ -13554,7 +14079,8 @@ int perf_buffer__consume(struct perf_buffer *pb) err = perf_buffer__process_records(pb, cpu_buf); if (err) { - pr_warn("perf_buffer: failed to process records in buffer #%d: %d\n", i, err); + pr_warn("perf_buffer: failed to process records in buffer #%d: %s\n", + i, errstr(err)); return libbpf_err(err); } } @@ -13570,12 +14096,12 @@ int bpf_program__set_attach_target(struct bpf_program *prog, if (!prog || attach_prog_fd < 0) return libbpf_err(-EINVAL); - if (prog->obj->loaded) + if (prog->obj->state >= 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 + /* Store attach_prog_fd. The BTF ID will be resolved later during + * the normal object/program load phase. */ prog->attach_prog_fd = attach_prog_fd; return 0; @@ -13583,7 +14109,7 @@ int bpf_program__set_attach_target(struct bpf_program *prog, if (attach_prog_fd) { btf_id = libbpf_find_prog_btf_id(attach_func_name, - attach_prog_fd); + attach_prog_fd, prog->obj->token_fd); if (btf_id < 0) return libbpf_err(btf_id); } else { @@ -13665,14 +14191,14 @@ int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz) fd = open(fcpu, O_RDONLY | O_CLOEXEC); if (fd < 0) { err = -errno; - pr_warn("Failed to open cpu mask file %s: %d\n", fcpu, err); + pr_warn("Failed to open cpu mask file %s: %s\n", fcpu, errstr(err)); return err; } len = read(fd, buf, sizeof(buf)); close(fd); if (len <= 0) { err = len ? -errno : -EINVAL; - pr_warn("Failed to read cpu mask from %s: %d\n", fcpu, err); + pr_warn("Failed to read cpu mask from %s: %s\n", fcpu, errstr(err)); return err; } if (len >= sizeof(buf)) { @@ -13758,42 +14284,27 @@ static int populate_skeleton_progs(const struct bpf_object *obj, int bpf_object__open_skeleton(struct bpf_object_skeleton *s, const struct bpf_object_open_opts *opts) { - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts, - .object_name = s->name, - ); struct bpf_object *obj; int err; - /* Attempt to preserve opts->object_name, unless overriden by user - * explicitly. Overwriting object name for skeletons is discouraged, - * as it breaks global data maps, because they contain object name - * prefix as their own map name prefix. When skeleton is generated, - * bpftool is making an assumption that this name will stay the same. - */ - if (opts) { - memcpy(&skel_opts, opts, sizeof(*opts)); - if (!opts->object_name) - skel_opts.object_name = s->name; - } - - obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts); - err = libbpf_get_error(obj); - if (err) { - pr_warn("failed to initialize skeleton BPF object '%s': %d\n", - s->name, err); + obj = bpf_object_open(NULL, s->data, s->data_sz, s->name, opts); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + pr_warn("failed to initialize skeleton BPF object '%s': %s\n", + s->name, errstr(err)); return libbpf_err(err); } *s->obj = obj; err = populate_skeleton_maps(obj, s->maps, s->map_cnt, s->map_skel_sz); if (err) { - pr_warn("failed to populate skeleton maps for '%s': %d\n", s->name, err); + pr_warn("failed to populate skeleton maps for '%s': %s\n", s->name, errstr(err)); return libbpf_err(err); } err = populate_skeleton_progs(obj, s->progs, s->prog_cnt, s->prog_skel_sz); if (err) { - pr_warn("failed to populate skeleton progs for '%s': %d\n", s->name, err); + pr_warn("failed to populate skeleton progs for '%s': %s\n", s->name, errstr(err)); return libbpf_err(err); } @@ -13823,13 +14334,13 @@ int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s) err = populate_skeleton_maps(s->obj, s->maps, s->map_cnt, s->map_skel_sz); if (err) { - pr_warn("failed to populate subskeleton maps: %d\n", err); + pr_warn("failed to populate subskeleton maps: %s\n", errstr(err)); return libbpf_err(err); } err = populate_skeleton_progs(s->obj, s->progs, s->prog_cnt, s->prog_skel_sz); if (err) { - pr_warn("failed to populate subskeleton maps: %d\n", err); + pr_warn("failed to populate subskeleton maps: %s\n", errstr(err)); return libbpf_err(err); } @@ -13840,7 +14351,7 @@ int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s) map_type = btf__type_by_id(btf, map_type_id); if (!btf_is_datasec(map_type)) { - pr_warn("type for map '%1$s' is not a datasec: %2$s", + pr_warn("type for map '%1$s' is not a datasec: %2$s\n", bpf_map__name(map), __btf_kind_str(btf_kind(map_type))); return libbpf_err(-EINVAL); @@ -13876,53 +14387,18 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) err = bpf_object__load(*s->obj); if (err) { - pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err); + pr_warn("failed to load BPF skeleton '%s': %s\n", s->name, errstr(err)); return libbpf_err(err); } for (i = 0; i < s->map_cnt; i++) { struct bpf_map_skeleton *map_skel = (void *)s->maps + i * s->map_skel_sz; struct bpf_map *map = *map_skel->map; - size_t mmap_sz = bpf_map_mmap_sz(map); - int prot, map_fd = map->fd; - void **mmaped = map_skel->mmaped; - - if (!mmaped) - continue; - - if (!(map->def.map_flags & BPF_F_MMAPABLE)) { - *mmaped = NULL; - continue; - } - if (map->def.type == BPF_MAP_TYPE_ARENA) { - *mmaped = map->mmaped; + if (!map_skel->mmaped) continue; - } - - if (map->def.map_flags & BPF_F_RDONLY_PROG) - prot = PROT_READ; - else - prot = PROT_READ | PROT_WRITE; - /* Remap anonymous mmap()-ed "map initialization image" as - * a BPF map-backed mmap()-ed memory, but preserving the same - * memory address. This will cause kernel to change process' - * page table to point to a different piece of kernel memory, - * but from userspace point of view memory address (and its - * contents, being identical at this point) will stay the - * same. This mapping will be released by bpf_object__close() - * as per normal clean up procedure, so we don't need to worry - * about it from skeleton's clean up perspective. - */ - *mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map_fd, 0); - if (*mmaped == MAP_FAILED) { - err = -errno; - *mmaped = NULL; - pr_warn("failed to re-mmap() map '%s': %d\n", - bpf_map__name(map), err); - return libbpf_err(err); - } + *map_skel->mmaped = map->mmaped; } return 0; @@ -13950,8 +14426,8 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, link); if (err) { - pr_warn("prog '%s': failed to auto-attach: %d\n", - bpf_program__name(prog), err); + pr_warn("prog '%s': failed to auto-attach: %s\n", + bpf_program__name(prog), errstr(err)); return libbpf_err(err); } @@ -13988,13 +14464,20 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) } link = map_skel->link; + if (!link) { + pr_warn("map '%s': BPF map skeleton link is uninitialized\n", + bpf_map__name(map)); + continue; + } + if (*link) continue; *link = bpf_map__attach_struct_ops(map); if (!*link) { err = -errno; - pr_warn("map '%s': failed to auto-attach: %d\n", bpf_map__name(map), err); + pr_warn("map '%s': failed to auto-attach: %s\n", + bpf_map__name(map), errstr(err)); return libbpf_err(err); } } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 64a6a3d323e3..65e68e964b89 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -24,8 +24,25 @@ extern "C" { #endif +/** + * @brief **libbpf_major_version()** provides the major version of libbpf. + * @return An integer, the major version number + */ LIBBPF_API __u32 libbpf_major_version(void); + +/** + * @brief **libbpf_minor_version()** provides the minor version of libbpf. + * @return An integer, the minor version number + */ LIBBPF_API __u32 libbpf_minor_version(void); + +/** + * @brief **libbpf_version_string()** provides the version of libbpf in a + * human-readable form, e.g., "v1.7". + * @return Pointer to a static string containing the version + * + * The format is *not* a part of a stable API and may change in the future. + */ LIBBPF_API const char *libbpf_version_string(void); enum libbpf_errno { @@ -49,6 +66,14 @@ enum libbpf_errno { __LIBBPF_ERRNO__END, }; +/** + * @brief **libbpf_strerror()** converts the provided error code into a + * human-readable string. + * @param err The error code to convert + * @param buf Pointer to a buffer where the error message will be stored + * @param size The number of bytes in the buffer + * @return 0, on success; negative error code, otherwise + */ LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size); /** @@ -152,7 +177,7 @@ struct bpf_object_open_opts { * log_buf and log_level settings. * * If specified, this log buffer will be passed for: - * - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden + * - each BPF progral load (BPF_PROG_LOAD) attempt, unless overridden * with bpf_program__set_log() on per-program level, to get * BPF verifier log output. * - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get @@ -242,6 +267,19 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts); /** + * @brief **bpf_object__prepare()** prepares BPF object for loading: + * performs ELF processing, relocations, prepares final state of BPF program + * instructions (accessible with bpf_program__insns()), creates and + * (potentially) pins maps. Leaves BPF object in the state ready for program + * loading. + * @param obj Pointer to a valid BPF object instance returned by + * **bpf_object__open*()** API + * @return 0, on success; negative error code, otherwise, error code is + * stored in errno + */ +LIBBPF_API int bpf_object__prepare(struct bpf_object *obj); + +/** * @brief **bpf_object__load()** loads BPF object into kernel. * @param obj Pointer to a valid BPF object instance returned by * **bpf_object__open*()** APIs @@ -294,6 +332,14 @@ LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); LIBBPF_API int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version); +/** + * @brief **bpf_object__token_fd** is an accessor for BPF token FD associated + * with BPF object. + * @param obj Pointer to a valid BPF object + * @return BPF token FD or -1, if it wasn't set + */ +LIBBPF_API int bpf_object__token_fd(const struct bpf_object *obj); + struct btf; LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); @@ -402,7 +448,7 @@ LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); /** * @brief **bpf_program__unpin()** unpins the BPF program from a file - * in the BPFFS specified by a path. This decrements the programs + * in the BPFFS specified by a path. This decrements program's in-kernel * reference count. * * The file pinning the BPF program can also be unlinked by a different @@ -435,14 +481,12 @@ LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path); /** * @brief **bpf_link__unpin()** unpins the BPF link from a file - * in the BPFFS specified by a path. This decrements the links - * reference count. + * in the BPFFS. This decrements link's in-kernel reference count. * * The file pinning the BPF link can also be unlinked by a different * process in which case this function will return an error. * - * @param prog BPF program to unpin - * @param path file path to the pin in a BPF file system + * @param link BPF link to unpin * @return 0, on success; negative error code, otherwise */ LIBBPF_API int bpf_link__unpin(struct bpf_link *link); @@ -455,7 +499,7 @@ LIBBPF_API int bpf_link__destroy(struct bpf_link *link); /** * @brief **bpf_program__attach()** is a generic function for attaching * a BPF program based on auto-detection of program type, attach type, - * and extra paremeters, where applicable. + * and extra parameters, where applicable. * * @param prog BPF program to attach * @return Reference to the newly created BPF link; or NULL is returned on error, @@ -478,9 +522,11 @@ struct bpf_perf_event_opts { __u64 bpf_cookie; /* don't use BPF link when attach BPF program */ bool force_ioctl_attach; + /* don't automatically enable the event */ + bool dont_enable; size_t :0; }; -#define bpf_perf_event_opts__last_field force_ioctl_attach +#define bpf_perf_event_opts__last_field dont_enable LIBBPF_API struct bpf_link * bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd); @@ -544,10 +590,12 @@ struct bpf_kprobe_multi_opts { bool retprobe; /* create session kprobes */ bool session; + /* enforce unique match */ + bool unique_match; size_t :0; }; -#define bpf_kprobe_multi_opts__last_field session +#define bpf_kprobe_multi_opts__last_field unique_match LIBBPF_API struct bpf_link * bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, @@ -569,10 +617,12 @@ struct bpf_uprobe_multi_opts { size_t cnt; /* create return uprobes */ bool retprobe; + /* create session kprobes */ + bool session; size_t :0; }; -#define bpf_uprobe_multi_opts__last_field retprobe +#define bpf_uprobe_multi_opts__last_field session /** * @brief **bpf_program__attach_uprobe_multi()** attaches a BPF program @@ -679,7 +729,7 @@ struct bpf_uprobe_opts { /** * @brief **bpf_program__attach_uprobe()** attaches a BPF program * to the userspace function which is found by binary path and - * offset. You can optionally specify a particular proccess to attach + * offset. You can optionally specify a particular process to attach * to. You can also optionally attach the program to the function * exit instead of entry. * @@ -852,6 +902,21 @@ LIBBPF_API struct bpf_link * bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex, const struct bpf_netkit_opts *opts); +struct bpf_cgroup_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + __u32 flags; + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + size_t :0; +}; +#define bpf_cgroup_opts__last_field expected_revision + +LIBBPF_API struct bpf_link * +bpf_program__attach_cgroup_opts(const struct bpf_program *prog, int cgroup_fd, + const struct bpf_cgroup_opts *opts); + struct bpf_map; LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map); @@ -915,6 +980,12 @@ LIBBPF_API int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_le LIBBPF_API const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size); LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size); +LIBBPF_API struct bpf_func_info *bpf_program__func_info(const struct bpf_program *prog); +LIBBPF_API __u32 bpf_program__func_info_cnt(const struct bpf_program *prog); + +LIBBPF_API struct bpf_line_info *bpf_program__line_info(const struct bpf_program *prog); +LIBBPF_API __u32 bpf_program__line_info_cnt(const struct bpf_program *prog); + /** * @brief **bpf_program__set_attach_target()** sets BTF-based attach target * for supported BPF program types: @@ -922,8 +993,13 @@ LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, * - fentry/fexit/fmod_ret; * - lsm; * - freplace. - * @param prog BPF program to set the attach type for - * @param type attach type to set the BPF map to have + * @param prog BPF program to configure; must be not yet loaded. + * @param attach_prog_fd FD of target BPF program (for freplace/extension). + * If >0 and func name omitted, defers BTF ID resolution. + * @param attach_func_name Target function name. Used either with + * attach_prog_fd to find destination BTF type ID in that BPF program, or + * alone (no attach_prog_fd) to resolve kernel (vmlinux/module) BTF ID. + * Must be provided if attach_prog_fd is 0. * @return error code; or 0 if no error occurred. */ LIBBPF_API int @@ -1025,6 +1101,7 @@ LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map); /** * @brief **bpf_map__set_value_size()** sets map value size. * @param map the BPF map instance + * @param size the new value size * @return 0, on success; negative error, otherwise * * There is a special case for maps with associated memory-mapped regions, like @@ -1129,7 +1206,7 @@ LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); * per-CPU values value size has to be aligned up to closest 8 bytes for * alignment reasons, so expected size is: `round_up(value_size, 8) * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__lookup_elem()** is high-level equivalent of @@ -1153,7 +1230,7 @@ LIBBPF_API int bpf_map__lookup_elem(const struct bpf_map *map, * per-CPU values value size has to be aligned up to closest 8 bytes for * alignment reasons, so expected size is: `round_up(value_size, 8) * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__update_elem()** is high-level equivalent of @@ -1169,7 +1246,7 @@ LIBBPF_API int bpf_map__update_elem(const struct bpf_map *map, * @param map BPF map to delete element from * @param key pointer to memory containing bytes of the key * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__delete_elem()** is high-level equivalent of @@ -1192,7 +1269,7 @@ LIBBPF_API int bpf_map__delete_elem(const struct bpf_map *map, * per-CPU values value size has to be aligned up to closest 8 bytes for * alignment reasons, so expected size is: `round_up(value_size, 8) * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__lookup_and_delete_elem()** is high-level equivalent of @@ -1218,6 +1295,28 @@ LIBBPF_API int bpf_map__lookup_and_delete_elem(const struct bpf_map *map, */ LIBBPF_API int bpf_map__get_next_key(const struct bpf_map *map, const void *cur_key, void *next_key, size_t key_sz); +/** + * @brief **bpf_map__set_exclusive_program()** sets a map to be exclusive to the + * specified program. This must be called *before* the map is created. + * + * @param map BPF map to make exclusive. + * @param prog BPF program to be the exclusive user of the map. Must belong + * to the same bpf_object as the map. + * @return 0 on success; a negative error code otherwise. + * + * This function must be called after the BPF object is opened but before + * it is loaded. Once the object is loaded, only the specified program + * will be able to access the map's contents. + */ +LIBBPF_API int bpf_map__set_exclusive_program(struct bpf_map *map, struct bpf_program *prog); + +/** + * @brief **bpf_map__exclusive_program()** returns the exclusive program + * that is registered with the map (if any). + * @param map BPF map to which the exclusive program is registered. + * @return the registered exclusive program. + */ +LIBBPF_API struct bpf_program *bpf_map__exclusive_program(struct bpf_map *map); struct bpf_xdp_set_link_opts { size_t sz; @@ -1258,6 +1357,7 @@ enum bpf_tc_attach_point { BPF_TC_INGRESS = 1 << 0, BPF_TC_EGRESS = 1 << 1, BPF_TC_CUSTOM = 1 << 2, + BPF_TC_QDISC = 1 << 3, }; #define BPF_TC_PARENT(a, b) \ @@ -1272,9 +1372,11 @@ struct bpf_tc_hook { int ifindex; enum bpf_tc_attach_point attach_point; __u32 parent; + __u32 handle; + const char *qdisc; size_t :0; }; -#define bpf_tc_hook__last_field parent +#define bpf_tc_hook__last_field qdisc struct bpf_tc_opts { size_t sz; @@ -1539,6 +1641,7 @@ struct perf_buffer_opts { * @param sample_cb function called on each received data record * @param lost_cb function called when record loss has occurred * @param ctx user-provided extra context passed into *sample_cb* and *lost_cb* + * @param opts optional parameters for the perf buffer, can be null * @return a new instance of struct perf_buffer on success, NULL on error with * *errno* containing an error code */ @@ -1593,11 +1696,11 @@ LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_i * memory region of the ring buffer. * This ring buffer can be used to implement a custom events consumer. * The ring buffer starts with the *struct perf_event_mmap_page*, which - * holds the ring buffer managment fields, when accessing the header + * holds the ring buffer management fields, when accessing the header * structure it's important to be SMP aware. * You can refer to *perf_event_read_simple* for a simple example. * @param pb the perf buffer structure - * @param buf_idx the buffer index to retreive + * @param buf_idx the buffer index to retrieve * @param buf (out) gets the base pointer of the mmap()'ed memory * @param buf_size (out) gets the size of the mmap()'ed region * @return 0 on success, negative error code for failure @@ -1759,9 +1862,10 @@ struct gen_loader_opts { const char *insns; __u32 data_sz; __u32 insns_sz; + bool gen_hash; }; -#define gen_loader_opts__last_field insns_sz +#define gen_loader_opts__last_field gen_hash LIBBPF_API int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts); @@ -1786,9 +1890,14 @@ struct bpf_linker_file_opts { struct bpf_linker; LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts); +LIBBPF_API struct bpf_linker *bpf_linker__new_fd(int fd, struct bpf_linker_opts *opts); LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, const struct bpf_linker_file_opts *opts); +LIBBPF_API int bpf_linker__add_fd(struct bpf_linker *linker, int fd, + const struct bpf_linker_file_opts *opts); +LIBBPF_API int bpf_linker__add_buf(struct bpf_linker *linker, void *buf, size_t buf_sz, + const struct bpf_linker_file_opts *opts); LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker); LIBBPF_API void bpf_linker__free(struct bpf_linker *linker); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 8f0d9ea3b1b4..8ed8749907d4 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -421,9 +421,34 @@ LIBBPF_1.5.0 { global: btf__distill_base; btf__relocate; + btf_ext__endianness; + btf_ext__set_endianness; bpf_map__autoattach; bpf_map__set_autoattach; + bpf_object__token_fd; bpf_program__attach_sockmap; ring__consume_n; ring_buffer__consume_n; } LIBBPF_1.4.0; + +LIBBPF_1.6.0 { + global: + bpf_linker__add_buf; + bpf_linker__add_fd; + bpf_linker__new_fd; + bpf_object__prepare; + bpf_prog_stream_read; + bpf_program__attach_cgroup_opts; + bpf_program__func_info; + bpf_program__func_info_cnt; + bpf_program__line_info; + bpf_program__line_info_cnt; + btf__add_decl_attr; + btf__add_type_attr; +} LIBBPF_1.5.0; + +LIBBPF_1.7.0 { + global: + bpf_map__set_exclusive_program; + bpf_map__exclusive_program; +} LIBBPF_1.6.0; diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c deleted file mode 100644 index 6b180172ec6b..000000000000 --- a/tools/lib/bpf/libbpf_errno.c +++ /dev/null @@ -1,75 +0,0 @@ -// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) - -/* - * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> - * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> - * Copyright (C) 2015 Huawei Inc. - * Copyright (C) 2017 Nicira, Inc. - */ - -#undef _GNU_SOURCE -#include <stdio.h> -#include <string.h> - -#include "libbpf.h" -#include "libbpf_internal.h" - -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - -#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START) -#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c) -#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START) - -static const char *libbpf_strerror_table[NR_ERRNO] = { - [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf", - [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid", - [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost", - [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch", - [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf", - [ERRCODE_OFFSET(RELOC)] = "Relocation failed", - [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading", - [ERRCODE_OFFSET(PROG2BIG)] = "Program too big", - [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version", - [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type", - [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message", - [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence", - [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing", -}; - -int libbpf_strerror(int err, char *buf, size_t size) -{ - int ret; - - if (!buf || !size) - return libbpf_err(-EINVAL); - - err = err > 0 ? err : -err; - - if (err < __LIBBPF_ERRNO__START) { - ret = strerror_r(err, buf, size); - buf[size - 1] = '\0'; - return libbpf_err_errno(ret); - } - - if (err < __LIBBPF_ERRNO__END) { - const char *msg; - - msg = libbpf_strerror_table[ERRNO_OFFSET(err)]; - ret = snprintf(buf, size, "%s", msg); - buf[size - 1] = '\0'; - /* The length of the buf and msg is positive. - * A negative number may be returned only when the - * size exceeds INT_MAX. Not likely to appear. - */ - if (ret >= size) - return libbpf_err(-ERANGE); - return 0; - } - - ret = snprintf(buf, size, "Unknown libbpf error %d", err); - buf[size - 1] = '\0'; - if (ret >= size) - return libbpf_err(-ERANGE); - return libbpf_err(-ENOENT); -} diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 408df59e0771..fc59b21b51b5 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -10,6 +10,7 @@ #define __LIBBPF_LIBBPF_INTERNAL_H #include <stdlib.h> +#include <byteswap.h> #include <limits.h> #include <errno.h> #include <linux/err.h> @@ -73,6 +74,8 @@ #define ELF64_ST_VISIBILITY(o) ((o) & 0x03) #endif +#define JUMPTABLES_SEC ".jumptables" + #define BTF_INFO_ENC(kind, kind_flag, vlen) \ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) @@ -171,6 +174,16 @@ do { \ #define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) #define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) +/** + * @brief **libbpf_errstr()** returns string corresponding to numeric errno + * @param err negative numeric errno + * @return pointer to string representation of the errno, that is invalidated + * upon the next call. + */ +const char *libbpf_errstr(int err); + +#define errstr(err) libbpf_errstr(err) + #ifndef __has_builtin #define __has_builtin(x) 0 #endif @@ -408,6 +421,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level, int token_fd); +struct btf *btf_load_from_kernel(__u32 id, struct btf *base_btf, int token_fd); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, @@ -448,11 +462,11 @@ struct btf_ext_info { * * The func_info subsection layout: * record size for struct bpf_func_info in the func_info subsection - * struct btf_sec_func_info for section #1 + * struct btf_ext_info_sec for section #1 * a list of bpf_func_info records for section #1 * where struct bpf_func_info mimics one in include/uapi/linux/bpf.h * but may not be identical - * struct btf_sec_func_info for section #2 + * struct btf_ext_info_sec for section #2 * a list of bpf_func_info records for section #2 * ...... * @@ -484,6 +498,8 @@ struct btf_ext { struct btf_ext_header *hdr; void *data; }; + void *data_swapped; + bool swapped_endian; struct btf_ext_info func_info; struct btf_ext_info line_info; struct btf_ext_info core_relo_info; @@ -511,6 +527,32 @@ struct bpf_line_info_min { __u32 line_col; }; +/* Functions to byte-swap info records */ + +typedef void (*info_rec_bswap_fn)(void *); + +static inline void bpf_func_info_bswap(struct bpf_func_info *i) +{ + i->insn_off = bswap_32(i->insn_off); + i->type_id = bswap_32(i->type_id); +} + +static inline void bpf_line_info_bswap(struct bpf_line_info *i) +{ + i->insn_off = bswap_32(i->insn_off); + i->file_name_off = bswap_32(i->file_name_off); + i->line_off = bswap_32(i->line_off); + i->line_col = bswap_32(i->line_col); +} + +static inline void bpf_core_relo_bswap(struct bpf_core_relo *i) +{ + i->insn_off = bswap_32(i->insn_off); + i->type_id = bswap_32(i->type_id); + i->access_str_off = bswap_32(i->access_str_off); + i->kind = bswap_32(i->kind); +} + enum btf_field_iter_kind { BTF_FIELD_ITER_IDS, BTF_FIELD_ITER_STRS, @@ -588,6 +630,16 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn) return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } +static inline void bpf_insn_bswap(struct bpf_insn *insn) +{ + __u8 tmp_reg = insn->dst_reg; + + insn->dst_reg = insn->src_reg; + insn->src_reg = tmp_reg; + insn->off = bswap_16(insn->off); + insn->imm = bswap_32(insn->imm); +} + /* Unconditionally dup FD, ensuring it doesn't use [0, 2] range. * Original FD is not closed or altered in any other way. * Preserves original FD value, if it's invalid (negative). @@ -627,6 +679,15 @@ static inline int sys_dup3(int oldfd, int newfd, int flags) return syscall(__NR_dup3, oldfd, newfd, flags); } +/* Some versions of Android don't provide memfd_create() in their libc + * implementation, so avoid complications and just go straight to Linux + * syscall. + */ +static inline int sys_memfd_create(const char *name, unsigned flags) +{ + return syscall(__NR_memfd_create, name, flags); +} + /* Point *fixed_fd* to the same file that *tmp_fd* points to. * Regardless of success, *tmp_fd* is closed. * Whatever *fixed_fd* pointed to is closed silently. @@ -663,6 +724,11 @@ static inline bool is_pow_of_2(size_t x) return x && (x & (x - 1)) == 0; } +static inline __u32 ror32(__u32 v, int bits) +{ + return (v >> bits) | (v << (32 - bits)); +} + #define PROG_LOAD_ATTEMPTS 5 int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts); @@ -687,4 +753,8 @@ int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern, int probe_fd(int fd); +#define SHA256_DIGEST_LENGTH 32 +#define SHA256_DWORD_SIZE SHA256_DIGEST_LENGTH / sizeof(__u64) + +void libbpf_sha256(const void *data, size_t len, __u8 out[SHA256_DIGEST_LENGTH]); #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index 1e1be467bede..60b2600be88a 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -76,7 +76,7 @@ enum libbpf_strict_mode { * first BPF program or map creation operation. This is done only if * kernel is too old to support memcg-based memory accounting for BPF * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY, - * but it can be overriden with libbpf_set_memlock_rlim() API. + * but it can be overridden with libbpf_set_memlock_rlim() API. * Note that libbpf_set_memlock_rlim() needs to be called before * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load() * operation. @@ -97,7 +97,7 @@ LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); * @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 + * @return error code; or 0 if no error occurred * * Note, as of libbpf 1.0 this function is not necessary and not recommended * to be used. Libbpf doesn't return error code embedded into the pointer diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 9dfbe7750f56..bccf4bb747e1 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -364,6 +364,10 @@ static int probe_map_create(enum bpf_map_type map_type) case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: break; + case BPF_MAP_TYPE_INSN_ARRAY: + key_size = sizeof(__u32); + value_size = sizeof(struct bpf_insn_array_value); + break; case BPF_MAP_TYPE_UNSPEC: default: return -EOPNOTSUPP; diff --git a/tools/lib/bpf/libbpf_utils.c b/tools/lib/bpf/libbpf_utils.c new file mode 100644 index 000000000000..ac3beae54cf6 --- /dev/null +++ b/tools/lib/bpf/libbpf_utils.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + * Copyright (C) 2017 Nicira, Inc. + */ + +#undef _GNU_SOURCE +#include <stdio.h> +#include <string.h> +#include <errno.h> +#include <inttypes.h> +#include <linux/kernel.h> + +#include "libbpf.h" +#include "libbpf_internal.h" + +#ifndef ENOTSUPP +#define ENOTSUPP 524 +#endif + +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START) +#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c) +#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START) + +static const char *libbpf_strerror_table[NR_ERRNO] = { + [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf", + [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid", + [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost", + [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch", + [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf", + [ERRCODE_OFFSET(RELOC)] = "Relocation failed", + [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading", + [ERRCODE_OFFSET(PROG2BIG)] = "Program too big", + [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version", + [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type", + [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message", + [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence", + [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing", +}; + +int libbpf_strerror(int err, char *buf, size_t size) +{ + int ret; + + if (!buf || !size) + return libbpf_err(-EINVAL); + + err = err > 0 ? err : -err; + + if (err < __LIBBPF_ERRNO__START) { + ret = strerror_r(err, buf, size); + buf[size - 1] = '\0'; + return libbpf_err_errno(ret); + } + + if (err < __LIBBPF_ERRNO__END) { + const char *msg; + + msg = libbpf_strerror_table[ERRNO_OFFSET(err)]; + ret = snprintf(buf, size, "%s", msg); + buf[size - 1] = '\0'; + /* The length of the buf and msg is positive. + * A negative number may be returned only when the + * size exceeds INT_MAX. Not likely to appear. + */ + if (ret >= size) + return libbpf_err(-ERANGE); + return 0; + } + + ret = snprintf(buf, size, "Unknown libbpf error %d", err); + buf[size - 1] = '\0'; + if (ret >= size) + return libbpf_err(-ERANGE); + return libbpf_err(-ENOENT); +} + +const char *libbpf_errstr(int err) +{ + static __thread char buf[12]; + + if (err > 0) + err = -err; + + switch (err) { + case -E2BIG: return "-E2BIG"; + case -EACCES: return "-EACCES"; + case -EADDRINUSE: return "-EADDRINUSE"; + case -EADDRNOTAVAIL: return "-EADDRNOTAVAIL"; + case -EAGAIN: return "-EAGAIN"; + case -EALREADY: return "-EALREADY"; + case -EBADF: return "-EBADF"; + case -EBADFD: return "-EBADFD"; + case -EBUSY: return "-EBUSY"; + case -ECANCELED: return "-ECANCELED"; + case -ECHILD: return "-ECHILD"; + case -EDEADLK: return "-EDEADLK"; + case -EDOM: return "-EDOM"; + case -EEXIST: return "-EEXIST"; + case -EFAULT: return "-EFAULT"; + case -EFBIG: return "-EFBIG"; + case -EILSEQ: return "-EILSEQ"; + case -EINPROGRESS: return "-EINPROGRESS"; + case -EINTR: return "-EINTR"; + case -EINVAL: return "-EINVAL"; + case -EIO: return "-EIO"; + case -EISDIR: return "-EISDIR"; + case -ELOOP: return "-ELOOP"; + case -EMFILE: return "-EMFILE"; + case -EMLINK: return "-EMLINK"; + case -EMSGSIZE: return "-EMSGSIZE"; + case -ENAMETOOLONG: return "-ENAMETOOLONG"; + case -ENFILE: return "-ENFILE"; + case -ENODATA: return "-ENODATA"; + case -ENODEV: return "-ENODEV"; + case -ENOENT: return "-ENOENT"; + case -ENOEXEC: return "-ENOEXEC"; + case -ENOLINK: return "-ENOLINK"; + case -ENOMEM: return "-ENOMEM"; + case -ENOSPC: return "-ENOSPC"; + case -ENOTBLK: return "-ENOTBLK"; + case -ENOTDIR: return "-ENOTDIR"; + case -ENOTSUPP: return "-ENOTSUPP"; + case -ENOTTY: return "-ENOTTY"; + case -ENXIO: return "-ENXIO"; + case -EOPNOTSUPP: return "-EOPNOTSUPP"; + case -EOVERFLOW: return "-EOVERFLOW"; + case -EPERM: return "-EPERM"; + case -EPIPE: return "-EPIPE"; + case -EPROTO: return "-EPROTO"; + case -EPROTONOSUPPORT: return "-EPROTONOSUPPORT"; + case -ERANGE: return "-ERANGE"; + case -EROFS: return "-EROFS"; + case -ESPIPE: return "-ESPIPE"; + case -ESRCH: return "-ESRCH"; + case -ETXTBSY: return "-ETXTBSY"; + case -EUCLEAN: return "-EUCLEAN"; + case -EXDEV: return "-EXDEV"; + default: + snprintf(buf, sizeof(buf), "%d", err); + return buf; + } +} + +static inline __u32 get_unaligned_be32(const void *p) +{ + __be32 val; + + memcpy(&val, p, sizeof(val)); + return be32_to_cpu(val); +} + +static inline void put_unaligned_be32(__u32 val, void *p) +{ + __be32 be_val = cpu_to_be32(val); + + memcpy(p, &be_val, sizeof(be_val)); +} + +#define SHA256_BLOCK_LENGTH 64 +#define Ch(x, y, z) (((x) & (y)) ^ (~(x) & (z))) +#define Maj(x, y, z) (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z))) +#define Sigma_0(x) (ror32((x), 2) ^ ror32((x), 13) ^ ror32((x), 22)) +#define Sigma_1(x) (ror32((x), 6) ^ ror32((x), 11) ^ ror32((x), 25)) +#define sigma_0(x) (ror32((x), 7) ^ ror32((x), 18) ^ ((x) >> 3)) +#define sigma_1(x) (ror32((x), 17) ^ ror32((x), 19) ^ ((x) >> 10)) + +static const __u32 sha256_K[64] = { + 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1, + 0x923f82a4, 0xab1c5ed5, 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, + 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174, 0xe49b69c1, 0xefbe4786, + 0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da, + 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147, + 0x06ca6351, 0x14292967, 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13, + 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85, 0xa2bfe8a1, 0xa81a664b, + 0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070, + 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a, + 0x5b9cca4f, 0x682e6ff3, 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208, + 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2, +}; + +#define SHA256_ROUND(i, a, b, c, d, e, f, g, h) \ + { \ + __u32 tmp = h + Sigma_1(e) + Ch(e, f, g) + sha256_K[i] + w[i]; \ + d += tmp; \ + h = tmp + Sigma_0(a) + Maj(a, b, c); \ + } + +static void sha256_blocks(__u32 state[8], const __u8 *data, size_t nblocks) +{ + while (nblocks--) { + __u32 a = state[0]; + __u32 b = state[1]; + __u32 c = state[2]; + __u32 d = state[3]; + __u32 e = state[4]; + __u32 f = state[5]; + __u32 g = state[6]; + __u32 h = state[7]; + __u32 w[64]; + int i; + + for (i = 0; i < 16; i++) + w[i] = get_unaligned_be32(&data[4 * i]); + for (; i < ARRAY_SIZE(w); i++) + w[i] = sigma_1(w[i - 2]) + w[i - 7] + + sigma_0(w[i - 15]) + w[i - 16]; + for (i = 0; i < ARRAY_SIZE(w); i += 8) { + SHA256_ROUND(i + 0, a, b, c, d, e, f, g, h); + SHA256_ROUND(i + 1, h, a, b, c, d, e, f, g); + SHA256_ROUND(i + 2, g, h, a, b, c, d, e, f); + SHA256_ROUND(i + 3, f, g, h, a, b, c, d, e); + SHA256_ROUND(i + 4, e, f, g, h, a, b, c, d); + SHA256_ROUND(i + 5, d, e, f, g, h, a, b, c); + SHA256_ROUND(i + 6, c, d, e, f, g, h, a, b); + SHA256_ROUND(i + 7, b, c, d, e, f, g, h, a); + } + state[0] += a; + state[1] += b; + state[2] += c; + state[3] += d; + state[4] += e; + state[5] += f; + state[6] += g; + state[7] += h; + data += SHA256_BLOCK_LENGTH; + } +} + +void libbpf_sha256(const void *data, size_t len, __u8 out[SHA256_DIGEST_LENGTH]) +{ + __u32 state[8] = { 0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a, + 0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19 }; + const __be64 bitcount = cpu_to_be64((__u64)len * 8); + __u8 final_data[2 * SHA256_BLOCK_LENGTH] = { 0 }; + size_t final_len = len % SHA256_BLOCK_LENGTH; + int i; + + sha256_blocks(state, data, len / SHA256_BLOCK_LENGTH); + + memcpy(final_data, data + len - final_len, final_len); + final_data[final_len] = 0x80; + final_len = roundup(final_len + 9, SHA256_BLOCK_LENGTH); + memcpy(&final_data[final_len - 8], &bitcount, 8); + + sha256_blocks(state, final_data, final_len / SHA256_BLOCK_LENGTH); + + for (i = 0; i < ARRAY_SIZE(state); i++) + put_unaligned_be32(state[i], &out[4 * i]); +} diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index d6e5eff967cb..99331e317dee 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 1 -#define LIBBPF_MINOR_VERSION 5 +#define LIBBPF_MINOR_VERSION 7 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 9cd3d4109788..f4403e3cf994 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -4,6 +4,10 @@ * * Copyright (c) 2021 Facebook */ +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif + #include <stdbool.h> #include <stddef.h> #include <stdio.h> @@ -16,6 +20,7 @@ #include <elf.h> #include <libelf.h> #include <fcntl.h> +#include <sys/mman.h> #include "libbpf.h" #include "btf.h" #include "libbpf_internal.h" @@ -135,6 +140,7 @@ struct bpf_linker { int fd; Elf *elf; Elf64_Ehdr *elf_hdr; + bool swapped_endian; /* Output sections metadata */ struct dst_sec *secs; @@ -150,15 +156,19 @@ struct bpf_linker { /* global (including extern) ELF symbols */ int glob_sym_cnt; struct glob_sym *glob_syms; + + bool fd_is_owned; }; #define pr_warn_elf(fmt, ...) \ libbpf_print(LIBBPF_WARN, "libbpf: " fmt ": %s\n", ##__VA_ARGS__, elf_errmsg(-1)) -static int init_output_elf(struct bpf_linker *linker, const char *file); +static int init_output_elf(struct bpf_linker *linker); -static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, - const struct bpf_linker_file_opts *opts, +static int bpf_linker_add_file(struct bpf_linker *linker, int fd, + const char *filename); + +static int linker_load_obj_file(struct bpf_linker *linker, struct src_obj *obj); static int linker_sanity_check_elf(struct src_obj *obj); static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec); @@ -189,7 +199,7 @@ void bpf_linker__free(struct bpf_linker *linker) if (linker->elf) elf_end(linker->elf); - if (linker->fd >= 0) + if (linker->fd >= 0 && linker->fd_is_owned) close(linker->fd); strset__free(linker->strtab_strs); @@ -231,9 +241,63 @@ struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts if (!linker) return errno = ENOMEM, NULL; - linker->fd = -1; + linker->filename = strdup(filename); + if (!linker->filename) { + err = -ENOMEM; + goto err_out; + } + + linker->fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644); + if (linker->fd < 0) { + err = -errno; + pr_warn("failed to create '%s': %d\n", filename, err); + goto err_out; + } + linker->fd_is_owned = true; + + err = init_output_elf(linker); + if (err) + goto err_out; + + return linker; + +err_out: + bpf_linker__free(linker); + return errno = -err, NULL; +} + +struct bpf_linker *bpf_linker__new_fd(int fd, struct bpf_linker_opts *opts) +{ + struct bpf_linker *linker; + char filename[32]; + int err; + + if (fd < 0) + return errno = EINVAL, NULL; + + if (!OPTS_VALID(opts, bpf_linker_opts)) + return errno = EINVAL, NULL; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn_elf("libelf initialization failed"); + return errno = EINVAL, NULL; + } + + linker = calloc(1, sizeof(*linker)); + if (!linker) + return errno = ENOMEM, NULL; + + snprintf(filename, sizeof(filename), "fd:%d", fd); + linker->filename = strdup(filename); + if (!linker->filename) { + err = -ENOMEM; + goto err_out; + } + + linker->fd = fd; + linker->fd_is_owned = false; - err = init_output_elf(linker, filename); + err = init_output_elf(linker); if (err) goto err_out; @@ -292,23 +356,12 @@ static Elf64_Sym *add_new_sym(struct bpf_linker *linker, size_t *sym_idx) return sym; } -static int init_output_elf(struct bpf_linker *linker, const char *file) +static int init_output_elf(struct bpf_linker *linker) { int err, str_off; Elf64_Sym *init_sym; struct dst_sec *sec; - linker->filename = strdup(file); - if (!linker->filename) - return -ENOMEM; - - linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644); - if (linker->fd < 0) { - err = -errno; - pr_warn("failed to create '%s': %d\n", file, err); - return err; - } - linker->elf = elf_begin(linker->fd, ELF_C_WRITE, NULL); if (!linker->elf) { pr_warn_elf("failed to create ELF object"); @@ -324,13 +377,8 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) linker->elf_hdr->e_machine = EM_BPF; linker->elf_hdr->e_type = ET_REL; -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ - linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB; -#else -#error "Unknown __BYTE_ORDER__" -#endif + /* Set unknown ELF endianness, assign later from input files */ + linker->elf_hdr->e_ident[EI_DATA] = ELFDATANONE; /* STRTAB */ /* initialize strset with an empty string to conform to ELF */ @@ -396,6 +444,8 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) pr_warn_elf("failed to create SYMTAB data"); return -EINVAL; } + /* Ensure libelf translates byte-order of symbol records */ + sec->data->d_type = ELF_T_SYM; str_off = strset__add_str(linker->strtab_strs, sec->sec_name); if (str_off < 0) @@ -437,19 +487,16 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) return 0; } -int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, - const struct bpf_linker_file_opts *opts) +static int bpf_linker_add_file(struct bpf_linker *linker, int fd, + const char *filename) { struct src_obj obj = {}; int err = 0; - if (!OPTS_VALID(opts, bpf_linker_file_opts)) - return libbpf_err(-EINVAL); + obj.filename = filename; + obj.fd = fd; - if (!linker->elf) - return libbpf_err(-EINVAL); - - err = err ?: linker_load_obj_file(linker, filename, opts, &obj); + err = err ?: linker_load_obj_file(linker, &obj); err = err ?: linker_append_sec_data(linker, &obj); err = err ?: linker_append_elf_syms(linker, &obj); err = err ?: linker_append_elf_relos(linker, &obj); @@ -464,12 +511,91 @@ int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, free(obj.sym_map); if (obj.elf) elf_end(obj.elf); - if (obj.fd >= 0) - close(obj.fd); + return err; +} + +int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts) +{ + int fd, err; + + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); + + if (!linker->elf) + return libbpf_err(-EINVAL); + + fd = open(filename, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + err = -errno; + pr_warn("failed to open file '%s': %s\n", filename, errstr(err)); + return libbpf_err(err); + } + + err = bpf_linker_add_file(linker, fd, filename); + close(fd); + return libbpf_err(err); +} + +int bpf_linker__add_fd(struct bpf_linker *linker, int fd, + const struct bpf_linker_file_opts *opts) +{ + char filename[32]; + int err; + + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); + + if (!linker->elf) + return libbpf_err(-EINVAL); + + if (fd < 0) + return libbpf_err(-EINVAL); + + snprintf(filename, sizeof(filename), "fd:%d", fd); + err = bpf_linker_add_file(linker, fd, filename); return libbpf_err(err); } +int bpf_linker__add_buf(struct bpf_linker *linker, void *buf, size_t buf_sz, + const struct bpf_linker_file_opts *opts) +{ + char filename[32]; + int fd, written, ret; + + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); + + if (!linker->elf) + return libbpf_err(-EINVAL); + + snprintf(filename, sizeof(filename), "mem:%p+%zu", buf, buf_sz); + + fd = sys_memfd_create(filename, 0); + if (fd < 0) { + ret = -errno; + pr_warn("failed to create memfd '%s': %s\n", filename, errstr(ret)); + return libbpf_err(ret); + } + + written = 0; + while (written < buf_sz) { + ret = write(fd, buf, buf_sz); + if (ret < 0) { + ret = -errno; + pr_warn("failed to write '%s': %s\n", filename, errstr(ret)); + goto err_out; + } + written += ret; + } + + ret = bpf_linker_add_file(linker, fd, filename); +err_out: + close(fd); + return libbpf_err(ret); +} + static bool is_dwarf_sec_name(const char *name) { /* approximation, but the actual list is too long */ @@ -535,65 +661,69 @@ static struct src_sec *add_src_sec(struct src_obj *obj, const char *sec_name) return sec; } -static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, - const struct bpf_linker_file_opts *opts, +static int linker_load_obj_file(struct bpf_linker *linker, struct src_obj *obj) { -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ - const int host_endianness = ELFDATA2LSB; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - const int host_endianness = ELFDATA2MSB; -#else -#error "Unknown __BYTE_ORDER__" -#endif int err = 0; Elf_Scn *scn; Elf_Data *data; Elf64_Ehdr *ehdr; Elf64_Shdr *shdr; struct src_sec *sec; + unsigned char obj_byteorder; + unsigned char link_byteorder = linker->elf_hdr->e_ident[EI_DATA]; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + const unsigned char host_byteorder = ELFDATA2LSB; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + const unsigned char host_byteorder = ELFDATA2MSB; +#else +#error "Unknown __BYTE_ORDER__" +#endif - pr_debug("linker: adding object file '%s'...\n", filename); - - obj->filename = filename; + pr_debug("linker: adding object file '%s'...\n", obj->filename); - obj->fd = open(filename, O_RDONLY | O_CLOEXEC); - if (obj->fd < 0) { - err = -errno; - pr_warn("failed to open file '%s': %d\n", filename, err); - return err; - } obj->elf = elf_begin(obj->fd, ELF_C_READ_MMAP, NULL); if (!obj->elf) { - err = -errno; - pr_warn_elf("failed to parse ELF file '%s'", filename); - return err; + pr_warn_elf("failed to parse ELF file '%s'", obj->filename); + return -EINVAL; } /* Sanity check ELF file high-level properties */ ehdr = elf64_getehdr(obj->elf); if (!ehdr) { - err = -errno; - pr_warn_elf("failed to get ELF header for %s", filename); + pr_warn_elf("failed to get ELF header for %s", obj->filename); + return -EINVAL; + } + + /* Linker output endianness set by first input object */ + obj_byteorder = ehdr->e_ident[EI_DATA]; + if (obj_byteorder != ELFDATA2LSB && obj_byteorder != ELFDATA2MSB) { + err = -EOPNOTSUPP; + pr_warn("unknown byte order of ELF file %s\n", obj->filename); return err; } - if (ehdr->e_ident[EI_DATA] != host_endianness) { + if (link_byteorder == ELFDATANONE) { + linker->elf_hdr->e_ident[EI_DATA] = obj_byteorder; + linker->swapped_endian = obj_byteorder != host_byteorder; + pr_debug("linker: set %s-endian output byte order\n", + obj_byteorder == ELFDATA2MSB ? "big" : "little"); + } else if (link_byteorder != obj_byteorder) { err = -EOPNOTSUPP; - pr_warn_elf("unsupported byte order of ELF file %s", filename); + pr_warn("byte order mismatch with ELF file %s\n", obj->filename); return err; } + if (ehdr->e_type != ET_REL || ehdr->e_machine != EM_BPF || ehdr->e_ident[EI_CLASS] != ELFCLASS64) { err = -EOPNOTSUPP; - pr_warn_elf("unsupported kind of ELF file %s", filename); + pr_warn_elf("unsupported kind of ELF file %s", obj->filename); return err; } if (elf_getshdrstrndx(obj->elf, &obj->shstrs_sec_idx)) { - err = -errno; - pr_warn_elf("failed to get SHSTRTAB section index for %s", filename); - return err; + pr_warn_elf("failed to get SHSTRTAB section index for %s", obj->filename); + return -EINVAL; } scn = NULL; @@ -603,26 +733,23 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, shdr = elf64_getshdr(scn); if (!shdr) { - err = -errno; pr_warn_elf("failed to get section #%zu header for %s", - sec_idx, filename); - return err; + sec_idx, obj->filename); + return -EINVAL; } sec_name = elf_strptr(obj->elf, obj->shstrs_sec_idx, shdr->sh_name); if (!sec_name) { - err = -errno; pr_warn_elf("failed to get section #%zu name for %s", - sec_idx, filename); - return err; + sec_idx, obj->filename); + return -EINVAL; } data = elf_getdata(scn, 0); if (!data) { - err = -errno; pr_warn_elf("failed to get section #%zu (%s) data from %s", - sec_idx, sec_name, filename); - return err; + sec_idx, sec_name, obj->filename); + return -EINVAL; } sec = add_src_sec(obj, sec_name); @@ -656,7 +783,8 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, obj->btf = btf__new(data->d_buf, shdr->sh_size); err = libbpf_get_error(obj->btf); if (err) { - pr_warn("failed to parse .BTF from %s: %d\n", filename, err); + pr_warn("failed to parse .BTF from %s: %s\n", + obj->filename, errstr(err)); return err; } sec->skipped = true; @@ -666,7 +794,8 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, obj->btf_ext = btf_ext__new(data->d_buf, shdr->sh_size); err = libbpf_get_error(obj->btf_ext); if (err) { - pr_warn("failed to parse .BTF.ext from '%s': %d\n", filename, err); + pr_warn("failed to parse .BTF.ext from '%s': %s\n", + obj->filename, errstr(err)); return err; } sec->skipped = true; @@ -683,7 +812,7 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, break; default: pr_warn("unrecognized section #%zu (%s) in %s\n", - sec_idx, sec_name, filename); + sec_idx, sec_name, obj->filename); err = -EINVAL; return err; } @@ -1109,6 +1238,24 @@ static bool sec_content_is_same(struct dst_sec *dst_sec, struct src_sec *src_sec return true; } +static bool is_exec_sec(struct dst_sec *sec) +{ + if (!sec || sec->ephemeral) + return false; + return (sec->shdr->sh_type == SHT_PROGBITS) && + (sec->shdr->sh_flags & SHF_EXECINSTR); +} + +static void exec_sec_bswap(void *raw_data, int size) +{ + const int insn_cnt = size / sizeof(struct bpf_insn); + struct bpf_insn *insn = raw_data; + int i; + + for (i = 0; i < insn_cnt; i++, insn++) + bpf_insn_bswap(insn); +} + static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src_sec *src) { void *tmp; @@ -1168,6 +1315,10 @@ static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src memset(dst->raw_data + dst->sec_sz, 0, dst_align_sz - dst->sec_sz); /* now copy src data at a properly aligned offset */ memcpy(dst->raw_data + dst_align_sz, src->data->d_buf, src->shdr->sh_size); + + /* convert added bpf insns to native byte-order */ + if (linker->swapped_endian && is_exec_sec(dst)) + exec_sec_bswap(dst->raw_data + dst_align_sz, src->shdr->sh_size); } dst->sec_sz = dst_final_sz; @@ -1224,7 +1375,7 @@ static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj } else { if (!secs_match(dst_sec, src_sec)) { pr_warn("ELF sections %s are incompatible\n", src_sec->sec_name); - return -1; + return -EINVAL; } /* "license" and "version" sections are deduped */ @@ -1413,7 +1564,7 @@ recur: return true; case BTF_KIND_PTR: /* just validate overall shape of the referenced type, so no - * contents comparison for struct/union, and allowd fwd vs + * contents comparison for struct/union, and allowed fwd vs * struct/union */ exact = false; @@ -1874,6 +2025,9 @@ static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj, obj->sym_map[src_sym_idx] = dst_sec->sec_sym_idx; return 0; } + + if (strcmp(src_sec->sec_name, JUMPTABLES_SEC) == 0) + goto add_sym; } if (sym_bind == STB_LOCAL) @@ -1962,7 +2116,7 @@ static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj, /* If existing symbol is a strong resolved symbol, bail out, * because we lost resolution battle have nothing to - * contribute. We already checked abover that there is no + * contribute. We already checked above that there is no * strong-strong conflict. We also already tightened binding * and visibility, so nothing else to contribute at that point. */ @@ -2011,7 +2165,7 @@ add_sym: obj->sym_map[src_sym_idx] = dst_sym_idx; - if (sym_type == STT_SECTION && dst_sym) { + if (sym_type == STT_SECTION && dst_sec) { dst_sec->sec_sym_idx = dst_sym_idx; dst_sym->st_value = 0; } @@ -2071,7 +2225,7 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob } } else if (!secs_match(dst_sec, src_sec)) { pr_warn("sections %s are not compatible\n", src_sec->sec_name); - return -1; + return -EINVAL; } /* shdr->sh_link points to SYMTAB */ @@ -2415,6 +2569,10 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) if (glob_sym && glob_sym->var_idx >= 0) { __s64 sz; + /* FUNCs don't have size, nothing to update */ + if (btf_is_func(t)) + continue; + dst_var = &dst_sec->sec_vars[glob_sym->var_idx]; /* Because underlying BTF type might have * changed, so might its size have changed, so @@ -2628,27 +2786,32 @@ int bpf_linker__finalize(struct bpf_linker *linker) if (!sec->scn) continue; + /* restore sections with bpf insns to target byte-order */ + if (linker->swapped_endian && is_exec_sec(sec)) + exec_sec_bswap(sec->raw_data, sec->sec_sz); + sec->data->d_buf = sec->raw_data; } /* Finalize ELF layout */ if (elf_update(linker->elf, ELF_C_NULL) < 0) { - err = -errno; + err = -EINVAL; pr_warn_elf("failed to finalize ELF layout"); return libbpf_err(err); } /* Write out final ELF contents */ if (elf_update(linker->elf, ELF_C_WRITE) < 0) { - err = -errno; + err = -EINVAL; pr_warn_elf("failed to write ELF contents"); return libbpf_err(err); } elf_end(linker->elf); - close(linker->fd); - linker->elf = NULL; + + if (linker->fd_is_owned) + close(linker->fd); linker->fd = -1; return 0; @@ -2696,6 +2859,7 @@ static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name, static int finalize_btf(struct bpf_linker *linker) { + enum btf_endianness link_endianness; LIBBPF_OPTS(btf_dedup_opts, opts); struct btf *btf = linker->btf; const void *raw_data; @@ -2729,17 +2893,24 @@ static int finalize_btf(struct bpf_linker *linker) err = finalize_btf_ext(linker); if (err) { - pr_warn(".BTF.ext generation failed: %d\n", err); + pr_warn(".BTF.ext generation failed: %s\n", errstr(err)); return err; } opts.btf_ext = linker->btf_ext; err = btf__dedup(linker->btf, &opts); if (err) { - pr_warn("BTF dedup failed: %d\n", err); + pr_warn("BTF dedup failed: %s\n", errstr(err)); return err; } + /* Set .BTF and .BTF.ext output byte order */ + link_endianness = linker->elf_hdr->e_ident[EI_DATA] == ELFDATA2MSB ? + BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN; + btf__set_endianness(linker->btf, link_endianness); + if (linker->btf_ext) + btf_ext__set_endianness(linker->btf_ext, link_endianness); + /* Emit .BTF section */ raw_data = btf__raw_data(linker->btf, &raw_sz); if (!raw_data) @@ -2747,7 +2918,7 @@ static int finalize_btf(struct bpf_linker *linker) err = emit_elf_data_sec(linker, BTF_ELF_SEC, 8, raw_data, raw_sz); if (err) { - pr_warn("failed to write out .BTF ELF section: %d\n", err); + pr_warn("failed to write out .BTF ELF section: %s\n", errstr(err)); return err; } @@ -2759,7 +2930,7 @@ static int finalize_btf(struct bpf_linker *linker) err = emit_elf_data_sec(linker, BTF_EXT_ELF_SEC, 8, raw_data, raw_sz); if (err) { - pr_warn("failed to write out .BTF.ext ELF section: %d\n", err); + pr_warn("failed to write out .BTF.ext ELF section: %s\n", errstr(err)); return err; } } @@ -2935,7 +3106,7 @@ static int finalize_btf_ext(struct bpf_linker *linker) err = libbpf_get_error(linker->btf_ext); if (err) { linker->btf_ext = NULL; - pr_warn("failed to parse final .BTF.ext data: %d\n", err); + pr_warn("failed to parse final .BTF.ext data: %s\n", errstr(err)); goto out; } diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 68a2def17175..c997e69d507f 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -529,9 +529,9 @@ int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id) } -typedef int (*qdisc_config_t)(struct libbpf_nla_req *req); +typedef int (*qdisc_config_t)(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook); -static int clsact_config(struct libbpf_nla_req *req) +static int clsact_config(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook) { req->tc.tcm_parent = TC_H_CLSACT; req->tc.tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0); @@ -539,6 +539,16 @@ static int clsact_config(struct libbpf_nla_req *req) return nlattr_add(req, TCA_KIND, "clsact", sizeof("clsact")); } +static int qdisc_config(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook) +{ + const char *qdisc = OPTS_GET(hook, qdisc, NULL); + + req->tc.tcm_parent = OPTS_GET(hook, parent, TC_H_ROOT); + req->tc.tcm_handle = OPTS_GET(hook, handle, 0); + + return nlattr_add(req, TCA_KIND, qdisc, strlen(qdisc) + 1); +} + static int attach_point_to_config(struct bpf_tc_hook *hook, qdisc_config_t *config) { @@ -552,6 +562,9 @@ static int attach_point_to_config(struct bpf_tc_hook *hook, return 0; case BPF_TC_CUSTOM: return -EOPNOTSUPP; + case BPF_TC_QDISC: + *config = &qdisc_config; + return 0; default: return -EINVAL; } @@ -596,7 +609,7 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags) req.tc.tcm_family = AF_UNSPEC; req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0); - ret = config(&req); + ret = config(&req, hook); if (ret < 0) return ret; @@ -639,6 +652,7 @@ int bpf_tc_hook_destroy(struct bpf_tc_hook *hook) case BPF_TC_INGRESS: case BPF_TC_EGRESS: return libbpf_err(__bpf_tc_detach(hook, NULL, true)); + case BPF_TC_QDISC: case BPF_TC_INGRESS | BPF_TC_EGRESS: return libbpf_err(tc_qdisc_delete(hook)); case BPF_TC_CUSTOM: diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index 975e265eab3b..06663f9ea581 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -63,16 +63,16 @@ static int validate_nla(struct nlattr *nla, int maxtype, minlen = nla_attr_minlen[pt->type]; if (libbpf_nla_len(nla) < minlen) - return -1; + return -EINVAL; if (pt->maxlen && libbpf_nla_len(nla) > pt->maxlen) - return -1; + return -EINVAL; if (pt->type == LIBBPF_NLA_STRING) { char *data = libbpf_nla_data(nla); if (data[libbpf_nla_len(nla) - 1] != '\0') - return -1; + return -EINVAL; } return 0; @@ -118,19 +118,18 @@ int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, if (policy) { err = validate_nla(nla, maxtype, policy); if (err < 0) - goto errout; + return err; } - if (tb[type]) + if (tb[type]) { pr_warn("Attribute of type %#x found multiple times in message, " "previous attribute is being ignored.\n", type); + } tb[type] = nla; } - err = 0; -errout: - return err; + return 0; } /** diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index 63a4d5ad12d1..6eea5edba58a 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -64,7 +64,6 @@ enum libbpf_print_level { #include "libbpf.h" #include "bpf.h" #include "btf.h" -#include "str_error.h" #include "libbpf_internal.h" #endif @@ -683,7 +682,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, { const struct bpf_core_accessor *acc; const struct btf_type *t; - __u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id; + __u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id, elem_id; const struct btf_member *m; const struct btf_type *mt; bool bitfield; @@ -706,8 +705,14 @@ static int bpf_core_calc_field_relo(const char *prog_name, if (!acc->name) { if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) { *val = spec->bit_offset / 8; - /* remember field size for load/store mem size */ - sz = btf__resolve_size(spec->btf, acc->type_id); + /* remember field size for load/store mem size; + * note, for arrays we care about individual element + * sizes, not the overall array size + */ + t = skip_mods_and_typedefs(spec->btf, acc->type_id, &elem_id); + while (btf_is_array(t)) + t = skip_mods_and_typedefs(spec->btf, btf_array(t)->type, &elem_id); + sz = btf__resolve_size(spec->btf, elem_id); if (sz < 0) return -EINVAL; *field_sz = sz; @@ -767,7 +772,17 @@ static int bpf_core_calc_field_relo(const char *prog_name, case BPF_CORE_FIELD_BYTE_OFFSET: *val = byte_off; if (!bitfield) { - *field_sz = byte_sz; + /* remember field size for load/store mem size; + * note, for arrays we care about individual element + * sizes, not the overall array size + */ + t = skip_mods_and_typedefs(spec->btf, field_type_id, &elem_id); + while (btf_is_array(t)) + t = skip_mods_and_typedefs(spec->btf, btf_array(t)->type, &elem_id); + sz = btf__resolve_size(spec->btf, elem_id); + if (sz < 0) + return -EINVAL; + *field_sz = sz; *type_id = field_type_id; } break; @@ -1339,7 +1354,7 @@ int bpf_core_calc_relo_insn(const char *prog_name, cands->cands[i].id, cand_spec); if (err < 0) { bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec); - pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n ", + pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n", prog_name, relo_idx, i, spec_buf, err); return err; } diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index bfd8dac4c0cc..00ec4837a06d 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -88,8 +88,8 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, err = bpf_map_get_info_by_fd(map_fd, &info, &len); if (err) { err = -errno; - pr_warn("ringbuf: failed to get map info for fd=%d: %d\n", - map_fd, err); + pr_warn("ringbuf: failed to get map info for fd=%d: %s\n", + map_fd, errstr(err)); return libbpf_err(err); } @@ -123,8 +123,8 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0); if (tmp == MAP_FAILED) { err = -errno; - pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n", - map_fd, err); + pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %s\n", + map_fd, errstr(err)); goto err_out; } r->consumer_pos = tmp; @@ -142,8 +142,8 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ, MAP_SHARED, map_fd, rb->page_size); if (tmp == MAP_FAILED) { err = -errno; - pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n", - map_fd, err); + pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %s\n", + map_fd, errstr(err)); goto err_out; } r->producer_pos = tmp; @@ -156,8 +156,8 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, e->data.fd = rb->ring_cnt; if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) { err = -errno; - pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n", - map_fd, err); + pr_warn("ringbuf: failed to epoll add map fd=%d: %s\n", + map_fd, errstr(err)); goto err_out; } @@ -205,7 +205,7 @@ ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx, rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); if (rb->epoll_fd < 0) { err = -errno; - pr_warn("ringbuf: failed to create epoll instance: %d\n", err); + pr_warn("ringbuf: failed to create epoll instance: %s\n", errstr(err)); goto err_out; } @@ -458,7 +458,8 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) err = bpf_map_get_info_by_fd(map_fd, &info, &len); if (err) { err = -errno; - pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err); + pr_warn("user ringbuf: failed to get map info for fd=%d: %s\n", + map_fd, errstr(err)); return err; } @@ -474,8 +475,8 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) tmp = mmap(NULL, rb->page_size, PROT_READ, MAP_SHARED, map_fd, 0); if (tmp == MAP_FAILED) { err = -errno; - pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n", - map_fd, err); + pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %s\n", + map_fd, errstr(err)); return err; } rb->consumer_pos = tmp; @@ -494,8 +495,8 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) map_fd, rb->page_size); if (tmp == MAP_FAILED) { err = -errno; - pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n", - map_fd, err); + pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %s\n", + map_fd, errstr(err)); return err; } @@ -506,7 +507,7 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) rb_epoll->events = EPOLLOUT; if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, rb_epoll) < 0) { err = -errno; - pr_warn("user ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err); + pr_warn("user ringbuf: failed to epoll add map fd=%d: %s\n", map_fd, errstr(err)); return err; } @@ -531,7 +532,7 @@ user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts) rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); if (rb->epoll_fd < 0) { err = -errno; - pr_warn("user ringbuf: failed to create epoll instance: %d\n", err); + pr_warn("user ringbuf: failed to create epoll instance: %s\n", errstr(err)); goto err_out; } diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 1e82ab06c3eb..6a8f5c7a02eb 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -13,10 +13,15 @@ #include <unistd.h> #include <sys/syscall.h> #include <sys/mman.h> +#include <linux/keyctl.h> #include <stdlib.h> #include "bpf.h" #endif +#ifndef SHA256_DIGEST_LENGTH +#define SHA256_DIGEST_LENGTH 32 +#endif + #ifndef __NR_bpf # if defined(__mips__) && defined(_ABIO32) # define __NR_bpf 4355 @@ -64,6 +69,11 @@ struct bpf_load_and_run_opts { __u32 data_sz; __u32 insns_sz; const char *errstr; + void *signature; + __u32 signature_sz; + __s32 keyring_id; + void *excl_prog_hash; + __u32 excl_prog_hash_sz; }; long kern_sys_bpf(__u32 cmd, void *attr, __u32 attr_size); @@ -107,7 +117,7 @@ static inline void skel_free(const void *p) * The loader program will perform probe_read_kernel() from maps.rodata.initial_value. * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree - * is not nessary. + * is not necessary. * * For user space: * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly. @@ -220,14 +230,19 @@ static inline int skel_map_create(enum bpf_map_type map_type, const char *map_name, __u32 key_size, __u32 value_size, - __u32 max_entries) + __u32 max_entries, + const void *excl_prog_hash, + __u32 excl_prog_hash_sz) { - const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + const size_t attr_sz = offsetofend(union bpf_attr, excl_prog_hash_size); union bpf_attr attr; memset(&attr, 0, attr_sz); attr.map_type = map_type; + attr.excl_prog_hash = (unsigned long) excl_prog_hash; + attr.excl_prog_hash_size = excl_prog_hash_sz; + strncpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.key_size = key_size; attr.value_size = value_size; @@ -300,6 +315,35 @@ static inline int skel_link_create(int prog_fd, int target_fd, return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz); } +static inline int skel_obj_get_info_by_fd(int fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, info); + __u8 sha[SHA256_DIGEST_LENGTH]; + struct bpf_map_info info; + __u32 info_len = sizeof(info); + union bpf_attr attr; + + memset(&info, 0, sizeof(info)); + info.hash = (long) &sha; + info.hash_size = SHA256_DIGEST_LENGTH; + + memset(&attr, 0, attr_sz); + attr.info.bpf_fd = fd; + attr.info.info = (long) &info; + attr.info.info_len = info_len; + return skel_sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, attr_sz); +} + +static inline int skel_map_freeze(int fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, map_fd); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + + return skel_sys_bpf(BPF_MAP_FREEZE, &attr, attr_sz); +} #ifdef __KERNEL__ #define set_err #else @@ -308,12 +352,13 @@ static inline int skel_link_create(int prog_fd, int target_fd, static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) { - const size_t prog_load_attr_sz = offsetofend(union bpf_attr, fd_array); + const size_t prog_load_attr_sz = offsetofend(union bpf_attr, keyring_id); const size_t test_run_attr_sz = offsetofend(union bpf_attr, test); int map_fd = -1, prog_fd = -1, key = 0, err; union bpf_attr attr; - err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1); + err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1, + opts->excl_prog_hash, opts->excl_prog_hash_sz); if (map_fd < 0) { opts->errstr = "failed to create loader map"; set_err; @@ -327,11 +372,34 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) goto out; } +#ifndef __KERNEL__ + err = skel_map_freeze(map_fd); + if (err < 0) { + opts->errstr = "failed to freeze map"; + set_err; + goto out; + } + err = skel_obj_get_info_by_fd(map_fd); + if (err < 0) { + opts->errstr = "failed to fetch obj info"; + set_err; + goto out; + } +#endif + memset(&attr, 0, prog_load_attr_sz); attr.prog_type = BPF_PROG_TYPE_SYSCALL; attr.insns = (long) opts->insns; attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); attr.license = (long) "Dual BSD/GPL"; +#ifndef __KERNEL__ + attr.signature = (long) opts->signature; + attr.signature_size = opts->signature_sz; +#else + if (opts->signature || opts->signature_sz) + pr_warn("signatures are not supported from bpf_preload\n"); +#endif + attr.keyring_id = opts->keyring_id; memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog")); attr.fd_array = (long) &map_fd; attr.log_level = opts->ctx->log_level; @@ -351,10 +419,11 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) attr.test.ctx_size_in = opts->ctx->sz; err = skel_sys_bpf(BPF_PROG_RUN, &attr, test_run_attr_sz); if (err < 0 || (int)attr.test.retval < 0) { - opts->errstr = "failed to execute loader prog"; if (err < 0) { + opts->errstr = "failed to execute loader prog"; set_err; } else { + opts->errstr = "error returned by loader prog"; err = (int)attr.test.retval; #ifndef __KERNEL__ errno = -err; diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c deleted file mode 100644 index 5e6a1e27ddf9..000000000000 --- a/tools/lib/bpf/str_error.c +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) -#undef _GNU_SOURCE -#include <string.h> -#include <stdio.h> -#include <errno.h> -#include "str_error.h" - -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - -/* - * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl - * libc, while checking strerror_r() return to avoid having to check this in - * all places calling it. - */ -char *libbpf_strerror_r(int err, char *dst, int len) -{ - int ret = strerror_r(err < 0 ? -err : err, dst, len); - /* on glibc <2.13, ret == -1 and errno is set, if strerror_r() can't - * handle the error, on glibc >=2.13 *positive* (errno-like) error - * code is returned directly - */ - if (ret == -1) - ret = errno; - if (ret) { - if (ret == EINVAL) - /* strerror_r() doesn't recognize this specific error */ - snprintf(dst, len, "unknown error (%d)", err < 0 ? err : -err); - else - snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret); - } - return dst; -} diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h deleted file mode 100644 index 626d7ffb03d6..000000000000 --- a/tools/lib/bpf/str_error.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#ifndef __LIBBPF_STR_ERROR_H -#define __LIBBPF_STR_ERROR_H - -#define STRERR_BUFSIZE 128 - -char *libbpf_strerror_r(int err, char *dst, int len); - -#endif /* __LIBBPF_STR_ERROR_H */ diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index 76359bcdc94a..43deb05a5197 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -34,13 +34,32 @@ enum __bpf_usdt_arg_type { BPF_USDT_ARG_CONST, BPF_USDT_ARG_REG, BPF_USDT_ARG_REG_DEREF, + BPF_USDT_ARG_SIB, }; +/* + * This struct layout is designed specifically to be backwards/forward + * compatible between libbpf versions for ARG_CONST, ARG_REG, and + * ARG_REG_DEREF modes. ARG_SIB requires libbpf v1.7+. + */ struct __bpf_usdt_arg_spec { /* u64 scalar interpreted depending on arg_type, see below */ __u64 val_off; - /* arg location case, see bpf_udst_arg() for details */ - enum __bpf_usdt_arg_type arg_type; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + /* arg location case, see bpf_usdt_arg() for details */ + enum __bpf_usdt_arg_type arg_type: 8; + /* index register offset within struct pt_regs */ + __u16 idx_reg_off: 12; + /* scale factor for index register (1, 2, 4, or 8) */ + __u16 scale_bitshift: 4; + /* reserved for future use, keeps reg_off offset stable */ + __u8 __reserved: 8; +#else + __u8 __reserved: 8; + __u16 idx_reg_off: 12; + __u16 scale_bitshift: 4; + enum __bpf_usdt_arg_type arg_type: 8; +#endif /* offset of referenced register within struct pt_regs */ short reg_off; /* whether arg should be interpreted as signed value */ @@ -108,6 +127,38 @@ int bpf_usdt_arg_cnt(struct pt_regs *ctx) return spec->arg_cnt; } +/* Returns the size in bytes of the #*arg_num* (zero-indexed) USDT argument. + * Returns negative error if argument is not found or arg_num is invalid. + */ +static __always_inline +int bpf_usdt_arg_size(struct pt_regs *ctx, __u64 arg_num) +{ + struct __bpf_usdt_arg_spec *arg_spec; + struct __bpf_usdt_spec *spec; + int spec_id; + + spec_id = __bpf_usdt_spec_id(ctx); + if (spec_id < 0) + return -ESRCH; + + spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); + if (!spec) + return -ESRCH; + + if (arg_num >= BPF_USDT_MAX_ARG_CNT) + return -ENOENT; + barrier_var(arg_num); + if (arg_num >= spec->arg_cnt) + return -ENOENT; + + arg_spec = &spec->args[arg_num]; + + /* arg_spec->arg_bitshift = 64 - arg_sz * 8 + * so: arg_sz = (64 - arg_spec->arg_bitshift) / 8 + */ + return (unsigned int)(64 - arg_spec->arg_bitshift) / 8; +} + /* Fetch USDT argument #*arg_num* (zero-indexed) and put its value into *res. * Returns 0 on success; negative error, otherwise. * On error *res is guaranteed to be set to zero. @@ -117,7 +168,7 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) { struct __bpf_usdt_spec *spec; struct __bpf_usdt_arg_spec *arg_spec; - unsigned long val; + unsigned long val, idx; int err, spec_id; *res = 0; @@ -172,6 +223,27 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) val >>= arg_spec->arg_bitshift; #endif break; + case BPF_USDT_ARG_SIB: + /* Arg is in memory addressed by SIB (Scale-Index-Base) mode + * (e.g., "-1@-96(%rbp,%rax,8)" in USDT arg spec). We first + * fetch the base register contents and the index register + * contents from pt_regs. Then we calculate the final address + * as base + (index * scale) + offset, and do a user-space + * probe read to fetch the argument value. + */ + err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off); + if (err) + return err; + err = bpf_probe_read_kernel(&idx, sizeof(idx), (void *)ctx + arg_spec->idx_reg_off); + if (err) + return err; + err = bpf_probe_read_user(&val, sizeof(val), (void *)(val + (idx << arg_spec->scale_bitshift) + arg_spec->val_off)); + if (err) + return err; +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + val >>= arg_spec->arg_bitshift; +#endif + break; default: return -EINVAL; } diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index 93794f01bb67..d1524f6f54ae 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -58,7 +58,7 @@ * * STAP_PROBE3(my_usdt_provider, my_usdt_probe_name, 123, x, &y); * - * USDT is identified by it's <provider-name>:<probe-name> pair of names. Each + * USDT is identified by its <provider-name>:<probe-name> pair of names. Each * individual USDT has a fixed number of arguments (3 in the above example) * and specifies values of each argument as if it was a function call. * @@ -80,7 +80,7 @@ * NOP instruction that kernel can replace with an interrupt instruction to * trigger instrumentation code (BPF program for all that we care about). * - * Semaphore above is and optional feature. It records an address of a 2-byte + * Semaphore above is an optional feature. It records an address of a 2-byte * refcount variable (normally in '.probes' ELF section) used for signaling if * there is anything that is attached to USDT. This is useful for user * applications if, for example, they need to prepare some arguments that are @@ -120,7 +120,7 @@ * a uprobe BPF program (which for kernel, at least currently, is just a kprobe * program, so BPF_PROG_TYPE_KPROBE program type). With the only difference * that uprobe is usually attached at the function entry, while USDT will - * normally will be somewhere inside the function. But it should always be + * normally be somewhere inside the function. But it should always be * pointing to NOP instruction, which makes such uprobes the fastest uprobe * kind. * @@ -150,7 +150,7 @@ * libbpf sets to spec ID during attach time, or, if kernel is too old to * support BPF cookie, through IP-to-spec-ID map that libbpf maintains in such * case. The latter means that some modes of operation can't be supported - * without BPF cookie. Such mode is attaching to shared library "generically", + * without BPF cookie. Such a mode is attaching to shared library "generically", * without specifying target process. In such case, it's impossible to * calculate absolute IP addresses for IP-to-spec-ID map, and thus such mode * is not supported without BPF cookie support. @@ -184,7 +184,7 @@ * as even if USDT spec string is the same, USDT cookie value can be * different. It was deemed excessive to try to deduplicate across independent * USDT attachments by taking into account USDT spec string *and* USDT cookie - * value, which would complicated spec ID accounting significantly for little + * value, which would complicate spec ID accounting significantly for little * gain. */ @@ -199,12 +199,23 @@ enum usdt_arg_type { USDT_ARG_CONST, USDT_ARG_REG, USDT_ARG_REG_DEREF, + USDT_ARG_SIB, }; /* should match exactly struct __bpf_usdt_arg_spec from usdt.bpf.h */ struct usdt_arg_spec { __u64 val_off; - enum usdt_arg_type arg_type; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + enum usdt_arg_type arg_type: 8; + __u16 idx_reg_off: 12; + __u16 scale_bitshift: 4; + __u8 __reserved: 8; /* keep reg_off offset stable */ +#else + __u8 __reserved: 8; /* keep reg_off offset stable */ + __u16 idx_reg_off: 12; + __u16 scale_bitshift: 4; + enum usdt_arg_type arg_type: 8; +#endif short reg_off; bool arg_signed; char arg_bitshift; @@ -465,8 +476,8 @@ static int parse_vma_segs(int pid, const char *lib_path, struct elf_seg **segs, goto proceed; if (!realpath(lib_path, path)) { - pr_warn("usdt: failed to get absolute path of '%s' (err %d), using path as is...\n", - lib_path, -errno); + pr_warn("usdt: failed to get absolute path of '%s' (err %s), using path as is...\n", + lib_path, errstr(-errno)); libbpf_strlcpy(path, lib_path, sizeof(path)); } @@ -475,8 +486,8 @@ proceed: f = fopen(line, "re"); if (!f) { err = -errno; - pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n", - line, lib_path, err); + pr_warn("usdt: failed to open '%s' to get base addr of '%s': %s\n", + line, lib_path, errstr(err)); return err; } @@ -569,9 +580,8 @@ static struct elf_seg *find_vma_seg(struct elf_seg *segs, size_t seg_cnt, long o return NULL; } -static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, - const char *data, size_t name_off, size_t desc_off, - struct usdt_note *usdt_note); +static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off, + size_t desc_off, struct usdt_note *usdt_note); static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie); @@ -606,7 +616,8 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * err = parse_elf_segs(elf, path, &segs, &seg_cnt); if (err) { - pr_warn("usdt: failed to process ELF program segments for '%s': %d\n", path, err); + pr_warn("usdt: failed to process ELF program segments for '%s': %s\n", + path, errstr(err)); goto err_out; } @@ -624,7 +635,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * struct elf_seg *seg = NULL; void *tmp; - err = parse_usdt_note(elf, path, &nhdr, data->d_buf, name_off, desc_off, ¬e); + err = parse_usdt_note(&nhdr, data->d_buf, name_off, desc_off, ¬e); if (err) goto err_out; @@ -659,7 +670,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * * [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation */ usdt_abs_ip = note.loc_addr; - if (base_addr) + if (base_addr && note.base_addr) usdt_abs_ip += base_addr - note.base_addr; /* When attaching uprobes (which is what USDTs basically are) @@ -708,8 +719,8 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * if (vma_seg_cnt == 0) { err = parse_vma_segs(pid, path, &vma_segs, &vma_seg_cnt); if (err) { - pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %d\n", - pid, path, err); + pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %s\n", + pid, path, errstr(err)); goto err_out; } } @@ -1047,8 +1058,8 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct if (is_new && bpf_map_update_elem(spec_map_fd, &spec_id, &target->spec, BPF_ANY)) { err = -errno; - pr_warn("usdt: failed to set USDT spec #%d for '%s:%s' in '%s': %d\n", - spec_id, usdt_provider, usdt_name, path, err); + pr_warn("usdt: failed to set USDT spec #%d for '%s:%s' in '%s': %s\n", + spec_id, usdt_provider, usdt_name, path, errstr(err)); goto err_out; } if (!man->has_bpf_cookie && @@ -1058,9 +1069,9 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct pr_warn("usdt: IP collision detected for spec #%d for '%s:%s' in '%s'\n", spec_id, usdt_provider, usdt_name, path); } else { - pr_warn("usdt: failed to map IP 0x%lx to spec #%d for '%s:%s' in '%s': %d\n", + pr_warn("usdt: failed to map IP 0x%lx to spec #%d for '%s:%s' in '%s': %s\n", target->abs_ip, spec_id, usdt_provider, usdt_name, - path, err); + path, errstr(err)); } goto err_out; } @@ -1076,8 +1087,8 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct target->rel_ip, &opts); err = libbpf_get_error(uprobe_link); if (err) { - pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n", - i, usdt_provider, usdt_name, path, err); + pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %s\n", + i, usdt_provider, usdt_name, path, errstr(err)); goto err_out; } @@ -1099,8 +1110,8 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct NULL, &opts_multi); if (!link->multi_link) { err = -errno; - pr_warn("usdt: failed to attach uprobe multi for '%s:%s' in '%s': %d\n", - usdt_provider, usdt_name, path, err); + pr_warn("usdt: failed to attach uprobe multi for '%s:%s' in '%s': %s\n", + usdt_provider, usdt_name, path, errstr(err)); goto err_out; } @@ -1130,8 +1141,7 @@ err_out: /* Parse out USDT ELF note from '.note.stapsdt' section. * Logic inspired by perf's code. */ -static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, - const char *data, size_t name_off, size_t desc_off, +static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off, size_t desc_off, struct usdt_note *note) { const char *provider, *name, *args; @@ -1281,11 +1291,51 @@ static int calc_pt_regs_off(const char *reg_name) static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz) { - char reg_name[16]; - int len, reg_off; - long off; + char reg_name[16] = {0}, idx_reg_name[16] = {0}; + int len, reg_off, idx_reg_off, scale = 1; + long off = 0; + + if (sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^,] , %d ) %n", + arg_sz, &off, reg_name, idx_reg_name, &scale, &len) == 5 || + sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^,] , %d ) %n", + arg_sz, reg_name, idx_reg_name, &scale, &len) == 4 || + sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^)] ) %n", + arg_sz, &off, reg_name, idx_reg_name, &len) == 4 || + sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^)] ) %n", + arg_sz, reg_name, idx_reg_name, &len) == 3 + ) { + /* + * Scale Index Base case: + * 1@-96(%rbp,%rax,8) + * 1@(%rbp,%rax,8) + * 1@-96(%rbp,%rax) + * 1@(%rbp,%rax) + */ + arg->arg_type = USDT_ARG_SIB; + arg->val_off = off; - if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", arg_sz, &off, reg_name, &len) == 3) { + reg_off = calc_pt_regs_off(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + + idx_reg_off = calc_pt_regs_off(idx_reg_name); + if (idx_reg_off < 0) + return idx_reg_off; + arg->idx_reg_off = idx_reg_off; + + /* validate scale factor and set fields directly */ + switch (scale) { + case 1: arg->scale_bitshift = 0; break; + case 2: arg->scale_bitshift = 1; break; + case 4: arg->scale_bitshift = 2; break; + case 8: arg->scale_bitshift = 3; break; + default: + pr_warn("usdt: invalid SIB scale %d, expected 1, 2, 4, 8\n", scale); + return -EINVAL; + } + } else if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", + arg_sz, &off, reg_name, &len) == 3) { /* Memory dereference case, e.g., -4@-20(%rbp) */ arg->arg_type = USDT_ARG_REG_DEREF; arg->val_off = off; @@ -1304,6 +1354,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec } else if (sscanf(arg_str, " %d @ %%%15s %n", arg_sz, reg_name, &len) == 2) { /* Register read case, e.g., -4@%eax */ arg->arg_type = USDT_ARG_REG; + /* register read has no memory offset */ arg->val_off = 0; reg_off = calc_pt_regs_off(reg_name); @@ -1325,8 +1376,6 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec #elif defined(__s390x__) -/* Do not support __s390__ for now, since user_pt_regs is broken with -m31. */ - static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz) { unsigned int reg; diff --git a/tools/lib/bpf/zip.c b/tools/lib/bpf/zip.c index 3f26d629b2b4..88c376a8348d 100644 --- a/tools/lib/bpf/zip.c +++ b/tools/lib/bpf/zip.c @@ -223,7 +223,7 @@ struct zip_archive *zip_archive_open(const char *path) if (!archive) { munmap(data, size); return ERR_PTR(-ENOMEM); - }; + } archive->data = data; archive->size = size; |