diff options
Diffstat (limited to 'tools/lib')
28 files changed, 1679 insertions, 407 deletions
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index f947b61b2107..b8b37fe76006 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -131,7 +131,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ sed 's/\[.*\]//' | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) @@ -194,7 +194,7 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ sed 's/\[.*\]//' | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}'| \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ diff -u $(OUTPUT)libbpf_global_syms.tmp \ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 550b4cbb6c99..cf27251adb92 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -29,6 +29,7 @@ #include <errno.h> #include <linux/bpf.h> #include <linux/filter.h> +#include <linux/kernel.h> #include <limits.h> #include <sys/resource.h> #include "bpf.h" @@ -111,7 +112,7 @@ int probe_memcg_account(void) BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns), BPF_EXIT_INSN(), }; - size_t insn_cnt = sizeof(insns) / sizeof(insns[0]); + size_t insn_cnt = ARRAY_SIZE(insns); union bpf_attr attr; int prog_fd; @@ -754,10 +755,10 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, .flags = flags, ); - return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts); + return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts); } -int bpf_prog_attach_xattr(int prog_fd, int target_fd, +int bpf_prog_attach_opts(int prog_fd, int target_fd, enum bpf_attach_type type, const struct bpf_prog_attach_opts *opts) { @@ -778,6 +779,11 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd, return libbpf_err_errno(ret); } +__attribute__((alias("bpf_prog_attach_opts"))) +int bpf_prog_attach_xattr(int prog_fd, int target_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); + int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { union bpf_attr attr; @@ -848,6 +854,15 @@ int bpf_link_create(int prog_fd, int target_fd, if (!OPTS_ZEROED(opts, perf_event)) return libbpf_err(-EINVAL); break; + case BPF_TRACE_KPROBE_MULTI: + attr.link_create.kprobe_multi.flags = OPTS_GET(opts, kprobe_multi.flags, 0); + attr.link_create.kprobe_multi.cnt = OPTS_GET(opts, kprobe_multi.cnt, 0); + attr.link_create.kprobe_multi.syms = ptr_to_u64(OPTS_GET(opts, kprobe_multi.syms, 0)); + attr.link_create.kprobe_multi.addrs = ptr_to_u64(OPTS_GET(opts, kprobe_multi.addrs, 0)); + attr.link_create.kprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, kprobe_multi.cookies, 0)); + if (!OPTS_ZEROED(opts, kprobe_multi)) + return libbpf_err(-EINVAL); + break; default: if (!OPTS_ZEROED(opts, flags)) return libbpf_err(-EINVAL); @@ -989,6 +1004,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) memset(&attr, 0, sizeof(attr)); attr.test.prog_fd = prog_fd; + attr.test.batch_size = OPTS_GET(opts, batch_size, 0); attr.test.cpu = OPTS_GET(opts, cpu, 0); attr.test.flags = OPTS_GET(opts, flags, 0); attr.test.repeat = OPTS_GET(opts, repeat, 0); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 14e0d97ad2cf..f4b4afb6d4ba 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -391,6 +391,10 @@ struct bpf_prog_attach_opts { LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); +LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_prog_attach_opts() instead") LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd, enum bpf_attach_type type, const struct bpf_prog_attach_opts *opts); @@ -409,10 +413,17 @@ struct bpf_link_create_opts { struct { __u64 bpf_cookie; } perf_event; + struct { + __u32 flags; + __u32 cnt; + const char **syms; + const unsigned long *addrs; + const __u64 *cookies; + } kprobe_multi; }; size_t :0; }; -#define bpf_link_create_opts__last_field perf_event +#define bpf_link_create_opts__last_field kprobe_multi.cookies LIBBPF_API int bpf_link_create(int prog_fd, int target_fd, enum bpf_attach_type attach_type, @@ -449,12 +460,14 @@ struct bpf_prog_test_run_attr { * out: length of cxt_out */ }; +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead") LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr); /* * bpf_prog_test_run does not check that data_out is large enough. Consider - * using bpf_prog_test_run_xattr instead. + * using bpf_prog_test_run_opts instead. */ +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_test_run_opts() instead") LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, void *data_out, __u32 *size_out, __u32 *retval, __u32 *duration); @@ -506,8 +519,9 @@ struct bpf_test_run_opts { __u32 duration; /* out: average per repetition in ns */ __u32 flags; __u32 cpu; + __u32 batch_size; }; -#define bpf_test_run_opts__last_field cpu +#define bpf_test_run_opts__last_field batch_size LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 963b1060d944..44df982d2a5c 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -133,7 +133,7 @@ struct bpf_map_def { unsigned int value_size; unsigned int max_entries; unsigned int map_flags; -}; +} __attribute__((deprecated("use BTF-defined maps in .maps section"))); enum libbpf_pin_type { LIBBPF_PIN_NONE, diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 90f56b0f585f..e3a8c947e89f 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -76,6 +76,9 @@ #define __PT_RC_REG ax #define __PT_SP_REG sp #define __PT_IP_REG ip +/* syscall uses r10 for PARM4 */ +#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) #else @@ -105,6 +108,9 @@ #define __PT_RC_REG rax #define __PT_SP_REG rsp #define __PT_IP_REG rip +/* syscall uses r10 for PARM4 */ +#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) #endif /* __i386__ */ @@ -112,6 +118,10 @@ #elif defined(bpf_target_s390) +struct pt_regs___s390 { + unsigned long orig_gpr2; +}; + /* s390 provides user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const user_pt_regs *)(x)) #define __PT_PARM1_REG gprs[2] @@ -124,6 +134,8 @@ #define __PT_RC_REG gprs[2] #define __PT_SP_REG gprs[15] #define __PT_IP_REG psw.addr +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; }) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2) #elif defined(bpf_target_arm) @@ -140,6 +152,10 @@ #elif defined(bpf_target_arm64) +struct pt_regs___arm64 { + unsigned long orig_x0; +}; + /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) #define __PT_PARM1_REG regs[0] @@ -152,6 +168,8 @@ #define __PT_RC_REG regs[0] #define __PT_SP_REG sp #define __PT_IP_REG pc +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; }) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0) #elif defined(bpf_target_mips) @@ -178,6 +196,8 @@ #define __PT_RC_REG gpr[3] #define __PT_SP_REG sp #define __PT_IP_REG nip +/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx #elif defined(bpf_target_sparc) @@ -206,10 +226,12 @@ #define __PT_PARM4_REG a3 #define __PT_PARM5_REG a4 #define __PT_RET_REG ra -#define __PT_FP_REG fp +#define __PT_FP_REG s0 #define __PT_RC_REG a5 #define __PT_SP_REG sp -#define __PT_IP_REG epc +#define __PT_IP_REG pc +/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx #endif @@ -263,6 +285,26 @@ struct pt_regs; #endif +#ifndef PT_REGS_PARM1_SYSCALL +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x) +#endif +#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x) +#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x) +#ifndef PT_REGS_PARM4_SYSCALL +#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x) +#endif +#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x) + +#ifndef PT_REGS_PARM1_CORE_SYSCALL +#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x) +#endif +#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x) +#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x) +#ifndef PT_REGS_PARM4_CORE_SYSCALL +#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x) +#endif +#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x) + #else /* defined(bpf_target_defined) */ #define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) @@ -290,8 +332,30 @@ struct pt_regs; #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + #endif /* defined(bpf_target_defined) */ +/* + * When invoked from a syscall handler kprobe, returns a pointer to a + * struct pt_regs containing syscall arguments and suitable for passing to + * PT_REGS_PARMn_SYSCALL() and PT_REGS_PARMn_CORE_SYSCALL(). + */ +#ifndef PT_REGS_SYSCALL_REGS +/* By default, assume that the arch selects ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ((struct pt_regs *)PT_REGS_PARM1(ctx)) +#endif + #ifndef ___bpf_concat #define ___bpf_concat(a, b) a ## b #endif @@ -406,4 +470,39 @@ typeof(name(0)) name(struct pt_regs *ctx) \ } \ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) +#define ___bpf_syscall_args0() ctx +#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs) +#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs) +#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs) +#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs) +#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs) +#define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args) + +/* + * BPF_KPROBE_SYSCALL is a variant of BPF_KPROBE, which is intended for + * tracing syscall functions, like __x64_sys_close. It hides the underlying + * platform-specific low-level way of getting syscall input arguments from + * struct pt_regs, and provides a familiar typed and named function arguments + * syntax and semantics of accessing syscall input parameters. + * + * Original struct pt_regs* context is preserved as 'ctx' argument. This might + * be necessary when using BPF helpers like bpf_perf_event_output(). + * + * This macro relies on BPF CO-RE support. + */ +#define BPF_KPROBE_SYSCALL(name, args...) \ +name(struct pt_regs *ctx); \ +static __attribute__((always_inline)) typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + struct pt_regs *regs = PT_REGS_SYSCALL_REGS(ctx); \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_syscall_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __attribute__((always_inline)) typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args) + #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 9aa19c89f758..1383e26c5d1f 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1620,20 +1620,37 @@ static int btf_commit_type(struct btf *btf, int data_sz) struct btf_pipe { const struct btf *src; struct btf *dst; + struct hashmap *str_off_map; /* map string offsets from src to dst */ }; static int btf_rewrite_str(__u32 *str_off, void *ctx) { struct btf_pipe *p = ctx; - int off; + void *mapped_off; + int off, err; if (!*str_off) /* nothing to do for empty strings */ return 0; + if (p->str_off_map && + hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) { + *str_off = (__u32)(long)mapped_off; + return 0; + } + off = btf__add_str(p->dst, btf__str_by_offset(p->src, *str_off)); if (off < 0) return off; + /* Remember string mapping from src to dst. It avoids + * performing expensive string comparisons. + */ + if (p->str_off_map) { + err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off); + if (err) + return err; + } + *str_off = off; return 0; } @@ -1680,6 +1697,9 @@ static int btf_rewrite_type_ids(__u32 *type_id, void *ctx) return 0; } +static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx); +static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx); + int btf__add_btf(struct btf *btf, const struct btf *src_btf) { struct btf_pipe p = { .src = src_btf, .dst = btf }; @@ -1713,6 +1733,11 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) if (!off) return libbpf_err(-ENOMEM); + /* Map the string offsets from src_btf to the offsets from btf to improve performance */ + p.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL); + if (IS_ERR(p.str_off_map)) + return libbpf_err(-ENOMEM); + /* bulk copy types data for all types from src_btf */ memcpy(t, src_btf->types_data, data_sz); @@ -1754,6 +1779,8 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) btf->hdr->str_off += data_sz; btf->nr_types += cnt; + hashmap__free(p.str_off_map); + /* return type ID of the first added BTF type */ return btf->start_id + btf->nr_types - cnt; err_out: @@ -1767,6 +1794,8 @@ err_out: * wasn't modified, so doesn't need restoring, see big comment above */ btf->hdr->str_len = old_strs_len; + hashmap__free(p.str_off_map); + return libbpf_err(err); } diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 061839f04525..951ac7475794 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -147,11 +147,10 @@ LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); LIBBPF_API int btf__fd(const struct btf *btf); LIBBPF_API void btf__set_fd(struct btf *btf, int fd); -LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__raw_data() instead") -LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset); +LIBBPF_DEPRECATED_SINCE(0, 7, "this API is not necessary when BTF-defined maps are used") LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, __u32 expected_key_size, __u32 expected_value_size, @@ -159,8 +158,7 @@ LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size); LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); -LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, - __u32 *size); +LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size); LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info was never meant as a public API and has wrong assumptions embedded in it; it will be removed in the future libbpf versions") int btf_ext__reloc_func_info(const struct btf *btf, const struct btf_ext *btf_ext, @@ -171,8 +169,10 @@ int btf_ext__reloc_line_info(const struct btf *btf, const struct btf_ext *btf_ext, const char *sec_name, __u32 insns_cnt, void **line_info, __u32 *cnt); -LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); -LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_func_info is deprecated; write custom func_info parsing to fetch rec_size") +__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_info is deprecated; write custom line_info parsing to fetch rec_size") +__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); LIBBPF_API int btf__find_str(struct btf *btf, const char *s); LIBBPF_API int btf__add_str(struct btf *btf, const char *s); @@ -375,8 +375,28 @@ btf_dump__dump_type_data(struct btf_dump *d, __u32 id, const struct btf_dump_type_data_opts *opts); /* - * A set of helpers for easier BTF types handling + * A set of helpers for easier BTF types handling. + * + * The inline functions below rely on constants from the kernel headers which + * may not be available for applications including this header file. To avoid + * compilation errors, we define all the constants here that were added after + * the initial introduction of the BTF_KIND* constants. */ +#ifndef BTF_KIND_FUNC +#define BTF_KIND_FUNC 12 /* Function */ +#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ +#endif +#ifndef BTF_KIND_VAR +#define BTF_KIND_VAR 14 /* Variable */ +#define BTF_KIND_DATASEC 15 /* Section */ +#endif +#ifndef BTF_KIND_FLOAT +#define BTF_KIND_FLOAT 16 /* Floating point */ +#endif +/* The kernel header switched to enums, so these two were never #defined */ +#define BTF_KIND_DECL_TAG 17 /* Decl Tag */ +#define BTF_KIND_TYPE_TAG 18 /* Type Tag */ + static inline __u16 btf_kind(const struct btf_type *t) { return BTF_INFO_KIND(t->info); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index b9a3260c83cb..6b1bc1f43728 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -1505,6 +1505,11 @@ static const char *btf_dump_resolve_name(struct btf_dump *d, __u32 id, if (s->name_resolved) return *cached_name ? *cached_name : orig_name; + if (btf_is_fwd(t) || (btf_is_enum(t) && btf_vlen(t) == 0)) { + s->name_resolved = 1; + return orig_name; + } + dup_cnt = btf_dump_name_dups(d, name_map, orig_name); if (dup_cnt > 1) { const size_t max_len = 256; @@ -1861,14 +1866,16 @@ static int btf_dump_array_data(struct btf_dump *d, { const struct btf_array *array = btf_array(t); const struct btf_type *elem_type; - __u32 i, elem_size = 0, elem_type_id; + __u32 i, elem_type_id; + __s64 elem_size; bool is_array_member; elem_type_id = array->type; elem_type = skip_mods_and_typedefs(d->btf, elem_type_id, NULL); elem_size = btf__resolve_size(d->btf, elem_type_id); if (elem_size <= 0) { - pr_warn("unexpected elem size %d for array type [%u]\n", elem_size, id); + pr_warn("unexpected elem size %zd for array type [%u]\n", + (ssize_t)elem_size, id); return -EINVAL; } diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 8ecef1088ba2..927745b08014 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -1043,18 +1043,27 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, value = add_data(gen, pvalue, value_size); key = add_data(gen, &zero, sizeof(zero)); - /* if (map_desc[map_idx].initial_value) - * copy_from_user(value, initial_value, value_size); + /* if (map_desc[map_idx].initial_value) { + * if (ctx->flags & BPF_SKEL_KERNEL) + * bpf_probe_read_kernel(value, value_size, initial_value); + * else + * bpf_copy_from_user(value, value_size, initial_value); + * } */ emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6, sizeof(struct bpf_loader_ctx) + sizeof(struct bpf_map_desc) * map_idx + offsetof(struct bpf_map_desc, initial_value))); - emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 4)); + emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 8)); emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, value)); emit(gen, BPF_MOV64_IMM(BPF_REG_2, value_size)); + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, + offsetof(struct bpf_loader_ctx, flags))); + emit(gen, BPF_JMP_IMM(BPF_JSET, BPF_REG_0, BPF_SKEL_KERNEL, 2)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user)); + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 1)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); map_update_attr = add_data(gen, &attr, attr_size); move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c index 3c20b126d60d..aeb09c288716 100644 --- a/tools/lib/bpf/hashmap.c +++ b/tools/lib/bpf/hashmap.c @@ -75,7 +75,7 @@ void hashmap__clear(struct hashmap *map) void hashmap__free(struct hashmap *map) { - if (!map) + if (IS_ERR_OR_NULL(map)) return; hashmap__clear(map); @@ -238,4 +238,3 @@ bool hashmap__delete(struct hashmap *map, const void *key, return true; } - diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 7f10dd501a52..809fe209cdcc 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -156,14 +156,6 @@ enum libbpf_strict_mode libbpf_mode = LIBBPF_STRICT_NONE; int libbpf_set_strict_mode(enum libbpf_strict_mode mode) { - /* __LIBBPF_STRICT_LAST is the last power-of-2 value used + 1, so to - * get all possible values we compensate last +1, and then (2*x - 1) - * to get the bit mask - */ - if (mode != LIBBPF_STRICT_ALL - && (mode & ~((__LIBBPF_STRICT_LAST - 1) * 2 - 1))) - return errno = EINVAL, -EINVAL; - libbpf_mode = mode; return 0; } @@ -209,12 +201,6 @@ struct reloc_desc { }; }; -struct bpf_sec_def; - -typedef int (*init_fn_t)(struct bpf_program *prog, long cookie); -typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_opts *opts, long cookie); -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie); - /* stored as sec_def->cookie for all libbpf-supported SEC()s */ enum sec_def_flags { SEC_NONE = 0, @@ -235,17 +221,22 @@ enum sec_def_flags { SEC_SLEEPABLE = 8, /* allow non-strict prefix matching */ SEC_SLOPPY_PFX = 16, + /* BPF program support non-linear XDP buffer */ + SEC_XDP_FRAGS = 32, + /* deprecated sec definitions not supposed to be used */ + SEC_DEPRECATED = 64, }; struct bpf_sec_def { - const char *sec; + char *sec; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; long cookie; + int handler_id; - init_fn_t init_fn; - preload_fn_t preload_fn; - attach_fn_t attach_fn; + libbpf_prog_setup_fn_t prog_setup_fn; + libbpf_prog_prepare_load_fn_t prog_prepare_load_fn; + libbpf_prog_attach_fn_t prog_attach_fn; }; /* @@ -1378,22 +1369,20 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32 *size) { - int ret = -ENOENT; Elf_Data *data; Elf_Scn *scn; - *size = 0; if (!name) return -EINVAL; scn = elf_sec_by_name(obj, name); data = elf_sec_data(obj, scn); if (data) { - ret = 0; /* found it */ *size = data->d_size; + return 0; /* found it */ } - return *size ? 0 : ret; + return -ENOENT; } static int find_elf_var_offset(const struct bpf_object *obj, const char *name, __u32 *off) @@ -1529,6 +1518,9 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name) } static int +bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map); + +static int bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, const char *real_name, int sec_idx, void *data, size_t data_sz) { @@ -1575,6 +1567,9 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, return err; } + /* failures are fine because of maps like .rodata.str1.1 */ + (void) bpf_map_find_btf_info(obj, map); + if (data) memcpy(map->mmaped, data, data_sz); @@ -1937,6 +1932,11 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) if (obj->efile.maps_shndx < 0) return 0; + if (libbpf_mode & LIBBPF_STRICT_MAP_DEFINITIONS) { + pr_warn("legacy map definitions in SEC(\"maps\") are not supported\n"); + return -EOPNOTSUPP; + } + if (!symbols) return -EINVAL; @@ -1999,6 +1999,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return -LIBBPF_ERRNO__FORMAT; } + pr_warn("map '%s' (legacy): legacy map definitions are deprecated, use BTF-defined maps instead\n", map_name); + if (ELF64_ST_BIND(sym->st_info) == STB_LOCAL) { pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); return -ENOTSUP; @@ -2050,6 +2052,9 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) } memcpy(&map->def, def, sizeof(struct bpf_map_def)); } + + /* btf info may not exist but fill it in if it does exist */ + (void) bpf_map_find_btf_info(obj, map); } return 0; } @@ -2538,6 +2543,10 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, fill_map_from_def(map->inner_map, &inner_def); } + err = bpf_map_find_btf_info(obj, map); + if (err) + return err; + return 0; } @@ -2792,7 +2801,7 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, goto sort_vars; ret = find_elf_sec_sz(obj, name, &size); - if (ret || !size || (t->size && t->size != size)) { + if (ret || !size) { pr_debug("Invalid size for section %s: %u bytes\n", name, size); return -ENOENT; } @@ -3836,7 +3845,14 @@ static bool prog_is_subprog(const struct bpf_object *obj, * .text programs are subprograms (even if they are not called from * other programs), because libbpf never explicitly supported mixing * SEC()-designated BPF programs and .text entry-point BPF programs. + * + * In libbpf 1.0 strict mode, we always consider .text + * programs to be subprograms. */ + + if (libbpf_mode & LIBBPF_STRICT_SEC_NAME) + return prog->sec_idx == obj->efile.text_shndx; + return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; } @@ -4181,6 +4197,9 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) __u32 key_type_id = 0, value_type_id = 0; int ret; + if (!obj->btf) + return -ENOENT; + /* if it's BTF-defined map, we don't need to search for type IDs. * For struct_ops map, it does not need btf_key_type_id and * btf_value_type_id. @@ -4190,9 +4209,13 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) return 0; if (!bpf_map__is_internal(map)) { + pr_warn("Use of BPF_ANNOTATE_KV_PAIR is deprecated, use BTF-defined maps in .maps section instead\n"); +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size, def->value_size, &key_type_id, &value_type_id); +#pragma GCC diagnostic pop } else { /* * LLVM annotates global data differently in BTF, that is, @@ -4800,8 +4823,8 @@ bpf_object__reuse_map(struct bpf_map *map) } err = bpf_map__reuse_fd(map, pin_fd); + close(pin_fd); if (err) { - close(pin_fd); return err; } map->pinned = true; @@ -4854,7 +4877,6 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b LIBBPF_OPTS(bpf_map_create_opts, create_attr); struct bpf_map_def *def = &map->def; const char *map_name = NULL; - __u32 max_entries; int err = 0; if (kernel_supports(obj, FEAT_PROG_NAME)) @@ -4864,25 +4886,10 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.numa_node = map->numa_node; create_attr.map_extra = map->map_extra; - if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) { - int nr_cpus; - - nr_cpus = libbpf_num_possible_cpus(); - if (nr_cpus < 0) { - pr_warn("map '%s': failed to determine number of system CPUs: %d\n", - map->name, nr_cpus); - return nr_cpus; - } - pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus); - max_entries = nr_cpus; - } else { - max_entries = def->max_entries; - } - if (bpf_map__is_struct_ops(map)) create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; - if (obj->btf && btf__fd(obj->btf) >= 0 && !bpf_map_find_btf_info(obj, map)) { + if (obj->btf && btf__fd(obj->btf) >= 0) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; create_attr.btf_value_type_id = map->btf_value_type_id; @@ -4928,7 +4935,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b if (obj->gen_loader) { bpf_gen__map_create(obj->gen_loader, def->type, map_name, - def->key_size, def->value_size, max_entries, + def->key_size, def->value_size, def->max_entries, &create_attr, is_inner ? -1 : map - obj->maps); /* Pretend to have valid FD to pass various fd >= 0 checks. * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. @@ -4937,7 +4944,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b } else { map->fd = bpf_map_create(def->type, map_name, def->key_size, def->value_size, - max_entries, &create_attr); + def->max_entries, &create_attr); } if (map->fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { @@ -4954,7 +4961,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b map->btf_value_type_id = 0; map->fd = bpf_map_create(def->type, map_name, def->key_size, def->value_size, - max_entries, &create_attr); + def->max_entries, &create_attr); } err = map->fd < 0 ? -errno : 0; @@ -5058,6 +5065,24 @@ static int bpf_object_init_prog_arrays(struct bpf_object *obj) return 0; } +static int map_set_def_max_entries(struct bpf_map *map) +{ + if (map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !map->def.max_entries) { + int nr_cpus; + + nr_cpus = libbpf_num_possible_cpus(); + if (nr_cpus < 0) { + pr_warn("map '%s': failed to determine number of system CPUs: %d\n", + map->name, nr_cpus); + return nr_cpus; + } + pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus); + map->def.max_entries = nr_cpus; + } + + return 0; +} + static int bpf_object__create_maps(struct bpf_object *obj) { @@ -5090,6 +5115,10 @@ bpf_object__create_maps(struct bpf_object *obj) continue; } + err = map_set_def_max_entries(map); + if (err) + goto err_out; + retried = false; retry: if (map->pin_path) { @@ -5185,18 +5214,21 @@ size_t bpf_core_essential_name_len(const char *name) return n; } -static void bpf_core_free_cands(struct bpf_core_cand_list *cands) +void bpf_core_free_cands(struct bpf_core_cand_list *cands) { + if (!cands) + return; + free(cands->cands); free(cands); } -static int bpf_core_add_cands(struct bpf_core_cand *local_cand, - size_t local_essent_len, - const struct btf *targ_btf, - const char *targ_btf_name, - int targ_start_id, - struct bpf_core_cand_list *cands) +int bpf_core_add_cands(struct bpf_core_cand *local_cand, + size_t local_essent_len, + const struct btf *targ_btf, + const char *targ_btf_name, + int targ_start_id, + struct bpf_core_cand_list *cands) { struct bpf_core_cand *new_cands, *cand; const struct btf_type *t, *local_t; @@ -5523,11 +5555,12 @@ static int record_relo_core(struct bpf_program *prog, return 0; } -static int bpf_core_apply_relo(struct bpf_program *prog, - const struct bpf_core_relo *relo, - int relo_idx, - const struct btf *local_btf, - struct hashmap *cand_cache) +static int bpf_core_resolve_relo(struct bpf_program *prog, + const struct bpf_core_relo *relo, + int relo_idx, + const struct btf *local_btf, + struct hashmap *cand_cache, + struct bpf_core_relo_res *targ_res) { struct bpf_core_spec specs_scratch[3] = {}; const void *type_key = u32_as_hash_key(relo->type_id); @@ -5536,20 +5569,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog, const struct btf_type *local_type; const char *local_name; __u32 local_id = relo->type_id; - struct bpf_insn *insn; - int insn_idx, err; - - if (relo->insn_off % BPF_INSN_SZ) - return -EINVAL; - insn_idx = relo->insn_off / BPF_INSN_SZ; - /* adjust insn_idx from section frame of reference to the local - * program's frame of reference; (sub-)program code is not yet - * relocated, so it's enough to just subtract in-section offset - */ - insn_idx = insn_idx - prog->sec_insn_off; - if (insn_idx >= prog->insns_cnt) - return -EINVAL; - insn = &prog->insns[insn_idx]; + int err; local_type = btf__type_by_id(local_btf, local_id); if (!local_type) @@ -5559,15 +5579,6 @@ static int bpf_core_apply_relo(struct bpf_program *prog, if (!local_name) return -EINVAL; - if (prog->obj->gen_loader) { - const char *spec_str = btf__name_by_offset(local_btf, relo->access_str_off); - - pr_debug("record_relo_core: prog %td insn[%d] %s %s %s final insn_idx %d\n", - prog - prog->obj->programs, relo->insn_off / 8, - btf_kind_str(local_type), local_name, spec_str, insn_idx); - return record_relo_core(prog, relo, insn_idx); - } - if (relo->kind != BPF_CORE_TYPE_ID_LOCAL && !hashmap__find(cand_cache, type_key, (void **)&cands)) { cands = bpf_core_find_cands(prog->obj, local_btf, local_id); @@ -5584,19 +5595,21 @@ static int bpf_core_apply_relo(struct bpf_program *prog, } } - return bpf_core_apply_relo_insn(prog_name, insn, insn_idx, relo, - relo_idx, local_btf, cands, specs_scratch); + return bpf_core_calc_relo_insn(prog_name, relo, relo_idx, local_btf, cands, specs_scratch, + targ_res); } static int bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) { const struct btf_ext_info_sec *sec; + struct bpf_core_relo_res targ_res; const struct bpf_core_relo *rec; const struct btf_ext_info *seg; struct hashmap_entry *entry; struct hashmap *cand_cache = NULL; struct bpf_program *prog; + struct bpf_insn *insn; const char *sec_name; int i, err = 0, insn_idx, sec_idx; @@ -5647,6 +5660,8 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) sec_name, sec->num_info); for_each_btf_ext_rec(seg, sec, i, rec) { + if (rec->insn_off % BPF_INSN_SZ) + return -EINVAL; insn_idx = rec->insn_off / BPF_INSN_SZ; prog = find_prog_by_sec_insn(obj, sec_idx, insn_idx); if (!prog) { @@ -5661,12 +5676,38 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) if (!prog->load) continue; - err = bpf_core_apply_relo(prog, rec, i, obj->btf, cand_cache); + /* adjust insn_idx from section frame of reference to the local + * program's frame of reference; (sub-)program code is not yet + * relocated, so it's enough to just subtract in-section offset + */ + insn_idx = insn_idx - prog->sec_insn_off; + if (insn_idx >= prog->insns_cnt) + return -EINVAL; + insn = &prog->insns[insn_idx]; + + if (prog->obj->gen_loader) { + err = record_relo_core(prog, rec, insn_idx); + if (err) { + pr_warn("prog '%s': relo #%d: failed to record relocation: %d\n", + prog->name, i, err); + goto out; + } + continue; + } + + err = bpf_core_resolve_relo(prog, rec, i, obj->btf, cand_cache, &targ_res); if (err) { pr_warn("prog '%s': relo #%d: failed to relocate: %d\n", prog->name, i, err); goto out; } + + err = bpf_core_patch_insn(prog->name, insn, insn_idx, rec, i, &targ_res); + if (err) { + pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n", + prog->name, i, insn_idx, err); + goto out; + } } } @@ -6549,9 +6590,9 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name, int *btf_obj_fd, int *btf_type_id); -/* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */ -static int libbpf_preload_prog(struct bpf_program *prog, - struct bpf_prog_load_opts *opts, long cookie) +/* this is called as prog->sec_def->prog_prepare_load_fn for libbpf-supported sec_defs */ +static int libbpf_prepare_prog_load(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie) { enum sec_def_flags def = cookie; @@ -6562,6 +6603,13 @@ static int libbpf_preload_prog(struct bpf_program *prog, if (def & SEC_SLEEPABLE) opts->prog_flags |= BPF_F_SLEEPABLE; + if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS)) + opts->prog_flags |= BPF_F_XDP_HAS_FRAGS; + + if (def & SEC_DEPRECATED) + pr_warn("SEC(\"%s\") is deprecated, please see https://github.com/libbpf/libbpf/wiki/Libbpf-1.0-migration-guide#bpf-program-sec-annotation-deprecations for details\n", + prog->sec_name); + if ((prog->type == BPF_PROG_TYPE_TRACING || prog->type == BPF_PROG_TYPE_LSM || prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { @@ -6640,8 +6688,8 @@ static int bpf_object_load_prog_instance(struct bpf_object *obj, struct bpf_prog load_attr.fd_array = obj->fd_array; /* adjust load_attr if sec_def provides custom preload callback */ - if (prog->sec_def && prog->sec_def->preload_fn) { - err = prog->sec_def->preload_fn(prog, &load_attr, prog->sec_def->cookie); + if (prog->sec_def && prog->sec_def->prog_prepare_load_fn) { + err = prog->sec_def->prog_prepare_load_fn(prog, &load_attr, prog->sec_def->cookie); if (err < 0) { pr_warn("prog '%s': failed to prepare load attributes: %d\n", prog->name, err); @@ -6941,8 +6989,8 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object /* sec_def can have custom callback which should be called * after bpf_program is initialized to adjust its properties */ - if (prog->sec_def->init_fn) { - err = prog->sec_def->init_fn(prog, prog->sec_def->cookie); + if (prog->sec_def->prog_setup_fn) { + err = prog->sec_def->prog_setup_fn(prog, prog->sec_def->cookie); if (err < 0) { pr_warn("prog '%s': failed to initialize: %d\n", prog->name, err); @@ -7146,12 +7194,10 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) return 0; } -static int bpf_object__read_kallsyms_file(struct bpf_object *obj) +int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) { char sym_type, sym_name[500]; unsigned long long sym_addr; - const struct btf_type *t; - struct extern_desc *ext; int ret, err = 0; FILE *f; @@ -7170,35 +7216,51 @@ static int bpf_object__read_kallsyms_file(struct bpf_object *obj) if (ret != 3) { pr_warn("failed to read kallsyms entry: %d\n", ret); err = -EINVAL; - goto out; + break; } - ext = find_extern_by_name(obj, sym_name); - if (!ext || ext->type != EXT_KSYM) - continue; - - t = btf__type_by_id(obj->btf, ext->btf_id); - if (!btf_is_var(t)) - continue; - - if (ext->is_set && ext->ksym.addr != sym_addr) { - pr_warn("extern (ksym) '%s' resolution is ambiguous: 0x%llx or 0x%llx\n", - sym_name, ext->ksym.addr, sym_addr); - err = -EINVAL; - goto out; - } - if (!ext->is_set) { - ext->is_set = true; - ext->ksym.addr = sym_addr; - pr_debug("extern (ksym) %s=0x%llx\n", sym_name, sym_addr); - } + err = cb(sym_addr, sym_type, sym_name, ctx); + if (err) + break; } -out: fclose(f); return err; } +static int kallsyms_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) +{ + struct bpf_object *obj = ctx; + const struct btf_type *t; + struct extern_desc *ext; + + ext = find_extern_by_name(obj, sym_name); + if (!ext || ext->type != EXT_KSYM) + return 0; + + t = btf__type_by_id(obj->btf, ext->btf_id); + if (!btf_is_var(t)) + return 0; + + if (ext->is_set && ext->ksym.addr != sym_addr) { + pr_warn("extern (ksym) '%s' resolution is ambiguous: 0x%llx or 0x%llx\n", + sym_name, ext->ksym.addr, sym_addr); + return -EINVAL; + } + if (!ext->is_set) { + ext->is_set = true; + ext->ksym.addr = sym_addr; + pr_debug("extern (ksym) %s=0x%llx\n", sym_name, sym_addr); + } + return 0; +} + +static int bpf_object__read_kallsyms_file(struct bpf_object *obj) +{ + return libbpf_kallsyms_parse(kallsyms_cb, obj); +} + static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, __u16 kind, struct btf **res_btf, struct module_btf **res_mod_btf) @@ -7883,10 +7945,8 @@ int bpf_map__set_pin_path(struct bpf_map *map, const char *path) return 0; } -const char *bpf_map__get_pin_path(const struct bpf_map *map) -{ - return map->pin_path; -} +__alias(bpf_map__pin_path) +const char *bpf_map__get_pin_path(const struct bpf_map *map); const char *bpf_map__pin_path(const struct bpf_map *map) { @@ -8451,7 +8511,10 @@ static int bpf_program_nth_fd(const struct bpf_program *prog, int n) return fd; } -enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog) +__alias(bpf_program__type) +enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); + +enum bpf_prog_type bpf_program__type(const struct bpf_program *prog) { return prog->type; } @@ -8495,8 +8558,10 @@ BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS); BPF_PROG_TYPE_FNS(extension, BPF_PROG_TYPE_EXT); BPF_PROG_TYPE_FNS(sk_lookup, BPF_PROG_TYPE_SK_LOOKUP); -enum bpf_attach_type -bpf_program__get_expected_attach_type(const struct bpf_program *prog) +__alias(bpf_program__expected_attach_type) +enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog); + +enum bpf_attach_type bpf_program__expected_attach_type(const struct bpf_program *prog) { return prog->expected_attach_type; } @@ -8556,20 +8621,21 @@ int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log } #define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ - .sec = sec_pfx, \ + .sec = (char *)sec_pfx, \ .prog_type = BPF_PROG_TYPE_##ptype, \ .expected_attach_type = atype, \ .cookie = (long)(flags), \ - .preload_fn = libbpf_preload_prog, \ + .prog_prepare_load_fn = libbpf_prepare_prog_load, \ __VA_ARGS__ \ } -static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie); -static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie); +static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link); static const struct bpf_sec_def section_defs[] = { SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE | SEC_SLOPPY_PFX), @@ -8579,8 +8645,10 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("uprobe/", KPROBE, 0, SEC_NONE), SEC_DEF("kretprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), SEC_DEF("uretprobe/", KPROBE, 0, SEC_NONE), + SEC_DEF("kprobe.multi/", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), + SEC_DEF("kretprobe.multi/", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX), + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX | SEC_DEPRECATED), SEC_DEF("action", SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX), SEC_DEF("tracepoint/", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("tp/", TRACEPOINT, 0, SEC_NONE, attach_tp), @@ -8599,9 +8667,15 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("lsm/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm), SEC_DEF("lsm.s/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), SEC_DEF("iter/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter), + SEC_DEF("iter.s/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_iter), SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), - SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), - SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp.frags/devmap", XDP, BPF_XDP_DEVMAP, SEC_XDP_FRAGS), + SEC_DEF("xdp/devmap", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), + SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE | SEC_DEPRECATED), + SEC_DEF("xdp.frags/cpumap", XDP, BPF_XDP_CPUMAP, SEC_XDP_FRAGS), + SEC_DEF("xdp/cpumap", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE | SEC_DEPRECATED), + SEC_DEF("xdp.frags", XDP, BPF_XDP, SEC_XDP_FRAGS), SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX), SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX), @@ -8643,61 +8717,167 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE | SEC_SLOPPY_PFX), }; -#define MAX_TYPE_NAME_SIZE 32 +static size_t custom_sec_def_cnt; +static struct bpf_sec_def *custom_sec_defs; +static struct bpf_sec_def custom_fallback_def; +static bool has_custom_fallback_def; -static const struct bpf_sec_def *find_sec_def(const char *sec_name) +static int last_custom_sec_def_handler_id; + +int libbpf_register_prog_handler(const char *sec, + enum bpf_prog_type prog_type, + enum bpf_attach_type exp_attach_type, + const struct libbpf_prog_handler_opts *opts) { - const struct bpf_sec_def *sec_def; - enum sec_def_flags sec_flags; - int i, n = ARRAY_SIZE(section_defs), len; - bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME; + struct bpf_sec_def *sec_def; - for (i = 0; i < n; i++) { - sec_def = §ion_defs[i]; - sec_flags = sec_def->cookie; - len = strlen(sec_def->sec); + if (!OPTS_VALID(opts, libbpf_prog_handler_opts)) + return libbpf_err(-EINVAL); - /* "type/" always has to have proper SEC("type/extras") form */ - if (sec_def->sec[len - 1] == '/') { - if (str_has_pfx(sec_name, sec_def->sec)) - return sec_def; - continue; - } + if (last_custom_sec_def_handler_id == INT_MAX) /* prevent overflow */ + return libbpf_err(-E2BIG); - /* "type+" means it can be either exact SEC("type") or - * well-formed SEC("type/extras") with proper '/' separator - */ - if (sec_def->sec[len - 1] == '+') { - len--; - /* not even a prefix */ - if (strncmp(sec_name, sec_def->sec, len) != 0) - continue; - /* exact match or has '/' separator */ - if (sec_name[len] == '\0' || sec_name[len] == '/') - return sec_def; - continue; - } + if (sec) { + sec_def = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt + 1, + sizeof(*sec_def)); + if (!sec_def) + return libbpf_err(-ENOMEM); - /* SEC_SLOPPY_PFX definitions are allowed to be just prefix - * matches, unless strict section name mode - * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the - * match has to be exact. - */ - if ((sec_flags & SEC_SLOPPY_PFX) && !strict) { - if (str_has_pfx(sec_name, sec_def->sec)) - return sec_def; - continue; - } + custom_sec_defs = sec_def; + sec_def = &custom_sec_defs[custom_sec_def_cnt]; + } else { + if (has_custom_fallback_def) + return libbpf_err(-EBUSY); - /* Definitions not marked SEC_SLOPPY_PFX (e.g., - * SEC("syscall")) are exact matches in both modes. - */ - if (strcmp(sec_name, sec_def->sec) == 0) + sec_def = &custom_fallback_def; + } + + sec_def->sec = sec ? strdup(sec) : NULL; + if (sec && !sec_def->sec) + return libbpf_err(-ENOMEM); + + sec_def->prog_type = prog_type; + sec_def->expected_attach_type = exp_attach_type; + sec_def->cookie = OPTS_GET(opts, cookie, 0); + + sec_def->prog_setup_fn = OPTS_GET(opts, prog_setup_fn, NULL); + sec_def->prog_prepare_load_fn = OPTS_GET(opts, prog_prepare_load_fn, NULL); + sec_def->prog_attach_fn = OPTS_GET(opts, prog_attach_fn, NULL); + + sec_def->handler_id = ++last_custom_sec_def_handler_id; + + if (sec) + custom_sec_def_cnt++; + else + has_custom_fallback_def = true; + + return sec_def->handler_id; +} + +int libbpf_unregister_prog_handler(int handler_id) +{ + struct bpf_sec_def *sec_defs; + int i; + + if (handler_id <= 0) + return libbpf_err(-EINVAL); + + if (has_custom_fallback_def && custom_fallback_def.handler_id == handler_id) { + memset(&custom_fallback_def, 0, sizeof(custom_fallback_def)); + has_custom_fallback_def = false; + return 0; + } + + for (i = 0; i < custom_sec_def_cnt; i++) { + if (custom_sec_defs[i].handler_id == handler_id) + break; + } + + if (i == custom_sec_def_cnt) + return libbpf_err(-ENOENT); + + free(custom_sec_defs[i].sec); + for (i = i + 1; i < custom_sec_def_cnt; i++) + custom_sec_defs[i - 1] = custom_sec_defs[i]; + custom_sec_def_cnt--; + + /* try to shrink the array, but it's ok if we couldn't */ + sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs)); + if (sec_defs) + custom_sec_defs = sec_defs; + + return 0; +} + +static bool sec_def_matches(const struct bpf_sec_def *sec_def, const char *sec_name, + bool allow_sloppy) +{ + size_t len = strlen(sec_def->sec); + + /* "type/" always has to have proper SEC("type/extras") form */ + if (sec_def->sec[len - 1] == '/') { + if (str_has_pfx(sec_name, sec_def->sec)) + return true; + return false; + } + + /* "type+" means it can be either exact SEC("type") or + * well-formed SEC("type/extras") with proper '/' separator + */ + if (sec_def->sec[len - 1] == '+') { + len--; + /* not even a prefix */ + if (strncmp(sec_name, sec_def->sec, len) != 0) + return false; + /* exact match or has '/' separator */ + if (sec_name[len] == '\0' || sec_name[len] == '/') + return true; + return false; + } + + /* SEC_SLOPPY_PFX definitions are allowed to be just prefix + * matches, unless strict section name mode + * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the + * match has to be exact. + */ + if (allow_sloppy && str_has_pfx(sec_name, sec_def->sec)) + return true; + + /* Definitions not marked SEC_SLOPPY_PFX (e.g., + * SEC("syscall")) are exact matches in both modes. + */ + return strcmp(sec_name, sec_def->sec) == 0; +} + +static const struct bpf_sec_def *find_sec_def(const char *sec_name) +{ + const struct bpf_sec_def *sec_def; + int i, n; + bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME, allow_sloppy; + + n = custom_sec_def_cnt; + for (i = 0; i < n; i++) { + sec_def = &custom_sec_defs[i]; + if (sec_def_matches(sec_def, sec_name, false)) return sec_def; } + + n = ARRAY_SIZE(section_defs); + for (i = 0; i < n; i++) { + sec_def = §ion_defs[i]; + allow_sloppy = (sec_def->cookie & SEC_SLOPPY_PFX) && !strict; + if (sec_def_matches(sec_def, sec_name, allow_sloppy)) + return sec_def; + } + + if (has_custom_fallback_def) + return &custom_fallback_def; + return NULL; } +#define MAX_TYPE_NAME_SIZE 32 + static char *libbpf_get_type_names(bool attach_type) { int i, len = ARRAY_SIZE(section_defs) * MAX_TYPE_NAME_SIZE; @@ -8713,7 +8893,7 @@ static char *libbpf_get_type_names(bool attach_type) const struct bpf_sec_def *sec_def = §ion_defs[i]; if (attach_type) { - if (sec_def->preload_fn != libbpf_preload_prog) + if (sec_def->prog_prepare_load_fn != libbpf_prepare_prog_load) continue; if (!(sec_def->cookie & SEC_ATTACHABLE)) @@ -9096,7 +9276,7 @@ int libbpf_attach_type_by_name(const char *name, return libbpf_err(-EINVAL); } - if (sec_def->preload_fn != libbpf_preload_prog) + if (sec_def->prog_prepare_load_fn != libbpf_prepare_prog_load) return libbpf_err(-EINVAL); if (!(sec_def->cookie & SEC_ATTACHABLE)) return libbpf_err(-EINVAL); @@ -9443,7 +9623,7 @@ static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, open_attr.file = attr->file; open_attr.prog_type = attr->prog_type; - obj = bpf_object__open_xattr(&open_attr); + obj = __bpf_object__open_xattr(&open_attr, 0); err = libbpf_get_error(obj); if (err) return libbpf_err(-ENOENT); @@ -9460,7 +9640,7 @@ static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, bpf_program__set_expected_attach_type(prog, attach_type); } - if (bpf_program__get_type(prog) == BPF_PROG_TYPE_UNSPEC) { + if (bpf_program__type(prog) == BPF_PROG_TYPE_UNSPEC) { /* * we haven't guessed from section name and user * didn't provide a fallback type, too bad... @@ -9477,7 +9657,7 @@ static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, } bpf_object__for_each_map(map, obj) { - if (!bpf_map__is_offload_neutral(map)) + if (map->def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) map->map_ifindex = attr->ifindex; } @@ -10070,14 +10250,146 @@ struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, return bpf_program__attach_kprobe_opts(prog, func_name, &opts); } -static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie) +/* Adapted from perf/util/string.c */ +static bool glob_match(const char *str, const char *pat) +{ + while (*str && *pat && *pat != '*') { + if (*pat == '?') { /* Matches any single character */ + str++; + pat++; + continue; + } + if (*str != *pat) + return false; + str++; + pat++; + } + /* Check wild card */ + if (*pat == '*') { + while (*pat == '*') + pat++; + if (!*pat) /* Tail wild card matches all */ + return true; + while (*str) + if (glob_match(str++, pat)) + return true; + } + return !*str && !*pat; +} + +struct kprobe_multi_resolve { + const char *pattern; + unsigned long *addrs; + size_t cap; + size_t cnt; +}; + +static int +resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) +{ + struct kprobe_multi_resolve *res = ctx; + int err; + + if (!glob_match(sym_name, res->pattern)) + return 0; + + err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long), + res->cnt + 1); + if (err) + return err; + + res->addrs[res->cnt++] = (unsigned long) sym_addr; + return 0; +} + +struct bpf_link * +bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, + const char *pattern, + const struct bpf_kprobe_multi_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, lopts); + struct kprobe_multi_resolve res = { + .pattern = pattern, + }; + struct bpf_link *link = NULL; + char errmsg[STRERR_BUFSIZE]; + const unsigned long *addrs; + int err, link_fd, prog_fd; + const __u64 *cookies; + const char **syms; + bool retprobe; + size_t cnt; + + if (!OPTS_VALID(opts, bpf_kprobe_multi_opts)) + return libbpf_err_ptr(-EINVAL); + + syms = OPTS_GET(opts, syms, false); + addrs = OPTS_GET(opts, addrs, false); + cnt = OPTS_GET(opts, cnt, false); + cookies = OPTS_GET(opts, cookies, false); + + if (!pattern && !addrs && !syms) + return libbpf_err_ptr(-EINVAL); + if (pattern && (addrs || syms || cookies || cnt)) + return libbpf_err_ptr(-EINVAL); + if (!pattern && !cnt) + return libbpf_err_ptr(-EINVAL); + if (addrs && syms) + return libbpf_err_ptr(-EINVAL); + + if (pattern) { + err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res); + if (err) + goto error; + if (!res.cnt) { + err = -ENOENT; + goto error; + } + addrs = res.addrs; + cnt = res.cnt; + } + + retprobe = OPTS_GET(opts, retprobe, false); + + lopts.kprobe_multi.syms = syms; + lopts.kprobe_multi.addrs = addrs; + lopts.kprobe_multi.cookies = cookies; + lopts.kprobe_multi.cnt = cnt; + lopts.kprobe_multi.flags = retprobe ? BPF_F_KPROBE_MULTI_RETURN : 0; + + link = calloc(1, sizeof(*link)); + if (!link) { + err = -ENOMEM; + goto error; + } + link->detach = &bpf_link__detach_fd; + + prog_fd = bpf_program__fd(prog); + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &lopts); + if (link_fd < 0) { + err = -errno; + pr_warn("prog '%s': failed to attach: %s\n", + prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto error; + } + link->fd = link_fd; + free(res.addrs); + return link; + +error: + free(link); + free(res.addrs); + return libbpf_err_ptr(err); +} + +static int attach_kprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link) { DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts); unsigned long offset = 0; - struct bpf_link *link; const char *func_name; char *func; - int n, err; + int n; opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/"); if (opts.retprobe) @@ -10087,21 +10399,43 @@ static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cooki n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset); if (n < 1) { - err = -EINVAL; pr_warn("kprobe name is invalid: %s\n", func_name); - return libbpf_err_ptr(err); + return -EINVAL; } if (opts.retprobe && offset != 0) { free(func); - err = -EINVAL; pr_warn("kretprobes do not support offset specification\n"); - return libbpf_err_ptr(err); + return -EINVAL; } opts.offset = offset; - link = bpf_program__attach_kprobe_opts(prog, func, &opts); + *link = bpf_program__attach_kprobe_opts(prog, func, &opts); free(func); - return link; + return libbpf_get_error(*link); +} + +static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + const char *spec; + char *pattern; + int n; + + opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe.multi/"); + if (opts.retprobe) + spec = prog->sec_name + sizeof("kretprobe.multi/") - 1; + else + spec = prog->sec_name + sizeof("kprobe.multi/") - 1; + + n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern); + if (n < 1) { + pr_warn("kprobe multi pattern is invalid: %s\n", pattern); + return -EINVAL; + } + + *link = bpf_program__attach_kprobe_multi_opts(prog, pattern, &opts); + free(pattern); + return libbpf_get_error(*link); } static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, @@ -10356,14 +10690,13 @@ struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog, return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL); } -static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) +static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link) { char *sec_name, *tp_cat, *tp_name; - struct bpf_link *link; sec_name = strdup(prog->sec_name); if (!sec_name) - return libbpf_err_ptr(-ENOMEM); + return -ENOMEM; /* extract "tp/<category>/<name>" or "tracepoint/<category>/<name>" */ if (str_has_pfx(prog->sec_name, "tp/")) @@ -10373,14 +10706,14 @@ static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie) tp_name = strchr(tp_cat, '/'); if (!tp_name) { free(sec_name); - return libbpf_err_ptr(-EINVAL); + return -EINVAL; } *tp_name = '\0'; tp_name++; - link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); + *link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); free(sec_name); - return link; + return libbpf_get_error(*link); } struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, @@ -10413,7 +10746,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr return link; } -static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie) +static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link) { static const char *const prefixes[] = { "raw_tp/", @@ -10433,10 +10766,11 @@ static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cooki if (!tp_name) { pr_warn("prog '%s': invalid section name '%s'\n", prog->name, prog->sec_name); - return libbpf_err_ptr(-EINVAL); + return -EINVAL; } - return bpf_program__attach_raw_tracepoint(prog, tp_name); + *link = bpf_program__attach_raw_tracepoint(prog, tp_name); + return libbpf_get_error(link); } /* Common logic for all BPF program types that attach to a btf_id */ @@ -10479,14 +10813,16 @@ struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog) return bpf_program__attach_btf_id(prog); } -static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie) +static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link) { - return bpf_program__attach_trace(prog); + *link = bpf_program__attach_trace(prog); + return libbpf_get_error(*link); } -static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie) +static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link) { - return bpf_program__attach_lsm(prog); + *link = bpf_program__attach_lsm(prog); + return libbpf_get_error(*link); } static struct bpf_link * @@ -10511,7 +10847,7 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_fd; - attach_type = bpf_program__get_expected_attach_type(prog); + attach_type = bpf_program__expected_attach_type(prog); link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts); if (link_fd < 0) { link_fd = -errno; @@ -10615,17 +10951,33 @@ bpf_program__attach_iter(const struct bpf_program *prog, return link; } -static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie) +static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link) { - return bpf_program__attach_iter(prog, NULL); + *link = bpf_program__attach_iter(prog, NULL); + return libbpf_get_error(*link); } struct bpf_link *bpf_program__attach(const struct bpf_program *prog) { - if (!prog->sec_def || !prog->sec_def->attach_fn) - return libbpf_err_ptr(-ESRCH); + struct bpf_link *link = NULL; + int err; + + if (!prog->sec_def || !prog->sec_def->prog_attach_fn) + return libbpf_err_ptr(-EOPNOTSUPP); + + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, &link); + if (err) + return libbpf_err_ptr(err); - return prog->sec_def->attach_fn(prog, prog->sec_def->cookie); + /* When calling bpf_program__attach() explicitly, auto-attach support + * is expected to work, so NULL returned link is considered an error. + * This is different for skeleton's attach, see comment in + * bpf_object__attach_skeleton(). + */ + if (!link) + return libbpf_err_ptr(-EOPNOTSUPP); + + return link; } static int bpf_link__detach_struct_ops(struct bpf_link *link) @@ -10912,7 +11264,7 @@ struct perf_buffer *perf_buffer__new_raw_v0_6_0(int map_fd, size_t page_cnt, { struct perf_buffer_params p = {}; - if (page_cnt == 0 || !attr) + if (!attr) return libbpf_err_ptr(-EINVAL); if (!OPTS_VALID(opts, perf_buffer_raw_opts)) @@ -10953,7 +11305,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, __u32 map_info_len; int err, i, j, n; - if (page_cnt & (page_cnt - 1)) { + if (page_cnt == 0 || (page_cnt & (page_cnt - 1))) { pr_warn("page count should be power of two, but is %zu\n", page_cnt); return ERR_PTR(-EINVAL); @@ -11640,6 +11992,49 @@ int libbpf_num_possible_cpus(void) return tmp_cpus; } +static int populate_skeleton_maps(const struct bpf_object *obj, + struct bpf_map_skeleton *maps, + size_t map_cnt) +{ + int i; + + for (i = 0; i < map_cnt; i++) { + struct bpf_map **map = maps[i].map; + const char *name = maps[i].name; + void **mmaped = maps[i].mmaped; + + *map = bpf_object__find_map_by_name(obj, name); + if (!*map) { + pr_warn("failed to find skeleton map '%s'\n", name); + return -ESRCH; + } + + /* externs shouldn't be pre-setup from user code */ + if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) + *mmaped = (*map)->mmaped; + } + return 0; +} + +static int populate_skeleton_progs(const struct bpf_object *obj, + struct bpf_prog_skeleton *progs, + size_t prog_cnt) +{ + int i; + + for (i = 0; i < prog_cnt; i++) { + struct bpf_program **prog = progs[i].prog; + const char *name = progs[i].name; + + *prog = bpf_object__find_program_by_name(obj, name); + if (!*prog) { + pr_warn("failed to find skeleton program '%s'\n", name); + return -ESRCH; + } + } + return 0; +} + int bpf_object__open_skeleton(struct bpf_object_skeleton *s, const struct bpf_object_open_opts *opts) { @@ -11647,7 +12042,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s, .object_name = s->name, ); struct bpf_object *obj; - int i, err; + int err; /* Attempt to preserve opts->object_name, unless overriden by user * explicitly. Overwriting object name for skeletons is discouraged, @@ -11670,37 +12065,91 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s, } *s->obj = obj; + err = populate_skeleton_maps(obj, s->maps, s->map_cnt); + if (err) { + pr_warn("failed to populate skeleton maps for '%s': %d\n", s->name, err); + return libbpf_err(err); + } - for (i = 0; i < s->map_cnt; i++) { - struct bpf_map **map = s->maps[i].map; - const char *name = s->maps[i].name; - void **mmaped = s->maps[i].mmaped; + err = populate_skeleton_progs(obj, s->progs, s->prog_cnt); + if (err) { + pr_warn("failed to populate skeleton progs for '%s': %d\n", s->name, err); + return libbpf_err(err); + } - *map = bpf_object__find_map_by_name(obj, name); - if (!*map) { - pr_warn("failed to find skeleton map '%s'\n", name); - return libbpf_err(-ESRCH); - } + return 0; +} - /* externs shouldn't be pre-setup from user code */ - if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) - *mmaped = (*map)->mmaped; +int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s) +{ + int err, len, var_idx, i; + const char *var_name; + const struct bpf_map *map; + struct btf *btf; + __u32 map_type_id; + const struct btf_type *map_type, *var_type; + const struct bpf_var_skeleton *var_skel; + struct btf_var_secinfo *var; + + if (!s->obj) + return libbpf_err(-EINVAL); + + btf = bpf_object__btf(s->obj); + if (!btf) { + pr_warn("subskeletons require BTF at runtime (object %s)\n", + bpf_object__name(s->obj)); + return libbpf_err(-errno); } - for (i = 0; i < s->prog_cnt; i++) { - struct bpf_program **prog = s->progs[i].prog; - const char *name = s->progs[i].name; + err = populate_skeleton_maps(s->obj, s->maps, s->map_cnt); + if (err) { + pr_warn("failed to populate subskeleton maps: %d\n", err); + return libbpf_err(err); + } - *prog = bpf_object__find_program_by_name(obj, name); - if (!*prog) { - pr_warn("failed to find skeleton program '%s'\n", name); - return libbpf_err(-ESRCH); - } + err = populate_skeleton_progs(s->obj, s->progs, s->prog_cnt); + if (err) { + pr_warn("failed to populate subskeleton maps: %d\n", err); + return libbpf_err(err); } + for (var_idx = 0; var_idx < s->var_cnt; var_idx++) { + var_skel = &s->vars[var_idx]; + map = *var_skel->map; + map_type_id = bpf_map__btf_value_type_id(map); + map_type = btf__type_by_id(btf, map_type_id); + + if (!btf_is_datasec(map_type)) { + pr_warn("type for map '%1$s' is not a datasec: %2$s", + bpf_map__name(map), + __btf_kind_str(btf_kind(map_type))); + return libbpf_err(-EINVAL); + } + + len = btf_vlen(map_type); + var = btf_var_secinfos(map_type); + for (i = 0; i < len; i++, var++) { + var_type = btf__type_by_id(btf, var->type); + var_name = btf__name_by_offset(btf, var_type->name_off); + if (strcmp(var_name, var_skel->name) == 0) { + *var_skel->addr = map->mmaped + var->offset; + break; + } + } + } return 0; } +void bpf_object__destroy_subskeleton(struct bpf_object_subskeleton *s) +{ + if (!s) + return; + free(s->maps); + free(s->progs); + free(s->vars); + free(s); +} + int bpf_object__load_skeleton(struct bpf_object_skeleton *s) { int i, err; @@ -11766,16 +12215,30 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) continue; /* auto-attaching not supported for this program */ - if (!prog->sec_def || !prog->sec_def->attach_fn) + if (!prog->sec_def || !prog->sec_def->prog_attach_fn) continue; - *link = bpf_program__attach(prog); - err = libbpf_get_error(*link); + /* if user already set the link manually, don't attempt auto-attach */ + if (*link) + continue; + + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, link); if (err) { - pr_warn("failed to auto-attach program '%s': %d\n", + pr_warn("prog '%s': failed to auto-attach: %d\n", bpf_program__name(prog), err); return libbpf_err(err); } + + /* It's possible that for some SEC() definitions auto-attach + * is supported in some cases (e.g., if definition completely + * specifies target information), but is not in other cases. + * SEC("uprobe") is one such case. If user specified target + * binary and function name, such BPF program can be + * auto-attached. But if not, it shouldn't trigger skeleton's + * attach to fail. It should just be skipped. + * attach_fn signals such case with returning 0 (no error) and + * setting link to NULL. + */ } return 0; @@ -11795,6 +12258,9 @@ void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) { + if (!s) + return; + if (s->progs) bpf_object__detach_skeleton(s); if (s->obj) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 8b9bc5e90c2b..05dde85e19a6 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -180,9 +180,11 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts); /* deprecated bpf_object__open variants */ +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open_mem() instead") LIBBPF_API struct bpf_object * bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, const char *name); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open_file() instead") LIBBPF_API struct bpf_object * bpf_object__open_xattr(struct bpf_object_open_attr *attr); @@ -244,8 +246,10 @@ struct bpf_object *bpf_object__next(struct bpf_object *prev); (pos) = (tmp), (tmp) = bpf_object__next(tmp)) typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog); LIBBPF_API int @@ -277,9 +281,10 @@ bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *prog) typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv, bpf_program_clear_priv_t clear_priv); - +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); @@ -420,6 +425,29 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, const char *func_name, const struct bpf_kprobe_opts *opts); +struct bpf_kprobe_multi_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* array of function symbols to attach */ + const char **syms; + /* array of function addresses to attach */ + const unsigned long *addrs; + /* array of user-provided values fetchable through bpf_get_attach_cookie */ + const __u64 *cookies; + /* number of elements in syms/addrs/cookies arrays */ + size_t cnt; + /* create return kprobes */ + bool retprobe; + size_t :0; +}; + +#define bpf_kprobe_multi_opts__last_field retprobe + +LIBBPF_API struct bpf_link * +bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, + const char *pattern, + const struct bpf_kprobe_multi_opts *opts); + struct bpf_uprobe_opts { /* size of this struct, for forward/backward compatiblity */ size_t sz; @@ -591,26 +619,39 @@ LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n); /* * Adjust type of BPF program. Default is kprobe. */ +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_lsm(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__set_type() instead") LIBBPF_API int bpf_program__set_sk_lookup(struct bpf_program *prog); -LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); +LIBBPF_API enum bpf_prog_type bpf_program__type(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); LIBBPF_API enum bpf_attach_type -bpf_program__get_expected_attach_type(const struct bpf_program *prog); +bpf_program__expected_attach_type(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type); @@ -631,18 +672,31 @@ LIBBPF_API int bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, const char *attach_func_name); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_lsm(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_program__type() instead") LIBBPF_API bool bpf_program__is_sk_lookup(const struct bpf_program *prog); /* @@ -706,7 +760,8 @@ bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map); LIBBPF_API int bpf_map__fd(const struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); /* get map definition */ -LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use appropriate getters or setters instead") +const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); /* get map name */ LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); /* get/set map type */ @@ -715,6 +770,7 @@ LIBBPF_API int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type); /* get/set map size (max_entries) */ LIBBPF_API __u32 bpf_map__max_entries(const struct bpf_map *map); LIBBPF_API int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_map__set_max_entries() instead") LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); /* get/set map flags */ LIBBPF_API __u32 bpf_map__map_flags(const struct bpf_map *map); @@ -739,8 +795,10 @@ LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map); LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv); +LIBBPF_DEPRECATED_SINCE(0, 7, "storage via set_priv/priv is deprecated") LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); @@ -757,7 +815,6 @@ LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); */ LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); -LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); LIBBPF_API const char *bpf_map__pin_path(const struct bpf_map *map); LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map); LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); @@ -832,13 +889,42 @@ struct bpf_xdp_set_link_opts { }; #define bpf_xdp_set_link_opts__last_field old_fd +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead") LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead") LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, const struct bpf_xdp_set_link_opts *opts); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query_id() instead") LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query() instead") LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags); +struct bpf_xdp_attach_opts { + size_t sz; + int old_prog_fd; + size_t :0; +}; +#define bpf_xdp_attach_opts__last_field old_prog_fd + +struct bpf_xdp_query_opts { + size_t sz; + __u32 prog_id; /* output */ + __u32 drv_prog_id; /* output */ + __u32 hw_prog_id; /* output */ + __u32 skb_prog_id; /* output */ + __u8 attach_mode; /* output */ + size_t :0; +}; +#define bpf_xdp_query_opts__last_field attach_mode + +LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, + const struct bpf_xdp_attach_opts *opts); +LIBBPF_API int bpf_xdp_detach(int ifindex, __u32 flags, + const struct bpf_xdp_attach_opts *opts); +LIBBPF_API int bpf_xdp_query(int ifindex, int flags, struct bpf_xdp_query_opts *opts); +LIBBPF_API int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id); + /* TC related API */ enum bpf_tc_attach_point { BPF_TC_INGRESS = 1 << 0, @@ -1226,6 +1312,35 @@ LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s); LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s); LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s); +struct bpf_var_skeleton { + const char *name; + struct bpf_map **map; + void **addr; +}; + +struct bpf_object_subskeleton { + size_t sz; /* size of this struct, for forward/backward compatibility */ + + const struct bpf_object *obj; + + int map_cnt; + int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */ + struct bpf_map_skeleton *maps; + + int prog_cnt; + int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */ + struct bpf_prog_skeleton *progs; + + int var_cnt; + int var_skel_sz; /* sizeof(struct bpf_var_skeleton) */ + struct bpf_var_skeleton *vars; +}; + +LIBBPF_API int +bpf_object__open_subskeleton(struct bpf_object_subskeleton *s); +LIBBPF_API void +bpf_object__destroy_subskeleton(struct bpf_object_subskeleton *s); + struct gen_loader_opts { size_t sz; /* size of this struct, for forward/backward compatiblity */ const char *data; @@ -1265,6 +1380,115 @@ LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker); LIBBPF_API void bpf_linker__free(struct bpf_linker *linker); +/* + * Custom handling of BPF program's SEC() definitions + */ + +struct bpf_prog_load_opts; /* defined in bpf.h */ + +/* Called during bpf_object__open() for each recognized BPF program. Callback + * can use various bpf_program__set_*() setters to adjust whatever properties + * are necessary. + */ +typedef int (*libbpf_prog_setup_fn_t)(struct bpf_program *prog, long cookie); + +/* Called right before libbpf performs bpf_prog_load() to load BPF program + * into the kernel. Callback can adjust opts as necessary. + */ +typedef int (*libbpf_prog_prepare_load_fn_t)(struct bpf_program *prog, + struct bpf_prog_load_opts *opts, long cookie); + +/* Called during skeleton attach or through bpf_program__attach(). If + * auto-attach is not supported, callback should return 0 and set link to + * NULL (it's not considered an error during skeleton attach, but it will be + * an error for bpf_program__attach() calls). On error, error should be + * returned directly and link set to NULL. On success, return 0 and set link + * to a valid struct bpf_link. + */ +typedef int (*libbpf_prog_attach_fn_t)(const struct bpf_program *prog, long cookie, + struct bpf_link **link); + +struct libbpf_prog_handler_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* User-provided value that is passed to prog_setup_fn, + * prog_prepare_load_fn, and prog_attach_fn callbacks. Allows user to + * register one set of callbacks for multiple SEC() definitions and + * still be able to distinguish them, if necessary. For example, + * libbpf itself is using this to pass necessary flags (e.g., + * sleepable flag) to a common internal SEC() handler. + */ + long cookie; + /* BPF program initialization callback (see libbpf_prog_setup_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_setup_fn_t prog_setup_fn; + /* BPF program loading callback (see libbpf_prog_prepare_load_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_prepare_load_fn_t prog_prepare_load_fn; + /* BPF program attach callback (see libbpf_prog_attach_fn_t). + * Callback is optional, pass NULL if it's not necessary. + */ + libbpf_prog_attach_fn_t prog_attach_fn; +}; +#define libbpf_prog_handler_opts__last_field prog_attach_fn + +/** + * @brief **libbpf_register_prog_handler()** registers a custom BPF program + * SEC() handler. + * @param sec section prefix for which custom handler is registered + * @param prog_type BPF program type associated with specified section + * @param exp_attach_type Expected BPF attach type associated with specified section + * @param opts optional cookie, callbacks, and other extra options + * @return Non-negative handler ID is returned on success. This handler ID has + * to be passed to *libbpf_unregister_prog_handler()* to unregister such + * custom handler. Negative error code is returned on error. + * + * *sec* defines which SEC() definitions are handled by this custom handler + * registration. *sec* can have few different forms: + * - if *sec* is just a plain string (e.g., "abc"), it will match only + * SEC("abc"). If BPF program specifies SEC("abc/whatever") it will result + * in an error; + * - if *sec* is of the form "abc/", proper SEC() form is + * SEC("abc/something"), where acceptable "something" should be checked by + * *prog_init_fn* callback, if there are additional restrictions; + * - if *sec* is of the form "abc+", it will successfully match both + * SEC("abc") and SEC("abc/whatever") forms; + * - if *sec* is NULL, custom handler is registered for any BPF program that + * doesn't match any of the registered (custom or libbpf's own) SEC() + * handlers. There could be only one such generic custom handler registered + * at any given time. + * + * All custom handlers (except the one with *sec* == NULL) are processed + * before libbpf's own SEC() handlers. It is allowed to "override" libbpf's + * SEC() handlers by registering custom ones for the same section prefix + * (i.e., it's possible to have custom SEC("perf_event/LLC-load-misses") + * handler). + * + * Note, like much of global libbpf APIs (e.g., libbpf_set_print(), + * libbpf_set_strict_mode(), etc)) these APIs are not thread-safe. User needs + * to ensure synchronization if there is a risk of running this API from + * multiple threads simultaneously. + */ +LIBBPF_API int libbpf_register_prog_handler(const char *sec, + enum bpf_prog_type prog_type, + enum bpf_attach_type exp_attach_type, + const struct libbpf_prog_handler_opts *opts); +/** + * @brief *libbpf_unregister_prog_handler()* unregisters previously registered + * custom BPF program SEC() handler. + * @param handler_id handler ID returned by *libbpf_register_prog_handler()* + * after successful registration + * @return 0 on success, negative error code if handler isn't found + * + * Note, like much of global libbpf APIs (e.g., libbpf_set_print(), + * libbpf_set_strict_mode(), etc)) these APIs are not thread-safe. User needs + * to ensure synchronization if there is a risk of running this API from + * multiple threads simultaneously. + */ +LIBBPF_API int libbpf_unregister_prog_handler(int handler_id); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 529783967793..dd35ee58bfaa 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -247,6 +247,7 @@ LIBBPF_0.0.8 { bpf_link_create; bpf_link_update; bpf_map__set_initial_value; + bpf_prog_attach_opts; bpf_program__attach_cgroup; bpf_program__attach_lsm; bpf_program__is_lsm; @@ -423,12 +424,27 @@ LIBBPF_0.6.0 { LIBBPF_0.7.0 { global: bpf_btf_load; + bpf_program__expected_attach_type; bpf_program__log_buf; bpf_program__log_level; bpf_program__set_log_buf; bpf_program__set_log_level; + bpf_program__type; + bpf_xdp_attach; + bpf_xdp_detach; + bpf_xdp_query; + bpf_xdp_query_id; libbpf_probe_bpf_helper; libbpf_probe_bpf_map_type; libbpf_probe_bpf_prog_type; libbpf_set_memlock_rlim_max; -}; +} LIBBPF_0.6.0; + +LIBBPF_0.8.0 { + global: + bpf_object__destroy_subskeleton; + bpf_object__open_subskeleton; + libbpf_register_prog_handler; + libbpf_unregister_prog_handler; + bpf_program__attach_kprobe_multi_opts; +} LIBBPF_0.7.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 1565679eb432..b6247dc7f8eb 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -92,6 +92,9 @@ # define offsetofend(TYPE, FIELD) \ (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) #endif +#ifndef __alias +#define __alias(symbol) __attribute__((alias(#symbol))) +#endif /* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is * a string literal known at compilation time or char * pointer known only at @@ -446,6 +449,11 @@ __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name, extern enum libbpf_strict_mode libbpf_mode; +typedef int (*kallsyms_cb_t)(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx); + +int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *arg); + /* handle direct returned errors */ static inline int libbpf_err(int ret) { @@ -526,4 +534,13 @@ static inline int ensure_good_fd(int fd) return fd; } +/* The following two functions are exposed to bpftool */ +int bpf_core_add_cands(struct bpf_core_cand *local_cand, + size_t local_essent_len, + const struct btf *targ_btf, + const char *targ_btf_name, + int targ_start_id, + struct bpf_core_cand_list *cands); +void bpf_core_free_cands(struct bpf_core_cand_list *cands); + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index 79131f761a27..d7bcbd01f66f 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -54,6 +54,10 @@ enum libbpf_strict_mode { * * Note, in this mode the program pin path will be based on the * function name instead of section name. + * + * Additionally, routines in the .text section are always considered + * sub-programs. Legacy behavior allows for a single routine in .text + * to be a program. */ LIBBPF_STRICT_SEC_NAME = 0x04, /* @@ -73,6 +77,11 @@ enum libbpf_strict_mode { * operation. */ LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10, + /* + * Error out on any SEC("maps") map definition, which are deprecated + * in favor of BTF-defined map definitions in SEC(".maps"). + */ + LIBBPF_STRICT_MAP_DEFINITIONS = 0x20, __LIBBPF_STRICT_LAST, }; @@ -81,6 +90,23 @@ LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); #define DECLARE_LIBBPF_OPTS LIBBPF_OPTS +/* "Discouraged" APIs which don't follow consistent libbpf naming patterns. + * They are normally a trivial aliases or wrappers for proper APIs and are + * left to minimize unnecessary disruption for users of libbpf. But they + * shouldn't be used going forward. + */ + +struct bpf_program; +struct bpf_map; +struct btf; +struct btf_ext; + +LIBBPF_API enum bpf_prog_type bpf_program__get_type(const struct bpf_program *prog); +LIBBPF_API enum bpf_attach_type bpf_program__get_expected_attach_type(const struct bpf_program *prog); +LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); +LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); +LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index 0fefefc3500b..61f2039404b6 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 0 -#define LIBBPF_MINOR_VERSION 7 +#define LIBBPF_MINOR_VERSION 8 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 39f25e09b51e..cbc8967d5402 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -87,29 +87,75 @@ enum { NL_DONE, }; +static int netlink_recvmsg(int sock, struct msghdr *mhdr, int flags) +{ + int len; + + do { + len = recvmsg(sock, mhdr, flags); + } while (len < 0 && (errno == EINTR || errno == EAGAIN)); + + if (len < 0) + return -errno; + return len; +} + +static int alloc_iov(struct iovec *iov, int len) +{ + void *nbuf; + + nbuf = realloc(iov->iov_base, len); + if (!nbuf) + return -ENOMEM; + + iov->iov_base = nbuf; + iov->iov_len = len; + return 0; +} + static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq, __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn, void *cookie) { + struct iovec iov = {}; + struct msghdr mhdr = { + .msg_iov = &iov, + .msg_iovlen = 1, + }; bool multipart = true; struct nlmsgerr *err; struct nlmsghdr *nh; - char buf[4096]; int len, ret; + ret = alloc_iov(&iov, 4096); + if (ret) + goto done; + while (multipart) { start: multipart = false; - len = recv(sock, buf, sizeof(buf), 0); + len = netlink_recvmsg(sock, &mhdr, MSG_PEEK | MSG_TRUNC); if (len < 0) { - ret = -errno; + ret = len; + goto done; + } + + if (len > iov.iov_len) { + ret = alloc_iov(&iov, len); + if (ret) + goto done; + } + + len = netlink_recvmsg(sock, &mhdr, 0); + if (len < 0) { + ret = len; goto done; } if (len == 0) break; - for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); + for (nh = (struct nlmsghdr *)iov.iov_base; NLMSG_OK(nh, len); nh = NLMSG_NEXT(nh, len)) { if (nh->nlmsg_pid != nl_pid) { ret = -LIBBPF_ERRNO__WRNGPID; @@ -130,7 +176,8 @@ start: libbpf_nla_dump_errormsg(nh); goto done; case NLMSG_DONE: - return 0; + ret = 0; + goto done; default: break; } @@ -142,15 +189,17 @@ start: case NL_NEXT: goto start; case NL_DONE: - return 0; + ret = 0; + goto done; default: - return ret; + goto done; } } } } ret = 0; done: + free(iov.iov_base); return ret; } @@ -217,6 +266,28 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); } +int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts) +{ + int old_prog_fd, err; + + if (!OPTS_VALID(opts, bpf_xdp_attach_opts)) + return libbpf_err(-EINVAL); + + old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + if (old_prog_fd) + flags |= XDP_FLAGS_REPLACE; + else + old_prog_fd = -1; + + err = __bpf_set_link_xdp_fd_replace(ifindex, prog_fd, old_prog_fd, flags); + return libbpf_err(err); +} + +int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *opts) +{ + return bpf_xdp_attach(ifindex, -1, flags, opts); +} + int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, const struct bpf_xdp_set_link_opts *opts) { @@ -303,69 +374,98 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } -int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, - size_t info_size, __u32 flags) +int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) { - struct xdp_id_md xdp_id = {}; - __u32 mask; - int ret; struct libbpf_nla_req req = { .nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), .nh.nlmsg_type = RTM_GETLINK, .nh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, .ifinfo.ifi_family = AF_PACKET, }; + struct xdp_id_md xdp_id = {}; + int err; - if (flags & ~XDP_FLAGS_MASK || !info_size) + if (!OPTS_VALID(opts, bpf_xdp_query_opts)) + return libbpf_err(-EINVAL); + + if (xdp_flags & ~XDP_FLAGS_MASK) return libbpf_err(-EINVAL); /* Check whether the single {HW,DRV,SKB} mode is set */ - flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE); - mask = flags - 1; - if (flags && flags & mask) + xdp_flags &= XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE; + if (xdp_flags & (xdp_flags - 1)) return libbpf_err(-EINVAL); xdp_id.ifindex = ifindex; - xdp_id.flags = flags; + xdp_id.flags = xdp_flags; - ret = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, + err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, get_xdp_info, &xdp_id); - if (!ret) { - size_t sz = min(info_size, sizeof(xdp_id.info)); + if (err) + return libbpf_err(err); - memcpy(info, &xdp_id.info, sz); - memset((void *) info + sz, 0, info_size - sz); - } + OPTS_SET(opts, prog_id, xdp_id.info.prog_id); + OPTS_SET(opts, drv_prog_id, xdp_id.info.drv_prog_id); + OPTS_SET(opts, hw_prog_id, xdp_id.info.hw_prog_id); + OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id); + OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode); - return libbpf_err(ret); + return 0; } -static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags) +int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, + size_t info_size, __u32 flags) { - flags &= XDP_FLAGS_MODES; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + size_t sz; + int err; - if (info->attach_mode != XDP_ATTACHED_MULTI && !flags) - return info->prog_id; - if (flags & XDP_FLAGS_DRV_MODE) - return info->drv_prog_id; - if (flags & XDP_FLAGS_HW_MODE) - return info->hw_prog_id; - if (flags & XDP_FLAGS_SKB_MODE) - return info->skb_prog_id; + if (!info_size) + return libbpf_err(-EINVAL); + + err = bpf_xdp_query(ifindex, flags, &opts); + if (err) + return libbpf_err(err); + + /* struct xdp_link_info field layout matches struct bpf_xdp_query_opts + * layout after sz field + */ + sz = min(info_size, offsetofend(struct xdp_link_info, attach_mode)); + memcpy(info, &opts.prog_id, sz); + memset((void *)info + sz, 0, info_size - sz); return 0; } -int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id) { - struct xdp_link_info info; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); int ret; - ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags); - if (!ret) - *prog_id = get_xdp_id(&info, flags); + ret = bpf_xdp_query(ifindex, flags, &opts); + if (ret) + return libbpf_err(ret); - return libbpf_err(ret); + flags &= XDP_FLAGS_MODES; + + if (opts.attach_mode != XDP_ATTACHED_MULTI && !flags) + *prog_id = opts.prog_id; + else if (flags & XDP_FLAGS_DRV_MODE) + *prog_id = opts.drv_prog_id; + else if (flags & XDP_FLAGS_HW_MODE) + *prog_id = opts.hw_prog_id; + else if (flags & XDP_FLAGS_SKB_MODE) + *prog_id = opts.skb_prog_id; + else + *prog_id = 0; + + return 0; +} + + +int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +{ + return bpf_xdp_query_id(ifindex, flags, prog_id); } typedef int (*qdisc_config_t)(struct libbpf_nla_req *req); diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index 910865e29edc..f946f23eab20 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -775,31 +775,6 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, return 0; } -struct bpf_core_relo_res -{ - /* expected value in the instruction, unless validate == false */ - __u32 orig_val; - /* new value that needs to be patched up to */ - __u32 new_val; - /* relocation unsuccessful, poison instruction, but don't fail load */ - bool poison; - /* some relocations can't be validated against orig_val */ - bool validate; - /* for field byte offset relocations or the forms: - * *(T *)(rX + <off>) = rY - * rX = *(T *)(rY + <off>), - * we remember original and resolved field size to adjust direct - * memory loads of pointers and integers; this is necessary for 32-bit - * host kernel architectures, but also allows to automatically - * relocate fields that were resized from, e.g., u32 to u64, etc. - */ - bool fail_memsz_adjust; - __u32 orig_sz; - __u32 orig_type_id; - __u32 new_sz; - __u32 new_type_id; -}; - /* Calculate original and target relocation values, given local and target * specs and relocation kind. These values are calculated for each candidate. * If there are multiple candidates, resulting values should all be consistent @@ -951,9 +926,9 @@ static int insn_bytes_to_bpf_size(__u32 sz) * 5. *(T *)(rX + <off>) = rY, where T is one of {u8, u16, u32, u64}; * 6. *(T *)(rX + <off>) = <imm>, where T is one of {u8, u16, u32, u64}. */ -static int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn, - int insn_idx, const struct bpf_core_relo *relo, - int relo_idx, const struct bpf_core_relo_res *res) +int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn, + int insn_idx, const struct bpf_core_relo *relo, + int relo_idx, const struct bpf_core_relo_res *res) { __u32 orig_val, new_val; __u8 class; @@ -1128,7 +1103,7 @@ static void bpf_core_dump_spec(const char *prog_name, int level, const struct bp } /* - * CO-RE relocate single instruction. + * Calculate CO-RE relocation target result. * * The outline and important points of the algorithm: * 1. For given local type, find corresponding candidate target types. @@ -1177,18 +1152,18 @@ static void bpf_core_dump_spec(const char *prog_name, int level, const struct bp * between multiple relocations for the same type ID and is updated as some * of the candidates are pruned due to structural incompatibility. */ -int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, - int insn_idx, - const struct bpf_core_relo *relo, - int relo_idx, - const struct btf *local_btf, - struct bpf_core_cand_list *cands, - struct bpf_core_spec *specs_scratch) +int bpf_core_calc_relo_insn(const char *prog_name, + const struct bpf_core_relo *relo, + int relo_idx, + const struct btf *local_btf, + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch, + struct bpf_core_relo_res *targ_res) { struct bpf_core_spec *local_spec = &specs_scratch[0]; struct bpf_core_spec *cand_spec = &specs_scratch[1]; struct bpf_core_spec *targ_spec = &specs_scratch[2]; - struct bpf_core_relo_res cand_res, targ_res; + struct bpf_core_relo_res cand_res; const struct btf_type *local_type; const char *local_name; __u32 local_id; @@ -1223,12 +1198,12 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */ if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) { /* bpf_insn's imm value could get out of sync during linking */ - memset(&targ_res, 0, sizeof(targ_res)); - targ_res.validate = false; - targ_res.poison = false; - targ_res.orig_val = local_spec->root_type_id; - targ_res.new_val = local_spec->root_type_id; - goto patch_insn; + memset(targ_res, 0, sizeof(*targ_res)); + targ_res->validate = false; + targ_res->poison = false; + targ_res->orig_val = local_spec->root_type_id; + targ_res->new_val = local_spec->root_type_id; + return 0; } /* libbpf doesn't support candidate search for anonymous types */ @@ -1262,7 +1237,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, return err; if (j == 0) { - targ_res = cand_res; + *targ_res = cand_res; *targ_spec = *cand_spec; } else if (cand_spec->bit_offset != targ_spec->bit_offset) { /* if there are many field relo candidates, they @@ -1272,7 +1247,8 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, prog_name, relo_idx, cand_spec->bit_offset, targ_spec->bit_offset); return -EINVAL; - } else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) { + } else if (cand_res.poison != targ_res->poison || + cand_res.new_val != targ_res->new_val) { /* all candidates should result in the same relocation * decision and value, otherwise it's dangerous to * proceed due to ambiguity @@ -1280,7 +1256,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %u != %s %u\n", prog_name, relo_idx, cand_res.poison ? "failure" : "success", cand_res.new_val, - targ_res.poison ? "failure" : "success", targ_res.new_val); + targ_res->poison ? "failure" : "success", targ_res->new_val); return -EINVAL; } @@ -1314,19 +1290,10 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, prog_name, relo_idx); /* calculate single target relo result explicitly */ - err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, &targ_res); + err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, targ_res); if (err) return err; } -patch_insn: - /* bpf_core_patch_insn() should know how to handle missing targ_spec */ - err = bpf_core_patch_insn(prog_name, insn, insn_idx, relo, relo_idx, &targ_res); - if (err) { - pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n", - prog_name, relo_idx, relo->insn_off / 8, err); - return -EINVAL; - } - return 0; } diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h index 17799819ad7c..a28bf3711ce2 100644 --- a/tools/lib/bpf/relo_core.h +++ b/tools/lib/bpf/relo_core.h @@ -44,14 +44,44 @@ struct bpf_core_spec { __u32 bit_offset; }; -int bpf_core_apply_relo_insn(const char *prog_name, - struct bpf_insn *insn, int insn_idx, - const struct bpf_core_relo *relo, int relo_idx, - const struct btf *local_btf, - struct bpf_core_cand_list *cands, - struct bpf_core_spec *specs_scratch); +struct bpf_core_relo_res { + /* expected value in the instruction, unless validate == false */ + __u32 orig_val; + /* new value that needs to be patched up to */ + __u32 new_val; + /* relocation unsuccessful, poison instruction, but don't fail load */ + bool poison; + /* some relocations can't be validated against orig_val */ + bool validate; + /* for field byte offset relocations or the forms: + * *(T *)(rX + <off>) = rY + * rX = *(T *)(rY + <off>), + * we remember original and resolved field size to adjust direct + * memory loads of pointers and integers; this is necessary for 32-bit + * host kernel architectures, but also allows to automatically + * relocate fields that were resized from, e.g., u32 to u64, etc. + */ + bool fail_memsz_adjust; + __u32 orig_sz; + __u32 orig_type_id; + __u32 new_sz; + __u32 new_type_id; +}; + int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id); size_t bpf_core_essential_name_len(const char *name); + +int bpf_core_calc_relo_insn(const char *prog_name, + const struct bpf_core_relo *relo, int relo_idx, + const struct btf *local_btf, + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch, + struct bpf_core_relo_res *targ_res); + +int bpf_core_patch_insn(const char *prog_name, struct bpf_insn *insn, + int insn_idx, const struct bpf_core_relo *relo, + int relo_idx, const struct bpf_core_relo_res *res); + #endif diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 0b84d8e6b72a..bd6f4505e7b1 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -3,9 +3,19 @@ #ifndef __SKEL_INTERNAL_H #define __SKEL_INTERNAL_H +#ifdef __KERNEL__ +#include <linux/fdtable.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/slab.h> +#include <linux/bpf.h> +#else #include <unistd.h> #include <sys/syscall.h> #include <sys/mman.h> +#include <stdlib.h> +#include "bpf.h" +#endif #ifndef __NR_bpf # if defined(__mips__) && defined(_ABIO32) @@ -25,24 +35,23 @@ * requested during loader program generation. */ struct bpf_map_desc { - union { - /* input for the loader prog */ - struct { - __aligned_u64 initial_value; - __u32 max_entries; - }; - /* output of the loader prog */ - struct { - int map_fd; - }; - }; + /* output of the loader prog */ + int map_fd; + /* input for the loader prog */ + __u32 max_entries; + __aligned_u64 initial_value; }; struct bpf_prog_desc { int prog_fd; }; +enum { + BPF_SKEL_KERNEL = (1ULL << 0), +}; + struct bpf_loader_ctx { - size_t sz; + __u32 sz; + __u32 flags; __u32 log_level; __u32 log_size; __u64 log_buf; @@ -57,12 +66,144 @@ struct bpf_load_and_run_opts { const char *errstr; }; +long bpf_sys_bpf(__u32 cmd, void *attr, __u32 attr_size); + static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, unsigned int size) { +#ifdef __KERNEL__ + return bpf_sys_bpf(cmd, attr, size); +#else return syscall(__NR_bpf, cmd, attr, size); +#endif +} + +#ifdef __KERNEL__ +static inline int close(int fd) +{ + return close_fd(fd); +} + +static inline void *skel_alloc(size_t size) +{ + struct bpf_loader_ctx *ctx = kzalloc(size, GFP_KERNEL); + + if (!ctx) + return NULL; + ctx->flags |= BPF_SKEL_KERNEL; + return ctx; +} + +static inline void skel_free(const void *p) +{ + kfree(p); +} + +/* skel->bss/rodata maps are populated the following way: + * + * For kernel use: + * skel_prep_map_data() allocates kernel memory that kernel module can directly access. + * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value. + * The loader program will perform probe_read_kernel() from maps.rodata.initial_value. + * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and + * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree + * is not nessary. + * + * For user space: + * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly. + * Generated lskel stores the pointer in skel->rodata and in skel->maps.rodata.initial_value. + * The loader program will perform copy_from_user() from maps.rodata.initial_value. + * skel_finalize_map_data() remaps bpf array map value from the kernel memory into + * skel->rodata address. + * + * The "bpftool gen skeleton -L" command generates lskel.h that is suitable for + * both kernel and user space. The generated loader program does + * either bpf_probe_read_kernel() or bpf_copy_from_user() from initial_value + * depending on bpf_loader_ctx->flags. + */ +static inline void skel_free_map_data(void *p, __u64 addr, size_t sz) +{ + if (addr != ~0ULL) + kvfree(p); + /* When addr == ~0ULL the 'p' points to + * ((struct bpf_array *)map)->value. See skel_finalize_map_data. + */ +} + +static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz) +{ + void *addr; + + addr = kvmalloc(val_sz, GFP_KERNEL); + if (!addr) + return NULL; + memcpy(addr, val, val_sz); + return addr; +} + +static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd) +{ + struct bpf_map *map; + void *addr = NULL; + + kvfree((void *) (long) *init_val); + *init_val = ~0ULL; + + /* At this point bpf_load_and_run() finished without error and + * 'fd' is a valid bpf map FD. All sanity checks below should succeed. + */ + map = bpf_map_get(fd); + if (IS_ERR(map)) + return NULL; + if (map->map_type != BPF_MAP_TYPE_ARRAY) + goto out; + addr = ((struct bpf_array *)map)->value; + /* the addr stays valid, since FD is not closed */ +out: + bpf_map_put(map); + return addr; +} + +#else + +static inline void *skel_alloc(size_t size) +{ + return calloc(1, size); +} + +static inline void skel_free(void *p) +{ + free(p); +} + +static inline void skel_free_map_data(void *p, __u64 addr, size_t sz) +{ + munmap(p, sz); +} + +static inline void *skel_prep_map_data(const void *val, size_t mmap_sz, size_t val_sz) +{ + void *addr; + + addr = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (addr == (void *) -1) + return NULL; + memcpy(addr, val, val_sz); + return addr; } +static inline void *skel_finalize_map_data(__u64 *init_val, size_t mmap_sz, int flags, int fd) +{ + void *addr; + + addr = mmap((void *) (long) *init_val, mmap_sz, flags, MAP_SHARED | MAP_FIXED, fd, 0); + if (addr == (void *) -1) + return NULL; + return addr; +} +#endif + static inline int skel_closenz(int fd) { if (fd > 0) @@ -70,22 +211,94 @@ static inline int skel_closenz(int fd) return -EINVAL; } +#ifndef offsetofend +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER))) +#endif + +static inline int skel_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries) +{ + const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + + attr.map_type = map_type; + strncpy(attr.map_name, map_name, sizeof(attr.map_name)); + attr.key_size = key_size; + attr.value_size = value_size; + attr.max_entries = max_entries; + + return skel_sys_bpf(BPF_MAP_CREATE, &attr, attr_sz); +} + +static inline int skel_map_update_elem(int fd, const void *key, + const void *value, __u64 flags) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = (long) key; + attr.value = (long) value; + attr.flags = flags; + + return skel_sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz); +} + +static inline int skel_raw_tracepoint_open(const char *name, int prog_fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint.prog_fd); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.raw_tracepoint.name = (long) name; + attr.raw_tracepoint.prog_fd = prog_fd; + + return skel_sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz); +} + +static inline int skel_link_create(int prog_fd, int target_fd, + enum bpf_attach_type attach_type) +{ + const size_t attr_sz = offsetofend(union bpf_attr, link_create.iter_info_len); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.link_create.prog_fd = prog_fd; + attr.link_create.target_fd = target_fd; + attr.link_create.attach_type = attach_type; + + return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz); +} + +#ifdef __KERNEL__ +#define set_err +#else +#define set_err err = -errno +#endif + static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) { int map_fd = -1, prog_fd = -1, key = 0, err; union bpf_attr attr; - map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1, NULL); + err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1); if (map_fd < 0) { opts->errstr = "failed to create loader map"; - err = -errno; + set_err; goto out; } - err = bpf_map_update_elem(map_fd, &key, opts->data, 0); + err = skel_map_update_elem(map_fd, &key, opts->data, 0); if (err < 0) { opts->errstr = "failed to update loader map"; - err = -errno; + set_err; goto out; } @@ -100,10 +313,10 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) attr.log_size = opts->ctx->log_size; attr.log_buf = opts->ctx->log_buf; attr.prog_flags = BPF_F_SLEEPABLE; - prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); + err = prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); if (prog_fd < 0) { opts->errstr = "failed to load loader prog"; - err = -errno; + set_err; goto out; } @@ -115,10 +328,12 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) if (err < 0 || (int)attr.test.retval < 0) { opts->errstr = "failed to execute loader prog"; if (err < 0) { - err = -errno; + set_err; } else { err = (int)attr.test.retval; +#ifndef __KERNEL__ errno = -err; +#endif } goto out; } diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index edafe56664f3..af136f73b09d 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -481,8 +481,8 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) BPF_EMIT_CALL(BPF_FUNC_redirect_map), BPF_EXIT_INSN(), }; - size_t insns_cnt[] = {sizeof(prog) / sizeof(struct bpf_insn), - sizeof(prog_redirect_flags) / sizeof(struct bpf_insn), + size_t insns_cnt[] = {ARRAY_SIZE(prog), + ARRAY_SIZE(prog_redirect_flags), }; struct bpf_insn *progs[] = {prog, prog_redirect_flags}; enum xsk_prog option = get_xsk_prog(); @@ -1193,12 +1193,23 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, int xsk_umem__delete(struct xsk_umem *umem) { + struct xdp_mmap_offsets off; + int err; + if (!umem) return 0; if (umem->refcount) return -EBUSY; + err = xsk_get_mmap_offsets(umem->fd, &off); + if (!err && umem->fill_save && umem->comp_save) { + munmap(umem->fill_save->ring - off.fr.desc, + off.fr.desc + umem->config.fill_size * sizeof(__u64)); + munmap(umem->comp_save->ring - off.cr.desc, + off.cr.desc + umem->config.comp_size * sizeof(__u64)); + } + close(umem->fd); free(umem); diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 581f9ffb4237..1973a18c096b 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -3,11 +3,7 @@ #define __LIBPERF_INTERNAL_CPUMAP_H #include <linux/refcount.h> - -/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */ -struct perf_cpu { - int cpu; -}; +#include <perf/cpumap.h> /** * A sized, reference counted, sorted array of integers representing CPU diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 15b8faafd615..4a2edbdb5e2b 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -7,6 +7,11 @@ #include <stdio.h> #include <stdbool.h> +/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */ +struct perf_cpu { + int cpu; +}; + LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 75ee385fb078..e7758707cadd 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -240,7 +240,7 @@ struct id_index_entry { struct perf_record_id_index { struct perf_event_header header; __u64 nr; - struct id_index_entry entries[0]; + struct id_index_entry entries[]; }; struct perf_record_auxtrace_info { diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map index 93696affda2e..6fa0d651576b 100644 --- a/tools/lib/perf/libperf.map +++ b/tools/lib/perf/libperf.map @@ -2,6 +2,7 @@ LIBPERF_0.0.1 { global: libperf_init; perf_cpu_map__dummy_new; + perf_cpu_map__default_new; perf_cpu_map__get; perf_cpu_map__put; perf_cpu_map__new; diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c index d39378eaf897..87b0510a556f 100644 --- a/tools/lib/perf/tests/test-cpumap.c +++ b/tools/lib/perf/tests/test-cpumap.c @@ -14,6 +14,8 @@ static int libperf_print(enum libperf_print_level level, int test_cpumap(int argc, char **argv) { struct perf_cpu_map *cpus; + struct perf_cpu cpu; + int idx; __T_START; @@ -27,6 +29,15 @@ int test_cpumap(int argc, char **argv) perf_cpu_map__put(cpus); perf_cpu_map__put(cpus); + cpus = perf_cpu_map__default_new(); + if (!cpus) + return -1; + + perf_cpu_map__for_each_cpu(cpu, idx, cpus) + __T("wrong cpu number", cpu.cpu != -1); + + perf_cpu_map__put(cpus); + __T_END; return tests_failed == 0 ? 0 : -1; } diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c index b3479dfa9a1c..fa854c83b7e7 100644 --- a/tools/lib/perf/tests/test-evlist.c +++ b/tools/lib/perf/tests/test-evlist.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #define _GNU_SOURCE // needed for sched.h to get sched_[gs]etaffinity and CPU_(ZERO,SET) +#include <inttypes.h> #include <sched.h> #include <stdio.h> #include <stdarg.h> @@ -526,12 +527,12 @@ static int test_stat_multiplexing(void) min = counts[0].val; for (i = 0; i < EVENT_NUM; i++) { - __T_VERBOSE("Event %2d -- Raw count = %lu, run = %lu, enable = %lu\n", + __T_VERBOSE("Event %2d -- Raw count = %" PRIu64 ", run = %" PRIu64 ", enable = %" PRIu64 "\n", i, counts[i].val, counts[i].run, counts[i].ena); perf_counts_values__scale(&counts[i], true, &scaled); if (scaled == 1) { - __T_VERBOSE("\t Scaled count = %lu (%.2lf%%, %lu/%lu)\n", + __T_VERBOSE("\t Scaled count = %" PRIu64 " (%.2lf%%, %" PRIu64 "/%" PRIu64 ")\n", counts[i].val, (double)counts[i].run / (double)counts[i].ena * 100.0, counts[i].run, counts[i].ena); diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h index 794a375dad36..b2aec04fce8f 100644 --- a/tools/lib/subcmd/subcmd-util.h +++ b/tools/lib/subcmd/subcmd-util.h @@ -50,15 +50,8 @@ static NORETURN inline void die(const char *err, ...) static inline void *xrealloc(void *ptr, size_t size) { void *ret = realloc(ptr, size); - if (!ret && !size) - ret = realloc(ptr, 1); - if (!ret) { - ret = realloc(ptr, size); - if (!ret && !size) - ret = realloc(ptr, 1); - if (!ret) - die("Out of memory, realloc failed"); - } + if (!ret) + die("Out of memory, realloc failed"); return ret; } |