diff options
Diffstat (limited to '')
80 files changed, 12032 insertions, 5991 deletions
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile index a13e9c7f1fc5..e21e1b40b525 100644 --- a/tools/lib/api/Makefile +++ b/tools/lib/api/Makefile @@ -60,7 +60,7 @@ $(LIBFILE): $(API_IN) clean: $(call QUIET_CLEAN, libapi) $(RM) $(LIBFILE); \ - find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) + find $(or $(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) FORCE: diff --git a/tools/lib/api/fd/array.c b/tools/lib/api/fd/array.c index 5e6cb9debe37..f0f195207fca 100644 --- a/tools/lib/api/fd/array.c +++ b/tools/lib/api/fd/array.c @@ -88,6 +88,23 @@ int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags return pos; } +int fdarray__dup_entry_from(struct fdarray *fda, int pos, struct fdarray *from) +{ + struct pollfd *entry; + int npos; + + if (pos >= from->nr) + return -EINVAL; + + entry = &from->entries[pos]; + + npos = fdarray__add(fda, entry->fd, entry->events, from->priv[pos].flags); + if (npos >= 0) + fda->priv[npos] = from->priv[pos]; + + return npos; +} + int fdarray__filter(struct fdarray *fda, short revents, void (*entry_destructor)(struct fdarray *fda, int fd, void *arg), void *arg) diff --git a/tools/lib/api/fd/array.h b/tools/lib/api/fd/array.h index 7fcf21a33c0c..5c01f7b05dfb 100644 --- a/tools/lib/api/fd/array.h +++ b/tools/lib/api/fd/array.h @@ -31,8 +31,9 @@ struct fdarray { }; enum fdarray_flags { - fdarray_flag__default = 0x00000000, - fdarray_flag__nonfilterable = 0x00000001 + fdarray_flag__default = 0x00000000, + fdarray_flag__nonfilterable = 0x00000001, + fdarray_flag__non_perf_event = 0x00000002, }; void fdarray__init(struct fdarray *fda, int nr_autogrow); @@ -42,6 +43,7 @@ struct fdarray *fdarray__new(int nr_alloc, int nr_autogrow); void fdarray__delete(struct fdarray *fda); int fdarray__add(struct fdarray *fda, int fd, short revents, enum fdarray_flags flags); +int fdarray__dup_entry_from(struct fdarray *fda, int pos, struct fdarray *from); int fdarray__poll(struct fdarray *fda, int timeout); int fdarray__filter(struct fdarray *fda, short revents, void (*entry_destructor)(struct fdarray *fda, int fd, void *arg), diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index db466ef7be9d..c3e4871967bc 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -5,9 +5,9 @@ */ #include <linux/bitmap.h> -int __bitmap_weight(const unsigned long *bitmap, int bits) +unsigned int __bitmap_weight(const unsigned long *bitmap, int bits) { - int k, w = 0, lim = bits/BITS_PER_LONG; + unsigned int k, w = 0, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; k++) w += hweight_long(bitmap[k]); @@ -57,7 +57,7 @@ size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits, return ret; } -int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; @@ -72,31 +72,31 @@ int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, return result != 0; } -int __bitmap_equal(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int bits) +bool __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] != bitmap2[k]) - return 0; + return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) - return 0; + return false; - return 1; + return true; } -int __bitmap_intersects(const unsigned long *bitmap1, - const unsigned long *bitmap2, unsigned int bits) +bool __bitmap_intersects(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & bitmap2[k]) - return 1; + return true; if (bits % BITS_PER_LONG) if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) - return 1; - return 0; + return true; + return false; } diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 94f0a146bb7b..5a3dfb56d78f 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,3 +1,4 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ - netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \ - btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o + netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ + btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ + usdt.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index b393b5e82380..4c904ef0b47e 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -60,7 +60,7 @@ ifndef VERBOSE VERBOSE = 0 endif -INCLUDES = -I$(if $(OUTPUT),$(OUTPUT),.) \ +INCLUDES = -I$(or $(OUTPUT),.) \ -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi export prefix libdir src obj @@ -84,11 +84,13 @@ else endif # Append required CFLAGS +override CFLAGS += -std=gnu89 override CFLAGS += $(EXTRA_WARNINGS) -Wno-switch-enum override CFLAGS += -Werror -Wall override CFLAGS += $(INCLUDES) override CFLAGS += -fvisibility=hidden override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 +override CFLAGS += $(CLANG_CROSS_FLAGS) # flags specific for shared library SHLIB_FLAGS := -DSHARED -fPIC @@ -125,11 +127,11 @@ TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags) GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ sed 's/\[.*\]//' | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \ 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) @@ -161,7 +163,7 @@ $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(VERSION_SCRIPT) - $(QUIET_LINK)$(CC) $(LDFLAGS) \ + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) \ --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ -Wl,--version-script=$(VERSION_SCRIPT) $< -lelf -lz -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so @@ -192,7 +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 \ @@ -235,9 +237,9 @@ install_lib: all_cmd $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) -SRC_HDRS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \ +SRC_HDRS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h \ bpf_helpers.h bpf_tracing.h bpf_endian.h bpf_core_read.h \ - skel_internal.h libbpf_version.h + skel_internal.h libbpf_version.h usdt.bpf.h GEN_HDRS := $(BPF_GENERATED) INSTALL_PFX := $(DESTDIR)$(prefix)/include/bpf diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 725701235fd8..1d49a0352836 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -28,6 +28,10 @@ #include <asm/unistd.h> #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" #include "libbpf.h" #include "libbpf_internal.h" @@ -49,6 +53,12 @@ # define __NR_bpf 351 # elif defined(__arc__) # define __NR_bpf 280 +# elif defined(__mips__) && defined(_ABIO32) +# define __NR_bpf 4355 +# elif defined(__mips__) && defined(_ABIN32) +# define __NR_bpf 6319 +# elif defined(__mips__) && defined(_ABI64) +# define __NR_bpf 5315 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif @@ -74,158 +84,122 @@ static inline int sys_bpf_fd(enum bpf_cmd cmd, union bpf_attr *attr, return ensure_good_fd(fd); } -static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size) +int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts) { - int retries = 5; int fd; do { fd = sys_bpf_fd(BPF_PROG_LOAD, attr, size); - } while (fd < 0 && errno == EAGAIN && retries-- > 0); + } while (fd < 0 && errno == EAGAIN && --attempts > 0); return fd; } -int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr) +/* Probe whether kernel switched from memlock-based (RLIMIT_MEMLOCK) to + * memcg-based memory accounting for BPF maps and progs. This was done in [0]. + * We use the support for bpf_ktime_get_coarse_ns() helper, which was added in + * the same 5.11 Linux release ([1]), to detect memcg-based accounting for BPF. + * + * [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/ + * [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper") + */ +int probe_memcg_account(void) { + const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd); + struct bpf_insn insns[] = { + BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); union bpf_attr attr; - int fd; + int prog_fd; - memset(&attr, '\0', sizeof(attr)); - - attr.map_type = create_attr->map_type; - attr.key_size = create_attr->key_size; - attr.value_size = create_attr->value_size; - attr.max_entries = create_attr->max_entries; - attr.map_flags = create_attr->map_flags; - if (create_attr->name) - memcpy(attr.map_name, create_attr->name, - min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1)); - attr.numa_node = create_attr->numa_node; - attr.btf_fd = create_attr->btf_fd; - attr.btf_key_type_id = create_attr->btf_key_type_id; - attr.btf_value_type_id = create_attr->btf_value_type_id; - attr.map_ifindex = create_attr->map_ifindex; - if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS) - attr.btf_vmlinux_value_type_id = - create_attr->btf_vmlinux_value_type_id; - else - attr.inner_map_fd = create_attr->inner_map_fd; - attr.map_extra = create_attr->map_extra; + /* attempt loading freplace trying to use custom BTF */ + memset(&attr, 0, attr_sz); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = insn_cnt; + attr.license = ptr_to_u64("GPL"); - fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, sizeof(attr)); - return libbpf_err_errno(fd); + prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz); + if (prog_fd >= 0) { + close(prog_fd); + return 1; + } + return 0; } -int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) -{ - struct bpf_create_map_params p = {}; - - p.map_type = create_attr->map_type; - p.key_size = create_attr->key_size; - p.value_size = create_attr->value_size; - p.max_entries = create_attr->max_entries; - p.map_flags = create_attr->map_flags; - p.name = create_attr->name; - p.numa_node = create_attr->numa_node; - p.btf_fd = create_attr->btf_fd; - p.btf_key_type_id = create_attr->btf_key_type_id; - p.btf_value_type_id = create_attr->btf_value_type_id; - p.map_ifindex = create_attr->map_ifindex; - if (p.map_type == BPF_MAP_TYPE_STRUCT_OPS) - p.btf_vmlinux_value_type_id = - create_attr->btf_vmlinux_value_type_id; - else - p.inner_map_fd = create_attr->inner_map_fd; +static bool memlock_bumped; +static rlim_t memlock_rlim = RLIM_INFINITY; - return libbpf__bpf_create_map_xattr(&p); -} - -int bpf_create_map_node(enum bpf_map_type map_type, const char *name, - int key_size, int value_size, int max_entries, - __u32 map_flags, int node) +int libbpf_set_memlock_rlim(size_t memlock_bytes) { - struct bpf_create_map_attr map_attr = {}; - - map_attr.name = name; - map_attr.map_type = map_type; - map_attr.map_flags = map_flags; - map_attr.key_size = key_size; - map_attr.value_size = value_size; - map_attr.max_entries = max_entries; - if (node >= 0) { - map_attr.numa_node = node; - map_attr.map_flags |= BPF_F_NUMA_NODE; - } + if (memlock_bumped) + return libbpf_err(-EBUSY); - return bpf_create_map_xattr(&map_attr); + memlock_rlim = memlock_bytes; + return 0; } -int bpf_create_map(enum bpf_map_type map_type, int key_size, - int value_size, int max_entries, __u32 map_flags) +int bump_rlimit_memlock(void) { - struct bpf_create_map_attr map_attr = {}; + struct rlimit rlim; - map_attr.map_type = map_type; - map_attr.map_flags = map_flags; - map_attr.key_size = key_size; - map_attr.value_size = value_size; - map_attr.max_entries = max_entries; + /* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */ + if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT)) + return 0; - return bpf_create_map_xattr(&map_attr); -} + memlock_bumped = true; -int bpf_create_map_name(enum bpf_map_type map_type, const char *name, - int key_size, int value_size, int max_entries, - __u32 map_flags) -{ - struct bpf_create_map_attr map_attr = {}; + /* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */ + if (memlock_rlim == 0) + return 0; - map_attr.name = name; - map_attr.map_type = map_type; - map_attr.map_flags = map_flags; - map_attr.key_size = key_size; - map_attr.value_size = value_size; - map_attr.max_entries = max_entries; + rlim.rlim_cur = rlim.rlim_max = memlock_rlim; + if (setrlimit(RLIMIT_MEMLOCK, &rlim)) + return -errno; - return bpf_create_map_xattr(&map_attr); + return 0; } -int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, - int key_size, int inner_map_fd, int max_entries, - __u32 map_flags, int node) +int bpf_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, map_extra); union bpf_attr attr; int fd; - memset(&attr, '\0', sizeof(attr)); + bump_rlimit_memlock(); + + memset(&attr, 0, attr_sz); + + if (!OPTS_VALID(opts, bpf_map_create_opts)) + return libbpf_err(-EINVAL); attr.map_type = map_type; + if (map_name && kernel_supports(NULL, FEAT_PROG_NAME)) + libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.key_size = key_size; - attr.value_size = 4; - attr.inner_map_fd = inner_map_fd; + attr.value_size = value_size; attr.max_entries = max_entries; - attr.map_flags = map_flags; - if (name) - memcpy(attr.map_name, name, - min(strlen(name), BPF_OBJ_NAME_LEN - 1)); - - if (node >= 0) { - attr.map_flags |= BPF_F_NUMA_NODE; - attr.numa_node = node; - } - fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, sizeof(attr)); - return libbpf_err_errno(fd); -} + attr.btf_fd = OPTS_GET(opts, btf_fd, 0); + attr.btf_key_type_id = OPTS_GET(opts, btf_key_type_id, 0); + attr.btf_value_type_id = OPTS_GET(opts, btf_value_type_id, 0); + attr.btf_vmlinux_value_type_id = OPTS_GET(opts, btf_vmlinux_value_type_id, 0); -int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, - int key_size, int inner_map_fd, int max_entries, - __u32 map_flags) -{ - return bpf_create_map_in_map_node(map_type, name, key_size, - inner_map_fd, max_entries, map_flags, - -1); + attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0); + attr.map_flags = OPTS_GET(opts, map_flags, 0); + attr.map_extra = OPTS_GET(opts, map_extra, 0); + attr.numa_node = OPTS_GET(opts, numa_node, 0); + attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); + + fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); + return libbpf_err_errno(fd); } static void * @@ -253,58 +227,95 @@ alloc_zero_tailing_info(const void *orecord, __u32 cnt, return info; } -int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) +int bpf_prog_load(enum bpf_prog_type prog_type, + const char *prog_name, const char *license, + const struct bpf_insn *insns, size_t insn_cnt, + const struct bpf_prog_load_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, fd_array); void *finfo = NULL, *linfo = NULL; + const char *func_info, *line_info; + __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; + __u32 func_info_rec_size, line_info_rec_size; + int fd, attempts; union bpf_attr attr; - int fd; + char *log_buf; - if (!load_attr->log_buf != !load_attr->log_buf_sz) + bump_rlimit_memlock(); + + if (!OPTS_VALID(opts, bpf_prog_load_opts)) return libbpf_err(-EINVAL); - if (load_attr->log_level > (4 | 2 | 1) || (load_attr->log_level && !load_attr->log_buf)) + attempts = OPTS_GET(opts, attempts, 0); + if (attempts < 0) return libbpf_err(-EINVAL); + if (attempts == 0) + attempts = PROG_LOAD_ATTEMPTS; - memset(&attr, 0, sizeof(attr)); - attr.prog_type = load_attr->prog_type; - attr.expected_attach_type = load_attr->expected_attach_type; + memset(&attr, 0, attr_sz); - if (load_attr->attach_prog_fd) - attr.attach_prog_fd = load_attr->attach_prog_fd; - else - attr.attach_btf_obj_fd = load_attr->attach_btf_obj_fd; - attr.attach_btf_id = load_attr->attach_btf_id; + attr.prog_type = prog_type; + attr.expected_attach_type = OPTS_GET(opts, expected_attach_type, 0); - attr.prog_ifindex = load_attr->prog_ifindex; - attr.kern_version = load_attr->kern_version; + attr.prog_btf_fd = OPTS_GET(opts, prog_btf_fd, 0); + attr.prog_flags = OPTS_GET(opts, prog_flags, 0); + attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0); + attr.kern_version = OPTS_GET(opts, kern_version, 0); - attr.insn_cnt = (__u32)load_attr->insn_cnt; - attr.insns = ptr_to_u64(load_attr->insns); - attr.license = ptr_to_u64(load_attr->license); + if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME)) + libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); + attr.license = ptr_to_u64(license); - attr.log_level = load_attr->log_level; - if (attr.log_level) { - attr.log_buf = ptr_to_u64(load_attr->log_buf); - attr.log_size = load_attr->log_buf_sz; - } + if (insn_cnt > UINT_MAX) + return libbpf_err(-E2BIG); + + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)insn_cnt; + + attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); + attach_btf_obj_fd = OPTS_GET(opts, attach_btf_obj_fd, 0); + + if (attach_prog_fd && attach_btf_obj_fd) + return libbpf_err(-EINVAL); + + attr.attach_btf_id = OPTS_GET(opts, attach_btf_id, 0); + if (attach_prog_fd) + attr.attach_prog_fd = attach_prog_fd; + else + attr.attach_btf_obj_fd = attach_btf_obj_fd; + + log_buf = OPTS_GET(opts, log_buf, NULL); + log_size = OPTS_GET(opts, log_size, 0); + log_level = OPTS_GET(opts, log_level, 0); - attr.prog_btf_fd = load_attr->prog_btf_fd; - attr.prog_flags = load_attr->prog_flags; + if (!!log_buf != !!log_size) + return libbpf_err(-EINVAL); + if (log_level > (4 | 2 | 1)) + return libbpf_err(-EINVAL); + if (log_level && !log_buf) + return libbpf_err(-EINVAL); - attr.func_info_rec_size = load_attr->func_info_rec_size; - attr.func_info_cnt = load_attr->func_info_cnt; - attr.func_info = ptr_to_u64(load_attr->func_info); + func_info_rec_size = OPTS_GET(opts, func_info_rec_size, 0); + func_info = OPTS_GET(opts, func_info, NULL); + attr.func_info_rec_size = func_info_rec_size; + attr.func_info = ptr_to_u64(func_info); + attr.func_info_cnt = OPTS_GET(opts, func_info_cnt, 0); - attr.line_info_rec_size = load_attr->line_info_rec_size; - attr.line_info_cnt = load_attr->line_info_cnt; - attr.line_info = ptr_to_u64(load_attr->line_info); - attr.fd_array = ptr_to_u64(load_attr->fd_array); + line_info_rec_size = OPTS_GET(opts, line_info_rec_size, 0); + line_info = OPTS_GET(opts, line_info, NULL); + attr.line_info_rec_size = line_info_rec_size; + attr.line_info = ptr_to_u64(line_info); + attr.line_info_cnt = OPTS_GET(opts, line_info_cnt, 0); - if (load_attr->name) - memcpy(attr.prog_name, load_attr->name, - min(strlen(load_attr->name), (size_t)BPF_OBJ_NAME_LEN - 1)); + attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL)); - fd = sys_bpf_prog_load(&attr, sizeof(attr)); + if (log_level) { + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_size; + attr.log_level = log_level; + } + + fd = sys_bpf_prog_load(&attr, attr_sz, attempts); if (fd >= 0) return fd; @@ -314,11 +325,11 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) */ while (errno == E2BIG && (!finfo || !linfo)) { if (!finfo && attr.func_info_cnt && - attr.func_info_rec_size < load_attr->func_info_rec_size) { + attr.func_info_rec_size < func_info_rec_size) { /* try with corrected func info records */ - finfo = alloc_zero_tailing_info(load_attr->func_info, - load_attr->func_info_cnt, - load_attr->func_info_rec_size, + finfo = alloc_zero_tailing_info(func_info, + attr.func_info_cnt, + func_info_rec_size, attr.func_info_rec_size); if (!finfo) { errno = E2BIG; @@ -326,13 +337,12 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) } attr.func_info = ptr_to_u64(finfo); - attr.func_info_rec_size = load_attr->func_info_rec_size; + attr.func_info_rec_size = func_info_rec_size; } else if (!linfo && attr.line_info_cnt && - attr.line_info_rec_size < - load_attr->line_info_rec_size) { - linfo = alloc_zero_tailing_info(load_attr->line_info, - load_attr->line_info_cnt, - load_attr->line_info_rec_size, + attr.line_info_rec_size < line_info_rec_size) { + linfo = alloc_zero_tailing_info(line_info, + attr.line_info_cnt, + line_info_rec_size, attr.line_info_rec_size); if (!linfo) { errno = E2BIG; @@ -340,26 +350,27 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) } attr.line_info = ptr_to_u64(linfo); - attr.line_info_rec_size = load_attr->line_info_rec_size; + attr.line_info_rec_size = line_info_rec_size; } else { break; } - fd = sys_bpf_prog_load(&attr, sizeof(attr)); + fd = sys_bpf_prog_load(&attr, attr_sz, attempts); if (fd >= 0) goto done; } - if (load_attr->log_level || !load_attr->log_buf) - goto done; + if (log_level == 0 && log_buf) { + /* log_level == 0 with non-NULL log_buf requires retrying on error + * with log_level == 1 and log_buf/log_buf_size set, to get details of + * failure + */ + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_size; + attr.log_level = 1; - /* Try again with log */ - attr.log_buf = ptr_to_u64(load_attr->log_buf); - attr.log_size = load_attr->log_buf_sz; - attr.log_level = 1; - load_attr->log_buf[0] = 0; - - fd = sys_bpf_prog_load(&attr, sizeof(attr)); + fd = sys_bpf_prog_load(&attr, attr_sz, attempts); + } done: /* free() doesn't affect errno, so we don't need to restore it */ free(finfo); @@ -367,202 +378,139 @@ done: return libbpf_err_errno(fd); } -int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, - char *log_buf, size_t log_buf_sz) -{ - struct bpf_prog_load_params p = {}; - - if (!load_attr || !log_buf != !log_buf_sz) - return libbpf_err(-EINVAL); - - p.prog_type = load_attr->prog_type; - p.expected_attach_type = load_attr->expected_attach_type; - switch (p.prog_type) { - case BPF_PROG_TYPE_STRUCT_OPS: - case BPF_PROG_TYPE_LSM: - p.attach_btf_id = load_attr->attach_btf_id; - break; - case BPF_PROG_TYPE_TRACING: - case BPF_PROG_TYPE_EXT: - p.attach_btf_id = load_attr->attach_btf_id; - p.attach_prog_fd = load_attr->attach_prog_fd; - break; - default: - p.prog_ifindex = load_attr->prog_ifindex; - p.kern_version = load_attr->kern_version; - } - p.insn_cnt = load_attr->insns_cnt; - p.insns = load_attr->insns; - p.license = load_attr->license; - p.log_level = load_attr->log_level; - p.log_buf = log_buf; - p.log_buf_sz = log_buf_sz; - p.prog_btf_fd = load_attr->prog_btf_fd; - p.func_info_rec_size = load_attr->func_info_rec_size; - p.func_info_cnt = load_attr->func_info_cnt; - p.func_info = load_attr->func_info; - p.line_info_rec_size = load_attr->line_info_rec_size; - p.line_info_cnt = load_attr->line_info_cnt; - p.line_info = load_attr->line_info; - p.name = load_attr->name; - p.prog_flags = load_attr->prog_flags; - - return libbpf__bpf_prog_load(&p); -} - -int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, - size_t insns_cnt, const char *license, - __u32 kern_version, char *log_buf, - size_t log_buf_sz) -{ - struct bpf_load_program_attr load_attr; - - memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); - load_attr.prog_type = type; - load_attr.expected_attach_type = 0; - load_attr.name = NULL; - load_attr.insns = insns; - load_attr.insns_cnt = insns_cnt; - load_attr.license = license; - load_attr.kern_version = kern_version; - - return bpf_load_program_xattr(&load_attr, log_buf, log_buf_sz); -} - -int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, - size_t insns_cnt, __u32 prog_flags, const char *license, - __u32 kern_version, char *log_buf, size_t log_buf_sz, - int log_level) -{ - union bpf_attr attr; - int fd; - - memset(&attr, 0, sizeof(attr)); - attr.prog_type = type; - attr.insn_cnt = (__u32)insns_cnt; - attr.insns = ptr_to_u64(insns); - attr.license = ptr_to_u64(license); - attr.log_buf = ptr_to_u64(log_buf); - attr.log_size = log_buf_sz; - attr.log_level = log_level; - log_buf[0] = 0; - attr.kern_version = kern_version; - attr.prog_flags = prog_flags; - - fd = sys_bpf_prog_load(&attr, sizeof(attr)); - return libbpf_err_errno(fd); -} - int bpf_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; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); attr.flags = flags; - ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_lookup_elem(int fd, const void *key, void *value) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); - ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); attr.flags = flags; - ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); - ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); attr.flags = flags; - ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_delete_elem(int fd, const void *key) { + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + + ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz); + return libbpf_err_errno(ret); +} + +int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); + attr.flags = flags; - ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_get_next_key(int fd, const void *key, void *next_key) { + const size_t attr_sz = offsetofend(union bpf_attr, next_key); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.next_key = ptr_to_u64(next_key); - ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_map_freeze(int fd) { + const size_t attr_sz = offsetofend(union bpf_attr, map_fd); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_fd = fd; - ret = sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_FREEZE, &attr, attr_sz); return libbpf_err_errno(ret); } @@ -571,13 +519,14 @@ static int bpf_map_batch_common(int cmd, int fd, void *in_batch, __u32 *count, const struct bpf_map_batch_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, batch); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_map_batch_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.batch.map_fd = fd; attr.batch.in_batch = ptr_to_u64(in_batch); attr.batch.out_batch = ptr_to_u64(out_batch); @@ -587,17 +536,17 @@ static int bpf_map_batch_common(int cmd, int fd, void *in_batch, attr.batch.elem_flags = OPTS_GET(opts, elem_flags, 0); attr.batch.flags = OPTS_GET(opts, flags, 0); - ret = sys_bpf(cmd, &attr, sizeof(attr)); + ret = sys_bpf(cmd, &attr, attr_sz); *count = attr.batch.count; return libbpf_err_errno(ret); } -int bpf_map_delete_batch(int fd, void *keys, __u32 *count, +int bpf_map_delete_batch(int fd, const void *keys, __u32 *count, const struct bpf_map_batch_opts *opts) { return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL, - NULL, keys, NULL, count, opts); + NULL, (void *)keys, NULL, count, opts); } int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys, @@ -617,35 +566,46 @@ int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch, count, opts); } -int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count, +int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *count, const struct bpf_map_batch_opts *opts) { return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL, - keys, values, count, opts); + (void *)keys, (void *)values, count, opts); } int bpf_obj_pin(int fd, const char *pathname) { + const size_t attr_sz = offsetofend(union bpf_attr, file_flags); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.pathname = ptr_to_u64((void *)pathname); attr.bpf_fd = fd; - ret = sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr)); + ret = sys_bpf(BPF_OBJ_PIN, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_obj_get(const char *pathname) { + return bpf_obj_get_opts(pathname, NULL); +} + +int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, file_flags); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + if (!OPTS_VALID(opts, bpf_obj_get_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); attr.pathname = ptr_to_u64((void *)pathname); + attr.file_flags = OPTS_GET(opts, file_flags, 0); - fd = sys_bpf_fd(BPF_OBJ_GET, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_OBJ_GET, &attr, attr_sz); return libbpf_err_errno(fd); } @@ -656,54 +616,57 @@ 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) { + const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_prog_attach_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; attr.attach_flags = OPTS_GET(opts, flags, 0); attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0); - ret = sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_ATTACH, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { + const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.target_fd = target_fd; attr.attach_type = type; - ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) { + const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; - ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz); return libbpf_err_errno(ret); } @@ -711,9 +674,10 @@ int bpf_link_create(int prog_fd, int target_fd, enum bpf_attach_type attach_type, const struct bpf_link_create_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, link_create); __u32 target_btf_id, iter_info_len; union bpf_attr attr; - int fd; + int fd, err; if (!OPTS_VALID(opts, bpf_link_create_opts)) return libbpf_err(-EINVAL); @@ -729,7 +693,7 @@ int bpf_link_create(int prog_fd, int target_fd, return libbpf_err(-EINVAL); } - memset(&attr, 0, sizeof(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; @@ -750,147 +714,168 @@ 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; + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + case BPF_LSM_MAC: + attr.link_create.tracing.cookie = OPTS_GET(opts, tracing.cookie, 0); + if (!OPTS_ZEROED(opts, tracing)) + return libbpf_err(-EINVAL); + break; default: if (!OPTS_ZEROED(opts, flags)) return libbpf_err(-EINVAL); break; } proceed: - fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, sizeof(attr)); - return libbpf_err_errno(fd); + fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, attr_sz); + if (fd >= 0) + return fd; + /* we'll get EINVAL if LINK_CREATE doesn't support attaching fentry + * and other similar programs + */ + err = -errno; + if (err != -EINVAL) + return libbpf_err(err); + + /* if user used features not supported by + * BPF_RAW_TRACEPOINT_OPEN command, then just give up immediately + */ + if (attr.link_create.target_fd || attr.link_create.target_btf_id) + return libbpf_err(err); + if (!OPTS_ZEROED(opts, sz)) + return libbpf_err(err); + + /* otherwise, for few select kinds of programs that can be + * attached using BPF_RAW_TRACEPOINT_OPEN command, try that as + * a fallback for older kernels + */ + switch (attach_type) { + case BPF_TRACE_RAW_TP: + case BPF_LSM_MAC: + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + return bpf_raw_tracepoint_open(NULL, prog_fd); + default: + return libbpf_err(err); + } } int bpf_link_detach(int link_fd) { + const size_t attr_sz = offsetofend(union bpf_attr, link_detach); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.link_detach.link_fd = link_fd; - ret = sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_LINK_DETACH, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_link_update(int link_fd, int new_prog_fd, const struct bpf_link_update_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, link_update); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_link_update_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.link_update.link_fd = link_fd; attr.link_update.new_prog_fd = new_prog_fd; attr.link_update.flags = OPTS_GET(opts, flags, 0); attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); - ret = sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr)); + ret = sys_bpf(BPF_LINK_UPDATE, &attr, attr_sz); return libbpf_err_errno(ret); } int bpf_iter_create(int link_fd) { + const size_t attr_sz = offsetofend(union bpf_attr, iter_create); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.iter_create.link_fd = link_fd; - fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } -int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, - __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt) +int bpf_prog_query_opts(int target_fd, + enum bpf_attach_type type, + struct bpf_prog_query_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, query); union bpf_attr attr; int ret; - memset(&attr, 0, sizeof(attr)); + if (!OPTS_VALID(opts, bpf_prog_query_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.query.target_fd = target_fd; attr.query.attach_type = type; - attr.query.query_flags = query_flags; - attr.query.prog_cnt = *prog_cnt; - attr.query.prog_ids = ptr_to_u64(prog_ids); + attr.query.query_flags = OPTS_GET(opts, query_flags, 0); + attr.query.prog_cnt = OPTS_GET(opts, prog_cnt, 0); + attr.query.prog_ids = ptr_to_u64(OPTS_GET(opts, prog_ids, NULL)); + attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL)); - ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_QUERY, &attr, attr_sz); - if (attach_flags) - *attach_flags = attr.query.attach_flags; - *prog_cnt = attr.query.prog_cnt; + OPTS_SET(opts, attach_flags, attr.query.attach_flags); + OPTS_SET(opts, prog_cnt, attr.query.prog_cnt); return libbpf_err_errno(ret); } -int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, - void *data_out, __u32 *size_out, __u32 *retval, - __u32 *duration) +int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, + __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt) { - union bpf_attr attr; + LIBBPF_OPTS(bpf_prog_query_opts, opts); int ret; - memset(&attr, 0, sizeof(attr)); - attr.test.prog_fd = prog_fd; - attr.test.data_in = ptr_to_u64(data); - attr.test.data_out = ptr_to_u64(data_out); - attr.test.data_size_in = size; - attr.test.repeat = repeat; - - ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); + opts.query_flags = query_flags; + opts.prog_ids = prog_ids; + opts.prog_cnt = *prog_cnt; - if (size_out) - *size_out = attr.test.data_size_out; - if (retval) - *retval = attr.test.retval; - if (duration) - *duration = attr.test.duration; + ret = bpf_prog_query_opts(target_fd, type, &opts); - return libbpf_err_errno(ret); -} - -int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) -{ - union bpf_attr attr; - int ret; - - if (!test_attr->data_out && test_attr->data_size_out > 0) - return libbpf_err(-EINVAL); - - memset(&attr, 0, sizeof(attr)); - attr.test.prog_fd = test_attr->prog_fd; - attr.test.data_in = ptr_to_u64(test_attr->data_in); - attr.test.data_out = ptr_to_u64(test_attr->data_out); - attr.test.data_size_in = test_attr->data_size_in; - attr.test.data_size_out = test_attr->data_size_out; - attr.test.ctx_in = ptr_to_u64(test_attr->ctx_in); - attr.test.ctx_out = ptr_to_u64(test_attr->ctx_out); - attr.test.ctx_size_in = test_attr->ctx_size_in; - attr.test.ctx_size_out = test_attr->ctx_size_out; - attr.test.repeat = test_attr->repeat; - - ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); - - test_attr->data_size_out = attr.test.data_size_out; - test_attr->ctx_size_out = attr.test.ctx_size_out; - test_attr->retval = attr.test.retval; - test_attr->duration = attr.test.duration; + if (attach_flags) + *attach_flags = opts.attach_flags; + *prog_cnt = opts.prog_cnt; return libbpf_err_errno(ret); } int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, test); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_test_run_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); 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); @@ -904,7 +889,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) attr.test.data_in = ptr_to_u64(OPTS_GET(opts, data_in, NULL)); attr.test.data_out = ptr_to_u64(OPTS_GET(opts, data_out, NULL)); - ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, attr_sz); OPTS_SET(opts, data_size_out, attr.test.data_size_out); OPTS_SET(opts, ctx_size_out, attr.test.ctx_size_out); @@ -916,13 +901,14 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd) { + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); union bpf_attr attr; int err; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.start_id = start_id; - err = sys_bpf(cmd, &attr, sizeof(attr)); + err = sys_bpf(cmd, &attr, attr_sz); if (!err) *next_id = attr.next_id; @@ -951,106 +937,132 @@ int bpf_link_get_next_id(__u32 start_id, __u32 *next_id) int bpf_prog_get_fd_by_id(__u32 id) { + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.prog_id = id; - fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_map_get_fd_by_id(__u32 id) { + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.map_id = id; - fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_btf_get_fd_by_id(__u32 id) { + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.btf_id = id; - fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_link_get_fd_by_id(__u32 id) { + const size_t attr_sz = offsetofend(union bpf_attr, open_flags); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.link_id = id; - fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len) { + const size_t attr_sz = offsetofend(union bpf_attr, info); union bpf_attr attr; int err; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.info.bpf_fd = bpf_fd; attr.info.info_len = *info_len; attr.info.info = ptr_to_u64(info); - err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr)); - + err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, attr_sz); if (!err) *info_len = attr.info.info_len; - return libbpf_err_errno(err); } int bpf_raw_tracepoint_open(const char *name, int prog_fd) { + const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.raw_tracepoint.name = ptr_to_u64(name); attr.raw_tracepoint.prog_fd = prog_fd; - fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz); return libbpf_err_errno(fd); } -int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, - bool do_log) +int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_load_opts *opts) { - union bpf_attr attr = {}; + const size_t attr_sz = offsetofend(union bpf_attr, btf_log_level); + union bpf_attr attr; + char *log_buf; + size_t log_size; + __u32 log_level; int fd; - attr.btf = ptr_to_u64(btf); - attr.btf_size = btf_size; + bump_rlimit_memlock(); -retry: - if (do_log && log_buf && log_buf_size) { - attr.btf_log_level = 1; - attr.btf_log_size = log_buf_size; - attr.btf_log_buf = ptr_to_u64(log_buf); - } + memset(&attr, 0, attr_sz); - fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, sizeof(attr)); + if (!OPTS_VALID(opts, bpf_btf_load_opts)) + return libbpf_err(-EINVAL); + + log_buf = OPTS_GET(opts, log_buf, NULL); + log_size = OPTS_GET(opts, log_size, 0); + log_level = OPTS_GET(opts, log_level, 0); - if (fd < 0 && !do_log && log_buf && log_buf_size) { - do_log = true; - goto retry; + if (log_size > UINT_MAX) + return libbpf_err(-EINVAL); + if (log_size && !log_buf) + return libbpf_err(-EINVAL); + + attr.btf = ptr_to_u64(btf_data); + attr.btf_size = btf_size; + /* log_level == 0 and log_buf != NULL means "try loading without + * log_buf, but retry with log_buf and log_level=1 on error", which is + * consistent across low-level and high-level BTF and program loading + * APIs within libbpf and provides a sensible behavior in practice + */ + if (log_level) { + attr.btf_log_buf = ptr_to_u64(log_buf); + attr.btf_log_size = (__u32)log_size; + attr.btf_log_level = log_level; } + fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz); + if (fd < 0 && log_buf && log_level == 0) { + attr.btf_log_buf = ptr_to_u64(log_buf); + attr.btf_log_size = (__u32)log_size; + attr.btf_log_level = 1; + fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz); + } return libbpf_err_errno(fd); } @@ -1058,16 +1070,18 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr) { - union bpf_attr attr = {}; + const size_t attr_sz = offsetofend(union bpf_attr, task_fd_query); + union bpf_attr attr; int err; + memset(&attr, 0, attr_sz); attr.task_fd_query.pid = pid; attr.task_fd_query.fd = fd; attr.task_fd_query.flags = flags; attr.task_fd_query.buf = ptr_to_u64(buf); attr.task_fd_query.buf_len = *buf_len; - err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr)); + err = sys_bpf(BPF_TASK_FD_QUERY, &attr, attr_sz); *buf_len = attr.task_fd_query.buf_len; *prog_id = attr.task_fd_query.prog_id; @@ -1080,30 +1094,32 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, int bpf_enable_stats(enum bpf_stats_type type) { + const size_t attr_sz = offsetofend(union bpf_attr, enable_stats); union bpf_attr attr; int fd; - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.enable_stats.type = type; - fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, sizeof(attr)); + fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_prog_bind_map(int prog_fd, int map_fd, const struct bpf_prog_bind_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, prog_bind_map); union bpf_attr attr; int ret; if (!OPTS_VALID(opts, bpf_prog_bind_opts)) return libbpf_err(-EINVAL); - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.prog_bind_map.prog_fd = prog_fd; attr.prog_bind_map.map_fd = map_fd; attr.prog_bind_map.flags = OPTS_GET(opts, flags, 0); - ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz); return libbpf_err_errno(ret); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 6fffb3cdf39b..9c50beabdd14 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -29,92 +29,99 @@ #include <stdint.h> #include "libbpf_common.h" +#include "libbpf_legacy.h" #ifdef __cplusplus extern "C" { #endif -struct bpf_create_map_attr { - const char *name; - enum bpf_map_type map_type; - __u32 map_flags; - __u32 key_size; - __u32 value_size; - __u32 max_entries; - __u32 numa_node; +int libbpf_set_memlock_rlim(size_t memlock_bytes); + +struct bpf_map_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 btf_fd; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 btf_vmlinux_value_type_id; + + __u32 inner_map_fd; + __u32 map_flags; + __u64 map_extra; + + __u32 numa_node; __u32 map_ifindex; - union { - __u32 inner_map_fd; - __u32 btf_vmlinux_value_type_id; - }; }; +#define bpf_map_create_opts__last_field map_ifindex + +LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts); + +struct bpf_prog_load_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + /* libbpf can retry BPF_PROG_LOAD command if bpf() syscall returns + * -EAGAIN. This field determines how many attempts libbpf has to + * make. If not specified, libbpf will use default value of 5. + */ + int attempts; -LIBBPF_API int -bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); -LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name, - int key_size, int value_size, - int max_entries, __u32 map_flags, int node); -LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name, - int key_size, int value_size, - int max_entries, __u32 map_flags); -LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size, - int value_size, int max_entries, __u32 map_flags); -LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type, - const char *name, int key_size, - int inner_map_fd, int max_entries, - __u32 map_flags, int node); -LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type, - const char *name, int key_size, - int inner_map_fd, int max_entries, - __u32 map_flags); - -struct bpf_load_program_attr { - enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; - const char *name; - const struct bpf_insn *insns; - size_t insns_cnt; - const char *license; - union { - __u32 kern_version; - __u32 attach_prog_fd; - }; - union { - __u32 prog_ifindex; - __u32 attach_btf_id; - }; __u32 prog_btf_fd; - __u32 func_info_rec_size; + __u32 prog_flags; + __u32 prog_ifindex; + __u32 kern_version; + + __u32 attach_btf_id; + __u32 attach_prog_fd; + __u32 attach_btf_obj_fd; + + const int *fd_array; + + /* .BTF.ext func info data */ const void *func_info; __u32 func_info_cnt; - __u32 line_info_rec_size; + __u32 func_info_rec_size; + + /* .BTF.ext line info data */ const void *line_info; __u32 line_info_cnt; + __u32 line_info_rec_size; + + /* verifier log options */ __u32 log_level; - __u32 prog_flags; + __u32 log_size; + char *log_buf; }; +#define bpf_prog_load_opts__last_field log_buf + +LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, + const char *prog_name, const char *license, + const struct bpf_insn *insns, size_t insn_cnt, + const struct bpf_prog_load_opts *opts); /* Flags to direct loading requirements */ #define MAPS_RELAX_COMPAT 0x01 -/* Recommend log buffer size */ +/* Recommended log buffer size */ #define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */ -LIBBPF_API int -bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, - char *log_buf, size_t log_buf_sz); -LIBBPF_API int bpf_load_program(enum bpf_prog_type type, - const struct bpf_insn *insns, size_t insns_cnt, - const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz); -LIBBPF_API int bpf_verify_program(enum bpf_prog_type type, - const struct bpf_insn *insns, - size_t insns_cnt, __u32 prog_flags, - const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz, - int log_level); + +struct bpf_btf_load_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + /* kernel log options */ + char *log_buf; + __u32 log_level; + __u32 log_size; +}; +#define bpf_btf_load_opts__last_field log_size + +LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, + const struct bpf_btf_load_opts *opts); LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); @@ -127,6 +134,7 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, LIBBPF_API int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags); LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); +LIBBPF_API int bpf_map_delete_elem_flags(int fd, const void *key, __u64 flags); LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); LIBBPF_API int bpf_map_freeze(int fd); @@ -137,22 +145,144 @@ struct bpf_map_batch_opts { }; #define bpf_map_batch_opts__last_field flags -LIBBPF_API int bpf_map_delete_batch(int fd, void *keys, + +/** + * @brief **bpf_map_delete_batch()** allows for batch deletion of multiple + * elements in a BPF map. + * + * @param fd BPF map file descriptor + * @param keys pointer to an array of *count* keys + * @param count input and output parameter; on input **count** represents the + * number of elements in the map to delete in batch; + * on output if a non-EFAULT error is returned, **count** represents the number of deleted + * elements if the output **count** value is not equal to the input **count** value + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch deletion works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys, __u32 *count, const struct bpf_map_batch_opts *opts); + +/** + * @brief **bpf_map_lookup_batch()** allows for batch lookup of BPF map elements. + * + * The parameter *in_batch* is the address of the first element in the batch to read. + * *out_batch* is an output parameter that should be passed as *in_batch* to subsequent + * calls to **bpf_map_lookup_batch()**. NULL can be passed for *in_batch* to indicate + * that the batched lookup starts from the beginning of the map. + * + * The *keys* and *values* are output parameters which must point to memory large enough to + * hold *count* items based on the key and value size of the map *map_fd*. The *keys* + * buffer must be of *key_size* * *count*. The *values* buffer must be of + * *value_size* * *count*. + * + * @param fd BPF map file descriptor + * @param in_batch address of the first element in batch to read, can pass NULL to + * indicate that the batched lookup starts from the beginning of the map. + * @param out_batch output parameter that should be passed to next call as *in_batch* + * @param keys pointer to an array large enough for *count* keys + * @param values pointer to an array large enough for *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to read in batch; on output it's the number of elements that were + * successfully read. + * If a non-EFAULT error is returned, count will be set as the number of elements + * that were read before the error occurred. + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch lookup works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys, void *values, __u32 *count, const struct bpf_map_batch_opts *opts); + +/** + * @brief **bpf_map_lookup_and_delete_batch()** allows for batch lookup and deletion + * of BPF map elements where each element is deleted after being retrieved. + * + * @param fd BPF map file descriptor + * @param in_batch address of the first element in batch to read, can pass NULL to + * get address of the first element in *out_batch* + * @param out_batch output parameter that should be passed to next call as *in_batch* + * @param keys pointer to an array of *count* keys + * @param values pointer to an array large enough for *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to read and delete in batch; on output it represents the number of + * elements that were successfully read and deleted + * If a non-**EFAULT** error code is returned and if the output **count** value + * is not equal to the input **count** value, up to **count** elements may + * have been deleted. + * if **EFAULT** is returned up to *count* elements may have been deleted without + * being returned via the *keys* and *values* output parameters. + * @param opts options for configuring the way the batch lookup and delete works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch, void *keys, void *values, __u32 *count, const struct bpf_map_batch_opts *opts); -LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values, + +/** + * @brief **bpf_map_update_batch()** updates multiple elements in a map + * by specifying keys and their corresponding values. + * + * The *keys* and *values* parameters must point to memory large enough + * to hold *count* items based on the key and value size of the map. + * + * The *opts* parameter can be used to control how *bpf_map_update_batch()* + * should handle keys that either do or do not already exist in the map. + * In particular the *flags* parameter of *bpf_map_batch_opts* can be + * one of the following: + * + * Note that *count* is an input and output parameter, where on output it + * represents how many elements were successfully updated. Also note that if + * **EFAULT** then *count* should not be trusted to be correct. + * + * **BPF_ANY** + * Create new elements or update existing. + * + * **BPF_NOEXIST** + * Create new elements only if they do not exist. + * + * **BPF_EXIST** + * Update existing elements. + * + * **BPF_F_LOCK** + * Update spin_lock-ed map elements. This must be + * specified if the map value contains a spinlock. + * + * @param fd BPF map file descriptor + * @param keys pointer to an array of *count* keys + * @param values pointer to an array of *count* values + * @param count input and output parameter; on input it's the number of elements + * in the map to update in batch; on output if a non-EFAULT error is returned, + * **count** represents the number of updated elements if the output **count** + * value is not equal to the input **count** value. + * If EFAULT is returned, **count** should not be trusted to be correct. + * @param opts options for configuring the way the batch update works + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *count, const struct bpf_map_batch_opts *opts); +struct bpf_obj_get_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + __u32 file_flags; + + size_t :0; +}; +#define bpf_obj_get_opts__last_field file_flags + LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); LIBBPF_API int bpf_obj_get(const char *pathname); +LIBBPF_API int bpf_obj_get_opts(const char *pathname, + const struct bpf_obj_get_opts *opts); struct bpf_prog_attach_opts { size_t sz; /* size of this struct for forward/backward compatibility */ @@ -163,7 +293,7 @@ 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_xattr(int prog_fd, int attachable_fd, +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_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); @@ -181,10 +311,20 @@ 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; + struct { + __u64 cookie; + } tracing; }; 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, @@ -221,15 +361,6 @@ struct bpf_prog_test_run_attr { * out: length of cxt_out */ }; -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. - */ -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); LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id); @@ -239,12 +370,25 @@ LIBBPF_API int bpf_map_get_fd_by_id(__u32 id); LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id); LIBBPF_API int bpf_link_get_fd_by_id(__u32 id); LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len); + +struct bpf_prog_query_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 query_flags; + __u32 attach_flags; /* output argument */ + __u32 *prog_ids; + __u32 prog_cnt; /* input+output argument */ + __u32 *prog_attach_flags; +}; +#define bpf_prog_query_opts__last_field prog_attach_flags + +LIBBPF_API int bpf_prog_query_opts(int target_fd, + enum bpf_attach_type type, + struct bpf_prog_query_opts *opts); LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); + LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd); -LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, - __u32 log_buf_size, bool do_log); LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr); @@ -280,8 +424,9 @@ 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_core_read.h b/tools/lib/bpf/bpf_core_read.h index e4aa9996a550..496e6a8ee0dc 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -29,6 +29,7 @@ enum bpf_type_id_kind { enum bpf_type_info_kind { BPF_TYPE_EXISTS = 0, /* type existence in target kernel */ BPF_TYPE_SIZE = 1, /* type size in target kernel */ + BPF_TYPE_MATCHES = 2, /* type match in target kernel */ }; /* second argument to __builtin_preserve_enum_value() built-in */ @@ -110,21 +111,50 @@ enum bpf_enum_value_kind { val; \ }) +#define ___bpf_field_ref1(field) (field) +#define ___bpf_field_ref2(type, field) (((typeof(type) *)0)->field) +#define ___bpf_field_ref(args...) \ + ___bpf_apply(___bpf_field_ref, ___bpf_narg(args))(args) + /* * Convenience macro to check that field actually exists in target kernel's. * Returns: * 1, if matching field is present in target kernel; * 0, if no matching field found. + * + * Supports two forms: + * - field reference through variable access: + * bpf_core_field_exists(p->my_field); + * - field reference through type and field names: + * bpf_core_field_exists(struct my_type, my_field). */ -#define bpf_core_field_exists(field) \ - __builtin_preserve_field_info(field, BPF_FIELD_EXISTS) +#define bpf_core_field_exists(field...) \ + __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_EXISTS) /* * Convenience macro to get the byte size of a field. Works for integers, * struct/unions, pointers, arrays, and enums. + * + * Supports two forms: + * - field reference through variable access: + * bpf_core_field_size(p->my_field); + * - field reference through type and field names: + * bpf_core_field_size(struct my_type, my_field). + */ +#define bpf_core_field_size(field...) \ + __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_SIZE) + +/* + * Convenience macro to get field's byte offset. + * + * Supports two forms: + * - field reference through variable access: + * bpf_core_field_offset(p->my_field); + * - field reference through type and field names: + * bpf_core_field_offset(struct my_type, my_field). */ -#define bpf_core_field_size(field) \ - __builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE) +#define bpf_core_field_offset(field...) \ + __builtin_preserve_field_info(___bpf_field_ref(field), BPF_FIELD_BYTE_OFFSET) /* * Convenience macro to get BTF type ID of a specified type, using a local BTF @@ -155,6 +185,16 @@ enum bpf_enum_value_kind { __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_EXISTS) /* + * Convenience macro to check that provided named type + * (struct/union/enum/typedef) "matches" that in a target kernel. + * Returns: + * 1, if the type matches in the target kernel's BTF; + * 0, if the type does not match any in the target kernel + */ +#define bpf_core_type_matches(type) \ + __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_MATCHES) + +/* * Convenience macro to get the byte size of a provided named type * (struct/union/enum/typedef) in a target kernel. * Returns: diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index 6f3df004479b..223308931d55 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -3,6 +3,8 @@ #ifndef __BPF_GEN_INTERNAL_H #define __BPF_GEN_INTERNAL_H +#include "bpf.h" + struct ksym_relo_desc { const char *name; int kind; @@ -37,6 +39,8 @@ struct bpf_gen { int error; struct ksym_relo_desc *relos; int relo_cnt; + struct bpf_core_relo *core_relos; + int core_relo_cnt; char attach_target[128]; int attach_kind; struct ksym_desc *ksyms; @@ -49,13 +53,20 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps); void bpf_gen__free(struct bpf_gen *gen); void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size); -void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx); -struct bpf_prog_load_params; -void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx); +void bpf_gen__map_create(struct bpf_gen *gen, + enum bpf_map_type map_type, const char *map_name, + __u32 key_size, __u32 value_size, __u32 max_entries, + struct bpf_map_create_opts *map_attr, int map_idx); +void bpf_gen__prog_load(struct bpf_gen *gen, + enum bpf_prog_type prog_type, const char *prog_name, + const char *license, struct bpf_insn *insns, size_t insn_cnt, + struct bpf_prog_load_opts *load_attr, int prog_idx); void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size); void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx); void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type); void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, bool is_typeless, int kind, int insn_idx); +void bpf_gen__record_relo_core(struct bpf_gen *gen, const struct bpf_core_relo *core_relo); +void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int key, int inner_map_idx); #endif diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 963b1060d944..d37c4fe2849d 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -22,12 +22,25 @@ * To allow use of SEC() with externs (e.g., for extern .maps declarations), * make sure __attribute__((unused)) doesn't trigger compilation warning. */ +#if __GNUC__ && !__clang__ + +/* + * Pragma macros are broken on GCC + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=55578 + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90400 + */ +#define SEC(name) __attribute__((section(name), used)) + +#else + #define SEC(name) \ _Pragma("GCC diagnostic push") \ _Pragma("GCC diagnostic ignored \"-Wignored-attributes\"") \ __attribute__((section(name), used)) \ _Pragma("GCC diagnostic pop") \ +#endif + /* Avoid 'linux/stddef.h' definition of '__always_inline'. */ #undef __always_inline #define __always_inline inline __attribute__((always_inline)) @@ -76,6 +89,30 @@ #endif /* + * Compiler (optimization) barrier. + */ +#ifndef barrier +#define barrier() asm volatile("" ::: "memory") +#endif + +/* Variable-specific compiler (optimization) barrier. It's a no-op which makes + * compiler believe that there is some black box modification of a given + * variable and thus prevents compiler from making extra assumption about its + * value and potential simplifications and optimizations on this variable. + * + * E.g., compiler might often delay or even omit 32-bit to 64-bit casting of + * a variable, making some code patterns unverifiable. Putting barrier_var() + * in place will ensure that cast is performed before the barrier_var() + * invocation, because compiler has to pessimistically assume that embedded + * asm section might perform some extra operations on that variable. + * + * This is a variable-specific variant of more global barrier(). + */ +#ifndef barrier_var +#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var)) +#endif + +/* * Helper macro to throw a compilation error if __bpf_unreachable() gets * built into the resulting code. This works given BPF back end does not * implement __builtin_trap(). This is useful to assert that certain paths @@ -123,18 +160,6 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot) } #endif -/* - * Helper structure used by eBPF C program - * to describe BPF map attributes to libbpf loader - */ -struct bpf_map_def { - unsigned int type; - unsigned int key_size; - unsigned int value_size; - unsigned int max_entries; - unsigned int map_flags; -}; - enum libbpf_pin_type { LIBBPF_PIN_NONE, /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ @@ -149,6 +174,8 @@ enum libbpf_tristate { #define __kconfig __attribute__((section(".kconfig"))) #define __ksym __attribute__((section(".ksyms"))) +#define __kptr __attribute__((btf_type_tag("kptr"))) +#define __kptr_ref __attribute__((btf_type_tag("kptr_ref"))) #ifndef ___bpf_concat #define ___bpf_concat(a, b) a ## b diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index db05a5937105..2972dc25ff72 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -2,6 +2,8 @@ #ifndef __BPF_TRACING_H__ #define __BPF_TRACING_H__ +#include <bpf/bpf_helpers.h> + /* Scan the ARCH passed in from ARCH env variable (see Makefile) */ #if defined(__TARGET_ARCH_x86) #define bpf_target_x86 @@ -27,6 +29,9 @@ #elif defined(__TARGET_ARCH_riscv) #define bpf_target_riscv #define bpf_target_defined +#elif defined(__TARGET_ARCH_arc) + #define bpf_target_arc + #define bpf_target_defined #else /* Fall back to what the compiler says */ @@ -54,6 +59,9 @@ #elif defined(__riscv) && __riscv_xlen == 64 #define bpf_target_riscv #define bpf_target_defined +#elif defined(__arc__) + #define bpf_target_arc + #define bpf_target_defined #endif /* no compiler target */ #endif @@ -66,277 +74,263 @@ #if defined(__KERNEL__) || defined(__VMLINUX_H__) -#define PT_REGS_PARM1(x) ((x)->di) -#define PT_REGS_PARM2(x) ((x)->si) -#define PT_REGS_PARM3(x) ((x)->dx) -#define PT_REGS_PARM4(x) ((x)->cx) -#define PT_REGS_PARM5(x) ((x)->r8) -#define PT_REGS_RET(x) ((x)->sp) -#define PT_REGS_FP(x) ((x)->bp) -#define PT_REGS_RC(x) ((x)->ax) -#define PT_REGS_SP(x) ((x)->sp) -#define PT_REGS_IP(x) ((x)->ip) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), di) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), si) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), dx) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), cx) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), sp) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), bp) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), ax) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), ip) +#define __PT_PARM1_REG di +#define __PT_PARM2_REG si +#define __PT_PARM3_REG dx +#define __PT_PARM4_REG cx +#define __PT_PARM5_REG r8 +#define __PT_RET_REG sp +#define __PT_FP_REG bp +#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 #ifdef __i386__ -/* i386 kernel is built with -mregparm=3 */ -#define PT_REGS_PARM1(x) ((x)->eax) -#define PT_REGS_PARM2(x) ((x)->edx) -#define PT_REGS_PARM3(x) ((x)->ecx) -#define PT_REGS_PARM4(x) 0 -#define PT_REGS_PARM5(x) 0 -#define PT_REGS_RET(x) ((x)->esp) -#define PT_REGS_FP(x) ((x)->ebp) -#define PT_REGS_RC(x) ((x)->eax) -#define PT_REGS_SP(x) ((x)->esp) -#define PT_REGS_IP(x) ((x)->eip) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), eax) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), edx) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), ecx) -#define PT_REGS_PARM4_CORE(x) 0 -#define PT_REGS_PARM5_CORE(x) 0 -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), esp) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), ebp) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), eax) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), esp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), eip) -#else - -#define PT_REGS_PARM1(x) ((x)->rdi) -#define PT_REGS_PARM2(x) ((x)->rsi) -#define PT_REGS_PARM3(x) ((x)->rdx) -#define PT_REGS_PARM4(x) ((x)->rcx) -#define PT_REGS_PARM5(x) ((x)->r8) -#define PT_REGS_RET(x) ((x)->rsp) -#define PT_REGS_FP(x) ((x)->rbp) -#define PT_REGS_RC(x) ((x)->rax) -#define PT_REGS_SP(x) ((x)->rsp) -#define PT_REGS_IP(x) ((x)->rip) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), rdi) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), rsi) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), rdx) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), rcx) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), r8) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), rsp) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), rbp) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), rax) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), rsp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), rip) - -#endif -#endif +#define __PT_PARM1_REG eax +#define __PT_PARM2_REG edx +#define __PT_PARM3_REG ecx +/* i386 kernel is built with -mregparm=3 */ +#define __PT_PARM4_REG __unsupported__ +#define __PT_PARM5_REG __unsupported__ +#define __PT_RET_REG esp +#define __PT_FP_REG ebp +#define __PT_RC_REG eax +#define __PT_SP_REG esp +#define __PT_IP_REG eip + +#else /* __i386__ */ + +#define __PT_PARM1_REG rdi +#define __PT_PARM2_REG rsi +#define __PT_PARM3_REG rdx +#define __PT_PARM4_REG rcx +#define __PT_PARM5_REG r8 +#define __PT_RET_REG rsp +#define __PT_FP_REG rbp +#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__ */ + +#endif /* __KERNEL__ || __VMLINUX_H__ */ #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 */ -struct pt_regs; -#define PT_REGS_S390 const volatile user_pt_regs -#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2]) -#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3]) -#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4]) -#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5]) -#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6]) -#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14]) -/* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11]) -#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2]) -#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15]) -#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[3]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14]) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15]) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr) +#define __PT_REGS_CAST(x) ((const user_pt_regs *)(x)) +#define __PT_PARM1_REG gprs[2] +#define __PT_PARM2_REG gprs[3] +#define __PT_PARM3_REG gprs[4] +#define __PT_PARM4_REG gprs[5] +#define __PT_PARM5_REG gprs[6] +#define __PT_RET_REG grps[14] +#define __PT_FP_REG gprs[11] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG gprs[2] +#define __PT_SP_REG gprs[15] +#define __PT_IP_REG psw.addr +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2) #elif defined(bpf_target_arm) -#define PT_REGS_PARM1(x) ((x)->uregs[0]) -#define PT_REGS_PARM2(x) ((x)->uregs[1]) -#define PT_REGS_PARM3(x) ((x)->uregs[2]) -#define PT_REGS_PARM4(x) ((x)->uregs[3]) -#define PT_REGS_PARM5(x) ((x)->uregs[4]) -#define PT_REGS_RET(x) ((x)->uregs[14]) -#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_RC(x) ((x)->uregs[0]) -#define PT_REGS_SP(x) ((x)->uregs[13]) -#define PT_REGS_IP(x) ((x)->uregs[12]) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), uregs[0]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), uregs[1]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), uregs[2]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), uregs[3]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), uregs[4]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), uregs[14]) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), uregs[11]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), uregs[0]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), uregs[13]) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), uregs[12]) +#define __PT_PARM1_REG uregs[0] +#define __PT_PARM2_REG uregs[1] +#define __PT_PARM3_REG uregs[2] +#define __PT_PARM4_REG uregs[3] +#define __PT_PARM5_REG uregs[4] +#define __PT_RET_REG uregs[14] +#define __PT_FP_REG uregs[11] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG uregs[0] +#define __PT_SP_REG uregs[13] +#define __PT_IP_REG uregs[12] #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 */ -struct pt_regs; -#define PT_REGS_ARM64 const volatile struct user_pt_regs -#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0]) -#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1]) -#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2]) -#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3]) -#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4]) -#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30]) -/* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29]) -#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0]) -#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp) -#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[1]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[2]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[3]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[4]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[30]) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[29]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), regs[0]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), sp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_ARM64 *)(x), pc) +#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) +#define __PT_PARM1_REG regs[0] +#define __PT_PARM2_REG regs[1] +#define __PT_PARM3_REG regs[2] +#define __PT_PARM4_REG regs[3] +#define __PT_PARM5_REG regs[4] +#define __PT_RET_REG regs[30] +#define __PT_FP_REG regs[29] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG regs[0] +#define __PT_SP_REG sp +#define __PT_IP_REG pc +#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0) #elif defined(bpf_target_mips) -#define PT_REGS_PARM1(x) ((x)->regs[4]) -#define PT_REGS_PARM2(x) ((x)->regs[5]) -#define PT_REGS_PARM3(x) ((x)->regs[6]) -#define PT_REGS_PARM4(x) ((x)->regs[7]) -#define PT_REGS_PARM5(x) ((x)->regs[8]) -#define PT_REGS_RET(x) ((x)->regs[31]) -#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_RC(x) ((x)->regs[2]) -#define PT_REGS_SP(x) ((x)->regs[29]) -#define PT_REGS_IP(x) ((x)->cp0_epc) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), regs[4]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), regs[5]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), regs[6]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), regs[7]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), regs[8]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), regs[31]) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((x), regs[30]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), regs[2]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), regs[29]) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), cp0_epc) +#define __PT_PARM1_REG regs[4] +#define __PT_PARM2_REG regs[5] +#define __PT_PARM3_REG regs[6] +#define __PT_PARM4_REG regs[7] +#define __PT_PARM5_REG regs[8] +#define __PT_RET_REG regs[31] +#define __PT_FP_REG regs[30] /* Works only with CONFIG_FRAME_POINTER */ +#define __PT_RC_REG regs[2] +#define __PT_SP_REG regs[29] +#define __PT_IP_REG cp0_epc #elif defined(bpf_target_powerpc) -#define PT_REGS_PARM1(x) ((x)->gpr[3]) -#define PT_REGS_PARM2(x) ((x)->gpr[4]) -#define PT_REGS_PARM3(x) ((x)->gpr[5]) -#define PT_REGS_PARM4(x) ((x)->gpr[6]) -#define PT_REGS_PARM5(x) ((x)->gpr[7]) -#define PT_REGS_RC(x) ((x)->gpr[3]) -#define PT_REGS_SP(x) ((x)->sp) -#define PT_REGS_IP(x) ((x)->nip) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), gpr[3]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), gpr[4]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), gpr[5]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), gpr[6]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), gpr[7]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), gpr[3]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), sp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), nip) +#define __PT_PARM1_REG gpr[3] +#define __PT_PARM2_REG gpr[4] +#define __PT_PARM3_REG gpr[5] +#define __PT_PARM4_REG gpr[6] +#define __PT_PARM5_REG gpr[7] +#define __PT_RET_REG regs[31] +#define __PT_FP_REG __unsupported__ +#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) -#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0]) -#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1]) -#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2]) -#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3]) -#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4]) -#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7]) -#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0]) -#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP]) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0]) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I1]) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I2]) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I3]) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I4]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I7]) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((x), u_regs[UREG_I0]) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((x), u_regs[UREG_FP]) - +#define __PT_PARM1_REG u_regs[UREG_I0] +#define __PT_PARM2_REG u_regs[UREG_I1] +#define __PT_PARM3_REG u_regs[UREG_I2] +#define __PT_PARM4_REG u_regs[UREG_I3] +#define __PT_PARM5_REG u_regs[UREG_I4] +#define __PT_RET_REG u_regs[UREG_I7] +#define __PT_FP_REG __unsupported__ +#define __PT_RC_REG u_regs[UREG_I0] +#define __PT_SP_REG u_regs[UREG_FP] /* Should this also be a bpf_target check for the sparc case? */ #if defined(__arch64__) -#define PT_REGS_IP(x) ((x)->tpc) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), tpc) +#define __PT_IP_REG tpc #else -#define PT_REGS_IP(x) ((x)->pc) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc) +#define __PT_IP_REG pc #endif #elif defined(bpf_target_riscv) +#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) +#define __PT_PARM1_REG a0 +#define __PT_PARM2_REG a1 +#define __PT_PARM3_REG a2 +#define __PT_PARM4_REG a3 +#define __PT_PARM5_REG a4 +#define __PT_RET_REG ra +#define __PT_FP_REG s0 +#define __PT_RC_REG a0 +#define __PT_SP_REG sp +#define __PT_IP_REG pc +/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx + +#elif defined(bpf_target_arc) + +/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */ +#define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) +#define __PT_PARM1_REG scratch.r0 +#define __PT_PARM2_REG scratch.r1 +#define __PT_PARM3_REG scratch.r2 +#define __PT_PARM4_REG scratch.r3 +#define __PT_PARM5_REG scratch.r4 +#define __PT_RET_REG scratch.blink +#define __PT_FP_REG __unsupported__ +#define __PT_RC_REG scratch.r0 +#define __PT_SP_REG scratch.sp +#define __PT_IP_REG scratch.ret +/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx + +#endif + +#if defined(bpf_target_defined) + struct pt_regs; -#define PT_REGS_RV const volatile struct user_regs_struct -#define PT_REGS_PARM1(x) (((PT_REGS_RV *)(x))->a0) -#define PT_REGS_PARM2(x) (((PT_REGS_RV *)(x))->a1) -#define PT_REGS_PARM3(x) (((PT_REGS_RV *)(x))->a2) -#define PT_REGS_PARM4(x) (((PT_REGS_RV *)(x))->a3) -#define PT_REGS_PARM5(x) (((PT_REGS_RV *)(x))->a4) -#define PT_REGS_RET(x) (((PT_REGS_RV *)(x))->ra) -#define PT_REGS_FP(x) (((PT_REGS_RV *)(x))->s5) -#define PT_REGS_RC(x) (((PT_REGS_RV *)(x))->a5) -#define PT_REGS_SP(x) (((PT_REGS_RV *)(x))->sp) -#define PT_REGS_IP(x) (((PT_REGS_RV *)(x))->epc) - -#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a0) -#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a1) -#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a2) -#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a3) -#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a4) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), ra) -#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), fp) -#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a5) -#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), sp) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), epc) +/* allow some architecutres to override `struct pt_regs` */ +#ifndef __PT_REGS_CAST +#define __PT_REGS_CAST(x) (x) #endif +#define PT_REGS_PARM1(x) (__PT_REGS_CAST(x)->__PT_PARM1_REG) +#define PT_REGS_PARM2(x) (__PT_REGS_CAST(x)->__PT_PARM2_REG) +#define PT_REGS_PARM3(x) (__PT_REGS_CAST(x)->__PT_PARM3_REG) +#define PT_REGS_PARM4(x) (__PT_REGS_CAST(x)->__PT_PARM4_REG) +#define PT_REGS_PARM5(x) (__PT_REGS_CAST(x)->__PT_PARM5_REG) +#define PT_REGS_RET(x) (__PT_REGS_CAST(x)->__PT_RET_REG) +#define PT_REGS_FP(x) (__PT_REGS_CAST(x)->__PT_FP_REG) +#define PT_REGS_RC(x) (__PT_REGS_CAST(x)->__PT_RC_REG) +#define PT_REGS_SP(x) (__PT_REGS_CAST(x)->__PT_SP_REG) +#define PT_REGS_IP(x) (__PT_REGS_CAST(x)->__PT_IP_REG) + +#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_REG) +#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_REG) +#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_REG) +#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_REG) +#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_REG) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RET_REG) +#define PT_REGS_FP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_FP_REG) +#define PT_REGS_RC_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_RC_REG) +#define PT_REGS_SP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_SP_REG) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_IP_REG) + #if defined(bpf_target_powerpc) + #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP + #elif defined(bpf_target_sparc) + #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP -#elif defined(bpf_target_defined) + +#else + #define BPF_KPROBE_READ_RET_IP(ip, ctx) \ ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) \ - ({ bpf_probe_read_kernel(&(ip), sizeof(ip), \ - (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) + ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) + #endif -#if !defined(bpf_target_defined) +#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; }) #define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) @@ -363,7 +357,29 @@ 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; }) -#endif /* !defined(bpf_target_defined) */ +#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 @@ -375,25 +391,23 @@ struct pt_regs; #define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N #endif #ifndef ___bpf_narg -#define ___bpf_narg(...) \ - ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#define ___bpf_narg(...) ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) #endif -#define ___bpf_ctx_cast0() ctx -#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] -#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1] -#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2] -#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3] -#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4] -#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5] -#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6] -#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7] -#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8] +#define ___bpf_ctx_cast0() ctx +#define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] +#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), (void *)ctx[1] +#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), (void *)ctx[2] +#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), (void *)ctx[3] +#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), (void *)ctx[4] +#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), (void *)ctx[5] +#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), (void *)ctx[6] +#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), (void *)ctx[7] +#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), (void *)ctx[8] #define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), (void *)ctx[9] #define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), (void *)ctx[10] #define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), (void *)ctx[11] -#define ___bpf_ctx_cast(args...) \ - ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) +#define ___bpf_ctx_cast(args...) ___bpf_apply(___bpf_ctx_cast, ___bpf_narg(args))(args) /* * BPF_PROG is a convenience wrapper for generic tp_btf/fentry/fexit and @@ -412,7 +426,7 @@ struct pt_regs; */ #define BPF_PROG(name, args...) \ name(unsigned long long *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(unsigned long long *ctx, ##args); \ typeof(name(0)) name(unsigned long long *ctx) \ { \ @@ -421,24 +435,125 @@ typeof(name(0)) name(unsigned long long *ctx) \ return ____##name(___bpf_ctx_cast(args)); \ _Pragma("GCC diagnostic pop") \ } \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(unsigned long long *ctx, ##args) +#ifndef ___bpf_nth2 +#define ___bpf_nth2(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, \ + _14, _15, _16, _17, _18, _19, _20, _21, _22, _23, _24, N, ...) N +#endif +#ifndef ___bpf_narg2 +#define ___bpf_narg2(...) \ + ___bpf_nth2(_, ##__VA_ARGS__, 12, 12, 11, 11, 10, 10, 9, 9, 8, 8, 7, 7, \ + 6, 6, 5, 5, 4, 4, 3, 3, 2, 2, 1, 1, 0) +#endif + +#define ___bpf_treg_cnt(t) \ + __builtin_choose_expr(sizeof(t) == 1, 1, \ + __builtin_choose_expr(sizeof(t) == 2, 1, \ + __builtin_choose_expr(sizeof(t) == 4, 1, \ + __builtin_choose_expr(sizeof(t) == 8, 1, \ + __builtin_choose_expr(sizeof(t) == 16, 2, \ + (void)0))))) + +#define ___bpf_reg_cnt0() (0) +#define ___bpf_reg_cnt1(t, x) (___bpf_reg_cnt0() + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt2(t, x, args...) (___bpf_reg_cnt1(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt3(t, x, args...) (___bpf_reg_cnt2(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt4(t, x, args...) (___bpf_reg_cnt3(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt5(t, x, args...) (___bpf_reg_cnt4(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt6(t, x, args...) (___bpf_reg_cnt5(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt7(t, x, args...) (___bpf_reg_cnt6(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt8(t, x, args...) (___bpf_reg_cnt7(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt9(t, x, args...) (___bpf_reg_cnt8(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt10(t, x, args...) (___bpf_reg_cnt9(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt11(t, x, args...) (___bpf_reg_cnt10(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt12(t, x, args...) (___bpf_reg_cnt11(args) + ___bpf_treg_cnt(t)) +#define ___bpf_reg_cnt(args...) ___bpf_apply(___bpf_reg_cnt, ___bpf_narg2(args))(args) + +#define ___bpf_union_arg(t, x, n) \ + __builtin_choose_expr(sizeof(t) == 1, ({ union { __u8 z[1]; t x; } ___t = { .z = {ctx[n]}}; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 2, ({ union { __u16 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 4, ({ union { __u32 z[1]; t x; } ___t = { .z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 8, ({ union { __u64 z[1]; t x; } ___t = {.z = {ctx[n]} }; ___t.x; }), \ + __builtin_choose_expr(sizeof(t) == 16, ({ union { __u64 z[2]; t x; } ___t = {.z = {ctx[n], ctx[n + 1]} }; ___t.x; }), \ + (void)0))))) + +#define ___bpf_ctx_arg0(n, args...) +#define ___bpf_ctx_arg1(n, t, x) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt1(t, x)) +#define ___bpf_ctx_arg2(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt2(t, x, args)) ___bpf_ctx_arg1(n, args) +#define ___bpf_ctx_arg3(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt3(t, x, args)) ___bpf_ctx_arg2(n, args) +#define ___bpf_ctx_arg4(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt4(t, x, args)) ___bpf_ctx_arg3(n, args) +#define ___bpf_ctx_arg5(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt5(t, x, args)) ___bpf_ctx_arg4(n, args) +#define ___bpf_ctx_arg6(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt6(t, x, args)) ___bpf_ctx_arg5(n, args) +#define ___bpf_ctx_arg7(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt7(t, x, args)) ___bpf_ctx_arg6(n, args) +#define ___bpf_ctx_arg8(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt8(t, x, args)) ___bpf_ctx_arg7(n, args) +#define ___bpf_ctx_arg9(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt9(t, x, args)) ___bpf_ctx_arg8(n, args) +#define ___bpf_ctx_arg10(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt10(t, x, args)) ___bpf_ctx_arg9(n, args) +#define ___bpf_ctx_arg11(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt11(t, x, args)) ___bpf_ctx_arg10(n, args) +#define ___bpf_ctx_arg12(n, t, x, args...) , ___bpf_union_arg(t, x, n - ___bpf_reg_cnt12(t, x, args)) ___bpf_ctx_arg11(n, args) +#define ___bpf_ctx_arg(args...) ___bpf_apply(___bpf_ctx_arg, ___bpf_narg2(args))(___bpf_reg_cnt(args), args) + +#define ___bpf_ctx_decl0() +#define ___bpf_ctx_decl1(t, x) , t x +#define ___bpf_ctx_decl2(t, x, args...) , t x ___bpf_ctx_decl1(args) +#define ___bpf_ctx_decl3(t, x, args...) , t x ___bpf_ctx_decl2(args) +#define ___bpf_ctx_decl4(t, x, args...) , t x ___bpf_ctx_decl3(args) +#define ___bpf_ctx_decl5(t, x, args...) , t x ___bpf_ctx_decl4(args) +#define ___bpf_ctx_decl6(t, x, args...) , t x ___bpf_ctx_decl5(args) +#define ___bpf_ctx_decl7(t, x, args...) , t x ___bpf_ctx_decl6(args) +#define ___bpf_ctx_decl8(t, x, args...) , t x ___bpf_ctx_decl7(args) +#define ___bpf_ctx_decl9(t, x, args...) , t x ___bpf_ctx_decl8(args) +#define ___bpf_ctx_decl10(t, x, args...) , t x ___bpf_ctx_decl9(args) +#define ___bpf_ctx_decl11(t, x, args...) , t x ___bpf_ctx_decl10(args) +#define ___bpf_ctx_decl12(t, x, args...) , t x ___bpf_ctx_decl11(args) +#define ___bpf_ctx_decl(args...) ___bpf_apply(___bpf_ctx_decl, ___bpf_narg2(args))(args) + +/* + * BPF_PROG2 is an enhanced version of BPF_PROG in order to handle struct + * arguments. Since each struct argument might take one or two u64 values + * in the trampoline stack, argument type size is needed to place proper number + * of u64 values for each argument. Therefore, BPF_PROG2 has different + * syntax from BPF_PROG. For example, for the following BPF_PROG syntax: + * + * int BPF_PROG(test2, int a, int b) { ... } + * + * the corresponding BPF_PROG2 syntax is: + * + * int BPF_PROG2(test2, int, a, int, b) { ... } + * + * where type and the corresponding argument name are separated by comma. + * + * Use BPF_PROG2 macro if one of the arguments might be a struct/union larger + * than 8 bytes: + * + * int BPF_PROG2(test_struct_arg, struct bpf_testmod_struct_arg_1, a, int, b, + * int, c, int, d, struct bpf_testmod_struct_arg_2, e, int, ret) + * { + * // access a, b, c, d, e, and ret directly + * ... + * } + */ +#define BPF_PROG2(name, args...) \ +name(unsigned long long *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx ___bpf_ctx_decl(args)); \ +typeof(name(0)) name(unsigned long long *ctx) \ +{ \ + return ____##name(ctx ___bpf_ctx_arg(args)); \ +} \ +static __always_inline typeof(name(0)) \ +____##name(unsigned long long *ctx ___bpf_ctx_decl(args)) + struct pt_regs; -#define ___bpf_kprobe_args0() ctx -#define ___bpf_kprobe_args1(x) \ - ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) -#define ___bpf_kprobe_args2(x, args...) \ - ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) -#define ___bpf_kprobe_args3(x, args...) \ - ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) -#define ___bpf_kprobe_args4(x, args...) \ - ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) -#define ___bpf_kprobe_args5(x, args...) \ - ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) -#define ___bpf_kprobe_args(args...) \ - ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) +#define ___bpf_kprobe_args0() ctx +#define ___bpf_kprobe_args1(x) ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) +#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) +#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) +#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) +#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) +#define ___bpf_kprobe_args(args...) ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) /* * BPF_KPROBE serves the same purpose for kprobes as BPF_PROG for @@ -452,7 +567,7 @@ struct pt_regs; */ #define BPF_KPROBE(name, args...) \ name(struct pt_regs *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args); \ typeof(name(0)) name(struct pt_regs *ctx) \ { \ @@ -461,14 +576,12 @@ typeof(name(0)) name(struct pt_regs *ctx) \ return ____##name(___bpf_kprobe_args(args)); \ _Pragma("GCC diagnostic pop") \ } \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args) -#define ___bpf_kretprobe_args0() ctx -#define ___bpf_kretprobe_args1(x) \ - ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx) -#define ___bpf_kretprobe_args(args...) \ - ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) +#define ___bpf_kretprobe_args0() ctx +#define ___bpf_kretprobe_args1(x) ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx) +#define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) /* * BPF_KRETPROBE is similar to BPF_KPROBE, except, it only provides optional @@ -478,7 +591,7 @@ ____##name(struct pt_regs *ctx, ##args) */ #define BPF_KRETPROBE(name, args...) \ name(struct pt_regs *ctx); \ -static __attribute__((always_inline)) typeof(name(0)) \ +static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args); \ typeof(name(0)) name(struct pt_regs *ctx) \ { \ @@ -489,4 +602,69 @@ typeof(name(0)) name(struct pt_regs *ctx) \ } \ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) +/* If kernel has CONFIG_ARCH_HAS_SYSCALL_WRAPPER, read pt_regs directly */ +#define ___bpf_syscall_args0() ctx +#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_SYSCALL(regs) +#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_SYSCALL(regs) +#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs) +#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs) +#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs) +#define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args) + +/* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */ +#define ___bpf_syswrap_args0() ctx +#define ___bpf_syswrap_args1(x) ___bpf_syswrap_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args(args...) ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args) + +/* + * BPF_KSYSCALL 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(). + * + * At the moment BPF_KSYSCALL does not transparently handle all the calling + * convention quirks for the following syscalls: + * + * - mmap(): __ARCH_WANT_SYS_OLD_MMAP. + * - clone(): CONFIG_CLONE_BACKWARDS, CONFIG_CLONE_BACKWARDS2 and + * CONFIG_CLONE_BACKWARDS3. + * - socket-related syscalls: __ARCH_WANT_SYS_SOCKETCALL. + * - compat syscalls. + * + * This may or may not change in the future. User needs to take extra measures + * to handle such quirks explicitly, if necessary. + * + * This macro relies on BPF CO-RE support and virtual __kconfig externs. + */ +#define BPF_KSYSCALL(name, args...) \ +name(struct pt_regs *ctx); \ +extern _Bool LINUX_HAS_SYSCALL_WRAPPER __kconfig; \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + struct pt_regs *regs = LINUX_HAS_SYSCALL_WRAPPER \ + ? (struct pt_regs *)PT_REGS_PARM1(ctx) \ + : ctx; \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + if (LINUX_HAS_SYSCALL_WRAPPER) \ + return ____##name(___bpf_syswrap_args(args)); \ + else \ + return ____##name(___bpf_syscall_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args) + +#define BPF_KPROBE_SYSCALL BPF_KSYSCALL + #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 7e4c5586bd87..d88647da2c7f 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -130,7 +130,7 @@ static inline __u64 ptr_to_u64(const void *ptr) /* Ensure given dynamically allocated memory region pointed to by *data* with * capacity of *cap_cnt* elements each taking *elem_sz* bytes has enough - * memory to accomodate *add_cnt* new elements, assuming *cur_cnt* elements + * memory to accommodate *add_cnt* new elements, assuming *cur_cnt* elements * are already used. At most *max_cnt* elements can be ever allocated. * If necessary, memory is reallocated and all existing data is copied over, * new pointer to the memory region is stored at *data, new memory region @@ -299,11 +299,14 @@ static int btf_type_size(const struct btf_type *t) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: return base_size; case BTF_KIND_INT: return base_size + sizeof(__u32); case BTF_KIND_ENUM: return base_size + vlen * sizeof(struct btf_enum); + case BTF_KIND_ENUM64: + return base_size + vlen * sizeof(struct btf_enum64); case BTF_KIND_ARRAY: return base_size + sizeof(struct btf_array); case BTF_KIND_STRUCT: @@ -333,6 +336,7 @@ static void btf_bswap_type_base(struct btf_type *t) static int btf_bswap_type_rest(struct btf_type *t) { struct btf_var_secinfo *v; + struct btf_enum64 *e64; struct btf_member *m; struct btf_array *a; struct btf_param *p; @@ -349,6 +353,7 @@ static int btf_bswap_type_rest(struct btf_type *t) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: return 0; case BTF_KIND_INT: *(__u32 *)(t + 1) = bswap_32(*(__u32 *)(t + 1)); @@ -359,6 +364,13 @@ static int btf_bswap_type_rest(struct btf_type *t) e->val = bswap_32(e->val); } return 0; + case BTF_KIND_ENUM64: + for (i = 0, e64 = btf_enum64(t); i < vlen; i++, e64++) { + e64->name_off = bswap_32(e64->name_off); + e64->val_lo32 = bswap_32(e64->val_lo32); + e64->val_hi32 = bswap_32(e64->val_hi32); + } + return 0; case BTF_KIND_ARRAY: a = btf_array(t); a->type = bswap_32(a->type); @@ -436,11 +448,6 @@ static int btf_parse_type_sec(struct btf *btf) return 0; } -__u32 btf__get_nr_types(const struct btf *btf) -{ - return btf->start_id + btf->nr_types - 1; -} - __u32 btf__type_cnt(const struct btf *btf) { return btf->start_id + btf->nr_types; @@ -452,7 +459,7 @@ const struct btf *btf__base_btf(const struct btf *btf) } /* internal helper returning non-const pointer to a type */ -struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id) +struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id) { if (type_id == 0) return &btf_void; @@ -470,9 +477,22 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) static int determine_ptr_size(const struct btf *btf) { + static const char * const long_aliases[] = { + "long", + "long int", + "int long", + "unsigned long", + "long unsigned", + "unsigned long int", + "unsigned int long", + "long unsigned int", + "long int unsigned", + "int unsigned long", + "int long unsigned", + }; const struct btf_type *t; const char *name; - int i, n; + int i, j, n; if (btf->base_btf && btf->base_btf->ptr_sz > 0) return btf->base_btf->ptr_sz; @@ -483,15 +503,16 @@ static int determine_ptr_size(const struct btf *btf) if (!btf_is_int(t)) continue; + if (t->size != 4 && t->size != 8) + continue; + name = btf__name_by_offset(btf, t->name_off); if (!name) continue; - if (strcmp(name, "long int") == 0 || - strcmp(name, "long unsigned int") == 0) { - if (t->size != 4 && t->size != 8) - continue; - return t->size; + for (j = 0; j < ARRAY_SIZE(long_aliases); j++) { + if (strcmp(name, long_aliases[j]) == 0) + return t->size; } } @@ -595,6 +616,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_DATASEC: case BTF_KIND_FLOAT: size = t->size; @@ -608,6 +630,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_RESTRICT: case BTF_KIND_VAR: case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: type_id = t->type; break; case BTF_KIND_ARRAY: @@ -641,6 +664,7 @@ int btf__align_of(const struct btf *btf, __u32 id) switch (kind) { case BTF_KIND_INT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FLOAT: return min(btf_ptr_sz(btf), (size_t)t->size); case BTF_KIND_PTR: @@ -649,6 +673,7 @@ int btf__align_of(const struct btf *btf, __u32 id) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: return btf__align_of(btf, t->type); case BTF_KIND_ARRAY: return btf__align_of(btf, btf_array(t)->type); @@ -1120,55 +1145,85 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf) static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian); -int btf__load_into_kernel(struct btf *btf) +int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level) { - __u32 log_buf_size = 0, raw_size; - char *log_buf = NULL; + LIBBPF_OPTS(bpf_btf_load_opts, opts); + __u32 buf_sz = 0, raw_size; + char *buf = NULL, *tmp; void *raw_data; int err = 0; if (btf->fd >= 0) return libbpf_err(-EEXIST); + if (log_sz && !log_buf) + return libbpf_err(-EINVAL); -retry_load: - if (log_buf_size) { - log_buf = malloc(log_buf_size); - if (!log_buf) - return libbpf_err(-ENOMEM); - - *log_buf = 0; - } - + /* cache native raw data representation */ raw_data = btf_get_raw_data(btf, &raw_size, false); if (!raw_data) { err = -ENOMEM; goto done; } - /* cache native raw data representation */ btf->raw_size = raw_size; btf->raw_data = raw_data; - btf->fd = bpf_load_btf(raw_data, raw_size, log_buf, log_buf_size, false); +retry_load: + /* if log_level is 0, we won't provide log_buf/log_size to the kernel, + * initially. Only if BTF loading fails, we bump log_level to 1 and + * retry, using either auto-allocated or custom log_buf. This way + * non-NULL custom log_buf provides a buffer just in case, but hopes + * for successful load and no need for log_buf. + */ + if (log_level) { + /* if caller didn't provide custom log_buf, we'll keep + * allocating our own progressively bigger buffers for BTF + * verification log + */ + if (!log_buf) { + buf_sz = max((__u32)BPF_LOG_BUF_SIZE, buf_sz * 2); + tmp = realloc(buf, buf_sz); + if (!tmp) { + err = -ENOMEM; + goto done; + } + buf = tmp; + buf[0] = '\0'; + } + + opts.log_buf = log_buf ? log_buf : buf; + opts.log_size = log_buf ? log_sz : buf_sz; + opts.log_level = log_level; + } + + btf->fd = bpf_btf_load(raw_data, raw_size, &opts); if (btf->fd < 0) { - if (!log_buf || errno == ENOSPC) { - log_buf_size = max((__u32)BPF_LOG_BUF_SIZE, - log_buf_size << 1); - free(log_buf); + /* time to turn on verbose mode and try again */ + if (log_level == 0) { + log_level = 1; goto retry_load; } + /* only retry if caller didn't provide custom log_buf, but + * make sure we can never overflow buf_sz + */ + if (!log_buf && errno == ENOSPC && buf_sz <= UINT_MAX / 2) + goto retry_load; err = -errno; - pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno); - if (*log_buf) - pr_warn("%s\n", log_buf); - goto done; + pr_warn("BTF loading error: %d\n", err); + /* don't print out contents of custom log_buf */ + if (!log_buf && buf[0]) + pr_warn("-- BEGIN BTF LOAD LOG ---\n%s\n-- END BTF LOAD LOG --\n", buf); } done: - free(log_buf); + free(buf); return libbpf_err(err); } -int btf__load(struct btf *) __attribute__((alias("btf__load_into_kernel"))); + +int btf__load_into_kernel(struct btf *btf) +{ + return btf_load_into_kernel(btf, NULL, 0, 0); +} int btf__fd(const struct btf *btf) { @@ -1346,92 +1401,6 @@ struct btf *btf__load_from_kernel_by_id(__u32 id) return btf__load_from_kernel_by_id_split(id, NULL); } -int btf__get_from_id(__u32 id, struct btf **btf) -{ - struct btf *res; - int err; - - *btf = NULL; - res = btf__load_from_kernel_by_id(id); - err = libbpf_get_error(res); - - if (err) - return libbpf_err(err); - - *btf = res; - return 0; -} - -int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, - __u32 expected_key_size, __u32 expected_value_size, - __u32 *key_type_id, __u32 *value_type_id) -{ - const struct btf_type *container_type; - const struct btf_member *key, *value; - const size_t max_name = 256; - char container_name[max_name]; - __s64 key_size, value_size; - __s32 container_id; - - if (snprintf(container_name, max_name, "____btf_map_%s", map_name) == max_name) { - pr_warn("map:%s length of '____btf_map_%s' is too long\n", - map_name, map_name); - return libbpf_err(-EINVAL); - } - - container_id = btf__find_by_name(btf, container_name); - if (container_id < 0) { - pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n", - map_name, container_name); - return libbpf_err(container_id); - } - - container_type = btf__type_by_id(btf, container_id); - if (!container_type) { - pr_warn("map:%s cannot find BTF type for container_id:%u\n", - map_name, container_id); - return libbpf_err(-EINVAL); - } - - if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) { - pr_warn("map:%s container_name:%s is an invalid container struct\n", - map_name, container_name); - return libbpf_err(-EINVAL); - } - - key = btf_members(container_type); - value = key + 1; - - key_size = btf__resolve_size(btf, key->type); - if (key_size < 0) { - pr_warn("map:%s invalid BTF key_type_size\n", map_name); - return libbpf_err(key_size); - } - - if (expected_key_size != key_size) { - pr_warn("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", - map_name, (__u32)key_size, expected_key_size); - return libbpf_err(-EINVAL); - } - - value_size = btf__resolve_size(btf, value->type); - if (value_size < 0) { - pr_warn("map:%s invalid BTF value_type_size\n", map_name); - return libbpf_err(value_size); - } - - if (expected_value_size != value_size) { - pr_warn("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", - map_name, (__u32)value_size, expected_value_size); - return libbpf_err(-EINVAL); - } - - *key_type_id = key->type; - *value_type_id = value->type; - - return 0; -} - static void btf_invalidate_raw_data(struct btf *btf) { if (btf->raw_data) { @@ -1584,20 +1553,37 @@ 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; } @@ -1644,6 +1630,9 @@ 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 }; @@ -1677,6 +1666,11 @@ 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); @@ -1718,6 +1712,8 @@ 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: @@ -1731,6 +1727,8 @@ 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); } @@ -2050,20 +2048,8 @@ int btf__add_field(struct btf *btf, const char *name, int type_id, return 0; } -/* - * Append new BTF_KIND_ENUM type with: - * - *name* - name of the enum, can be NULL or empty for anonymous enums; - * - *byte_sz* - size of the enum, in bytes. - * - * Enum initially has no enum values in it (and corresponds to enum forward - * declaration). Enumerator values can be added by btf__add_enum_value() - * immediately after btf__add_enum() succeeds. - * - * Returns: - * - >0, type ID of newly added BTF type; - * - <0, on error. - */ -int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz) +static int btf_add_enum_common(struct btf *btf, const char *name, __u32 byte_sz, + bool is_signed, __u8 kind) { struct btf_type *t; int sz, name_off = 0; @@ -2088,13 +2074,35 @@ int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz) /* start out with vlen=0; it will be adjusted when adding enum values */ t->name_off = name_off; - t->info = btf_type_info(BTF_KIND_ENUM, 0, 0); + t->info = btf_type_info(kind, 0, is_signed); t->size = byte_sz; return btf_commit_type(btf, sz); } /* + * Append new BTF_KIND_ENUM type with: + * - *name* - name of the enum, can be NULL or empty for anonymous enums; + * - *byte_sz* - size of the enum, in bytes. + * + * Enum initially has no enum values in it (and corresponds to enum forward + * declaration). Enumerator values can be added by btf__add_enum_value() + * immediately after btf__add_enum() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz) +{ + /* + * set the signedness to be unsigned, it will change to signed + * if any later enumerator is negative. + */ + return btf_add_enum_common(btf, name, byte_sz, false, BTF_KIND_ENUM); +} + +/* * Append new enum value for the current ENUM type with: * - *name* - name of the enumerator value, can't be NULL or empty; * - *value* - integer value corresponding to enum value *name*; @@ -2141,6 +2149,82 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value) t = btf_last_type(btf); btf_type_inc_vlen(t); + /* if negative value, set signedness to signed */ + if (value < 0) + t->info = btf_type_info(btf_kind(t), btf_vlen(t), true); + + btf->hdr->type_len += sz; + btf->hdr->str_off += sz; + return 0; +} + +/* + * Append new BTF_KIND_ENUM64 type with: + * - *name* - name of the enum, can be NULL or empty for anonymous enums; + * - *byte_sz* - size of the enum, in bytes. + * - *is_signed* - whether the enum values are signed or not; + * + * Enum initially has no enum values in it (and corresponds to enum forward + * declaration). Enumerator values can be added by btf__add_enum64_value() + * immediately after btf__add_enum64() succeeds. + * + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_enum64(struct btf *btf, const char *name, __u32 byte_sz, + bool is_signed) +{ + return btf_add_enum_common(btf, name, byte_sz, is_signed, + BTF_KIND_ENUM64); +} + +/* + * Append new enum value for the current ENUM64 type with: + * - *name* - name of the enumerator value, can't be NULL or empty; + * - *value* - integer value corresponding to enum value *name*; + * Returns: + * - 0, on success; + * - <0, on error. + */ +int btf__add_enum64_value(struct btf *btf, const char *name, __u64 value) +{ + struct btf_enum64 *v; + struct btf_type *t; + int sz, name_off; + + /* last type should be BTF_KIND_ENUM64 */ + if (btf->nr_types == 0) + return libbpf_err(-EINVAL); + t = btf_last_type(btf); + if (!btf_is_enum64(t)) + return libbpf_err(-EINVAL); + + /* non-empty name */ + if (!name || !name[0]) + return libbpf_err(-EINVAL); + + /* decompose and invalidate raw data */ + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_enum64); + v = btf_add_type_mem(btf, sz); + if (!v) + return libbpf_err(-ENOMEM); + + name_off = btf__add_str(btf, name); + if (name_off < 0) + return name_off; + + v->name_off = name_off; + v->val_lo32 = (__u32)value; + v->val_hi32 = value >> 32; + + /* update parent type's vlen */ + t = btf_last_type(btf); + btf_type_inc_vlen(t); + btf->hdr->type_len += sz; btf->hdr->str_off += sz; return 0; @@ -2236,6 +2320,22 @@ int btf__add_restrict(struct btf *btf, int ref_type_id) } /* + * Append new BTF_KIND_TYPE_TAG type with: + * - *value*, non-empty/non-NULL tag value; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id) +{ + if (!value|| !value[0]) + return libbpf_err(-EINVAL); + + return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id); +} + +/* * Append new BTF_KIND_FUNC type with: * - *name*, non-empty/non-NULL name; * - *proto_type_id* - FUNC_PROTO's type ID, it might not exist yet; @@ -2545,6 +2645,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, const struct btf_ext_info_sec *sinfo; struct btf_ext_info *ext_info; __u32 info_left, record_size; + size_t sec_cnt = 0; /* The start of the info sec (including the __u32 record_size). */ void *info; @@ -2608,8 +2709,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return -EINVAL; } - total_record_size = sec_hdrlen + - (__u64)num_records * record_size; + total_record_size = sec_hdrlen + (__u64)num_records * record_size; if (info_left < total_record_size) { pr_debug("%s section has incorrect num_records in .BTF.ext\n", ext_sec->desc); @@ -2618,12 +2718,14 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, info_left -= total_record_size; sinfo = (void *)sinfo + total_record_size; + sec_cnt++; } ext_info = ext_sec->ext_info; ext_info->len = ext_sec->len - sizeof(__u32); ext_info->rec_size = record_size; ext_info->info = info + sizeof(__u32); + ext_info->sec_cnt = sec_cnt; return 0; } @@ -2707,19 +2809,18 @@ void btf_ext__free(struct btf_ext *btf_ext) { if (IS_ERR_OR_NULL(btf_ext)) return; + free(btf_ext->func_info.sec_idxs); + free(btf_ext->line_info.sec_idxs); + free(btf_ext->core_relo_info.sec_idxs); free(btf_ext->data); free(btf_ext); } -struct btf_ext *btf_ext__new(__u8 *data, __u32 size) +struct btf_ext *btf_ext__new(const __u8 *data, __u32 size) { struct btf_ext *btf_ext; int err; - err = btf_ext_parse_hdr(data, size); - if (err) - return libbpf_err_ptr(err); - btf_ext = calloc(1, sizeof(struct btf_ext)); if (!btf_ext) return libbpf_err_ptr(-ENOMEM); @@ -2732,6 +2833,10 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) } memcpy(btf_ext->data, data, size); + err = btf_ext_parse_hdr(btf_ext->data, size); + if (err) + goto done; + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) { err = -EINVAL; goto done; @@ -2745,10 +2850,8 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) if (err) goto done; - if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) { - err = -EINVAL; - goto done; - } + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + goto done; /* skip core relos parsing */ err = btf_ext_setup_core_relos(btf_ext); if (err) @@ -2769,85 +2872,9 @@ const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size) return btf_ext->data; } -static int btf_ext_reloc_info(const struct btf *btf, - const struct btf_ext_info *ext_info, - const char *sec_name, __u32 insns_cnt, - void **info, __u32 *cnt) -{ - __u32 sec_hdrlen = sizeof(struct btf_ext_info_sec); - __u32 i, record_size, existing_len, records_len; - struct btf_ext_info_sec *sinfo; - const char *info_sec_name; - __u64 remain_len; - void *data; - - record_size = ext_info->rec_size; - sinfo = ext_info->info; - remain_len = ext_info->len; - while (remain_len > 0) { - records_len = sinfo->num_info * record_size; - info_sec_name = btf__name_by_offset(btf, sinfo->sec_name_off); - if (strcmp(info_sec_name, sec_name)) { - remain_len -= sec_hdrlen + records_len; - sinfo = (void *)sinfo + sec_hdrlen + records_len; - continue; - } - - existing_len = (*cnt) * record_size; - data = realloc(*info, existing_len + records_len); - if (!data) - return libbpf_err(-ENOMEM); - - memcpy(data + existing_len, sinfo->data, records_len); - /* adjust insn_off only, the rest data will be passed - * to the kernel. - */ - for (i = 0; i < sinfo->num_info; i++) { - __u32 *insn_off; - - insn_off = data + existing_len + (i * record_size); - *insn_off = *insn_off / sizeof(struct bpf_insn) + insns_cnt; - } - *info = data; - *cnt += sinfo->num_info; - return 0; - } - - return libbpf_err(-ENOENT); -} - -int btf_ext__reloc_func_info(const struct btf *btf, - const struct btf_ext *btf_ext, - const char *sec_name, __u32 insns_cnt, - void **func_info, __u32 *cnt) -{ - return btf_ext_reloc_info(btf, &btf_ext->func_info, sec_name, - insns_cnt, func_info, cnt); -} - -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) -{ - return btf_ext_reloc_info(btf, &btf_ext->line_info, sec_name, - insns_cnt, line_info, cnt); -} - -__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext) -{ - return btf_ext->func_info.rec_size; -} - -__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext) -{ - return btf_ext->line_info.rec_size; -} - struct btf_dedup; -static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, - const struct btf_dedup_opts *opts); +static struct btf_dedup *btf_dedup_new(struct btf *btf, const struct btf_dedup_opts *opts); static void btf_dedup_free(struct btf_dedup *d); static int btf_dedup_prep(struct btf_dedup *d); static int btf_dedup_strings(struct btf_dedup *d); @@ -2994,12 +3021,15 @@ static int btf_dedup_remap_types(struct btf_dedup *d); * deduplicating structs/unions is described in greater details in comments for * `btf_dedup_is_equiv` function. */ -int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, - const struct btf_dedup_opts *opts) +int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts) { - struct btf_dedup *d = btf_dedup_new(btf, btf_ext, opts); + struct btf_dedup *d; int err; + if (!OPTS_VALID(opts, btf_dedup_opts)) + return libbpf_err(-EINVAL); + + d = btf_dedup_new(btf, opts); if (IS_ERR(d)) { pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d)); return libbpf_err(-EINVAL); @@ -3163,8 +3193,7 @@ static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx) return k1 == k2; } -static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, - const struct btf_dedup_opts *opts) +static struct btf_dedup *btf_dedup_new(struct btf *btf, const struct btf_dedup_opts *opts) { struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup)); hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn; @@ -3173,13 +3202,11 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, if (!d) return ERR_PTR(-ENOMEM); - d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds; - /* dedup_table_size is now used only to force collisions in tests */ - if (opts && opts->dedup_table_size == 1) + if (OPTS_GET(opts, force_collisions, false)) hash_fn = btf_dedup_collision_hash_fn; d->btf = btf; - d->btf_ext = btf_ext; + d->btf_ext = OPTS_GET(opts, btf_ext, NULL); d->dedup_table = hashmap__new(hash_fn, btf_dedup_equal_fn, NULL); if (IS_ERR(d->dedup_table)) { @@ -3372,7 +3399,7 @@ static bool btf_equal_int_tag(struct btf_type *t1, struct btf_type *t2) return info1 == info2; } -/* Calculate type signature hash of ENUM. */ +/* Calculate type signature hash of ENUM/ENUM64. */ static long btf_hash_enum(struct btf_type *t) { long h; @@ -3406,9 +3433,31 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) return true; } +static bool btf_equal_enum64(struct btf_type *t1, struct btf_type *t2) +{ + const struct btf_enum64 *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + vlen = btf_vlen(t1); + m1 = btf_enum64(t1); + m2 = btf_enum64(t2); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off || m1->val_lo32 != m2->val_lo32 || + m1->val_hi32 != m2->val_hi32) + return false; + m1++; + m2++; + } + return true; +} + static inline bool btf_is_enum_fwd(struct btf_type *t) { - return btf_is_enum(t) && btf_vlen(t) == 0; + return btf_is_any_enum(t) && btf_vlen(t) == 0; } static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) @@ -3421,6 +3470,17 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) t1->size == t2->size; } +static bool btf_compat_enum64(struct btf_type *t1, struct btf_type *t2) +{ + if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2)) + return btf_equal_enum64(t1, t2); + + /* ignore vlen when comparing */ + return t1->name_off == t2->name_off && + (t1->info & ~0xffff) == (t2->info & ~0xffff) && + t1->size == t2->size; +} + /* * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs, * as referenced type IDs equivalence is established separately during type @@ -3443,8 +3503,8 @@ static long btf_hash_struct(struct btf_type *t) } /* - * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type - * IDs. This check is performed during type graph equivalence check and + * Check structural compatibility of two STRUCTs/UNIONs, ignoring referenced + * type IDs. This check is performed during type graph equivalence check and * referenced types equivalence is checked separately. */ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) @@ -3625,6 +3685,7 @@ static int btf_dedup_prep(struct btf_dedup *d) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: h = btf_hash_common(t); break; case BTF_KIND_INT: @@ -3632,6 +3693,7 @@ static int btf_dedup_prep(struct btf_dedup *d) h = btf_hash_int_decl_tag(t); break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: h = btf_hash_enum(t); break; case BTF_KIND_STRUCT: @@ -3685,6 +3747,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_VAR: case BTF_KIND_DATASEC: case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: return 0; case BTF_KIND_INT: @@ -3708,8 +3771,6 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) new_id = cand_id; break; } - if (d->opts.dont_resolve_fwds) - continue; if (btf_compat_enum(t, cand)) { if (btf_is_enum_fwd(t)) { /* resolve fwd to full enum */ @@ -3722,6 +3783,27 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) } break; + case BTF_KIND_ENUM64: + h = btf_hash_enum(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_enum64(t, cand)) { + new_id = cand_id; + break; + } + if (btf_compat_enum64(t, cand)) { + if (btf_is_enum_fwd(t)) { + /* resolve fwd to full enum */ + new_id = cand_id; + break; + } + /* resolve canonical enum fwd to full enum */ + d->map[cand_id] = type_id; + } + } + break; + case BTF_KIND_FWD: case BTF_KIND_FLOAT: h = btf_hash_common(t); @@ -3817,6 +3899,31 @@ static int btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2) return btf_equal_array(t1, t2); } +/* Check if given two types are identical STRUCT/UNION definitions */ +static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id2) +{ + const struct btf_member *m1, *m2; + struct btf_type *t1, *t2; + int n, i; + + t1 = btf_type_by_id(d->btf, id1); + t2 = btf_type_by_id(d->btf, id2); + + if (!btf_is_composite(t1) || btf_kind(t1) != btf_kind(t2)) + return false; + + if (!btf_shallow_equal_struct(t1, t2)) + return false; + + m1 = btf_members(t1); + m2 = btf_members(t2); + for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) { + if (m1->type != m2->type) + return false; + } + return true; +} + /* * Check equivalence of BTF type graph formed by candidate struct/union (we'll * call it "candidate graph" in this description for brevity) to a type graph @@ -3928,6 +4035,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, hypot_type_id = d->hypot_map[canon_id]; if (hypot_type_id <= BTF_MAX_NR_TYPES) { + if (hypot_type_id == cand_id) + return 1; /* In some cases compiler will generate different DWARF types * for *identical* array type definitions and use them for * different fields within the *same* struct. This breaks type @@ -3936,8 +4045,18 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, * types within a single CU. So work around that by explicitly * allowing identical array types here. */ - return hypot_type_id == cand_id || - btf_dedup_identical_arrays(d, hypot_type_id, cand_id); + if (btf_dedup_identical_arrays(d, hypot_type_id, cand_id)) + return 1; + /* It turns out that similar situation can happen with + * struct/union sometimes, sigh... Handle the case where + * structs/unions are exactly the same, down to the referenced + * type IDs. Anything more complicated (e.g., if referenced + * types are different, but equivalent) is *way more* + * complicated and requires a many-to-many equivalence mapping. + */ + if (btf_dedup_identical_structs(d, hypot_type_id, cand_id)) + return 1; + return 0; } if (btf_dedup_hypot_map_add(d, canon_id, cand_id)) @@ -3952,8 +4071,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return 0; /* FWD <--> STRUCT/UNION equivalence check, if enabled */ - if (!d->opts.dont_resolve_fwds - && (cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD) + if ((cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD) && cand_kind != canon_kind) { __u16 real_kind; __u16 fwd_kind; @@ -3979,10 +4097,10 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return btf_equal_int_tag(cand_type, canon_type); case BTF_KIND_ENUM: - if (d->opts.dont_resolve_fwds) - return btf_equal_enum(cand_type, canon_type); - else - return btf_compat_enum(cand_type, canon_type); + return btf_compat_enum(cand_type, canon_type); + + case BTF_KIND_ENUM64: + return btf_compat_enum64(cand_type, canon_type); case BTF_KIND_FWD: case BTF_KIND_FLOAT: @@ -3994,6 +4112,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + case BTF_KIND_TYPE_TAG: if (cand_type->info != canon_type->info) return 0; return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); @@ -4289,6 +4408,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + case BTF_KIND_TYPE_TAG: ref_type_id = btf_dedup_ref_type(d, t->type); if (ref_type_id < 0) return ref_type_id; @@ -4522,20 +4642,17 @@ static int btf_dedup_remap_types(struct btf_dedup *d) */ struct btf *btf__load_vmlinux_btf(void) { - struct { - const char *path_fmt; - bool raw_btf; - } locations[] = { + const char *locations[] = { /* try canonical vmlinux BTF through sysfs first */ - { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, - /* fall back to trying to find vmlinux ELF on disk otherwise */ - { "/boot/vmlinux-%1$s" }, - { "/lib/modules/%1$s/vmlinux-%1$s" }, - { "/lib/modules/%1$s/build/vmlinux" }, - { "/usr/lib/modules/%1$s/kernel/vmlinux" }, - { "/usr/lib/debug/boot/vmlinux-%1$s" }, - { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, - { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, + "/sys/kernel/btf/vmlinux", + /* fall back to trying to find vmlinux on disk otherwise */ + "/boot/vmlinux-%1$s", + "/lib/modules/%1$s/vmlinux-%1$s", + "/lib/modules/%1$s/build/vmlinux", + "/usr/lib/modules/%1$s/kernel/vmlinux", + "/usr/lib/debug/boot/vmlinux-%1$s", + "/usr/lib/debug/boot/vmlinux-%1$s.debug", + "/usr/lib/debug/lib/modules/%1$s/vmlinux", }; char path[PATH_MAX + 1]; struct utsname buf; @@ -4545,15 +4662,12 @@ struct btf *btf__load_vmlinux_btf(void) uname(&buf); for (i = 0; i < ARRAY_SIZE(locations); i++) { - snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); + snprintf(path, PATH_MAX, locations[i], buf.release); - if (access(path, R_OK)) + if (faccessat(AT_FDCWD, path, R_OK, AT_EACCESS)) continue; - if (locations[i].raw_btf) - btf = btf__parse_raw(path); - else - btf = btf__parse_elf(path, NULL); + btf = btf__parse(path, NULL); err = libbpf_get_error(btf); pr_debug("loading kernel BTF '%s': %d\n", path, err); if (err) @@ -4584,6 +4698,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct case BTF_KIND_INT: case BTF_KIND_FLOAT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: return 0; case BTF_KIND_FWD: @@ -4595,6 +4710,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct case BTF_KIND_FUNC: case BTF_KIND_VAR: case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: return visit(&t->type, ctx); case BTF_KIND_ARRAY: { @@ -4677,6 +4793,16 @@ int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ct } break; } + case BTF_KIND_ENUM64: { + struct btf_enum64 *m = btf_enum64(t); + + for (i = 0, n = btf_vlen(t); i < n; i++, m++) { + err = visit(&m->name_off, ctx); + if (err) + return err; + } + break; + } case BTF_KIND_FUNC_PROTO: { struct btf_param *m = btf_params(t); diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index bc005ba3ceec..8e6880d91c84 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -116,24 +116,15 @@ LIBBPF_API struct btf *btf__parse_raw_split(const char *path, struct btf *base_b LIBBPF_API struct btf *btf__load_vmlinux_btf(void); LIBBPF_API struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_btf); -LIBBPF_API struct btf *libbpf_find_kernel_btf(void); LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id); LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf); -LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead") -LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf); -LIBBPF_DEPRECATED_SINCE(0, 6, "intended for internal libbpf use only") -LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf); -LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead") -LIBBPF_API int btf__load(struct btf *btf); LIBBPF_API int btf__load_into_kernel(struct btf *btf); LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, const char *type_name); LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, __u32 kind); -LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__type_cnt() instead; note that btf__get_nr_types() == btf__type_cnt() - 1") -LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf); LIBBPF_API __u32 btf__type_cnt(const struct btf *btf); LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf); LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, @@ -147,32 +138,13 @@ 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_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, - __u32 expected_key_size, - __u32 expected_value_size, - __u32 *key_type_id, __u32 *value_type_id); -LIBBPF_API struct btf_ext *btf_ext__new(__u8 *data, __u32 size); +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 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, - const char *sec_name, __u32 insns_cnt, - void **func_info, __u32 *cnt); -LIBBPF_API LIBBPF_DEPRECATED("btf_ext__reloc_line_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_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 const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size); LIBBPF_API int btf__find_str(struct btf *btf, const char *s); LIBBPF_API int btf__add_str(struct btf *btf, const char *s); @@ -215,6 +187,8 @@ LIBBPF_API int btf__add_field(struct btf *btf, const char *name, int field_type_ /* enum construction APIs */ LIBBPF_API int btf__add_enum(struct btf *btf, const char *name, __u32 bytes_sz); LIBBPF_API int btf__add_enum_value(struct btf *btf, const char *name, __s64 value); +LIBBPF_API int btf__add_enum64(struct btf *btf, const char *name, __u32 bytes_sz, bool is_signed); +LIBBPF_API int btf__add_enum64_value(struct btf *btf, const char *name, __u64 value); enum btf_fwd_kind { BTF_FWD_STRUCT = 0, @@ -227,6 +201,7 @@ LIBBPF_API int btf__add_typedef(struct btf *btf, const char *name, int ref_type_ LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id); +LIBBPF_API int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id); /* func and func_proto construction APIs */ LIBBPF_API int btf__add_func(struct btf *btf, const char *name, @@ -245,25 +220,31 @@ LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_typ int component_idx); struct btf_dedup_opts { - unsigned int dedup_table_size; - bool dont_resolve_fwds; + size_t sz; + /* optional .BTF.ext info to dedup along the main BTF info */ + struct btf_ext *btf_ext; + /* force hash collisions (used for testing) */ + bool force_collisions; + size_t :0; }; +#define btf_dedup_opts__last_field force_collisions -LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, - const struct btf_dedup_opts *opts); +LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts); struct btf_dump; struct btf_dump_opts { - void *ctx; + size_t sz; }; +#define btf_dump_opts__last_field sz typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args); LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf, - const struct btf_ext *btf_ext, - const struct btf_dump_opts *opts, - btf_dump_printf_fn_t printf_fn); + btf_dump_printf_fn_t printf_fn, + void *ctx, + const struct btf_dump_opts *opts); + LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); @@ -313,8 +294,29 @@ 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 the following were never #defined */ +#define BTF_KIND_DECL_TAG 17 /* Decl Tag */ +#define BTF_KIND_TYPE_TAG 18 /* Type Tag */ +#define BTF_KIND_ENUM64 19 /* Enum for up-to 64bit values */ + static inline __u16 btf_kind(const struct btf_type *t) { return BTF_INFO_KIND(t->info); @@ -372,6 +374,11 @@ static inline bool btf_is_enum(const struct btf_type *t) return btf_kind(t) == BTF_KIND_ENUM; } +static inline bool btf_is_enum64(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM64; +} + static inline bool btf_is_fwd(const struct btf_type *t) { return btf_kind(t) == BTF_KIND_FWD; @@ -403,7 +410,8 @@ static inline bool btf_is_mod(const struct btf_type *t) return kind == BTF_KIND_VOLATILE || kind == BTF_KIND_CONST || - kind == BTF_KIND_RESTRICT; + kind == BTF_KIND_RESTRICT || + kind == BTF_KIND_TYPE_TAG; } static inline bool btf_is_func(const struct btf_type *t) @@ -436,6 +444,23 @@ static inline bool btf_is_decl_tag(const struct btf_type *t) return btf_kind(t) == BTF_KIND_DECL_TAG; } +static inline bool btf_is_type_tag(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_TYPE_TAG; +} + +static inline bool btf_is_any_enum(const struct btf_type *t) +{ + return btf_is_enum(t) || btf_is_enum64(t); +} + +static inline bool btf_kind_core_compat(const struct btf_type *t1, + const struct btf_type *t2) +{ + return btf_kind(t1) == btf_kind(t2) || + (btf_is_any_enum(t1) && btf_is_any_enum(t2)); +} + static inline __u8 btf_int_encoding(const struct btf_type *t) { return BTF_INT_ENCODING(*(__u32 *)(t + 1)); @@ -461,6 +486,39 @@ static inline struct btf_enum *btf_enum(const struct btf_type *t) return (struct btf_enum *)(t + 1); } +struct btf_enum64; + +static inline struct btf_enum64 *btf_enum64(const struct btf_type *t) +{ + return (struct btf_enum64 *)(t + 1); +} + +static inline __u64 btf_enum64_value(const struct btf_enum64 *e) +{ + /* struct btf_enum64 is introduced in Linux 6.0, which is very + * bleeding-edge. Here we are avoiding relying on struct btf_enum64 + * definition coming from kernel UAPI headers to support wider range + * of system-wide kernel headers. + * + * Given this header can be also included from C++ applications, that + * further restricts C tricks we can use (like using compatible + * anonymous struct). So just treat struct btf_enum64 as + * a three-element array of u32 and access second (lo32) and third + * (hi32) elements directly. + * + * For reference, here is a struct btf_enum64 definition: + * + * const struct btf_enum64 { + * __u32 name_off; + * __u32 val_lo32; + * __u32 val_hi32; + * }; + */ + const __u32 *e64 = (const __u32 *)e; + + return ((__u64)e64[2] << 32) | e64[1]; +} + static inline struct btf_member *btf_members(const struct btf_type *t) { return (struct btf_member *)(t + 1); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 17db62b5002e..4221f73a74d0 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -77,9 +77,8 @@ struct btf_dump_data { struct btf_dump { const struct btf *btf; - const struct btf_ext *btf_ext; btf_dump_printf_fn_t printf_fn; - struct btf_dump_opts opts; + void *cb_ctx; int ptr_sz; bool strip_mods; bool skip_anon_defs; @@ -138,7 +137,7 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...) va_list args; va_start(args, fmt); - d->printf_fn(d->opts.ctx, fmt, args); + d->printf_fn(d->cb_ctx, fmt, args); va_end(args); } @@ -146,21 +145,26 @@ static int btf_dump_mark_referenced(struct btf_dump *d); static int btf_dump_resize(struct btf_dump *d); struct btf_dump *btf_dump__new(const struct btf *btf, - const struct btf_ext *btf_ext, - const struct btf_dump_opts *opts, - btf_dump_printf_fn_t printf_fn) + btf_dump_printf_fn_t printf_fn, + void *ctx, + const struct btf_dump_opts *opts) { struct btf_dump *d; int err; + if (!OPTS_VALID(opts, btf_dump_opts)) + return libbpf_err_ptr(-EINVAL); + + if (!printf_fn) + return libbpf_err_ptr(-EINVAL); + d = calloc(1, sizeof(struct btf_dump)); if (!d) return libbpf_err_ptr(-ENOMEM); d->btf = btf; - d->btf_ext = btf_ext; d->printf_fn = printf_fn; - d->opts.ctx = opts ? opts->ctx : NULL; + d->cb_ctx = ctx; d->ptr_sz = btf__pointer_size(btf) ? : sizeof(void *); d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); @@ -305,6 +309,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d) switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FWD: case BTF_KIND_FLOAT: break; @@ -317,6 +322,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d) case BTF_KIND_FUNC: case BTF_KIND_VAR: case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: d->type_states[t->type].referenced = 1; break; @@ -524,6 +530,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return 1; } case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FWD: /* * non-anonymous or non-referenced enums are top-level @@ -560,6 +567,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: return btf_dump_order_type(d, t->type, through_ptr); case BTF_KIND_FUNC_PROTO: { @@ -724,6 +732,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) tstate->emit_state = EMITTED; break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: if (top_level_def) { btf_dump_emit_enum_def(d, id, t, 0); btf_dump_printf(d, ";\n\n"); @@ -734,6 +743,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_TYPE_TAG: btf_dump_emit_type(d, t->type, cont_id); break; case BTF_KIND_ARRAY: @@ -973,38 +983,81 @@ static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, btf_dump_printf(d, "enum %s", btf_dump_type_name(d, id)); } -static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, - const struct btf_type *t, - int lvl) +static void btf_dump_emit_enum32_val(struct btf_dump *d, + const struct btf_type *t, + int lvl, __u16 vlen) { const struct btf_enum *v = btf_enum(t); - __u16 vlen = btf_vlen(t); + bool is_signed = btf_kflag(t); + const char *fmt_str; const char *name; size_t dup_cnt; int i; + for (i = 0; i < vlen; i++, v++) { + name = btf_name_of(d, v->name_off); + /* enumerators share namespace with typedef idents */ + dup_cnt = btf_dump_name_dups(d, d->ident_names, name); + if (dup_cnt > 1) { + fmt_str = is_signed ? "\n%s%s___%zd = %d," : "\n%s%s___%zd = %u,"; + btf_dump_printf(d, fmt_str, pfx(lvl + 1), name, dup_cnt, v->val); + } else { + fmt_str = is_signed ? "\n%s%s = %d," : "\n%s%s = %u,"; + btf_dump_printf(d, fmt_str, pfx(lvl + 1), name, v->val); + } + } +} + +static void btf_dump_emit_enum64_val(struct btf_dump *d, + const struct btf_type *t, + int lvl, __u16 vlen) +{ + const struct btf_enum64 *v = btf_enum64(t); + bool is_signed = btf_kflag(t); + const char *fmt_str; + const char *name; + size_t dup_cnt; + __u64 val; + int i; + + for (i = 0; i < vlen; i++, v++) { + name = btf_name_of(d, v->name_off); + dup_cnt = btf_dump_name_dups(d, d->ident_names, name); + val = btf_enum64_value(v); + if (dup_cnt > 1) { + fmt_str = is_signed ? "\n%s%s___%zd = %lldLL," + : "\n%s%s___%zd = %lluULL,"; + btf_dump_printf(d, fmt_str, + pfx(lvl + 1), name, dup_cnt, + (unsigned long long)val); + } else { + fmt_str = is_signed ? "\n%s%s = %lldLL," + : "\n%s%s = %lluULL,"; + btf_dump_printf(d, fmt_str, + pfx(lvl + 1), name, + (unsigned long long)val); + } + } +} +static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, + int lvl) +{ + __u16 vlen = btf_vlen(t); + btf_dump_printf(d, "enum%s%s", t->name_off ? " " : "", btf_dump_type_name(d, id)); - if (vlen) { - btf_dump_printf(d, " {"); - for (i = 0; i < vlen; i++, v++) { - name = btf_name_of(d, v->name_off); - /* enumerators share namespace with typedef idents */ - dup_cnt = btf_dump_name_dups(d, d->ident_names, name); - if (dup_cnt > 1) { - btf_dump_printf(d, "\n%s%s___%zu = %u,", - pfx(lvl + 1), name, dup_cnt, - (__u32)v->val); - } else { - btf_dump_printf(d, "\n%s%s = %u,", - pfx(lvl + 1), name, - (__u32)v->val); - } - } - btf_dump_printf(d, "\n%s}", pfx(lvl)); - } + if (!vlen) + return; + + btf_dump_printf(d, " {"); + if (btf_is_enum(t)) + btf_dump_emit_enum32_val(d, t, lvl, vlen); + else + btf_dump_emit_enum64_val(d, t, lvl, vlen); + btf_dump_printf(d, "\n%s}", pfx(lvl)); } static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, @@ -1154,6 +1207,7 @@ skip_mod: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_FUNC_PROTO: + case BTF_KIND_TYPE_TAG: id = t->type; break; case BTF_KIND_ARRAY: @@ -1161,6 +1215,7 @@ skip_mod: break; case BTF_KIND_INT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FWD: case BTF_KIND_STRUCT: case BTF_KIND_UNION: @@ -1295,6 +1350,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, btf_dump_emit_struct_fwd(d, id, t); break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: btf_dump_emit_mods(d, decls); /* inline anonymous enum */ if (t->name_off == 0 && !d->skip_anon_defs) @@ -1322,6 +1378,11 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, case BTF_KIND_RESTRICT: btf_dump_printf(d, " restrict"); break; + case BTF_KIND_TYPE_TAG: + btf_dump_emit_mods(d, decls); + name = btf_name_of(d, t->name_off); + btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name); + break; case BTF_KIND_ARRAY: { const struct btf_array *a = btf_array(t); const struct btf_type *next_t; @@ -1483,6 +1544,11 @@ 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; @@ -1839,14 +1905,16 @@ 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; } @@ -1959,7 +2027,8 @@ static int btf_dump_get_enum_value(struct btf_dump *d, __u32 id, __s64 *value) { - /* handle unaligned enum value */ + bool is_signed = btf_kflag(t); + if (!ptr_is_aligned(d->btf, id, data)) { __u64 val; int err; @@ -1976,13 +2045,13 @@ static int btf_dump_get_enum_value(struct btf_dump *d, *value = *(__s64 *)data; return 0; case 4: - *value = *(__s32 *)data; + *value = is_signed ? (__s64)*(__s32 *)data : *(__u32 *)data; return 0; case 2: - *value = *(__s16 *)data; + *value = is_signed ? *(__s16 *)data : *(__u16 *)data; return 0; case 1: - *value = *(__s8 *)data; + *value = is_signed ? *(__s8 *)data : *(__u8 *)data; return 0; default: pr_warn("unexpected size %d for enum, id:[%u]\n", t->size, id); @@ -1995,7 +2064,7 @@ static int btf_dump_enum_data(struct btf_dump *d, __u32 id, const void *data) { - const struct btf_enum *e; + bool is_signed; __s64 value; int i, err; @@ -2003,14 +2072,31 @@ static int btf_dump_enum_data(struct btf_dump *d, if (err) return err; - for (i = 0, e = btf_enum(t); i < btf_vlen(t); i++, e++) { - if (value != e->val) - continue; - btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off)); - return 0; - } + is_signed = btf_kflag(t); + if (btf_is_enum(t)) { + const struct btf_enum *e; + + for (i = 0, e = btf_enum(t); i < btf_vlen(t); i++, e++) { + if (value != e->val) + continue; + btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off)); + return 0; + } - btf_dump_type_values(d, "%d", value); + btf_dump_type_values(d, is_signed ? "%d" : "%u", value); + } else { + const struct btf_enum64 *e; + + for (i = 0, e = btf_enum64(t); i < btf_vlen(t); i++, e++) { + if (value != btf_enum64_value(e)) + continue; + btf_dump_type_values(d, "%s", btf_name_of(d, e->name_off)); + return 0; + } + + btf_dump_type_values(d, is_signed ? "%lldLL" : "%lluULL", + (unsigned long long)value); + } return 0; } @@ -2070,6 +2156,7 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d, case BTF_KIND_FLOAT: case BTF_KIND_PTR: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: if (data + bits_offset / 8 + size > d->typed_dump->data_end) return -E2BIG; break; @@ -2174,6 +2261,7 @@ static int btf_dump_type_data_check_zero(struct btf_dump *d, return -ENODATA; } case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: err = btf_dump_get_enum_value(d, t, data, id, &value); if (err) return err; @@ -2194,7 +2282,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, __u8 bits_offset, __u8 bit_sz) { - int size, err; + int size, err = 0; size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset); if (size < 0) @@ -2246,6 +2334,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, err = btf_dump_struct_data(d, t, id, data); break; case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: /* handle bitfield and int enum values */ if (bit_sz) { __u64 print_num; @@ -2296,11 +2385,11 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, d->typed_dump->indent_lvl = OPTS_GET(opts, indent_level, 0); /* default indent string is a tab */ - if (!opts->indent_str) + if (!OPTS_GET(opts, indent_str, NULL)) d->typed_dump->indent_str[0] = '\t'; else - strncat(d->typed_dump->indent_str, opts->indent_str, - sizeof(d->typed_dump->indent_str) - 1); + libbpf_strlcpy(d->typed_dump->indent_str, opts->indent_str, + sizeof(d->typed_dump->indent_str)); d->typed_dump->compact = OPTS_GET(opts, compact, false); d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false); diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 9934851ccde7..23f5c46708f8 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -371,8 +371,9 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) { int i; - if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) { - pr_warn("progs/maps mismatch\n"); + if (nr_progs < gen->nr_progs || nr_maps != gen->nr_maps) { + pr_warn("nr_progs %d/%d nr_maps %d/%d mismatch\n", + nr_progs, gen->nr_progs, nr_maps, gen->nr_maps); gen->error = -EFAULT; return gen->error; } @@ -445,47 +446,32 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, } void bpf_gen__map_create(struct bpf_gen *gen, - struct bpf_create_map_params *map_attr, int map_idx) + enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, __u32 value_size, __u32 max_entries, + struct bpf_map_create_opts *map_attr, int map_idx) { - int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id); + int attr_size = offsetofend(union bpf_attr, map_extra); bool close_inner_map_fd = false; int map_create_attr, idx; union bpf_attr attr; memset(&attr, 0, attr_size); - attr.map_type = map_attr->map_type; - attr.key_size = map_attr->key_size; - attr.value_size = map_attr->value_size; + attr.map_type = map_type; + attr.key_size = key_size; + attr.value_size = value_size; attr.map_flags = map_attr->map_flags; attr.map_extra = map_attr->map_extra; - memcpy(attr.map_name, map_attr->name, - min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1)); + if (map_name) + libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.numa_node = map_attr->numa_node; attr.map_ifindex = map_attr->map_ifindex; - attr.max_entries = map_attr->max_entries; - switch (attr.map_type) { - case BPF_MAP_TYPE_PERF_EVENT_ARRAY: - case BPF_MAP_TYPE_CGROUP_ARRAY: - case BPF_MAP_TYPE_STACK_TRACE: - case BPF_MAP_TYPE_ARRAY_OF_MAPS: - case BPF_MAP_TYPE_HASH_OF_MAPS: - case BPF_MAP_TYPE_DEVMAP: - case BPF_MAP_TYPE_DEVMAP_HASH: - case BPF_MAP_TYPE_CPUMAP: - case BPF_MAP_TYPE_XSKMAP: - case BPF_MAP_TYPE_SOCKMAP: - case BPF_MAP_TYPE_SOCKHASH: - case BPF_MAP_TYPE_QUEUE: - case BPF_MAP_TYPE_STACK: - case BPF_MAP_TYPE_RINGBUF: - break; - default: - attr.btf_key_type_id = map_attr->btf_key_type_id; - attr.btf_value_type_id = map_attr->btf_value_type_id; - } + attr.max_entries = max_entries; + attr.btf_key_type_id = map_attr->btf_key_type_id; + attr.btf_value_type_id = map_attr->btf_value_type_id; pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n", - attr.map_name, map_idx, map_attr->map_type, attr.btf_value_type_id); + attr.map_name, map_idx, map_type, attr.btf_value_type_id); map_create_attr = add_data(gen, &attr, attr_size); if (attr.btf_value_type_id) @@ -512,7 +498,7 @@ void bpf_gen__map_create(struct bpf_gen *gen, /* emit MAP_CREATE command */ emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size); debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d", - attr.map_name, map_idx, map_attr->map_type, attr.value_size, + attr.map_name, map_idx, map_type, value_size, attr.btf_value_type_id); emit_check_err(gen); /* remember map_fd in the stack, if successful */ @@ -547,7 +533,7 @@ void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name, gen->attach_kind = kind; ret = snprintf(gen->attach_target, sizeof(gen->attach_target), "%s%s", prefix, attach_name); - if (ret == sizeof(gen->attach_target)) + if (ret >= sizeof(gen->attach_target)) gen->error = -ENOSPC; } @@ -597,8 +583,9 @@ void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_desc *relo) { struct ksym_desc *kdesc; + int i; - for (int i = 0; i < gen->nr_ksyms; i++) { + for (i = 0; i < gen->nr_ksyms; i++) { if (!strcmp(gen->ksyms[i].name, relo->name)) { gen->ksyms[i].ref++; return &gen->ksyms[i]; @@ -700,27 +687,29 @@ static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo return; } kdesc->off = btf_fd_idx; - /* set a default value for imm */ + /* jump to success case */ + emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); + /* set value for imm, off as 0 */ emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0)); - /* skip success case store if ret < 0 */ - emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 1)); + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip success case for ret < 0 */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 10)); /* store btf_id into insn[insn_idx].imm */ emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm))); + /* obtain fd in BPF_REG_9 */ + emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7)); + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); + /* jump to fd_array store if fd denotes module BTF */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2)); + /* set the default value for off */ + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip BTF fd store for vmlinux BTF */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); /* load fd_array slot pointer */ emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx))); - /* skip store of BTF fd if ret < 0 */ - emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 3)); /* store BTF fd in slot */ - emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7)); - emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0)); - /* set a default value for off */ - emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); - /* skip insn->off store if ret < 0 */ - emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 2)); - /* skip if vmlinux BTF */ - emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 0, 1)); /* store index into insn[insn_idx].off */ emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx)); log: @@ -819,9 +808,8 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, kdesc->insn + offsetof(struct bpf_insn, imm)); move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4, kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)); - emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_8, offsetof(struct bpf_insn, imm))); - /* jump over src_reg adjustment if imm is not 0 */ - emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 3)); + /* jump over src_reg adjustment if imm is not 0, reuse BPF_REG_0 from move_blob2blob */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3)); goto clear_src_reg; } /* remember insn offset, so we can copy BTF ID and FD later */ @@ -829,17 +817,20 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, emit_bpf_find_by_name_kind(gen, relo); if (!relo->is_weak) emit_check_err(gen); - /* set default values as 0 */ + /* jump to success case */ + emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); + /* set values for insn[insn_idx].imm, insn[insn_idx + 1].imm as 0 */ emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0)); emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 0)); - /* skip success case stores if ret < 0 */ - emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 4)); + /* skip success case for ret < 0 */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); /* store btf_id into insn[insn_idx].imm */ emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm))); /* store btf_obj_fd into insn[insn_idx + 1].imm */ emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32)); emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm))); + /* skip src_reg adjustment */ emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); clear_src_reg: /* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */ @@ -851,6 +842,22 @@ clear_src_reg: emit_ksym_relo_log(gen, relo, kdesc->ref); } +void bpf_gen__record_relo_core(struct bpf_gen *gen, + const struct bpf_core_relo *core_relo) +{ + struct bpf_core_relo *relos; + + relos = libbpf_reallocarray(gen->core_relos, gen->core_relo_cnt + 1, sizeof(*relos)); + if (!relos) { + gen->error = -ENOMEM; + return; + } + gen->core_relos = relos; + relos += gen->core_relo_cnt; + memcpy(relos, core_relo, sizeof(*relos)); + gen->core_relo_cnt++; +} + static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns) { int insn; @@ -883,6 +890,15 @@ static void emit_relos(struct bpf_gen *gen, int insns) emit_relo(gen, gen->relos + i, insns); } +static void cleanup_core_relo(struct bpf_gen *gen) +{ + if (!gen->core_relo_cnt) + return; + free(gen->core_relos); + gen->core_relo_cnt = 0; + gen->core_relos = NULL; +} + static void cleanup_relos(struct bpf_gen *gen, int insns) { int i, insn; @@ -910,30 +926,32 @@ static void cleanup_relos(struct bpf_gen *gen, int insns) gen->relo_cnt = 0; gen->relos = NULL; } + cleanup_core_relo(gen); } void bpf_gen__prog_load(struct bpf_gen *gen, - struct bpf_prog_load_params *load_attr, int prog_idx) + enum bpf_prog_type prog_type, const char *prog_name, + const char *license, struct bpf_insn *insns, size_t insn_cnt, + struct bpf_prog_load_opts *load_attr, int prog_idx) { - int attr_size = offsetofend(union bpf_attr, fd_array); - int prog_load_attr, license, insns, func_info, line_info; + int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos; + int attr_size = offsetofend(union bpf_attr, core_relo_rec_size); union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: prog_load: type %d insns_cnt %zd\n", - load_attr->prog_type, load_attr->insn_cnt); + pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n", + prog_type, insn_cnt, prog_idx); /* add license string to blob of bytes */ - license = add_data(gen, load_attr->license, strlen(load_attr->license) + 1); + license_off = add_data(gen, license, strlen(license) + 1); /* add insns to blob of bytes */ - insns = add_data(gen, load_attr->insns, - load_attr->insn_cnt * sizeof(struct bpf_insn)); + insns_off = add_data(gen, insns, insn_cnt * sizeof(struct bpf_insn)); - attr.prog_type = load_attr->prog_type; + attr.prog_type = prog_type; attr.expected_attach_type = load_attr->expected_attach_type; attr.attach_btf_id = load_attr->attach_btf_id; attr.prog_ifindex = load_attr->prog_ifindex; attr.kern_version = 0; - attr.insn_cnt = (__u32)load_attr->insn_cnt; + attr.insn_cnt = (__u32)insn_cnt; attr.prog_flags = load_attr->prog_flags; attr.func_info_rec_size = load_attr->func_info_rec_size; @@ -946,15 +964,19 @@ void bpf_gen__prog_load(struct bpf_gen *gen, line_info = add_data(gen, load_attr->line_info, attr.line_info_cnt * attr.line_info_rec_size); - memcpy(attr.prog_name, load_attr->name, - min((unsigned)strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1)); + attr.core_relo_rec_size = sizeof(struct bpf_core_relo); + attr.core_relo_cnt = gen->core_relo_cnt; + core_relos = add_data(gen, gen->core_relos, + attr.core_relo_cnt * attr.core_relo_rec_size); + + libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); prog_load_attr = add_data(gen, &attr, attr_size); /* populate union bpf_attr with a pointer to license */ - emit_rel_store(gen, attr_field(prog_load_attr, license), license); + emit_rel_store(gen, attr_field(prog_load_attr, license), license_off); /* populate union bpf_attr with a pointer to instructions */ - emit_rel_store(gen, attr_field(prog_load_attr, insns), insns); + emit_rel_store(gen, attr_field(prog_load_attr, insns), insns_off); /* populate union bpf_attr with a pointer to func_info */ emit_rel_store(gen, attr_field(prog_load_attr, func_info), func_info); @@ -962,6 +984,9 @@ void bpf_gen__prog_load(struct bpf_gen *gen, /* populate union bpf_attr with a pointer to line_info */ emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info); + /* populate union bpf_attr with a pointer to core_relos */ + emit_rel_store(gen, attr_field(prog_load_attr, core_relos), core_relos); + /* populate union bpf_attr fd_array with a pointer to data where map_fds are saved */ emit_rel_store(gen, attr_field(prog_load_attr, fd_array), gen->fd_array); @@ -986,15 +1011,17 @@ void bpf_gen__prog_load(struct bpf_gen *gen, emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(union bpf_attr, attach_btf_obj_fd))); } - emit_relos(gen, insns); + emit_relos(gen, insns_off); /* emit PROG_LOAD command */ emit_sys_bpf(gen, BPF_PROG_LOAD, prog_load_attr, attr_size); debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt); /* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */ - cleanup_relos(gen, insns); - if (gen->attach_kind) + cleanup_relos(gen, insns_off); + if (gen->attach_kind) { emit_sys_close_blob(gen, attr_field(prog_load_attr, attach_btf_obj_fd)); + gen->attach_kind = 0; + } emit_check_err(gen); /* remember prog_fd in the stack, if successful */ emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, @@ -1016,18 +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, @@ -1040,6 +1076,33 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, emit_check_err(gen); } +void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slot, + int inner_map_idx) +{ + int attr_size = offsetofend(union bpf_attr, flags); + int map_update_attr, key; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n", + outer_map_idx, slot, inner_map_idx); + + key = add_data(gen, &slot, sizeof(slot)); + + map_update_attr = add_data(gen, &attr, attr_size); + move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, + blob_fd_array_off(gen, outer_map_idx)); + emit_rel_store(gen, attr_field(map_update_attr, key), key); + emit_rel_store(gen, attr_field(map_update_attr, value), + blob_fd_array_off(gen, inner_map_idx)); + + /* emit MAP_UPDATE_ELEM command */ + emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size); + debug_ret(gen, "populate_outer_map outer %d key %d inner %d", + outer_map_idx, slot, inner_map_idx); + emit_check_err(gen); +} + void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx) { int attr_size = offsetofend(union bpf_attr, map_fd); 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 7c74342bb668..184ce1684dcd 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -31,7 +31,6 @@ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/filter.h> -#include <linux/list.h> #include <linux/limits.h> #include <linux/perf_event.h> #include <linux/ring_buffer.h> @@ -72,6 +71,136 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog); +static const char * const attach_type_name[] = { + [BPF_CGROUP_INET_INGRESS] = "cgroup_inet_ingress", + [BPF_CGROUP_INET_EGRESS] = "cgroup_inet_egress", + [BPF_CGROUP_INET_SOCK_CREATE] = "cgroup_inet_sock_create", + [BPF_CGROUP_INET_SOCK_RELEASE] = "cgroup_inet_sock_release", + [BPF_CGROUP_SOCK_OPS] = "cgroup_sock_ops", + [BPF_CGROUP_DEVICE] = "cgroup_device", + [BPF_CGROUP_INET4_BIND] = "cgroup_inet4_bind", + [BPF_CGROUP_INET6_BIND] = "cgroup_inet6_bind", + [BPF_CGROUP_INET4_CONNECT] = "cgroup_inet4_connect", + [BPF_CGROUP_INET6_CONNECT] = "cgroup_inet6_connect", + [BPF_CGROUP_INET4_POST_BIND] = "cgroup_inet4_post_bind", + [BPF_CGROUP_INET6_POST_BIND] = "cgroup_inet6_post_bind", + [BPF_CGROUP_INET4_GETPEERNAME] = "cgroup_inet4_getpeername", + [BPF_CGROUP_INET6_GETPEERNAME] = "cgroup_inet6_getpeername", + [BPF_CGROUP_INET4_GETSOCKNAME] = "cgroup_inet4_getsockname", + [BPF_CGROUP_INET6_GETSOCKNAME] = "cgroup_inet6_getsockname", + [BPF_CGROUP_UDP4_SENDMSG] = "cgroup_udp4_sendmsg", + [BPF_CGROUP_UDP6_SENDMSG] = "cgroup_udp6_sendmsg", + [BPF_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_CGROUP_UDP4_RECVMSG] = "cgroup_udp4_recvmsg", + [BPF_CGROUP_UDP6_RECVMSG] = "cgroup_udp6_recvmsg", + [BPF_CGROUP_GETSOCKOPT] = "cgroup_getsockopt", + [BPF_CGROUP_SETSOCKOPT] = "cgroup_setsockopt", + [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", + [BPF_SK_SKB_STREAM_VERDICT] = "sk_skb_stream_verdict", + [BPF_SK_SKB_VERDICT] = "sk_skb_verdict", + [BPF_SK_MSG_VERDICT] = "sk_msg_verdict", + [BPF_LIRC_MODE2] = "lirc_mode2", + [BPF_FLOW_DISSECTOR] = "flow_dissector", + [BPF_TRACE_RAW_TP] = "trace_raw_tp", + [BPF_TRACE_FENTRY] = "trace_fentry", + [BPF_TRACE_FEXIT] = "trace_fexit", + [BPF_MODIFY_RETURN] = "modify_return", + [BPF_LSM_MAC] = "lsm_mac", + [BPF_LSM_CGROUP] = "lsm_cgroup", + [BPF_SK_LOOKUP] = "sk_lookup", + [BPF_TRACE_ITER] = "trace_iter", + [BPF_XDP_DEVMAP] = "xdp_devmap", + [BPF_XDP_CPUMAP] = "xdp_cpumap", + [BPF_XDP] = "xdp", + [BPF_SK_REUSEPORT_SELECT] = "sk_reuseport_select", + [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_reuseport_select_or_migrate", + [BPF_PERF_EVENT] = "perf_event", + [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", +}; + +static const char * const link_type_name[] = { + [BPF_LINK_TYPE_UNSPEC] = "unspec", + [BPF_LINK_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_LINK_TYPE_TRACING] = "tracing", + [BPF_LINK_TYPE_CGROUP] = "cgroup", + [BPF_LINK_TYPE_ITER] = "iter", + [BPF_LINK_TYPE_NETNS] = "netns", + [BPF_LINK_TYPE_XDP] = "xdp", + [BPF_LINK_TYPE_PERF_EVENT] = "perf_event", + [BPF_LINK_TYPE_KPROBE_MULTI] = "kprobe_multi", + [BPF_LINK_TYPE_STRUCT_OPS] = "struct_ops", +}; + +static const char * const map_type_name[] = { + [BPF_MAP_TYPE_UNSPEC] = "unspec", + [BPF_MAP_TYPE_HASH] = "hash", + [BPF_MAP_TYPE_ARRAY] = "array", + [BPF_MAP_TYPE_PROG_ARRAY] = "prog_array", + [BPF_MAP_TYPE_PERF_EVENT_ARRAY] = "perf_event_array", + [BPF_MAP_TYPE_PERCPU_HASH] = "percpu_hash", + [BPF_MAP_TYPE_PERCPU_ARRAY] = "percpu_array", + [BPF_MAP_TYPE_STACK_TRACE] = "stack_trace", + [BPF_MAP_TYPE_CGROUP_ARRAY] = "cgroup_array", + [BPF_MAP_TYPE_LRU_HASH] = "lru_hash", + [BPF_MAP_TYPE_LRU_PERCPU_HASH] = "lru_percpu_hash", + [BPF_MAP_TYPE_LPM_TRIE] = "lpm_trie", + [BPF_MAP_TYPE_ARRAY_OF_MAPS] = "array_of_maps", + [BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps", + [BPF_MAP_TYPE_DEVMAP] = "devmap", + [BPF_MAP_TYPE_DEVMAP_HASH] = "devmap_hash", + [BPF_MAP_TYPE_SOCKMAP] = "sockmap", + [BPF_MAP_TYPE_CPUMAP] = "cpumap", + [BPF_MAP_TYPE_XSKMAP] = "xskmap", + [BPF_MAP_TYPE_SOCKHASH] = "sockhash", + [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", + [BPF_MAP_TYPE_REUSEPORT_SOCKARRAY] = "reuseport_sockarray", + [BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE] = "percpu_cgroup_storage", + [BPF_MAP_TYPE_QUEUE] = "queue", + [BPF_MAP_TYPE_STACK] = "stack", + [BPF_MAP_TYPE_SK_STORAGE] = "sk_storage", + [BPF_MAP_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_MAP_TYPE_RINGBUF] = "ringbuf", + [BPF_MAP_TYPE_INODE_STORAGE] = "inode_storage", + [BPF_MAP_TYPE_TASK_STORAGE] = "task_storage", + [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter", + [BPF_MAP_TYPE_USER_RINGBUF] = "user_ringbuf", +}; + +static const char * const prog_type_name[] = { + [BPF_PROG_TYPE_UNSPEC] = "unspec", + [BPF_PROG_TYPE_SOCKET_FILTER] = "socket_filter", + [BPF_PROG_TYPE_KPROBE] = "kprobe", + [BPF_PROG_TYPE_SCHED_CLS] = "sched_cls", + [BPF_PROG_TYPE_SCHED_ACT] = "sched_act", + [BPF_PROG_TYPE_TRACEPOINT] = "tracepoint", + [BPF_PROG_TYPE_XDP] = "xdp", + [BPF_PROG_TYPE_PERF_EVENT] = "perf_event", + [BPF_PROG_TYPE_CGROUP_SKB] = "cgroup_skb", + [BPF_PROG_TYPE_CGROUP_SOCK] = "cgroup_sock", + [BPF_PROG_TYPE_LWT_IN] = "lwt_in", + [BPF_PROG_TYPE_LWT_OUT] = "lwt_out", + [BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit", + [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", + [BPF_PROG_TYPE_SK_SKB] = "sk_skb", + [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", + [BPF_PROG_TYPE_SK_MSG] = "sk_msg", + [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", + [BPF_PROG_TYPE_LWT_SEG6LOCAL] = "lwt_seg6local", + [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2", + [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", + [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", + [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", + [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", + [BPF_PROG_TYPE_TRACING] = "tracing", + [BPF_PROG_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_PROG_TYPE_EXT] = "ext", + [BPF_PROG_TYPE_LSM] = "lsm", + [BPF_PROG_TYPE_SK_LOOKUP] = "sk_lookup", + [BPF_PROG_TYPE_SYSCALL] = "syscall", +}; + static int __base_pr(enum libbpf_print_level level, const char *format, va_list args) { @@ -95,13 +224,18 @@ __printf(2, 3) void libbpf_print(enum libbpf_print_level level, const char *format, ...) { va_list args; + int old_errno; if (!__libbpf_pr) return; + old_errno = errno; + va_start(args, format); __libbpf_pr(level, format, args); va_end(args); + + errno = old_errno; } static void pr_perm_msg(int err) @@ -151,56 +285,30 @@ static inline __u64 ptr_to_u64(const void *ptr) return (__u64) (unsigned long) ptr; } -/* this goes away in libbpf 1.0 */ -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; + /* as of v1.0 libbpf_set_strict_mode() is a no-op */ return 0; } -enum kern_feature_id { - /* v4.14: kernel support for program & map names. */ - FEAT_PROG_NAME, - /* v5.2: kernel support for global data sections. */ - FEAT_GLOBAL_DATA, - /* BTF support */ - FEAT_BTF, - /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */ - FEAT_BTF_FUNC, - /* BTF_KIND_VAR and BTF_KIND_DATASEC support */ - FEAT_BTF_DATASEC, - /* BTF_FUNC_GLOBAL is supported */ - FEAT_BTF_GLOBAL_FUNC, - /* BPF_F_MMAPABLE is supported for arrays */ - FEAT_ARRAY_MMAP, - /* kernel support for expected_attach_type in BPF_PROG_LOAD */ - FEAT_EXP_ATTACH_TYPE, - /* bpf_probe_read_{kernel,user}[_str] helpers */ - FEAT_PROBE_READ_KERN, - /* BPF_PROG_BIND_MAP is supported */ - FEAT_PROG_BIND_MAP, - /* Kernel support for module BTFs */ - FEAT_MODULE_BTF, - /* BTF_KIND_FLOAT support */ - FEAT_BTF_FLOAT, - /* BPF perf link support */ - FEAT_PERF_LINK, - /* BTF_KIND_DECL_TAG support */ - FEAT_BTF_DECL_TAG, - __FEAT_CNT, -}; +__u32 libbpf_major_version(void) +{ + return LIBBPF_MAJOR_VERSION; +} -static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); +__u32 libbpf_minor_version(void) +{ + return LIBBPF_MINOR_VERSION; +} + +const char *libbpf_version_string(void) +{ +#define __S(X) #X +#define _S(X) __S(X) + return "v" _S(LIBBPF_MAJOR_VERSION) "." _S(LIBBPF_MINOR_VERSION); +#undef _S +#undef __S +} enum reloc_type { RELO_LD64, @@ -209,21 +317,21 @@ enum reloc_type { RELO_EXTERN_VAR, RELO_EXTERN_FUNC, RELO_SUBPROG_ADDR, + RELO_CORE, }; struct reloc_desc { enum reloc_type type; int insn_idx; - int map_idx; - int sym_off; + union { + const struct bpf_core_relo *core_relo; /* used when type == RELO_CORE */ + struct { + int map_idx; + int sym_off; + }; + }; }; -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_params *attr, long cookie); -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie); - /* stored as sec_def->cookie for all libbpf-supported SEC()s */ enum sec_def_flags { SEC_NONE = 0, @@ -242,19 +350,20 @@ enum sec_def_flags { SEC_ATTACH_BTF = 4, /* BPF program type allows sleeping/blocking in kernel */ SEC_SLEEPABLE = 8, - /* allow non-strict prefix matching */ - SEC_SLOPPY_PFX = 16, + /* BPF program support non-linear XDP buffer */ + SEC_XDP_FRAGS = 16, }; 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; }; /* @@ -262,9 +371,10 @@ struct bpf_sec_def { * linux/filter.h. */ struct bpf_program { - const struct bpf_sec_def *sec_def; + char *name; char *sec_name; size_t sec_idx; + const struct bpf_sec_def *sec_def; /* this program's instruction offset (in number of instructions) * within its containing ELF section */ @@ -284,12 +394,6 @@ struct bpf_program { */ size_t sub_insn_off; - char *name; - /* name with / replaced by _; makes recursive pinning - * in bpf_object__pin_programs easier - */ - char *pin_name; - /* instructions that belong to BPF program; insns[0] is located at * sec_insn_off instruction within its ELF section in ELF file, so * when mapping ELF file instruction index to the local instruction, @@ -304,26 +408,26 @@ struct bpf_program { struct reloc_desc *reloc_desc; int nr_reloc; - int log_level; - struct { - int nr; - int *fds; - } instances; - bpf_program_prep_t preprocessor; + /* BPF verifier log settings */ + char *log_buf; + size_t log_size; + __u32 log_level; struct bpf_object *obj; - void *priv; - bpf_program_clear_priv_t clear_priv; - bool load; + int fd; + bool autoload; + bool autoattach; bool mark_btf_static; enum bpf_prog_type type; enum bpf_attach_type expected_attach_type; + int prog_ifindex; __u32 attach_btf_obj_fd; __u32 attach_btf_id; __u32 attach_prog_fd; + void *func_info; __u32 func_info_rec_size; __u32 func_info_cnt; @@ -370,7 +474,16 @@ enum libbpf_map_type { LIBBPF_MAP_KCONFIG, }; +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; +}; + struct bpf_map { + struct bpf_object *obj; char *name; /* real_name is defined for special internal maps (.rodata*, * .data*, .bss, .kconfig) and preserves their original ELF section @@ -389,8 +502,6 @@ struct bpf_map { __u32 btf_key_type_id; __u32 btf_value_type_id; __u32 btf_vmlinux_value_type_id; - void *priv; - bpf_map_clear_priv_t clear_priv; enum libbpf_map_type libbpf_type; void *mmaped; struct bpf_struct_ops *st_ops; @@ -400,6 +511,7 @@ struct bpf_map { char *pin_path; bool pinned; bool reused; + bool autocreate; __u64 map_extra; }; @@ -452,8 +564,6 @@ struct extern_desc { }; }; -static LIST_HEAD(bpf_objects_list); - struct module_btf { struct btf *btf; char *name; @@ -488,7 +598,6 @@ struct elf_state { size_t strtabidx; struct elf_sec_desc *secs; int sec_cnt; - int maps_shndx; int btf_maps_shndx; __u32 btf_maps_sec_btf_id; int text_shndx; @@ -496,6 +605,8 @@ struct elf_state { int st_ops_shndx; }; +struct usdt_manager; + struct bpf_object { char name[BPF_OBJ_NAME_LEN]; char license[64]; @@ -520,12 +631,6 @@ struct bpf_object { /* Information when doing ELF related work. Only valid if efile.elf is not NULL */ struct elf_state efile; - /* - * All loaded bpf_object are linked in a list, which is - * hidden to caller. bpf_objects__<func> handlers deal with - * all objects. - */ - struct list_head list; struct btf *btf; struct btf_ext *btf_ext; @@ -546,13 +651,17 @@ struct bpf_object { size_t btf_module_cnt; size_t btf_module_cap; - void *priv; - bpf_object_clear_priv_t clear_priv; + /* optional log settings passed to BPF_BTF_LOAD and BPF_PROG_LOAD commands */ + char *log_buf; + size_t log_size; + __u32 log_level; int *fd_array; size_t fd_array_cap; size_t fd_array_cnt; + struct usdt_manager *usdt_man; + char path[]; }; @@ -568,25 +677,10 @@ static Elf64_Rel *elf_rel_by_idx(Elf_Data *data, size_t idx); void bpf_program__unload(struct bpf_program *prog) { - int i; - if (!prog) return; - /* - * If the object is opened but the program was never loaded, - * it is possible that prog->instances.nr == -1. - */ - if (prog->instances.nr > 0) { - for (i = 0; i < prog->instances.nr; i++) - zclose(prog->instances.fds[i]); - } else if (prog->instances.nr != -1) { - pr_warn("Internal error: instances.nr is %d\n", - prog->instances.nr); - } - - prog->instances.nr = -1; - zfree(&prog->instances.fds); + zclose(prog->fd); zfree(&prog->func_info); zfree(&prog->line_info); @@ -597,16 +691,9 @@ static void bpf_program__exit(struct bpf_program *prog) if (!prog) return; - if (prog->clear_priv) - prog->clear_priv(prog, prog->priv); - - prog->priv = NULL; - prog->clear_priv = NULL; - bpf_program__unload(prog); zfree(&prog->name); zfree(&prog->sec_name); - zfree(&prog->pin_name); zfree(&prog->insns); zfree(&prog->reloc_desc); @@ -615,26 +702,6 @@ static void bpf_program__exit(struct bpf_program *prog) prog->sec_idx = -1; } -static char *__bpf_program__pin_name(struct bpf_program *prog) -{ - char *name, *p; - - if (libbpf_mode & LIBBPF_STRICT_SEC_NAME) - name = strdup(prog->name); - else - name = strdup(prog->sec_name); - - if (!name) - return NULL; - - p = name; - - while ((p = strchr(p, '/'))) - *p = '_'; - - return name; -} - static bool insn_is_subprog_call(const struct bpf_insn *insn) { return BPF_CLASS(insn->code) == BPF_JMP && @@ -676,10 +743,24 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, prog->insns_cnt = prog->sec_insn_cnt; prog->type = BPF_PROG_TYPE_UNSPEC; - prog->load = true; + prog->fd = -1; - prog->instances.fds = NULL; - prog->instances.nr = -1; + /* libbpf's convention for SEC("?abc...") is that it's just like + * SEC("abc...") but the corresponding bpf_program starts out with + * autoload set to false. + */ + if (sec_name[0] == '?') { + prog->autoload = false; + /* from now on forget there was ? in section name */ + sec_name++; + } else { + prog->autoload = true; + } + + prog->autoattach = true; + + /* inherit object's log_level */ + prog->log_level = obj->log_level; prog->sec_name = strdup(sec_name); if (!prog->sec_name) @@ -689,10 +770,6 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, if (!prog->name) goto errout; - prog->pin_name = __bpf_program__pin_name(prog); - if (!prog->pin_name) - goto errout; - prog->insns = malloc(insn_data_sz); if (!prog->insns) goto errout; @@ -791,11 +868,36 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return 0; } -static __u32 get_kernel_version(void) +__u32 get_kernel_version(void) { + /* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release, + * but Ubuntu provides /proc/version_signature file, as described at + * https://ubuntu.com/kernel, with an example contents below, which we + * can use to get a proper LINUX_VERSION_CODE. + * + * Ubuntu 5.4.0-12.15-generic 5.4.8 + * + * In the above, 5.4.8 is what kernel is actually expecting, while + * uname() call will return 5.4.0 in info.release. + */ + const char *ubuntu_kver_file = "/proc/version_signature"; __u32 major, minor, patch; struct utsname info; + if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) == 0) { + FILE *f; + + f = fopen(ubuntu_kver_file, "r"); + if (f) { + if (fscanf(f, "%*s %*s %d.%d.%d\n", &major, &minor, &patch) == 3) { + fclose(f); + return KERNEL_VERSION(major, minor, patch); + } + fclose(f); + } + /* something went wrong, fall back to uname() approach */ + } + uname(&info); if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) return 0; @@ -1149,7 +1251,6 @@ static struct bpf_object *bpf_object__new(const char *path, size_t obj_buf_sz, const char *obj_name) { - bool strict = (libbpf_mode & LIBBPF_STRICT_NO_OBJECT_LIST); struct bpf_object *obj; char *end; @@ -1161,12 +1262,10 @@ static struct bpf_object *bpf_object__new(const char *path, strcpy(obj->path, path); if (obj_name) { - strncpy(obj->name, obj_name, sizeof(obj->name) - 1); - obj->name[sizeof(obj->name) - 1] = 0; + libbpf_strlcpy(obj->name, obj_name, sizeof(obj->name)); } else { /* Using basename() GNU version which doesn't modify arg. */ - strncpy(obj->name, basename((void *)path), - sizeof(obj->name) - 1); + libbpf_strlcpy(obj->name, basename((void *)path), sizeof(obj->name)); end = strchr(obj->name, '.'); if (end) *end = 0; @@ -1181,7 +1280,6 @@ static struct bpf_object *bpf_object__new(const char *path, */ obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; - obj->efile.maps_shndx = -1; obj->efile.btf_maps_shndx = -1; obj->efile.st_ops_shndx = -1; obj->kconfig_map_idx = -1; @@ -1189,9 +1287,6 @@ static struct bpf_object *bpf_object__new(const char *path, obj->kern_version = get_kernel_version(); obj->loaded = false; - INIT_LIST_HEAD(&obj->list); - if (!strict) - list_add(&obj->list, &bpf_objects_list); return obj; } @@ -1200,10 +1295,8 @@ static void bpf_object__elf_finish(struct bpf_object *obj) if (!obj->efile.elf) return; - if (obj->efile.elf) { - elf_end(obj->efile.elf); - obj->efile.elf = NULL; - } + elf_end(obj->efile.elf); + obj->efile.elf = NULL; obj->efile.symbols = NULL; obj->efile.st_ops_data = NULL; @@ -1226,10 +1319,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) } if (obj->efile.obj_buf_sz > 0) { - /* - * obj_buf should have been validated by - * bpf_object__open_buffer(). - */ + /* obj_buf should have been validated by bpf_object__open_mem(). */ elf = elf_memory((char *)obj->efile.obj_buf, obj->efile.obj_buf_sz); } else { obj->efile.fd = open(obj->path, O_RDONLY | O_CLOEXEC); @@ -1318,7 +1408,10 @@ static int bpf_object__check_endianness(struct bpf_object *obj) static int bpf_object__init_license(struct bpf_object *obj, void *data, size_t size) { - memcpy(obj->license, data, min(size, sizeof(obj->license) - 1)); + /* libbpf_strlcpy() only copies first N - 1 bytes, so size + 1 won't + * go over allowed ELF data section buffer + */ + libbpf_strlcpy(obj->license, data, min(size + 1, sizeof(obj->license))); pr_debug("license of %s is %s\n", obj->path, obj->license); return 0; } @@ -1348,22 +1441,20 @@ 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) @@ -1378,8 +1469,11 @@ static int find_elf_var_offset(const struct bpf_object *obj, const char *name, _ for (si = 0; si < symbols->d_size / sizeof(Elf64_Sym); si++) { Elf64_Sym *sym = elf_sym_by_idx(obj, si); - if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL || - ELF64_ST_TYPE(sym->st_info) != STT_OBJECT) + if (ELF64_ST_TYPE(sym->st_info) != STT_OBJECT) + continue; + + if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL && + ELF64_ST_BIND(sym->st_info) != STB_WEAK) continue; sname = elf_sym_str(obj, sym->st_name); @@ -1398,36 +1492,21 @@ static int find_elf_var_offset(const struct bpf_object *obj, const char *name, _ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) { - struct bpf_map *new_maps; - size_t new_cap; - int i; - - if (obj->nr_maps < obj->maps_cap) - return &obj->maps[obj->nr_maps++]; + struct bpf_map *map; + int err; - new_cap = max((size_t)4, obj->maps_cap * 3 / 2); - new_maps = libbpf_reallocarray(obj->maps, new_cap, sizeof(*obj->maps)); - if (!new_maps) { - pr_warn("alloc maps for object failed\n"); - return ERR_PTR(-ENOMEM); - } + err = libbpf_ensure_mem((void **)&obj->maps, &obj->maps_cap, + sizeof(*obj->maps), obj->nr_maps + 1); + if (err) + return ERR_PTR(err); - obj->maps_cap = new_cap; - obj->maps = new_maps; + map = &obj->maps[obj->nr_maps++]; + map->obj = obj; + map->fd = -1; + map->inner_map_fd = -1; + map->autocreate = true; - /* zero out new maps */ - memset(obj->maps + obj->nr_maps, 0, - (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps)); - /* - * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin) - * when failure (zclose won't close negative fd)). - */ - for (i = obj->nr_maps; i < obj->maps_cap; i++) { - obj->maps[i].fd = -1; - obj->maps[i].inner_map_fd = -1; - } - - return &obj->maps[obj->nr_maps++]; + return map; } static size_t bpf_map_mmap_sz(const struct bpf_map *map) @@ -1499,6 +1578,9 @@ 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) { @@ -1545,6 +1627,9 @@ 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); @@ -1564,6 +1649,10 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj) for (sec_idx = 1; sec_idx < obj->efile.sec_cnt; sec_idx++) { sec_desc = &obj->efile.secs[sec_idx]; + /* Skip recognized sections with size 0. */ + if (!sec_desc->data || sec_desc->data->d_size == 0) + continue; + switch (sec_desc->sec_type) { case SEC_DATA: sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); @@ -1616,7 +1705,7 @@ static int set_kcfg_value_tri(struct extern_desc *ext, void *ext_val, switch (ext->kcfg.type) { case KCFG_BOOL: if (value == 'm') { - pr_warn("extern (kcfg) %s=%c should be tristate or char\n", + pr_warn("extern (kcfg) '%s': value '%c' implies tristate or char type\n", ext->name, value); return -EINVAL; } @@ -1637,7 +1726,7 @@ static int set_kcfg_value_tri(struct extern_desc *ext, void *ext_val, case KCFG_INT: case KCFG_CHAR_ARR: default: - pr_warn("extern (kcfg) %s=%c should be bool, tristate, or char\n", + pr_warn("extern (kcfg) '%s': value '%c' implies bool, tristate, or char type\n", ext->name, value); return -EINVAL; } @@ -1651,7 +1740,8 @@ static int set_kcfg_value_str(struct extern_desc *ext, char *ext_val, size_t len; if (ext->kcfg.type != KCFG_CHAR_ARR) { - pr_warn("extern (kcfg) %s=%s should be char array\n", ext->name, value); + pr_warn("extern (kcfg) '%s': value '%s' implies char array type\n", + ext->name, value); return -EINVAL; } @@ -1665,7 +1755,7 @@ static int set_kcfg_value_str(struct extern_desc *ext, char *ext_val, /* strip quotes */ len -= 2; if (len >= ext->kcfg.sz) { - pr_warn("extern (kcfg) '%s': long string config %s of (%zu bytes) truncated to %d bytes\n", + pr_warn("extern (kcfg) '%s': long string '%s' of (%zu bytes) truncated to %d bytes\n", ext->name, value, len, ext->kcfg.sz - 1); len = ext->kcfg.sz - 1; } @@ -1722,13 +1812,20 @@ static bool is_kcfg_value_in_range(const struct extern_desc *ext, __u64 v) static int set_kcfg_value_num(struct extern_desc *ext, void *ext_val, __u64 value) { - if (ext->kcfg.type != KCFG_INT && ext->kcfg.type != KCFG_CHAR) { - pr_warn("extern (kcfg) %s=%llu should be integer\n", + if (ext->kcfg.type != KCFG_INT && ext->kcfg.type != KCFG_CHAR && + ext->kcfg.type != KCFG_BOOL) { + pr_warn("extern (kcfg) '%s': value '%llu' implies integer, char, or boolean type\n", ext->name, (unsigned long long)value); return -EINVAL; } + if (ext->kcfg.type == KCFG_BOOL && value > 1) { + pr_warn("extern (kcfg) '%s': value '%llu' isn't boolean compatible\n", + ext->name, (unsigned long long)value); + return -EINVAL; + + } if (!is_kcfg_value_in_range(ext, value)) { - pr_warn("extern (kcfg) %s=%llu value doesn't fit in %d bytes\n", + pr_warn("extern (kcfg) '%s': value '%llu' doesn't fit in %d bytes\n", ext->name, (unsigned long long)value, ext->kcfg.sz); return -ERANGE; } @@ -1792,16 +1889,19 @@ static int bpf_object__process_kconfig_line(struct bpf_object *obj, /* assume integer */ err = parse_u64(value, &num); if (err) { - pr_warn("extern (kcfg) %s=%s should be integer\n", - ext->name, value); + pr_warn("extern (kcfg) '%s': value '%s' isn't a valid integer\n", ext->name, value); return err; } + if (ext->kcfg.type != KCFG_INT && ext->kcfg.type != KCFG_CHAR) { + pr_warn("extern (kcfg) '%s': value '%s' implies integer type\n", ext->name, value); + return -EINVAL; + } err = set_kcfg_value_num(ext, ext_val, num); break; } if (err) return err; - pr_debug("extern (kcfg) %s=%s\n", ext->name, value); + pr_debug("extern (kcfg) '%s': set to %s\n", ext->name, value); return 0; } @@ -1897,133 +1997,6 @@ static int bpf_object__init_kconfig_map(struct bpf_object *obj) return 0; } -static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) -{ - Elf_Data *symbols = obj->efile.symbols; - int i, map_def_sz = 0, nr_maps = 0, nr_syms; - Elf_Data *data = NULL; - Elf_Scn *scn; - - if (obj->efile.maps_shndx < 0) - return 0; - - if (!symbols) - return -EINVAL; - - scn = elf_sec_by_idx(obj, obj->efile.maps_shndx); - data = elf_sec_data(obj, scn); - if (!scn || !data) { - pr_warn("elf: failed to get legacy map definitions for %s\n", - obj->path); - return -EINVAL; - } - - /* - * Count number of maps. Each map has a name. - * Array of maps is not supported: only the first element is - * considered. - * - * TODO: Detect array of map and report error. - */ - nr_syms = symbols->d_size / sizeof(Elf64_Sym); - for (i = 0; i < nr_syms; i++) { - Elf64_Sym *sym = elf_sym_by_idx(obj, i); - - if (sym->st_shndx != obj->efile.maps_shndx) - continue; - if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION) - continue; - nr_maps++; - } - /* Assume equally sized map definitions */ - pr_debug("elf: found %d legacy map definitions (%zd bytes) in %s\n", - nr_maps, data->d_size, obj->path); - - if (!data->d_size || nr_maps == 0 || (data->d_size % nr_maps) != 0) { - pr_warn("elf: unable to determine legacy map definition size in %s\n", - obj->path); - return -EINVAL; - } - map_def_sz = data->d_size / nr_maps; - - /* Fill obj->maps using data in "maps" section. */ - for (i = 0; i < nr_syms; i++) { - Elf64_Sym *sym = elf_sym_by_idx(obj, i); - const char *map_name; - struct bpf_map_def *def; - struct bpf_map *map; - - if (sym->st_shndx != obj->efile.maps_shndx) - continue; - if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION) - continue; - - map = bpf_object__add_map(obj); - if (IS_ERR(map)) - return PTR_ERR(map); - - map_name = elf_sym_str(obj, sym->st_name); - if (!map_name) { - pr_warn("failed to get map #%d name sym string for obj %s\n", - i, obj->path); - return -LIBBPF_ERRNO__FORMAT; - } - - if (ELF64_ST_BIND(sym->st_info) == STB_LOCAL) { - pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); - return -ENOTSUP; - } - - map->libbpf_type = LIBBPF_MAP_UNSPEC; - map->sec_idx = sym->st_shndx; - map->sec_offset = sym->st_value; - pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n", - map_name, map->sec_idx, map->sec_offset); - if (sym->st_value + map_def_sz > data->d_size) { - pr_warn("corrupted maps section in %s: last map \"%s\" too small\n", - obj->path, map_name); - return -EINVAL; - } - - map->name = strdup(map_name); - if (!map->name) { - pr_warn("map '%s': failed to alloc map name\n", map_name); - return -ENOMEM; - } - pr_debug("map %d is \"%s\"\n", i, map->name); - def = (struct bpf_map_def *)(data->d_buf + sym->st_value); - /* - * If the definition of the map in the object file fits in - * bpf_map_def, copy it. Any extra fields in our version - * of bpf_map_def will default to zero as a result of the - * calloc above. - */ - if (map_def_sz <= sizeof(struct bpf_map_def)) { - memcpy(&map->def, def, map_def_sz); - } else { - /* - * Here the map structure being read is bigger than what - * we expect, truncate if the excess bits are all zero. - * If they are not zero, reject this map as - * incompatible. - */ - char *b; - - for (b = ((char *)def) + sizeof(struct bpf_map_def); - b < ((char *)def) + map_def_sz; b++) { - if (*b != 0) { - pr_warn("maps section in %s: \"%s\" has unrecognized, non-zero options\n", - obj->path, map_name); - if (strict) - return -EINVAL; - } - } - memcpy(&map->def, def, sizeof(struct bpf_map_def)); - } - } - return 0; -} - const struct btf_type * skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id) { @@ -2076,6 +2049,8 @@ static const char *__btf_kind_str(__u16 kind) case BTF_KIND_DATASEC: return "datasec"; case BTF_KIND_FLOAT: return "float"; case BTF_KIND_DECL_TAG: return "decl_tag"; + case BTF_KIND_TYPE_TAG: return "type_tag"; + case BTF_KIND_ENUM64: return "enum64"; default: return "unknown"; } } @@ -2122,23 +2097,41 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf, return true; } +static int pathname_concat(char *buf, size_t buf_sz, const char *path, const char *name) +{ + int len; + + len = snprintf(buf, buf_sz, "%s/%s", path, name); + if (len < 0) + return -EINVAL; + if (len >= buf_sz) + return -ENAMETOOLONG; + + return 0; +} + static int build_map_pin_path(struct bpf_map *map, const char *path) { char buf[PATH_MAX]; - int len; + int err; if (!path) path = "/sys/fs/bpf"; - len = snprintf(buf, PATH_MAX, "%s/%s", path, bpf_map__name(map)); - if (len < 0) - return -EINVAL; - else if (len >= PATH_MAX) - return -ENAMETOOLONG; + err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); + if (err) + return err; return bpf_map__set_pin_path(map, buf); } +/* should match definition in bpf_helpers.h */ +enum libbpf_pin_type { + LIBBPF_PIN_NONE, + /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ + LIBBPF_PIN_BY_NAME, +}; + int parse_btf_map_def(const char *map_name, struct btf *btf, const struct btf_type *def_t, bool strict, struct btf_map_def *map_def, struct btf_map_def *inner_def) @@ -2255,6 +2248,9 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, map_def->parts |= MAP_DEF_VALUE_SIZE | MAP_DEF_VALUE_TYPE; } else if (strcmp(name, "values") == 0) { + bool is_map_in_map = bpf_map_type__is_map_in_map(map_def->map_type); + bool is_prog_array = map_def->map_type == BPF_MAP_TYPE_PROG_ARRAY; + const char *desc = is_map_in_map ? "map-in-map inner" : "prog-array value"; char inner_map_name[128]; int err; @@ -2268,8 +2264,8 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, map_name, name); return -EINVAL; } - if (!bpf_map_type__is_map_in_map(map_def->map_type)) { - pr_warn("map '%s': should be map-in-map.\n", + if (!is_map_in_map && !is_prog_array) { + pr_warn("map '%s': should be map-in-map or prog-array.\n", map_name); return -ENOTSUP; } @@ -2281,22 +2277,30 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, map_def->value_size = 4; t = btf__type_by_id(btf, m->type); if (!t) { - pr_warn("map '%s': map-in-map inner type [%d] not found.\n", - map_name, m->type); + pr_warn("map '%s': %s type [%d] not found.\n", + map_name, desc, m->type); return -EINVAL; } if (!btf_is_array(t) || btf_array(t)->nelems) { - pr_warn("map '%s': map-in-map inner spec is not a zero-sized array.\n", - map_name); + pr_warn("map '%s': %s spec is not a zero-sized array.\n", + map_name, desc); return -EINVAL; } t = skip_mods_and_typedefs(btf, btf_array(t)->type, NULL); if (!btf_is_ptr(t)) { - pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", - map_name, btf_kind_str(t)); + pr_warn("map '%s': %s def is of unexpected kind %s.\n", + map_name, desc, btf_kind_str(t)); return -EINVAL; } t = skip_mods_and_typedefs(btf, t->type, NULL); + if (is_prog_array) { + if (!btf_is_func_proto(t)) { + pr_warn("map '%s': prog-array value def is of unexpected kind %s.\n", + map_name, btf_kind_str(t)); + return -EINVAL; + } + continue; + } if (!btf_is_struct(t)) { pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", map_name, btf_kind_str(t)); @@ -2349,6 +2353,43 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, return 0; } +static size_t adjust_ringbuf_sz(size_t sz) +{ + __u32 page_sz = sysconf(_SC_PAGE_SIZE); + __u32 mul; + + /* if user forgot to set any size, make sure they see error */ + if (sz == 0) + return 0; + /* Kernel expects BPF_MAP_TYPE_RINGBUF's max_entries to be + * a power-of-2 multiple of kernel's page size. If user diligently + * satisified these conditions, pass the size through. + */ + if ((sz % page_sz) == 0 && is_pow_of_2(sz / page_sz)) + return sz; + + /* Otherwise find closest (page_sz * power_of_2) product bigger than + * user-set size to satisfy both user size request and kernel + * requirements and substitute correct max_entries for map creation. + */ + for (mul = 1; mul <= UINT_MAX / page_sz; mul <<= 1) { + if (mul * page_sz > sz) + return mul * page_sz; + } + + /* if it's impossible to satisfy the conditions (i.e., user size is + * very close to UINT_MAX but is not a power-of-2 multiple of + * page_size) then just return original size and let kernel reject it + */ + return sz; +} + +static bool map_is_ringbuf(const struct bpf_map *map) +{ + return map->def.type == BPF_MAP_TYPE_RINGBUF || + map->def.type == BPF_MAP_TYPE_USER_RINGBUF; +} + static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def) { map->def.type = def->map_type; @@ -2362,6 +2403,10 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def map->btf_key_type_id = def->key_type_id; map->btf_value_type_id = def->value_type_id; + /* auto-adjust BPF ringbuf map max_entries to be a multiple of page size */ + if (map_is_ringbuf(map)) + map->def.max_entries = adjust_ringbuf_sz(map->def.max_entries); + if (def->parts & MAP_DEF_MAP_TYPE) pr_debug("map '%s': found type = %u.\n", map->name, def->map_type); @@ -2496,6 +2541,10 @@ 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; } @@ -2556,12 +2605,11 @@ static int bpf_object__init_maps(struct bpf_object *obj, { const char *pin_root_path; bool strict; - int err; + int err = 0; strict = !OPTS_GET(opts, relaxed_maps, false); pin_root_path = OPTS_GET(opts, pin_root_path, NULL); - err = bpf_object__init_user_maps(obj, strict); err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path); err = err ?: bpf_object__init_global_data_maps(obj); err = err ?: bpf_object__init_kconfig_map(obj); @@ -2588,17 +2636,23 @@ static bool btf_needs_sanitization(struct bpf_object *obj) bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); + bool has_type_tag = kernel_supports(obj, FEAT_BTF_TYPE_TAG); + bool has_enum64 = kernel_supports(obj, FEAT_BTF_ENUM64); - return !has_func || !has_datasec || !has_func_global || !has_float || !has_decl_tag; + return !has_func || !has_datasec || !has_func_global || !has_float || + !has_decl_tag || !has_type_tag || !has_enum64; } -static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) +static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) { bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC); bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); + bool has_type_tag = kernel_supports(obj, FEAT_BTF_TYPE_TAG); + bool has_enum64 = kernel_supports(obj, FEAT_BTF_ENUM64); + int enum64_placeholder_id = 0; struct btf_type *t; int i, j, vlen; @@ -2657,8 +2711,36 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) */ t->name_off = 0; t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0); - } + } else if (!has_type_tag && btf_is_type_tag(t)) { + /* replace TYPE_TAG with a CONST */ + t->name_off = 0; + t->info = BTF_INFO_ENC(BTF_KIND_CONST, 0, 0); + } else if (!has_enum64 && btf_is_enum(t)) { + /* clear the kflag */ + t->info = btf_type_info(btf_kind(t), btf_vlen(t), false); + } else if (!has_enum64 && btf_is_enum64(t)) { + /* replace ENUM64 with a union */ + struct btf_member *m; + + if (enum64_placeholder_id == 0) { + enum64_placeholder_id = btf__add_int(btf, "enum64_placeholder", 1, 0); + if (enum64_placeholder_id < 0) + return enum64_placeholder_id; + + t = (struct btf_type *)btf__type_by_id(btf, i); + } + + m = btf_members(t); + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_UNION, 0, vlen); + for (j = 0; j < vlen; j++, m++) { + m->type = enum64_placeholder_id; + m->offset = 0; + } + } } + + return 0; } static bool libbpf_needs_btf(const struct bpf_object *obj) @@ -2691,6 +2773,9 @@ static int bpf_object__init_btf(struct bpf_object *obj, btf__set_pointer_size(obj->btf, 8); } if (btf_ext_data) { + struct btf_ext_info *ext_segs[3]; + int seg_num, sec_num; + if (!obj->btf) { pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", BTF_EXT_ELF_SEC, BTF_ELF_SEC); @@ -2704,6 +2789,43 @@ static int bpf_object__init_btf(struct bpf_object *obj, obj->btf_ext = NULL; goto out; } + + /* setup .BTF.ext to ELF section mapping */ + ext_segs[0] = &obj->btf_ext->func_info; + ext_segs[1] = &obj->btf_ext->line_info; + ext_segs[2] = &obj->btf_ext->core_relo_info; + for (seg_num = 0; seg_num < ARRAY_SIZE(ext_segs); seg_num++) { + struct btf_ext_info *seg = ext_segs[seg_num]; + const struct btf_ext_info_sec *sec; + const char *sec_name; + Elf_Scn *scn; + + if (seg->sec_cnt == 0) + continue; + + seg->sec_idxs = calloc(seg->sec_cnt, sizeof(*seg->sec_idxs)); + if (!seg->sec_idxs) { + err = -ENOMEM; + goto out; + } + + sec_num = 0; + for_each_btf_ext_sec(seg, sec) { + /* preventively increment index to avoid doing + * this before every continue below + */ + sec_num++; + + sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); + if (str_is_empty(sec_name)) + continue; + scn = elf_sec_by_name(obj, sec_name); + if (!scn) + continue; + + seg->sec_idxs[sec_num - 1] = elf_ndxscn(scn); + } + } } out: if (err && libbpf_needs_btf(obj)) { @@ -2743,7 +2865,7 @@ 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; } @@ -2752,13 +2874,12 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) { t_var = btf__type_by_id(btf, vsi->type); - var = btf_var(t_var); - - if (!btf_is_var(t_var)) { + if (!t_var || !btf_is_var(t_var)) { pr_debug("Non-VAR type seen in section %s\n", name); return -EINVAL; } + var = btf_var(t_var); if (var->linkage == BTF_VAR_STATIC) continue; @@ -2806,11 +2927,6 @@ static int btf_finalize_data(struct bpf_object *obj, struct btf *btf) return libbpf_err(err); } -int btf__finalize_data(struct bpf_object *obj, struct btf *btf) -{ - return btf_finalize_data(obj, btf); -} - static int bpf_object__finalize_btf(struct bpf_object *obj) { int err; @@ -2863,7 +2979,7 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj) } bpf_object__for_each_program(prog, obj) { - if (!prog->load) + if (!prog->autoload) continue; if (prog_needs_vmlinux_btf(prog)) return true; @@ -2957,7 +3073,9 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) /* enforce 8-byte pointers for BPF-targeted BTFs */ btf__set_pointer_size(obj->btf, 8); - bpf_object__sanitize_btf(obj, kern_btf); + err = bpf_object__sanitize_btf(obj, kern_btf); + if (err) + return err; } if (obj->gen_loader) { @@ -2972,7 +3090,9 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) */ btf__set_fd(kern_btf, 0); } else { - err = btf__load_into_kernel(kern_btf); + /* currently BPF_BTF_LOAD only supports log_level 1 */ + err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size, + obj->log_level ? 1 : 0); } if (sanitize) { if (!err) { @@ -3191,11 +3311,11 @@ static int bpf_object__elf_collect(struct bpf_object *obj) Elf_Scn *scn; Elf64_Shdr *sh; - /* ELF section indices are 1-based, so allocate +1 element to keep - * indexing simple. Also include 0th invalid section into sec_cnt for - * simpler and more traditional iteration logic. + /* ELF section indices are 0-based, but sec #0 is special "invalid" + * section. e_shnum does include sec #0, so e_shnum is the necessary + * size of an array to keep all the sections. */ - obj->efile.sec_cnt = 1 + obj->efile.ehdr->e_shnum; + obj->efile.sec_cnt = obj->efile.ehdr->e_shnum; obj->efile.secs = calloc(obj->efile.sec_cnt, sizeof(*obj->efile.secs)); if (!obj->efile.secs) return -ENOMEM; @@ -3267,12 +3387,17 @@ static int bpf_object__elf_collect(struct bpf_object *obj) if (err) return err; } else if (strcmp(name, "maps") == 0) { - obj->efile.maps_shndx = idx; + pr_warn("elf: legacy map definitions in 'maps' section are not supported by libbpf v1.0+\n"); + return -ENOTSUP; } else if (strcmp(name, MAPS_ELF_SEC) == 0) { obj->efile.btf_maps_shndx = idx; } else if (strcmp(name, BTF_ELF_SEC) == 0) { + if (sh->sh_type != SHT_PROGBITS) + return -LIBBPF_ERRNO__FORMAT; btf_data = data; } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { + if (sh->sh_type != SHT_PROGBITS) + return -LIBBPF_ERRNO__FORMAT; btf_ext_data = data; } else if (sh->sh_type == SHT_SYMTAB) { /* already processed during the first pass above */ @@ -3303,6 +3428,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } else if (sh->sh_type == SHT_REL) { int targ_sec_idx = sh->sh_info; /* points to other section */ + if (sh->sh_entsize != sizeof(Elf64_Rel) || + targ_sec_idx >= obj->efile.sec_cnt) + return -LIBBPF_ERRNO__FORMAT; + /* Only do relo for section with exec instructions */ if (!section_have_execinstr(obj, targ_sec_idx) && strcmp(name, ".rel" STRUCT_OPS_SEC) && @@ -3333,7 +3462,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) /* sort BPF programs by section name and in-section instruction offset * for faster search */ - qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs); + if (obj->nr_programs) + qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs); return bpf_object__init_btf(obj, btf_data, btf_ext_data); } @@ -3453,6 +3583,10 @@ static enum kcfg_type find_kcfg_type(const struct btf *btf, int id, if (strcmp(name, "libbpf_tristate")) return KCFG_UNKNOWN; return KCFG_TRISTATE; + case BTF_KIND_ENUM64: + if (strcmp(name, "libbpf_tristate")) + return KCFG_UNKNOWN; + return KCFG_TRISTATE; case BTF_KIND_ARRAY: if (btf_array(t)->nelems == 0) return KCFG_UNKNOWN; @@ -3555,7 +3689,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj) scn = elf_sec_by_idx(obj, obj->efile.symbols_shndx); sh = elf_sec_hdr(obj, scn); - if (!sh) + if (!sh || sh->sh_entsize != sizeof(Elf64_Sym)) return -LIBBPF_ERRNO__FORMAT; dummy_var_btf_id = add_dummy_ksym_var(obj->btf); @@ -3628,7 +3762,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj) ext->kcfg.type = find_kcfg_type(obj->btf, t->type, &ext->kcfg.is_signed); if (ext->kcfg.type == KCFG_UNKNOWN) { - pr_warn("extern (kcfg) '%s' type is unsupported\n", ext_name); + pr_warn("extern (kcfg) '%s': type is unsupported\n", ext_name); return -ENOTSUP; } } else if (strcmp(sec_name, KSYMS_SEC) == 0) { @@ -3750,34 +3884,8 @@ static int bpf_object__collect_externs(struct bpf_object *obj) return 0; } -struct bpf_program * -bpf_object__find_program_by_title(const struct bpf_object *obj, - const char *title) +static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog) { - struct bpf_program *pos; - - bpf_object__for_each_program(pos, obj) { - if (pos->sec_name && !strcmp(pos->sec_name, title)) - return pos; - } - return errno = ENOENT, NULL; -} - -static bool prog_is_subprog(const struct bpf_object *obj, - const struct bpf_program *prog) -{ - /* For legacy reasons, libbpf supports an entry-point BPF programs - * without SEC() attribute, i.e., those in the .text section. But if - * there are 2 or more such programs in the .text section, they all - * must be subprograms called from entry-point BPF programs in - * designated SEC()'tions, otherwise there is no way to distinguish - * which of those programs should be loaded vs which are a subprogram. - * Similarly, if there is a function/program in .text and at least one - * other BPF program with custom SEC() attribute, then we just assume - * .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. - */ return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; } @@ -3812,8 +3920,7 @@ static bool bpf_object__shndx_is_data(const struct bpf_object *obj, static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, int shndx) { - return shndx == obj->efile.maps_shndx || - shndx == obj->efile.btf_maps_shndx; + return shndx == obj->efile.btf_maps_shndx; } static enum libbpf_map_type @@ -4022,7 +4129,7 @@ static int bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Data *data) { const char *relo_sec_name, *sec_name; - size_t sec_idx = shdr->sh_info; + size_t sec_idx = shdr->sh_info, sym_idx; struct bpf_program *prog; struct reloc_desc *relos; int err, i, nrels; @@ -4033,6 +4140,9 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Dat Elf64_Sym *sym; Elf64_Rel *rel; + if (sec_idx >= obj->efile.sec_cnt) + return -EINVAL; + scn = elf_sec_by_idx(obj, sec_idx); scn_data = elf_sec_data(obj, scn); @@ -4052,16 +4162,23 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Dat return -LIBBPF_ERRNO__FORMAT; } - sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info)); + sym_idx = ELF64_R_SYM(rel->r_info); + sym = elf_sym_by_idx(obj, sym_idx); if (!sym) { - pr_warn("sec '%s': symbol 0x%zx not found for relo #%d\n", - relo_sec_name, (size_t)ELF64_R_SYM(rel->r_info), i); + pr_warn("sec '%s': symbol #%zu not found for relo #%d\n", + relo_sec_name, sym_idx, i); + return -LIBBPF_ERRNO__FORMAT; + } + + if (sym->st_shndx >= obj->efile.sec_cnt) { + pr_warn("sec '%s': corrupted symbol #%zu pointing to invalid section #%zu for relo #%d\n", + relo_sec_name, sym_idx, (size_t)sym->st_shndx, i); return -LIBBPF_ERRNO__FORMAT; } if (rel->r_offset % BPF_INSN_SZ || rel->r_offset >= scn_data->d_size) { pr_warn("sec '%s': invalid offset 0x%zx for relo #%d\n", - relo_sec_name, (size_t)ELF64_R_SYM(rel->r_info), i); + relo_sec_name, (size_t)rel->r_offset, i); return -LIBBPF_ERRNO__FORMAT; } @@ -4108,35 +4225,31 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Dat static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) { - struct bpf_map_def *def = &map->def; - __u32 key_type_id = 0, value_type_id = 0; - int ret; + int id; + + 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. */ - if (map->sec_idx == obj->efile.btf_maps_shndx || - bpf_map__is_struct_ops(map)) + if (map->sec_idx == obj->efile.btf_maps_shndx || bpf_map__is_struct_ops(map)) return 0; - if (!bpf_map__is_internal(map)) { - ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size, - def->value_size, &key_type_id, - &value_type_id); - } else { - /* - * LLVM annotates global data differently in BTF, that is, - * only as '.data', '.bss' or '.rodata'. - */ - ret = btf__find_by_name(obj->btf, map->real_name); - } - if (ret < 0) - return ret; + /* + * LLVM annotates global data differently in BTF, that is, + * only as '.data', '.bss' or '.rodata'. + */ + if (!bpf_map__is_internal(map)) + return -ENOENT; - map->btf_key_type_id = key_type_id; - map->btf_value_type_id = bpf_map__is_internal(map) ? - ret : value_type_id; + id = btf__find_by_name(obj->btf, map->real_name); + if (id < 0) + return id; + + map->btf_key_type_id = 0; + map->btf_value_type_id = id; return 0; } @@ -4176,20 +4289,40 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) return 0; } +bool bpf_map__autocreate(const struct bpf_map *map) +{ + return map->autocreate; +} + +int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate) +{ + if (map->obj->loaded) + return libbpf_err(-EBUSY); + + map->autocreate = autocreate; + return 0; +} + int bpf_map__reuse_fd(struct bpf_map *map, int fd) { - struct bpf_map_info info = {}; - __u32 len = sizeof(info); + struct bpf_map_info info; + __u32 len = sizeof(info), name_len; int new_fd, err; char *new_name; + memset(&info, 0, len); err = bpf_obj_get_info_by_fd(fd, &info, &len); if (err && errno == EINVAL) err = bpf_get_map_info_from_fdinfo(fd, &info); if (err) return libbpf_err(err); - new_name = strdup(info.name); + name_len = strlen(info.name); + if (name_len == BPF_OBJ_NAME_LEN - 1 && strncmp(map->name, info.name, name_len) == 0) + new_name = strdup(map->name); + else + new_name = strdup(info.name); + if (!new_name) return libbpf_err(-errno); @@ -4248,47 +4381,39 @@ struct bpf_map *bpf_map__inner_map(struct bpf_map *map) int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) { - if (map->fd >= 0) + if (map->obj->loaded) return libbpf_err(-EBUSY); + map->def.max_entries = max_entries; - return 0; -} -int bpf_map__resize(struct bpf_map *map, __u32 max_entries) -{ - if (!map || !max_entries) - return libbpf_err(-EINVAL); + /* auto-adjust BPF ringbuf map max_entries to be a multiple of page size */ + if (map_is_ringbuf(map)) + map->def.max_entries = adjust_ringbuf_sz(map->def.max_entries); - return bpf_map__set_max_entries(map, max_entries); + return 0; } static int bpf_object__probe_loading(struct bpf_object *obj) { - struct bpf_load_program_attr attr; char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int ret; + int ret, insn_cnt = ARRAY_SIZE(insns); if (obj->gen_loader) return 0; - /* make sure basic loading works */ - - memset(&attr, 0, sizeof(attr)); - attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.insns = insns; - attr.insns_cnt = ARRAY_SIZE(insns); - attr.license = "GPL"; + ret = bump_rlimit_memlock(); + if (ret) + pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret); - ret = bpf_load_program_xattr(&attr, NULL, 0); - if (ret < 0) { - attr.prog_type = BPF_PROG_TYPE_TRACEPOINT; - ret = bpf_load_program_xattr(&attr, NULL, 0); - } + /* make sure basic loading works */ + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + if (ret < 0) + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); if (ret < 0) { ret = errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4312,29 +4437,28 @@ static int probe_fd(int fd) static int probe_kern_prog_name(void) { - struct bpf_load_program_attr attr; + const size_t attr_sz = offsetofend(union bpf_attr, prog_name); struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; + union bpf_attr attr; int ret; - /* make sure loading with name works */ - - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, attr_sz); attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.insns = insns; - attr.insns_cnt = ARRAY_SIZE(insns); - attr.license = "GPL"; - attr.name = "test"; - ret = bpf_load_program_xattr(&attr, NULL, 0); + attr.license = ptr_to_u64("GPL"); + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)ARRAY_SIZE(insns); + libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); + + /* make sure loading with name works */ + ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); return probe_fd(ret); } static int probe_kern_global_data(void) { - struct bpf_load_program_attr prg_attr; - struct bpf_create_map_attr map_attr; char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), @@ -4342,15 +4466,9 @@ static int probe_kern_global_data(void) BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int ret, map; + int ret, map, insn_cnt = ARRAY_SIZE(insns); - memset(&map_attr, 0, sizeof(map_attr)); - map_attr.map_type = BPF_MAP_TYPE_ARRAY; - map_attr.key_size = sizeof(int); - map_attr.value_size = 32; - map_attr.max_entries = 1; - - map = bpf_create_map_xattr(&map_attr); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4361,13 +4479,7 @@ static int probe_kern_global_data(void) insns[0].imm = map; - memset(&prg_attr, 0, sizeof(prg_attr)); - prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - prg_attr.insns = insns; - prg_attr.insns_cnt = ARRAY_SIZE(insns); - prg_attr.license = "GPL"; - - ret = bpf_load_program_xattr(&prg_attr, NULL, 0); + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); close(map); return probe_fd(ret); } @@ -4468,45 +4580,51 @@ static int probe_kern_btf_decl_tag(void) strs, sizeof(strs))); } -static int probe_kern_array_mmap(void) +static int probe_kern_btf_type_tag(void) { - struct bpf_create_map_attr attr = { - .map_type = BPF_MAP_TYPE_ARRAY, - .map_flags = BPF_F_MMAPABLE, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 1, + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* attr */ + BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ + /* ptr */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ }; - return probe_fd(bpf_create_map_xattr(&attr)); + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_array_mmap(void) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); + return probe_fd(fd); } static int probe_kern_exp_attach_type(void) { - struct bpf_load_program_attr attr; + LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE); struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; + int fd, insn_cnt = ARRAY_SIZE(insns); - memset(&attr, 0, sizeof(attr)); /* use any valid combination of program type and (optional) * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) * to see if kernel supports expected_attach_type field for * BPF_PROG_LOAD command */ - attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK; - attr.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; - attr.insns = insns; - attr.insns_cnt = ARRAY_SIZE(insns); - attr.license = "GPL"; - - return probe_fd(bpf_load_program_xattr(&attr, NULL, 0)); + fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(fd); } static int probe_kern_probe_read_kernel(void) { - struct bpf_load_program_attr attr; struct bpf_insn insns[] = { BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ @@ -4515,34 +4633,22 @@ static int probe_kern_probe_read_kernel(void) BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), BPF_EXIT_INSN(), }; + int fd, insn_cnt = ARRAY_SIZE(insns); - memset(&attr, 0, sizeof(attr)); - attr.prog_type = BPF_PROG_TYPE_KPROBE; - attr.insns = insns; - attr.insns_cnt = ARRAY_SIZE(insns); - attr.license = "GPL"; - - return probe_fd(bpf_load_program_xattr(&attr, NULL, 0)); + fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); + return probe_fd(fd); } static int probe_prog_bind_map(void) { - struct bpf_load_program_attr prg_attr; - struct bpf_create_map_attr map_attr; char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int ret, map, prog; + int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); - memset(&map_attr, 0, sizeof(map_attr)); - map_attr.map_type = BPF_MAP_TYPE_ARRAY; - map_attr.key_size = sizeof(int); - map_attr.value_size = 32; - map_attr.max_entries = 1; - - map = bpf_create_map_xattr(&map_attr); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4551,13 +4657,7 @@ static int probe_prog_bind_map(void) return ret; } - memset(&prg_attr, 0, sizeof(prg_attr)); - prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - prg_attr.insns = insns; - prg_attr.insns_cnt = ARRAY_SIZE(insns); - prg_attr.license = "GPL"; - - prog = bpf_load_program_xattr(&prg_attr, NULL, 0); + prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); if (prog < 0) { close(map); return 0; @@ -4602,19 +4702,14 @@ static int probe_module_btf(void) static int probe_perf_link(void) { - struct bpf_load_program_attr attr; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; int prog_fd, link_fd, err; - memset(&attr, 0, sizeof(attr)); - attr.prog_type = BPF_PROG_TYPE_TRACEPOINT; - attr.insns = insns; - attr.insns_cnt = ARRAY_SIZE(insns); - attr.license = "GPL"; - prog_fd = bpf_load_program_xattr(&attr, NULL, 0); + prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", + insns, ARRAY_SIZE(insns), NULL); if (prog_fd < 0) return -errno; @@ -4631,6 +4726,31 @@ static int probe_perf_link(void) return link_fd < 0 && err == -EBADF; } +static int probe_kern_bpf_cookie(void) +{ + struct bpf_insn insns[] = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), + BPF_EXIT_INSN(), + }; + int ret, insn_cnt = ARRAY_SIZE(insns); + + ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL); + return probe_fd(ret); +} + +static int probe_kern_btf_enum64(void) +{ + static const char strs[] = "\0enum64"; + __u32 types[] = { + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + +static int probe_kern_syscall_wrapper(void); + enum kern_feature_result { FEAT_UNKNOWN = 0, FEAT_SUPPORTED = 1, @@ -4687,14 +4807,29 @@ static struct kern_feature_desc { [FEAT_BTF_DECL_TAG] = { "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, }, + [FEAT_BTF_TYPE_TAG] = { + "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, + }, + [FEAT_MEMCG_ACCOUNT] = { + "memcg-based memory accounting", probe_memcg_account, + }, + [FEAT_BPF_COOKIE] = { + "BPF cookie support", probe_kern_bpf_cookie, + }, + [FEAT_BTF_ENUM64] = { + "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, + }, + [FEAT_SYSCALL_WRAPPER] = { + "Kernel using syscall wrapper", probe_kern_syscall_wrapper, + }, }; -static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) +bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) { struct kern_feature_desc *feat = &feature_probes[feat_id]; int ret; - if (obj->gen_loader) + if (obj && obj->gen_loader) /* To generate loader program assume the latest kernel * to avoid doing extra prog_load, map_create syscalls. */ @@ -4717,13 +4852,12 @@ static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id f static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) { - struct bpf_map_info map_info = {}; + struct bpf_map_info map_info; char msg[STRERR_BUFSIZE]; - __u32 map_info_len; + __u32 map_info_len = sizeof(map_info); int err; - map_info_len = sizeof(map_info); - + memset(&map_info, 0, map_info_len); err = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len); if (err && errno == EINVAL) err = bpf_get_map_info_from_fdinfo(map_fd, &map_info); @@ -4770,8 +4904,8 @@ 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; @@ -4821,45 +4955,22 @@ static void bpf_map__destroy(struct bpf_map *map); static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner) { - struct bpf_create_map_params create_attr; + LIBBPF_OPTS(bpf_map_create_opts, create_attr); struct bpf_map_def *def = &map->def; + const char *map_name = NULL; int err = 0; - memset(&create_attr, 0, sizeof(create_attr)); - if (kernel_supports(obj, FEAT_PROG_NAME)) - create_attr.name = map->name; + map_name = map->name; create_attr.map_ifindex = map->map_ifindex; - create_attr.map_type = def->type; create_attr.map_flags = def->map_flags; - create_attr.key_size = def->key_size; - create_attr.value_size = def->value_size; 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); - create_attr.max_entries = nr_cpus; - } else { - create_attr.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; + create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; - create_attr.btf_fd = 0; - create_attr.btf_key_type_id = 0; - create_attr.btf_value_type_id = 0; - 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; @@ -4893,7 +5004,6 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: - case BPF_MAP_TYPE_RINGBUF: create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; @@ -4904,13 +5014,17 @@ 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, &create_attr, is_inner ? -1 : map - obj->maps); + bpf_gen__map_create(obj->gen_loader, def->type, map_name, + 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. */ map->fd = 0; } else { - map->fd = libbpf__bpf_create_map_xattr(&create_attr); + map->fd = bpf_map_create(def->type, map_name, + def->key_size, def->value_size, + def->max_entries, &create_attr); } if (map->fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { @@ -4925,7 +5039,9 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.btf_value_type_id = 0; map->btf_key_type_id = 0; map->btf_value_type_id = 0; - map->fd = libbpf__bpf_create_map_xattr(&create_attr); + map->fd = bpf_map_create(def->type, map_name, + def->key_size, def->value_size, + def->max_entries, &create_attr); } err = map->fd < 0 ? -errno : 0; @@ -4940,7 +5056,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b return err; } -static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) +static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map) { const struct bpf_map *targ_map; unsigned int i; @@ -4952,18 +5068,18 @@ static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) targ_map = map->init_slots[i]; fd = bpf_map__fd(targ_map); + if (obj->gen_loader) { - pr_warn("// TODO map_update_elem: idx %td key %d value==map_idx %td\n", - map - obj->maps, i, targ_map - obj->maps); - return -ENOTSUP; + bpf_gen__populate_outer_map(obj->gen_loader, + map - obj->maps, i, + targ_map - obj->maps); } else { err = bpf_map_update_elem(map->fd, &i, &fd, 0); } if (err) { err = -errno; pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", - map->name, i, targ_map->name, - fd, err); + map->name, i, targ_map->name, fd, err); return err; } pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n", @@ -4976,6 +5092,77 @@ static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) return 0; } +static int init_prog_array_slots(struct bpf_object *obj, struct bpf_map *map) +{ + const struct bpf_program *targ_prog; + unsigned int i; + int fd, err; + + if (obj->gen_loader) + return -ENOTSUP; + + for (i = 0; i < map->init_slots_sz; i++) { + if (!map->init_slots[i]) + continue; + + targ_prog = map->init_slots[i]; + fd = bpf_program__fd(targ_prog); + + err = bpf_map_update_elem(map->fd, &i, &fd, 0); + if (err) { + err = -errno; + pr_warn("map '%s': failed to initialize slot [%d] to prog '%s' fd=%d: %d\n", + map->name, i, targ_prog->name, fd, err); + return err; + } + pr_debug("map '%s': slot [%d] set to prog '%s' fd=%d\n", + map->name, i, targ_prog->name, fd); + } + + zfree(&map->init_slots); + map->init_slots_sz = 0; + + return 0; +} + +static int bpf_object_init_prog_arrays(struct bpf_object *obj) +{ + struct bpf_map *map; + int i, err; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + + if (!map->init_slots_sz || map->def.type != BPF_MAP_TYPE_PROG_ARRAY) + continue; + + err = init_prog_array_slots(obj, map); + if (err < 0) { + zclose(map->fd); + return err; + } + } + 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) { @@ -4988,6 +5175,32 @@ bpf_object__create_maps(struct bpf_object *obj) for (i = 0; i < obj->nr_maps; i++) { map = &obj->maps[i]; + /* To support old kernels, we skip creating global data maps + * (.rodata, .data, .kconfig, etc); later on, during program + * loading, if we detect that at least one of the to-be-loaded + * programs is referencing any global data map, we'll error + * out with program name and relocation index logged. + * This approach allows to accommodate Clang emitting + * unnecessary .rodata.str1.1 sections for string literals, + * but also it allows to have CO-RE applications that use + * global variables in some of BPF programs, but not others. + * If those global variable-using programs are not loaded at + * runtime due to bpf_program__set_autoload(prog, false), + * bpf_object loading will succeed just fine even on old + * kernels. + */ + if (bpf_map__is_internal(map) && !kernel_supports(obj, FEAT_GLOBAL_DATA)) + map->autocreate = false; + + if (!map->autocreate) { + pr_debug("map '%s': skipped auto-creating...\n", map->name); + continue; + } + + err = map_set_def_max_entries(map); + if (err) + goto err_out; + retried = false; retry: if (map->pin_path) { @@ -5024,8 +5237,8 @@ retry: } } - if (map->init_slots_sz) { - err = init_map_slots(obj, map); + if (map->init_slots_sz && map->def.type != BPF_MAP_TYPE_PROG_ARRAY) { + err = init_map_in_map_slots(obj, map); if (err < 0) { zclose(map->fd); goto err_out; @@ -5083,29 +5296,35 @@ 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; - const char *targ_name; + const struct btf_type *t, *local_t; + const char *targ_name, *local_name; size_t targ_essent_len; int n, i; + local_t = btf__type_by_id(local_cand->btf, local_cand->id); + local_name = btf__str_by_offset(local_cand->btf, local_t->name_off); + n = btf__type_cnt(targ_btf); for (i = targ_start_id; i < n; i++) { t = btf__type_by_id(targ_btf, i); - if (btf_kind(t) != btf_kind(local_cand->t)) + if (!btf_kind_core_compat(t, local_t)) continue; targ_name = btf__name_by_offset(targ_btf, t->name_off); @@ -5116,12 +5335,12 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand, if (targ_essent_len != local_essent_len) continue; - if (strncmp(local_cand->name, targ_name, local_essent_len) != 0) + if (strncmp(local_name, targ_name, local_essent_len) != 0) continue; pr_debug("CO-RE relocating [%d] %s %s: found target candidate [%d] %s %s in [%s]\n", - local_cand->id, btf_kind_str(local_cand->t), - local_cand->name, i, btf_kind_str(t), targ_name, + local_cand->id, btf_kind_str(local_t), + local_name, i, btf_kind_str(t), targ_name, targ_btf_name); new_cands = libbpf_reallocarray(cands->cands, cands->len + 1, sizeof(*cands->cands)); @@ -5130,8 +5349,6 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand, cand = &new_cands[cands->len]; cand->btf = targ_btf; - cand->t = t; - cand->name = targ_name; cand->id = i; cands->cands = new_cands; @@ -5238,18 +5455,21 @@ bpf_core_find_cands(struct bpf_object *obj, const struct btf *local_btf, __u32 l struct bpf_core_cand local_cand = {}; struct bpf_core_cand_list *cands; const struct btf *main_btf; + const struct btf_type *local_t; + const char *local_name; size_t local_essent_len; int err, i; local_cand.btf = local_btf; - local_cand.t = btf__type_by_id(local_btf, local_type_id); - if (!local_cand.t) + local_cand.id = local_type_id; + local_t = btf__type_by_id(local_btf, local_type_id); + if (!local_t) return ERR_PTR(-EINVAL); - local_cand.name = btf__name_by_offset(local_btf, local_cand.t->name_off); - if (str_is_empty(local_cand.name)) + local_name = btf__name_by_offset(local_btf, local_t->name_off); + if (str_is_empty(local_name)) return ERR_PTR(-EINVAL); - local_essent_len = bpf_core_essential_name_len(local_cand.name); + local_essent_len = bpf_core_essential_name_len(local_name); cands = calloc(1, sizeof(*cands)); if (!cands) @@ -5312,76 +5532,13 @@ err_out: int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id) { - const struct btf_type *local_type, *targ_type; - int depth = 32; /* max recursion depth */ - - /* caller made sure that names match (ignoring flavor suffix) */ - local_type = btf__type_by_id(local_btf, local_id); - targ_type = btf__type_by_id(targ_btf, targ_id); - if (btf_kind(local_type) != btf_kind(targ_type)) - return 0; - -recur: - depth--; - if (depth < 0) - return -EINVAL; - - local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id); - targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); - if (!local_type || !targ_type) - return -EINVAL; - - if (btf_kind(local_type) != btf_kind(targ_type)) - return 0; - - switch (btf_kind(local_type)) { - case BTF_KIND_UNKN: - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: - case BTF_KIND_ENUM: - case BTF_KIND_FWD: - return 1; - case BTF_KIND_INT: - /* just reject deprecated bitfield-like integers; all other - * integers are by default compatible between each other - */ - return btf_int_offset(local_type) == 0 && btf_int_offset(targ_type) == 0; - case BTF_KIND_PTR: - local_id = local_type->type; - targ_id = targ_type->type; - goto recur; - case BTF_KIND_ARRAY: - local_id = btf_array(local_type)->type; - targ_id = btf_array(targ_type)->type; - goto recur; - case BTF_KIND_FUNC_PROTO: { - struct btf_param *local_p = btf_params(local_type); - struct btf_param *targ_p = btf_params(targ_type); - __u16 local_vlen = btf_vlen(local_type); - __u16 targ_vlen = btf_vlen(targ_type); - int i, err; - - if (local_vlen != targ_vlen) - return 0; - - for (i = 0; i < local_vlen; i++, local_p++, targ_p++) { - skip_mods_and_typedefs(local_btf, local_p->type, &local_id); - skip_mods_and_typedefs(targ_btf, targ_p->type, &targ_id); - err = bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id); - if (err <= 0) - return err; - } + return __bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id, 32); +} - /* tail recurse for return type check */ - skip_mods_and_typedefs(local_btf, local_type->type, &local_id); - skip_mods_and_typedefs(targ_btf, targ_type->type, &targ_id); - goto recur; - } - default: - pr_warn("unexpected kind %s relocated, local [%d], target [%d]\n", - btf_kind_str(local_type), local_id, targ_id); - return 0; - } +int bpf_core_types_match(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id) +{ + return __bpf_core_types_match(local_btf, local_id, targ_btf, targ_id, false, 32); } static size_t bpf_core_hash_fn(const void *key, void *ctx) @@ -5399,32 +5556,55 @@ static void *u32_as_hash_key(__u32 x) return (void *)(uintptr_t)x; } -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 record_relo_core(struct bpf_program *prog, + const struct bpf_core_relo *core_relo, int insn_idx) +{ + struct reloc_desc *relos, *relo; + + relos = libbpf_reallocarray(prog->reloc_desc, + prog->nr_reloc + 1, sizeof(*relos)); + if (!relos) + return -ENOMEM; + relo = &relos[prog->nr_reloc]; + relo->type = RELO_CORE; + relo->insn_idx = insn_idx; + relo->core_relo = core_relo; + prog->reloc_desc = relos; + prog->nr_reloc++; + return 0; +} + +static const struct bpf_core_relo *find_relo_core(struct bpf_program *prog, int insn_idx) +{ + struct reloc_desc *relo; + int i; + + for (i = 0; i < prog->nr_reloc; i++) { + relo = &prog->reloc_desc[i]; + if (relo->type != RELO_CORE || relo->insn_idx != insn_idx) + continue; + + return relo->core_relo; + } + + return NULL; +} + +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); struct bpf_core_cand_list *cands = NULL; const char *prog_name = prog->name; 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) @@ -5434,14 +5614,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog, if (!local_name) return -EINVAL; - if (prog->obj->gen_loader) { - pr_warn("// TODO core_relo: prog %td insn[%d] %s kind %d\n", - prog - prog->obj->programs, relo->insn_off / 8, - local_name, relo->kind); - return -ENOTSUP; - } - - if (relo->kind != BPF_TYPE_ID_LOCAL && + 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); if (IS_ERR(cands)) { @@ -5457,20 +5630,23 @@ 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); + 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; + int i, err = 0, insn_idx, sec_idx, sec_num; if (obj->btf_ext->core_relo_info.len == 0) return 0; @@ -5491,54 +5667,75 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) } seg = &obj->btf_ext->core_relo_info; + sec_num = 0; for_each_btf_ext_sec(seg, sec) { + sec_idx = seg->sec_idxs[sec_num]; + sec_num++; + sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); if (str_is_empty(sec_name)) { err = -EINVAL; goto out; } - /* bpf_object's ELF is gone by now so it's not easy to find - * section index by section name, but we can find *any* - * bpf_program within desired section name and use it's - * prog->sec_idx to do a proper search by section index and - * instruction offset - */ - prog = NULL; - for (i = 0; i < obj->nr_programs; i++) { - prog = &obj->programs[i]; - if (strcmp(prog->sec_name, sec_name) == 0) - break; - } - if (!prog) { - pr_warn("sec '%s': failed to find a BPF program\n", sec_name); - return -ENOENT; - } - sec_idx = prog->sec_idx; - pr_debug("sec '%s': found %d CO-RE relocations\n", - sec_name, sec->num_info); + pr_debug("sec '%s': found %d CO-RE relocations\n", 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) { - pr_warn("sec '%s': failed to find program at insn #%d for CO-RE offset relocation #%d\n", - sec_name, insn_idx, i); - err = -EINVAL; - goto out; + /* When __weak subprog is "overridden" by another instance + * of the subprog from a different object file, linker still + * appends all the .BTF.ext info that used to belong to that + * eliminated subprogram. + * This is similar to what x86-64 linker does for relocations. + * So just ignore such relocations just like we ignore + * subprog instructions when discovering subprograms. + */ + pr_debug("sec '%s': skipping CO-RE relocation #%d for insn #%d belonging to eliminated weak subprogram\n", + sec_name, i, insn_idx); + continue; } /* no need to apply CO-RE relocation if the program is * not going to be loaded */ - if (!prog->load) + if (!prog->autoload) + continue; + + /* 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]; + + 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; + } + + if (prog->obj->gen_loader) continue; - err = bpf_core_apply_relo(prog, rec, i, obj->btf, cand_cache); + 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; + } } } @@ -5556,6 +5753,36 @@ out: return err; } +/* base map load ldimm64 special constant, used also for log fixup logic */ +#define MAP_LDIMM64_POISON_BASE 2001000000 +#define MAP_LDIMM64_POISON_PFX "200100" + +static void poison_map_ldimm64(struct bpf_program *prog, int relo_idx, + int insn_idx, struct bpf_insn *insn, + int map_idx, const struct bpf_map *map) +{ + int i; + + pr_debug("prog '%s': relo #%d: poisoning insn #%d that loads map #%d '%s'\n", + prog->name, relo_idx, insn_idx, map_idx, map->name); + + /* we turn single ldimm64 into two identical invalid calls */ + for (i = 0; i < 2; i++) { + insn->code = BPF_JMP | BPF_CALL; + insn->dst_reg = 0; + insn->src_reg = 0; + insn->off = 0; + /* if this instruction is reachable (not a dead code), + * verifier will complain with something like: + * invalid func unknown#2001000123 + * where lower 123 is map index into obj->maps[] array + */ + insn->imm = MAP_LDIMM64_POISON_BASE + map_idx; + + insn++; + } +} + /* Relocate data references within program code: * - map references; * - global variable references; @@ -5569,26 +5796,35 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) for (i = 0; i < prog->nr_reloc; i++) { struct reloc_desc *relo = &prog->reloc_desc[i]; struct bpf_insn *insn = &prog->insns[relo->insn_idx]; + const struct bpf_map *map; struct extern_desc *ext; switch (relo->type) { case RELO_LD64: + map = &obj->maps[relo->map_idx]; if (obj->gen_loader) { insn[0].src_reg = BPF_PSEUDO_MAP_IDX; insn[0].imm = relo->map_idx; - } else { + } else if (map->autocreate) { insn[0].src_reg = BPF_PSEUDO_MAP_FD; - insn[0].imm = obj->maps[relo->map_idx].fd; + insn[0].imm = map->fd; + } else { + poison_map_ldimm64(prog, i, relo->insn_idx, insn, + relo->map_idx, map); } break; case RELO_DATA: + map = &obj->maps[relo->map_idx]; insn[1].imm = insn[0].imm + relo->sym_off; if (obj->gen_loader) { insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; insn[0].imm = relo->map_idx; - } else { + } else if (map->autocreate) { insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; - insn[0].imm = obj->maps[relo->map_idx].fd; + insn[0].imm = map->fd; + } else { + poison_map_ldimm64(prog, i, relo->insn_idx, insn, + relo->map_idx, map); } break; case RELO_EXTERN_VAR: @@ -5635,6 +5871,9 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) case RELO_CALL: /* handled already */ break; + case RELO_CORE: + /* will be handled by bpf_program_record_relos() */ + break; default: pr_warn("prog '%s': relo #%d: bad relo type %d\n", prog->name, i, relo->type); @@ -5655,14 +5894,13 @@ static int adjust_prog_btf_ext_info(const struct bpf_object *obj, void *rec, *rec_end, *new_prog_info; const struct btf_ext_info_sec *sec; size_t old_sz, new_sz; - const char *sec_name; - int i, off_adj; + int i, sec_num, sec_idx, off_adj; + sec_num = 0; for_each_btf_ext_sec(ext_info, sec) { - sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); - if (!sec_name) - return -EINVAL; - if (strcmp(sec_name, prog->sec_name) != 0) + sec_idx = ext_info->sec_idxs[sec_num]; + sec_num++; + if (prog->sec_idx != sec_idx) continue; for_each_btf_ext_rec(ext_info, sec, i, rec) { @@ -5798,6 +6036,8 @@ static int cmp_relo_by_insn_idx(const void *key, const void *elem) static struct reloc_desc *find_prog_insn_relo(const struct bpf_program *prog, size_t insn_idx) { + if (!prog->nr_reloc) + return NULL; return bsearch(&insn_idx, prog->reloc_desc, prog->nr_reloc, sizeof(*prog->reloc_desc), cmp_relo_by_insn_idx); } @@ -5813,8 +6053,9 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos)); if (!relos) return -ENOMEM; - memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, - sizeof(*relos) * subprog->nr_reloc); + if (subprog->nr_reloc) + memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, + sizeof(*relos) * subprog->nr_reloc); for (i = main_prog->nr_reloc; i < new_cnt; i++) relos[i].insn_idx += subprog->sub_insn_off; @@ -6054,7 +6295,6 @@ bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog) if (err) return err; - return 0; } @@ -6072,6 +6312,35 @@ bpf_object__free_relocs(struct bpf_object *obj) } } +static int cmp_relocs(const void *_a, const void *_b) +{ + const struct reloc_desc *a = _a; + const struct reloc_desc *b = _b; + + if (a->insn_idx != b->insn_idx) + return a->insn_idx < b->insn_idx ? -1 : 1; + + /* no two relocations should have the same insn_idx, but ... */ + if (a->type != b->type) + return a->type < b->type ? -1 : 1; + + return 0; +} + +static void bpf_object__sort_relos(struct bpf_object *obj) +{ + int i; + + for (i = 0; i < obj->nr_programs; i++) { + struct bpf_program *p = &obj->programs[i]; + + if (!p->nr_reloc) + continue; + + qsort(p->reloc_desc, p->nr_reloc, sizeof(*p->reloc_desc), cmp_relocs); + } +} + static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { @@ -6086,6 +6355,7 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) err); return err; } + bpf_object__sort_relos(obj); } /* Before relocating calls pre-process relocations and mark @@ -6121,6 +6391,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) */ if (prog_is_subprog(obj, prog)) continue; + if (!prog->autoload) + continue; err = bpf_object__relocate_calls(obj, prog); if (err) { @@ -6134,6 +6406,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) prog = &obj->programs[i]; if (prog_is_subprog(obj, prog)) continue; + if (!prog->autoload) + continue; err = bpf_object__relocate_data(obj, prog); if (err) { pr_warn("prog '%s': failed to relocate data references: %d\n", @@ -6141,8 +6415,7 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) return err; } } - if (!obj->gen_loader) - bpf_object__free_relocs(obj); + return 0; } @@ -6156,9 +6429,11 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, int i, j, nrels, new_sz; const struct btf_var_secinfo *vi = NULL; const struct btf_type *sec, *var, *def; - struct bpf_map *map = NULL, *targ_map; + struct bpf_map *map = NULL, *targ_map = NULL; + struct bpf_program *targ_prog = NULL; + bool is_prog_array, is_map_in_map; const struct btf_member *member; - const char *name, *mname; + const char *name, *mname, *type; unsigned int moff; Elf64_Sym *sym; Elf64_Rel *rel; @@ -6185,11 +6460,6 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, return -LIBBPF_ERRNO__FORMAT; } name = elf_sym_str(obj, sym->st_name) ?: "<?>"; - if (sym->st_shndx != obj->efile.btf_maps_shndx) { - pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n", - i, name); - return -LIBBPF_ERRNO__RELOC; - } pr_debug(".maps relo #%d: for %zd value %zd rel->r_offset %zu name %d ('%s')\n", i, (ssize_t)(rel->r_info >> 32), (size_t)sym->st_value, @@ -6211,19 +6481,45 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, return -EINVAL; } - if (!bpf_map_type__is_map_in_map(map->def.type)) - return -EINVAL; - if (map->def.type == BPF_MAP_TYPE_HASH_OF_MAPS && - map->def.key_size != sizeof(int)) { - pr_warn(".maps relo #%d: hash-of-maps '%s' should have key size %zu.\n", - i, map->name, sizeof(int)); + is_map_in_map = bpf_map_type__is_map_in_map(map->def.type); + is_prog_array = map->def.type == BPF_MAP_TYPE_PROG_ARRAY; + type = is_map_in_map ? "map" : "prog"; + if (is_map_in_map) { + if (sym->st_shndx != obj->efile.btf_maps_shndx) { + pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n", + i, name); + return -LIBBPF_ERRNO__RELOC; + } + if (map->def.type == BPF_MAP_TYPE_HASH_OF_MAPS && + map->def.key_size != sizeof(int)) { + pr_warn(".maps relo #%d: hash-of-maps '%s' should have key size %zu.\n", + i, map->name, sizeof(int)); + return -EINVAL; + } + targ_map = bpf_object__find_map_by_name(obj, name); + if (!targ_map) { + pr_warn(".maps relo #%d: '%s' isn't a valid map reference\n", + i, name); + return -ESRCH; + } + } else if (is_prog_array) { + targ_prog = bpf_object__find_program_by_name(obj, name); + if (!targ_prog) { + pr_warn(".maps relo #%d: '%s' isn't a valid program reference\n", + i, name); + return -ESRCH; + } + if (targ_prog->sec_idx != sym->st_shndx || + targ_prog->sec_insn_off * 8 != sym->st_value || + prog_is_subprog(obj, targ_prog)) { + pr_warn(".maps relo #%d: '%s' isn't an entry-point program\n", + i, name); + return -LIBBPF_ERRNO__RELOC; + } + } else { return -EINVAL; } - targ_map = bpf_object__find_map_by_name(obj, name); - if (!targ_map) - return -ESRCH; - var = btf__type_by_id(obj->btf, vi->type); def = skip_mods_and_typedefs(obj->btf, var->type, NULL); if (btf_vlen(def) == 0) @@ -6254,30 +6550,15 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, (new_sz - map->init_slots_sz) * host_ptr_sz); map->init_slots_sz = new_sz; } - map->init_slots[moff] = targ_map; + map->init_slots[moff] = is_map_in_map ? (void *)targ_map : (void *)targ_prog; - pr_debug(".maps relo #%d: map '%s' slot [%d] points to map '%s'\n", - i, map->name, moff, name); + pr_debug(".maps relo #%d: map '%s' slot [%d] points to %s '%s'\n", + i, map->name, moff, type, name); } return 0; } -static int cmp_relocs(const void *_a, const void *_b) -{ - const struct reloc_desc *a = _a; - const struct reloc_desc *b = _b; - - if (a->insn_idx != b->insn_idx) - return a->insn_idx < b->insn_idx ? -1 : 1; - - /* no two relocations should have the same insn_idx, but ... */ - if (a->type != b->type) - return a->type < b->type ? -1 : 1; - - return 0; -} - static int bpf_object__collect_relos(struct bpf_object *obj) { int i, err; @@ -6310,14 +6591,7 @@ static int bpf_object__collect_relos(struct bpf_object *obj) return err; } - for (i = 0; i < obj->nr_programs; i++) { - struct bpf_program *p = &obj->programs[i]; - - if (!p->nr_reloc) - continue; - - qsort(p->reloc_desc, p->nr_reloc, sizeof(*p->reloc_desc), cmp_relocs); - } + bpf_object__sort_relos(obj); return 0; } @@ -6372,26 +6646,43 @@ 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_params *attr, 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; /* old kernels might not support specifying expected_attach_type */ if ((def & SEC_EXP_ATTACH_OPT) && !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE)) - attr->expected_attach_type = 0; + opts->expected_attach_type = 0; if (def & SEC_SLEEPABLE) - attr->prog_flags |= BPF_F_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 ((prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_LSM || - prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { + if ((def & SEC_ATTACH_BTF) && !prog->attach_btf_id) { int btf_obj_fd = 0, btf_type_id = 0, err; const char *attach_name; - attach_name = strchr(prog->sec_name, '/') + 1; + attach_name = strchr(prog->sec_name, '/'); + if (!attach_name) { + /* if BPF program is annotated with just SEC("fentry") + * (or similar) without declaratively specifying + * target, then it is expected that target will be + * specified with bpf_program__set_attach_target() at + * runtime before BPF object load step. If not, then + * there is nothing to load into the kernel as BPF + * verifier won't be able to validate BPF program + * correctness anyways. + */ + pr_warn("prog '%s': no BTF-based attach target is specified, use bpf_program__set_attach_target()\n", + prog->name); + return -EINVAL; + } + attach_name++; /* skip over / */ + err = libbpf_find_attach_btf_id(prog, attach_name, &btf_obj_fd, &btf_type_id); if (err) return err; @@ -6402,25 +6693,29 @@ static int libbpf_preload_prog(struct bpf_program *prog, /* but by now libbpf common logic is not utilizing * prog->atach_btf_obj_fd/prog->attach_btf_id anymore because - * this callback is called after attrs were populated by - * libbpf, so this callback has to update attr explicitly here + * this callback is called after opts were populated by + * libbpf, so this callback has to update opts explicitly here */ - attr->attach_btf_obj_fd = btf_obj_fd; - attr->attach_btf_id = btf_type_id; + opts->attach_btf_obj_fd = btf_obj_fd; + opts->attach_btf_id = btf_type_id; } return 0; } -static int -load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, - char *license, __u32 kern_version, int *pfd) +static void fixup_verifier_log(struct bpf_program *prog, char *buf, size_t buf_sz); + +static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog, + struct bpf_insn *insns, int insns_cnt, + const char *license, __u32 kern_version, int *prog_fd) { - struct bpf_prog_load_params load_attr = {}; - struct bpf_object *obj = prog->obj; + LIBBPF_OPTS(bpf_prog_load_opts, load_attr); + const char *prog_name = NULL; char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; - char *log_buf = NULL; + char *log_buf = NULL, *tmp; int btf_fd, ret, err; + bool own_log_buf = true; + __u32 log_level = prog->log_level; if (prog->type == BPF_PROG_TYPE_UNSPEC) { /* @@ -6435,14 +6730,9 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, if (!insns || !insns_cnt) return -EINVAL; - load_attr.prog_type = prog->type; load_attr.expected_attach_type = prog->expected_attach_type; if (kernel_supports(obj, FEAT_PROG_NAME)) - load_attr.name = prog->name; - load_attr.insns = insns; - load_attr.insn_cnt = insns_cnt; - load_attr.license = license; - load_attr.attach_btf_id = prog->attach_btf_id; + prog_name = prog->name; load_attr.attach_prog_fd = prog->attach_prog_fd; load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; load_attr.attach_btf_id = prog->attach_btf_id; @@ -6460,42 +6750,68 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.line_info_rec_size = prog->line_info_rec_size; load_attr.line_info_cnt = prog->line_info_cnt; } - load_attr.log_level = prog->log_level; + load_attr.log_level = log_level; load_attr.prog_flags = prog->prog_flags; 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); return err; } + insns = prog->insns; + insns_cnt = prog->insns_cnt; } if (obj->gen_loader) { - bpf_gen__prog_load(obj->gen_loader, &load_attr, + bpf_gen__prog_load(obj->gen_loader, prog->type, prog->name, + license, insns, insns_cnt, &load_attr, prog - obj->programs); - *pfd = -1; + *prog_fd = -1; return 0; } -retry_load: - if (log_buf_size) { - log_buf = malloc(log_buf_size); - if (!log_buf) - return -ENOMEM; - *log_buf = 0; +retry_load: + /* if log_level is zero, we don't request logs initially even if + * custom log_buf is specified; if the program load fails, then we'll + * bump log_level to 1 and use either custom log_buf or we'll allocate + * our own and retry the load to get details on what failed + */ + if (log_level) { + if (prog->log_buf) { + log_buf = prog->log_buf; + log_buf_size = prog->log_size; + own_log_buf = false; + } else if (obj->log_buf) { + log_buf = obj->log_buf; + log_buf_size = obj->log_size; + own_log_buf = false; + } else { + log_buf_size = max((size_t)BPF_LOG_BUF_SIZE, log_buf_size * 2); + tmp = realloc(log_buf, log_buf_size); + if (!tmp) { + ret = -ENOMEM; + goto out; + } + log_buf = tmp; + log_buf[0] = '\0'; + own_log_buf = true; + } } load_attr.log_buf = log_buf; - load_attr.log_buf_sz = log_buf_size; - ret = libbpf__bpf_prog_load(&load_attr); + load_attr.log_size = log_buf_size; + load_attr.log_level = log_level; + ret = bpf_prog_load(prog->type, prog_name, license, insns, insns_cnt, &load_attr); if (ret >= 0) { - if (log_buf && load_attr.log_level) - pr_debug("verifier log:\n%s", log_buf); + if (log_level && own_log_buf) { + pr_debug("prog '%s': -- BEGIN PROG LOAD LOG --\n%s-- END PROG LOAD LOG --\n", + prog->name, log_buf); + } if (obj->has_rodata && kernel_supports(obj, FEAT_PROG_BIND_MAP)) { struct bpf_map *map; @@ -6508,61 +6824,216 @@ retry_load: if (bpf_prog_bind_map(ret, bpf_map__fd(map), NULL)) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("prog '%s': failed to bind .rodata map: %s\n", - prog->name, cp); + pr_warn("prog '%s': failed to bind map '%s': %s\n", + prog->name, map->real_name, cp); /* Don't fail hard if can't bind rodata. */ } } } - *pfd = ret; + *prog_fd = ret; ret = 0; goto out; } - if (!log_buf || errno == ENOSPC) { - log_buf_size = max((size_t)BPF_LOG_BUF_SIZE, - log_buf_size << 1); - - free(log_buf); + if (log_level == 0) { + log_level = 1; goto retry_load; } - ret = errno ? -errno : -LIBBPF_ERRNO__LOAD; + /* On ENOSPC, increase log buffer size and retry, unless custom + * log_buf is specified. + * Be careful to not overflow u32, though. Kernel's log buf size limit + * isn't part of UAPI so it can always be bumped to full 4GB. So don't + * multiply by 2 unless we are sure we'll fit within 32 bits. + * Currently, we'll get -EINVAL when we reach (UINT_MAX >> 2). + */ + if (own_log_buf && errno == ENOSPC && log_buf_size <= UINT_MAX / 2) + goto retry_load; + + ret = -errno; + + /* post-process verifier log to improve error descriptions */ + fixup_verifier_log(prog, log_buf, log_buf_size); + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("load bpf program failed: %s\n", cp); + pr_warn("prog '%s': BPF program load failed: %s\n", prog->name, cp); pr_perm_msg(ret); - if (log_buf && log_buf[0] != '\0') { - ret = -LIBBPF_ERRNO__VERIFY; - pr_warn("-- BEGIN DUMP LOG ---\n"); - pr_warn("\n%s\n", log_buf); - pr_warn("-- END LOG --\n"); - } else if (load_attr.insn_cnt >= BPF_MAXINSNS) { - pr_warn("Program too large (%zu insns), at most %d insns\n", - load_attr.insn_cnt, BPF_MAXINSNS); - ret = -LIBBPF_ERRNO__PROG2BIG; - } else if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) { - /* Wrong program type? */ - int fd; - - load_attr.prog_type = BPF_PROG_TYPE_KPROBE; - load_attr.expected_attach_type = 0; - load_attr.log_buf = NULL; - load_attr.log_buf_sz = 0; - fd = libbpf__bpf_prog_load(&load_attr); - if (fd >= 0) { - close(fd); - ret = -LIBBPF_ERRNO__PROGTYPE; - goto out; - } + if (own_log_buf && log_buf && log_buf[0] != '\0') { + pr_warn("prog '%s': -- BEGIN PROG LOAD LOG --\n%s-- END PROG LOAD LOG --\n", + prog->name, log_buf); } out: - free(log_buf); + if (own_log_buf) + free(log_buf); return ret; } -static int bpf_program__record_externs(struct bpf_program *prog) +static char *find_prev_line(char *buf, char *cur) +{ + char *p; + + if (cur == buf) /* end of a log buf */ + return NULL; + + p = cur - 1; + while (p - 1 >= buf && *(p - 1) != '\n') + p--; + + return p; +} + +static void patch_log(char *buf, size_t buf_sz, size_t log_sz, + char *orig, size_t orig_sz, const char *patch) +{ + /* size of the remaining log content to the right from the to-be-replaced part */ + size_t rem_sz = (buf + log_sz) - (orig + orig_sz); + size_t patch_sz = strlen(patch); + + if (patch_sz != orig_sz) { + /* If patch line(s) are longer than original piece of verifier log, + * shift log contents by (patch_sz - orig_sz) bytes to the right + * starting from after to-be-replaced part of the log. + * + * If patch line(s) are shorter than original piece of verifier log, + * shift log contents by (orig_sz - patch_sz) bytes to the left + * starting from after to-be-replaced part of the log + * + * We need to be careful about not overflowing available + * buf_sz capacity. If that's the case, we'll truncate the end + * of the original log, as necessary. + */ + if (patch_sz > orig_sz) { + if (orig + patch_sz >= buf + buf_sz) { + /* patch is big enough to cover remaining space completely */ + patch_sz -= (orig + patch_sz) - (buf + buf_sz) + 1; + rem_sz = 0; + } else if (patch_sz - orig_sz > buf_sz - log_sz) { + /* patch causes part of remaining log to be truncated */ + rem_sz -= (patch_sz - orig_sz) - (buf_sz - log_sz); + } + } + /* shift remaining log to the right by calculated amount */ + memmove(orig + patch_sz, orig + orig_sz, rem_sz); + } + + memcpy(orig, patch, patch_sz); +} + +static void fixup_log_failed_core_relo(struct bpf_program *prog, + char *buf, size_t buf_sz, size_t log_sz, + char *line1, char *line2, char *line3) +{ + /* Expected log for failed and not properly guarded CO-RE relocation: + * line1 -> 123: (85) call unknown#195896080 + * line2 -> invalid func unknown#195896080 + * line3 -> <anything else or end of buffer> + * + * "123" is the index of the instruction that was poisoned. We extract + * instruction index to find corresponding CO-RE relocation and + * replace this part of the log with more relevant information about + * failed CO-RE relocation. + */ + const struct bpf_core_relo *relo; + struct bpf_core_spec spec; + char patch[512], spec_buf[256]; + int insn_idx, err, spec_len; + + if (sscanf(line1, "%d: (%*d) call unknown#195896080\n", &insn_idx) != 1) + return; + + relo = find_relo_core(prog, insn_idx); + if (!relo) + return; + + err = bpf_core_parse_spec(prog->name, prog->obj->btf, relo, &spec); + if (err) + return; + + spec_len = bpf_core_format_spec(spec_buf, sizeof(spec_buf), &spec); + snprintf(patch, sizeof(patch), + "%d: <invalid CO-RE relocation>\n" + "failed to resolve CO-RE relocation %s%s\n", + insn_idx, spec_buf, spec_len >= sizeof(spec_buf) ? "..." : ""); + + patch_log(buf, buf_sz, log_sz, line1, line3 - line1, patch); +} + +static void fixup_log_missing_map_load(struct bpf_program *prog, + char *buf, size_t buf_sz, size_t log_sz, + char *line1, char *line2, char *line3) +{ + /* Expected log for failed and not properly guarded CO-RE relocation: + * line1 -> 123: (85) call unknown#2001000345 + * line2 -> invalid func unknown#2001000345 + * line3 -> <anything else or end of buffer> + * + * "123" is the index of the instruction that was poisoned. + * "345" in "2001000345" are map index in obj->maps to fetch map name. + */ + struct bpf_object *obj = prog->obj; + const struct bpf_map *map; + int insn_idx, map_idx; + char patch[128]; + + if (sscanf(line1, "%d: (%*d) call unknown#%d\n", &insn_idx, &map_idx) != 2) + return; + + map_idx -= MAP_LDIMM64_POISON_BASE; + if (map_idx < 0 || map_idx >= obj->nr_maps) + return; + map = &obj->maps[map_idx]; + + snprintf(patch, sizeof(patch), + "%d: <invalid BPF map reference>\n" + "BPF map '%s' is referenced but wasn't created\n", + insn_idx, map->name); + + patch_log(buf, buf_sz, log_sz, line1, line3 - line1, patch); +} + +static void fixup_verifier_log(struct bpf_program *prog, char *buf, size_t buf_sz) +{ + /* look for familiar error patterns in last N lines of the log */ + const size_t max_last_line_cnt = 10; + char *prev_line, *cur_line, *next_line; + size_t log_sz; + int i; + + if (!buf) + return; + + log_sz = strlen(buf) + 1; + next_line = buf + log_sz - 1; + + for (i = 0; i < max_last_line_cnt; i++, next_line = cur_line) { + cur_line = find_prev_line(buf, next_line); + if (!cur_line) + return; + + /* failed CO-RE relocation case */ + if (str_has_pfx(cur_line, "invalid func unknown#195896080\n")) { + prev_line = find_prev_line(buf, cur_line); + if (!prev_line) + continue; + + fixup_log_failed_core_relo(prog, buf, buf_sz, log_sz, + prev_line, cur_line, next_line); + return; + } else if (str_has_pfx(cur_line, "invalid func unknown#"MAP_LDIMM64_POISON_PFX)) { + prev_line = find_prev_line(buf, cur_line); + if (!prev_line) + continue; + + fixup_log_missing_map_load(prog, buf, buf_sz, log_sz, + prev_line, cur_line, next_line); + return; + } + } +} + +static int bpf_program_record_relos(struct bpf_program *prog) { struct bpf_object *obj = prog->obj; int i; @@ -6584,6 +7055,17 @@ static int bpf_program__record_externs(struct bpf_program *prog) ext->is_weak, false, BTF_KIND_FUNC, relo->insn_idx); break; + case RELO_CORE: { + struct bpf_core_relo cr = { + .insn_off = relo->insn_idx * 8, + .type_id = relo->core_relo->type_id, + .access_str_off = relo->core_relo->access_str_off, + .kind = relo->core_relo->kind, + }; + + bpf_gen__record_relo_core(obj->gen_loader, &cr); + break; + } default: continue; } @@ -6591,85 +7073,6 @@ static int bpf_program__record_externs(struct bpf_program *prog) return 0; } -int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) -{ - int err = 0, fd, i; - - if (prog->obj->loaded) { - pr_warn("prog '%s': can't load after object was loaded\n", prog->name); - return libbpf_err(-EINVAL); - } - - if (prog->instances.nr < 0 || !prog->instances.fds) { - if (prog->preprocessor) { - pr_warn("Internal error: can't load program '%s'\n", - prog->name); - return libbpf_err(-LIBBPF_ERRNO__INTERNAL); - } - - prog->instances.fds = malloc(sizeof(int)); - if (!prog->instances.fds) { - pr_warn("Not enough memory for BPF fds\n"); - return libbpf_err(-ENOMEM); - } - prog->instances.nr = 1; - prog->instances.fds[0] = -1; - } - - if (!prog->preprocessor) { - if (prog->instances.nr != 1) { - pr_warn("prog '%s': inconsistent nr(%d) != 1\n", - prog->name, prog->instances.nr); - } - if (prog->obj->gen_loader) - bpf_program__record_externs(prog); - err = load_program(prog, prog->insns, prog->insns_cnt, - license, kern_ver, &fd); - if (!err) - prog->instances.fds[0] = fd; - goto out; - } - - for (i = 0; i < prog->instances.nr; i++) { - struct bpf_prog_prep_result result; - bpf_program_prep_t preprocessor = prog->preprocessor; - - memset(&result, 0, sizeof(result)); - err = preprocessor(prog, i, prog->insns, - prog->insns_cnt, &result); - if (err) { - pr_warn("Preprocessing the %dth instance of program '%s' failed\n", - i, prog->name); - goto out; - } - - if (!result.new_insn_ptr || !result.new_insn_cnt) { - pr_debug("Skip loading the %dth instance of program '%s'\n", - i, prog->name); - prog->instances.fds[i] = -1; - if (result.pfd) - *result.pfd = -1; - continue; - } - - err = load_program(prog, result.new_insn_ptr, - result.new_insn_cnt, license, kern_ver, &fd); - if (err) { - pr_warn("Loading the %dth instance of program '%s' failed\n", - i, prog->name); - goto out; - } - - if (result.pfd) - *result.pfd = fd; - prog->instances.fds[i] = fd; - } -out: - if (err) - pr_warn("failed to load program '%s'\n", prog->name); - return libbpf_err(err); -} - static int bpf_object__load_progs(struct bpf_object *obj, int log_level) { @@ -6688,17 +7091,24 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) prog = &obj->programs[i]; if (prog_is_subprog(obj, prog)) continue; - if (!prog->load) { + if (!prog->autoload) { pr_debug("prog '%s': skipped loading\n", prog->name); continue; } prog->log_level |= log_level; - err = bpf_program__load(prog, obj->license, obj->kern_version); - if (err) + + if (obj->gen_loader) + bpf_program_record_relos(prog); + + err = bpf_object_load_prog(obj, prog, prog->insns, prog->insns_cnt, + obj->license, obj->kern_version, &prog->fd); + if (err) { + pr_warn("prog '%s': failed to load: %d\n", prog->name, err); return err; + } } - if (obj->gen_loader) - bpf_object__free_relocs(obj); + + bpf_object__free_relocs(obj); return 0; } @@ -6718,21 +7128,14 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object continue; } - bpf_program__set_type(prog, prog->sec_def->prog_type); - bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type); - -#pragma GCC diagnostic push -#pragma GCC diagnostic ignored "-Wdeprecated-declarations" - if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING || - prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) - prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); -#pragma GCC diagnostic pop + prog->type = prog->sec_def->prog_type; + prog->expected_attach_type = prog->sec_def->expected_attach_type; /* 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); @@ -6744,14 +7147,16 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object return 0; } -static struct bpf_object * -__bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, - const struct bpf_object_open_opts *opts) +static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz, + const struct bpf_object_open_opts *opts) { const char *obj_name, *kconfig, *btf_tmp_path; struct bpf_object *obj; char tmp_name[64]; int err; + char *log_buf; + size_t log_size; + __u32 log_level; if (elf_version(EV_CURRENT) == EV_NONE) { pr_warn("failed to init libelf for %s\n", @@ -6774,10 +7179,22 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, pr_debug("loading object '%s' from buffer\n", obj_name); } + log_buf = OPTS_GET(opts, kernel_log_buf, NULL); + log_size = OPTS_GET(opts, kernel_log_size, 0); + log_level = OPTS_GET(opts, kernel_log_level, 0); + if (log_size > UINT_MAX) + return ERR_PTR(-EINVAL); + if (log_size && !log_buf) + return ERR_PTR(-EINVAL); + obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); if (IS_ERR(obj)) return obj; + obj->log_buf = log_buf; + obj->log_size = log_size; + obj->log_level = log_level; + btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL); if (btf_tmp_path) { if (strlen(btf_tmp_path) >= PATH_MAX) { @@ -6819,36 +7236,6 @@ out: return ERR_PTR(err); } -static struct bpf_object * -__bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags) -{ - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, - .relaxed_maps = flags & MAPS_RELAX_COMPAT, - ); - - /* param validation */ - if (!attr->file) - return NULL; - - pr_debug("loading %s\n", attr->file); - return __bpf_object__open(attr->file, NULL, 0, &opts); -} - -struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) -{ - return libbpf_ptr(__bpf_object__open_xattr(attr, 0)); -} - -struct bpf_object *bpf_object__open(const char *path) -{ - struct bpf_object_open_attr attr = { - .file = path, - .prog_type = BPF_PROG_TYPE_UNSPEC, - }; - - return libbpf_ptr(__bpf_object__open_xattr(&attr, 0)); -} - struct bpf_object * bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) { @@ -6857,34 +7244,22 @@ bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) pr_debug("loading %s\n", path); - return libbpf_ptr(__bpf_object__open(path, NULL, 0, opts)); + return libbpf_ptr(bpf_object_open(path, NULL, 0, opts)); } -struct bpf_object * -bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, - const struct bpf_object_open_opts *opts) +struct bpf_object *bpf_object__open(const char *path) { - if (!obj_buf || obj_buf_sz == 0) - return libbpf_err_ptr(-EINVAL); - - return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, opts)); + return bpf_object__open_file(path, NULL); } struct bpf_object * -bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, - const char *name) +bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, + const struct bpf_object_open_opts *opts) { - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, - .object_name = name, - /* wrong default, but backwards-compatible */ - .relaxed_maps = true, - ); - - /* returning NULL is wrong, but backwards-compatible */ if (!obj_buf || obj_buf_sz == 0) - return errno = EINVAL, NULL; + return libbpf_err_ptr(-EINVAL); - return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, &opts)); + return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, opts)); } static int bpf_object_unload(struct bpf_object *obj) @@ -6906,8 +7281,6 @@ static int bpf_object_unload(struct bpf_object *obj) return 0; } -int bpf_object__unload(struct bpf_object *obj) __attribute__((alias("bpf_object_unload"))); - static int bpf_object__sanitize_maps(struct bpf_object *obj) { struct bpf_map *m; @@ -6915,10 +7288,6 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) bpf_object__for_each_map(m, obj) { if (!bpf_map__is_internal(m)) continue; - if (!kernel_supports(obj, FEAT_GLOBAL_DATA)) { - pr_warn("kernel doesn't support global data\n"); - return -ENOTSUP; - } if (!kernel_supports(obj, FEAT_ARRAY_MMAP)) m->def.map_flags ^= BPF_F_MMAPABLE; } @@ -6926,12 +7295,10 @@ 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; @@ -6950,35 +7317,51 @@ 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': set to 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) @@ -7173,28 +7556,52 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, for (i = 0; i < obj->nr_extern; i++) { ext = &obj->externs[i]; - if (ext->type == EXT_KCFG && - strcmp(ext->name, "LINUX_KERNEL_VERSION") == 0) { - void *ext_val = kcfg_data + ext->kcfg.data_off; - __u32 kver = get_kernel_version(); + if (ext->type == EXT_KSYM) { + if (ext->ksym.type_id) + need_vmlinux_btf = true; + else + need_kallsyms = true; + continue; + } else if (ext->type == EXT_KCFG) { + void *ext_ptr = kcfg_data + ext->kcfg.data_off; + __u64 value = 0; - if (!kver) { - pr_warn("failed to get kernel version\n"); + /* Kconfig externs need actual /proc/config.gz */ + if (str_has_pfx(ext->name, "CONFIG_")) { + need_config = true; + continue; + } + + /* Virtual kcfg externs are customly handled by libbpf */ + if (strcmp(ext->name, "LINUX_KERNEL_VERSION") == 0) { + value = get_kernel_version(); + if (!value) { + pr_warn("extern (kcfg) '%s': failed to get kernel version\n", ext->name); + return -EINVAL; + } + } else if (strcmp(ext->name, "LINUX_HAS_BPF_COOKIE") == 0) { + value = kernel_supports(obj, FEAT_BPF_COOKIE); + } else if (strcmp(ext->name, "LINUX_HAS_SYSCALL_WRAPPER") == 0) { + value = kernel_supports(obj, FEAT_SYSCALL_WRAPPER); + } else if (!str_has_pfx(ext->name, "LINUX_") || !ext->is_weak) { + /* Currently libbpf supports only CONFIG_ and LINUX_ prefixed + * __kconfig externs, where LINUX_ ones are virtual and filled out + * customly by libbpf (their values don't come from Kconfig). + * If LINUX_xxx variable is not recognized by libbpf, but is marked + * __weak, it defaults to zero value, just like for CONFIG_xxx + * externs. + */ + pr_warn("extern (kcfg) '%s': unrecognized virtual extern\n", ext->name); return -EINVAL; } - err = set_kcfg_value_num(ext, ext_val, kver); + + err = set_kcfg_value_num(ext, ext_ptr, value); if (err) return err; - pr_debug("extern (kcfg) %s=0x%x\n", ext->name, kver); - } else if (ext->type == EXT_KCFG && str_has_pfx(ext->name, "CONFIG_")) { - need_config = true; - } else if (ext->type == EXT_KSYM) { - if (ext->ksym.type_id) - need_vmlinux_btf = true; - else - need_kallsyms = true; + pr_debug("extern (kcfg) '%s': set to 0x%llx\n", + ext->name, (long long)value); } else { - pr_warn("unrecognized extern '%s'\n", ext->name); + pr_warn("extern '%s': unrecognized extern kind\n", ext->name); return -EINVAL; } } @@ -7230,10 +7637,10 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, ext = &obj->externs[i]; if (!ext->is_set && !ext->is_weak) { - pr_warn("extern %s (strong) not resolved\n", ext->name); + pr_warn("extern '%s' (strong): not resolved\n", ext->name); return -ESRCH; } else if (!ext->is_set) { - pr_debug("extern %s (weak) not resolved, defaulting to zero\n", + pr_debug("extern '%s' (weak): not resolved, defaulting to zero\n", ext->name); } } @@ -7241,14 +7648,10 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, return 0; } -int bpf_object__load_xattr(struct bpf_object_load_attr *attr) +static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path) { - struct bpf_object *obj; int err, i; - if (!attr) - return libbpf_err(-EINVAL); - obj = attr->obj; if (!obj) return libbpf_err(-EINVAL); @@ -7258,7 +7661,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) } if (obj->gen_loader) - bpf_gen__init(obj->gen_loader, attr->log_level, obj->nr_programs, obj->nr_maps); + bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); err = bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); @@ -7267,8 +7670,9 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) err = err ? : bpf_object__sanitize_maps(obj); err = err ? : bpf_object__init_kern_struct_ops_maps(obj); err = err ? : bpf_object__create_maps(obj); - err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : attr->target_btf_path); - err = err ? : bpf_object__load_progs(obj, attr->log_level); + err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path); + err = err ? : bpf_object__load_progs(obj, extra_log_level); + err = err ? : bpf_object_init_prog_arrays(obj); if (obj->gen_loader) { /* reset FDs */ @@ -7314,11 +7718,7 @@ out: int bpf_object__load(struct bpf_object *obj) { - struct bpf_object_load_attr attr = { - .obj = obj, - }; - - return bpf_object__load_xattr(&attr); + return bpf_object_load(obj, 0, NULL); } static int make_parent_dir(const char *path) @@ -7373,11 +7773,16 @@ static int check_path(const char *path) return err; } -static int bpf_program_pin_instance(struct bpf_program *prog, const char *path, int instance) +int bpf_program__pin(struct bpf_program *prog, const char *path) { char *cp, errmsg[STRERR_BUFSIZE]; int err; + if (prog->fd < 0) { + pr_warn("prog '%s': can't pin program that wasn't loaded\n", prog->name); + return libbpf_err(-EINVAL); + } + err = make_parent_dir(path); if (err) return libbpf_err(err); @@ -7386,170 +7791,35 @@ static int bpf_program_pin_instance(struct bpf_program *prog, const char *path, if (err) return libbpf_err(err); - if (prog == NULL) { - pr_warn("invalid program pointer\n"); - return libbpf_err(-EINVAL); - } - - if (instance < 0 || instance >= prog->instances.nr) { - pr_warn("invalid prog instance %d of prog %s (max %d)\n", - instance, prog->name, prog->instances.nr); - return libbpf_err(-EINVAL); - } - - if (bpf_obj_pin(prog->instances.fds[instance], path)) { + if (bpf_obj_pin(prog->fd, path)) { err = -errno; cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("failed to pin program: %s\n", cp); + pr_warn("prog '%s': failed to pin at '%s': %s\n", prog->name, path, cp); return libbpf_err(err); } - pr_debug("pinned program '%s'\n", path); + pr_debug("prog '%s': pinned at '%s'\n", prog->name, path); return 0; } -static int bpf_program_unpin_instance(struct bpf_program *prog, const char *path, int instance) +int bpf_program__unpin(struct bpf_program *prog, const char *path) { int err; - err = check_path(path); - if (err) - return libbpf_err(err); - - if (prog == NULL) { - pr_warn("invalid program pointer\n"); - return libbpf_err(-EINVAL); - } - - if (instance < 0 || instance >= prog->instances.nr) { - pr_warn("invalid prog instance %d of prog %s (max %d)\n", - instance, prog->name, prog->instances.nr); + if (prog->fd < 0) { + pr_warn("prog '%s': can't unpin program that wasn't loaded\n", prog->name); return libbpf_err(-EINVAL); } - err = unlink(path); - if (err != 0) - return libbpf_err(-errno); - - pr_debug("unpinned program '%s'\n", path); - - return 0; -} - -__attribute__((alias("bpf_program_pin_instance"))) -int bpf_object__pin_instance(struct bpf_program *prog, const char *path, int instance); - -__attribute__((alias("bpf_program_unpin_instance"))) -int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, int instance); - -int bpf_program__pin(struct bpf_program *prog, const char *path) -{ - int i, err; - - err = make_parent_dir(path); - if (err) - return libbpf_err(err); - err = check_path(path); if (err) return libbpf_err(err); - if (prog == NULL) { - pr_warn("invalid program pointer\n"); - return libbpf_err(-EINVAL); - } - - if (prog->instances.nr <= 0) { - pr_warn("no instances of prog %s to pin\n", prog->name); - return libbpf_err(-EINVAL); - } - - if (prog->instances.nr == 1) { - /* don't create subdirs when pinning single instance */ - return bpf_program_pin_instance(prog, path, 0); - } - - for (i = 0; i < prog->instances.nr; i++) { - char buf[PATH_MAX]; - int len; - - len = snprintf(buf, PATH_MAX, "%s/%d", path, i); - if (len < 0) { - err = -EINVAL; - goto err_unpin; - } else if (len >= PATH_MAX) { - err = -ENAMETOOLONG; - goto err_unpin; - } - - err = bpf_program_pin_instance(prog, buf, i); - if (err) - goto err_unpin; - } - - return 0; - -err_unpin: - for (i = i - 1; i >= 0; i--) { - char buf[PATH_MAX]; - int len; - - len = snprintf(buf, PATH_MAX, "%s/%d", path, i); - if (len < 0) - continue; - else if (len >= PATH_MAX) - continue; - - bpf_program_unpin_instance(prog, buf, i); - } - - rmdir(path); - - return libbpf_err(err); -} - -int bpf_program__unpin(struct bpf_program *prog, const char *path) -{ - int i, err; - - err = check_path(path); - if (err) - return libbpf_err(err); - - if (prog == NULL) { - pr_warn("invalid program pointer\n"); - return libbpf_err(-EINVAL); - } - - if (prog->instances.nr <= 0) { - pr_warn("no instances of prog %s to pin\n", prog->name); - return libbpf_err(-EINVAL); - } - - if (prog->instances.nr == 1) { - /* don't create subdirs when pinning single instance */ - return bpf_program_unpin_instance(prog, path, 0); - } - - for (i = 0; i < prog->instances.nr; i++) { - char buf[PATH_MAX]; - int len; - - len = snprintf(buf, PATH_MAX, "%s/%d", path, i); - if (len < 0) - return libbpf_err(-EINVAL); - else if (len >= PATH_MAX) - return libbpf_err(-ENAMETOOLONG); - - err = bpf_program_unpin_instance(prog, buf, i); - if (err) - return err; - } - - err = rmdir(path); + err = unlink(path); if (err) return libbpf_err(-errno); + pr_debug("prog '%s': unpinned from '%s'\n", prog->name, path); return 0; } @@ -7665,10 +7935,8 @@ 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) { @@ -7707,18 +7975,13 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) char *pin_path = NULL; char buf[PATH_MAX]; - if (path) { - int len; + if (!map->autocreate) + continue; - len = snprintf(buf, PATH_MAX, "%s/%s", path, - bpf_map__name(map)); - if (len < 0) { - err = -EINVAL; - goto err_unpin_maps; - } else if (len >= PATH_MAX) { - err = -ENAMETOOLONG; + if (path) { + err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); + if (err) goto err_unpin_maps; - } sanitize_pin_path(buf); pin_path = buf; } else if (!map->pin_path) { @@ -7733,7 +7996,7 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) return 0; err_unpin_maps: - while ((map = bpf_map__prev(map, obj))) { + while ((map = bpf_object__prev_map(obj, map))) { if (!map->pin_path) continue; @@ -7756,14 +8019,9 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) char buf[PATH_MAX]; if (path) { - int len; - - len = snprintf(buf, PATH_MAX, "%s/%s", path, - bpf_map__name(map)); - if (len < 0) - return libbpf_err(-EINVAL); - else if (len >= PATH_MAX) - return libbpf_err(-ENAMETOOLONG); + err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); + if (err) + return libbpf_err(err); sanitize_pin_path(buf); pin_path = buf; } else if (!map->pin_path) { @@ -7781,6 +8039,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) int bpf_object__pin_programs(struct bpf_object *obj, const char *path) { struct bpf_program *prog; + char buf[PATH_MAX]; int err; if (!obj) @@ -7792,18 +8051,9 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) } bpf_object__for_each_program(prog, obj) { - char buf[PATH_MAX]; - int len; - - len = snprintf(buf, PATH_MAX, "%s/%s", path, - prog->pin_name); - if (len < 0) { - err = -EINVAL; - goto err_unpin_programs; - } else if (len >= PATH_MAX) { - err = -ENAMETOOLONG; + err = pathname_concat(buf, sizeof(buf), path, prog->name); + if (err) goto err_unpin_programs; - } err = bpf_program__pin(prog, buf); if (err) @@ -7813,15 +8063,8 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) return 0; err_unpin_programs: - while ((prog = bpf_program__prev(prog, obj))) { - char buf[PATH_MAX]; - int len; - - len = snprintf(buf, PATH_MAX, "%s/%s", path, - prog->pin_name); - if (len < 0) - continue; - else if (len >= PATH_MAX) + while ((prog = bpf_object__prev_program(obj, prog))) { + if (pathname_concat(buf, sizeof(buf), path, prog->name)) continue; bpf_program__unpin(prog, buf); @@ -7840,14 +8083,10 @@ int bpf_object__unpin_programs(struct bpf_object *obj, const char *path) bpf_object__for_each_program(prog, obj) { char buf[PATH_MAX]; - int len; - len = snprintf(buf, PATH_MAX, "%s/%s", path, - prog->pin_name); - if (len < 0) - return libbpf_err(-EINVAL); - else if (len >= PATH_MAX) - return libbpf_err(-ENAMETOOLONG); + err = pathname_concat(buf, sizeof(buf), path, prog->name); + if (err) + return libbpf_err(err); err = bpf_program__unpin(prog, buf); if (err) @@ -7876,11 +8115,6 @@ int bpf_object__pin(struct bpf_object *obj, const char *path) static void bpf_map__destroy(struct bpf_map *map) { - if (map->clear_priv) - map->clear_priv(map, map->priv); - map->priv = NULL; - map->clear_priv = NULL; - if (map->inner_map) { bpf_map__destroy(map->inner_map); zfree(&map->inner_map); @@ -7916,8 +8150,8 @@ void bpf_object__close(struct bpf_object *obj) if (IS_ERR_OR_NULL(obj)) return; - if (obj->clear_priv) - obj->clear_priv(obj, obj->priv); + usdt_manager_free(obj->usdt_man); + obj->usdt_man = NULL; bpf_gen__free(obj->gen_loader); bpf_object__elf_finish(obj); @@ -7942,33 +8176,9 @@ void bpf_object__close(struct bpf_object *obj) } zfree(&obj->programs); - list_del(&obj->list); free(obj); } -struct bpf_object * -bpf_object__next(struct bpf_object *prev) -{ - struct bpf_object *next; - bool strict = (libbpf_mode & LIBBPF_STRICT_NO_OBJECT_LIST); - - if (strict) - return NULL; - - if (!prev) - next = list_first_entry(&bpf_objects_list, - struct bpf_object, - list); - else - next = list_next_entry(prev, list); - - /* Empty list is noticed here so don't need checking on entry. */ - if (&next->list == &bpf_objects_list) - return NULL; - - return next; -} - const char *bpf_object__name(const struct bpf_object *obj) { return obj ? obj->name : libbpf_err_ptr(-EINVAL); @@ -7999,22 +8209,6 @@ int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version) return 0; } -int bpf_object__set_priv(struct bpf_object *obj, void *priv, - bpf_object_clear_priv_t clear_priv) -{ - if (obj->priv && obj->clear_priv) - obj->clear_priv(obj, obj->priv); - - obj->priv = priv; - obj->clear_priv = clear_priv; - return 0; -} - -void *bpf_object__priv(const struct bpf_object *obj) -{ - return obj ? obj->priv : libbpf_err_ptr(-EINVAL); -} - int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts) { struct bpf_gen *gen; @@ -8058,12 +8252,6 @@ __bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, } struct bpf_program * -bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj) -{ - return bpf_object__next_program(obj, prev); -} - -struct bpf_program * bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev) { struct bpf_program *prog = prev; @@ -8076,12 +8264,6 @@ bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev) } struct bpf_program * -bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj) -{ - return bpf_object__prev_program(obj, next); -} - -struct bpf_program * bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *next) { struct bpf_program *prog = next; @@ -8093,22 +8275,6 @@ bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *next) return prog; } -int bpf_program__set_priv(struct bpf_program *prog, void *priv, - bpf_program_clear_priv_t clear_priv) -{ - if (prog->priv && prog->clear_priv) - prog->clear_priv(prog, prog->priv); - - prog->priv = priv; - prog->clear_priv = clear_priv; - return 0; -} - -void *bpf_program__priv(const struct bpf_program *prog) -{ - return prog ? prog->priv : libbpf_err_ptr(-EINVAL); -} - void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) { prog->prog_ifindex = ifindex; @@ -8124,25 +8290,9 @@ const char *bpf_program__section_name(const struct bpf_program *prog) return prog->sec_name; } -const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) -{ - const char *title; - - title = prog->sec_name; - if (needs_copy) { - title = strdup(title); - if (!title) { - pr_warn("failed to strdup program title\n"); - return libbpf_err_ptr(-ENOMEM); - } - } - - return title; -} - bool bpf_program__autoload(const struct bpf_program *prog) { - return prog->load; + return prog->autoload; } int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) @@ -8150,18 +8300,18 @@ int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) if (prog->obj->loaded) return libbpf_err(-EINVAL); - prog->load = autoload; + prog->autoload = autoload; return 0; } -int bpf_program__fd(const struct bpf_program *prog) +bool bpf_program__autoattach(const struct bpf_program *prog) { - return bpf_program__nth_fd(prog, 0); + return prog->autoattach; } -size_t bpf_program__size(const struct bpf_program *prog) +void bpf_program__set_autoattach(struct bpf_program *prog, bool autoattach) { - return prog->insns_cnt * BPF_INSN_SZ; + prog->autoattach = autoattach; } const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog) @@ -8174,256 +8324,371 @@ size_t bpf_program__insn_cnt(const struct bpf_program *prog) return prog->insns_cnt; } -int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, - bpf_program_prep_t prep) +int bpf_program__set_insns(struct bpf_program *prog, + struct bpf_insn *new_insns, size_t new_insn_cnt) { - int *instances_fds; - - if (nr_instances <= 0 || !prep) - return libbpf_err(-EINVAL); + struct bpf_insn *insns; - if (prog->instances.nr > 0 || prog->instances.fds) { - pr_warn("Can't set pre-processor after loading\n"); - return libbpf_err(-EINVAL); - } + if (prog->obj->loaded) + return -EBUSY; - instances_fds = malloc(sizeof(int) * nr_instances); - if (!instances_fds) { - pr_warn("alloc memory failed for fds\n"); - return libbpf_err(-ENOMEM); + insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns)); + if (!insns) { + pr_warn("prog '%s': failed to realloc prog code\n", prog->name); + return -ENOMEM; } + memcpy(insns, new_insns, new_insn_cnt * sizeof(*insns)); - /* fill all fd with -1 */ - memset(instances_fds, -1, sizeof(int) * nr_instances); - - prog->instances.nr = nr_instances; - prog->instances.fds = instances_fds; - prog->preprocessor = prep; + prog->insns = insns; + prog->insns_cnt = new_insn_cnt; return 0; } -int bpf_program__nth_fd(const struct bpf_program *prog, int n) +int bpf_program__fd(const struct bpf_program *prog) { - int fd; - if (!prog) return libbpf_err(-EINVAL); - if (n >= prog->instances.nr || n < 0) { - pr_warn("Can't get the %dth fd from program %s: only %d instances\n", - n, prog->name, prog->instances.nr); - return libbpf_err(-EINVAL); - } - - fd = prog->instances.fds[n]; - if (fd < 0) { - pr_warn("%dth instance of program '%s' is invalid\n", - n, prog->name); + if (prog->fd < 0) return libbpf_err(-ENOENT); - } - return fd; + return prog->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; } -void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) +int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) { + if (prog->obj->loaded) + return libbpf_err(-EBUSY); + prog->type = type; + return 0; } -static bool bpf_program__is_type(const struct bpf_program *prog, - enum bpf_prog_type type) -{ - return prog ? (prog->type == type) : false; -} - -#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ -int bpf_program__set_##NAME(struct bpf_program *prog) \ -{ \ - if (!prog) \ - return libbpf_err(-EINVAL); \ - bpf_program__set_type(prog, TYPE); \ - return 0; \ -} \ - \ -bool bpf_program__is_##NAME(const struct bpf_program *prog) \ -{ \ - return bpf_program__is_type(prog, TYPE); \ -} \ - -BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER); -BPF_PROG_TYPE_FNS(lsm, BPF_PROG_TYPE_LSM); -BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); -BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS); -BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT); -BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); -BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); -BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); -BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); -BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING); -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; } -void bpf_program__set_expected_attach_type(struct bpf_program *prog, +int bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type) { + if (prog->obj->loaded) + return libbpf_err(-EBUSY); + prog->expected_attach_type = type; + return 0; +} + +__u32 bpf_program__flags(const struct bpf_program *prog) +{ + return prog->prog_flags; +} + +int bpf_program__set_flags(struct bpf_program *prog, __u32 flags) +{ + if (prog->obj->loaded) + return libbpf_err(-EBUSY); + + prog->prog_flags = flags; + return 0; +} + +__u32 bpf_program__log_level(const struct bpf_program *prog) +{ + return prog->log_level; +} + +int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level) +{ + if (prog->obj->loaded) + return libbpf_err(-EBUSY); + + prog->log_level = log_level; + return 0; +} + +const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size) +{ + *log_size = prog->log_size; + return prog->log_buf; +} + +int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size) +{ + if (log_size && !log_buf) + return -EINVAL; + if (prog->log_size > UINT_MAX) + return -EINVAL; + if (prog->obj->loaded) + return -EBUSY; + + prog->log_buf = log_buf; + prog->log_size = log_size; + return 0; } #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_uprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_ksyscall(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_usdt(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), - SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("kprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), - SEC_DEF("uprobe/", KPROBE, 0, SEC_NONE), - SEC_DEF("kretprobe/", KPROBE, 0, SEC_NONE, attach_kprobe), - SEC_DEF("uretprobe/", KPROBE, 0, SEC_NONE), + SEC_DEF("socket", SOCKET_FILTER, 0, SEC_NONE), + SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE), + SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE), + SEC_DEF("kprobe+", KPROBE, 0, SEC_NONE, attach_kprobe), + SEC_DEF("uprobe+", KPROBE, 0, SEC_NONE, attach_uprobe), + SEC_DEF("uprobe.s+", KPROBE, 0, SEC_SLEEPABLE, attach_uprobe), + SEC_DEF("kretprobe+", KPROBE, 0, SEC_NONE, attach_kprobe), + SEC_DEF("uretprobe+", KPROBE, 0, SEC_NONE, attach_uprobe), + SEC_DEF("uretprobe.s+", KPROBE, 0, SEC_SLEEPABLE, attach_uprobe), + 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("ksyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), + SEC_DEF("kretsyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), + SEC_DEF("usdt+", KPROBE, 0, SEC_NONE, attach_usdt), SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX), - SEC_DEF("action", SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX), - SEC_DEF("tracepoint/", TRACEPOINT, 0, SEC_NONE, attach_tp), - SEC_DEF("tp/", TRACEPOINT, 0, SEC_NONE, attach_tp), - SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), - SEC_DEF("raw_tp/", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), - SEC_DEF("raw_tracepoint.w/", RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp), - SEC_DEF("raw_tp.w/", RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp), - SEC_DEF("tp_btf/", TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace), - SEC_DEF("fentry/", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace), - SEC_DEF("fmod_ret/", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace), - SEC_DEF("fexit/", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF, attach_trace), - SEC_DEF("fentry.s/", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), - SEC_DEF("fmod_ret.s/", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), - SEC_DEF("fexit.s/", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), - SEC_DEF("freplace/", EXT, 0, SEC_ATTACH_BTF, attach_trace), - SEC_DEF("lsm/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm), - SEC_DEF("lsm.s/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), - SEC_DEF("iter/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter), + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), + SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), + SEC_DEF("tracepoint+", TRACEPOINT, 0, SEC_NONE, attach_tp), + SEC_DEF("tp+", TRACEPOINT, 0, SEC_NONE, attach_tp), + SEC_DEF("raw_tracepoint+", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tp+", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tracepoint.w+", RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("raw_tp.w+", RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp), + SEC_DEF("tp_btf+", TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry+", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fmod_ret+", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fexit+", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("fentry.s+", TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fmod_ret.s+", TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("fexit.s+", TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace), + SEC_DEF("freplace+", EXT, 0, SEC_ATTACH_BTF, attach_trace), + SEC_DEF("lsm+", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm), + SEC_DEF("lsm.s+", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), + SEC_DEF("lsm_cgroup+", LSM, BPF_LSM_CGROUP, SEC_ATTACH_BTF), + 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", XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX), - SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX), - SEC_DEF("lwt_out", LWT_OUT, 0, SEC_NONE | SEC_SLOPPY_PFX), - SEC_DEF("lwt_xmit", LWT_XMIT, 0, SEC_NONE | SEC_SLOPPY_PFX), - SEC_DEF("lwt_seg6local", LWT_SEG6LOCAL, 0, SEC_NONE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/skb", CGROUP_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX), - SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), - SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("xdp.frags/devmap", XDP, BPF_XDP_DEVMAP, SEC_XDP_FRAGS), + SEC_DEF("xdp/devmap", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), + 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.frags", XDP, BPF_XDP, SEC_XDP_FRAGS), + SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT), + SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE), + SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE), + SEC_DEF("lwt_out", LWT_OUT, 0, SEC_NONE), + SEC_DEF("lwt_xmit", LWT_XMIT, 0, SEC_NONE), + SEC_DEF("lwt_seg6local", LWT_SEG6LOCAL, 0, SEC_NONE), + SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT), + SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT), + SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT), + SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE), + SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT), + SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT), + SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup/skb", CGROUP_SKB, 0, SEC_NONE), + SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE), + SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE), + SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT), + SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE), + SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE), + SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE), + SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE), + SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE), + SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE), + SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT), SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), - SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), }; -#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) +{ + 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; + } + + 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; + + 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)) return sec_def; } + + n = ARRAY_SIZE(section_defs); + for (i = 0; i < n; i++) { + sec_def = §ion_defs[i]; + if (sec_def_matches(sec_def, sec_name)) + 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; @@ -8439,7 +8704,7 @@ 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)) @@ -8483,6 +8748,38 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, return libbpf_err(-ESRCH); } +const char *libbpf_bpf_attach_type_str(enum bpf_attach_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(attach_type_name)) + return NULL; + + return attach_type_name[t]; +} + +const char *libbpf_bpf_link_type_str(enum bpf_link_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(link_type_name)) + return NULL; + + return link_type_name[t]; +} + +const char *libbpf_bpf_map_type_str(enum bpf_map_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(map_type_name)) + return NULL; + + return map_type_name[t]; +} + +const char *libbpf_bpf_prog_type_str(enum bpf_prog_type t) +{ + if (t < 0 || t >= ARRAY_SIZE(prog_type_name)) + return NULL; + + return prog_type_name[t]; +} + static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, size_t offset) { @@ -8633,6 +8930,7 @@ void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, *kind = BTF_KIND_TYPEDEF; break; case BPF_LSM_MAC: + case BPF_LSM_CGROUP: *prefix = BTF_LSM_PREFIX; *kind = BTF_KIND_FUNC; break; @@ -8696,11 +8994,12 @@ int libbpf_find_vmlinux_btf_id(const char *name, static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) { - struct bpf_prog_info info = {}; + struct bpf_prog_info info; __u32 info_len = sizeof(info); struct btf *btf; int err; + memset(&info, 0, info_len); err = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len); if (err) { pr_warn("failed bpf_obj_get_info_by_fd for FD %d: %d\n", @@ -8774,11 +9073,15 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac int err = 0; /* BPF program's BTF ID */ - if (attach_prog_fd) { + if (prog->type == BPF_PROG_TYPE_EXT || attach_prog_fd) { + if (!attach_prog_fd) { + pr_warn("prog '%s': attach program FD is not set\n", prog->name); + return -EINVAL; + } err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd); if (err < 0) { - pr_warn("failed to find BPF program (FD %d) BTF ID for '%s': %d\n", - attach_prog_fd, attach_name, err); + pr_warn("prog '%s': failed to find BPF program (FD %d) BTF ID for '%s': %d\n", + prog->name, attach_prog_fd, attach_name, err); return err; } *btf_obj_fd = 0; @@ -8795,7 +9098,8 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); } if (err) { - pr_warn("failed to find kernel BTF type ID of '%s': %d\n", attach_name, err); + pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %d\n", + prog->name, attach_name, err); return err; } return 0; @@ -8822,7 +9126,7 @@ 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); @@ -8836,11 +9140,6 @@ int bpf_map__fd(const struct bpf_map *map) return map ? map->fd : libbpf_err(-EINVAL); } -const struct bpf_map_def *bpf_map__def(const struct bpf_map *map) -{ - return map ? &map->def : libbpf_err_ptr(-EINVAL); -} - static bool map_uses_real_name(const struct bpf_map *map) { /* Since libbpf started to support custom .data.* and .rodata.* maps, @@ -8955,27 +9254,6 @@ __u32 bpf_map__btf_value_type_id(const struct bpf_map *map) return map ? map->btf_value_type_id : 0; } -int bpf_map__set_priv(struct bpf_map *map, void *priv, - bpf_map_clear_priv_t clear_priv) -{ - if (!map) - return libbpf_err(-EINVAL); - - if (map->priv) { - if (map->clear_priv) - map->clear_priv(map, map->priv); - } - - map->priv = priv; - map->clear_priv = clear_priv; - return 0; -} - -void *bpf_map__priv(const struct bpf_map *map) -{ - return map ? map->priv : libbpf_err_ptr(-EINVAL); -} - int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size) { @@ -8995,11 +9273,6 @@ const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) return map->mmaped; } -bool bpf_map__is_offload_neutral(const struct bpf_map *map) -{ - return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; -} - bool bpf_map__is_internal(const struct bpf_map *map) { return map->libbpf_type != LIBBPF_MAP_UNSPEC; @@ -9028,7 +9301,10 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) pr_warn("error: inner_map_fd already specified\n"); return libbpf_err(-EINVAL); } - zfree(&map->inner_map); + if (map->inner_map) { + bpf_map__destroy(map->inner_map); + zfree(&map->inner_map); + } map->inner_map_fd = fd; return 0; } @@ -9058,12 +9334,6 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) } struct bpf_map * -bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj) -{ - return bpf_object__next_map(obj, prev); -} - -struct bpf_map * bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev) { if (prev == NULL) @@ -9073,12 +9343,6 @@ bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev) } struct bpf_map * -bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj) -{ - return bpf_object__prev_map(obj, next); -} - -struct bpf_map * bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *next) { if (next == NULL) { @@ -9123,120 +9387,125 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name) return bpf_map__fd(bpf_object__find_map_by_name(obj, name)); } -struct bpf_map * -bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) +static int validate_map_op(const struct bpf_map *map, size_t key_sz, + size_t value_sz, bool check_value_sz) { - return libbpf_err_ptr(-ENOTSUP); -} + if (map->fd <= 0) + return -ENOENT; -long libbpf_get_error(const void *ptr) -{ - if (!IS_ERR_OR_NULL(ptr)) - return 0; + if (map->def.key_size != key_sz) { + pr_warn("map '%s': unexpected key size %zu provided, expected %u\n", + map->name, key_sz, map->def.key_size); + return -EINVAL; + } - if (IS_ERR(ptr)) - errno = -PTR_ERR(ptr); + if (!check_value_sz) + return 0; - /* If ptr == NULL, then errno should be already set by the failing - * API, because libbpf never returns NULL on success and it now always - * sets errno on error. So no extra errno handling for ptr == NULL - * case. - */ - return -errno; + switch (map->def.type) { + case BPF_MAP_TYPE_PERCPU_ARRAY: + case BPF_MAP_TYPE_PERCPU_HASH: + case BPF_MAP_TYPE_LRU_PERCPU_HASH: + case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: { + int num_cpu = libbpf_num_possible_cpus(); + size_t elem_sz = roundup(map->def.value_size, 8); + + if (value_sz != num_cpu * elem_sz) { + pr_warn("map '%s': unexpected value size %zu provided for per-CPU map, expected %d * %zu = %zd\n", + map->name, value_sz, num_cpu, elem_sz, num_cpu * elem_sz); + return -EINVAL; + } + break; + } + default: + if (map->def.value_size != value_sz) { + pr_warn("map '%s': unexpected value size %zu provided, expected %u\n", + map->name, value_sz, map->def.value_size); + return -EINVAL; + } + break; + } + return 0; } -int bpf_prog_load(const char *file, enum bpf_prog_type type, - struct bpf_object **pobj, int *prog_fd) +int bpf_map__lookup_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + void *value, size_t value_sz, __u64 flags) { - struct bpf_prog_load_attr attr; + int err; - memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); - attr.file = file; - attr.prog_type = type; - attr.expected_attach_type = 0; + err = validate_map_op(map, key_sz, value_sz, true); + if (err) + return libbpf_err(err); - return bpf_prog_load_xattr(&attr, pobj, prog_fd); + return bpf_map_lookup_elem_flags(map->fd, key, value, flags); } -int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, - struct bpf_object **pobj, int *prog_fd) +int bpf_map__update_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + const void *value, size_t value_sz, __u64 flags) { - struct bpf_object_open_attr open_attr = {}; - struct bpf_program *prog, *first_prog = NULL; - struct bpf_object *obj; - struct bpf_map *map; int err; - if (!attr) - return libbpf_err(-EINVAL); - if (!attr->file) - return libbpf_err(-EINVAL); + err = validate_map_op(map, key_sz, value_sz, true); + if (err) + return libbpf_err(err); - open_attr.file = attr->file; - open_attr.prog_type = attr->prog_type; + return bpf_map_update_elem(map->fd, key, value, flags); +} - obj = bpf_object__open_xattr(&open_attr); - err = libbpf_get_error(obj); +int bpf_map__delete_elem(const struct bpf_map *map, + const void *key, size_t key_sz, __u64 flags) +{ + int err; + + err = validate_map_op(map, key_sz, 0, false /* check_value_sz */); if (err) - return libbpf_err(-ENOENT); + return libbpf_err(err); - bpf_object__for_each_program(prog, obj) { - enum bpf_attach_type attach_type = attr->expected_attach_type; - /* - * to preserve backwards compatibility, bpf_prog_load treats - * attr->prog_type, if specified, as an override to whatever - * bpf_object__open guessed - */ - if (attr->prog_type != BPF_PROG_TYPE_UNSPEC) { - bpf_program__set_type(prog, attr->prog_type); - bpf_program__set_expected_attach_type(prog, - attach_type); - } - if (bpf_program__get_type(prog) == BPF_PROG_TYPE_UNSPEC) { - /* - * we haven't guessed from section name and user - * didn't provide a fallback type, too bad... - */ - bpf_object__close(obj); - return libbpf_err(-EINVAL); - } + return bpf_map_delete_elem_flags(map->fd, key, flags); +} - prog->prog_ifindex = attr->ifindex; - prog->log_level = attr->log_level; - prog->prog_flags |= attr->prog_flags; - if (!first_prog) - first_prog = prog; - } +int bpf_map__lookup_and_delete_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + void *value, size_t value_sz, __u64 flags) +{ + int err; - bpf_object__for_each_map(map, obj) { - if (!bpf_map__is_offload_neutral(map)) - map->map_ifindex = attr->ifindex; - } + err = validate_map_op(map, key_sz, value_sz, true); + if (err) + return libbpf_err(err); - if (!first_prog) { - pr_warn("object file doesn't contain bpf program\n"); - bpf_object__close(obj); - return libbpf_err(-ENOENT); - } + return bpf_map_lookup_and_delete_elem_flags(map->fd, key, value, flags); +} - err = bpf_object__load(obj); - if (err) { - bpf_object__close(obj); +int bpf_map__get_next_key(const struct bpf_map *map, + const void *cur_key, void *next_key, size_t key_sz) +{ + int err; + + err = validate_map_op(map, key_sz, 0, false /* check_value_sz */); + if (err) return libbpf_err(err); - } - *pobj = obj; - *prog_fd = bpf_program__fd(first_prog); - return 0; + return bpf_map_get_next_key(map->fd, cur_key, next_key); } -struct bpf_link { - int (*detach)(struct bpf_link *link); - void (*dealloc)(struct bpf_link *link); - char *pin_path; /* NULL, if not pinned */ - int fd; /* hook FD, -1 if not applicable */ - bool disconnected; -}; +long libbpf_get_error(const void *ptr) +{ + if (!IS_ERR_OR_NULL(ptr)) + return 0; + + if (IS_ERR(ptr)) + errno = -PTR_ERR(ptr); + + /* If ptr == NULL, then errno should be already set by the failing + * API, because libbpf never returns NULL on success and it now always + * sets errno on error. So no extra errno handling for ptr == NULL + * case. + */ + return -errno; +} /* Replace link's underlying BPF program with the new one */ int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog) @@ -9563,13 +9832,16 @@ static int determine_uprobe_retprobe_bit(void) static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, uint64_t offset, int pid, size_t ref_ctr_off) { - struct perf_event_attr attr = {}; + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; char errmsg[STRERR_BUFSIZE]; - int type, pfd, err; + int type, pfd; if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS)) return -EINVAL; + memset(&attr, 0, attr_sz); + type = uprobe ? determine_uprobe_perf_type() : determine_kprobe_perf_type(); if (type < 0) { @@ -9590,7 +9862,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, } attr.config |= 1 << bit; } - attr.size = sizeof(attr); + attr.size = attr_sz; attr.type = type; attr.config |= (__u64)ref_ctr_off << PERF_UPROBE_REF_CTR_OFFSET_SHIFT; attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */ @@ -9601,14 +9873,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, pid < 0 ? -1 : pid /* pid */, pid == -1 ? 0 : -1 /* cpu */, -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); - if (pfd < 0) { - err = -errno; - pr_warn("%s perf_event_open() failed: %s\n", - uprobe ? "uprobe" : "kprobe", - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return err; - } - return pfd; + return pfd >= 0 ? pfd : -errno; } static int append_to_file(const char *file, const char *fmt, ...) @@ -9631,18 +9896,47 @@ static int append_to_file(const char *file, const char *fmt, ...) return err; } +#define DEBUGFS "/sys/kernel/debug/tracing" +#define TRACEFS "/sys/kernel/tracing" + +static bool use_debugfs(void) +{ + static int has_debugfs = -1; + + if (has_debugfs < 0) + has_debugfs = faccessat(AT_FDCWD, DEBUGFS, F_OK, AT_EACCESS) == 0; + + return has_debugfs == 1; +} + +static const char *tracefs_path(void) +{ + return use_debugfs() ? DEBUGFS : TRACEFS; +} + +static const char *tracefs_kprobe_events(void) +{ + return use_debugfs() ? DEBUGFS"/kprobe_events" : TRACEFS"/kprobe_events"; +} + +static const char *tracefs_uprobe_events(void) +{ + return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events"; +} + static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, const char *kfunc_name, size_t offset) { - snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), kfunc_name, offset); + static int index = 0; + + snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx_%d", getpid(), kfunc_name, offset, + __sync_fetch_and_add(&index, 1)); } static int add_kprobe_event_legacy(const char *probe_name, bool retprobe, const char *kfunc_name, size_t offset) { - const char *file = "/sys/kernel/debug/tracing/kprobe_events"; - - return append_to_file(file, "%c:%s/%s %s+0x%zx", + return append_to_file(tracefs_kprobe_events(), "%c:%s/%s %s+0x%zx", retprobe ? 'r' : 'p', retprobe ? "kretprobes" : "kprobes", probe_name, kfunc_name, offset); @@ -9650,18 +9944,16 @@ static int add_kprobe_event_legacy(const char *probe_name, bool retprobe, static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe) { - const char *file = "/sys/kernel/debug/tracing/kprobe_events"; - - return append_to_file(file, "-:%s/%s", retprobe ? "kretprobes" : "kprobes", probe_name); + return append_to_file(tracefs_kprobe_events(), "-:%s/%s", + retprobe ? "kretprobes" : "kprobes", probe_name); } static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retprobe) { char file[256]; - snprintf(file, sizeof(file), - "/sys/kernel/debug/tracing/events/%s/%s/id", - retprobe ? "kretprobes" : "kprobes", probe_name); + snprintf(file, sizeof(file), "%s/events/%s/%s/id", + tracefs_path(), retprobe ? "kretprobes" : "kprobes", probe_name); return parse_uint_from_file(file, "%d\n"); } @@ -9669,7 +9961,8 @@ static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retpro static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, const char *kfunc_name, size_t offset, int pid) { - struct perf_event_attr attr = {}; + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; char errmsg[STRERR_BUFSIZE]; int type, pfd, err; @@ -9682,12 +9975,15 @@ static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, } type = determine_kprobe_perf_type_legacy(probe_name, retprobe); if (type < 0) { + err = type; pr_warn("failed to determine legacy kprobe event id for '%s+0x%zx': %s\n", kfunc_name, offset, - libbpf_strerror_r(type, errmsg, sizeof(errmsg))); - return type; + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + goto err_clean_legacy; } - attr.size = sizeof(attr); + + memset(&attr, 0, attr_sz); + attr.size = attr_sz; attr.config = type; attr.type = PERF_TYPE_TRACEPOINT; @@ -9699,9 +9995,72 @@ static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, err = -errno; pr_warn("legacy kprobe perf_event_open() failed: %s\n", libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return err; + goto err_clean_legacy; } return pfd; + +err_clean_legacy: + /* Clear the newly added legacy kprobe_event */ + remove_kprobe_event_legacy(probe_name, retprobe); + return err; +} + +static const char *arch_specific_syscall_pfx(void) +{ +#if defined(__x86_64__) + return "x64"; +#elif defined(__i386__) + return "ia32"; +#elif defined(__s390x__) + return "s390x"; +#elif defined(__s390__) + return "s390"; +#elif defined(__arm__) + return "arm"; +#elif defined(__aarch64__) + return "arm64"; +#elif defined(__mips__) + return "mips"; +#elif defined(__riscv) + return "riscv"; +#elif defined(__powerpc__) + return "powerpc"; +#elif defined(__powerpc64__) + return "powerpc64"; +#else + return NULL; +#endif +} + +static int probe_kern_syscall_wrapper(void) +{ + char syscall_name[64]; + const char *ksys_pfx; + + ksys_pfx = arch_specific_syscall_pfx(); + if (!ksys_pfx) + return 0; + + snprintf(syscall_name, sizeof(syscall_name), "__%s_sys_bpf", ksys_pfx); + + if (determine_kprobe_perf_type() >= 0) { + int pfd; + + pfd = perf_event_open_probe(false, false, syscall_name, 0, getpid(), 0); + if (pfd >= 0) + close(pfd); + + return pfd >= 0 ? 1 : 0; + } else { /* legacy mode */ + char probe_name[128]; + + gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0); + if (add_kprobe_event_legacy(probe_name, false, syscall_name, 0) < 0) + return 0; + + (void)remove_kprobe_event_legacy(probe_name, false); + return 1; + } } struct bpf_link * @@ -9735,7 +10094,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), func_name, offset); - legacy_probe = strdup(func_name); + legacy_probe = strdup(probe_name); if (!legacy_probe) return libbpf_err_ptr(-ENOMEM); @@ -9758,7 +10117,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, prog->name, retprobe ? "kretprobe" : "kprobe", func_name, offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - goto err_out; + goto err_clean_legacy; } if (legacy) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); @@ -9769,6 +10128,10 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, } return link; + +err_clean_legacy: + if (legacy) + remove_kprobe_event_legacy(legacy_probe, retprobe); err_out: free(legacy_probe); return libbpf_err_ptr(err); @@ -9785,14 +10148,180 @@ 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) +struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog, + const char *syscall_name, + const struct bpf_ksyscall_opts *opts) +{ + LIBBPF_OPTS(bpf_kprobe_opts, kprobe_opts); + char func_name[128]; + + if (!OPTS_VALID(opts, bpf_ksyscall_opts)) + return libbpf_err_ptr(-EINVAL); + + if (kernel_supports(prog->obj, FEAT_SYSCALL_WRAPPER)) { + /* arch_specific_syscall_pfx() should never return NULL here + * because it is guarded by kernel_supports(). However, since + * compiler does not know that we have an explicit conditional + * as well. + */ + snprintf(func_name, sizeof(func_name), "__%s_sys_%s", + arch_specific_syscall_pfx() ? : "", syscall_name); + } else { + snprintf(func_name, sizeof(func_name), "__se_sys_%s", syscall_name); + } + + kprobe_opts.retprobe = OPTS_GET(opts, retprobe, false); + kprobe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); + + return bpf_program__attach_kprobe_opts(prog, func_name, &kprobe_opts); +} + +/* 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; + + *link = NULL; + + /* no auto-attach for SEC("kprobe") and SEC("kretprobe") */ + if (strcmp(prog->sec_name, "kprobe") == 0 || strcmp(prog->sec_name, "kretprobe") == 0) + return 0; opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/"); if (opts.retprobe) @@ -9802,21 +10331,71 @@ 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_ksyscall(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + LIBBPF_OPTS(bpf_ksyscall_opts, opts); + const char *syscall_name; + + *link = NULL; + + /* no auto-attach for SEC("ksyscall") and SEC("kretsyscall") */ + if (strcmp(prog->sec_name, "ksyscall") == 0 || strcmp(prog->sec_name, "kretsyscall") == 0) + return 0; + + opts.retprobe = str_has_pfx(prog->sec_name, "kretsyscall/"); + if (opts.retprobe) + syscall_name = prog->sec_name + sizeof("kretsyscall/") - 1; + else + syscall_name = prog->sec_name + sizeof("ksyscall/") - 1; + + *link = bpf_program__attach_ksyscall(prog, syscall_name, &opts); + return *link ? 0 : -errno; +} + +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; + + *link = NULL; + + /* no auto-attach for SEC("kprobe.multi") and SEC("kretprobe.multi") */ + if (strcmp(prog->sec_name, "kprobe.multi") == 0 || + strcmp(prog->sec_name, "kretprobe.multi") == 0) + return 0; + + 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, @@ -9836,9 +10415,7 @@ static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, static inline int add_uprobe_event_legacy(const char *probe_name, bool retprobe, const char *binary_path, size_t offset) { - const char *file = "/sys/kernel/debug/tracing/uprobe_events"; - - return append_to_file(file, "%c:%s/%s %s:0x%zx", + return append_to_file(tracefs_uprobe_events(), "%c:%s/%s %s:0x%zx", retprobe ? 'r' : 'p', retprobe ? "uretprobes" : "uprobes", probe_name, binary_path, offset); @@ -9846,18 +10423,16 @@ static inline int add_uprobe_event_legacy(const char *probe_name, bool retprobe, static inline int remove_uprobe_event_legacy(const char *probe_name, bool retprobe) { - const char *file = "/sys/kernel/debug/tracing/uprobe_events"; - - return append_to_file(file, "-:%s/%s", retprobe ? "uretprobes" : "uprobes", probe_name); + return append_to_file(tracefs_uprobe_events(), "-:%s/%s", + retprobe ? "uretprobes" : "uprobes", probe_name); } static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retprobe) { char file[512]; - snprintf(file, sizeof(file), - "/sys/kernel/debug/tracing/events/%s/%s/id", - retprobe ? "uretprobes" : "uprobes", probe_name); + snprintf(file, sizeof(file), "%s/events/%s/%s/id", + tracefs_path(), retprobe ? "uretprobes" : "uprobes", probe_name); return parse_uint_from_file(file, "%d\n"); } @@ -9865,6 +10440,7 @@ static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retpro static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, const char *binary_path, size_t offset, int pid) { + const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_event_attr attr; int type, pfd, err; @@ -9876,13 +10452,14 @@ static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, } type = determine_uprobe_perf_type_legacy(probe_name, retprobe); if (type < 0) { + err = type; pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %d\n", binary_path, offset, err); - return type; + goto err_clean_legacy; } - memset(&attr, 0, sizeof(attr)); - attr.size = sizeof(attr); + memset(&attr, 0, attr_sz); + attr.size = attr_sz; attr.config = type; attr.type = PERF_TYPE_TRACEPOINT; @@ -9893,9 +10470,264 @@ static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, if (pfd < 0) { err = -errno; pr_warn("legacy uprobe perf_event_open() failed: %d\n", err); - return err; + goto err_clean_legacy; } return pfd; + +err_clean_legacy: + /* Clear the newly added legacy uprobe_event */ + remove_uprobe_event_legacy(probe_name, retprobe); + return err; +} + +/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */ +static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn) +{ + while ((scn = elf_nextscn(elf, scn)) != NULL) { + GElf_Shdr sh; + + if (!gelf_getshdr(scn, &sh)) + continue; + if (sh.sh_type == sh_type) + return scn; + } + return NULL; +} + +/* Find offset of function name in object specified by path. "name" matches + * symbol name or name@@LIB for library functions. + */ +static long elf_find_func_offset(const char *binary_path, const char *name) +{ + int fd, i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB }; + bool is_shared_lib, is_name_qualified; + char errmsg[STRERR_BUFSIZE]; + long ret = -ENOENT; + size_t name_len; + GElf_Ehdr ehdr; + Elf *elf; + + fd = open(binary_path, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + ret = -errno; + pr_warn("failed to open %s: %s\n", binary_path, + libbpf_strerror_r(ret, errmsg, sizeof(errmsg))); + return ret; + } + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) { + pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1)); + close(fd); + return -LIBBPF_ERRNO__FORMAT; + } + if (!gelf_getehdr(elf, &ehdr)) { + pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1)); + ret = -LIBBPF_ERRNO__FORMAT; + goto out; + } + /* for shared lib case, we do not need to calculate relative offset */ + is_shared_lib = ehdr.e_type == ET_DYN; + + name_len = strlen(name); + /* Does name specify "@@LIB"? */ + is_name_qualified = strstr(name, "@@") != NULL; + + /* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if + * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically + * linked binary may not have SHT_DYMSYM, so absence of a section should not be + * reported as a warning/error. + */ + for (i = 0; i < ARRAY_SIZE(sh_types); i++) { + size_t nr_syms, strtabidx, idx; + Elf_Data *symbols = NULL; + Elf_Scn *scn = NULL; + int last_bind = -1; + const char *sname; + GElf_Shdr sh; + + scn = elf_find_next_scn_by_type(elf, sh_types[i], NULL); + if (!scn) { + pr_debug("elf: failed to find symbol table ELF sections in '%s'\n", + binary_path); + continue; + } + if (!gelf_getshdr(scn, &sh)) + continue; + strtabidx = sh.sh_link; + symbols = elf_getdata(scn, 0); + if (!symbols) { + pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n", + binary_path, elf_errmsg(-1)); + ret = -LIBBPF_ERRNO__FORMAT; + goto out; + } + nr_syms = symbols->d_size / sh.sh_entsize; + + for (idx = 0; idx < nr_syms; idx++) { + int curr_bind; + GElf_Sym sym; + Elf_Scn *sym_scn; + GElf_Shdr sym_sh; + + if (!gelf_getsym(symbols, idx, &sym)) + continue; + + if (GELF_ST_TYPE(sym.st_info) != STT_FUNC) + continue; + + sname = elf_strptr(elf, strtabidx, sym.st_name); + if (!sname) + continue; + + curr_bind = GELF_ST_BIND(sym.st_info); + + /* User can specify func, func@@LIB or func@@LIB_VERSION. */ + if (strncmp(sname, name, name_len) != 0) + continue; + /* ...but we don't want a search for "foo" to match 'foo2" also, so any + * additional characters in sname should be of the form "@@LIB". + */ + if (!is_name_qualified && sname[name_len] != '\0' && sname[name_len] != '@') + continue; + + if (ret >= 0) { + /* handle multiple matches */ + if (last_bind != STB_WEAK && curr_bind != STB_WEAK) { + /* Only accept one non-weak bind. */ + pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n", + sname, name, binary_path); + ret = -LIBBPF_ERRNO__FORMAT; + goto out; + } else if (curr_bind == STB_WEAK) { + /* already have a non-weak bind, and + * this is a weak bind, so ignore. + */ + continue; + } + } + + /* Transform symbol's virtual address (absolute for + * binaries and relative for shared libs) into file + * offset, which is what kernel is expecting for + * uprobe/uretprobe attachment. + * See Documentation/trace/uprobetracer.rst for more + * details. + * This is done by looking up symbol's containing + * section's header and using it's virtual address + * (sh_addr) and corresponding file offset (sh_offset) + * to transform sym.st_value (virtual address) into + * desired final file offset. + */ + sym_scn = elf_getscn(elf, sym.st_shndx); + if (!sym_scn) + continue; + if (!gelf_getshdr(sym_scn, &sym_sh)) + continue; + + ret = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset; + last_bind = curr_bind; + } + if (ret > 0) + break; + } + + if (ret > 0) { + pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path, + ret); + } else { + if (ret == 0) { + pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path, + is_shared_lib ? "should not be 0 in a shared library" : + "try using shared library path instead"); + ret = -ENOENT; + } else { + pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path); + } + } +out: + elf_end(elf); + close(fd); + return ret; +} + +static const char *arch_specific_lib_paths(void) +{ + /* + * Based on https://packages.debian.org/sid/libc6. + * + * Assume that the traced program is built for the same architecture + * as libbpf, which should cover the vast majority of cases. + */ +#if defined(__x86_64__) + return "/lib/x86_64-linux-gnu"; +#elif defined(__i386__) + return "/lib/i386-linux-gnu"; +#elif defined(__s390x__) + return "/lib/s390x-linux-gnu"; +#elif defined(__s390__) + return "/lib/s390-linux-gnu"; +#elif defined(__arm__) && defined(__SOFTFP__) + return "/lib/arm-linux-gnueabi"; +#elif defined(__arm__) && !defined(__SOFTFP__) + return "/lib/arm-linux-gnueabihf"; +#elif defined(__aarch64__) + return "/lib/aarch64-linux-gnu"; +#elif defined(__mips__) && defined(__MIPSEL__) && _MIPS_SZLONG == 64 + return "/lib/mips64el-linux-gnuabi64"; +#elif defined(__mips__) && defined(__MIPSEL__) && _MIPS_SZLONG == 32 + return "/lib/mipsel-linux-gnu"; +#elif defined(__powerpc64__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + return "/lib/powerpc64le-linux-gnu"; +#elif defined(__sparc__) && defined(__arch64__) + return "/lib/sparc64-linux-gnu"; +#elif defined(__riscv) && __riscv_xlen == 64 + return "/lib/riscv64-linux-gnu"; +#else + return NULL; +#endif +} + +/* Get full path to program/shared library. */ +static int resolve_full_path(const char *file, char *result, size_t result_sz) +{ + const char *search_paths[3] = {}; + int i, perm; + + if (str_has_sfx(file, ".so") || strstr(file, ".so.")) { + search_paths[0] = getenv("LD_LIBRARY_PATH"); + search_paths[1] = "/usr/lib64:/usr/lib"; + search_paths[2] = arch_specific_lib_paths(); + perm = R_OK; + } else { + search_paths[0] = getenv("PATH"); + search_paths[1] = "/usr/bin:/usr/sbin"; + perm = R_OK | X_OK; + } + + for (i = 0; i < ARRAY_SIZE(search_paths); i++) { + const char *s; + + if (!search_paths[i]) + continue; + for (s = search_paths[i]; s != NULL; s = strchr(s, ':')) { + char *next_path; + int seg_len; + + if (s[0] == ':') + s++; + next_path = strchr(s, ':'); + seg_len = next_path ? next_path - s : strlen(s); + if (!seg_len) + continue; + snprintf(result, result_sz, "%.*s/%s", seg_len, s, file); + /* ensure it has required permissions */ + if (faccessat(AT_FDCWD, result, perm, AT_EACCESS) < 0) + continue; + pr_debug("resolved '%s' to '%s'\n", file, result); + return 0; + } + } + return -ENOENT; } LIBBPF_API struct bpf_link * @@ -9905,10 +10737,12 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); char errmsg[STRERR_BUFSIZE], *legacy_probe = NULL; + char full_binary_path[PATH_MAX]; struct bpf_link *link; size_t ref_ctr_off; int pfd, err; bool retprobe, legacy; + const char *func_name; if (!OPTS_VALID(opts, bpf_uprobe_opts)) return libbpf_err_ptr(-EINVAL); @@ -9917,12 +10751,35 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0); pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); + if (!binary_path) + return libbpf_err_ptr(-EINVAL); + + if (!strchr(binary_path, '/')) { + err = resolve_full_path(binary_path, full_binary_path, + sizeof(full_binary_path)); + if (err) { + pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", + prog->name, binary_path, err); + return libbpf_err_ptr(err); + } + binary_path = full_binary_path; + } + func_name = OPTS_GET(opts, func_name, NULL); + if (func_name) { + long sym_off; + + sym_off = elf_find_func_offset(binary_path, func_name); + if (sym_off < 0) + return libbpf_err_ptr(sym_off); + func_offset += sym_off; + } + legacy = determine_uprobe_perf_type() < 0; if (!legacy) { pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, func_offset, pid, ref_ctr_off); } else { - char probe_name[512]; + char probe_name[PATH_MAX + 64]; if (ref_ctr_off) return libbpf_err_ptr(-EINVAL); @@ -9954,7 +10811,7 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - goto err_out; + goto err_clean_legacy; } if (legacy) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); @@ -9964,10 +10821,68 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, perf_link->legacy_is_retprobe = retprobe; } return link; + +err_clean_legacy: + if (legacy) + remove_uprobe_event_legacy(legacy_probe, retprobe); err_out: free(legacy_probe); return libbpf_err_ptr(err); +} + +/* Format of u[ret]probe section definition supporting auto-attach: + * u[ret]probe/binary:function[+offset] + * + * binary can be an absolute/relative path or a filename; the latter is resolved to a + * full binary path via bpf_program__attach_uprobe_opts. + * + * Specifying uprobe+ ensures we carry out strict matching; either "uprobe" must be + * specified (and auto-attach is not possible) or the above format is specified for + * auto-attach. + */ +static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts); + char *probe_type = NULL, *binary_path = NULL, *func_name = NULL; + int n, ret = -EINVAL; + long offset = 0; + *link = NULL; + + n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[a-zA-Z0-9_.]+%li", + &probe_type, &binary_path, &func_name, &offset); + switch (n) { + case 1: + /* handle SEC("u[ret]probe") - format is valid, but auto-attach is impossible. */ + ret = 0; + break; + case 2: + pr_warn("prog '%s': section '%s' missing ':function[+offset]' specification\n", + prog->name, prog->sec_name); + break; + case 3: + case 4: + opts.retprobe = strcmp(probe_type, "uretprobe") == 0 || + strcmp(probe_type, "uretprobe.s") == 0; + if (opts.retprobe && offset != 0) { + pr_warn("prog '%s': uretprobes do not support offset specification\n", + prog->name); + break; + } + opts.func_name = func_name; + *link = bpf_program__attach_uprobe_opts(prog, -1, binary_path, offset, &opts); + ret = libbpf_get_error(*link); + break; + default: + pr_warn("prog '%s': invalid format of section definition '%s'\n", prog->name, + prog->sec_name); + break; + } + free(probe_type); + free(binary_path); + free(func_name); + + return ret; } struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog, @@ -9980,15 +10895,96 @@ struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog, return bpf_program__attach_uprobe_opts(prog, pid, binary_path, func_offset, &opts); } +struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog, + pid_t pid, const char *binary_path, + const char *usdt_provider, const char *usdt_name, + const struct bpf_usdt_opts *opts) +{ + char resolved_path[512]; + struct bpf_object *obj = prog->obj; + struct bpf_link *link; + __u64 usdt_cookie; + int err; + + if (!OPTS_VALID(opts, bpf_uprobe_opts)) + return libbpf_err_ptr(-EINVAL); + + if (bpf_program__fd(prog) < 0) { + pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + if (!binary_path) + return libbpf_err_ptr(-EINVAL); + + if (!strchr(binary_path, '/')) { + err = resolve_full_path(binary_path, resolved_path, sizeof(resolved_path)); + if (err) { + pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", + prog->name, binary_path, err); + return libbpf_err_ptr(err); + } + binary_path = resolved_path; + } + + /* USDT manager is instantiated lazily on first USDT attach. It will + * be destroyed together with BPF object in bpf_object__close(). + */ + if (IS_ERR(obj->usdt_man)) + return libbpf_ptr(obj->usdt_man); + if (!obj->usdt_man) { + obj->usdt_man = usdt_manager_new(obj); + if (IS_ERR(obj->usdt_man)) + return libbpf_ptr(obj->usdt_man); + } + + usdt_cookie = OPTS_GET(opts, usdt_cookie, 0); + link = usdt_manager_attach_usdt(obj->usdt_man, prog, pid, binary_path, + usdt_provider, usdt_name, usdt_cookie); + err = libbpf_get_error(link); + if (err) + return libbpf_err_ptr(err); + return link; +} + +static int attach_usdt(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + char *path = NULL, *provider = NULL, *name = NULL; + const char *sec_name; + int n, err; + + sec_name = bpf_program__section_name(prog); + if (strcmp(sec_name, "usdt") == 0) { + /* no auto-attach for just SEC("usdt") */ + *link = NULL; + return 0; + } + + n = sscanf(sec_name, "usdt/%m[^:]:%m[^:]:%m[^:]", &path, &provider, &name); + if (n != 3) { + pr_warn("invalid section '%s', expected SEC(\"usdt/<path>:<provider>:<name>\")\n", + sec_name); + err = -EINVAL; + } else { + *link = bpf_program__attach_usdt(prog, -1 /* any process */, path, + provider, name, NULL); + err = libbpf_get_error(*link); + } + free(path); + free(provider); + free(name); + return err; +} + static int determine_tracepoint_id(const char *tp_category, const char *tp_name) { char file[PATH_MAX]; int ret; - ret = snprintf(file, sizeof(file), - "/sys/kernel/debug/tracing/events/%s/%s/id", - tp_category, tp_name); + ret = snprintf(file, sizeof(file), "%s/events/%s/%s/id", + tracefs_path(), tp_category, tp_name); if (ret < 0) return -errno; if (ret >= sizeof(file)) { @@ -10002,7 +10998,8 @@ static int determine_tracepoint_id(const char *tp_category, static int perf_event_open_tracepoint(const char *tp_category, const char *tp_name) { - struct perf_event_attr attr = {}; + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; char errmsg[STRERR_BUFSIZE]; int tp_id, pfd, err; @@ -10014,8 +11011,9 @@ static int perf_event_open_tracepoint(const char *tp_category, return tp_id; } + memset(&attr, 0, attr_sz); attr.type = PERF_TYPE_TRACEPOINT; - attr.size = sizeof(attr); + attr.size = attr_sz; attr.config = tp_id; pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu */, @@ -10071,14 +11069,19 @@ 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; + + *link = NULL; + + /* no auto-attach for SEC("tp") or SEC("tracepoint") */ + if (strcmp(prog->sec_name, "tp") == 0 || strcmp(prog->sec_name, "tracepoint") == 0) + return 0; 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/")) @@ -10088,14 +11091,14 @@ 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, @@ -10128,39 +11131,59 @@ 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/", - "raw_tracepoint/", - "raw_tp.w/", - "raw_tracepoint.w/", + "raw_tp", + "raw_tracepoint", + "raw_tp.w", + "raw_tracepoint.w", }; size_t i; const char *tp_name = NULL; + *link = NULL; + for (i = 0; i < ARRAY_SIZE(prefixes); i++) { - if (str_has_pfx(prog->sec_name, prefixes[i])) { - tp_name = prog->sec_name + strlen(prefixes[i]); - break; - } + size_t pfx_len; + + if (!str_has_pfx(prog->sec_name, prefixes[i])) + continue; + + pfx_len = strlen(prefixes[i]); + /* no auto-attach case of, e.g., SEC("raw_tp") */ + if (prog->sec_name[pfx_len] == '\0') + return 0; + + if (prog->sec_name[pfx_len] != '/') + continue; + + tp_name = prog->sec_name + pfx_len + 1; + break; } + 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 */ -static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *prog) +static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *prog, + const struct bpf_trace_opts *opts) { + LIBBPF_OPTS(bpf_link_create_opts, link_opts); char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int prog_fd, pfd; + if (!OPTS_VALID(opts, bpf_trace_opts)) + return libbpf_err_ptr(-EINVAL); + prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { pr_warn("prog '%s': can't attach before loaded\n", prog->name); @@ -10172,7 +11195,9 @@ static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *pro return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_fd; - pfd = bpf_raw_tracepoint_open(NULL, prog_fd); + /* libbpf is smart enough to redirect to BPF_RAW_TRACEPOINT_OPEN on old kernels */ + link_opts.tracing.cookie = OPTS_GET(opts, cookie, 0); + pfd = bpf_link_create(prog_fd, 0, bpf_program__expected_attach_type(prog), &link_opts); if (pfd < 0) { pfd = -errno; free(link); @@ -10181,27 +11206,35 @@ static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *pro return libbpf_err_ptr(pfd); } link->fd = pfd; - return (struct bpf_link *)link; + return link; } struct bpf_link *bpf_program__attach_trace(const struct bpf_program *prog) { - return bpf_program__attach_btf_id(prog); + return bpf_program__attach_btf_id(prog, NULL); +} + +struct bpf_link *bpf_program__attach_trace_opts(const struct bpf_program *prog, + const struct bpf_trace_opts *opts) +{ + return bpf_program__attach_btf_id(prog, opts); } struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog) { - return bpf_program__attach_btf_id(prog); + return bpf_program__attach_btf_id(prog, NULL); } -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 * @@ -10226,7 +11259,7 @@ 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; @@ -10330,17 +11363,33 @@ 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); - return prog->sec_def->attach_fn(prog, prog->sec_def->cookie); + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, &link); + if (err) + return libbpf_err_ptr(err); + + /* 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) @@ -10394,10 +11443,13 @@ struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) return link; } -enum bpf_perf_event_ret -bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, - void **copy_mem, size_t *copy_size, - bpf_perf_event_print_t fn, void *private_data) +typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, + void *private_data); + +static enum bpf_perf_event_ret +perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, + void **copy_mem, size_t *copy_size, + bpf_perf_event_print_t fn, void *private_data) { struct perf_event_mmap_page *header = mmap_mem; __u64 data_head = ring_buffer_read_head(header); @@ -10576,11 +11628,20 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, struct perf_buffer_params *p); struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, + perf_buffer_sample_fn sample_cb, + perf_buffer_lost_fn lost_cb, + void *ctx, const struct perf_buffer_opts *opts) { + const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_buffer_params p = {}; - struct perf_event_attr attr = { 0, }; + struct perf_event_attr attr; + + if (!OPTS_VALID(opts, perf_buffer_opts)) + return libbpf_err_ptr(-EINVAL); + memset(&attr, 0, attr_sz); + attr.size = attr_sz; attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; attr.sample_type = PERF_SAMPLE_RAW; @@ -10588,25 +11649,32 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, attr.wakeup_events = 1; p.attr = &attr; - p.sample_cb = opts ? opts->sample_cb : NULL; - p.lost_cb = opts ? opts->lost_cb : NULL; - p.ctx = opts ? opts->ctx : NULL; + p.sample_cb = sample_cb; + p.lost_cb = lost_cb; + p.ctx = ctx; return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p)); } -struct perf_buffer * -perf_buffer__new_raw(int map_fd, size_t page_cnt, - const struct perf_buffer_raw_opts *opts) +struct perf_buffer *perf_buffer__new_raw(int map_fd, size_t page_cnt, + struct perf_event_attr *attr, + perf_buffer_event_fn event_cb, void *ctx, + const struct perf_buffer_raw_opts *opts) { struct perf_buffer_params p = {}; - p.attr = opts->attr; - p.event_cb = opts->event_cb; - p.ctx = opts->ctx; - p.cpu_cnt = opts->cpu_cnt; - p.cpus = opts->cpus; - p.map_keys = opts->map_keys; + if (!attr) + return libbpf_err_ptr(-EINVAL); + + if (!OPTS_VALID(opts, perf_buffer_raw_opts)) + return libbpf_err_ptr(-EINVAL); + + p.attr = attr; + p.event_cb = event_cb; + p.ctx = ctx; + p.cpu_cnt = OPTS_GET(opts, cpu_cnt, 0); + p.cpus = OPTS_GET(opts, cpus, NULL); + p.map_keys = OPTS_GET(opts, map_keys, NULL); return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p)); } @@ -10622,7 +11690,7 @@ 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); @@ -10810,10 +11878,10 @@ static int perf_buffer__process_records(struct perf_buffer *pb, { enum bpf_perf_event_ret ret; - ret = bpf_perf_event_read_simple(cpu_buf->base, pb->mmap_size, - pb->page_size, &cpu_buf->buf, - &cpu_buf->buf_size, - perf_buffer__process_record, cpu_buf); + ret = perf_event_read_simple(cpu_buf->base, pb->mmap_size, + pb->page_size, &cpu_buf->buf, + &cpu_buf->buf_size, + perf_buffer__process_record, cpu_buf); if (ret != LIBBPF_PERF_EVENT_CONT) return ret; return 0; @@ -10871,6 +11939,22 @@ int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx) return cpu_buf->fd; } +int perf_buffer__buffer(struct perf_buffer *pb, int buf_idx, void **buf, size_t *buf_size) +{ + struct perf_cpu_buf *cpu_buf; + + if (buf_idx >= pb->cpu_cnt) + return libbpf_err(-EINVAL); + + cpu_buf = pb->cpu_bufs[buf_idx]; + if (!cpu_buf) + return libbpf_err(-ENOENT); + + *buf = cpu_buf->base; + *buf_size = pb->mmap_size; + return 0; +} + /* * Consume data from perf ring buffer corresponding to slot *buf_idx* in * PERF_EVENT_ARRAY BPF map without waiting/polling. If there is no data to @@ -10912,254 +11996,6 @@ int perf_buffer__consume(struct perf_buffer *pb) return 0; } -struct bpf_prog_info_array_desc { - int array_offset; /* e.g. offset of jited_prog_insns */ - int count_offset; /* e.g. offset of jited_prog_len */ - int size_offset; /* > 0: offset of rec size, - * < 0: fix size of -size_offset - */ -}; - -static struct bpf_prog_info_array_desc bpf_prog_info_array_desc[] = { - [BPF_PROG_INFO_JITED_INSNS] = { - offsetof(struct bpf_prog_info, jited_prog_insns), - offsetof(struct bpf_prog_info, jited_prog_len), - -1, - }, - [BPF_PROG_INFO_XLATED_INSNS] = { - offsetof(struct bpf_prog_info, xlated_prog_insns), - offsetof(struct bpf_prog_info, xlated_prog_len), - -1, - }, - [BPF_PROG_INFO_MAP_IDS] = { - offsetof(struct bpf_prog_info, map_ids), - offsetof(struct bpf_prog_info, nr_map_ids), - -(int)sizeof(__u32), - }, - [BPF_PROG_INFO_JITED_KSYMS] = { - offsetof(struct bpf_prog_info, jited_ksyms), - offsetof(struct bpf_prog_info, nr_jited_ksyms), - -(int)sizeof(__u64), - }, - [BPF_PROG_INFO_JITED_FUNC_LENS] = { - offsetof(struct bpf_prog_info, jited_func_lens), - offsetof(struct bpf_prog_info, nr_jited_func_lens), - -(int)sizeof(__u32), - }, - [BPF_PROG_INFO_FUNC_INFO] = { - offsetof(struct bpf_prog_info, func_info), - offsetof(struct bpf_prog_info, nr_func_info), - offsetof(struct bpf_prog_info, func_info_rec_size), - }, - [BPF_PROG_INFO_LINE_INFO] = { - offsetof(struct bpf_prog_info, line_info), - offsetof(struct bpf_prog_info, nr_line_info), - offsetof(struct bpf_prog_info, line_info_rec_size), - }, - [BPF_PROG_INFO_JITED_LINE_INFO] = { - offsetof(struct bpf_prog_info, jited_line_info), - offsetof(struct bpf_prog_info, nr_jited_line_info), - offsetof(struct bpf_prog_info, jited_line_info_rec_size), - }, - [BPF_PROG_INFO_PROG_TAGS] = { - offsetof(struct bpf_prog_info, prog_tags), - offsetof(struct bpf_prog_info, nr_prog_tags), - -(int)sizeof(__u8) * BPF_TAG_SIZE, - }, - -}; - -static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, - int offset) -{ - __u32 *array = (__u32 *)info; - - if (offset >= 0) - return array[offset / sizeof(__u32)]; - return -(int)offset; -} - -static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, - int offset) -{ - __u64 *array = (__u64 *)info; - - if (offset >= 0) - return array[offset / sizeof(__u64)]; - return -(int)offset; -} - -static void bpf_prog_info_set_offset_u32(struct bpf_prog_info *info, int offset, - __u32 val) -{ - __u32 *array = (__u32 *)info; - - if (offset >= 0) - array[offset / sizeof(__u32)] = val; -} - -static void bpf_prog_info_set_offset_u64(struct bpf_prog_info *info, int offset, - __u64 val) -{ - __u64 *array = (__u64 *)info; - - if (offset >= 0) - array[offset / sizeof(__u64)] = val; -} - -struct bpf_prog_info_linear * -bpf_program__get_prog_info_linear(int fd, __u64 arrays) -{ - struct bpf_prog_info_linear *info_linear; - struct bpf_prog_info info = {}; - __u32 info_len = sizeof(info); - __u32 data_len = 0; - int i, err; - void *ptr; - - if (arrays >> BPF_PROG_INFO_LAST_ARRAY) - return libbpf_err_ptr(-EINVAL); - - /* step 1: get array dimensions */ - err = bpf_obj_get_info_by_fd(fd, &info, &info_len); - if (err) { - pr_debug("can't get prog info: %s", strerror(errno)); - return libbpf_err_ptr(-EFAULT); - } - - /* step 2: calculate total size of all arrays */ - for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) { - bool include_array = (arrays & (1UL << i)) > 0; - struct bpf_prog_info_array_desc *desc; - __u32 count, size; - - desc = bpf_prog_info_array_desc + i; - - /* kernel is too old to support this field */ - if (info_len < desc->array_offset + sizeof(__u32) || - info_len < desc->count_offset + sizeof(__u32) || - (desc->size_offset > 0 && info_len < desc->size_offset)) - include_array = false; - - if (!include_array) { - arrays &= ~(1UL << i); /* clear the bit */ - continue; - } - - count = bpf_prog_info_read_offset_u32(&info, desc->count_offset); - size = bpf_prog_info_read_offset_u32(&info, desc->size_offset); - - data_len += count * size; - } - - /* step 3: allocate continuous memory */ - data_len = roundup(data_len, sizeof(__u64)); - info_linear = malloc(sizeof(struct bpf_prog_info_linear) + data_len); - if (!info_linear) - return libbpf_err_ptr(-ENOMEM); - - /* step 4: fill data to info_linear->info */ - info_linear->arrays = arrays; - memset(&info_linear->info, 0, sizeof(info)); - ptr = info_linear->data; - - for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) { - struct bpf_prog_info_array_desc *desc; - __u32 count, size; - - if ((arrays & (1UL << i)) == 0) - continue; - - desc = bpf_prog_info_array_desc + i; - count = bpf_prog_info_read_offset_u32(&info, desc->count_offset); - size = bpf_prog_info_read_offset_u32(&info, desc->size_offset); - bpf_prog_info_set_offset_u32(&info_linear->info, - desc->count_offset, count); - bpf_prog_info_set_offset_u32(&info_linear->info, - desc->size_offset, size); - bpf_prog_info_set_offset_u64(&info_linear->info, - desc->array_offset, - ptr_to_u64(ptr)); - ptr += count * size; - } - - /* step 5: call syscall again to get required arrays */ - err = bpf_obj_get_info_by_fd(fd, &info_linear->info, &info_len); - if (err) { - pr_debug("can't get prog info: %s", strerror(errno)); - free(info_linear); - return libbpf_err_ptr(-EFAULT); - } - - /* step 6: verify the data */ - for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) { - struct bpf_prog_info_array_desc *desc; - __u32 v1, v2; - - if ((arrays & (1UL << i)) == 0) - continue; - - desc = bpf_prog_info_array_desc + i; - v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset); - v2 = bpf_prog_info_read_offset_u32(&info_linear->info, - desc->count_offset); - if (v1 != v2) - pr_warn("%s: mismatch in element count\n", __func__); - - v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset); - v2 = bpf_prog_info_read_offset_u32(&info_linear->info, - desc->size_offset); - if (v1 != v2) - pr_warn("%s: mismatch in rec size\n", __func__); - } - - /* step 7: update info_len and data_len */ - info_linear->info_len = sizeof(struct bpf_prog_info); - info_linear->data_len = data_len; - - return info_linear; -} - -void bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear) -{ - int i; - - for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) { - struct bpf_prog_info_array_desc *desc; - __u64 addr, offs; - - if ((info_linear->arrays & (1UL << i)) == 0) - continue; - - desc = bpf_prog_info_array_desc + i; - addr = bpf_prog_info_read_offset_u64(&info_linear->info, - desc->array_offset); - offs = addr - ptr_to_u64(info_linear->data); - bpf_prog_info_set_offset_u64(&info_linear->info, - desc->array_offset, offs); - } -} - -void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) -{ - int i; - - for (i = BPF_PROG_INFO_FIRST_ARRAY; i < BPF_PROG_INFO_LAST_ARRAY; ++i) { - struct bpf_prog_info_array_desc *desc; - __u64 addr, offs; - - if ((info_linear->arrays & (1UL << i)) == 0) - continue; - - desc = bpf_prog_info_array_desc + i; - offs = bpf_prog_info_read_offset_u64(&info_linear->info, - desc->array_offset); - addr = offs + ptr_to_u64(info_linear->data); - bpf_prog_info_set_offset_u64(&info_linear->info, - desc->array_offset, addr); - } -} - int bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, const char *attach_func_name) @@ -11309,6 +12145,49 @@ 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) { @@ -11316,7 +12195,7 @@ 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, @@ -11339,37 +12218,91 @@ 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; @@ -11431,20 +12364,34 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) struct bpf_program *prog = *s->progs[i].prog; struct bpf_link **link = s->progs[i].link; - if (!prog->load) + if (!prog->autoload || !prog->autoattach) 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; @@ -11464,6 +12411,9 @@ 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 9de0f299706b..eee883f007f9 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -24,6 +24,10 @@ extern "C" { #endif +LIBBPF_API __u32 libbpf_major_version(void); +LIBBPF_API __u32 libbpf_minor_version(void); +LIBBPF_API const char *libbpf_version_string(void); + enum libbpf_errno { __LIBBPF_ERRNO__START = 4000, @@ -47,6 +51,42 @@ enum libbpf_errno { LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size); +/** + * @brief **libbpf_bpf_attach_type_str()** converts the provided attach type + * value into a textual representation. + * @param t The attach type. + * @return Pointer to a static string identifying the attach type. NULL is + * returned for unknown **bpf_attach_type** values. + */ +LIBBPF_API const char *libbpf_bpf_attach_type_str(enum bpf_attach_type t); + +/** + * @brief **libbpf_bpf_link_type_str()** converts the provided link type value + * into a textual representation. + * @param t The link type. + * @return Pointer to a static string identifying the link type. NULL is + * returned for unknown **bpf_link_type** values. + */ +LIBBPF_API const char *libbpf_bpf_link_type_str(enum bpf_link_type t); + +/** + * @brief **libbpf_bpf_map_type_str()** converts the provided map type value + * into a textual representation. + * @param t The map type. + * @return Pointer to a static string identifying the map type. NULL is + * returned for unknown **bpf_map_type** values. + */ +LIBBPF_API const char *libbpf_bpf_map_type_str(enum bpf_map_type t); + +/** + * @brief **libbpf_bpf_prog_type_str()** converts the provided program type + * value into a textual representation. + * @param t The program type. + * @return Pointer to a static string identifying the program type. NULL is + * returned for unknown **bpf_prog_type** values. + */ +LIBBPF_API const char *libbpf_bpf_prog_type_str(enum bpf_prog_type t); + enum libbpf_print_level { LIBBPF_WARN, LIBBPF_INFO, @@ -61,13 +101,8 @@ LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); /* Hide internal to user */ struct bpf_object; -struct bpf_object_open_attr { - const char *file; - enum bpf_prog_type prog_type; -}; - struct bpf_object_open_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; /* object name override, if provided: * - for object open from file, this will override setting object @@ -78,21 +113,14 @@ struct bpf_object_open_opts { const char *object_name; /* parse map definitions non-strictly, allowing extra attributes/data */ bool relaxed_maps; - /* DEPRECATED: handle CO-RE relocations non-strictly, allowing failures. - * Value is ignored. Relocations always are processed non-strictly. - * Non-relocatable instructions are replaced with invalid ones to - * prevent accidental errors. - * */ - LIBBPF_DEPRECATED_SINCE(0, 6, "field has no effect") - bool relaxed_core_relocs; /* maps that set the 'pinning' attribute in their definition will have * their pin_path attribute set to a file in this directory, and be * auto-pinned to that path on load; defaults to "/sys/fs/bpf". */ const char *pin_root_path; - LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__set_attach_target() on each individual bpf_program") - __u32 attach_prog_fd; + __u32 :32; /* stub out now removed attach_prog_fd */ + /* Additional kernel config content that augments and overrides * system Kconfig for CONFIG_xxx externs. */ @@ -104,28 +132,81 @@ struct bpf_object_open_opts { * struct_ops, etc) will need actual kernel BTF at /sys/kernel/btf/vmlinux. */ const char *btf_custom_path; + /* Pointer to a buffer for storing kernel logs for applicable BPF + * commands. Valid kernel_log_size has to be specified as well and are + * passed-through to bpf() syscall. Keep in mind that kernel might + * fail operation with -ENOSPC error if provided buffer is too small + * to contain entire log output. + * See the comment below for kernel_log_level for interaction between + * log_buf and log_level settings. + * + * If specified, this log buffer will be passed for: + * - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden + * with bpf_program__set_log() on per-program level, to get + * BPF verifier log output. + * - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get + * BTF sanity checking log. + * + * Each BPF command (BPF_BTF_LOAD or BPF_PROG_LOAD) will overwrite + * previous contents, so if you need more fine-grained control, set + * per-program buffer with bpf_program__set_log_buf() to preserve each + * individual program's verification log. Keep using kernel_log_buf + * for BTF verification log, if necessary. + */ + char *kernel_log_buf; + size_t kernel_log_size; + /* + * Log level can be set independently from log buffer. Log_level=0 + * means that libbpf will attempt loading BTF or program without any + * logging requested, but will retry with either its own or custom log + * buffer, if provided, and log_level=1 on any error. + * And vice versa, setting log_level>0 will request BTF or prog + * loading with verbose log from the first attempt (and as such also + * for successfully loaded BTF or program), and the actual log buffer + * could be either libbpf's own auto-allocated log buffer, if + * kernel_log_buffer is NULL, or user-provided custom kernel_log_buf. + * If user didn't provide custom log buffer, libbpf will emit captured + * logs through its print callback. + */ + __u32 kernel_log_level; + + size_t :0; }; -#define bpf_object_open_opts__last_field btf_custom_path +#define bpf_object_open_opts__last_field kernel_log_level LIBBPF_API struct bpf_object *bpf_object__open(const char *path); + +/** + * @brief **bpf_object__open_file()** creates a bpf_object by opening + * the BPF ELF object file pointed to by the passed path and loading it + * into memory. + * @param path BPF object file path + * @param opts options for how to load the bpf object, this parameter is + * optional and can be set to NULL + * @return pointer to the new bpf_object; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_object * bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts); + +/** + * @brief **bpf_object__open_mem()** creates a bpf_object by reading + * the BPF objects raw bytes from a memory buffer containing a valid + * BPF ELF object file. + * @param obj_buf pointer to the buffer containing ELF file bytes + * @param obj_buf_sz number of bytes in the buffer + * @param opts options for how to load the bpf object + * @return pointer to the new bpf_object; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_object * 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_API struct bpf_object * -bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, - const char *name); -LIBBPF_API struct bpf_object * -bpf_object__open_xattr(struct bpf_object_open_attr *attr); +/* Load/unload object into/from kernel */ +LIBBPF_API int bpf_object__load(struct bpf_object *obj); -enum libbpf_pin_type { - LIBBPF_PIN_NONE, - /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ - LIBBPF_PIN_BY_NAME, -}; +LIBBPF_API void bpf_object__close(struct bpf_object *object); /* pin_maps and unpin_maps can both be called with a NULL path, in which case * they will use the pin_path attribute of each map (and ignore all maps that @@ -139,19 +220,6 @@ LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj, LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj, const char *path); LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path); -LIBBPF_API void bpf_object__close(struct bpf_object *object); - -struct bpf_object_load_attr { - struct bpf_object *obj; - int log_level; - const char *target_btf_path; -}; - -/* Load/unload object into/from kernel */ -LIBBPF_API int bpf_object__load(struct bpf_object *obj); -LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); -LIBBPF_DEPRECATED_SINCE(0, 6, "bpf_object__unload() is deprecated, use bpf_object__close() instead") -LIBBPF_API int bpf_object__unload(struct bpf_object *obj); LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); @@ -162,25 +230,9 @@ LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); LIBBPF_API struct bpf_program * -bpf_object__find_program_by_title(const struct bpf_object *obj, - const char *title); -LIBBPF_API struct bpf_program * bpf_object__find_program_by_name(const struct bpf_object *obj, const char *name); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "track bpf_objects in application code instead") -struct bpf_object *bpf_object__next(struct bpf_object *prev); -#define bpf_object__for_each_safe(pos, tmp) \ - for ((pos) = bpf_object__next(NULL), \ - (tmp) = bpf_object__next(pos); \ - (pos) != NULL; \ - (pos) = (tmp), (tmp) = bpf_object__next(tmp)) - -typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *); -LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv, - bpf_object_clear_priv_t clear_priv); -LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog); - LIBBPF_API int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, enum bpf_attach_type *expected_attach_type); @@ -191,9 +243,7 @@ LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name, /* Accessors of bpf_program */ struct bpf_program; -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_program() instead") -struct bpf_program *bpf_program__next(struct bpf_program *prog, - const struct bpf_object *obj); + LIBBPF_API struct bpf_program * bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prog); @@ -202,31 +252,18 @@ bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prog) (pos) != NULL; \ (pos) = bpf_object__next_program((obj), (pos))) -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_program() instead") -struct bpf_program *bpf_program__prev(struct bpf_program *prog, - const struct bpf_object *obj); LIBBPF_API struct bpf_program * 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_API int bpf_program__set_priv(struct bpf_program *prog, void *priv, - bpf_program_clear_priv_t clear_priv); - -LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog); LIBBPF_API const char *bpf_program__section_name(const struct bpf_program *prog); -LIBBPF_API LIBBPF_DEPRECATED("BPF program title is confusing term; please use bpf_program__section_name() instead") -const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy); LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog); LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload); - -/* returns program size in bytes */ -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insn_cnt() instead") -LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__autoattach(const struct bpf_program *prog); +LIBBPF_API void bpf_program__set_autoattach(struct bpf_program *prog, bool autoattach); struct bpf_insn; @@ -251,6 +288,24 @@ struct bpf_insn; * different. */ LIBBPF_API const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog); + +/** + * @brief **bpf_program__set_insns()** can set BPF program's underlying + * BPF instructions. + * + * WARNING: This is a very advanced libbpf API and users need to know + * what they are doing. This should be used from prog_prepare_load_fn + * callback only. + * + * @param prog BPF program for which to return instructions + * @param new_insns a pointer to an array of BPF instructions + * @param new_insn_cnt number of `struct bpf_insn`'s that form + * specified BPF program + * @return 0, on success; negative error code, otherwise + */ +LIBBPF_API int bpf_program__set_insns(struct bpf_program *prog, + struct bpf_insn *new_insns, size_t new_insn_cnt); + /** * @brief **bpf_program__insn_cnt()** returns number of `struct bpf_insn`'s * that form specified BPF program. @@ -262,18 +317,32 @@ LIBBPF_API const struct bpf_insn *bpf_program__insns(const struct bpf_program *p */ LIBBPF_API size_t bpf_program__insn_cnt(const struct bpf_program *prog); -LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license, - __u32 kern_version); LIBBPF_API int bpf_program__fd(const struct bpf_program *prog); -LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated") -LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog, - const char *path, - int instance); -LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated") -LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog, - const char *path, - int instance); + +/** + * @brief **bpf_program__pin()** pins the BPF program to a file + * in the BPF FS specified by a path. This increments the programs + * reference count, allowing it to stay loaded after the process + * which loaded it has exited. + * + * @param prog BPF program to pin, must already be loaded + * @param path file path in a BPF file system + * @return 0, on success; negative error code, otherwise + */ LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); + +/** + * @brief **bpf_program__unpin()** unpins the BPF program from a file + * in the BPFFS specified by a path. This decrements the programs + * reference count. + * + * The file pinning the BPF program can also be unlinked by a different + * process in which case this function will return an error. + * + * @param prog BPF program to unpin + * @param path file path to the pin in a BPF file system + * @return 0, on success; negative error code, otherwise + */ LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path); LIBBPF_API void bpf_program__unload(struct bpf_program *prog); @@ -282,7 +351,31 @@ struct bpf_link; LIBBPF_API struct bpf_link *bpf_link__open(const char *path); LIBBPF_API int bpf_link__fd(const struct bpf_link *link); LIBBPF_API const char *bpf_link__pin_path(const struct bpf_link *link); +/** + * @brief **bpf_link__pin()** pins the BPF link to a file + * in the BPF FS specified by a path. This increments the links + * reference count, allowing it to stay loaded after the process + * which loaded it has exited. + * + * @param link BPF link to pin, must already be loaded + * @param path file path in a BPF file system + * @return 0, on success; negative error code, otherwise + */ + LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path); + +/** + * @brief **bpf_link__unpin()** unpins the BPF link from a file + * in the BPFFS specified by a path. This decrements the links + * reference count. + * + * The file pinning the BPF link can also be unlinked by a different + * process in which case this function will return an error. + * + * @param prog BPF program to unpin + * @param path file path to the pin in a BPF file system + * @return 0, on success; negative error code, otherwise + */ LIBBPF_API int bpf_link__unpin(struct bpf_link *link); LIBBPF_API int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog); @@ -290,6 +383,22 @@ LIBBPF_API void bpf_link__disconnect(struct bpf_link *link); LIBBPF_API int bpf_link__detach(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); +/** + * @brief **bpf_program__attach()** is a generic function for attaching + * a BPF program based on auto-detection of program type, attach type, + * and extra paremeters, where applicable. + * + * @param prog BPF program to attach + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + * + * This is supported for: + * - kprobe/kretprobe (depends on SEC() definition) + * - uprobe/uretprobe (depends on SEC() definition) + * - tracepoint + * - raw tracepoint + * - tracing programs (typed raw TP/fentry/fexit/fmod_ret) + */ LIBBPF_API struct bpf_link * bpf_program__attach(const struct bpf_program *prog); @@ -329,6 +438,75 @@ 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_ksyscall_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* custom user-provided value fetchable through bpf_get_attach_cookie() */ + __u64 bpf_cookie; + /* attach as return probe? */ + bool retprobe; + size_t :0; +}; +#define bpf_ksyscall_opts__last_field retprobe + +/** + * @brief **bpf_program__attach_ksyscall()** attaches a BPF program + * to kernel syscall handler of a specified syscall. Optionally it's possible + * to request to install retprobe that will be triggered at syscall exit. It's + * also possible to associate BPF cookie (though options). + * + * Libbpf automatically will determine correct full kernel function name, + * which depending on system architecture and kernel version/configuration + * could be of the form __<arch>_sys_<syscall> or __se_sys_<syscall>, and will + * attach specified program using kprobe/kretprobe mechanism. + * + * **bpf_program__attach_ksyscall()** is an API counterpart of declarative + * **SEC("ksyscall/<syscall>")** annotation of BPF programs. + * + * At the moment **SEC("ksyscall")** and **bpf_program__attach_ksyscall()** do + * not handle all the calling convention quirks for mmap(), clone() and compat + * syscalls. It also only attaches to "native" syscall interfaces. If host + * system supports compat syscalls or defines 32-bit syscalls in 64-bit + * kernel, such syscall interfaces won't be attached to by libbpf. + * + * These limitations may or may not change in the future. Therefore it is + * recommended to use SEC("kprobe") for these syscalls or if working with + * compat and 32-bit interfaces is required. + * + * @param prog BPF program to attach + * @param syscall_name Symbolic name of the syscall (e.g., "bpf") + * @param opts Additional options (see **struct bpf_ksyscall_opts**) + * @return Reference to the newly created BPF link; or NULL is returned on + * error, error code is stored in errno + */ +LIBBPF_API struct bpf_link * +bpf_program__attach_ksyscall(const struct bpf_program *prog, + const char *syscall_name, + const struct bpf_ksyscall_opts *opts); + struct bpf_uprobe_opts { /* size of this struct, for forward/backward compatiblity */ size_t sz; @@ -340,19 +518,89 @@ struct bpf_uprobe_opts { __u64 bpf_cookie; /* uprobe is return probe, invoked at function return time */ bool retprobe; + /* Function name to attach to. Could be an unqualified ("abc") or library-qualified + * "abc@LIBXYZ" name. To specify function entry, func_name should be set while + * func_offset argument to bpf_prog__attach_uprobe_opts() should be 0. To trace an + * offset within a function, specify func_name and use func_offset argument to specify + * offset within the function. Shared library functions must specify the shared library + * binary_path. + */ + const char *func_name; size_t :0; }; -#define bpf_uprobe_opts__last_field retprobe +#define bpf_uprobe_opts__last_field func_name +/** + * @brief **bpf_program__attach_uprobe()** attaches a BPF program + * to the userspace function which is found by binary path and + * offset. You can optionally specify a particular proccess to attach + * to. You can also optionally attach the program to the function + * exit instead of entry. + * + * @param prog BPF program to attach + * @param retprobe Attach to function exit + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary that contains the function symbol + * @param func_offset Offset within the binary of the function symbol + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_link * bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, size_t func_offset); + +/** + * @brief **bpf_program__attach_uprobe_opts()** is just like + * bpf_program__attach_uprobe() except with a options struct + * for various configurations. + * + * @param prog BPF program to attach + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary that contains the function symbol + * @param func_offset Offset within the binary of the function symbol + * @param opts Options for altering program attachment + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_link * bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, const struct bpf_uprobe_opts *opts); +struct bpf_usdt_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* custom user-provided value accessible through usdt_cookie() */ + __u64 usdt_cookie; + size_t :0; +}; +#define bpf_usdt_opts__last_field usdt_cookie + +/** + * @brief **bpf_program__attach_usdt()** is just like + * bpf_program__attach_uprobe_opts() except it covers USDT (User-space + * Statically Defined Tracepoint) attachment, instead of attaching to + * user-space function entry or exit. + * + * @param prog BPF program to attach + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary that contains provided USDT probe + * @param usdt_provider USDT provider name + * @param usdt_name USDT probe name + * @param opts Options for altering program attachment + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + */ +LIBBPF_API struct bpf_link * +bpf_program__attach_usdt(const struct bpf_program *prog, + pid_t pid, const char *binary_path, + const char *usdt_provider, const char *usdt_name, + const struct bpf_usdt_opts *opts); + struct bpf_tracepoint_opts { /* size of this struct, for forward/backward compatiblity */ size_t sz; @@ -374,9 +622,21 @@ bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, LIBBPF_API struct bpf_link * bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, const char *tp_name); + +struct bpf_trace_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* custom user-provided value fetchable through bpf_get_attach_cookie() */ + __u64 cookie; +}; +#define bpf_trace_opts__last_field cookie + LIBBPF_API struct bpf_link * bpf_program__attach_trace(const struct bpf_program *prog); LIBBPF_API struct bpf_link * +bpf_program__attach_trace_opts(const struct bpf_program *prog, const struct bpf_trace_opts *opts); + +LIBBPF_API struct bpf_link * bpf_program__attach_lsm(const struct bpf_program *prog); LIBBPF_API struct bpf_link * bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd); @@ -403,129 +663,68 @@ LIBBPF_API struct bpf_link * bpf_program__attach_iter(const struct bpf_program *prog, const struct bpf_iter_attach_opts *opts); -/* - * Libbpf allows callers to adjust BPF programs before being loaded - * into kernel. One program in an object file can be transformed into - * multiple variants to be attached to different hooks. - * - * bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd - * form an API for this purpose. - * - * - bpf_program_prep_t: - * Defines a 'preprocessor', which is a caller defined function - * passed to libbpf through bpf_program__set_prep(), and will be - * called before program is loaded. The processor should adjust - * the program one time for each instance according to the instance id - * passed to it. - * - * - bpf_program__set_prep: - * Attaches a preprocessor to a BPF program. The number of instances - * that should be created is also passed through this function. - * - * - bpf_program__nth_fd: - * After the program is loaded, get resulting FD of a given instance - * of the BPF program. +LIBBPF_API enum bpf_prog_type bpf_program__type(const struct bpf_program *prog); + +/** + * @brief **bpf_program__set_type()** sets the program + * type of the passed BPF program. + * @param prog BPF program to set the program type for + * @param type program type to set the BPF map to have + * @return error code; or 0 if no error. An error occurs + * if the object is already loaded. * - * If bpf_program__set_prep() is not used, the program would be loaded - * without adjustment during bpf_object__load(). The program has only - * one instance. In this case bpf_program__fd(prog) is equal to - * bpf_program__nth_fd(prog, 0). + * This must be called before the BPF object is loaded, + * otherwise it has no effect and an error is returned. */ -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insns() for getting bpf_program instructions") -struct bpf_prog_prep_result { - /* - * If not NULL, load new instruction array. - * If set to NULL, don't load this instance. - */ - struct bpf_insn *new_insn_ptr; - int new_insn_cnt; +LIBBPF_API int bpf_program__set_type(struct bpf_program *prog, + enum bpf_prog_type type); - /* If not NULL, result FD is written to it. */ - int *pfd; -}; +LIBBPF_API enum bpf_attach_type +bpf_program__expected_attach_type(const struct bpf_program *prog); -/* - * Parameters of bpf_program_prep_t: - * - prog: The bpf_program being loaded. - * - n: Index of instance being generated. - * - insns: BPF instructions array. - * - insns_cnt:Number of instructions in insns. - * - res: Output parameter, result of transformation. +/** + * @brief **bpf_program__set_expected_attach_type()** sets the + * attach type of the passed BPF program. This is used for + * auto-detection of attachment when programs are loaded. + * @param prog BPF program to set the attach type for + * @param type attach type to set the BPF map to have + * @return error code; or 0 if no error. An error occurs + * if the object is already loaded. * - * Return value: - * - Zero: pre-processing success. - * - Non-zero: pre-processing error, stop loading. + * This must be called before the BPF object is loaded, + * otherwise it has no effect and an error is returned. */ -typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, - struct bpf_insn *insns, int insns_cnt, - struct bpf_prog_prep_result *res); - -LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insns() for getting bpf_program instructions") -LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, - bpf_program_prep_t prep); +LIBBPF_API int +bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type); -LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated") -LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n); +LIBBPF_API __u32 bpf_program__flags(const struct bpf_program *prog); +LIBBPF_API int bpf_program__set_flags(struct bpf_program *prog, __u32 flags); -/* - * Adjust type of BPF program. Default is kprobe. +/* Per-program log level and log buffer getters/setters. + * See bpf_object_open_opts comments regarding log_level and log_buf + * interactions. */ -LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_lsm(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog); -LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog); -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 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); -LIBBPF_API void -bpf_program__set_expected_attach_type(struct bpf_program *prog, - enum bpf_attach_type type); +LIBBPF_API __u32 bpf_program__log_level(const struct bpf_program *prog); +LIBBPF_API int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level); +LIBBPF_API const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size); +LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size); +/** + * @brief **bpf_program__set_attach_target()** sets BTF-based attach target + * for supported BPF program types: + * - BTF-aware raw tracepoints (tp_btf); + * - fentry/fexit/fmod_ret; + * - lsm; + * - freplace. + * @param prog BPF program to set the attach type for + * @param type attach type to set the BPF map to have + * @return error code; or 0 if no error occurred. + */ LIBBPF_API int bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, const char *attach_func_name); -LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_lsm(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_sk_lookup(const struct bpf_program *prog); - -/* - * No need for __attribute__((packed)), all members of 'bpf_map_def' - * are all aligned. In addition, using __attribute__((packed)) - * would trigger a -Wpacked warning message, and lead to an error - * if -Werror is set. - */ -struct bpf_map_def { - unsigned int type; - unsigned int key_size; - unsigned int value_size; - unsigned int max_entries; - unsigned int map_flags; -}; - /** * @brief **bpf_object__find_map_by_name()** returns BPF map of * the given name, if it exists within the passed BPF object @@ -540,15 +739,6 @@ bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); LIBBPF_API int bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name); -/* - * Get bpf_map through the offset of corresponding struct bpf_map_def - * in the BPF object file. - */ -LIBBPF_API struct bpf_map * -bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); - -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_map() instead") -struct bpf_map *bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); LIBBPF_API struct bpf_map * bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *map); @@ -558,12 +748,32 @@ bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *map); (pos) = bpf_object__next_map((obj), (pos))) #define bpf_map__for_each bpf_object__for_each_map -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_map() instead") -struct bpf_map *bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); LIBBPF_API struct bpf_map * bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map); /** + * @brief **bpf_map__set_autocreate()** sets whether libbpf has to auto-create + * BPF map during BPF object load phase. + * @param map the BPF map instance + * @param autocreate whether to create BPF map during BPF object load + * @return 0 on success; -EBUSY if BPF object was already loaded + * + * **bpf_map__set_autocreate()** allows to opt-out from libbpf auto-creating + * BPF map. By default, libbpf will attempt to create every single BPF map + * defined in BPF object file using BPF_MAP_CREATE command of bpf() syscall + * and fill in map FD in BPF instructions. + * + * This API allows to opt-out of this process for specific map instance. This + * can be useful if host kernel doesn't support such BPF map type or used + * combination of flags and user application wants to avoid creating such + * a map in the first place. User is still responsible to make sure that their + * BPF-side code that expects to use such missing BPF map is recognized by BPF + * verifier as dead code, otherwise BPF verifier will reject such BPF program. + */ +LIBBPF_API int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate); +LIBBPF_API bool bpf_map__autocreate(const struct bpf_map *map); + +/** * @brief **bpf_map__fd()** gets the file descriptor of the passed * BPF map * @param map the BPF map instance @@ -571,8 +781,6 @@ 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); /* get map name */ LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); /* get/set map type */ @@ -581,7 +789,6 @@ 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_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); LIBBPF_API int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags); @@ -604,14 +811,9 @@ LIBBPF_API int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); 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_API int bpf_map__set_priv(struct bpf_map *map, void *priv, - bpf_map_clear_priv_t clear_priv); -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); LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); -LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); /** * @brief **bpf_map__is_internal()** tells the caller whether or not the @@ -622,7 +824,6 @@ 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); @@ -632,75 +833,140 @@ LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); /** - * @brief **libbpf_get_error()** extracts the error code from the passed - * pointer - * @param ptr pointer returned from libbpf API function - * @return error code; or 0 if no error occured - * - * Many libbpf API functions which return pointers have logic to encode error - * codes as pointers, and do not return NULL. Meaning **libbpf_get_error()** - * should be used on the return value from these functions immediately after - * calling the API function, with no intervening calls that could clobber the - * `errno` variable. Consult the individual functions documentation to verify - * if this logic applies should be used. + * @brief **bpf_map__lookup_elem()** allows to lookup BPF map value + * corresponding to provided key. + * @param map BPF map to lookup element in + * @param key pointer to memory containing bytes of the key used for lookup + * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** + * @param value pointer to memory in which looked up value will be stored + * @param value_sz size in byte of value data memory; it has to match BPF map + * definition's **value_size**. For per-CPU BPF maps value size has to be + * a product of BPF map value size and number of possible CPUs in the system + * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for + * per-CPU values value size has to be aligned up to closest 8 bytes for + * alignment reasons, so expected size is: `round_up(value_size, 8) + * * libbpf_num_possible_cpus()`. + * @flags extra flags passed to kernel for this operation + * @return 0, on success; negative error, otherwise * - * For these API functions, if `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` - * is enabled, NULL is returned on error instead. + * **bpf_map__lookup_elem()** is high-level equivalent of + * **bpf_map_lookup_elem()** API with added check for key and value size. + */ +LIBBPF_API int bpf_map__lookup_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + void *value, size_t value_sz, __u64 flags); + +/** + * @brief **bpf_map__update_elem()** allows to insert or update value in BPF + * map that corresponds to provided key. + * @param map BPF map to insert to or update element in + * @param key pointer to memory containing bytes of the key + * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** + * @param value pointer to memory containing bytes of the value + * @param value_sz size in byte of value data memory; it has to match BPF map + * definition's **value_size**. For per-CPU BPF maps value size has to be + * a product of BPF map value size and number of possible CPUs in the system + * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for + * per-CPU values value size has to be aligned up to closest 8 bytes for + * alignment reasons, so expected size is: `round_up(value_size, 8) + * * libbpf_num_possible_cpus()`. + * @flags extra flags passed to kernel for this operation + * @return 0, on success; negative error, otherwise * - * If ptr is NULL, then errno should be already set by the failing - * API, because libbpf never returns NULL on success and it now always - * sets errno on error. + * **bpf_map__update_elem()** is high-level equivalent of + * **bpf_map_update_elem()** API with added check for key and value size. + */ +LIBBPF_API int bpf_map__update_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + const void *value, size_t value_sz, __u64 flags); + +/** + * @brief **bpf_map__delete_elem()** allows to delete element in BPF map that + * corresponds to provided key. + * @param map BPF map to delete element from + * @param key pointer to memory containing bytes of the key + * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** + * @flags extra flags passed to kernel for this operation + * @return 0, on success; negative error, otherwise * - * Example usage: + * **bpf_map__delete_elem()** is high-level equivalent of + * **bpf_map_delete_elem()** API with added check for key size. + */ +LIBBPF_API int bpf_map__delete_elem(const struct bpf_map *map, + const void *key, size_t key_sz, __u64 flags); + +/** + * @brief **bpf_map__lookup_and_delete_elem()** allows to lookup BPF map value + * corresponding to provided key and atomically delete it afterwards. + * @param map BPF map to lookup element in + * @param key pointer to memory containing bytes of the key used for lookup + * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** + * @param value pointer to memory in which looked up value will be stored + * @param value_sz size in byte of value data memory; it has to match BPF map + * definition's **value_size**. For per-CPU BPF maps value size has to be + * a product of BPF map value size and number of possible CPUs in the system + * (could be fetched with **libbpf_num_possible_cpus()**). Note also that for + * per-CPU values value size has to be aligned up to closest 8 bytes for + * alignment reasons, so expected size is: `round_up(value_size, 8) + * * libbpf_num_possible_cpus()`. + * @flags extra flags passed to kernel for this operation + * @return 0, on success; negative error, otherwise * - * struct perf_buffer *pb; + * **bpf_map__lookup_and_delete_elem()** is high-level equivalent of + * **bpf_map_lookup_and_delete_elem()** API with added check for key and value size. + */ +LIBBPF_API int bpf_map__lookup_and_delete_elem(const struct bpf_map *map, + const void *key, size_t key_sz, + void *value, size_t value_sz, __u64 flags); + +/** + * @brief **bpf_map__get_next_key()** allows to iterate BPF map keys by + * fetching next key that follows current key. + * @param map BPF map to fetch next key from + * @param cur_key pointer to memory containing bytes of current key or NULL to + * fetch the first key + * @param next_key pointer to memory to write next key into + * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** + * @return 0, on success; -ENOENT if **cur_key** is the last key in BPF map; + * negative error, otherwise * - * pb = perf_buffer__new(bpf_map__fd(obj->maps.events), PERF_BUFFER_PAGES, &opts); - * err = libbpf_get_error(pb); - * if (err) { - * pb = NULL; - * fprintf(stderr, "failed to open perf buffer: %d\n", err); - * goto cleanup; - * } + * **bpf_map__get_next_key()** is high-level equivalent of + * **bpf_map_get_next_key()** API with added check for key size. */ -LIBBPF_API long libbpf_get_error(const void *ptr); +LIBBPF_API int bpf_map__get_next_key(const struct bpf_map *map, + const void *cur_key, void *next_key, size_t key_sz); -struct bpf_prog_load_attr { - const char *file; - enum bpf_prog_type prog_type; - enum bpf_attach_type expected_attach_type; - int ifindex; - int log_level; - int prog_flags; +struct bpf_xdp_set_link_opts { + size_t sz; + int old_fd; + size_t :0; }; +#define bpf_xdp_set_link_opts__last_field old_fd -LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, - struct bpf_object **pobj, int *prog_fd); -LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type, - struct bpf_object **pobj, int *prog_fd); - -/* XDP related API */ -struct xdp_link_info { - __u32 prog_id; - __u32 drv_prog_id; - __u32 hw_prog_id; - __u32 skb_prog_id; - __u8 attach_mode; +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_set_link_opts { +struct bpf_xdp_query_opts { size_t sz; - int old_fd; + __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_set_link_opts__last_field old_fd +#define bpf_xdp_query_opts__last_field attach_mode -LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); -LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, - const struct bpf_xdp_set_link_opts *opts); -LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); -LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, - size_t info_size, __u32 flags); +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 { @@ -747,6 +1013,7 @@ LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook, /* Ring buffer APIs */ struct ring_buffer; +struct user_ring_buffer; typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size); @@ -766,6 +1033,112 @@ LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms); LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb); LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb); +struct user_ring_buffer_opts { + size_t sz; /* size of this struct, for forward/backward compatibility */ +}; + +#define user_ring_buffer_opts__last_field sz + +/* @brief **user_ring_buffer__new()** creates a new instance of a user ring + * buffer. + * + * @param map_fd A file descriptor to a BPF_MAP_TYPE_USER_RINGBUF map. + * @param opts Options for how the ring buffer should be created. + * @return A user ring buffer on success; NULL and errno being set on a + * failure. + */ +LIBBPF_API struct user_ring_buffer * +user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts); + +/* @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the + * user ring buffer. + * @param rb A pointer to a user ring buffer. + * @param size The size of the sample, in bytes. + * @return A pointer to an 8-byte aligned reserved region of the user ring + * buffer; NULL, and errno being set if a sample could not be reserved. + * + * This function is *not* thread safe, and callers must synchronize accessing + * this function if there are multiple producers. If a size is requested that + * is larger than the size of the entire ring buffer, errno will be set to + * E2BIG and NULL is returned. If the ring buffer could accommodate the size, + * but currently does not have enough space, errno is set to ENOSPC and NULL is + * returned. + * + * After initializing the sample, callers must invoke + * **user_ring_buffer__submit()** to post the sample to the kernel. Otherwise, + * the sample must be freed with **user_ring_buffer__discard()**. + */ +LIBBPF_API void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size); + +/* @brief **user_ring_buffer__reserve_blocking()** reserves a record in the + * ring buffer, possibly blocking for up to @timeout_ms until a sample becomes + * available. + * @param rb The user ring buffer. + * @param size The size of the sample, in bytes. + * @param timeout_ms The amount of time, in milliseconds, for which the caller + * should block when waiting for a sample. -1 causes the caller to block + * indefinitely. + * @return A pointer to an 8-byte aligned reserved region of the user ring + * buffer; NULL, and errno being set if a sample could not be reserved. + * + * This function is *not* thread safe, and callers must synchronize + * accessing this function if there are multiple producers + * + * If **timeout_ms** is -1, the function will block indefinitely until a sample + * becomes available. Otherwise, **timeout_ms** must be non-negative, or errno + * is set to EINVAL, and NULL is returned. If **timeout_ms** is 0, no blocking + * will occur and the function will return immediately after attempting to + * reserve a sample. + * + * If **size** is larger than the size of the entire ring buffer, errno is set + * to E2BIG and NULL is returned. If the ring buffer could accommodate + * **size**, but currently does not have enough space, the caller will block + * until at most **timeout_ms** has elapsed. If insufficient space is available + * at that time, errno is set to ENOSPC, and NULL is returned. + * + * The kernel guarantees that it will wake up this thread to check if + * sufficient space is available in the ring buffer at least once per + * invocation of the **bpf_ringbuf_drain()** helper function, provided that at + * least one sample is consumed, and the BPF program did not invoke the + * function with BPF_RB_NO_WAKEUP. A wakeup may occur sooner than that, but the + * kernel does not guarantee this. If the helper function is invoked with + * BPF_RB_FORCE_WAKEUP, a wakeup event will be sent even if no sample is + * consumed. + * + * When a sample of size **size** is found within **timeout_ms**, a pointer to + * the sample is returned. After initializing the sample, callers must invoke + * **user_ring_buffer__submit()** to post the sample to the ring buffer. + * Otherwise, the sample must be freed with **user_ring_buffer__discard()**. + */ +LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, + __u32 size, + int timeout_ms); + +/* @brief **user_ring_buffer__submit()** submits a previously reserved sample + * into the ring buffer. + * @param rb The user ring buffer. + * @param sample A reserved sample. + * + * It is not necessary to synchronize amongst multiple producers when invoking + * this function. + */ +LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample); + +/* @brief **user_ring_buffer__discard()** discards a previously reserved sample. + * @param rb The user ring buffer. + * @param sample A reserved sample. + * + * It is not necessary to synchronize amongst multiple producers when invoking + * this function. + */ +LIBBPF_API void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample); + +/* @brief **user_ring_buffer__free()** frees a ring buffer that was previously + * created with **user_ring_buffer__new()**. + * @param rb The user ring buffer being freed. + */ +LIBBPF_API void user_ring_buffer__free(struct user_ring_buffer *rb); + /* Perf buffer APIs */ struct perf_buffer; @@ -775,16 +1148,25 @@ typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); /* common use perf buffer options */ struct perf_buffer_opts { - /* if specified, sample_cb is called for each sample */ - perf_buffer_sample_fn sample_cb; - /* if specified, lost_cb is called for each batch of lost samples */ - perf_buffer_lost_fn lost_cb; - /* ctx is provided to sample_cb and lost_cb */ - void *ctx; + size_t sz; }; +#define perf_buffer_opts__last_field sz +/** + * @brief **perf_buffer__new()** creates BPF perfbuf manager for a specified + * BPF_PERF_EVENT_ARRAY map + * @param map_fd FD of BPF_PERF_EVENT_ARRAY BPF map that will be used by BPF + * code to send data over to user-space + * @param page_cnt number of memory pages allocated for each per-CPU buffer + * @param sample_cb function called on each received data record + * @param lost_cb function called when record loss has occurred + * @param ctx user-provided extra context passed into *sample_cb* and *lost_cb* + * @return a new instance of struct perf_buffer on success, NULL on error with + * *errno* containing an error code + */ LIBBPF_API struct perf_buffer * perf_buffer__new(int map_fd, size_t page_cnt, + perf_buffer_sample_fn sample_cb, perf_buffer_lost_fn lost_cb, void *ctx, const struct perf_buffer_opts *opts); enum bpf_perf_event_ret { @@ -800,12 +1182,9 @@ typedef enum bpf_perf_event_ret /* raw perf buffer options, giving most power and control */ struct perf_buffer_raw_opts { - /* perf event attrs passed directly into perf_event_open() */ - struct perf_event_attr *attr; - /* raw event callback */ - perf_buffer_event_fn event_cb; - /* ctx is provided to event_cb */ - void *ctx; + size_t sz; + long :0; + long :0; /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of * max_entries of given PERF_EVENT_ARRAY map) */ @@ -815,9 +1194,13 @@ struct perf_buffer_raw_opts { /* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */ int *map_keys; }; +#define perf_buffer_raw_opts__last_field map_keys + +struct perf_event_attr; LIBBPF_API struct perf_buffer * -perf_buffer__new_raw(int map_fd, size_t page_cnt, +perf_buffer__new_raw(int map_fd, size_t page_cnt, struct perf_event_attr *attr, + perf_buffer_event_fn event_cb, void *ctx, const struct perf_buffer_raw_opts *opts); LIBBPF_API void perf_buffer__free(struct perf_buffer *pb); @@ -827,14 +1210,22 @@ LIBBPF_API int perf_buffer__consume(struct perf_buffer *pb); LIBBPF_API int perf_buffer__consume_buffer(struct perf_buffer *pb, size_t buf_idx); LIBBPF_API size_t perf_buffer__buffer_cnt(const struct perf_buffer *pb); LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx); - -typedef enum bpf_perf_event_ret - (*bpf_perf_event_print_t)(struct perf_event_header *hdr, - void *private_data); -LIBBPF_API enum bpf_perf_event_ret -bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, - void **copy_mem, size_t *copy_size, - bpf_perf_event_print_t fn, void *private_data); +/** + * @brief **perf_buffer__buffer()** returns the per-cpu raw mmap()'ed underlying + * memory region of the ring buffer. + * This ring buffer can be used to implement a custom events consumer. + * The ring buffer starts with the *struct perf_event_mmap_page*, which + * holds the ring buffer managment fields, when accessing the header + * structure it's important to be SMP aware. + * You can refer to *perf_event_read_simple* for a simple example. + * @param pb the perf buffer structure + * @param buf_idx the buffer index to retreive + * @param buf (out) gets the base pointer of the mmap()'ed memory + * @param buf_size (out) gets the size of the mmap()'ed region + * @return 0 on success, negative error code for failure + */ +LIBBPF_API int perf_buffer__buffer(struct perf_buffer *pb, int buf_idx, void **buf, + size_t *buf_size); struct bpf_prog_linfo; struct bpf_prog_info; @@ -857,75 +1248,48 @@ bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo, * user, causing subsequent probes to fail. In this case, the caller may want * to adjust that limit with setrlimit(). */ -LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, - __u32 ifindex); -LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex); -LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, - enum bpf_prog_type prog_type, __u32 ifindex); -LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex); -/* - * Get bpf_prog_info in continuous memory - * - * struct bpf_prog_info has multiple arrays. The user has option to choose - * arrays to fetch from kernel. The following APIs provide an uniform way to - * fetch these data. All arrays in bpf_prog_info are stored in a single - * continuous memory region. This makes it easy to store the info in a - * file. - * - * Before writing bpf_prog_info_linear to files, it is necessary to - * translate pointers in bpf_prog_info to offsets. Helper functions - * bpf_program__bpil_addr_to_offs() and bpf_program__bpil_offs_to_addr() - * are introduced to switch between pointers and offsets. +/** + * @brief **libbpf_probe_bpf_prog_type()** detects if host kernel supports + * BPF programs of a given type. + * @param prog_type BPF program type to detect kernel support for + * @param opts reserved for future extensibility, should be NULL + * @return 1, if given program type is supported; 0, if given program type is + * not supported; negative error code if feature detection failed or can't be + * performed * - * Examples: - * # To fetch map_ids and prog_tags: - * __u64 arrays = (1UL << BPF_PROG_INFO_MAP_IDS) | - * (1UL << BPF_PROG_INFO_PROG_TAGS); - * struct bpf_prog_info_linear *info_linear = - * bpf_program__get_prog_info_linear(fd, arrays); + * Make sure the process has required set of CAP_* permissions (or runs as + * root) when performing feature checking. + */ +LIBBPF_API int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts); +/** + * @brief **libbpf_probe_bpf_map_type()** detects if host kernel supports + * BPF maps of a given type. + * @param map_type BPF map type to detect kernel support for + * @param opts reserved for future extensibility, should be NULL + * @return 1, if given map type is supported; 0, if given map type is + * not supported; negative error code if feature detection failed or can't be + * performed * - * # To save data in file - * bpf_program__bpil_addr_to_offs(info_linear); - * write(f, info_linear, sizeof(*info_linear) + info_linear->data_len); + * Make sure the process has required set of CAP_* permissions (or runs as + * root) when performing feature checking. + */ +LIBBPF_API int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts); +/** + * @brief **libbpf_probe_bpf_helper()** detects if host kernel supports the + * use of a given BPF helper from specified BPF program type. + * @param prog_type BPF program type used to check the support of BPF helper + * @param helper_id BPF helper ID (enum bpf_func_id) to check support for + * @param opts reserved for future extensibility, should be NULL + * @return 1, if given combination of program type and helper is supported; 0, + * if the combination is not supported; negative error code if feature + * detection for provided input arguments failed or can't be performed * - * # To read data from file - * read(f, info_linear, <proper_size>); - * bpf_program__bpil_offs_to_addr(info_linear); + * Make sure the process has required set of CAP_* permissions (or runs as + * root) when performing feature checking. */ -enum bpf_prog_info_array { - BPF_PROG_INFO_FIRST_ARRAY = 0, - BPF_PROG_INFO_JITED_INSNS = 0, - BPF_PROG_INFO_XLATED_INSNS, - BPF_PROG_INFO_MAP_IDS, - BPF_PROG_INFO_JITED_KSYMS, - BPF_PROG_INFO_JITED_FUNC_LENS, - BPF_PROG_INFO_FUNC_INFO, - BPF_PROG_INFO_LINE_INFO, - BPF_PROG_INFO_JITED_LINE_INFO, - BPF_PROG_INFO_PROG_TAGS, - BPF_PROG_INFO_LAST_ARRAY, -}; - -struct bpf_prog_info_linear { - /* size of struct bpf_prog_info, when the tool is compiled */ - __u32 info_len; - /* total bytes allocated for data, round up to 8 bytes */ - __u32 data_len; - /* which arrays are included in data */ - __u64 arrays; - struct bpf_prog_info info; - __u8 data[]; -}; - -LIBBPF_API struct bpf_prog_info_linear * -bpf_program__get_prog_info_linear(int fd, __u64 arrays); - -LIBBPF_API void -bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); - -LIBBPF_API void -bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); +LIBBPF_API int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, + enum bpf_func_id helper_id, const void *opts); /** * @brief **libbpf_num_possible_cpus()** is a helper function to get the @@ -965,11 +1329,11 @@ struct bpf_object_skeleton { struct bpf_object **obj; int map_cnt; - int map_skel_sz; /* sizeof(struct bpf_skeleton_map) */ + int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */ struct bpf_map_skeleton *maps; int prog_cnt; - int prog_skel_sz; /* sizeof(struct bpf_skeleton_prog) */ + int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */ struct bpf_prog_skeleton *progs; }; @@ -981,6 +1345,35 @@ 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; @@ -1020,6 +1413,115 @@ 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 43580eb47740..c1d6aa7c82b6 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -1,29 +1,14 @@ LIBBPF_0.0.1 { global: bpf_btf_get_fd_by_id; - bpf_create_map; - bpf_create_map_in_map; - bpf_create_map_in_map_node; - bpf_create_map_name; - bpf_create_map_node; - bpf_create_map_xattr; - bpf_load_btf; - bpf_load_program; - bpf_load_program_xattr; bpf_map__btf_key_type_id; bpf_map__btf_value_type_id; - bpf_map__def; bpf_map__fd; - bpf_map__is_offload_neutral; bpf_map__name; - bpf_map__next; bpf_map__pin; - bpf_map__prev; - bpf_map__priv; bpf_map__reuse_fd; bpf_map__set_ifindex; bpf_map__set_inner_map_fd; - bpf_map__set_priv; bpf_map__unpin; bpf_map_delete_elem; bpf_map_get_fd_by_id; @@ -38,79 +23,37 @@ LIBBPF_0.0.1 { bpf_object__btf_fd; bpf_object__close; bpf_object__find_map_by_name; - bpf_object__find_map_by_offset; - bpf_object__find_program_by_title; bpf_object__kversion; bpf_object__load; bpf_object__name; - bpf_object__next; bpf_object__open; - bpf_object__open_buffer; - bpf_object__open_xattr; bpf_object__pin; bpf_object__pin_maps; bpf_object__pin_programs; - bpf_object__priv; - bpf_object__set_priv; - bpf_object__unload; bpf_object__unpin_maps; bpf_object__unpin_programs; - bpf_perf_event_read_simple; bpf_prog_attach; bpf_prog_detach; bpf_prog_detach2; bpf_prog_get_fd_by_id; bpf_prog_get_next_id; - bpf_prog_load; - bpf_prog_load_xattr; bpf_prog_query; - bpf_prog_test_run; - bpf_prog_test_run_xattr; bpf_program__fd; - bpf_program__is_kprobe; - bpf_program__is_perf_event; - bpf_program__is_raw_tracepoint; - bpf_program__is_sched_act; - bpf_program__is_sched_cls; - bpf_program__is_socket_filter; - bpf_program__is_tracepoint; - bpf_program__is_xdp; - bpf_program__load; - bpf_program__next; - bpf_program__nth_fd; bpf_program__pin; - bpf_program__pin_instance; - bpf_program__prev; - bpf_program__priv; bpf_program__set_expected_attach_type; bpf_program__set_ifindex; - bpf_program__set_kprobe; - bpf_program__set_perf_event; - bpf_program__set_prep; - bpf_program__set_priv; - bpf_program__set_raw_tracepoint; - bpf_program__set_sched_act; - bpf_program__set_sched_cls; - bpf_program__set_socket_filter; - bpf_program__set_tracepoint; bpf_program__set_type; - bpf_program__set_xdp; - bpf_program__title; bpf_program__unload; bpf_program__unpin; - bpf_program__unpin_instance; bpf_prog_linfo__free; bpf_prog_linfo__new; bpf_prog_linfo__lfind_addr_func; bpf_prog_linfo__lfind; bpf_raw_tracepoint_open; - bpf_set_link_xdp_fd; bpf_task_fd_query; - bpf_verify_program; btf__fd; btf__find_by_name; btf__free; - btf__get_from_id; btf__name_by_offset; btf__new; btf__resolve_size; @@ -127,48 +70,24 @@ LIBBPF_0.0.1 { LIBBPF_0.0.2 { global: - bpf_probe_helper; - bpf_probe_map_type; - bpf_probe_prog_type; - bpf_map__resize; bpf_map_lookup_elem_flags; bpf_object__btf; bpf_object__find_map_fd_by_name; - bpf_get_link_xdp_id; - btf__dedup; - btf__get_map_kv_tids; - btf__get_nr_types; btf__get_raw_data; - btf__load; btf_ext__free; - btf_ext__func_info_rec_size; btf_ext__get_raw_data; - btf_ext__line_info_rec_size; btf_ext__new; - btf_ext__reloc_func_info; - btf_ext__reloc_line_info; - xsk_umem__create; - xsk_socket__create; - xsk_umem__delete; - xsk_socket__delete; - xsk_umem__fd; - xsk_socket__fd; - bpf_program__get_prog_info_linear; - bpf_program__bpil_addr_to_offs; - bpf_program__bpil_offs_to_addr; } LIBBPF_0.0.1; LIBBPF_0.0.3 { global: bpf_map__is_internal; bpf_map_freeze; - btf__finalize_data; } LIBBPF_0.0.2; LIBBPF_0.0.4 { global: bpf_link__destroy; - bpf_object__load_xattr; bpf_program__attach_kprobe; bpf_program__attach_perf_event; bpf_program__attach_raw_tracepoint; @@ -176,14 +95,10 @@ LIBBPF_0.0.4 { bpf_program__attach_uprobe; btf_dump__dump_type; btf_dump__free; - btf_dump__new; btf__parse_elf; libbpf_num_possible_cpus; perf_buffer__free; - perf_buffer__new; - perf_buffer__new_raw; perf_buffer__poll; - xsk_umem__create; } LIBBPF_0.0.3; LIBBPF_0.0.5 { @@ -193,7 +108,6 @@ LIBBPF_0.0.5 { LIBBPF_0.0.6 { global: - bpf_get_link_xdp_info; bpf_map__get_pin_path; bpf_map__is_pinned; bpf_map__set_pin_path; @@ -202,9 +116,6 @@ LIBBPF_0.0.6 { bpf_program__attach_trace; bpf_program__get_expected_attach_type; bpf_program__get_type; - bpf_program__is_tracing; - bpf_program__set_tracing; - bpf_program__size; btf__find_by_name_kind; libbpf_find_vmlinux_btf_id; } LIBBPF_0.0.5; @@ -224,14 +135,8 @@ LIBBPF_0.0.7 { bpf_object__detach_skeleton; bpf_object__load_skeleton; bpf_object__open_skeleton; - bpf_probe_large_insn_limit; - bpf_prog_attach_xattr; bpf_program__attach; bpf_program__name; - bpf_program__is_extension; - bpf_program__is_struct_ops; - bpf_program__set_extension; - bpf_program__set_struct_ops; btf__align_of; libbpf_find_kernel_btf; } LIBBPF_0.0.6; @@ -247,12 +152,10 @@ 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; bpf_program__set_attach_target; - bpf_program__set_lsm; - bpf_set_link_xdp_fd_opts; } LIBBPF_0.0.7; LIBBPF_0.0.9 { @@ -290,9 +193,7 @@ LIBBPF_0.1.0 { bpf_map__value_size; bpf_program__attach_xdp; bpf_program__autoload; - bpf_program__is_sk_lookup; bpf_program__set_autoload; - bpf_program__set_sk_lookup; btf__parse; btf__parse_raw; btf__pointer_size; @@ -335,7 +236,6 @@ LIBBPF_0.2.0 { perf_buffer__buffer_fd; perf_buffer__epoll_fd; perf_buffer__consume_buffer; - xsk_socket__create_shared; } LIBBPF_0.1.0; LIBBPF_0.3.0 { @@ -347,8 +247,6 @@ LIBBPF_0.3.0 { btf__new_empty_split; btf__new_split; ring_buffer__epoll_fd; - xsk_setup_xdp_prog; - xsk_socket__update_xskmap; } LIBBPF_0.2.0; LIBBPF_0.4.0 { @@ -391,14 +289,92 @@ LIBBPF_0.6.0 { global: bpf_map__map_extra; bpf_map__set_map_extra; + bpf_map_create; bpf_object__next_map; bpf_object__next_program; bpf_object__prev_map; bpf_object__prev_program; + bpf_prog_load; + bpf_program__flags; bpf_program__insn_cnt; bpf_program__insns; + bpf_program__set_flags; btf__add_btf; btf__add_decl_tag; + btf__add_type_tag; + btf__dedup; btf__raw_data; btf__type_cnt; + btf_dump__new; + libbpf_major_version; + libbpf_minor_version; + libbpf_version_string; + perf_buffer__new; + perf_buffer__new_raw; } LIBBPF_0.5.0; + +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; + btf_ext__raw_data; + libbpf_probe_bpf_helper; + libbpf_probe_bpf_map_type; + libbpf_probe_bpf_prog_type; + libbpf_set_memlock_rlim; +} LIBBPF_0.6.0; + +LIBBPF_0.8.0 { + global: + bpf_map__autocreate; + bpf_map__get_next_key; + bpf_map__delete_elem; + bpf_map__lookup_and_delete_elem; + bpf_map__lookup_elem; + bpf_map__set_autocreate; + bpf_map__update_elem; + bpf_map_delete_elem_flags; + bpf_object__destroy_subskeleton; + bpf_object__open_subskeleton; + bpf_program__attach_kprobe_multi_opts; + bpf_program__attach_trace_opts; + bpf_program__attach_usdt; + bpf_program__set_insns; + libbpf_register_prog_handler; + libbpf_unregister_prog_handler; +} LIBBPF_0.7.0; + +LIBBPF_1.0.0 { + global: + bpf_obj_get_opts; + bpf_prog_query_opts; + bpf_program__attach_ksyscall; + bpf_program__autoattach; + bpf_program__set_autoattach; + btf__add_enum64; + btf__add_enum64_value; + libbpf_bpf_attach_type_str; + libbpf_bpf_link_type_str; + libbpf_bpf_map_type_str; + libbpf_bpf_prog_type_str; + perf_buffer__buffer; +}; + +LIBBPF_1.1.0 { + global: + user_ring_buffer__discard; + user_ring_buffer__free; + user_ring_buffer__new; + user_ring_buffer__reserve; + user_ring_buffer__reserve_blocking; + user_ring_buffer__submit; +} LIBBPF_1.0.0; diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h index aaa1efbf6f51..9a7937f339df 100644 --- a/tools/lib/bpf/libbpf_common.h +++ b/tools/lib/bpf/libbpf_common.h @@ -30,17 +30,24 @@ /* Add checks for other versions below when planning deprecation of API symbols * with the LIBBPF_DEPRECATED_SINCE macro. */ -#if __LIBBPF_CURRENT_VERSION_GEQ(0, 6) -#define __LIBBPF_MARK_DEPRECATED_0_6(X) X +#if __LIBBPF_CURRENT_VERSION_GEQ(1, 0) +#define __LIBBPF_MARK_DEPRECATED_1_0(X) X #else -#define __LIBBPF_MARK_DEPRECATED_0_6(X) -#endif -#if __LIBBPF_CURRENT_VERSION_GEQ(0, 7) -#define __LIBBPF_MARK_DEPRECATED_0_7(X) X -#else -#define __LIBBPF_MARK_DEPRECATED_0_7(X) +#define __LIBBPF_MARK_DEPRECATED_1_0(X) #endif +/* This set of internal macros allows to do "function overloading" based on + * number of arguments provided by used in backwards-compatible way during the + * transition to libbpf 1.0 + * It's ugly but necessary evil that will be cleaned up when we get to 1.0. + * See bpf_prog_load() overload for example. + */ +#define ___libbpf_cat(A, B) A ## B +#define ___libbpf_select(NAME, NUM) ___libbpf_cat(NAME, NUM) +#define ___libbpf_nth(_1, _2, _3, _4, _5, _6, N, ...) N +#define ___libbpf_cnt(...) ___libbpf_nth(__VA_ARGS__, 6, 5, 4, 3, 2, 1) +#define ___libbpf_overload(NAME, ...) ___libbpf_select(NAME, ___libbpf_cnt(__VA_ARGS__))(__VA_ARGS__) + /* Helper macro to declare and initialize libbpf options struct * * This dance with uninitialized declaration, followed by memset to zero, @@ -54,7 +61,7 @@ * including any extra padding, it with memset() and then assigns initial * values provided by users in struct initializer-syntax as varargs. */ -#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...) \ +#define LIBBPF_OPTS(TYPE, NAME, ...) \ struct TYPE NAME = ({ \ memset(&NAME, 0, sizeof(struct TYPE)); \ (struct TYPE) { \ diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index aeb79e3a8ff9..377642ff51fc 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -15,7 +15,6 @@ #include <linux/err.h> #include <fcntl.h> #include <unistd.h> -#include "libbpf_legacy.h" #include "relo_core.h" /* make sure libbpf doesn't use kernel-only integer typedefs */ @@ -73,6 +72,8 @@ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) #define BTF_TYPE_DECL_TAG_ENC(value, type, component_idx) \ BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) +#define BTF_TYPE_TYPE_TAG_ENC(value, type) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 0, 0), type) #ifndef likely #define likely(x) __builtin_expect(!!(x), 1) @@ -90,6 +91,9 @@ # 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 @@ -98,6 +102,17 @@ #define str_has_pfx(str, pfx) \ (strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0) +/* suffix check */ +static inline bool str_has_sfx(const char *str, const char *sfx) +{ + size_t str_len = strlen(str); + size_t sfx_len = strlen(sfx); + + if (sfx_len > str_len) + return false; + return strcmp(str + str_len - sfx_len, sfx) == 0; +} + /* Symbol versioning is different between static and shared library. * Properly versioned symbols are needed for shared library, but * only the symbol of the new version is needed for static library. @@ -143,6 +158,15 @@ do { \ #ifndef __has_builtin #define __has_builtin(x) 0 #endif + +struct bpf_link { + int (*detach)(struct bpf_link *link); + void (*dealloc)(struct bpf_link *link); + char *pin_path; /* NULL, if not pinned */ + int fd; /* hook FD, -1 if not applicable */ + bool disconnected; +}; + /* * Re-implement glibc's reallocarray() for libbpf internal-only use. * reallocarray(), unfortunately, is not available in all versions of glibc, @@ -167,10 +191,31 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size) return realloc(ptr, total); } +/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst + * is zero-terminated string no matter what (unless sz == 0, in which case + * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs + * in what is returned. Given this is internal helper, it's trivial to extend + * this, when necessary. Use this instead of strncpy inside libbpf source code. + */ +static inline void libbpf_strlcpy(char *dst, const char *src, size_t sz) +{ + size_t i; + + if (sz == 0) + return; + + sz--; + for (i = 0; i < sz && src[i]; i++) + dst[i] = src[i]; + dst[i] = '\0'; +} + +__u32 get_kernel_version(void); + struct btf; struct btf_type; -struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id); +struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id); const char *btf_kind_str(const struct btf_type *t); const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); @@ -270,63 +315,57 @@ static inline bool libbpf_validate_opts(const char *opts, (opts)->sz - __off); \ }) +enum kern_feature_id { + /* v4.14: kernel support for program & map names. */ + FEAT_PROG_NAME, + /* v5.2: kernel support for global data sections. */ + FEAT_GLOBAL_DATA, + /* BTF support */ + FEAT_BTF, + /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */ + FEAT_BTF_FUNC, + /* BTF_KIND_VAR and BTF_KIND_DATASEC support */ + FEAT_BTF_DATASEC, + /* BTF_FUNC_GLOBAL is supported */ + FEAT_BTF_GLOBAL_FUNC, + /* BPF_F_MMAPABLE is supported for arrays */ + FEAT_ARRAY_MMAP, + /* kernel support for expected_attach_type in BPF_PROG_LOAD */ + FEAT_EXP_ATTACH_TYPE, + /* bpf_probe_read_{kernel,user}[_str] helpers */ + FEAT_PROBE_READ_KERN, + /* BPF_PROG_BIND_MAP is supported */ + FEAT_PROG_BIND_MAP, + /* Kernel support for module BTFs */ + FEAT_MODULE_BTF, + /* BTF_KIND_FLOAT support */ + FEAT_BTF_FLOAT, + /* BPF perf link support */ + FEAT_PERF_LINK, + /* BTF_KIND_DECL_TAG support */ + FEAT_BTF_DECL_TAG, + /* BTF_KIND_TYPE_TAG support */ + FEAT_BTF_TYPE_TAG, + /* memcg-based accounting for BPF maps and progs */ + FEAT_MEMCG_ACCOUNT, + /* BPF cookie (bpf_get_attach_cookie() BPF helper) support */ + FEAT_BPF_COOKIE, + /* BTF_KIND_ENUM64 support and BTF_KIND_ENUM kflag support */ + FEAT_BTF_ENUM64, + /* Kernel uses syscall wrapper (CONFIG_ARCH_HAS_SYSCALL_WRAPPER) */ + FEAT_SYSCALL_WRAPPER, + __FEAT_CNT, +}; + +int probe_memcg_account(void); +bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); +int bump_rlimit_memlock(void); int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); - -struct bpf_prog_load_params { - enum bpf_prog_type prog_type; - enum bpf_attach_type expected_attach_type; - const char *name; - const struct bpf_insn *insns; - size_t insn_cnt; - const char *license; - __u32 kern_version; - __u32 attach_prog_fd; - __u32 attach_btf_obj_fd; - __u32 attach_btf_id; - __u32 prog_ifindex; - __u32 prog_btf_fd; - __u32 prog_flags; - - __u32 func_info_rec_size; - const void *func_info; - __u32 func_info_cnt; - - __u32 line_info_rec_size; - const void *line_info; - __u32 line_info_cnt; - - __u32 log_level; - char *log_buf; - size_t log_buf_sz; - int *fd_array; -}; - -int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr); - -struct bpf_create_map_params { - const char *name; - enum bpf_map_type map_type; - __u32 map_flags; - __u32 key_size; - __u32 value_size; - __u32 max_entries; - __u32 numa_node; - __u32 btf_fd; - __u32 btf_key_type_id; - __u32 btf_value_type_id; - __u32 map_ifindex; - union { - __u32 inner_map_fd; - __u32 btf_vmlinux_value_type_id; - }; - __u64 map_extra; -}; - -int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr); +int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, @@ -340,6 +379,13 @@ struct btf_ext_info { void *info; __u32 rec_size; __u32 len; + /* optional (maintained internally by libbpf) mapping between .BTF.ext + * section and corresponding ELF section. This is used to join + * information like CO-RE relocation records with corresponding BPF + * programs defined in ELF sections + */ + __u32 *sec_idxs; + int sec_cnt; }; #define for_each_btf_ext_sec(seg, sec) \ @@ -433,7 +479,10 @@ int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name, __u32 kind); -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) @@ -448,12 +497,8 @@ static inline int libbpf_err(int ret) */ static inline int libbpf_err_errno(int ret) { - if (libbpf_mode & LIBBPF_STRICT_DIRECT_ERRS) - /* errno is already assumed to be set on error */ - return ret < 0 ? -errno : ret; - - /* legacy: on error return -1 directly and don't touch errno */ - return ret; + /* errno is already assumed to be set on error */ + return ret < 0 ? -errno : ret; } /* handle error for pointer-returning APIs, err is assumed to be < 0 always */ @@ -461,12 +506,7 @@ static inline void *libbpf_err_ptr(int err) { /* set errno on error, this doesn't break anything */ errno = -err; - - if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS) - return NULL; - - /* legacy: encode err as ptr */ - return ERR_PTR(err); + return NULL; } /* handle pointer-returning APIs' error handling */ @@ -476,11 +516,7 @@ static inline void *libbpf_ptr(void *ret) if (IS_ERR(ret)) errno = -PTR_ERR(ret); - if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS) - return IS_ERR(ret) ? NULL : ret; - - /* legacy: pass-through original pointer */ - return ret; + return IS_ERR(ret) ? NULL : ret; } static inline bool str_is_empty(const char *s) @@ -515,4 +551,29 @@ 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); + +struct usdt_manager *usdt_manager_new(struct bpf_object *obj); +void usdt_manager_free(struct usdt_manager *man); +struct bpf_link * usdt_manager_attach_usdt(struct usdt_manager *man, + const struct bpf_program *prog, + pid_t pid, const char *path, + const char *usdt_provider, const char *usdt_name, + __u64 usdt_cookie); + +static inline bool is_pow_of_2(size_t x) +{ + return x && (x & (x - 1)) == 0; +} + +#define PROG_LOAD_ATTEMPTS 5 +int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts); + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index 5ba5c9beccfa..1e1be467bede 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -20,6 +20,11 @@ extern "C" { #endif +/* As of libbpf 1.0 libbpf_set_strict_mode() and enum libbpf_struct_mode have + * no effect. But they are left in libbpf_legacy.h so that applications that + * prepared for libbpf 1.0 before final release by using + * libbpf_set_strict_mode() still work with libbpf 1.0+ without any changes. + */ enum libbpf_strict_mode { /* Turn on all supported strict features of libbpf to simulate libbpf * v1.0 behavior. @@ -45,7 +50,6 @@ enum libbpf_strict_mode { * (positive) error code. */ LIBBPF_STRICT_DIRECT_ERRS = 0x02, - /* * Enforce strict BPF program section (SEC()) names. * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were @@ -55,6 +59,10 @@ 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, /* @@ -63,12 +71,67 @@ enum libbpf_strict_mode { * Clients can maintain it on their own if it is valuable for them. */ LIBBPF_STRICT_NO_OBJECT_LIST = 0x08, + /* + * Automatically bump RLIMIT_MEMLOCK using setrlimit() before the + * first BPF program or map creation operation. This is done only if + * kernel is too old to support memcg-based memory accounting for BPF + * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY, + * but it can be overriden with libbpf_set_memlock_rlim() API. + * Note that libbpf_set_memlock_rlim() needs to be called before + * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load() + * operation. + */ + 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, }; LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); +/** + * @brief **libbpf_get_error()** extracts the error code from the passed + * pointer + * @param ptr pointer returned from libbpf API function + * @return error code; or 0 if no error occured + * + * Note, as of libbpf 1.0 this function is not necessary and not recommended + * to be used. Libbpf doesn't return error code embedded into the pointer + * itself. Instead, NULL is returned on error and error code is passed through + * thread-local errno variable. **libbpf_get_error()** is just returning -errno + * value if it receives NULL, which is correct only if errno hasn't been + * modified between libbpf API call and corresponding **libbpf_get_error()** + * call. Prefer to check return for NULL and use errno directly. + * + * This API is left in libbpf 1.0 to allow applications that were 1.0-ready + * before final libbpf 1.0 without needing to change them. + */ +LIBBPF_API long libbpf_get_error(const void *ptr); + +#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 struct btf *libbpf_find_kernel_btf(void); + +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" */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 68f2dbf364aa..f3a8e8e74eb8 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -17,72 +17,63 @@ #include "libbpf.h" #include "libbpf_internal.h" -static bool grep(const char *buffer, const char *pattern) +static int probe_prog_load(enum bpf_prog_type prog_type, + const struct bpf_insn *insns, size_t insns_cnt, + char *log_buf, size_t log_buf_sz) { - return !!strstr(buffer, pattern); -} - -static int get_vendor_id(int ifindex) -{ - char ifname[IF_NAMESIZE], path[64], buf[8]; - ssize_t len; - int fd; - - if (!if_indextoname(ifindex, ifname)) - return -1; - - snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname); - - fd = open(path, O_RDONLY | O_CLOEXEC); - if (fd < 0) - return -1; - - len = read(fd, buf, sizeof(buf)); - close(fd); - if (len < 0) - return -1; - if (len >= (ssize_t)sizeof(buf)) - return -1; - buf[len] = '\0'; - - return strtol(buf, NULL, 0); -} - -static int get_kernel_version(void) -{ - int version, subversion, patchlevel; - struct utsname utsn; - - /* Return 0 on failure, and attempt to probe with empty kversion */ - if (uname(&utsn)) - return 0; - - if (sscanf(utsn.release, "%d.%d.%d", - &version, &subversion, &patchlevel) != 3) - return 0; - - return (version << 16) + (subversion << 8) + patchlevel; -} - -static void -probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, - size_t insns_cnt, char *buf, size_t buf_len, __u32 ifindex) -{ - struct bpf_load_program_attr xattr = {}; - int fd; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_sz, + .log_level = log_buf ? 1 : 0, + ); + int fd, err, exp_err = 0; + const char *exp_msg = NULL; + char buf[4096]; switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: - xattr.expected_attach_type = BPF_CGROUP_INET4_CONNECT; + opts.expected_attach_type = BPF_CGROUP_INET4_CONNECT; break; case BPF_PROG_TYPE_CGROUP_SOCKOPT: - xattr.expected_attach_type = BPF_CGROUP_GETSOCKOPT; + opts.expected_attach_type = BPF_CGROUP_GETSOCKOPT; break; case BPF_PROG_TYPE_SK_LOOKUP: - xattr.expected_attach_type = BPF_SK_LOOKUP; + opts.expected_attach_type = BPF_SK_LOOKUP; break; case BPF_PROG_TYPE_KPROBE: - xattr.kern_version = get_kernel_version(); + opts.kern_version = get_kernel_version(); + break; + case BPF_PROG_TYPE_LIRC_MODE2: + opts.expected_attach_type = BPF_LIRC_MODE2; + break; + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: + opts.log_buf = buf; + opts.log_size = sizeof(buf); + opts.log_level = 1; + if (prog_type == BPF_PROG_TYPE_TRACING) + opts.expected_attach_type = BPF_TRACE_FENTRY; + else + opts.expected_attach_type = BPF_MODIFY_RETURN; + opts.attach_btf_id = 1; + + exp_err = -EINVAL; + exp_msg = "attach_btf_id 1 is not a function"; + break; + case BPF_PROG_TYPE_EXT: + opts.log_buf = buf; + opts.log_size = sizeof(buf); + opts.log_level = 1; + opts.attach_btf_id = 1; + + exp_err = -EINVAL; + exp_msg = "Cannot replace kernel functions"; + break; + case BPF_PROG_TYPE_SYSCALL: + opts.prog_flags = BPF_F_SLEEPABLE; + break; + case BPF_PROG_TYPE_STRUCT_OPS: + exp_err = -524; /* -ENOTSUPP */ break; case BPF_PROG_TYPE_UNSPEC: case BPF_PROG_TYPE_SOCKET_FILTER: @@ -103,44 +94,42 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_LWT_SEG6LOCAL: - case BPF_PROG_TYPE_LIRC_MODE2: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: - case BPF_PROG_TYPE_TRACING: - case BPF_PROG_TYPE_STRUCT_OPS: - case BPF_PROG_TYPE_EXT: - case BPF_PROG_TYPE_LSM: - default: break; + default: + return -EOPNOTSUPP; } - xattr.prog_type = prog_type; - xattr.insns = insns; - xattr.insns_cnt = insns_cnt; - xattr.license = "GPL"; - xattr.prog_ifindex = ifindex; - - fd = bpf_load_program_xattr(&xattr, buf, buf_len); + fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts); + err = -errno; if (fd >= 0) close(fd); + if (exp_err) { + if (fd >= 0 || err != exp_err) + return 0; + if (exp_msg && !strstr(buf, exp_msg)) + return 0; + return 1; + } + return fd >= 0 ? 1 : 0; } -bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex) +int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts) { - struct bpf_insn insns[2] = { + struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN() }; + const size_t insn_cnt = ARRAY_SIZE(insns); + int ret; - if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS) - /* nfp returns -EINVAL on exit(0) with TC offload */ - insns[0].imm = 2; + if (opts) + return libbpf_err(-EINVAL); - errno = 0; - probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex); - - return errno != EINVAL && errno != EOPNOTSUPP; + ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0); + return libbpf_err(ret); } int libbpf__load_raw_btf(const char *raw_types, size_t types_len, @@ -166,7 +155,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len); memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len); - btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false); + btf_fd = bpf_btf_load(raw_btf, btf_len, NULL); free(raw_btf); return btf_fd; @@ -199,17 +188,16 @@ static int load_local_storage_btf(void) strs, sizeof(strs)); } -bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) +static int probe_map_create(enum bpf_map_type map_type) { - int key_size, value_size, max_entries, map_flags; + LIBBPF_OPTS(bpf_map_create_opts, opts); + int key_size, value_size, max_entries; __u32 btf_key_type_id = 0, btf_value_type_id = 0; - struct bpf_create_map_attr attr = {}; - int fd = -1, btf_fd = -1, fd_inner; + int fd = -1, btf_fd = -1, fd_inner = -1, exp_err = 0, err = 0; key_size = sizeof(__u32); value_size = sizeof(__u32); max_entries = 1; - map_flags = 0; switch (map_type) { case BPF_MAP_TYPE_STACK_TRACE: @@ -218,7 +206,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_LPM_TRIE: key_size = sizeof(__u64); value_size = sizeof(__u64); - map_flags = BPF_F_NO_PREALLOC; + opts.map_flags = BPF_F_NO_PREALLOC; break; case BPF_MAP_TYPE_CGROUP_STORAGE: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: @@ -237,17 +225,26 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) btf_value_type_id = 3; value_size = 8; max_entries = 0; - map_flags = BPF_F_NO_PREALLOC; + opts.map_flags = BPF_F_NO_PREALLOC; btf_fd = load_local_storage_btf(); if (btf_fd < 0) - return false; + return btf_fd; break; case BPF_MAP_TYPE_RINGBUF: + case BPF_MAP_TYPE_USER_RINGBUF: key_size = 0; value_size = 0; max_entries = 4096; break; - case BPF_MAP_TYPE_UNSPEC: + case BPF_MAP_TYPE_STRUCT_OPS: + /* we'll get -ENOTSUPP for invalid BTF type ID for struct_ops */ + opts.btf_vmlinux_value_type_id = 1; + exp_err = -524; /* -ENOTSUPP */ + break; + case BPF_MAP_TYPE_BLOOM_FILTER: + key_size = 0; + max_entries = 1; + break; case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PROG_ARRAY: @@ -266,95 +263,101 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_XSKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: - case BPF_MAP_TYPE_STRUCT_OPS: - default: break; + case BPF_MAP_TYPE_UNSPEC: + default: + return -EOPNOTSUPP; } if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS || map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { - /* TODO: probe for device, once libbpf has a function to create - * map-in-map for offload - */ - if (ifindex) - return false; - - fd_inner = bpf_create_map(BPF_MAP_TYPE_HASH, - sizeof(__u32), sizeof(__u32), 1, 0); + fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, + sizeof(__u32), sizeof(__u32), 1, NULL); if (fd_inner < 0) - return false; - fd = bpf_create_map_in_map(map_type, NULL, sizeof(__u32), - fd_inner, 1, 0); - close(fd_inner); - } else { - /* Note: No other restriction on map type probes for offload */ - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = value_size; - attr.max_entries = max_entries; - attr.map_flags = map_flags; - attr.map_ifindex = ifindex; - if (btf_fd >= 0) { - attr.btf_fd = btf_fd; - attr.btf_key_type_id = btf_key_type_id; - attr.btf_value_type_id = btf_value_type_id; - } - - fd = bpf_create_map_xattr(&attr); + goto cleanup; + + opts.inner_map_fd = fd_inner; + } + + if (btf_fd >= 0) { + opts.btf_fd = btf_fd; + opts.btf_key_type_id = btf_key_type_id; + opts.btf_value_type_id = btf_value_type_id; } + + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts); + err = -errno; + +cleanup: if (fd >= 0) close(fd); + if (fd_inner >= 0) + close(fd_inner); if (btf_fd >= 0) close(btf_fd); - return fd >= 0; + if (exp_err) + return fd < 0 && err == exp_err ? 1 : 0; + else + return fd >= 0 ? 1 : 0; } -bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, - __u32 ifindex) +int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts) { - struct bpf_insn insns[2] = { - BPF_EMIT_CALL(id), - BPF_EXIT_INSN() - }; - char buf[4096] = {}; - bool res; - - probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), - ifindex); - res = !grep(buf, "invalid func ") && !grep(buf, "unknown func "); - - if (ifindex) { - switch (get_vendor_id(ifindex)) { - case 0x19ee: /* Netronome specific */ - res = res && !grep(buf, "not supported by FW") && - !grep(buf, "unsupported function id"); - break; - default: - break; - } - } + int ret; - return res; + if (opts) + return libbpf_err(-EINVAL); + + ret = probe_map_create(map_type); + return libbpf_err(ret); } -/* - * Probe for availability of kernel commit (5.3): - * - * c04c0d2b968a ("bpf: increase complexity limit and maximum program size") - */ -bool bpf_probe_large_insn_limit(__u32 ifindex) +int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helper_id, + const void *opts) { - struct bpf_insn insns[BPF_MAXINSNS + 1]; - int i; + struct bpf_insn insns[] = { + BPF_EMIT_CALL((__u32)helper_id), + BPF_EXIT_INSN(), + }; + const size_t insn_cnt = ARRAY_SIZE(insns); + char buf[4096]; + int ret; - for (i = 0; i < BPF_MAXINSNS; i++) - insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1); - insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); + if (opts) + return libbpf_err(-EINVAL); - errno = 0; - probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0, - ifindex); + /* we can't successfully load all prog types to check for BPF helper + * support, so bail out with -EOPNOTSUPP error + */ + switch (prog_type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_LSM: + case BPF_PROG_TYPE_STRUCT_OPS: + return -EOPNOTSUPP; + default: + break; + } - return errno != E2BIG && errno != EINVAL; + buf[0] = '\0'; + ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf)); + if (ret < 0) + return libbpf_err(ret); + + /* If BPF verifier doesn't recognize BPF helper ID (enum bpf_func_id) + * at all, it will emit something like "invalid func unknown#181". + * If BPF verifier recognizes BPF helper but it's not supported for + * given BPF program type, it will emit "unknown func bpf_sys_bpf#166". + * In both cases, provided combination of BPF program type and BPF + * helper is not supported by the kernel. + * In all other cases, probe_prog_load() above will either succeed (e.g., + * because BPF helper happens to accept no input arguments or it + * accepts one input argument and initial PTR_TO_CTX is fine for + * that), or we'll get some more specific BPF verifier error about + * some unsatisfied conditions. + */ + if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func "))) + return 0; + return 1; /* assume supported */ } diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index dd56d76f291c..e944f5bce728 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -3,7 +3,7 @@ #ifndef __LIBBPF_VERSION_H #define __LIBBPF_VERSION_H -#define LIBBPF_MAJOR_VERSION 0 -#define LIBBPF_MINOR_VERSION 6 +#define LIBBPF_MAJOR_VERSION 1 +#define LIBBPF_MINOR_VERSION 1 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index f677dccdeae4..4ac02c28e152 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -210,6 +210,7 @@ void bpf_linker__free(struct bpf_linker *linker) } free(linker->secs); + free(linker->glob_syms); free(linker); } @@ -696,11 +697,6 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, return err; } -static bool is_pow_of_2(size_t x) -{ - return x && (x & (x - 1)) == 0; -} - static int linker_sanity_check_elf(struct src_obj *obj) { struct src_sec *sec; @@ -1339,6 +1335,7 @@ recur: case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: case BTF_KIND_FWD: case BTF_KIND_FUNC: case BTF_KIND_VAR: @@ -1361,6 +1358,7 @@ recur: case BTF_KIND_INT: case BTF_KIND_FLOAT: case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: /* ignore encoding for int and enum values for enum */ if (t1->size != t2->size) { pr_warn("global '%s': incompatible %s '%s' size %u and %u\n", @@ -1999,7 +1997,7 @@ add_sym: static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *obj) { struct src_sec *src_symtab = &obj->secs[obj->symtab_sec_idx]; - struct dst_sec *dst_symtab = &linker->secs[linker->symtab_sec_idx]; + struct dst_sec *dst_symtab; int i, err; for (i = 1; i < obj->sec_cnt; i++) { @@ -2032,6 +2030,9 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob return -1; } + /* add_dst_sec() above could have invalidated linker->secs */ + dst_symtab = &linker->secs[linker->symtab_sec_idx]; + /* shdr->sh_link points to SYMTAB */ dst_sec->shdr->sh_link = linker->symtab_sec_idx; @@ -2650,6 +2651,7 @@ static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name, static int finalize_btf(struct bpf_linker *linker) { + LIBBPF_OPTS(btf_dedup_opts, opts); struct btf *btf = linker->btf; const void *raw_data; int i, j, id, err; @@ -2686,7 +2688,8 @@ static int finalize_btf(struct bpf_linker *linker) return err; } - err = btf__dedup(linker->btf, linker->btf_ext, NULL); + opts.btf_ext = linker->btf_ext; + err = btf__dedup(linker->btf, &opts); if (err) { pr_warn("BTF dedup failed: %d\n", err); return err; diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 39f25e09b51e..35104580870c 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -27,6 +27,14 @@ typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t, void *cookie); +struct xdp_link_info { + __u32 prog_id; + __u32 drv_prog_id; + __u32 hw_prog_id; + __u32 skb_prog_id; + __u8 attach_mode; +}; + struct xdp_id_md { int ifindex; __u32 flags; @@ -87,29 +95,75 @@ 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 = 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 = -errno; + 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 +184,8 @@ start: libbpf_nla_dump_errormsg(nh); goto done; case NLMSG_DONE: - return 0; + ret = 0; + goto done; default: break; } @@ -142,15 +197,17 @@ 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; } @@ -217,29 +274,26 @@ 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_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, - const struct bpf_xdp_set_link_opts *opts) +int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts) { - int old_fd = -1, ret; + int old_prog_fd, err; - if (!OPTS_VALID(opts, bpf_xdp_set_link_opts)) + if (!OPTS_VALID(opts, bpf_xdp_attach_opts)) return libbpf_err(-EINVAL); - if (OPTS_HAS(opts, old_fd)) { - old_fd = OPTS_GET(opts, old_fd, -1); + old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + if (old_prog_fd) flags |= XDP_FLAGS_REPLACE; - } + else + old_prog_fd = -1; - ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, old_fd, flags); - return libbpf_err(ret); + err = __bpf_set_link_xdp_fd_replace(ifindex, prog_fd, old_prog_fd, flags); + return libbpf_err(err); } -int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) +int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *opts) { - int ret; - - ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags); - return libbpf_err(ret); + return bpf_xdp_attach(ifindex, -1, flags, opts); } static int __dump_link_nlmsg(struct nlmsghdr *nlh, @@ -303,70 +357,70 @@ 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 (!OPTS_VALID(opts, bpf_xdp_query_opts)) + return libbpf_err(-EINVAL); - if (flags & ~XDP_FLAGS_MASK || !info_size) + 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_xdp_query_id(int ifindex, int flags, __u32 *prog_id) { + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + int ret; + + ret = bpf_xdp_query(ifindex, flags, &opts); + if (ret) + return libbpf_err(ret); + flags &= XDP_FLAGS_MODES; - 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 (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) -{ - struct xdp_link_info info; - int ret; - - ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags); - if (!ret) - *prog_id = get_xdp_id(&info, flags); - - return libbpf_err(ret); -} typedef int (*qdisc_config_t)(struct libbpf_nla_req *req); @@ -533,11 +587,12 @@ static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd) { - struct bpf_prog_info info = {}; + struct bpf_prog_info info; __u32 info_len = sizeof(info); char name[256]; int len, ret; + memset(&info, 0, info_len); ret = bpf_obj_get_info_by_fd(fd, &info, &info_len); if (ret < 0) return ret; diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index f57e77a6e40f..3900d052ed19 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -32,7 +32,7 @@ static struct nlattr *nla_next(const struct nlattr *nla, int *remaining) static int nla_ok(const struct nlattr *nla, int remaining) { - return remaining >= sizeof(*nla) && + return remaining >= (int)sizeof(*nla) && nla->nla_len >= sizeof(*nla) && nla->nla_len <= remaining; } diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index b5b8956a1be8..c4b0e81ae293 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -1,6 +1,60 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2019 Facebook */ +#ifdef __KERNEL__ +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/string.h> +#include <linux/bpf_verifier.h> +#include "relo_core.h" + +static const char *btf_kind_str(const struct btf_type *t) +{ + return btf_type_str(t); +} + +static bool is_ldimm64_insn(struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, u32 id, u32 *res_id) +{ + return btf_type_skip_modifiers(btf, id, res_id); +} + +static const char *btf__name_by_offset(const struct btf *btf, u32 offset) +{ + return btf_name_by_offset(btf, offset); +} + +static s64 btf__resolve_size(const struct btf *btf, u32 type_id) +{ + const struct btf_type *t; + int size; + + t = btf_type_by_id(btf, type_id); + t = btf_resolve_size(btf, t, &size); + if (IS_ERR(t)) + return PTR_ERR(t); + return size; +} + +enum libbpf_print_level { + LIBBPF_WARN, + LIBBPF_INFO, + LIBBPF_DEBUG, +}; + +#undef pr_warn +#undef pr_info +#undef pr_debug +#define pr_warn(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define pr_info(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define pr_debug(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define libbpf_print(level, fmt, ...) bpf_log((void *)prog_name, fmt, ##__VA_ARGS__) +#else #include <stdio.h> #include <string.h> #include <errno.h> @@ -12,33 +66,7 @@ #include "btf.h" #include "str_error.h" #include "libbpf_internal.h" - -#define BPF_CORE_SPEC_MAX_LEN 64 - -/* represents BPF CO-RE field or array element accessor */ -struct bpf_core_accessor { - __u32 type_id; /* struct/union type or array element type */ - __u32 idx; /* field index or array index */ - const char *name; /* field name or NULL for array accessor */ -}; - -struct bpf_core_spec { - const struct btf *btf; - /* high-level spec: named fields and array indices only */ - struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; - /* original unresolved (no skip_mods_or_typedefs) root type ID */ - __u32 root_type_id; - /* CO-RE relocation kind */ - enum bpf_core_relo_kind relo_kind; - /* high-level spec length */ - int len; - /* raw, low-level spec: 1-to-1 with accessor spec string */ - int raw_spec[BPF_CORE_SPEC_MAX_LEN]; - /* raw spec length */ - int raw_len; - /* field bit offset represented by spec */ - __u32 bit_offset; -}; +#endif static bool is_flex_arr(const struct btf *btf, const struct bpf_core_accessor *acc, @@ -51,25 +79,26 @@ static bool is_flex_arr(const struct btf *btf, return false; /* has to be the last member of enclosing struct */ - t = btf__type_by_id(btf, acc->type_id); + t = btf_type_by_id(btf, acc->type_id); return acc->idx == btf_vlen(t) - 1; } static const char *core_relo_kind_str(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_FIELD_BYTE_OFFSET: return "byte_off"; - case BPF_FIELD_BYTE_SIZE: return "byte_sz"; - case BPF_FIELD_EXISTS: return "field_exists"; - case BPF_FIELD_SIGNED: return "signed"; - case BPF_FIELD_LSHIFT_U64: return "lshift_u64"; - case BPF_FIELD_RSHIFT_U64: return "rshift_u64"; - case BPF_TYPE_ID_LOCAL: return "local_type_id"; - case BPF_TYPE_ID_TARGET: return "target_type_id"; - case BPF_TYPE_EXISTS: return "type_exists"; - case BPF_TYPE_SIZE: return "type_size"; - case BPF_ENUMVAL_EXISTS: return "enumval_exists"; - case BPF_ENUMVAL_VALUE: return "enumval_value"; + case BPF_CORE_FIELD_BYTE_OFFSET: return "byte_off"; + case BPF_CORE_FIELD_BYTE_SIZE: return "byte_sz"; + case BPF_CORE_FIELD_EXISTS: return "field_exists"; + case BPF_CORE_FIELD_SIGNED: return "signed"; + case BPF_CORE_FIELD_LSHIFT_U64: return "lshift_u64"; + case BPF_CORE_FIELD_RSHIFT_U64: return "rshift_u64"; + case BPF_CORE_TYPE_ID_LOCAL: return "local_type_id"; + case BPF_CORE_TYPE_ID_TARGET: return "target_type_id"; + case BPF_CORE_TYPE_EXISTS: return "type_exists"; + case BPF_CORE_TYPE_MATCHES: return "type_matches"; + case BPF_CORE_TYPE_SIZE: return "type_size"; + case BPF_CORE_ENUMVAL_EXISTS: return "enumval_exists"; + case BPF_CORE_ENUMVAL_VALUE: return "enumval_value"; default: return "unknown"; } } @@ -77,12 +106,12 @@ static const char *core_relo_kind_str(enum bpf_core_relo_kind kind) static bool core_relo_is_field_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_FIELD_BYTE_OFFSET: - case BPF_FIELD_BYTE_SIZE: - case BPF_FIELD_EXISTS: - case BPF_FIELD_SIGNED: - case BPF_FIELD_LSHIFT_U64: - case BPF_FIELD_RSHIFT_U64: + case BPF_CORE_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_EXISTS: + case BPF_CORE_FIELD_SIGNED: + case BPF_CORE_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: return true; default: return false; @@ -92,10 +121,11 @@ static bool core_relo_is_field_based(enum bpf_core_relo_kind kind) static bool core_relo_is_type_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_TYPE_ID_LOCAL: - case BPF_TYPE_ID_TARGET: - case BPF_TYPE_EXISTS: - case BPF_TYPE_SIZE: + case BPF_CORE_TYPE_ID_LOCAL: + case BPF_CORE_TYPE_ID_TARGET: + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_MATCHES: + case BPF_CORE_TYPE_SIZE: return true; default: return false; @@ -105,14 +135,94 @@ static bool core_relo_is_type_based(enum bpf_core_relo_kind kind) static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_ENUMVAL_EXISTS: - case BPF_ENUMVAL_VALUE: + case BPF_CORE_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_VALUE: return true; default: return false; } } +int __bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id, int level) +{ + const struct btf_type *local_type, *targ_type; + int depth = 32; /* max recursion depth */ + + /* caller made sure that names match (ignoring flavor suffix) */ + local_type = btf_type_by_id(local_btf, local_id); + targ_type = btf_type_by_id(targ_btf, targ_id); + if (!btf_kind_core_compat(local_type, targ_type)) + return 0; + +recur: + depth--; + if (depth < 0) + return -EINVAL; + + local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_type || !targ_type) + return -EINVAL; + + if (!btf_kind_core_compat(local_type, targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_UNKN: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + case BTF_KIND_ENUM64: + return 1; + case BTF_KIND_INT: + /* just reject deprecated bitfield-like integers; all other + * integers are by default compatible between each other + */ + return btf_int_offset(local_type) == 0 && btf_int_offset(targ_type) == 0; + case BTF_KIND_PTR: + local_id = local_type->type; + targ_id = targ_type->type; + goto recur; + case BTF_KIND_ARRAY: + local_id = btf_array(local_type)->type; + targ_id = btf_array(targ_type)->type; + goto recur; + case BTF_KIND_FUNC_PROTO: { + struct btf_param *local_p = btf_params(local_type); + struct btf_param *targ_p = btf_params(targ_type); + __u16 local_vlen = btf_vlen(local_type); + __u16 targ_vlen = btf_vlen(targ_type); + int i, err; + + if (local_vlen != targ_vlen) + return 0; + + for (i = 0; i < local_vlen; i++, local_p++, targ_p++) { + if (level <= 0) + return -EINVAL; + + skip_mods_and_typedefs(local_btf, local_p->type, &local_id); + skip_mods_and_typedefs(targ_btf, targ_p->type, &targ_id); + err = __bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id, + level - 1); + if (err <= 0) + return err; + } + + /* tail recurse for return type check */ + skip_mods_and_typedefs(local_btf, local_type->type, &local_id); + skip_mods_and_typedefs(targ_btf, targ_type->type, &targ_id); + goto recur; + } + default: + pr_warn("unexpected kind %s relocated, local [%d], target [%d]\n", + btf_kind_str(local_type), local_id, targ_id); + return 0; + } +} + /* * Turn bpf_core_relo into a low- and high-level spec representation, * validating correctness along the way, as well as calculating resulting @@ -139,40 +249,39 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) * just a parsed access string representation): [0, 1, 2, 3]. * * High-level spec will capture only 3 points: - * - intial zero-index access by pointer (&s->... is the same as &s[0]...); + * - initial zero-index access by pointer (&s->... is the same as &s[0]...); * - field 'a' access (corresponds to '2' in low-level spec); * - array element #3 access (corresponds to '3' in low-level spec). * - * Type-based relocations (TYPE_EXISTS/TYPE_SIZE, + * Type-based relocations (TYPE_EXISTS/TYPE_MATCHES/TYPE_SIZE, * TYPE_ID_LOCAL/TYPE_ID_TARGET) don't capture any field information. Their * spec and raw_spec are kept empty. * * Enum value-based relocations (ENUMVAL_EXISTS/ENUMVAL_VALUE) use access * string to specify enumerator's value index that need to be relocated. */ -static int bpf_core_parse_spec(const struct btf *btf, - __u32 type_id, - const char *spec_str, - enum bpf_core_relo_kind relo_kind, - struct bpf_core_spec *spec) +int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, + const struct bpf_core_relo *relo, + struct bpf_core_spec *spec) { int access_idx, parsed_len, i; struct bpf_core_accessor *acc; const struct btf_type *t; - const char *name; - __u32 id; + const char *name, *spec_str; + __u32 id, name_off; __s64 sz; + spec_str = btf__name_by_offset(btf, relo->access_str_off); if (str_is_empty(spec_str) || *spec_str == ':') return -EINVAL; memset(spec, 0, sizeof(*spec)); spec->btf = btf; - spec->root_type_id = type_id; - spec->relo_kind = relo_kind; + spec->root_type_id = relo->type_id; + spec->relo_kind = relo->kind; /* type-based relocations don't have a field access string */ - if (core_relo_is_type_based(relo_kind)) { + if (core_relo_is_type_based(relo->kind)) { if (strcmp(spec_str, "0")) return -EINVAL; return 0; @@ -193,7 +302,7 @@ static int bpf_core_parse_spec(const struct btf *btf, if (spec->raw_len == 0) return -EINVAL; - t = skip_mods_and_typedefs(btf, type_id, &id); + t = skip_mods_and_typedefs(btf, relo->type_id, &id); if (!t) return -EINVAL; @@ -203,16 +312,18 @@ static int bpf_core_parse_spec(const struct btf *btf, acc->idx = access_idx; spec->len++; - if (core_relo_is_enumval_based(relo_kind)) { - if (!btf_is_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t)) + if (core_relo_is_enumval_based(relo->kind)) { + if (!btf_is_any_enum(t) || spec->raw_len > 1 || access_idx >= btf_vlen(t)) return -EINVAL; /* record enumerator name in a first accessor */ - acc->name = btf__name_by_offset(btf, btf_enum(t)[access_idx].name_off); + name_off = btf_is_enum(t) ? btf_enum(t)[access_idx].name_off + : btf_enum64(t)[access_idx].name_off; + acc->name = btf__name_by_offset(btf, name_off); return 0; } - if (!core_relo_is_field_based(relo_kind)) + if (!core_relo_is_field_based(relo->kind)) return -EINVAL; sz = btf__resolve_size(btf, id); @@ -272,8 +383,8 @@ static int bpf_core_parse_spec(const struct btf *btf, return sz; spec->bit_offset += access_idx * sz * 8; } else { - pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n", - type_id, spec_str, i, id, btf_kind_str(t)); + pr_warn("prog '%s': relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n", + prog_name, relo->type_id, spec_str, i, id, btf_kind_str(t)); return -EINVAL; } } @@ -313,7 +424,7 @@ recur: if (btf_is_composite(local_type) && btf_is_composite(targ_type)) return 1; - if (btf_kind(local_type) != btf_kind(targ_type)) + if (!btf_kind_core_compat(local_type, targ_type)) return 0; switch (btf_kind(local_type)) { @@ -321,6 +432,7 @@ recur: case BTF_KIND_FLOAT: return 1; case BTF_KIND_FWD: + case BTF_KIND_ENUM64: case BTF_KIND_ENUM: { const char *local_name, *targ_name; size_t local_len, targ_len; @@ -346,8 +458,6 @@ recur: targ_id = btf_array(targ_type)->type; goto recur; default: - pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n", - btf_kind(local_type), local_id, targ_id); return 0; } } @@ -388,7 +498,7 @@ static int bpf_core_match_member(const struct btf *local_btf, return 0; local_id = local_acc->type_id; - local_type = btf__type_by_id(local_btf, local_id); + local_type = btf_type_by_id(local_btf, local_id); local_member = btf_members(local_type) + local_acc->idx; local_name = btf__name_by_offset(local_btf, local_member->name_off); @@ -452,6 +562,7 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, const struct bpf_core_accessor *local_acc; struct bpf_core_accessor *targ_acc; int i, sz, matched; + __u32 name_off; memset(targ_spec, 0, sizeof(*targ_spec)); targ_spec->btf = targ_btf; @@ -459,9 +570,14 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, targ_spec->relo_kind = local_spec->relo_kind; if (core_relo_is_type_based(local_spec->relo_kind)) { - return bpf_core_types_are_compat(local_spec->btf, - local_spec->root_type_id, - targ_btf, targ_id); + if (local_spec->relo_kind == BPF_CORE_TYPE_MATCHES) + return bpf_core_types_match(local_spec->btf, + local_spec->root_type_id, + targ_btf, targ_id); + else + return bpf_core_types_are_compat(local_spec->btf, + local_spec->root_type_id, + targ_btf, targ_id); } local_acc = &local_spec->spec[0]; @@ -469,18 +585,22 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, if (core_relo_is_enumval_based(local_spec->relo_kind)) { size_t local_essent_len, targ_essent_len; - const struct btf_enum *e; const char *targ_name; /* has to resolve to an enum */ targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, &targ_id); - if (!btf_is_enum(targ_type)) + if (!btf_is_any_enum(targ_type)) return 0; local_essent_len = bpf_core_essential_name_len(local_acc->name); - for (i = 0, e = btf_enum(targ_type); i < btf_vlen(targ_type); i++, e++) { - targ_name = btf__name_by_offset(targ_spec->btf, e->name_off); + for (i = 0; i < btf_vlen(targ_type); i++) { + if (btf_is_enum(targ_type)) + name_off = btf_enum(targ_type)[i].name_off; + else + name_off = btf_enum64(targ_type)[i].name_off; + + targ_name = btf__name_by_offset(targ_spec->btf, name_off); targ_essent_len = bpf_core_essential_name_len(targ_name); if (targ_essent_len != local_essent_len) continue; @@ -558,7 +678,7 @@ static int bpf_core_spec_match(struct bpf_core_spec *local_spec, static int bpf_core_calc_field_relo(const char *prog_name, const struct bpf_core_relo *relo, const struct bpf_core_spec *spec, - __u32 *val, __u32 *field_sz, __u32 *type_id, + __u64 *val, __u32 *field_sz, __u32 *type_id, bool *validate) { const struct bpf_core_accessor *acc; @@ -571,7 +691,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, *field_sz = 0; - if (relo->kind == BPF_FIELD_EXISTS) { + if (relo->kind == BPF_CORE_FIELD_EXISTS) { *val = spec ? 1 : 0; return 0; } @@ -580,11 +700,11 @@ static int bpf_core_calc_field_relo(const char *prog_name, return -EUCLEAN; /* request instruction poisoning */ acc = &spec->spec[spec->len - 1]; - t = btf__type_by_id(spec->btf, acc->type_id); + t = btf_type_by_id(spec->btf, acc->type_id); /* a[n] accessor needs special handling */ if (!acc->name) { - if (relo->kind == BPF_FIELD_BYTE_OFFSET) { + if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) { *val = spec->bit_offset / 8; /* remember field size for load/store mem size */ sz = btf__resolve_size(spec->btf, acc->type_id); @@ -592,7 +712,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, return -EINVAL; *field_sz = sz; *type_id = acc->type_id; - } else if (relo->kind == BPF_FIELD_BYTE_SIZE) { + } else if (relo->kind == BPF_CORE_FIELD_BYTE_SIZE) { sz = btf__resolve_size(spec->btf, acc->type_id); if (sz < 0) return -EINVAL; @@ -644,36 +764,35 @@ static int bpf_core_calc_field_relo(const char *prog_name, *validate = !bitfield; switch (relo->kind) { - case BPF_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_OFFSET: *val = byte_off; if (!bitfield) { *field_sz = byte_sz; *type_id = field_type_id; } break; - case BPF_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_BYTE_SIZE: *val = byte_sz; break; - case BPF_FIELD_SIGNED: - /* enums will be assumed unsigned */ - *val = btf_is_enum(mt) || + case BPF_CORE_FIELD_SIGNED: + *val = (btf_is_any_enum(mt) && BTF_INFO_KFLAG(mt->info)) || (btf_int_encoding(mt) & BTF_INT_SIGNED); if (validate) *validate = true; /* signedness is never ambiguous */ break; - case BPF_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_LSHIFT_U64: #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ *val = 64 - (bit_off + bit_sz - byte_off * 8); #else *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8); #endif break; - case BPF_FIELD_RSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: *val = 64 - bit_sz; if (validate) *validate = true; /* right shift is never ambiguous */ break; - case BPF_FIELD_EXISTS: + case BPF_CORE_FIELD_EXISTS: default: return -EOPNOTSUPP; } @@ -683,10 +802,14 @@ static int bpf_core_calc_field_relo(const char *prog_name, static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, const struct bpf_core_spec *spec, - __u32 *val) + __u64 *val, bool *validate) { __s64 sz; + /* by default, always check expected value in bpf_insn */ + if (validate) + *validate = true; + /* type-based relos return zero when target type is not found */ if (!spec) { *val = 0; @@ -694,20 +817,26 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, } switch (relo->kind) { - case BPF_TYPE_ID_TARGET: + case BPF_CORE_TYPE_ID_TARGET: *val = spec->root_type_id; + /* type ID, embedded in bpf_insn, might change during linking, + * so enforcing it is pointless + */ + if (validate) + *validate = false; break; - case BPF_TYPE_EXISTS: + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_MATCHES: *val = 1; break; - case BPF_TYPE_SIZE: + case BPF_CORE_TYPE_SIZE: sz = btf__resolve_size(spec->btf, spec->root_type_id); if (sz < 0) return -EINVAL; *val = sz; break; - case BPF_TYPE_ID_LOCAL: - /* BPF_TYPE_ID_LOCAL is handled specially and shouldn't get here */ + case BPF_CORE_TYPE_ID_LOCAL: + /* BPF_CORE_TYPE_ID_LOCAL is handled specially and shouldn't get here */ default: return -EOPNOTSUPP; } @@ -717,21 +846,22 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, const struct bpf_core_spec *spec, - __u32 *val) + __u64 *val) { const struct btf_type *t; - const struct btf_enum *e; switch (relo->kind) { - case BPF_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_EXISTS: *val = spec ? 1 : 0; break; - case BPF_ENUMVAL_VALUE: + case BPF_CORE_ENUMVAL_VALUE: if (!spec) return -EUCLEAN; /* request instruction poisoning */ - t = btf__type_by_id(spec->btf, spec->spec[0].type_id); - e = btf_enum(t) + spec->spec[0].idx; - *val = e->val; + t = btf_type_by_id(spec->btf, spec->spec[0].type_id); + if (btf_is_enum(t)) + *val = btf_enum(t)[spec->spec[0].idx].val; + else + *val = btf_enum64_value(btf_enum64(t) + spec->spec[0].idx); break; default: return -EOPNOTSUPP; @@ -740,31 +870,6 @@ 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 @@ -805,8 +910,8 @@ static int bpf_core_calc_relo(const char *prog_name, if (res->orig_sz != res->new_sz) { const struct btf_type *orig_t, *new_t; - orig_t = btf__type_by_id(local_spec->btf, res->orig_type_id); - new_t = btf__type_by_id(targ_spec->btf, res->new_type_id); + orig_t = btf_type_by_id(local_spec->btf, res->orig_type_id); + new_t = btf_type_by_id(targ_spec->btf, res->new_type_id); /* There are two use cases in which it's safe to * adjust load/store's mem size: @@ -835,8 +940,8 @@ static int bpf_core_calc_relo(const char *prog_name, res->fail_memsz_adjust = true; } } else if (core_relo_is_type_based(relo->kind)) { - err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val); - err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val); + err = bpf_core_calc_type_relo(relo, local_spec, &res->orig_val, &res->validate); + err = err ?: bpf_core_calc_type_relo(relo, targ_spec, &res->new_val, NULL); } else if (core_relo_is_enumval_based(relo->kind)) { err = bpf_core_calc_enumval_relo(relo, local_spec, &res->orig_val); err = err ?: bpf_core_calc_enumval_relo(relo, targ_spec, &res->new_val); @@ -916,11 +1021,11 @@ 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; + __u64 orig_val, new_val; __u8 class; class = BPF_CLASS(insn->code); @@ -945,28 +1050,30 @@ poison: if (BPF_SRC(insn->code) != BPF_K) return -EINVAL; if (res->validate && insn->imm != orig_val) { - pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n", + pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %llu -> %llu\n", prog_name, relo_idx, - insn_idx, insn->imm, orig_val, new_val); + insn_idx, insn->imm, (unsigned long long)orig_val, + (unsigned long long)new_val); return -EINVAL; } orig_val = insn->imm; insn->imm = new_val; - pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %u -> %u\n", + pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %llu -> %llu\n", prog_name, relo_idx, insn_idx, - orig_val, new_val); + (unsigned long long)orig_val, (unsigned long long)new_val); break; case BPF_LDX: case BPF_ST: case BPF_STX: if (res->validate && insn->off != orig_val) { - pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %u, exp %u -> %u\n", - prog_name, relo_idx, insn_idx, insn->off, orig_val, new_val); + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDX/ST/STX) value: got %u, exp %llu -> %llu\n", + prog_name, relo_idx, insn_idx, insn->off, (unsigned long long)orig_val, + (unsigned long long)new_val); return -EINVAL; } if (new_val > SHRT_MAX) { - pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %u\n", - prog_name, relo_idx, insn_idx, new_val); + pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %llu\n", + prog_name, relo_idx, insn_idx, (unsigned long long)new_val); return -ERANGE; } if (res->fail_memsz_adjust) { @@ -978,8 +1085,9 @@ poison: orig_val = insn->off; insn->off = new_val; - pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %u -> %u\n", - prog_name, relo_idx, insn_idx, orig_val, new_val); + pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %llu -> %llu\n", + prog_name, relo_idx, insn_idx, (unsigned long long)orig_val, + (unsigned long long)new_val); if (res->new_sz != res->orig_sz) { int insn_bytes_sz, insn_bpf_sz; @@ -1015,20 +1123,20 @@ poison: return -EINVAL; } - imm = insn[0].imm + ((__u64)insn[1].imm << 32); + imm = (__u32)insn[0].imm | ((__u64)insn[1].imm << 32); if (res->validate && imm != orig_val) { - pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %u -> %u\n", + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LDIMM64) value: got %llu, exp %llu -> %llu\n", prog_name, relo_idx, insn_idx, (unsigned long long)imm, - orig_val, new_val); + (unsigned long long)orig_val, (unsigned long long)new_val); return -EINVAL; } insn[0].imm = new_val; - insn[1].imm = 0; /* currently only 32-bit values are supported */ - pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %u\n", + insn[1].imm = new_val >> 32; + pr_debug("prog '%s': relo #%d: patched insn #%d (LDIMM64) imm64 %llu -> %llu\n", prog_name, relo_idx, insn_idx, - (unsigned long long)imm, new_val); + (unsigned long long)imm, (unsigned long long)new_val); break; } default: @@ -1045,55 +1153,82 @@ poison: * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>, * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b */ -static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) +int bpf_core_format_spec(char *buf, size_t buf_sz, const struct bpf_core_spec *spec) { const struct btf_type *t; - const struct btf_enum *e; const char *s; __u32 type_id; - int i; + int i, len = 0; + +#define append_buf(fmt, args...) \ + ({ \ + int r; \ + r = snprintf(buf, buf_sz, fmt, ##args); \ + len += r; \ + if (r >= buf_sz) \ + r = buf_sz; \ + buf += r; \ + buf_sz -= r; \ + }) type_id = spec->root_type_id; - t = btf__type_by_id(spec->btf, type_id); + t = btf_type_by_id(spec->btf, type_id); s = btf__name_by_offset(spec->btf, t->name_off); - libbpf_print(level, "[%u] %s %s", type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s); + append_buf("<%s> [%u] %s %s", + core_relo_kind_str(spec->relo_kind), + type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s); if (core_relo_is_type_based(spec->relo_kind)) - return; + return len; if (core_relo_is_enumval_based(spec->relo_kind)) { t = skip_mods_and_typedefs(spec->btf, type_id, NULL); - e = btf_enum(t) + spec->raw_spec[0]; - s = btf__name_by_offset(spec->btf, e->name_off); + if (btf_is_enum(t)) { + const struct btf_enum *e; + const char *fmt_str; + + e = btf_enum(t) + spec->raw_spec[0]; + s = btf__name_by_offset(spec->btf, e->name_off); + fmt_str = BTF_INFO_KFLAG(t->info) ? "::%s = %d" : "::%s = %u"; + append_buf(fmt_str, s, e->val); + } else { + const struct btf_enum64 *e; + const char *fmt_str; - libbpf_print(level, "::%s = %u", s, e->val); - return; + e = btf_enum64(t) + spec->raw_spec[0]; + s = btf__name_by_offset(spec->btf, e->name_off); + fmt_str = BTF_INFO_KFLAG(t->info) ? "::%s = %lld" : "::%s = %llu"; + append_buf(fmt_str, s, (unsigned long long)btf_enum64_value(e)); + } + return len; } if (core_relo_is_field_based(spec->relo_kind)) { for (i = 0; i < spec->len; i++) { if (spec->spec[i].name) - libbpf_print(level, ".%s", spec->spec[i].name); + append_buf(".%s", spec->spec[i].name); else if (i > 0 || spec->spec[i].idx > 0) - libbpf_print(level, "[%u]", spec->spec[i].idx); + append_buf("[%u]", spec->spec[i].idx); } - libbpf_print(level, " ("); + append_buf(" ("); for (i = 0; i < spec->raw_len; i++) - libbpf_print(level, "%s%d", i == 0 ? "" : ":", spec->raw_spec[i]); + append_buf("%s%d", i == 0 ? "" : ":", spec->raw_spec[i]); if (spec->bit_offset % 8) - libbpf_print(level, " @ offset %u.%u)", - spec->bit_offset / 8, spec->bit_offset % 8); + append_buf(" @ offset %u.%u)", spec->bit_offset / 8, spec->bit_offset % 8); else - libbpf_print(level, " @ offset %u)", spec->bit_offset / 8); - return; + append_buf(" @ offset %u)", spec->bit_offset / 8); + return len; } + + return len; +#undef append_buf } /* - * 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. @@ -1124,11 +1259,11 @@ static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) * 3. It is supported and expected that there might be multiple flavors * matching the spec. As long as all the specs resolve to the same set of * offsets across all candidates, there is no error. If there is any - * ambiguity, CO-RE relocation will fail. This is necessary to accomodate - * imprefection of BTF deduplication, which can cause slight duplication of + * ambiguity, CO-RE relocation will fail. This is necessary to accommodate + * imperfection of BTF deduplication, which can cause slight duplication of * the same BTF type, if some directly or indirectly referenced (by * pointer) type gets resolved to different actual types in different - * object files. If such situation occurs, deduplicated BTF will end up + * object files. If such a situation occurs, deduplicated BTF will end up * with two (or more) structurally identical types, which differ only in * types they refer to through pointer. This should be OK in most cases and * is not an error. @@ -1142,108 +1277,107 @@ static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) * 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) +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, cand_spec, targ_spec = {}; - struct bpf_core_relo_res cand_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; const struct btf_type *local_type; const char *local_name; __u32 local_id; - const char *spec_str; + char spec_buf[256]; int i, j, err; local_id = relo->type_id; - local_type = btf__type_by_id(local_btf, local_id); - if (!local_type) - return -EINVAL; - + local_type = btf_type_by_id(local_btf, local_id); local_name = btf__name_by_offset(local_btf, local_type->name_off); if (!local_name) return -EINVAL; - spec_str = btf__name_by_offset(local_btf, relo->access_str_off); - if (str_is_empty(spec_str)) - return -EINVAL; - - err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec); + err = bpf_core_parse_spec(prog_name, local_btf, relo, local_spec); if (err) { + const char *spec_str; + + spec_str = btf__name_by_offset(local_btf, relo->access_str_off); pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n", prog_name, relo_idx, local_id, btf_kind_str(local_type), str_is_empty(local_name) ? "<anon>" : local_name, - spec_str, err); + spec_str ?: "<?>", err); return -EINVAL; } - pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog_name, - relo_idx, core_relo_kind_str(relo->kind), relo->kind); - bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); - libbpf_print(LIBBPF_DEBUG, "\n"); + bpf_core_format_spec(spec_buf, sizeof(spec_buf), local_spec); + pr_debug("prog '%s': relo #%d: %s\n", prog_name, relo_idx, spec_buf); /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */ - if (relo->kind == BPF_TYPE_ID_LOCAL) { - targ_res.validate = true; - 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; + 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; + return 0; } /* libbpf doesn't support candidate search for anonymous types */ - if (str_is_empty(spec_str)) { + if (str_is_empty(local_name)) { pr_warn("prog '%s': relo #%d: <%s> (%d) relocation doesn't support anonymous types\n", prog_name, relo_idx, core_relo_kind_str(relo->kind), relo->kind); return -EOPNOTSUPP; } - for (i = 0, j = 0; i < cands->len; i++) { - err = bpf_core_spec_match(&local_spec, cands->cands[i].btf, - cands->cands[i].id, &cand_spec); + err = bpf_core_spec_match(local_spec, cands->cands[i].btf, + cands->cands[i].id, cand_spec); if (err < 0) { - pr_warn("prog '%s': relo #%d: error matching candidate #%d ", - prog_name, relo_idx, i); - bpf_core_dump_spec(LIBBPF_WARN, &cand_spec); - libbpf_print(LIBBPF_WARN, ": %d\n", err); + bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec); + pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n ", + prog_name, relo_idx, i, spec_buf, err); return err; } - pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog_name, - relo_idx, err == 0 ? "non-matching" : "matching", i); - bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); - libbpf_print(LIBBPF_DEBUG, "\n"); + bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec); + pr_debug("prog '%s': relo #%d: %s candidate #%d %s\n", prog_name, + relo_idx, err == 0 ? "non-matching" : "matching", i, spec_buf); if (err == 0) continue; - err = bpf_core_calc_relo(prog_name, relo, relo_idx, &local_spec, &cand_spec, &cand_res); + err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, cand_spec, &cand_res); if (err) return err; if (j == 0) { - targ_res = cand_res; - targ_spec = cand_spec; - } else if (cand_spec.bit_offset != targ_spec.bit_offset) { + *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 * should all resolve to the same bit offset */ pr_warn("prog '%s': relo #%d: field offset ambiguity: %u != %u\n", - prog_name, relo_idx, cand_spec.bit_offset, - targ_spec.bit_offset); + 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 */ - pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %u != %s %u\n", + pr_warn("prog '%s': relo #%d: relocation decision ambiguity: %s %llu != %s %llu\n", prog_name, relo_idx, - cand_res.poison ? "failure" : "success", cand_res.new_val, - targ_res.poison ? "failure" : "success", targ_res.new_val); + cand_res.poison ? "failure" : "success", + (unsigned long long)cand_res.new_val, + targ_res->poison ? "failure" : "success", + (unsigned long long)targ_res->new_val); return -EINVAL; } @@ -1251,7 +1385,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, } /* - * For BPF_FIELD_EXISTS relo or when used BPF program has field + * For BPF_CORE_FIELD_EXISTS relo or when used BPF program has field * existence checks or kernel version/config checks, it's expected * that we might not find any candidates. In this case, if field * wasn't found in any candidate, the list of candidates shouldn't @@ -1277,19 +1411,280 @@ 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 0; +} + +static bool bpf_core_names_match(const struct btf *local_btf, size_t local_name_off, + const struct btf *targ_btf, size_t targ_name_off) +{ + const char *local_n, *targ_n; + size_t local_len, targ_len; + + local_n = btf__name_by_offset(local_btf, local_name_off); + targ_n = btf__name_by_offset(targ_btf, targ_name_off); + + if (str_is_empty(targ_n)) + return str_is_empty(local_n); + + targ_len = bpf_core_essential_name_len(targ_n); + local_len = bpf_core_essential_name_len(local_n); + + return targ_len == local_len && strncmp(local_n, targ_n, local_len) == 0; +} + +static int bpf_core_enums_match(const struct btf *local_btf, const struct btf_type *local_t, + const struct btf *targ_btf, const struct btf_type *targ_t) +{ + __u16 local_vlen = btf_vlen(local_t); + __u16 targ_vlen = btf_vlen(targ_t); + int i, j; + + if (local_t->size != targ_t->size) + return 0; + + if (local_vlen > targ_vlen) + return 0; + + /* iterate over the local enum's variants and make sure each has + * a symbolic name correspondent in the target + */ + for (i = 0; i < local_vlen; i++) { + bool matched = false; + __u32 local_n_off, targ_n_off; + + local_n_off = btf_is_enum(local_t) ? btf_enum(local_t)[i].name_off : + btf_enum64(local_t)[i].name_off; + + for (j = 0; j < targ_vlen; j++) { + targ_n_off = btf_is_enum(targ_t) ? btf_enum(targ_t)[j].name_off : + btf_enum64(targ_t)[j].name_off; + + if (bpf_core_names_match(local_btf, local_n_off, targ_btf, targ_n_off)) { + matched = true; + break; + } + } + + if (!matched) + return 0; + } + return 1; +} + +static int bpf_core_composites_match(const struct btf *local_btf, const struct btf_type *local_t, + const struct btf *targ_btf, const struct btf_type *targ_t, + bool behind_ptr, int level) +{ + const struct btf_member *local_m = btf_members(local_t); + __u16 local_vlen = btf_vlen(local_t); + __u16 targ_vlen = btf_vlen(targ_t); + int i, j, err; + + if (local_vlen > targ_vlen) + return 0; + + /* check that all local members have a match in the target */ + for (i = 0; i < local_vlen; i++, local_m++) { + const struct btf_member *targ_m = btf_members(targ_t); + bool matched = false; + + for (j = 0; j < targ_vlen; j++, targ_m++) { + if (!bpf_core_names_match(local_btf, local_m->name_off, + targ_btf, targ_m->name_off)) + continue; + + err = __bpf_core_types_match(local_btf, local_m->type, targ_btf, + targ_m->type, behind_ptr, level - 1); + if (err < 0) + return err; + if (err > 0) { + matched = true; + break; + } + } + + if (!matched) + return 0; + } + return 1; +} + +/* Check that two types "match". This function assumes that root types were + * already checked for name match. + * + * The matching relation is defined as follows: + * - modifiers and typedefs are stripped (and, hence, effectively ignored) + * - generally speaking types need to be of same kind (struct vs. struct, union + * vs. union, etc.) + * - exceptions are struct/union behind a pointer which could also match a + * forward declaration of a struct or union, respectively, and enum vs. + * enum64 (see below) + * Then, depending on type: + * - integers: + * - match if size and signedness match + * - arrays & pointers: + * - target types are recursively matched + * - structs & unions: + * - local members need to exist in target with the same name + * - for each member we recursively check match unless it is already behind a + * pointer, in which case we only check matching names and compatible kind + * - enums: + * - local variants have to have a match in target by symbolic name (but not + * numeric value) + * - size has to match (but enum may match enum64 and vice versa) + * - function pointers: + * - number and position of arguments in local type has to match target + * - for each argument and the return value we recursively check match + */ +int __bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, + __u32 targ_id, bool behind_ptr, int level) +{ + const struct btf_type *local_t, *targ_t; + int depth = 32; /* max recursion depth */ + __u16 local_k, targ_k; + + if (level <= 0) + return -EINVAL; + + local_t = btf_type_by_id(local_btf, local_id); + targ_t = btf_type_by_id(targ_btf, targ_id); + +recur: + depth--; + if (depth < 0) return -EINVAL; + + local_t = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_t = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_t || !targ_t) + return -EINVAL; + + /* While the name check happens after typedefs are skipped, root-level + * typedefs would still be name-matched as that's the contract with + * callers. + */ + if (!bpf_core_names_match(local_btf, local_t->name_off, targ_btf, targ_t->name_off)) + return 0; + + local_k = btf_kind(local_t); + targ_k = btf_kind(targ_t); + + switch (local_k) { + case BTF_KIND_UNKN: + return local_k == targ_k; + case BTF_KIND_FWD: { + bool local_f = BTF_INFO_KFLAG(local_t->info); + + if (behind_ptr) { + if (local_k == targ_k) + return local_f == BTF_INFO_KFLAG(targ_t->info); + + /* for forward declarations kflag dictates whether the + * target is a struct (0) or union (1) + */ + return (targ_k == BTF_KIND_STRUCT && !local_f) || + (targ_k == BTF_KIND_UNION && local_f); + } else { + if (local_k != targ_k) + return 0; + + /* match if the forward declaration is for the same kind */ + return local_f == BTF_INFO_KFLAG(targ_t->info); + } } + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + if (!btf_is_any_enum(targ_t)) + return 0; - return 0; + return bpf_core_enums_match(local_btf, local_t, targ_btf, targ_t); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + if (behind_ptr) { + bool targ_f = BTF_INFO_KFLAG(targ_t->info); + + if (local_k == targ_k) + return 1; + + if (targ_k != BTF_KIND_FWD) + return 0; + + return (local_k == BTF_KIND_UNION) == targ_f; + } else { + if (local_k != targ_k) + return 0; + + return bpf_core_composites_match(local_btf, local_t, targ_btf, targ_t, + behind_ptr, level); + } + case BTF_KIND_INT: { + __u8 local_sgn; + __u8 targ_sgn; + + if (local_k != targ_k) + return 0; + + local_sgn = btf_int_encoding(local_t) & BTF_INT_SIGNED; + targ_sgn = btf_int_encoding(targ_t) & BTF_INT_SIGNED; + + return local_t->size == targ_t->size && local_sgn == targ_sgn; + } + case BTF_KIND_PTR: + if (local_k != targ_k) + return 0; + + behind_ptr = true; + + local_id = local_t->type; + targ_id = targ_t->type; + goto recur; + case BTF_KIND_ARRAY: { + const struct btf_array *local_array = btf_array(local_t); + const struct btf_array *targ_array = btf_array(targ_t); + + if (local_k != targ_k) + return 0; + + if (local_array->nelems != targ_array->nelems) + return 0; + + local_id = local_array->type; + targ_id = targ_array->type; + goto recur; + } + case BTF_KIND_FUNC_PROTO: { + struct btf_param *local_p = btf_params(local_t); + struct btf_param *targ_p = btf_params(targ_t); + __u16 local_vlen = btf_vlen(local_t); + __u16 targ_vlen = btf_vlen(targ_t); + int i, err; + + if (local_k != targ_k) + return 0; + + if (local_vlen != targ_vlen) + return 0; + + for (i = 0; i < local_vlen; i++, local_p++, targ_p++) { + err = __bpf_core_types_match(local_btf, local_p->type, targ_btf, + targ_p->type, behind_ptr, level - 1); + if (err <= 0) + return err; + } + + /* tail recurse for return type check */ + local_id = local_t->type; + targ_id = targ_t->type; + goto recur; + } + default: + pr_warn("unexpected kind %s relocated, local [%d], target [%d]\n", + btf_kind_str(local_t), local_id, targ_id); + return 0; + } } diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h index 3b9f8f18346c..1c0566daf8e8 100644 --- a/tools/lib/bpf/relo_core.h +++ b/tools/lib/bpf/relo_core.h @@ -4,81 +4,10 @@ #ifndef __RELO_CORE_H #define __RELO_CORE_H -/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value - * has to be adjusted by relocations. - */ -enum bpf_core_relo_kind { - BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */ - BPF_FIELD_BYTE_SIZE = 1, /* field size in bytes */ - BPF_FIELD_EXISTS = 2, /* field existence in target kernel */ - BPF_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ - BPF_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ - BPF_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ - BPF_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ - BPF_TYPE_ID_TARGET = 7, /* type ID in target kernel */ - BPF_TYPE_EXISTS = 8, /* type existence in target kernel */ - BPF_TYPE_SIZE = 9, /* type size in bytes */ - BPF_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ - BPF_ENUMVAL_VALUE = 11, /* enum value integer value */ -}; - -/* The minimum bpf_core_relo checked by the loader - * - * CO-RE relocation captures the following data: - * - insn_off - instruction offset (in bytes) within a BPF program that needs - * its insn->imm field to be relocated with actual field info; - * - type_id - BTF type ID of the "root" (containing) entity of a relocatable - * type or field; - * - access_str_off - offset into corresponding .BTF string section. String - * interpretation depends on specific relocation kind: - * - for field-based relocations, string encodes an accessed field using - * a sequence of field and array indices, separated by colon (:). It's - * conceptually very close to LLVM's getelementptr ([0]) instruction's - * arguments for identifying offset to a field. - * - for type-based relocations, strings is expected to be just "0"; - * - for enum value-based relocations, string contains an index of enum - * value within its enum type; - * - * Example to provide a better feel. - * - * struct sample { - * int a; - * struct { - * int b[10]; - * }; - * }; - * - * struct sample *s = ...; - * int x = &s->a; // encoded as "0:0" (a is field #0) - * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, - * // b is field #0 inside anon struct, accessing elem #5) - * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) - * - * type_id for all relocs in this example will capture BTF type id of - * `struct sample`. - * - * Such relocation is emitted when using __builtin_preserve_access_index() - * Clang built-in, passing expression that captures field address, e.g.: - * - * bpf_probe_read(&dst, sizeof(dst), - * __builtin_preserve_access_index(&src->a.b.c)); - * - * In this case Clang will emit field relocation recording necessary data to - * be able to find offset of embedded `a.b.c` field within `src` struct. - * - * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction - */ -struct bpf_core_relo { - __u32 insn_off; - __u32 type_id; - __u32 access_str_off; - enum bpf_core_relo_kind kind; -}; +#include <linux/bpf.h> struct bpf_core_cand { const struct btf *btf; - const struct btf_type *t; - const char *name; __u32 id; }; @@ -88,13 +17,83 @@ struct bpf_core_cand_list { int len; }; -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); +#define BPF_CORE_SPEC_MAX_LEN 64 + +/* represents BPF CO-RE field or array element accessor */ +struct bpf_core_accessor { + __u32 type_id; /* struct/union type or array element type */ + __u32 idx; /* field index or array index */ + const char *name; /* field name or NULL for array accessor */ +}; + +struct bpf_core_spec { + const struct btf *btf; + /* high-level spec: named fields and array indices only */ + struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* original unresolved (no skip_mods_or_typedefs) root type ID */ + __u32 root_type_id; + /* CO-RE relocation kind */ + enum bpf_core_relo_kind relo_kind; + /* high-level spec length */ + int len; + /* raw, low-level spec: 1-to-1 with accessor spec string */ + int raw_spec[BPF_CORE_SPEC_MAX_LEN]; + /* raw spec length */ + int raw_len; + /* field bit offset represented by spec */ + __u32 bit_offset; +}; + +struct bpf_core_relo_res { + /* expected value in the instruction, unless validate == false */ + __u64 orig_val; + /* new value that needs to be patched up to */ + __u64 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, int level); int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id); +int __bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, + __u32 targ_id, bool behind_ptr, int level); +int bpf_core_types_match(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); + +int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, + const struct bpf_core_relo *relo, + struct bpf_core_spec *spec); + +int bpf_core_format_spec(char *buf, size_t buf_sz, const struct bpf_core_spec *spec); + #endif diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 8bc117bcc7bc..d285171d4b69 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -16,6 +16,7 @@ #include <asm/barrier.h> #include <sys/mman.h> #include <sys/epoll.h> +#include <time.h> #include "libbpf.h" #include "libbpf_internal.h" @@ -39,6 +40,23 @@ struct ring_buffer { int ring_cnt; }; +struct user_ring_buffer { + struct epoll_event event; + unsigned long *consumer_pos; + unsigned long *producer_pos; + void *data; + unsigned long mask; + size_t page_size; + int map_fd; + int epoll_fd; +}; + +/* 8-byte ring buffer header structure */ +struct ringbuf_hdr { + __u32 len; + __u32 pad; +}; + static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r) { if (r->consumer_pos) { @@ -300,3 +318,256 @@ int ring_buffer__epoll_fd(const struct ring_buffer *rb) { return rb->epoll_fd; } + +static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb) +{ + if (rb->consumer_pos) { + munmap(rb->consumer_pos, rb->page_size); + rb->consumer_pos = NULL; + } + if (rb->producer_pos) { + munmap(rb->producer_pos, rb->page_size + 2 * (rb->mask + 1)); + rb->producer_pos = NULL; + } +} + +void user_ring_buffer__free(struct user_ring_buffer *rb) +{ + if (!rb) + return; + + user_ringbuf_unmap_ring(rb); + + if (rb->epoll_fd >= 0) + close(rb->epoll_fd); + + free(rb); +} + +static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) +{ + struct bpf_map_info info; + __u32 len = sizeof(info); + void *tmp; + struct epoll_event *rb_epoll; + int err; + + memset(&info, 0, sizeof(info)); + + err = bpf_obj_get_info_by_fd(map_fd, &info, &len); + if (err) { + err = -errno; + pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err); + return err; + } + + if (info.type != BPF_MAP_TYPE_USER_RINGBUF) { + pr_warn("user ringbuf: map fd=%d is not BPF_MAP_TYPE_USER_RINGBUF\n", map_fd); + return -EINVAL; + } + + rb->map_fd = map_fd; + rb->mask = info.max_entries - 1; + + /* Map read-only consumer page */ + tmp = mmap(NULL, rb->page_size, PROT_READ, MAP_SHARED, map_fd, 0); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n", + map_fd, err); + return err; + } + rb->consumer_pos = tmp; + + /* Map read-write the producer page and data pages. We map the data + * region as twice the total size of the ring buffer to allow the + * simple reading and writing of samples that wrap around the end of + * the buffer. See the kernel implementation for details. + */ + tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, + PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, rb->page_size); + if (tmp == MAP_FAILED) { + err = -errno; + pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n", + map_fd, err); + return err; + } + + rb->producer_pos = tmp; + rb->data = tmp + rb->page_size; + + rb_epoll = &rb->event; + rb_epoll->events = EPOLLOUT; + if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, rb_epoll) < 0) { + err = -errno; + pr_warn("user ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err); + return err; + } + + return 0; +} + +struct user_ring_buffer * +user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts) +{ + struct user_ring_buffer *rb; + int err; + + if (!OPTS_VALID(opts, user_ring_buffer_opts)) + return errno = EINVAL, NULL; + + rb = calloc(1, sizeof(*rb)); + if (!rb) + return errno = ENOMEM, NULL; + + rb->page_size = getpagesize(); + + rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (rb->epoll_fd < 0) { + err = -errno; + pr_warn("user ringbuf: failed to create epoll instance: %d\n", err); + goto err_out; + } + + err = user_ringbuf_map(rb, map_fd); + if (err) + goto err_out; + + return rb; + +err_out: + user_ring_buffer__free(rb); + return errno = -err, NULL; +} + +static void user_ringbuf_commit(struct user_ring_buffer *rb, void *sample, bool discard) +{ + __u32 new_len; + struct ringbuf_hdr *hdr; + uintptr_t hdr_offset; + + hdr_offset = rb->mask + 1 + (sample - rb->data) - BPF_RINGBUF_HDR_SZ; + hdr = rb->data + (hdr_offset & rb->mask); + + new_len = hdr->len & ~BPF_RINGBUF_BUSY_BIT; + if (discard) + new_len |= BPF_RINGBUF_DISCARD_BIT; + + /* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + __atomic_exchange_n(&hdr->len, new_len, __ATOMIC_ACQ_REL); +} + +void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample) +{ + user_ringbuf_commit(rb, sample, true); +} + +void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample) +{ + user_ringbuf_commit(rb, sample, false); +} + +void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size) +{ + __u32 avail_size, total_size, max_size; + /* 64-bit to avoid overflow in case of extreme application behavior */ + __u64 cons_pos, prod_pos; + struct ringbuf_hdr *hdr; + + /* Synchronizes with smp_store_release() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + cons_pos = smp_load_acquire(rb->consumer_pos); + /* Synchronizes with smp_store_release() in user_ringbuf_commit() */ + prod_pos = smp_load_acquire(rb->producer_pos); + + max_size = rb->mask + 1; + avail_size = max_size - (prod_pos - cons_pos); + /* Round up total size to a multiple of 8. */ + total_size = (size + BPF_RINGBUF_HDR_SZ + 7) / 8 * 8; + + if (total_size > max_size) + return errno = E2BIG, NULL; + + if (avail_size < total_size) + return errno = ENOSPC, NULL; + + hdr = rb->data + (prod_pos & rb->mask); + hdr->len = size | BPF_RINGBUF_BUSY_BIT; + hdr->pad = 0; + + /* Synchronizes with smp_load_acquire() in __bpf_user_ringbuf_peek() in + * the kernel. + */ + smp_store_release(rb->producer_pos, prod_pos + total_size); + + return (void *)rb->data + ((prod_pos + BPF_RINGBUF_HDR_SZ) & rb->mask); +} + +static __u64 ns_elapsed_timespec(const struct timespec *start, const struct timespec *end) +{ + __u64 start_ns, end_ns, ns_per_s = 1000000000; + + start_ns = (__u64)start->tv_sec * ns_per_s + start->tv_nsec; + end_ns = (__u64)end->tv_sec * ns_per_s + end->tv_nsec; + + return end_ns - start_ns; +} + +void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, __u32 size, int timeout_ms) +{ + void *sample; + int err, ms_remaining = timeout_ms; + struct timespec start; + + if (timeout_ms < 0 && timeout_ms != -1) + return errno = EINVAL, NULL; + + if (timeout_ms != -1) { + err = clock_gettime(CLOCK_MONOTONIC, &start); + if (err) + return NULL; + } + + do { + int cnt, ms_elapsed; + struct timespec curr; + __u64 ns_per_ms = 1000000; + + sample = user_ring_buffer__reserve(rb, size); + if (sample) + return sample; + else if (errno != ENOSPC) + return NULL; + + /* The kernel guarantees at least one event notification + * delivery whenever at least one sample is drained from the + * ring buffer in an invocation to bpf_ringbuf_drain(). Other + * additional events may be delivered at any time, but only one + * event is guaranteed per bpf_ringbuf_drain() invocation, + * provided that a sample is drained, and the BPF program did + * not pass BPF_RB_NO_WAKEUP to bpf_ringbuf_drain(). If + * BPF_RB_FORCE_WAKEUP is passed to bpf_ringbuf_drain(), a + * wakeup event will be delivered even if no samples are + * drained. + */ + cnt = epoll_wait(rb->epoll_fd, &rb->event, 1, ms_remaining); + if (cnt < 0) + return NULL; + + if (timeout_ms == -1) + continue; + + err = clock_gettime(CLOCK_MONOTONIC, &curr); + if (err) + return NULL; + + ms_elapsed = ns_elapsed_timespec(&start, &curr) / ns_per_ms; + ms_remaining = timeout_ms - ms_elapsed; + } while (ms_remaining > 0); + + /* Try one more time to reserve a sample after the specified timeout has elapsed. */ + return user_ring_buffer__reserve(rb, size); +} diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 9cf66702fa8d..1e82ab06c3eb 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -3,9 +3,29 @@ #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) +# define __NR_bpf 4355 +# elif defined(__mips__) && defined(_ABIN32) +# define __NR_bpf 6319 +# elif defined(__mips__) && defined(_ABI64) +# define __NR_bpf 5315 +# endif +#endif /* This file is a base header for auto-generated *.lskel.h files. * Its contents will change and may become part of auto-generation in the future. @@ -15,24 +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; @@ -47,11 +66,143 @@ struct bpf_load_and_run_opts { const char *errstr; }; +long kern_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 kern_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) { @@ -60,27 +211,123 @@ 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_map_delete_elem(int fd, const void *key) +{ + 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; + + return skel_sys_bpf(BPF_MAP_DELETE_ELEM, &attr, attr_sz); +} + +static inline int skel_map_get_fd_by_id(__u32 id) +{ + const size_t attr_sz = offsetofend(union bpf_attr, flags); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_id = id; + + return skel_sys_bpf(BPF_MAP_GET_FD_BY_ID, &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) { + const size_t prog_load_attr_sz = offsetofend(union bpf_attr, fd_array); + const size_t test_run_attr_sz = offsetofend(union bpf_attr, test); int map_fd = -1, prog_fd = -1, key = 0, err; union bpf_attr attr; - map_fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, - opts->data_sz, 1, 0); + 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; } - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, prog_load_attr_sz); attr.prog_type = BPF_PROG_TYPE_SYSCALL; attr.insns = (long) opts->insns; attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); @@ -91,25 +338,27 @@ 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, prog_load_attr_sz); if (prog_fd < 0) { opts->errstr = "failed to load loader prog"; - err = -errno; + set_err; goto out; } - memset(&attr, 0, sizeof(attr)); + memset(&attr, 0, test_run_attr_sz); attr.test.prog_fd = prog_fd; attr.test.ctx_in = (long) opts->ctx; attr.test.ctx_size_in = opts->ctx->sz; - err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr)); + err = skel_sys_bpf(BPF_PROG_RUN, &attr, test_run_attr_sz); if (err < 0 || (int)attr.test.retval < 0) { opts->errstr = "failed to execute loader prog"; if (err < 0) { - err = -errno; + set_err; } else { err = (int)attr.test.retval; +#ifndef __KERNEL__ errno = -err; +#endif } goto out; } diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h new file mode 100644 index 000000000000..fdfd235e52c4 --- /dev/null +++ b/tools/lib/bpf/usdt.bpf.h @@ -0,0 +1,247 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#ifndef __USDT_BPF_H__ +#define __USDT_BPF_H__ + +#include <linux/errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +/* Below types and maps are internal implementation details of libbpf's USDT + * support and are subjects to change. Also, bpf_usdt_xxx() API helpers should + * be considered an unstable API as well and might be adjusted based on user + * feedback from using libbpf's USDT support in production. + */ + +/* User can override BPF_USDT_MAX_SPEC_CNT to change default size of internal + * map that keeps track of USDT argument specifications. This might be + * necessary if there are a lot of USDT attachments. + */ +#ifndef BPF_USDT_MAX_SPEC_CNT +#define BPF_USDT_MAX_SPEC_CNT 256 +#endif +/* User can override BPF_USDT_MAX_IP_CNT to change default size of internal + * map that keeps track of IP (memory address) mapping to USDT argument + * specification. + * Note, if kernel supports BPF cookies, this map is not used and could be + * resized all the way to 1 to save a bit of memory. + */ +#ifndef BPF_USDT_MAX_IP_CNT +#define BPF_USDT_MAX_IP_CNT (4 * BPF_USDT_MAX_SPEC_CNT) +#endif + +enum __bpf_usdt_arg_type { + BPF_USDT_ARG_CONST, + BPF_USDT_ARG_REG, + BPF_USDT_ARG_REG_DEREF, +}; + +struct __bpf_usdt_arg_spec { + /* u64 scalar interpreted depending on arg_type, see below */ + __u64 val_off; + /* arg location case, see bpf_udst_arg() for details */ + enum __bpf_usdt_arg_type arg_type; + /* offset of referenced register within struct pt_regs */ + short reg_off; + /* whether arg should be interpreted as signed value */ + bool arg_signed; + /* number of bits that need to be cleared and, optionally, + * sign-extended to cast arguments that are 1, 2, or 4 bytes + * long into final 8-byte u64/s64 value returned to user + */ + char arg_bitshift; +}; + +/* should match USDT_MAX_ARG_CNT in usdt.c exactly */ +#define BPF_USDT_MAX_ARG_CNT 12 +struct __bpf_usdt_spec { + struct __bpf_usdt_arg_spec args[BPF_USDT_MAX_ARG_CNT]; + __u64 usdt_cookie; + short arg_cnt; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, BPF_USDT_MAX_SPEC_CNT); + __type(key, int); + __type(value, struct __bpf_usdt_spec); +} __bpf_usdt_specs SEC(".maps") __weak; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, BPF_USDT_MAX_IP_CNT); + __type(key, long); + __type(value, __u32); +} __bpf_usdt_ip_to_spec_id SEC(".maps") __weak; + +extern const _Bool LINUX_HAS_BPF_COOKIE __kconfig; + +static __always_inline +int __bpf_usdt_spec_id(struct pt_regs *ctx) +{ + if (!LINUX_HAS_BPF_COOKIE) { + long ip = PT_REGS_IP(ctx); + int *spec_id_ptr; + + spec_id_ptr = bpf_map_lookup_elem(&__bpf_usdt_ip_to_spec_id, &ip); + return spec_id_ptr ? *spec_id_ptr : -ESRCH; + } + + return bpf_get_attach_cookie(ctx); +} + +/* Return number of USDT arguments defined for currently traced USDT. */ +__weak __hidden +int bpf_usdt_arg_cnt(struct pt_regs *ctx) +{ + struct __bpf_usdt_spec *spec; + int spec_id; + + spec_id = __bpf_usdt_spec_id(ctx); + if (spec_id < 0) + return -ESRCH; + + spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); + if (!spec) + return -ESRCH; + + return spec->arg_cnt; +} + +/* Fetch USDT argument #*arg_num* (zero-indexed) and put its value into *res. + * Returns 0 on success; negative error, otherwise. + * On error *res is guaranteed to be set to zero. + */ +__weak __hidden +int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) +{ + struct __bpf_usdt_spec *spec; + struct __bpf_usdt_arg_spec *arg_spec; + unsigned long val; + int err, spec_id; + + *res = 0; + + spec_id = __bpf_usdt_spec_id(ctx); + if (spec_id < 0) + return -ESRCH; + + spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); + if (!spec) + return -ESRCH; + + if (arg_num >= BPF_USDT_MAX_ARG_CNT || arg_num >= spec->arg_cnt) + return -ENOENT; + + arg_spec = &spec->args[arg_num]; + switch (arg_spec->arg_type) { + case BPF_USDT_ARG_CONST: + /* Arg is just a constant ("-4@$-9" in USDT arg spec). + * value is recorded in arg_spec->val_off directly. + */ + val = arg_spec->val_off; + break; + case BPF_USDT_ARG_REG: + /* Arg is in a register (e.g, "8@%rax" in USDT arg spec), + * so we read the contents of that register directly from + * struct pt_regs. To keep things simple user-space parts + * record offsetof(struct pt_regs, <regname>) in arg_spec->reg_off. + */ + err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off); + if (err) + return err; + break; + case BPF_USDT_ARG_REG_DEREF: + /* Arg is in memory addressed by register, plus some offset + * (e.g., "-4@-1204(%rbp)" in USDT arg spec). Register is + * identified like with BPF_USDT_ARG_REG case, and the offset + * is in arg_spec->val_off. We first fetch register contents + * from pt_regs, then do another user-space probe read to + * fetch argument value itself. + */ + err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off); + if (err) + return err; + err = bpf_probe_read_user(&val, sizeof(val), (void *)val + arg_spec->val_off); + if (err) + return err; +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + val >>= arg_spec->arg_bitshift; +#endif + break; + default: + return -EINVAL; + } + + /* cast arg from 1, 2, or 4 bytes to final 8 byte size clearing + * necessary upper arg_bitshift bits, with sign extension if argument + * is signed + */ + val <<= arg_spec->arg_bitshift; + if (arg_spec->arg_signed) + val = ((long)val) >> arg_spec->arg_bitshift; + else + val = val >> arg_spec->arg_bitshift; + *res = val; + return 0; +} + +/* Retrieve user-specified cookie value provided during attach as + * bpf_usdt_opts.usdt_cookie. This serves the same purpose as BPF cookie + * returned by bpf_get_attach_cookie(). Libbpf's support for USDT is itself + * utilizing BPF cookies internally, so user can't use BPF cookie directly + * for USDT programs and has to use bpf_usdt_cookie() API instead. + */ +__weak __hidden +long bpf_usdt_cookie(struct pt_regs *ctx) +{ + struct __bpf_usdt_spec *spec; + int spec_id; + + spec_id = __bpf_usdt_spec_id(ctx); + if (spec_id < 0) + return 0; + + spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); + if (!spec) + return 0; + + return spec->usdt_cookie; +} + +/* we rely on ___bpf_apply() and ___bpf_narg() macros already defined in bpf_tracing.h */ +#define ___bpf_usdt_args0() ctx +#define ___bpf_usdt_args1(x) ___bpf_usdt_args0(), ({ long _x; bpf_usdt_arg(ctx, 0, &_x); (void *)_x; }) +#define ___bpf_usdt_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); (void *)_x; }) +#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); (void *)_x; }) +#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); (void *)_x; }) +#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); (void *)_x; }) +#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); (void *)_x; }) +#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); (void *)_x; }) +#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); (void *)_x; }) +#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); (void *)_x; }) +#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); (void *)_x; }) +#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); (void *)_x; }) +#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); (void *)_x; }) +#define ___bpf_usdt_args(args...) ___bpf_apply(___bpf_usdt_args, ___bpf_narg(args))(args) + +/* + * BPF_USDT serves the same purpose for USDT handlers as BPF_PROG for + * tp_btf/fentry/fexit BPF programs and BPF_KPROBE for kprobes. + * Original struct pt_regs * context is preserved as 'ctx' argument. + */ +#define BPF_USDT(name, args...) \ +name(struct pt_regs *ctx); \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args); \ +typeof(name(0)) name(struct pt_regs *ctx) \ +{ \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + return ____##name(___bpf_usdt_args(args)); \ + _Pragma("GCC diagnostic pop") \ +} \ +static __always_inline typeof(name(0)) \ +____##name(struct pt_regs *ctx, ##args) + +#endif /* __USDT_BPF_H__ */ diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c new file mode 100644 index 000000000000..e83b497c2245 --- /dev/null +++ b/tools/lib/bpf/usdt.c @@ -0,0 +1,1519 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ +#include <ctype.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <libelf.h> +#include <gelf.h> +#include <unistd.h> +#include <linux/ptrace.h> +#include <linux/kernel.h> + +/* s8 will be marked as poison while it's a reg of riscv */ +#if defined(__riscv) +#define rv_s8 s8 +#endif + +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_common.h" +#include "libbpf_internal.h" +#include "hashmap.h" + +/* libbpf's USDT support consists of BPF-side state/code and user-space + * state/code working together in concert. BPF-side parts are defined in + * usdt.bpf.h header library. User-space state is encapsulated by struct + * usdt_manager and all the supporting code centered around usdt_manager. + * + * usdt.bpf.h defines two BPF maps that usdt_manager expects: USDT spec map + * and IP-to-spec-ID map, which is auxiliary map necessary for kernels that + * don't support BPF cookie (see below). These two maps are implicitly + * embedded into user's end BPF object file when user's code included + * usdt.bpf.h. This means that libbpf doesn't do anything special to create + * these USDT support maps. They are created by normal libbpf logic of + * instantiating BPF maps when opening and loading BPF object. + * + * As such, libbpf is basically unaware of the need to do anything + * USDT-related until the very first call to bpf_program__attach_usdt(), which + * can be called by user explicitly or happen automatically during skeleton + * attach (or, equivalently, through generic bpf_program__attach() call). At + * this point, libbpf will instantiate and initialize struct usdt_manager and + * store it in bpf_object. USDT manager is per-BPF object construct, as each + * independent BPF object might or might not have USDT programs, and thus all + * the expected USDT-related state. There is no coordination between two + * bpf_object in parts of USDT attachment, they are oblivious of each other's + * existence and libbpf is just oblivious, dealing with bpf_object-specific + * USDT state. + * + * Quick crash course on USDTs. + * + * From user-space application's point of view, USDT is essentially just + * a slightly special function call that normally has zero overhead, unless it + * is being traced by some external entity (e.g, BPF-based tool). Here's how + * a typical application can trigger USDT probe: + * + * #include <sys/sdt.h> // provided by systemtap-sdt-devel package + * // folly also provide similar functionality in folly/tracing/StaticTracepoint.h + * + * STAP_PROBE3(my_usdt_provider, my_usdt_probe_name, 123, x, &y); + * + * USDT is identified by it's <provider-name>:<probe-name> pair of names. Each + * individual USDT has a fixed number of arguments (3 in the above example) + * and specifies values of each argument as if it was a function call. + * + * USDT call is actually not a function call, but is instead replaced by + * a single NOP instruction (thus zero overhead, effectively). But in addition + * to that, those USDT macros generate special SHT_NOTE ELF records in + * .note.stapsdt ELF section. Here's an example USDT definition as emitted by + * `readelf -n <binary>`: + * + * stapsdt 0x00000089 NT_STAPSDT (SystemTap probe descriptors) + * Provider: test + * Name: usdt12 + * Location: 0x0000000000549df3, Base: 0x00000000008effa4, Semaphore: 0x0000000000a4606e + * Arguments: -4@-1204(%rbp) -4@%edi -8@-1216(%rbp) -8@%r8 -4@$5 -8@%r9 8@%rdx 8@%r10 -4@$-9 -2@%cx -2@%ax -1@%sil + * + * In this case we have USDT test:usdt12 with 12 arguments. + * + * Location and base are offsets used to calculate absolute IP address of that + * NOP instruction that kernel can replace with an interrupt instruction to + * trigger instrumentation code (BPF program for all that we care about). + * + * Semaphore above is and optional feature. It records an address of a 2-byte + * refcount variable (normally in '.probes' ELF section) used for signaling if + * there is anything that is attached to USDT. This is useful for user + * applications if, for example, they need to prepare some arguments that are + * passed only to USDTs and preparation is expensive. By checking if USDT is + * "activated", an application can avoid paying those costs unnecessarily. + * Recent enough kernel has built-in support for automatically managing this + * refcount, which libbpf expects and relies on. If USDT is defined without + * associated semaphore, this value will be zero. See selftests for semaphore + * examples. + * + * Arguments is the most interesting part. This USDT specification string is + * providing information about all the USDT arguments and their locations. The + * part before @ sign defined byte size of the argument (1, 2, 4, or 8) and + * whether the argument is signed or unsigned (negative size means signed). + * The part after @ sign is assembly-like definition of argument location + * (see [0] for more details). Technically, assembler can provide some pretty + * advanced definitions, but libbpf is currently supporting three most common + * cases: + * 1) immediate constant, see 5th and 9th args above (-4@$5 and -4@-9); + * 2) register value, e.g., 8@%rdx, which means "unsigned 8-byte integer + * whose value is in register %rdx"; + * 3) memory dereference addressed by register, e.g., -4@-1204(%rbp), which + * specifies signed 32-bit integer stored at offset -1204 bytes from + * memory address stored in %rbp. + * + * [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation + * + * During attachment, libbpf parses all the relevant USDT specifications and + * prepares `struct usdt_spec` (USDT spec), which is then provided to BPF-side + * code through spec map. This allows BPF applications to quickly fetch the + * actual value at runtime using a simple BPF-side code. + * + * With basics out of the way, let's go over less immediately obvious aspects + * of supporting USDTs. + * + * First, there is no special USDT BPF program type. It is actually just + * a uprobe BPF program (which for kernel, at least currently, is just a kprobe + * program, so BPF_PROG_TYPE_KPROBE program type). With the only difference + * that uprobe is usually attached at the function entry, while USDT will + * normally will be somewhere inside the function. But it should always be + * pointing to NOP instruction, which makes such uprobes the fastest uprobe + * kind. + * + * Second, it's important to realize that such STAP_PROBEn(provider, name, ...) + * macro invocations can end up being inlined many-many times, depending on + * specifics of each individual user application. So single conceptual USDT + * (identified by provider:name pair of identifiers) is, generally speaking, + * multiple uprobe locations (USDT call sites) in different places in user + * application. Further, again due to inlining, each USDT call site might end + * up having the same argument #N be located in a different place. In one call + * site it could be a constant, in another will end up in a register, and in + * yet another could be some other register or even somewhere on the stack. + * + * As such, "attaching to USDT" means (in general case) attaching the same + * uprobe BPF program to multiple target locations in user application, each + * potentially having a completely different USDT spec associated with it. + * To wire all this up together libbpf allocates a unique integer spec ID for + * each unique USDT spec. Spec IDs are allocated as sequential small integers + * so that they can be used as keys in array BPF map (for performance reasons). + * Spec ID allocation and accounting is big part of what usdt_manager is + * about. This state has to be maintained per-BPF object and coordinate + * between different USDT attachments within the same BPF object. + * + * Spec ID is the key in spec BPF map, value is the actual USDT spec layed out + * as struct usdt_spec. Each invocation of BPF program at runtime needs to + * know its associated spec ID. It gets it either through BPF cookie, which + * libbpf sets to spec ID during attach time, or, if kernel is too old to + * support BPF cookie, through IP-to-spec-ID map that libbpf maintains in such + * case. The latter means that some modes of operation can't be supported + * without BPF cookie. Such mode is attaching to shared library "generically", + * without specifying target process. In such case, it's impossible to + * calculate absolute IP addresses for IP-to-spec-ID map, and thus such mode + * is not supported without BPF cookie support. + * + * Note that libbpf is using BPF cookie functionality for its own internal + * needs, so user itself can't rely on BPF cookie feature. To that end, libbpf + * provides conceptually equivalent USDT cookie support. It's still u64 + * user-provided value that can be associated with USDT attachment. Note that + * this will be the same value for all USDT call sites within the same single + * *logical* USDT attachment. This makes sense because to user attaching to + * USDT is a single BPF program triggered for singular USDT probe. The fact + * that this is done at multiple actual locations is a mostly hidden + * implementation details. This USDT cookie value can be fetched with + * bpf_usdt_cookie(ctx) API provided by usdt.bpf.h + * + * Lastly, while single USDT can have tons of USDT call sites, it doesn't + * necessarily have that many different USDT specs. It very well might be + * that 1000 USDT call sites only need 5 different USDT specs, because all the + * arguments are typically contained in a small set of registers or stack + * locations. As such, it's wasteful to allocate as many USDT spec IDs as + * there are USDT call sites. So libbpf tries to be frugal and performs + * on-the-fly deduplication during a single USDT attachment to only allocate + * the minimal required amount of unique USDT specs (and thus spec IDs). This + * is trivially achieved by using USDT spec string (Arguments string from USDT + * note) as a lookup key in a hashmap. USDT spec string uniquely defines + * everything about how to fetch USDT arguments, so two USDT call sites + * sharing USDT spec string can safely share the same USDT spec and spec ID. + * Note, this spec string deduplication is happening only during the same USDT + * attachment, so each USDT spec shares the same USDT cookie value. This is + * not generally true for other USDT attachments within the same BPF object, + * as even if USDT spec string is the same, USDT cookie value can be + * different. It was deemed excessive to try to deduplicate across independent + * USDT attachments by taking into account USDT spec string *and* USDT cookie + * value, which would complicated spec ID accounting significantly for little + * gain. + */ + +#define USDT_BASE_SEC ".stapsdt.base" +#define USDT_SEMA_SEC ".probes" +#define USDT_NOTE_SEC ".note.stapsdt" +#define USDT_NOTE_TYPE 3 +#define USDT_NOTE_NAME "stapsdt" + +/* should match exactly enum __bpf_usdt_arg_type from usdt.bpf.h */ +enum usdt_arg_type { + USDT_ARG_CONST, + USDT_ARG_REG, + USDT_ARG_REG_DEREF, +}; + +/* should match exactly struct __bpf_usdt_arg_spec from usdt.bpf.h */ +struct usdt_arg_spec { + __u64 val_off; + enum usdt_arg_type arg_type; + short reg_off; + bool arg_signed; + char arg_bitshift; +}; + +/* should match BPF_USDT_MAX_ARG_CNT in usdt.bpf.h */ +#define USDT_MAX_ARG_CNT 12 + +/* should match struct __bpf_usdt_spec from usdt.bpf.h */ +struct usdt_spec { + struct usdt_arg_spec args[USDT_MAX_ARG_CNT]; + __u64 usdt_cookie; + short arg_cnt; +}; + +struct usdt_note { + const char *provider; + const char *name; + /* USDT args specification string, e.g.: + * "-4@%esi -4@-24(%rbp) -4@%ecx 2@%ax 8@%rdx" + */ + const char *args; + long loc_addr; + long base_addr; + long sema_addr; +}; + +struct usdt_target { + long abs_ip; + long rel_ip; + long sema_off; + struct usdt_spec spec; + const char *spec_str; +}; + +struct usdt_manager { + struct bpf_map *specs_map; + struct bpf_map *ip_to_spec_id_map; + + int *free_spec_ids; + size_t free_spec_cnt; + size_t next_free_spec_id; + + bool has_bpf_cookie; + bool has_sema_refcnt; +}; + +struct usdt_manager *usdt_manager_new(struct bpf_object *obj) +{ + static const char *ref_ctr_sysfs_path = "/sys/bus/event_source/devices/uprobe/format/ref_ctr_offset"; + struct usdt_manager *man; + struct bpf_map *specs_map, *ip_to_spec_id_map; + + specs_map = bpf_object__find_map_by_name(obj, "__bpf_usdt_specs"); + ip_to_spec_id_map = bpf_object__find_map_by_name(obj, "__bpf_usdt_ip_to_spec_id"); + if (!specs_map || !ip_to_spec_id_map) { + pr_warn("usdt: failed to find USDT support BPF maps, did you forget to include bpf/usdt.bpf.h?\n"); + return ERR_PTR(-ESRCH); + } + + man = calloc(1, sizeof(*man)); + if (!man) + return ERR_PTR(-ENOMEM); + + man->specs_map = specs_map; + man->ip_to_spec_id_map = ip_to_spec_id_map; + + /* Detect if BPF cookie is supported for kprobes. + * We don't need IP-to-ID mapping if we can use BPF cookies. + * Added in: 7adfc6c9b315 ("bpf: Add bpf_get_attach_cookie() BPF helper to access bpf_cookie value") + */ + man->has_bpf_cookie = kernel_supports(obj, FEAT_BPF_COOKIE); + + /* Detect kernel support for automatic refcounting of USDT semaphore. + * If this is not supported, USDTs with semaphores will not be supported. + * Added in: a6ca88b241d5 ("trace_uprobe: support reference counter in fd-based uprobe") + */ + man->has_sema_refcnt = faccessat(AT_FDCWD, ref_ctr_sysfs_path, F_OK, AT_EACCESS) == 0; + + return man; +} + +void usdt_manager_free(struct usdt_manager *man) +{ + if (IS_ERR_OR_NULL(man)) + return; + + free(man->free_spec_ids); + free(man); +} + +static int sanity_check_usdt_elf(Elf *elf, const char *path) +{ + GElf_Ehdr ehdr; + int endianness; + + if (elf_kind(elf) != ELF_K_ELF) { + pr_warn("usdt: unrecognized ELF kind %d for '%s'\n", elf_kind(elf), path); + return -EBADF; + } + + switch (gelf_getclass(elf)) { + case ELFCLASS64: + if (sizeof(void *) != 8) { + pr_warn("usdt: attaching to 64-bit ELF binary '%s' is not supported\n", path); + return -EBADF; + } + break; + case ELFCLASS32: + if (sizeof(void *) != 4) { + pr_warn("usdt: attaching to 32-bit ELF binary '%s' is not supported\n", path); + return -EBADF; + } + break; + default: + pr_warn("usdt: unsupported ELF class for '%s'\n", path); + return -EBADF; + } + + if (!gelf_getehdr(elf, &ehdr)) + return -EINVAL; + + if (ehdr.e_type != ET_EXEC && ehdr.e_type != ET_DYN) { + pr_warn("usdt: unsupported type of ELF binary '%s' (%d), only ET_EXEC and ET_DYN are supported\n", + path, ehdr.e_type); + return -EBADF; + } + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + endianness = ELFDATA2LSB; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + endianness = ELFDATA2MSB; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif + if (endianness != ehdr.e_ident[EI_DATA]) { + pr_warn("usdt: ELF endianness mismatch for '%s'\n", path); + return -EBADF; + } + + return 0; +} + +static int find_elf_sec_by_name(Elf *elf, const char *sec_name, GElf_Shdr *shdr, Elf_Scn **scn) +{ + Elf_Scn *sec = NULL; + size_t shstrndx; + + if (elf_getshdrstrndx(elf, &shstrndx)) + return -EINVAL; + + /* check if ELF is corrupted and avoid calling elf_strptr if yes */ + if (!elf_rawdata(elf_getscn(elf, shstrndx), NULL)) + return -EINVAL; + + while ((sec = elf_nextscn(elf, sec)) != NULL) { + char *name; + + if (!gelf_getshdr(sec, shdr)) + return -EINVAL; + + name = elf_strptr(elf, shstrndx, shdr->sh_name); + if (name && strcmp(sec_name, name) == 0) { + *scn = sec; + return 0; + } + } + + return -ENOENT; +} + +struct elf_seg { + long start; + long end; + long offset; + bool is_exec; +}; + +static int cmp_elf_segs(const void *_a, const void *_b) +{ + const struct elf_seg *a = _a; + const struct elf_seg *b = _b; + + return a->start < b->start ? -1 : 1; +} + +static int parse_elf_segs(Elf *elf, const char *path, struct elf_seg **segs, size_t *seg_cnt) +{ + GElf_Phdr phdr; + size_t n; + int i, err; + struct elf_seg *seg; + void *tmp; + + *seg_cnt = 0; + + if (elf_getphdrnum(elf, &n)) { + err = -errno; + return err; + } + + for (i = 0; i < n; i++) { + if (!gelf_getphdr(elf, i, &phdr)) { + err = -errno; + return err; + } + + pr_debug("usdt: discovered PHDR #%d in '%s': vaddr 0x%lx memsz 0x%lx offset 0x%lx type 0x%lx flags 0x%lx\n", + i, path, (long)phdr.p_vaddr, (long)phdr.p_memsz, (long)phdr.p_offset, + (long)phdr.p_type, (long)phdr.p_flags); + if (phdr.p_type != PT_LOAD) + continue; + + tmp = libbpf_reallocarray(*segs, *seg_cnt + 1, sizeof(**segs)); + if (!tmp) + return -ENOMEM; + + *segs = tmp; + seg = *segs + *seg_cnt; + (*seg_cnt)++; + + seg->start = phdr.p_vaddr; + seg->end = phdr.p_vaddr + phdr.p_memsz; + seg->offset = phdr.p_offset; + seg->is_exec = phdr.p_flags & PF_X; + } + + if (*seg_cnt == 0) { + pr_warn("usdt: failed to find PT_LOAD program headers in '%s'\n", path); + return -ESRCH; + } + + qsort(*segs, *seg_cnt, sizeof(**segs), cmp_elf_segs); + return 0; +} + +static int parse_vma_segs(int pid, const char *lib_path, struct elf_seg **segs, size_t *seg_cnt) +{ + char path[PATH_MAX], line[PATH_MAX], mode[16]; + size_t seg_start, seg_end, seg_off; + struct elf_seg *seg; + int tmp_pid, i, err; + FILE *f; + + *seg_cnt = 0; + + /* Handle containerized binaries only accessible from + * /proc/<pid>/root/<path>. They will be reported as just /<path> in + * /proc/<pid>/maps. + */ + if (sscanf(lib_path, "/proc/%d/root%s", &tmp_pid, path) == 2 && pid == tmp_pid) + goto proceed; + + if (!realpath(lib_path, path)) { + pr_warn("usdt: failed to get absolute path of '%s' (err %d), using path as is...\n", + lib_path, -errno); + libbpf_strlcpy(path, lib_path, sizeof(path)); + } + +proceed: + sprintf(line, "/proc/%d/maps", pid); + f = fopen(line, "r"); + if (!f) { + err = -errno; + pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n", + line, lib_path, err); + return err; + } + + /* We need to handle lines with no path at the end: + * + * 7f5c6f5d1000-7f5c6f5d3000 rw-p 001c7000 08:04 21238613 /usr/lib64/libc-2.17.so + * 7f5c6f5d3000-7f5c6f5d8000 rw-p 00000000 00:00 0 + * 7f5c6f5d8000-7f5c6f5d9000 r-xp 00000000 103:01 362990598 /data/users/andriin/linux/tools/bpf/usdt/libhello_usdt.so + */ + while (fscanf(f, "%zx-%zx %s %zx %*s %*d%[^\n]\n", + &seg_start, &seg_end, mode, &seg_off, line) == 5) { + void *tmp; + + /* to handle no path case (see above) we need to capture line + * without skipping any whitespaces. So we need to strip + * leading whitespaces manually here + */ + i = 0; + while (isblank(line[i])) + i++; + if (strcmp(line + i, path) != 0) + continue; + + pr_debug("usdt: discovered segment for lib '%s': addrs %zx-%zx mode %s offset %zx\n", + path, seg_start, seg_end, mode, seg_off); + + /* ignore non-executable sections for shared libs */ + if (mode[2] != 'x') + continue; + + tmp = libbpf_reallocarray(*segs, *seg_cnt + 1, sizeof(**segs)); + if (!tmp) { + err = -ENOMEM; + goto err_out; + } + + *segs = tmp; + seg = *segs + *seg_cnt; + *seg_cnt += 1; + + seg->start = seg_start; + seg->end = seg_end; + seg->offset = seg_off; + seg->is_exec = true; + } + + if (*seg_cnt == 0) { + pr_warn("usdt: failed to find '%s' (resolved to '%s') within PID %d memory mappings\n", + lib_path, path, pid); + err = -ESRCH; + goto err_out; + } + + qsort(*segs, *seg_cnt, sizeof(**segs), cmp_elf_segs); + err = 0; +err_out: + fclose(f); + return err; +} + +static struct elf_seg *find_elf_seg(struct elf_seg *segs, size_t seg_cnt, long virtaddr) +{ + struct elf_seg *seg; + int i; + + /* for ELF binaries (both executables and shared libraries), we are + * given virtual address (absolute for executables, relative for + * libraries) which should match address range of [seg_start, seg_end) + */ + for (i = 0, seg = segs; i < seg_cnt; i++, seg++) { + if (seg->start <= virtaddr && virtaddr < seg->end) + return seg; + } + return NULL; +} + +static struct elf_seg *find_vma_seg(struct elf_seg *segs, size_t seg_cnt, long offset) +{ + struct elf_seg *seg; + int i; + + /* for VMA segments from /proc/<pid>/maps file, provided "address" is + * actually a file offset, so should be fall within logical + * offset-based range of [offset_start, offset_end) + */ + for (i = 0, seg = segs; i < seg_cnt; i++, seg++) { + if (seg->offset <= offset && offset < seg->offset + (seg->end - seg->start)) + return seg; + } + return NULL; +} + +static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, + const char *data, size_t name_off, size_t desc_off, + struct usdt_note *usdt_note); + +static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie); + +static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *path, pid_t pid, + const char *usdt_provider, const char *usdt_name, __u64 usdt_cookie, + struct usdt_target **out_targets, size_t *out_target_cnt) +{ + size_t off, name_off, desc_off, seg_cnt = 0, vma_seg_cnt = 0, target_cnt = 0; + struct elf_seg *segs = NULL, *vma_segs = NULL; + struct usdt_target *targets = NULL, *target; + long base_addr = 0; + Elf_Scn *notes_scn, *base_scn; + GElf_Shdr base_shdr, notes_shdr; + GElf_Ehdr ehdr; + GElf_Nhdr nhdr; + Elf_Data *data; + int err; + + *out_targets = NULL; + *out_target_cnt = 0; + + err = find_elf_sec_by_name(elf, USDT_NOTE_SEC, ¬es_shdr, ¬es_scn); + if (err) { + pr_warn("usdt: no USDT notes section (%s) found in '%s'\n", USDT_NOTE_SEC, path); + return err; + } + + if (notes_shdr.sh_type != SHT_NOTE || !gelf_getehdr(elf, &ehdr)) { + pr_warn("usdt: invalid USDT notes section (%s) in '%s'\n", USDT_NOTE_SEC, path); + return -EINVAL; + } + + err = parse_elf_segs(elf, path, &segs, &seg_cnt); + if (err) { + pr_warn("usdt: failed to process ELF program segments for '%s': %d\n", path, err); + goto err_out; + } + + /* .stapsdt.base ELF section is optional, but is used for prelink + * offset compensation (see a big comment further below) + */ + if (find_elf_sec_by_name(elf, USDT_BASE_SEC, &base_shdr, &base_scn) == 0) + base_addr = base_shdr.sh_addr; + + data = elf_getdata(notes_scn, 0); + off = 0; + while ((off = gelf_getnote(data, off, &nhdr, &name_off, &desc_off)) > 0) { + long usdt_abs_ip, usdt_rel_ip, usdt_sema_off = 0; + struct usdt_note note; + struct elf_seg *seg = NULL; + void *tmp; + + err = parse_usdt_note(elf, path, &nhdr, data->d_buf, name_off, desc_off, ¬e); + if (err) + goto err_out; + + if (strcmp(note.provider, usdt_provider) != 0 || strcmp(note.name, usdt_name) != 0) + continue; + + /* We need to compensate "prelink effect". See [0] for details, + * relevant parts quoted here: + * + * Each SDT probe also expands into a non-allocated ELF note. You can + * find this by looking at SHT_NOTE sections and decoding the format; + * see below for details. Because the note is non-allocated, it means + * there is no runtime cost, and also preserved in both stripped files + * and .debug files. + * + * However, this means that prelink won't adjust the note's contents + * for address offsets. Instead, this is done via the .stapsdt.base + * section. This is a special section that is added to the text. We + * will only ever have one of these sections in a final link and it + * will only ever be one byte long. Nothing about this section itself + * matters, we just use it as a marker to detect prelink address + * adjustments. + * + * Each probe note records the link-time address of the .stapsdt.base + * section alongside the probe PC address. The decoder compares the + * base address stored in the note with the .stapsdt.base section's + * sh_addr. Initially these are the same, but the section header will + * be adjusted by prelink. So the decoder applies the difference to + * the probe PC address to get the correct prelinked PC address; the + * same adjustment is applied to the semaphore address, if any. + * + * [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation + */ + usdt_abs_ip = note.loc_addr; + if (base_addr) + usdt_abs_ip += base_addr - note.base_addr; + + /* When attaching uprobes (which is what USDTs basically are) + * kernel expects file offset to be specified, not a relative + * virtual address, so we need to translate virtual address to + * file offset, for both ET_EXEC and ET_DYN binaries. + */ + seg = find_elf_seg(segs, seg_cnt, usdt_abs_ip); + if (!seg) { + err = -ESRCH; + pr_warn("usdt: failed to find ELF program segment for '%s:%s' in '%s' at IP 0x%lx\n", + usdt_provider, usdt_name, path, usdt_abs_ip); + goto err_out; + } + if (!seg->is_exec) { + err = -ESRCH; + pr_warn("usdt: matched ELF binary '%s' segment [0x%lx, 0x%lx) for '%s:%s' at IP 0x%lx is not executable\n", + path, seg->start, seg->end, usdt_provider, usdt_name, + usdt_abs_ip); + goto err_out; + } + /* translate from virtual address to file offset */ + usdt_rel_ip = usdt_abs_ip - seg->start + seg->offset; + + if (ehdr.e_type == ET_DYN && !man->has_bpf_cookie) { + /* If we don't have BPF cookie support but need to + * attach to a shared library, we'll need to know and + * record absolute addresses of attach points due to + * the need to lookup USDT spec by absolute IP of + * triggered uprobe. Doing this resolution is only + * possible when we have a specific PID of the process + * that's using specified shared library. BPF cookie + * removes the absolute address limitation as we don't + * need to do this lookup (we just use BPF cookie as + * an index of USDT spec), so for newer kernels with + * BPF cookie support libbpf supports USDT attachment + * to shared libraries with no PID filter. + */ + if (pid < 0) { + pr_warn("usdt: attaching to shared libraries without specific PID is not supported on current kernel\n"); + err = -ENOTSUP; + goto err_out; + } + + /* vma_segs are lazily initialized only if necessary */ + if (vma_seg_cnt == 0) { + err = parse_vma_segs(pid, path, &vma_segs, &vma_seg_cnt); + if (err) { + pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %d\n", + pid, path, err); + goto err_out; + } + } + + seg = find_vma_seg(vma_segs, vma_seg_cnt, usdt_rel_ip); + if (!seg) { + err = -ESRCH; + pr_warn("usdt: failed to find shared lib memory segment for '%s:%s' in '%s' at relative IP 0x%lx\n", + usdt_provider, usdt_name, path, usdt_rel_ip); + goto err_out; + } + + usdt_abs_ip = seg->start - seg->offset + usdt_rel_ip; + } + + pr_debug("usdt: probe for '%s:%s' in %s '%s': addr 0x%lx base 0x%lx (resolved abs_ip 0x%lx rel_ip 0x%lx) args '%s' in segment [0x%lx, 0x%lx) at offset 0x%lx\n", + usdt_provider, usdt_name, ehdr.e_type == ET_EXEC ? "exec" : "lib ", path, + note.loc_addr, note.base_addr, usdt_abs_ip, usdt_rel_ip, note.args, + seg ? seg->start : 0, seg ? seg->end : 0, seg ? seg->offset : 0); + + /* Adjust semaphore address to be a file offset */ + if (note.sema_addr) { + if (!man->has_sema_refcnt) { + pr_warn("usdt: kernel doesn't support USDT semaphore refcounting for '%s:%s' in '%s'\n", + usdt_provider, usdt_name, path); + err = -ENOTSUP; + goto err_out; + } + + seg = find_elf_seg(segs, seg_cnt, note.sema_addr); + if (!seg) { + err = -ESRCH; + pr_warn("usdt: failed to find ELF loadable segment with semaphore of '%s:%s' in '%s' at 0x%lx\n", + usdt_provider, usdt_name, path, note.sema_addr); + goto err_out; + } + if (seg->is_exec) { + err = -ESRCH; + pr_warn("usdt: matched ELF binary '%s' segment [0x%lx, 0x%lx] for semaphore of '%s:%s' at 0x%lx is executable\n", + path, seg->start, seg->end, usdt_provider, usdt_name, + note.sema_addr); + goto err_out; + } + + usdt_sema_off = note.sema_addr - seg->start + seg->offset; + + pr_debug("usdt: sema for '%s:%s' in %s '%s': addr 0x%lx base 0x%lx (resolved 0x%lx) in segment [0x%lx, 0x%lx] at offset 0x%lx\n", + usdt_provider, usdt_name, ehdr.e_type == ET_EXEC ? "exec" : "lib ", + path, note.sema_addr, note.base_addr, usdt_sema_off, + seg->start, seg->end, seg->offset); + } + + /* Record adjusted addresses and offsets and parse USDT spec */ + tmp = libbpf_reallocarray(targets, target_cnt + 1, sizeof(*targets)); + if (!tmp) { + err = -ENOMEM; + goto err_out; + } + targets = tmp; + + target = &targets[target_cnt]; + memset(target, 0, sizeof(*target)); + + target->abs_ip = usdt_abs_ip; + target->rel_ip = usdt_rel_ip; + target->sema_off = usdt_sema_off; + + /* notes.args references strings from Elf itself, so they can + * be referenced safely until elf_end() call + */ + target->spec_str = note.args; + + err = parse_usdt_spec(&target->spec, ¬e, usdt_cookie); + if (err) + goto err_out; + + target_cnt++; + } + + *out_targets = targets; + *out_target_cnt = target_cnt; + err = target_cnt; + +err_out: + free(segs); + free(vma_segs); + if (err < 0) + free(targets); + return err; +} + +struct bpf_link_usdt { + struct bpf_link link; + + struct usdt_manager *usdt_man; + + size_t spec_cnt; + int *spec_ids; + + size_t uprobe_cnt; + struct { + long abs_ip; + struct bpf_link *link; + } *uprobes; +}; + +static int bpf_link_usdt_detach(struct bpf_link *link) +{ + struct bpf_link_usdt *usdt_link = container_of(link, struct bpf_link_usdt, link); + struct usdt_manager *man = usdt_link->usdt_man; + int i; + + for (i = 0; i < usdt_link->uprobe_cnt; i++) { + /* detach underlying uprobe link */ + bpf_link__destroy(usdt_link->uprobes[i].link); + /* there is no need to update specs map because it will be + * unconditionally overwritten on subsequent USDT attaches, + * but if BPF cookies are not used we need to remove entry + * from ip_to_spec_id map, otherwise we'll run into false + * conflicting IP errors + */ + if (!man->has_bpf_cookie) { + /* not much we can do about errors here */ + (void)bpf_map_delete_elem(bpf_map__fd(man->ip_to_spec_id_map), + &usdt_link->uprobes[i].abs_ip); + } + } + + /* try to return the list of previously used spec IDs to usdt_manager + * for future reuse for subsequent USDT attaches + */ + if (!man->free_spec_ids) { + /* if there were no free spec IDs yet, just transfer our IDs */ + man->free_spec_ids = usdt_link->spec_ids; + man->free_spec_cnt = usdt_link->spec_cnt; + usdt_link->spec_ids = NULL; + } else { + /* otherwise concat IDs */ + size_t new_cnt = man->free_spec_cnt + usdt_link->spec_cnt; + int *new_free_ids; + + new_free_ids = libbpf_reallocarray(man->free_spec_ids, new_cnt, + sizeof(*new_free_ids)); + /* If we couldn't resize free_spec_ids, we'll just leak + * a bunch of free IDs; this is very unlikely to happen and if + * system is so exhausted on memory, it's the least of user's + * concerns, probably. + * So just do our best here to return those IDs to usdt_manager. + */ + if (new_free_ids) { + memcpy(new_free_ids + man->free_spec_cnt, usdt_link->spec_ids, + usdt_link->spec_cnt * sizeof(*usdt_link->spec_ids)); + man->free_spec_ids = new_free_ids; + man->free_spec_cnt = new_cnt; + } + } + + return 0; +} + +static void bpf_link_usdt_dealloc(struct bpf_link *link) +{ + struct bpf_link_usdt *usdt_link = container_of(link, struct bpf_link_usdt, link); + + free(usdt_link->spec_ids); + free(usdt_link->uprobes); + free(usdt_link); +} + +static size_t specs_hash_fn(const void *key, void *ctx) +{ + const char *s = key; + + return str_hash(s); +} + +static bool specs_equal_fn(const void *key1, const void *key2, void *ctx) +{ + const char *s1 = key1; + const char *s2 = key2; + + return strcmp(s1, s2) == 0; +} + +static int allocate_spec_id(struct usdt_manager *man, struct hashmap *specs_hash, + struct bpf_link_usdt *link, struct usdt_target *target, + int *spec_id, bool *is_new) +{ + void *tmp; + int err; + + /* check if we already allocated spec ID for this spec string */ + if (hashmap__find(specs_hash, target->spec_str, &tmp)) { + *spec_id = (long)tmp; + *is_new = false; + return 0; + } + + /* otherwise it's a new ID that needs to be set up in specs map and + * returned back to usdt_manager when USDT link is detached + */ + tmp = libbpf_reallocarray(link->spec_ids, link->spec_cnt + 1, sizeof(*link->spec_ids)); + if (!tmp) + return -ENOMEM; + link->spec_ids = tmp; + + /* get next free spec ID, giving preference to free list, if not empty */ + if (man->free_spec_cnt) { + *spec_id = man->free_spec_ids[man->free_spec_cnt - 1]; + + /* cache spec ID for current spec string for future lookups */ + err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id); + if (err) + return err; + + man->free_spec_cnt--; + } else { + /* don't allocate spec ID bigger than what fits in specs map */ + if (man->next_free_spec_id >= bpf_map__max_entries(man->specs_map)) + return -E2BIG; + + *spec_id = man->next_free_spec_id; + + /* cache spec ID for current spec string for future lookups */ + err = hashmap__add(specs_hash, target->spec_str, (void *)(long)*spec_id); + if (err) + return err; + + man->next_free_spec_id++; + } + + /* remember new spec ID in the link for later return back to free list on detach */ + link->spec_ids[link->spec_cnt] = *spec_id; + link->spec_cnt++; + *is_new = true; + return 0; +} + +struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct bpf_program *prog, + pid_t pid, const char *path, + const char *usdt_provider, const char *usdt_name, + __u64 usdt_cookie) +{ + int i, fd, err, spec_map_fd, ip_map_fd; + LIBBPF_OPTS(bpf_uprobe_opts, opts); + struct hashmap *specs_hash = NULL; + struct bpf_link_usdt *link = NULL; + struct usdt_target *targets = NULL; + size_t target_cnt; + Elf *elf; + + spec_map_fd = bpf_map__fd(man->specs_map); + ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map); + + /* TODO: perform path resolution similar to uprobe's */ + fd = open(path, O_RDONLY); + if (fd < 0) { + err = -errno; + pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err); + return libbpf_err_ptr(err); + } + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) { + err = -EBADF; + pr_warn("usdt: failed to parse ELF binary '%s': %s\n", path, elf_errmsg(-1)); + goto err_out; + } + + err = sanity_check_usdt_elf(elf, path); + if (err) + goto err_out; + + /* normalize PID filter */ + if (pid < 0) + pid = -1; + else if (pid == 0) + pid = getpid(); + + /* discover USDT in given binary, optionally limiting + * activations to a given PID, if pid > 0 + */ + err = collect_usdt_targets(man, elf, path, pid, usdt_provider, usdt_name, + usdt_cookie, &targets, &target_cnt); + if (err <= 0) { + err = (err == 0) ? -ENOENT : err; + goto err_out; + } + + specs_hash = hashmap__new(specs_hash_fn, specs_equal_fn, NULL); + if (IS_ERR(specs_hash)) { + err = PTR_ERR(specs_hash); + goto err_out; + } + + link = calloc(1, sizeof(*link)); + if (!link) { + err = -ENOMEM; + goto err_out; + } + + link->usdt_man = man; + link->link.detach = &bpf_link_usdt_detach; + link->link.dealloc = &bpf_link_usdt_dealloc; + + link->uprobes = calloc(target_cnt, sizeof(*link->uprobes)); + if (!link->uprobes) { + err = -ENOMEM; + goto err_out; + } + + for (i = 0; i < target_cnt; i++) { + struct usdt_target *target = &targets[i]; + struct bpf_link *uprobe_link; + bool is_new; + int spec_id; + + /* Spec ID can be either reused or newly allocated. If it is + * newly allocated, we'll need to fill out spec map, otherwise + * entire spec should be valid and can be just used by a new + * uprobe. We reuse spec when USDT arg spec is identical. We + * also never share specs between two different USDT + * attachments ("links"), so all the reused specs already + * share USDT cookie value implicitly. + */ + err = allocate_spec_id(man, specs_hash, link, target, &spec_id, &is_new); + if (err) + goto err_out; + + if (is_new && bpf_map_update_elem(spec_map_fd, &spec_id, &target->spec, BPF_ANY)) { + err = -errno; + pr_warn("usdt: failed to set USDT spec #%d for '%s:%s' in '%s': %d\n", + spec_id, usdt_provider, usdt_name, path, err); + goto err_out; + } + if (!man->has_bpf_cookie && + bpf_map_update_elem(ip_map_fd, &target->abs_ip, &spec_id, BPF_NOEXIST)) { + err = -errno; + if (err == -EEXIST) { + pr_warn("usdt: IP collision detected for spec #%d for '%s:%s' in '%s'\n", + spec_id, usdt_provider, usdt_name, path); + } else { + pr_warn("usdt: failed to map IP 0x%lx to spec #%d for '%s:%s' in '%s': %d\n", + target->abs_ip, spec_id, usdt_provider, usdt_name, + path, err); + } + goto err_out; + } + + opts.ref_ctr_offset = target->sema_off; + opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0; + uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path, + target->rel_ip, &opts); + err = libbpf_get_error(uprobe_link); + if (err) { + pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n", + i, usdt_provider, usdt_name, path, err); + goto err_out; + } + + link->uprobes[i].link = uprobe_link; + link->uprobes[i].abs_ip = target->abs_ip; + link->uprobe_cnt++; + } + + free(targets); + hashmap__free(specs_hash); + elf_end(elf); + close(fd); + + return &link->link; + +err_out: + if (link) + bpf_link__destroy(&link->link); + free(targets); + hashmap__free(specs_hash); + if (elf) + elf_end(elf); + close(fd); + return libbpf_err_ptr(err); +} + +/* Parse out USDT ELF note from '.note.stapsdt' section. + * Logic inspired by perf's code. + */ +static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, + const char *data, size_t name_off, size_t desc_off, + struct usdt_note *note) +{ + const char *provider, *name, *args; + long addrs[3]; + size_t len; + + /* sanity check USDT note name and type first */ + if (strncmp(data + name_off, USDT_NOTE_NAME, nhdr->n_namesz) != 0) + return -EINVAL; + if (nhdr->n_type != USDT_NOTE_TYPE) + return -EINVAL; + + /* sanity check USDT note contents ("description" in ELF terminology) */ + len = nhdr->n_descsz; + data = data + desc_off; + + /* +3 is the very minimum required to store three empty strings */ + if (len < sizeof(addrs) + 3) + return -EINVAL; + + /* get location, base, and semaphore addrs */ + memcpy(&addrs, data, sizeof(addrs)); + + /* parse string fields: provider, name, args */ + provider = data + sizeof(addrs); + + name = (const char *)memchr(provider, '\0', data + len - provider); + if (!name) /* non-zero-terminated provider */ + return -EINVAL; + name++; + if (name >= data + len || *name == '\0') /* missing or empty name */ + return -EINVAL; + + args = memchr(name, '\0', data + len - name); + if (!args) /* non-zero-terminated name */ + return -EINVAL; + ++args; + if (args >= data + len) /* missing arguments spec */ + return -EINVAL; + + note->provider = provider; + note->name = name; + if (*args == '\0' || *args == ':') + note->args = ""; + else + note->args = args; + note->loc_addr = addrs[0]; + note->base_addr = addrs[1]; + note->sema_addr = addrs[2]; + + return 0; +} + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg); + +static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie) +{ + const char *s; + int len; + + spec->usdt_cookie = usdt_cookie; + spec->arg_cnt = 0; + + s = note->args; + while (s[0]) { + if (spec->arg_cnt >= USDT_MAX_ARG_CNT) { + pr_warn("usdt: too many USDT arguments (> %d) for '%s:%s' with args spec '%s'\n", + USDT_MAX_ARG_CNT, note->provider, note->name, note->args); + return -E2BIG; + } + + len = parse_usdt_arg(s, spec->arg_cnt, &spec->args[spec->arg_cnt]); + if (len < 0) + return len; + + s += len; + spec->arg_cnt++; + } + + return 0; +} + +/* Architecture-specific logic for parsing USDT argument location specs */ + +#if defined(__x86_64__) || defined(__i386__) + +static int calc_pt_regs_off(const char *reg_name) +{ + static struct { + const char *names[4]; + size_t pt_regs_off; + } reg_map[] = { +#ifdef __x86_64__ +#define reg_off(reg64, reg32) offsetof(struct pt_regs, reg64) +#else +#define reg_off(reg64, reg32) offsetof(struct pt_regs, reg32) +#endif + { {"rip", "eip", "", ""}, reg_off(rip, eip) }, + { {"rax", "eax", "ax", "al"}, reg_off(rax, eax) }, + { {"rbx", "ebx", "bx", "bl"}, reg_off(rbx, ebx) }, + { {"rcx", "ecx", "cx", "cl"}, reg_off(rcx, ecx) }, + { {"rdx", "edx", "dx", "dl"}, reg_off(rdx, edx) }, + { {"rsi", "esi", "si", "sil"}, reg_off(rsi, esi) }, + { {"rdi", "edi", "di", "dil"}, reg_off(rdi, edi) }, + { {"rbp", "ebp", "bp", "bpl"}, reg_off(rbp, ebp) }, + { {"rsp", "esp", "sp", "spl"}, reg_off(rsp, esp) }, +#undef reg_off +#ifdef __x86_64__ + { {"r8", "r8d", "r8w", "r8b"}, offsetof(struct pt_regs, r8) }, + { {"r9", "r9d", "r9w", "r9b"}, offsetof(struct pt_regs, r9) }, + { {"r10", "r10d", "r10w", "r10b"}, offsetof(struct pt_regs, r10) }, + { {"r11", "r11d", "r11w", "r11b"}, offsetof(struct pt_regs, r11) }, + { {"r12", "r12d", "r12w", "r12b"}, offsetof(struct pt_regs, r12) }, + { {"r13", "r13d", "r13w", "r13b"}, offsetof(struct pt_regs, r13) }, + { {"r14", "r14d", "r14w", "r14b"}, offsetof(struct pt_regs, r14) }, + { {"r15", "r15d", "r15w", "r15b"}, offsetof(struct pt_regs, r15) }, +#endif + }; + int i, j; + + for (i = 0; i < ARRAY_SIZE(reg_map); i++) { + for (j = 0; j < ARRAY_SIZE(reg_map[i].names); j++) { + if (strcmp(reg_name, reg_map[i].names[j]) == 0) + return reg_map[i].pt_regs_off; + } + } + + pr_warn("usdt: unrecognized register '%s'\n", reg_name); + return -ENOENT; +} + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + char *reg_name = NULL; + int arg_sz, len, reg_off; + long off; + + if (sscanf(arg_str, " %d @ %ld ( %%%m[^)] ) %n", &arg_sz, &off, ®_name, &len) == 3) { + /* Memory dereference case, e.g., -4@-20(%rbp) */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = off; + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ %%%ms %n", &arg_sz, ®_name, &len) == 2) { + /* Register read case, e.g., -4@%eax */ + arg->arg_type = USDT_ARG_REG; + arg->val_off = 0; + + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ $%ld %n", &arg_sz, &off, &len) == 2) { + /* Constant value case, e.g., 4@$71 */ + arg->arg_type = USDT_ARG_CONST; + arg->val_off = off; + arg->reg_off = 0; + } else { + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); + return -EINVAL; + } + + arg->arg_signed = arg_sz < 0; + if (arg_sz < 0) + arg_sz = -arg_sz; + + switch (arg_sz) { + case 1: case 2: case 4: case 8: + arg->arg_bitshift = 64 - arg_sz * 8; + break; + default: + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", + arg_num, arg_str, arg_sz); + return -EINVAL; + } + + return len; +} + +#elif defined(__s390x__) + +/* Do not support __s390__ for now, since user_pt_regs is broken with -m31. */ + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + unsigned int reg; + int arg_sz, len; + long off; + + if (sscanf(arg_str, " %d @ %ld ( %%r%u ) %n", &arg_sz, &off, ®, &len) == 3) { + /* Memory dereference case, e.g., -2@-28(%r15) */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = off; + if (reg > 15) { + pr_warn("usdt: unrecognized register '%%r%u'\n", reg); + return -EINVAL; + } + arg->reg_off = offsetof(user_pt_regs, gprs[reg]); + } else if (sscanf(arg_str, " %d @ %%r%u %n", &arg_sz, ®, &len) == 2) { + /* Register read case, e.g., -8@%r0 */ + arg->arg_type = USDT_ARG_REG; + arg->val_off = 0; + if (reg > 15) { + pr_warn("usdt: unrecognized register '%%r%u'\n", reg); + return -EINVAL; + } + arg->reg_off = offsetof(user_pt_regs, gprs[reg]); + } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { + /* Constant value case, e.g., 4@71 */ + arg->arg_type = USDT_ARG_CONST; + arg->val_off = off; + arg->reg_off = 0; + } else { + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); + return -EINVAL; + } + + arg->arg_signed = arg_sz < 0; + if (arg_sz < 0) + arg_sz = -arg_sz; + + switch (arg_sz) { + case 1: case 2: case 4: case 8: + arg->arg_bitshift = 64 - arg_sz * 8; + break; + default: + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", + arg_num, arg_str, arg_sz); + return -EINVAL; + } + + return len; +} + +#elif defined(__aarch64__) + +static int calc_pt_regs_off(const char *reg_name) +{ + int reg_num; + + if (sscanf(reg_name, "x%d", ®_num) == 1) { + if (reg_num >= 0 && reg_num < 31) + return offsetof(struct user_pt_regs, regs[reg_num]); + } else if (strcmp(reg_name, "sp") == 0) { + return offsetof(struct user_pt_regs, sp); + } + pr_warn("usdt: unrecognized register '%s'\n", reg_name); + return -ENOENT; +} + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + char *reg_name = NULL; + int arg_sz, len, reg_off; + long off; + + if (sscanf(arg_str, " %d @ \[ %m[a-z0-9], %ld ] %n", &arg_sz, ®_name, &off, &len) == 3) { + /* Memory dereference case, e.g., -4@[sp, 96] */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = off; + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ \[ %m[a-z0-9] ] %n", &arg_sz, ®_name, &len) == 2) { + /* Memory dereference case, e.g., -4@[sp] */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = 0; + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { + /* Constant value case, e.g., 4@5 */ + arg->arg_type = USDT_ARG_CONST; + arg->val_off = off; + arg->reg_off = 0; + } else if (sscanf(arg_str, " %d @ %m[a-z0-9] %n", &arg_sz, ®_name, &len) == 2) { + /* Register read case, e.g., -8@x4 */ + arg->arg_type = USDT_ARG_REG; + arg->val_off = 0; + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else { + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); + return -EINVAL; + } + + arg->arg_signed = arg_sz < 0; + if (arg_sz < 0) + arg_sz = -arg_sz; + + switch (arg_sz) { + case 1: case 2: case 4: case 8: + arg->arg_bitshift = 64 - arg_sz * 8; + break; + default: + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", + arg_num, arg_str, arg_sz); + return -EINVAL; + } + + return len; +} + +#elif defined(__riscv) + +static int calc_pt_regs_off(const char *reg_name) +{ + static struct { + const char *name; + size_t pt_regs_off; + } reg_map[] = { + { "ra", offsetof(struct user_regs_struct, ra) }, + { "sp", offsetof(struct user_regs_struct, sp) }, + { "gp", offsetof(struct user_regs_struct, gp) }, + { "tp", offsetof(struct user_regs_struct, tp) }, + { "a0", offsetof(struct user_regs_struct, a0) }, + { "a1", offsetof(struct user_regs_struct, a1) }, + { "a2", offsetof(struct user_regs_struct, a2) }, + { "a3", offsetof(struct user_regs_struct, a3) }, + { "a4", offsetof(struct user_regs_struct, a4) }, + { "a5", offsetof(struct user_regs_struct, a5) }, + { "a6", offsetof(struct user_regs_struct, a6) }, + { "a7", offsetof(struct user_regs_struct, a7) }, + { "s0", offsetof(struct user_regs_struct, s0) }, + { "s1", offsetof(struct user_regs_struct, s1) }, + { "s2", offsetof(struct user_regs_struct, s2) }, + { "s3", offsetof(struct user_regs_struct, s3) }, + { "s4", offsetof(struct user_regs_struct, s4) }, + { "s5", offsetof(struct user_regs_struct, s5) }, + { "s6", offsetof(struct user_regs_struct, s6) }, + { "s7", offsetof(struct user_regs_struct, s7) }, + { "s8", offsetof(struct user_regs_struct, rv_s8) }, + { "s9", offsetof(struct user_regs_struct, s9) }, + { "s10", offsetof(struct user_regs_struct, s10) }, + { "s11", offsetof(struct user_regs_struct, s11) }, + { "t0", offsetof(struct user_regs_struct, t0) }, + { "t1", offsetof(struct user_regs_struct, t1) }, + { "t2", offsetof(struct user_regs_struct, t2) }, + { "t3", offsetof(struct user_regs_struct, t3) }, + { "t4", offsetof(struct user_regs_struct, t4) }, + { "t5", offsetof(struct user_regs_struct, t5) }, + { "t6", offsetof(struct user_regs_struct, t6) }, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(reg_map); i++) { + if (strcmp(reg_name, reg_map[i].name) == 0) + return reg_map[i].pt_regs_off; + } + + pr_warn("usdt: unrecognized register '%s'\n", reg_name); + return -ENOENT; +} + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + char *reg_name = NULL; + int arg_sz, len, reg_off; + long off; + + if (sscanf(arg_str, " %d @ %ld ( %m[a-z0-9] ) %n", &arg_sz, &off, ®_name, &len) == 3) { + /* Memory dereference case, e.g., -8@-88(s0) */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = off; + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { + /* Constant value case, e.g., 4@5 */ + arg->arg_type = USDT_ARG_CONST; + arg->val_off = off; + arg->reg_off = 0; + } else if (sscanf(arg_str, " %d @ %m[a-z0-9] %n", &arg_sz, ®_name, &len) == 2) { + /* Register read case, e.g., -8@a1 */ + arg->arg_type = USDT_ARG_REG; + arg->val_off = 0; + reg_off = calc_pt_regs_off(reg_name); + free(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else { + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); + return -EINVAL; + } + + arg->arg_signed = arg_sz < 0; + if (arg_sz < 0) + arg_sz = -arg_sz; + + switch (arg_sz) { + case 1: case 2: case 4: case 8: + arg->arg_bitshift = 64 - arg_sz * 8; + break; + default: + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", + arg_num, arg_str, arg_sz); + return -EINVAL; + } + + return len; +} + +#else + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +{ + pr_warn("usdt: libbpf doesn't support USDTs on current architecture\n"); + return -ENOTSUP; +} + +#endif diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c deleted file mode 100644 index 81f8fbc85e70..000000000000 --- a/tools/lib/bpf/xsk.c +++ /dev/null @@ -1,1266 +0,0 @@ -// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) - -/* - * AF_XDP user-space access library. - * - * Copyright(c) 2018 - 2019 Intel Corporation. - * - * Author(s): Magnus Karlsson <magnus.karlsson@intel.com> - */ - -#include <errno.h> -#include <stdlib.h> -#include <string.h> -#include <unistd.h> -#include <arpa/inet.h> -#include <asm/barrier.h> -#include <linux/compiler.h> -#include <linux/ethtool.h> -#include <linux/filter.h> -#include <linux/if_ether.h> -#include <linux/if_packet.h> -#include <linux/if_xdp.h> -#include <linux/kernel.h> -#include <linux/list.h> -#include <linux/sockios.h> -#include <net/if.h> -#include <sys/ioctl.h> -#include <sys/mman.h> -#include <sys/socket.h> -#include <sys/types.h> -#include <linux/if_link.h> - -#include "bpf.h" -#include "libbpf.h" -#include "libbpf_internal.h" -#include "xsk.h" - -#ifndef SOL_XDP - #define SOL_XDP 283 -#endif - -#ifndef AF_XDP - #define AF_XDP 44 -#endif - -#ifndef PF_XDP - #define PF_XDP AF_XDP -#endif - -enum xsk_prog { - XSK_PROG_FALLBACK, - XSK_PROG_REDIRECT_FLAGS, -}; - -struct xsk_umem { - struct xsk_ring_prod *fill_save; - struct xsk_ring_cons *comp_save; - char *umem_area; - struct xsk_umem_config config; - int fd; - int refcount; - struct list_head ctx_list; - bool rx_ring_setup_done; - bool tx_ring_setup_done; -}; - -struct xsk_ctx { - struct xsk_ring_prod *fill; - struct xsk_ring_cons *comp; - __u32 queue_id; - struct xsk_umem *umem; - int refcount; - int ifindex; - struct list_head list; - int prog_fd; - int link_fd; - int xsks_map_fd; - char ifname[IFNAMSIZ]; - bool has_bpf_link; -}; - -struct xsk_socket { - struct xsk_ring_cons *rx; - struct xsk_ring_prod *tx; - __u64 outstanding_tx; - struct xsk_ctx *ctx; - struct xsk_socket_config config; - int fd; -}; - -struct xsk_nl_info { - bool xdp_prog_attached; - int ifindex; - int fd; -}; - -/* Up until and including Linux 5.3 */ -struct xdp_ring_offset_v1 { - __u64 producer; - __u64 consumer; - __u64 desc; -}; - -/* Up until and including Linux 5.3 */ -struct xdp_mmap_offsets_v1 { - struct xdp_ring_offset_v1 rx; - struct xdp_ring_offset_v1 tx; - struct xdp_ring_offset_v1 fr; - struct xdp_ring_offset_v1 cr; -}; - -int xsk_umem__fd(const struct xsk_umem *umem) -{ - return umem ? umem->fd : -EINVAL; -} - -int xsk_socket__fd(const struct xsk_socket *xsk) -{ - return xsk ? xsk->fd : -EINVAL; -} - -static bool xsk_page_aligned(void *buffer) -{ - unsigned long addr = (unsigned long)buffer; - - return !(addr & (getpagesize() - 1)); -} - -static void xsk_set_umem_config(struct xsk_umem_config *cfg, - const struct xsk_umem_config *usr_cfg) -{ - if (!usr_cfg) { - cfg->fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - cfg->comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; - cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; - cfg->flags = XSK_UMEM__DEFAULT_FLAGS; - return; - } - - cfg->fill_size = usr_cfg->fill_size; - cfg->comp_size = usr_cfg->comp_size; - cfg->frame_size = usr_cfg->frame_size; - cfg->frame_headroom = usr_cfg->frame_headroom; - cfg->flags = usr_cfg->flags; -} - -static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, - const struct xsk_socket_config *usr_cfg) -{ - if (!usr_cfg) { - cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; - cfg->tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - cfg->libbpf_flags = 0; - cfg->xdp_flags = 0; - cfg->bind_flags = 0; - return 0; - } - - if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD) - return -EINVAL; - - cfg->rx_size = usr_cfg->rx_size; - cfg->tx_size = usr_cfg->tx_size; - cfg->libbpf_flags = usr_cfg->libbpf_flags; - cfg->xdp_flags = usr_cfg->xdp_flags; - cfg->bind_flags = usr_cfg->bind_flags; - - return 0; -} - -static void xsk_mmap_offsets_v1(struct xdp_mmap_offsets *off) -{ - struct xdp_mmap_offsets_v1 off_v1; - - /* getsockopt on a kernel <= 5.3 has no flags fields. - * Copy over the offsets to the correct places in the >=5.4 format - * and put the flags where they would have been on that kernel. - */ - memcpy(&off_v1, off, sizeof(off_v1)); - - off->rx.producer = off_v1.rx.producer; - off->rx.consumer = off_v1.rx.consumer; - off->rx.desc = off_v1.rx.desc; - off->rx.flags = off_v1.rx.consumer + sizeof(__u32); - - off->tx.producer = off_v1.tx.producer; - off->tx.consumer = off_v1.tx.consumer; - off->tx.desc = off_v1.tx.desc; - off->tx.flags = off_v1.tx.consumer + sizeof(__u32); - - off->fr.producer = off_v1.fr.producer; - off->fr.consumer = off_v1.fr.consumer; - off->fr.desc = off_v1.fr.desc; - off->fr.flags = off_v1.fr.consumer + sizeof(__u32); - - off->cr.producer = off_v1.cr.producer; - off->cr.consumer = off_v1.cr.consumer; - off->cr.desc = off_v1.cr.desc; - off->cr.flags = off_v1.cr.consumer + sizeof(__u32); -} - -static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off) -{ - socklen_t optlen; - int err; - - optlen = sizeof(*off); - err = getsockopt(fd, SOL_XDP, XDP_MMAP_OFFSETS, off, &optlen); - if (err) - return err; - - if (optlen == sizeof(*off)) - return 0; - - if (optlen == sizeof(struct xdp_mmap_offsets_v1)) { - xsk_mmap_offsets_v1(off); - return 0; - } - - return -EINVAL; -} - -static int xsk_create_umem_rings(struct xsk_umem *umem, int fd, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp) -{ - struct xdp_mmap_offsets off; - void *map; - int err; - - err = setsockopt(fd, SOL_XDP, XDP_UMEM_FILL_RING, - &umem->config.fill_size, - sizeof(umem->config.fill_size)); - if (err) - return -errno; - - err = setsockopt(fd, SOL_XDP, XDP_UMEM_COMPLETION_RING, - &umem->config.comp_size, - sizeof(umem->config.comp_size)); - if (err) - return -errno; - - err = xsk_get_mmap_offsets(fd, &off); - if (err) - return -errno; - - map = mmap(NULL, off.fr.desc + umem->config.fill_size * sizeof(__u64), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd, - XDP_UMEM_PGOFF_FILL_RING); - if (map == MAP_FAILED) - return -errno; - - fill->mask = umem->config.fill_size - 1; - fill->size = umem->config.fill_size; - fill->producer = map + off.fr.producer; - fill->consumer = map + off.fr.consumer; - fill->flags = map + off.fr.flags; - fill->ring = map + off.fr.desc; - fill->cached_cons = umem->config.fill_size; - - map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd, - XDP_UMEM_PGOFF_COMPLETION_RING); - if (map == MAP_FAILED) { - err = -errno; - goto out_mmap; - } - - comp->mask = umem->config.comp_size - 1; - comp->size = umem->config.comp_size; - comp->producer = map + off.cr.producer; - comp->consumer = map + off.cr.consumer; - comp->flags = map + off.cr.flags; - comp->ring = map + off.cr.desc; - - return 0; - -out_mmap: - munmap(map, off.fr.desc + umem->config.fill_size * sizeof(__u64)); - return err; -} - -DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) -int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, - __u64 size, struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_umem_config *usr_config) -{ - struct xdp_umem_reg mr; - struct xsk_umem *umem; - int err; - - if (!umem_area || !umem_ptr || !fill || !comp) - return -EFAULT; - if (!size && !xsk_page_aligned(umem_area)) - return -EINVAL; - - umem = calloc(1, sizeof(*umem)); - if (!umem) - return -ENOMEM; - - umem->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0); - if (umem->fd < 0) { - err = -errno; - goto out_umem_alloc; - } - - umem->umem_area = umem_area; - INIT_LIST_HEAD(&umem->ctx_list); - xsk_set_umem_config(&umem->config, usr_config); - - memset(&mr, 0, sizeof(mr)); - mr.addr = (uintptr_t)umem_area; - mr.len = size; - mr.chunk_size = umem->config.frame_size; - mr.headroom = umem->config.frame_headroom; - mr.flags = umem->config.flags; - - err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr)); - if (err) { - err = -errno; - goto out_socket; - } - - err = xsk_create_umem_rings(umem, umem->fd, fill, comp); - if (err) - goto out_socket; - - umem->fill_save = fill; - umem->comp_save = comp; - *umem_ptr = umem; - return 0; - -out_socket: - close(umem->fd); -out_umem_alloc: - free(umem); - return err; -} - -struct xsk_umem_config_v1 { - __u32 fill_size; - __u32 comp_size; - __u32 frame_size; - __u32 frame_headroom; -}; - -COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) -int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, - __u64 size, struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_umem_config *usr_config) -{ - struct xsk_umem_config config; - - memcpy(&config, usr_config, sizeof(struct xsk_umem_config_v1)); - config.flags = 0; - - return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp, - &config); -} - -static enum xsk_prog get_xsk_prog(void) -{ - enum xsk_prog detected = XSK_PROG_FALLBACK; - struct bpf_load_program_attr prog_attr; - struct bpf_create_map_attr map_attr; - __u32 size_out, retval, duration; - char data_in = 0, data_out; - struct bpf_insn insns[] = { - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_MOV64_IMM(BPF_REG_3, XDP_PASS), - BPF_EMIT_CALL(BPF_FUNC_redirect_map), - BPF_EXIT_INSN(), - }; - int prog_fd, map_fd, ret; - - memset(&map_attr, 0, sizeof(map_attr)); - map_attr.map_type = BPF_MAP_TYPE_XSKMAP; - map_attr.key_size = sizeof(int); - map_attr.value_size = sizeof(int); - map_attr.max_entries = 1; - - map_fd = bpf_create_map_xattr(&map_attr); - if (map_fd < 0) - return detected; - - insns[0].imm = map_fd; - - memset(&prog_attr, 0, sizeof(prog_attr)); - prog_attr.prog_type = BPF_PROG_TYPE_XDP; - prog_attr.insns = insns; - prog_attr.insns_cnt = ARRAY_SIZE(insns); - prog_attr.license = "GPL"; - - prog_fd = bpf_load_program_xattr(&prog_attr, NULL, 0); - if (prog_fd < 0) { - close(map_fd); - return detected; - } - - ret = bpf_prog_test_run(prog_fd, 0, &data_in, 1, &data_out, &size_out, &retval, &duration); - if (!ret && retval == XDP_PASS) - detected = XSK_PROG_REDIRECT_FLAGS; - close(prog_fd); - close(map_fd); - return detected; -} - -static int xsk_load_xdp_prog(struct xsk_socket *xsk) -{ - static const int log_buf_size = 16 * 1024; - struct xsk_ctx *ctx = xsk->ctx; - char log_buf[log_buf_size]; - int prog_fd; - - /* This is the fallback C-program: - * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) - * { - * int ret, index = ctx->rx_queue_index; - * - * // A set entry here means that the correspnding queue_id - * // has an active AF_XDP socket bound to it. - * ret = bpf_redirect_map(&xsks_map, index, XDP_PASS); - * if (ret > 0) - * return ret; - * - * // Fallback for pre-5.3 kernels, not supporting default - * // action in the flags parameter. - * if (bpf_map_lookup_elem(&xsks_map, &index)) - * return bpf_redirect_map(&xsks_map, index, 0); - * return XDP_PASS; - * } - */ - struct bpf_insn prog[] = { - /* r2 = *(u32 *)(r1 + 16) */ - BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16), - /* *(u32 *)(r10 - 4) = r2 */ - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -4), - /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), - /* r3 = XDP_PASS */ - BPF_MOV64_IMM(BPF_REG_3, 2), - /* call bpf_redirect_map */ - BPF_EMIT_CALL(BPF_FUNC_redirect_map), - /* if w0 != 0 goto pc+13 */ - BPF_JMP32_IMM(BPF_JSGT, BPF_REG_0, 0, 13), - /* r2 = r10 */ - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - /* r2 += -4 */ - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), - /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), - /* call bpf_map_lookup_elem */ - BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), - /* r1 = r0 */ - BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), - /* r0 = XDP_PASS */ - BPF_MOV64_IMM(BPF_REG_0, 2), - /* if r1 == 0 goto pc+5 */ - BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5), - /* r2 = *(u32 *)(r10 - 4) */ - BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_10, -4), - /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), - /* r3 = 0 */ - BPF_MOV64_IMM(BPF_REG_3, 0), - /* call bpf_redirect_map */ - BPF_EMIT_CALL(BPF_FUNC_redirect_map), - /* The jumps are to this instruction */ - BPF_EXIT_INSN(), - }; - - /* This is the post-5.3 kernel C-program: - * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) - * { - * return bpf_redirect_map(&xsks_map, ctx->rx_queue_index, XDP_PASS); - * } - */ - struct bpf_insn prog_redirect_flags[] = { - /* r2 = *(u32 *)(r1 + 16) */ - BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16), - /* r1 = xskmap[] */ - BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd), - /* r3 = XDP_PASS */ - BPF_MOV64_IMM(BPF_REG_3, 2), - /* call bpf_redirect_map */ - 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), - }; - struct bpf_insn *progs[] = {prog, prog_redirect_flags}; - enum xsk_prog option = get_xsk_prog(); - - prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, progs[option], insns_cnt[option], - "LGPL-2.1 or BSD-2-Clause", 0, log_buf, - log_buf_size); - if (prog_fd < 0) { - pr_warn("BPF log buffer:\n%s", log_buf); - return prog_fd; - } - - ctx->prog_fd = prog_fd; - return 0; -} - -static int xsk_create_bpf_link(struct xsk_socket *xsk) -{ - DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts); - struct xsk_ctx *ctx = xsk->ctx; - __u32 prog_id = 0; - int link_fd; - int err; - - err = bpf_get_link_xdp_id(ctx->ifindex, &prog_id, xsk->config.xdp_flags); - if (err) { - pr_warn("getting XDP prog id failed\n"); - return err; - } - - /* if there's a netlink-based XDP prog loaded on interface, bail out - * and ask user to do the removal by himself - */ - if (prog_id) { - pr_warn("Netlink-based XDP prog detected, please unload it in order to launch AF_XDP prog\n"); - return -EINVAL; - } - - opts.flags = xsk->config.xdp_flags & ~(XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_REPLACE); - - link_fd = bpf_link_create(ctx->prog_fd, ctx->ifindex, BPF_XDP, &opts); - if (link_fd < 0) { - pr_warn("bpf_link_create failed: %s\n", strerror(errno)); - return link_fd; - } - - ctx->link_fd = link_fd; - return 0; -} - -static int xsk_get_max_queues(struct xsk_socket *xsk) -{ - struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; - struct xsk_ctx *ctx = xsk->ctx; - struct ifreq ifr = {}; - int fd, err, ret; - - fd = socket(AF_LOCAL, SOCK_DGRAM | SOCK_CLOEXEC, 0); - if (fd < 0) - return -errno; - - ifr.ifr_data = (void *)&channels; - memcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ - 1); - ifr.ifr_name[IFNAMSIZ - 1] = '\0'; - err = ioctl(fd, SIOCETHTOOL, &ifr); - if (err && errno != EOPNOTSUPP) { - ret = -errno; - goto out; - } - - if (err) { - /* If the device says it has no channels, then all traffic - * is sent to a single stream, so max queues = 1. - */ - ret = 1; - } else { - /* Take the max of rx, tx, combined. Drivers return - * the number of channels in different ways. - */ - ret = max(channels.max_rx, channels.max_tx); - ret = max(ret, (int)channels.max_combined); - } - -out: - close(fd); - return ret; -} - -static int xsk_create_bpf_maps(struct xsk_socket *xsk) -{ - struct xsk_ctx *ctx = xsk->ctx; - int max_queues; - int fd; - - max_queues = xsk_get_max_queues(xsk); - if (max_queues < 0) - return max_queues; - - fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map", - sizeof(int), sizeof(int), max_queues, 0); - if (fd < 0) - return fd; - - ctx->xsks_map_fd = fd; - - return 0; -} - -static void xsk_delete_bpf_maps(struct xsk_socket *xsk) -{ - struct xsk_ctx *ctx = xsk->ctx; - - bpf_map_delete_elem(ctx->xsks_map_fd, &ctx->queue_id); - close(ctx->xsks_map_fd); -} - -static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) -{ - __u32 i, *map_ids, num_maps, prog_len = sizeof(struct bpf_prog_info); - __u32 map_len = sizeof(struct bpf_map_info); - struct bpf_prog_info prog_info = {}; - struct xsk_ctx *ctx = xsk->ctx; - struct bpf_map_info map_info; - int fd, err; - - err = bpf_obj_get_info_by_fd(ctx->prog_fd, &prog_info, &prog_len); - if (err) - return err; - - num_maps = prog_info.nr_map_ids; - - map_ids = calloc(prog_info.nr_map_ids, sizeof(*map_ids)); - if (!map_ids) - return -ENOMEM; - - memset(&prog_info, 0, prog_len); - prog_info.nr_map_ids = num_maps; - prog_info.map_ids = (__u64)(unsigned long)map_ids; - - err = bpf_obj_get_info_by_fd(ctx->prog_fd, &prog_info, &prog_len); - if (err) - goto out_map_ids; - - ctx->xsks_map_fd = -1; - - for (i = 0; i < prog_info.nr_map_ids; i++) { - fd = bpf_map_get_fd_by_id(map_ids[i]); - if (fd < 0) - continue; - - memset(&map_info, 0, map_len); - err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len); - if (err) { - close(fd); - continue; - } - - if (!strncmp(map_info.name, "xsks_map", sizeof(map_info.name))) { - ctx->xsks_map_fd = fd; - break; - } - - close(fd); - } - - if (ctx->xsks_map_fd == -1) - err = -ENOENT; - -out_map_ids: - free(map_ids); - return err; -} - -static int xsk_set_bpf_maps(struct xsk_socket *xsk) -{ - struct xsk_ctx *ctx = xsk->ctx; - - return bpf_map_update_elem(ctx->xsks_map_fd, &ctx->queue_id, - &xsk->fd, 0); -} - -static int xsk_link_lookup(int ifindex, __u32 *prog_id, int *link_fd) -{ - struct bpf_link_info link_info; - __u32 link_len; - __u32 id = 0; - int err; - int fd; - - while (true) { - err = bpf_link_get_next_id(id, &id); - if (err) { - if (errno == ENOENT) { - err = 0; - break; - } - pr_warn("can't get next link: %s\n", strerror(errno)); - break; - } - - fd = bpf_link_get_fd_by_id(id); - if (fd < 0) { - if (errno == ENOENT) - continue; - pr_warn("can't get link by id (%u): %s\n", id, strerror(errno)); - err = -errno; - break; - } - - link_len = sizeof(struct bpf_link_info); - memset(&link_info, 0, link_len); - err = bpf_obj_get_info_by_fd(fd, &link_info, &link_len); - if (err) { - pr_warn("can't get link info: %s\n", strerror(errno)); - close(fd); - break; - } - if (link_info.type == BPF_LINK_TYPE_XDP) { - if (link_info.xdp.ifindex == ifindex) { - *link_fd = fd; - if (prog_id) - *prog_id = link_info.prog_id; - break; - } - } - close(fd); - } - - return err; -} - -static bool xsk_probe_bpf_link(void) -{ - DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts, - .flags = XDP_FLAGS_SKB_MODE); - struct bpf_load_program_attr prog_attr; - struct bpf_insn insns[2] = { - BPF_MOV64_IMM(BPF_REG_0, XDP_PASS), - BPF_EXIT_INSN() - }; - int prog_fd, link_fd = -1; - int ifindex_lo = 1; - bool ret = false; - int err; - - err = xsk_link_lookup(ifindex_lo, NULL, &link_fd); - if (err) - return ret; - - if (link_fd >= 0) - return true; - - memset(&prog_attr, 0, sizeof(prog_attr)); - prog_attr.prog_type = BPF_PROG_TYPE_XDP; - prog_attr.insns = insns; - prog_attr.insns_cnt = ARRAY_SIZE(insns); - prog_attr.license = "GPL"; - - prog_fd = bpf_load_program_xattr(&prog_attr, NULL, 0); - if (prog_fd < 0) - return ret; - - link_fd = bpf_link_create(prog_fd, ifindex_lo, BPF_XDP, &opts); - close(prog_fd); - - if (link_fd >= 0) { - ret = true; - close(link_fd); - } - - return ret; -} - -static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk) -{ - char ifname[IFNAMSIZ]; - struct xsk_ctx *ctx; - char *interface; - - ctx = calloc(1, sizeof(*ctx)); - if (!ctx) - return -ENOMEM; - - interface = if_indextoname(ifindex, &ifname[0]); - if (!interface) { - free(ctx); - return -errno; - } - - ctx->ifindex = ifindex; - memcpy(ctx->ifname, ifname, IFNAMSIZ -1); - ctx->ifname[IFNAMSIZ - 1] = 0; - - xsk->ctx = ctx; - xsk->ctx->has_bpf_link = xsk_probe_bpf_link(); - - return 0; -} - -static int xsk_init_xdp_res(struct xsk_socket *xsk, - int *xsks_map_fd) -{ - struct xsk_ctx *ctx = xsk->ctx; - int err; - - err = xsk_create_bpf_maps(xsk); - if (err) - return err; - - err = xsk_load_xdp_prog(xsk); - if (err) - goto err_load_xdp_prog; - - if (ctx->has_bpf_link) - err = xsk_create_bpf_link(xsk); - else - err = bpf_set_link_xdp_fd(xsk->ctx->ifindex, ctx->prog_fd, - xsk->config.xdp_flags); - - if (err) - goto err_attach_xdp_prog; - - if (!xsk->rx) - return err; - - err = xsk_set_bpf_maps(xsk); - if (err) - goto err_set_bpf_maps; - - return err; - -err_set_bpf_maps: - if (ctx->has_bpf_link) - close(ctx->link_fd); - else - bpf_set_link_xdp_fd(ctx->ifindex, -1, 0); -err_attach_xdp_prog: - close(ctx->prog_fd); -err_load_xdp_prog: - xsk_delete_bpf_maps(xsk); - return err; -} - -static int xsk_lookup_xdp_res(struct xsk_socket *xsk, int *xsks_map_fd, int prog_id) -{ - struct xsk_ctx *ctx = xsk->ctx; - int err; - - ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id); - if (ctx->prog_fd < 0) { - err = -errno; - goto err_prog_fd; - } - err = xsk_lookup_bpf_maps(xsk); - if (err) - goto err_lookup_maps; - - if (!xsk->rx) - return err; - - err = xsk_set_bpf_maps(xsk); - if (err) - goto err_set_maps; - - return err; - -err_set_maps: - close(ctx->xsks_map_fd); -err_lookup_maps: - close(ctx->prog_fd); -err_prog_fd: - if (ctx->has_bpf_link) - close(ctx->link_fd); - return err; -} - -static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp, int *xsks_map_fd) -{ - struct xsk_socket *xsk = _xdp; - struct xsk_ctx *ctx = xsk->ctx; - __u32 prog_id = 0; - int err; - - if (ctx->has_bpf_link) - err = xsk_link_lookup(ctx->ifindex, &prog_id, &ctx->link_fd); - else - err = bpf_get_link_xdp_id(ctx->ifindex, &prog_id, xsk->config.xdp_flags); - - if (err) - return err; - - err = !prog_id ? xsk_init_xdp_res(xsk, xsks_map_fd) : - xsk_lookup_xdp_res(xsk, xsks_map_fd, prog_id); - - if (!err && xsks_map_fd) - *xsks_map_fd = ctx->xsks_map_fd; - - return err; -} - -static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex, - __u32 queue_id) -{ - struct xsk_ctx *ctx; - - if (list_empty(&umem->ctx_list)) - return NULL; - - list_for_each_entry(ctx, &umem->ctx_list, list) { - if (ctx->ifindex == ifindex && ctx->queue_id == queue_id) { - ctx->refcount++; - return ctx; - } - } - - return NULL; -} - -static void xsk_put_ctx(struct xsk_ctx *ctx, bool unmap) -{ - struct xsk_umem *umem = ctx->umem; - struct xdp_mmap_offsets off; - int err; - - if (--ctx->refcount) - return; - - if (!unmap) - goto out_free; - - err = xsk_get_mmap_offsets(umem->fd, &off); - if (err) - goto out_free; - - munmap(ctx->fill->ring - off.fr.desc, off.fr.desc + umem->config.fill_size * - sizeof(__u64)); - munmap(ctx->comp->ring - off.cr.desc, off.cr.desc + umem->config.comp_size * - sizeof(__u64)); - -out_free: - list_del(&ctx->list); - free(ctx); -} - -static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk, - struct xsk_umem *umem, int ifindex, - const char *ifname, __u32 queue_id, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp) -{ - struct xsk_ctx *ctx; - int err; - - ctx = calloc(1, sizeof(*ctx)); - if (!ctx) - return NULL; - - if (!umem->fill_save) { - err = xsk_create_umem_rings(umem, xsk->fd, fill, comp); - if (err) { - free(ctx); - return NULL; - } - } else if (umem->fill_save != fill || umem->comp_save != comp) { - /* Copy over rings to new structs. */ - memcpy(fill, umem->fill_save, sizeof(*fill)); - memcpy(comp, umem->comp_save, sizeof(*comp)); - } - - ctx->ifindex = ifindex; - ctx->refcount = 1; - ctx->umem = umem; - ctx->queue_id = queue_id; - memcpy(ctx->ifname, ifname, IFNAMSIZ - 1); - ctx->ifname[IFNAMSIZ - 1] = '\0'; - - ctx->fill = fill; - ctx->comp = comp; - list_add(&ctx->list, &umem->ctx_list); - return ctx; -} - -static void xsk_destroy_xsk_struct(struct xsk_socket *xsk) -{ - free(xsk->ctx); - free(xsk); -} - -int xsk_socket__update_xskmap(struct xsk_socket *xsk, int fd) -{ - xsk->ctx->xsks_map_fd = fd; - return xsk_set_bpf_maps(xsk); -} - -int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd) -{ - struct xsk_socket *xsk; - int res; - - xsk = calloc(1, sizeof(*xsk)); - if (!xsk) - return -ENOMEM; - - res = xsk_create_xsk_struct(ifindex, xsk); - if (res) { - free(xsk); - return -EINVAL; - } - - res = __xsk_setup_xdp_prog(xsk, xsks_map_fd); - - xsk_destroy_xsk_struct(xsk); - - return res; -} - -int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, - const char *ifname, - __u32 queue_id, struct xsk_umem *umem, - struct xsk_ring_cons *rx, - struct xsk_ring_prod *tx, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_socket_config *usr_config) -{ - bool unmap, rx_setup_done = false, tx_setup_done = false; - void *rx_map = NULL, *tx_map = NULL; - struct sockaddr_xdp sxdp = {}; - struct xdp_mmap_offsets off; - struct xsk_socket *xsk; - struct xsk_ctx *ctx; - int err, ifindex; - - if (!umem || !xsk_ptr || !(rx || tx)) - return -EFAULT; - - unmap = umem->fill_save != fill; - - xsk = calloc(1, sizeof(*xsk)); - if (!xsk) - return -ENOMEM; - - err = xsk_set_xdp_socket_config(&xsk->config, usr_config); - if (err) - goto out_xsk_alloc; - - xsk->outstanding_tx = 0; - ifindex = if_nametoindex(ifname); - if (!ifindex) { - err = -errno; - goto out_xsk_alloc; - } - - if (umem->refcount++ > 0) { - xsk->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0); - if (xsk->fd < 0) { - err = -errno; - goto out_xsk_alloc; - } - } else { - xsk->fd = umem->fd; - rx_setup_done = umem->rx_ring_setup_done; - tx_setup_done = umem->tx_ring_setup_done; - } - - ctx = xsk_get_ctx(umem, ifindex, queue_id); - if (!ctx) { - if (!fill || !comp) { - err = -EFAULT; - goto out_socket; - } - - ctx = xsk_create_ctx(xsk, umem, ifindex, ifname, queue_id, - fill, comp); - if (!ctx) { - err = -ENOMEM; - goto out_socket; - } - } - xsk->ctx = ctx; - xsk->ctx->has_bpf_link = xsk_probe_bpf_link(); - - if (rx && !rx_setup_done) { - err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING, - &xsk->config.rx_size, - sizeof(xsk->config.rx_size)); - if (err) { - err = -errno; - goto out_put_ctx; - } - if (xsk->fd == umem->fd) - umem->rx_ring_setup_done = true; - } - if (tx && !tx_setup_done) { - err = setsockopt(xsk->fd, SOL_XDP, XDP_TX_RING, - &xsk->config.tx_size, - sizeof(xsk->config.tx_size)); - if (err) { - err = -errno; - goto out_put_ctx; - } - if (xsk->fd == umem->fd) - umem->tx_ring_setup_done = true; - } - - err = xsk_get_mmap_offsets(xsk->fd, &off); - if (err) { - err = -errno; - goto out_put_ctx; - } - - if (rx) { - rx_map = mmap(NULL, off.rx.desc + - xsk->config.rx_size * sizeof(struct xdp_desc), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, - xsk->fd, XDP_PGOFF_RX_RING); - if (rx_map == MAP_FAILED) { - err = -errno; - goto out_put_ctx; - } - - rx->mask = xsk->config.rx_size - 1; - rx->size = xsk->config.rx_size; - rx->producer = rx_map + off.rx.producer; - rx->consumer = rx_map + off.rx.consumer; - rx->flags = rx_map + off.rx.flags; - rx->ring = rx_map + off.rx.desc; - rx->cached_prod = *rx->producer; - rx->cached_cons = *rx->consumer; - } - xsk->rx = rx; - - if (tx) { - tx_map = mmap(NULL, off.tx.desc + - xsk->config.tx_size * sizeof(struct xdp_desc), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, - xsk->fd, XDP_PGOFF_TX_RING); - if (tx_map == MAP_FAILED) { - err = -errno; - goto out_mmap_rx; - } - - tx->mask = xsk->config.tx_size - 1; - tx->size = xsk->config.tx_size; - tx->producer = tx_map + off.tx.producer; - tx->consumer = tx_map + off.tx.consumer; - tx->flags = tx_map + off.tx.flags; - tx->ring = tx_map + off.tx.desc; - tx->cached_prod = *tx->producer; - /* cached_cons is r->size bigger than the real consumer pointer - * See xsk_prod_nb_free - */ - tx->cached_cons = *tx->consumer + xsk->config.tx_size; - } - xsk->tx = tx; - - sxdp.sxdp_family = PF_XDP; - sxdp.sxdp_ifindex = ctx->ifindex; - sxdp.sxdp_queue_id = ctx->queue_id; - if (umem->refcount > 1) { - sxdp.sxdp_flags |= XDP_SHARED_UMEM; - sxdp.sxdp_shared_umem_fd = umem->fd; - } else { - sxdp.sxdp_flags = xsk->config.bind_flags; - } - - err = bind(xsk->fd, (struct sockaddr *)&sxdp, sizeof(sxdp)); - if (err) { - err = -errno; - goto out_mmap_tx; - } - - ctx->prog_fd = -1; - - if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { - err = __xsk_setup_xdp_prog(xsk, NULL); - if (err) - goto out_mmap_tx; - } - - *xsk_ptr = xsk; - umem->fill_save = NULL; - umem->comp_save = NULL; - return 0; - -out_mmap_tx: - if (tx) - munmap(tx_map, off.tx.desc + - xsk->config.tx_size * sizeof(struct xdp_desc)); -out_mmap_rx: - if (rx) - munmap(rx_map, off.rx.desc + - xsk->config.rx_size * sizeof(struct xdp_desc)); -out_put_ctx: - xsk_put_ctx(ctx, unmap); -out_socket: - if (--umem->refcount) - close(xsk->fd); -out_xsk_alloc: - free(xsk); - return err; -} - -int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, - __u32 queue_id, struct xsk_umem *umem, - struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, - const struct xsk_socket_config *usr_config) -{ - if (!umem) - return -EFAULT; - - return xsk_socket__create_shared(xsk_ptr, ifname, queue_id, umem, - rx, tx, umem->fill_save, - umem->comp_save, usr_config); -} - -int xsk_umem__delete(struct xsk_umem *umem) -{ - if (!umem) - return 0; - - if (umem->refcount) - return -EBUSY; - - close(umem->fd); - free(umem); - - return 0; -} - -void xsk_socket__delete(struct xsk_socket *xsk) -{ - size_t desc_sz = sizeof(struct xdp_desc); - struct xdp_mmap_offsets off; - struct xsk_umem *umem; - struct xsk_ctx *ctx; - int err; - - if (!xsk) - return; - - ctx = xsk->ctx; - umem = ctx->umem; - if (ctx->prog_fd != -1) { - xsk_delete_bpf_maps(xsk); - close(ctx->prog_fd); - if (ctx->has_bpf_link) - close(ctx->link_fd); - } - - err = xsk_get_mmap_offsets(xsk->fd, &off); - if (!err) { - if (xsk->rx) { - munmap(xsk->rx->ring - off.rx.desc, - off.rx.desc + xsk->config.rx_size * desc_sz); - } - if (xsk->tx) { - munmap(xsk->tx->ring - off.tx.desc, - off.tx.desc + xsk->config.tx_size * desc_sz); - } - } - - xsk_put_ctx(ctx, true); - - umem->refcount--; - /* Do not close an fd that also has an associated umem connected - * to it. - */ - if (xsk->fd != umem->fd) - close(xsk->fd); - free(xsk); -} diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c index 109aa7ffcf97..6a3dc167d30e 100644 --- a/tools/lib/find_bit.c +++ b/tools/lib/find_bit.c @@ -18,66 +18,54 @@ #include <linux/bitmap.h> #include <linux/kernel.h> -#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ - !defined(find_next_and_bit) - /* - * This is a common helper function for find_next_bit, find_next_zero_bit, and - * find_next_and_bit. The differences are: - * - The "invert" argument, which is XORed with each fetched word before - * searching it for one bits. - * - The optional "addr2", which is anded with "addr1" if present. + * Common helper for find_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits */ -unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le) -{ - unsigned long tmp, mask; - (void) le; - - if (unlikely(start >= nbits)) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - - /* Handle 1st word. */ - mask = BITMAP_FIRST_WORD_MASK(start); - - /* - * Due to the lack of swab() in tools, and the fact that it doesn't - * need little-endian support, just comment it out - */ -#if (0) - if (le) - mask = swab(mask); -#endif - - tmp &= mask; - - start = round_down(start, BITS_PER_LONG); +#define FIND_FIRST_BIT(FETCH, MUNGE, size) \ +({ \ + unsigned long idx, val, sz = (size); \ + \ + for (idx = 0; idx * BITS_PER_LONG < sz; idx++) { \ + val = (FETCH); \ + if (val) { \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(val)), sz); \ + break; \ + } \ + } \ + \ + sz; \ +}) - while (!tmp) { - start += BITS_PER_LONG; - if (start >= nbits) - return nbits; - - tmp = addr1[start / BITS_PER_LONG]; - if (addr2) - tmp &= addr2[start / BITS_PER_LONG]; - tmp ^= invert; - } - -#if (0) - if (le) - tmp = swab(tmp); -#endif - - return min(start + __ffs(tmp), nbits); -} -#endif +/* + * Common helper for find_next_bit() function family + * @FETCH: The expression that fetches and pre-processes each word of bitmap(s) + * @MUNGE: The expression that post-processes a word containing found bit (may be empty) + * @size: The bitmap size in bits + * @start: The bitnumber to start searching at + */ +#define FIND_NEXT_BIT(FETCH, MUNGE, size, start) \ +({ \ + unsigned long mask, idx, tmp, sz = (size), __start = (start); \ + \ + if (unlikely(__start >= sz)) \ + goto out; \ + \ + mask = MUNGE(BITMAP_FIRST_WORD_MASK(__start)); \ + idx = __start / BITS_PER_LONG; \ + \ + for (tmp = (FETCH) & mask; !tmp; tmp = (FETCH)) { \ + if ((idx + 1) * BITS_PER_LONG >= sz) \ + goto out; \ + idx++; \ + } \ + \ + sz = min(idx * BITS_PER_LONG + __ffs(MUNGE(tmp)), sz); \ +out: \ + sz; \ +}) #ifndef find_first_bit /* @@ -85,14 +73,19 @@ unsigned long _find_next_bit(const unsigned long *addr1, */ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) { - unsigned long idx; - - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - if (addr[idx]) - return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); - } + return FIND_FIRST_BIT(addr[idx], /* nop */, size); +} +#endif - return size; +#ifndef find_first_and_bit +/* + * Find the first set bit in two memory regions. + */ +unsigned long _find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + return FIND_FIRST_BIT(addr1[idx] & addr2[idx], /* nop */, size); } #endif @@ -102,13 +95,29 @@ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) */ unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size) { - unsigned long idx; + return FIND_FIRST_BIT(~addr[idx], /* nop */, size); +} +#endif + +#ifndef find_next_bit +unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr[idx], /* nop */, nbits, start); +} +#endif - for (idx = 0; idx * BITS_PER_LONG < size; idx++) { - if (addr[idx] != ~0UL) - return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); - } +#ifndef find_next_and_bit +unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr1[idx] & addr2[idx], /* nop */, nbits, start); +} +#endif - return size; +#ifndef find_next_zero_bit +unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, + unsigned long start) +{ + return FIND_NEXT_BIT(~addr[idx], /* nop */, nbits, start); } #endif diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt index 63ae5e0195ce..a8f1a237931b 100644 --- a/tools/lib/perf/Documentation/libperf.txt +++ b/tools/lib/perf/Documentation/libperf.txt @@ -48,6 +48,7 @@ SYNOPSIS int perf_cpu_map__nr(const struct perf_cpu_map *cpus); bool perf_cpu_map__empty(const struct perf_cpu_map *map); int perf_cpu_map__max(struct perf_cpu_map *map); + bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu); #define perf_cpu_map__for_each_cpu(cpu, idx, cpus) -- @@ -61,11 +62,12 @@ SYNOPSIS struct perf_thread_map; struct perf_thread_map *perf_thread_map__new_dummy(void); + struct perf_thread_map *perf_thread_map__new_array(int nr_threads, pid_t *array); - void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid); - char *perf_thread_map__comm(struct perf_thread_map *map, int thread); + void perf_thread_map__set_pid(struct perf_thread_map *map, int idx, pid_t pid); + char *perf_thread_map__comm(struct perf_thread_map *map, int idx); int perf_thread_map__nr(struct perf_thread_map *threads); - pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread); + pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx); struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map); void perf_thread_map__put(struct perf_thread_map *map); @@ -135,16 +137,16 @@ SYNOPSIS int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads); void perf_evsel__close(struct perf_evsel *evsel); - void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); + void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx); int perf_evsel__mmap(struct perf_evsel *evsel, int pages); void perf_evsel__munmap(struct perf_evsel *evsel); - void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread); - int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread); + int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count); int perf_evsel__enable(struct perf_evsel *evsel); - int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); + int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx); int perf_evsel__disable(struct perf_evsel *evsel); - int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); + int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx); struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile index 08fe6e3c4089..21df023a2103 100644 --- a/tools/lib/perf/Makefile +++ b/tools/lib/perf/Makefile @@ -153,7 +153,7 @@ $(TESTS_STATIC): $(TESTS_IN) $(LIBPERF_A) $(LIBAPI) $(QUIET_LINK)$(CC) -o $@ $^ $(TESTS_SHARED): $(TESTS_IN) $(LIBAPI) - $(QUIET_LINK)$(CC) -o $@ -L$(if $(OUTPUT),$(OUTPUT),.) $^ -lperf + $(QUIET_LINK)$(CC) -o $@ -L$(or $(OUTPUT),.) $^ -lperf make-tests: libs $(TESTS_SHARED) $(TESTS_STATIC) diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c index adaad3dddf6e..6cd0be7c1bb4 100644 --- a/tools/lib/perf/cpumap.c +++ b/tools/lib/perf/cpumap.c @@ -10,15 +10,24 @@ #include <ctype.h> #include <limits.h> -struct perf_cpu_map *perf_cpu_map__dummy_new(void) +static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) { - struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int)); + struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus); if (cpus != NULL) { - cpus->nr = 1; - cpus->map[0] = -1; + cpus->nr = nr_cpus; refcount_set(&cpus->refcnt, 1); + } + return cpus; +} + +struct perf_cpu_map *perf_cpu_map__dummy_new(void) +{ + struct perf_cpu_map *cpus = perf_cpu_map__alloc(1); + + if (cpus) + cpus->map[0].cpu = -1; return cpus; } @@ -54,15 +63,12 @@ static struct perf_cpu_map *cpu_map__default_new(void) if (nr_cpus < 0) return NULL; - cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int)); + cpus = perf_cpu_map__alloc(nr_cpus); if (cpus != NULL) { int i; for (i = 0; i < nr_cpus; ++i) - cpus->map[i] = i; - - cpus->nr = nr_cpus; - refcount_set(&cpus->refcnt, 1); + cpus->map[i].cpu = i; } return cpus; @@ -73,31 +79,32 @@ struct perf_cpu_map *perf_cpu_map__default_new(void) return cpu_map__default_new(); } -static int cmp_int(const void *a, const void *b) + +static int cmp_cpu(const void *a, const void *b) { - return *(const int *)a - *(const int*)b; + const struct perf_cpu *cpu_a = a, *cpu_b = b; + + return cpu_a->cpu - cpu_b->cpu; } -static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) +static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus) { - size_t payload_size = nr_cpus * sizeof(int); - struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size); + size_t payload_size = nr_cpus * sizeof(struct perf_cpu); + struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr_cpus); int i, j; if (cpus != NULL) { memcpy(cpus->map, tmp_cpus, payload_size); - qsort(cpus->map, nr_cpus, sizeof(int), cmp_int); + qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu); /* Remove dups */ j = 0; for (i = 0; i < nr_cpus; i++) { - if (i == 0 || cpus->map[i] != cpus->map[i - 1]) - cpus->map[j++] = cpus->map[i]; + if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu) + cpus->map[j++].cpu = cpus->map[i].cpu; } cpus->nr = j; assert(j <= nr_cpus); - refcount_set(&cpus->refcnt, 1); } - return cpus; } @@ -105,7 +112,7 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file) { struct perf_cpu_map *cpus = NULL; int nr_cpus = 0; - int *tmp_cpus = NULL, *tmp; + struct perf_cpu *tmp_cpus = NULL, *tmp; int max_entries = 0; int n, cpu, prev; char sep; @@ -124,24 +131,24 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file) if (new_max >= max_entries) { max_entries = new_max + MAX_NR_CPUS / 2; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); if (tmp == NULL) goto out_free_tmp; tmp_cpus = tmp; } while (++prev < cpu) - tmp_cpus[nr_cpus++] = prev; + tmp_cpus[nr_cpus++].cpu = prev; } if (nr_cpus == max_entries) { max_entries += MAX_NR_CPUS; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); if (tmp == NULL) goto out_free_tmp; tmp_cpus = tmp; } - tmp_cpus[nr_cpus++] = cpu; + tmp_cpus[nr_cpus++].cpu = cpu; if (n == 2 && sep == '-') prev = cpu; else @@ -179,7 +186,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) unsigned long start_cpu, end_cpu = 0; char *p = NULL; int i, nr_cpus = 0; - int *tmp_cpus = NULL, *tmp; + struct perf_cpu *tmp_cpus = NULL, *tmp; int max_entries = 0; if (!cpu_list) @@ -220,17 +227,17 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) for (; start_cpu <= end_cpu; start_cpu++) { /* check for duplicates */ for (i = 0; i < nr_cpus; i++) - if (tmp_cpus[i] == (int)start_cpu) + if (tmp_cpus[i].cpu == (int)start_cpu) goto invalid; if (nr_cpus == max_entries) { max_entries += MAX_NR_CPUS; - tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu)); if (tmp == NULL) goto invalid; tmp_cpus = tmp; } - tmp_cpus[nr_cpus++] = (int)start_cpu; + tmp_cpus[nr_cpus++].cpu = (int)start_cpu; } if (*p) ++p; @@ -250,12 +257,16 @@ out: return cpus; } -int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) +struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) { + struct perf_cpu result = { + .cpu = -1 + }; + if (cpus && idx < cpus->nr) return cpus->map[idx]; - return -1; + return result; } int perf_cpu_map__nr(const struct perf_cpu_map *cpus) @@ -265,21 +276,26 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus) bool perf_cpu_map__empty(const struct perf_cpu_map *map) { - return map ? map->map[0] == -1 : true; + return map ? map->map[0].cpu == -1 : true; } -int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu) +int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu) { - int low = 0, high = cpus->nr; + int low, high; + if (!cpus) + return -1; + + low = 0; + high = cpus->nr; while (low < high) { - int idx = (low + high) / 2, - cpu_at_idx = cpus->map[idx]; + int idx = (low + high) / 2; + struct perf_cpu cpu_at_idx = cpus->map[idx]; - if (cpu_at_idx == cpu) + if (cpu_at_idx.cpu == cpu.cpu) return idx; - if (cpu_at_idx > cpu) + if (cpu_at_idx.cpu > cpu.cpu) high = idx; else low = idx + 1; @@ -288,10 +304,39 @@ int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu) return -1; } -int perf_cpu_map__max(struct perf_cpu_map *map) +bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu) +{ + return perf_cpu_map__idx(cpus, cpu) != -1; +} + +struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map) { + struct perf_cpu result = { + .cpu = -1 + }; + // cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well. - return map->nr > 0 ? map->map[map->nr - 1] : -1; + return map->nr > 0 ? map->map[map->nr - 1] : result; +} + +/** Is 'b' a subset of 'a'. */ +bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b) +{ + if (a == b || !b) + return true; + if (!a || b->nr > a->nr) + return false; + + for (int i = 0, j = 0; i < a->nr; i++) { + if (a->map[i].cpu > b->map[j].cpu) + return false; + if (a->map[i].cpu == b->map[j].cpu) { + j++; + if (j == b->nr) + return true; + } + } + return false; } /* @@ -305,33 +350,28 @@ int perf_cpu_map__max(struct perf_cpu_map *map) struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, struct perf_cpu_map *other) { - int *tmp_cpus; + struct perf_cpu *tmp_cpus; int tmp_len; int i, j, k; struct perf_cpu_map *merged; - if (!orig && !other) - return NULL; - if (!orig) { - perf_cpu_map__get(other); - return other; - } - if (!other) - return orig; - if (orig->nr == other->nr && - !memcmp(orig->map, other->map, orig->nr * sizeof(int))) + if (perf_cpu_map__is_subset(orig, other)) return orig; + if (perf_cpu_map__is_subset(other, orig)) { + perf_cpu_map__put(orig); + return perf_cpu_map__get(other); + } tmp_len = orig->nr + other->nr; - tmp_cpus = malloc(tmp_len * sizeof(int)); + tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu)); if (!tmp_cpus) return NULL; /* Standard merge algorithm from wikipedia */ i = j = k = 0; while (i < orig->nr && j < other->nr) { - if (orig->map[i] <= other->map[j]) { - if (orig->map[i] == other->map[j]) + if (orig->map[i].cpu <= other->map[j].cpu) { + if (orig->map[i].cpu == other->map[j].cpu) j++; tmp_cpus[k++] = orig->map[i++]; } else diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index e37dfad31383..61b637f29b82 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -23,6 +23,7 @@ #include <perf/cpumap.h> #include <perf/threadmap.h> #include <api/fd/array.h> +#include "internal.h" void perf_evlist__init(struct perf_evlist *evlist) { @@ -39,19 +40,26 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, * We already have cpus for evsel (via PMU sysfs) so * keep it, if there's no target cpu list defined. */ - if (!evsel->own_cpus || evlist->has_user_cpus) { + if (evsel->system_wide) { perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evlist->cpus); - } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->cpus)) { + evsel->cpus = perf_cpu_map__new(NULL); + } else if (!evsel->own_cpus || evlist->has_user_cpus || + (!evsel->requires_cpu && perf_cpu_map__empty(evlist->user_requested_cpus))) { perf_cpu_map__put(evsel->cpus); - evsel->cpus = perf_cpu_map__get(evlist->cpus); + evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus); } else if (evsel->cpus != evsel->own_cpus) { perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__get(evsel->own_cpus); } - perf_thread_map__put(evsel->threads); - evsel->threads = perf_thread_map__get(evlist->threads); + if (evsel->system_wide) { + perf_thread_map__put(evsel->threads); + evsel->threads = perf_thread_map__new_dummy(); + } else { + perf_thread_map__put(evsel->threads); + evsel->threads = perf_thread_map__get(evlist->threads); + } + evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus); } @@ -59,6 +67,8 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist) { struct perf_evsel *evsel; + evlist->needs_map_propagation = true; + perf_evlist__for_each_evsel(evlist, evsel) __perf_evlist__propagate_maps(evlist, evsel); } @@ -69,7 +79,9 @@ void perf_evlist__add(struct perf_evlist *evlist, evsel->idx = evlist->nr_entries; list_add_tail(&evsel->node, &evlist->entries); evlist->nr_entries += 1; - __perf_evlist__propagate_maps(evlist, evsel); + + if (evlist->needs_map_propagation) + __perf_evlist__propagate_maps(evlist, evsel); } void perf_evlist__remove(struct perf_evlist *evlist, @@ -123,10 +135,10 @@ static void perf_evlist__purge(struct perf_evlist *evlist) void perf_evlist__exit(struct perf_evlist *evlist) { - perf_cpu_map__put(evlist->cpus); + perf_cpu_map__put(evlist->user_requested_cpus); perf_cpu_map__put(evlist->all_cpus); perf_thread_map__put(evlist->threads); - evlist->cpus = NULL; + evlist->user_requested_cpus = NULL; evlist->all_cpus = NULL; evlist->threads = NULL; fdarray__exit(&evlist->pollfd); @@ -155,9 +167,9 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, * original reference count of 1. If that is not the case it is up to * the caller to increase the reference count. */ - if (cpus != evlist->cpus) { - perf_cpu_map__put(evlist->cpus); - evlist->cpus = perf_cpu_map__get(cpus); + if (cpus != evlist->user_requested_cpus) { + perf_cpu_map__put(evlist->user_requested_cpus); + evlist->user_requested_cpus = perf_cpu_map__get(cpus); } if (threads != evlist->threads) { @@ -165,9 +177,6 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, evlist->threads = perf_thread_map__get(threads); } - if (!evlist->all_cpus && cpus) - evlist->all_cpus = perf_cpu_map__get(cpus); - perf_evlist__propagate_maps(evlist); } @@ -294,7 +303,7 @@ add: int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) { - int nr_cpus = perf_cpu_map__nr(evlist->cpus); + int nr_cpus = perf_cpu_map__nr(evlist->all_cpus); int nr_threads = perf_thread_map__nr(evlist->threads); int nfds = 0; struct perf_evsel *evsel; @@ -407,7 +416,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *evlist, bool overwrite, int idx) static int perf_evlist__mmap_cb_mmap(struct perf_mmap *map, struct perf_mmap_param *mp, - int output, int cpu) + int output, struct perf_cpu cpu) { return perf_mmap__mmap(map, mp, output, cpu); } @@ -424,14 +433,15 @@ static void perf_evlist__set_mmap_first(struct perf_evlist *evlist, struct perf_ static int mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, int idx, struct perf_mmap_param *mp, int cpu_idx, - int thread, int *_output, int *_output_overwrite) + int thread, int *_output, int *_output_overwrite, int *nr_mmaps) { - int evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx); + struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->all_cpus, cpu_idx); struct perf_evsel *evsel; int revent; perf_evlist__for_each_entry(evlist, evsel) { bool overwrite = evsel->attr.write_backward; + enum fdarray_flags flgs; struct perf_mmap *map; int *output, fd, cpu; @@ -474,12 +484,21 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, */ refcount_set(&map->refcnt, 2); + if (ops->idx) + ops->idx(evlist, evsel, mp, idx); + + /* Debug message used by test scripts */ + pr_debug("idx %d: mmapping fd %d\n", idx, *output); if (ops->mmap(map, mp, *output, evlist_cpu) < 0) return -1; + *nr_mmaps += 1; + if (!idx) perf_evlist__set_mmap_first(evlist, map, overwrite); } else { + /* Debug message used by test scripts */ + pr_debug("idx %d: set output fd %d -> %d\n", idx, fd, *output); if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) return -1; @@ -488,8 +507,8 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, revent = !overwrite ? POLLIN : 0; - if (!evsel->system_wide && - perf_evlist__add_pollfd(evlist, fd, map, revent, fdarray_flag__default) < 0) { + flgs = evsel->system_wide ? fdarray_flag__nonfilterable : fdarray_flag__default; + if (perf_evlist__add_pollfd(evlist, fd, map, revent, flgs) < 0) { perf_mmap__put(map); return -1; } @@ -509,21 +528,37 @@ static int mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, struct perf_mmap_param *mp) { - int thread; int nr_threads = perf_thread_map__nr(evlist->threads); + int nr_cpus = perf_cpu_map__nr(evlist->all_cpus); + int cpu, thread, idx = 0; + int nr_mmaps = 0; - for (thread = 0; thread < nr_threads; thread++) { + pr_debug("%s: nr cpu values (may include -1) %d nr threads %d\n", + __func__, nr_cpus, nr_threads); + + /* per-thread mmaps */ + for (thread = 0; thread < nr_threads; thread++, idx++) { int output = -1; int output_overwrite = -1; - if (ops->idx) - ops->idx(evlist, mp, thread, false); + if (mmap_per_evsel(evlist, ops, idx, mp, 0, thread, &output, + &output_overwrite, &nr_mmaps)) + goto out_unmap; + } - if (mmap_per_evsel(evlist, ops, thread, mp, 0, thread, - &output, &output_overwrite)) + /* system-wide mmaps i.e. per-cpu */ + for (cpu = 1; cpu < nr_cpus; cpu++, idx++) { + int output = -1; + int output_overwrite = -1; + + if (mmap_per_evsel(evlist, ops, idx, mp, cpu, 0, &output, + &output_overwrite, &nr_mmaps)) goto out_unmap; } + if (nr_mmaps != evlist->nr_mmaps) + pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps); + return 0; out_unmap: @@ -536,23 +571,26 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, struct perf_mmap_param *mp) { int nr_threads = perf_thread_map__nr(evlist->threads); - int nr_cpus = perf_cpu_map__nr(evlist->cpus); + int nr_cpus = perf_cpu_map__nr(evlist->all_cpus); + int nr_mmaps = 0; int cpu, thread; + pr_debug("%s: nr cpu values %d nr threads %d\n", __func__, nr_cpus, nr_threads); + for (cpu = 0; cpu < nr_cpus; cpu++) { int output = -1; int output_overwrite = -1; - if (ops->idx) - ops->idx(evlist, mp, cpu, true); - for (thread = 0; thread < nr_threads; thread++) { if (mmap_per_evsel(evlist, ops, cpu, mp, cpu, - thread, &output, &output_overwrite)) + thread, &output, &output_overwrite, &nr_mmaps)) goto out_unmap; } } + if (nr_mmaps != evlist->nr_mmaps) + pr_err("Miscounted nr_mmaps %d vs %d\n", nr_mmaps, evlist->nr_mmaps); + return 0; out_unmap: @@ -564,9 +602,14 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) { int nr_mmaps; - nr_mmaps = perf_cpu_map__nr(evlist->cpus); - if (perf_cpu_map__empty(evlist->cpus)) - nr_mmaps = perf_thread_map__nr(evlist->threads); + /* One for each CPU */ + nr_mmaps = perf_cpu_map__nr(evlist->all_cpus); + if (perf_cpu_map__empty(evlist->all_cpus)) { + /* Plus one for each thread */ + nr_mmaps += perf_thread_map__nr(evlist->threads); + /* Minus the per-thread CPU (-1) */ + nr_mmaps -= 1; + } return nr_mmaps; } @@ -575,9 +618,8 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, struct perf_mmap_param *mp) { + const struct perf_cpu_map *cpus = evlist->all_cpus; struct perf_evsel *evsel; - const struct perf_cpu_map *cpus = evlist->cpus; - const struct perf_thread_map *threads = evlist->threads; if (!ops || !ops->get || !ops->mmap) return -EINVAL; @@ -589,7 +631,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist, perf_evlist__for_each_entry(evlist, evsel) { if ((evsel->attr.read_format & PERF_FORMAT_ID) && evsel->sample_id == NULL && - perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0) + perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0) return -ENOMEM; } @@ -643,14 +685,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map, return overwrite ? evlist->mmap_ovw_first : evlist->mmap_first; } -void __perf_evlist__set_leader(struct list_head *list) +void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader) { - struct perf_evsel *evsel, *leader; + struct perf_evsel *first, *last, *evsel; - leader = list_entry(list->next, struct perf_evsel, node); - evsel = list_entry(list->prev, struct perf_evsel, node); + first = list_first_entry(list, struct perf_evsel, node); + last = list_last_entry(list, struct perf_evsel, node); - leader->nr_members = evsel->idx - leader->idx + 1; + leader->nr_members = last->idx - first->idx + 1; __perf_evlist__for_each_entry(list, evsel) evsel->leader = leader; @@ -659,7 +701,10 @@ void __perf_evlist__set_leader(struct list_head *list) void perf_evlist__set_leader(struct perf_evlist *evlist) { if (evlist->nr_entries) { + struct perf_evsel *first = list_entry(evlist->entries.next, + struct perf_evsel, node); + evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0; - __perf_evlist__set_leader(&evlist->entries); + __perf_evlist__set_leader(&evlist->entries, first); } } diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index 8441e3e1aaac..8b51b008a81f 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -43,18 +43,22 @@ void perf_evsel__delete(struct perf_evsel *evsel) free(evsel); } -#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y)) -#define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL) +#define FD(_evsel, _cpu_map_idx, _thread) \ + ((int *)xyarray__entry(_evsel->fd, _cpu_map_idx, _thread)) +#define MMAP(_evsel, _cpu_map_idx, _thread) \ + (_evsel->mmap ? ((struct perf_mmap *) xyarray__entry(_evsel->mmap, _cpu_map_idx, _thread)) \ + : NULL) int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) { evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); if (evsel->fd) { - int cpu, thread; - for (cpu = 0; cpu < ncpus; cpu++) { + int idx, thread; + + for (idx = 0; idx < ncpus; idx++) { for (thread = 0; thread < nthreads; thread++) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, idx, thread); if (fd) *fd = -1; @@ -74,13 +78,13 @@ static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthre static int sys_perf_event_open(struct perf_event_attr *attr, - pid_t pid, int cpu, int group_fd, + pid_t pid, struct perf_cpu cpu, int group_fd, unsigned long flags) { - return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); + return syscall(__NR_perf_event_open, attr, pid, cpu.cpu, group_fd, flags); } -static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd) +static int get_group_fd(struct perf_evsel *evsel, int cpu_map_idx, int thread, int *group_fd) { struct perf_evsel *leader = evsel->leader; int *fd; @@ -97,7 +101,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou if (!leader->fd) return -ENOTCONN; - fd = FD(leader, cpu, thread); + fd = FD(leader, cpu_map_idx, thread); if (fd == NULL || *fd == -1) return -EBADF; @@ -109,7 +113,8 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads) { - int cpu, thread, err = 0; + struct perf_cpu cpu; + int idx, thread, err = 0; if (cpus == NULL) { static struct perf_cpu_map *empty_cpu_map; @@ -136,41 +141,48 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, } if (evsel->fd == NULL && - perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) + perf_evsel__alloc_fd(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0) return -ENOMEM; - for (cpu = 0; cpu < cpus->nr; cpu++) { + perf_cpu_map__for_each_cpu(cpu, idx, cpus) { for (thread = 0; thread < threads->nr; thread++) { int fd, group_fd, *evsel_fd; - evsel_fd = FD(evsel, cpu, thread); - if (evsel_fd == NULL) - return -EINVAL; + evsel_fd = FD(evsel, idx, thread); + if (evsel_fd == NULL) { + err = -EINVAL; + goto out; + } - err = get_group_fd(evsel, cpu, thread, &group_fd); + err = get_group_fd(evsel, idx, thread, &group_fd); if (err < 0) - return err; + goto out; fd = sys_perf_event_open(&evsel->attr, threads->map[thread].pid, - cpus->map[cpu], group_fd, 0); + cpu, group_fd, 0); - if (fd < 0) - return -errno; + if (fd < 0) { + err = -errno; + goto out; + } *evsel_fd = fd; } } +out: + if (err) + perf_evsel__close(evsel); return err; } -static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) +static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu_map_idx) { int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); if (fd && *fd >= 0) { close(*fd); @@ -181,10 +193,8 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) void perf_evsel__close_fd(struct perf_evsel *evsel) { - int cpu; - - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) - perf_evsel__close_fd_cpu(evsel, cpu); + for (int idx = 0; idx < xyarray__max_x(evsel->fd); idx++) + perf_evsel__close_fd_cpu(evsel, idx); } void perf_evsel__free_fd(struct perf_evsel *evsel) @@ -202,29 +212,29 @@ void perf_evsel__close(struct perf_evsel *evsel) perf_evsel__free_fd(evsel); } -void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu) +void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx) { if (evsel->fd == NULL) return; - perf_evsel__close_fd_cpu(evsel, cpu); + perf_evsel__close_fd_cpu(evsel, cpu_map_idx); } void perf_evsel__munmap(struct perf_evsel *evsel) { - int cpu, thread; + int idx, thread; if (evsel->fd == NULL || evsel->mmap == NULL) return; - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { + for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) { for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, idx, thread); if (fd == NULL || *fd < 0) continue; - perf_mmap__munmap(MMAP(evsel, cpu, thread)); + perf_mmap__munmap(MMAP(evsel, idx, thread)); } } @@ -234,7 +244,7 @@ void perf_evsel__munmap(struct perf_evsel *evsel) int perf_evsel__mmap(struct perf_evsel *evsel, int pages) { - int ret, cpu, thread; + int ret, idx, thread; struct perf_mmap_param mp = { .prot = PROT_READ | PROT_WRITE, .mask = (pages * page_size) - 1, @@ -246,15 +256,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages) if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0) return -ENOMEM; - for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) { + for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) { for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, idx, thread); struct perf_mmap *map; + struct perf_cpu cpu = perf_cpu_map__cpu(evsel->cpus, idx); if (fd == NULL || *fd < 0) continue; - map = MMAP(evsel, cpu, thread); + map = MMAP(evsel, idx, thread); perf_mmap__init(map, NULL, false, NULL); ret = perf_mmap__mmap(map, &mp, *fd, cpu); @@ -268,14 +279,14 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages) return 0; } -void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread) +void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread) { - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); - if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL) + if (fd == NULL || *fd < 0 || MMAP(evsel, cpu_map_idx, thread) == NULL) return NULL; - return MMAP(evsel, cpu, thread)->base; + return MMAP(evsel, cpu_map_idx, thread)->base; } int perf_evsel__read_size(struct perf_evsel *evsel) @@ -294,6 +305,9 @@ int perf_evsel__read_size(struct perf_evsel *evsel) if (read_format & PERF_FORMAT_ID) entry += sizeof(u64); + if (read_format & PERF_FORMAT_LOST) + entry += sizeof(u64); + if (read_format & PERF_FORMAT_GROUP) { nr = evsel->nr_members; size += sizeof(u64); @@ -303,41 +317,120 @@ int perf_evsel__read_size(struct perf_evsel *evsel) return size; } -int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, +/* This only reads values for the leader */ +static int perf_evsel__read_group(struct perf_evsel *evsel, int cpu_map_idx, + int thread, struct perf_counts_values *count) +{ + size_t size = perf_evsel__read_size(evsel); + int *fd = FD(evsel, cpu_map_idx, thread); + u64 read_format = evsel->attr.read_format; + u64 *data; + int idx = 1; + + if (fd == NULL || *fd < 0) + return -EINVAL; + + data = calloc(1, size); + if (data == NULL) + return -ENOMEM; + + if (readn(*fd, data, size) <= 0) { + free(data); + return -errno; + } + + /* + * This reads only the leader event intentionally since we don't have + * perf counts values for sibling events. + */ + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + count->ena = data[idx++]; + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + count->run = data[idx++]; + + /* value is always available */ + count->val = data[idx++]; + if (read_format & PERF_FORMAT_ID) + count->id = data[idx++]; + if (read_format & PERF_FORMAT_LOST) + count->lost = data[idx++]; + + free(data); + return 0; +} + +/* + * The perf read format is very flexible. It needs to set the proper + * values according to the read format. + */ +static void perf_evsel__adjust_values(struct perf_evsel *evsel, u64 *buf, + struct perf_counts_values *count) +{ + u64 read_format = evsel->attr.read_format; + int n = 0; + + count->val = buf[n++]; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + count->ena = buf[n++]; + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + count->run = buf[n++]; + + if (read_format & PERF_FORMAT_ID) + count->id = buf[n++]; + + if (read_format & PERF_FORMAT_LOST) + count->lost = buf[n++]; +} + +int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count) { size_t size = perf_evsel__read_size(evsel); - int *fd = FD(evsel, cpu, thread); + int *fd = FD(evsel, cpu_map_idx, thread); + u64 read_format = evsel->attr.read_format; + struct perf_counts_values buf; memset(count, 0, sizeof(*count)); if (fd == NULL || *fd < 0) return -EINVAL; - if (MMAP(evsel, cpu, thread) && - !perf_mmap__read_self(MMAP(evsel, cpu, thread), count)) + if (read_format & PERF_FORMAT_GROUP) + return perf_evsel__read_group(evsel, cpu_map_idx, thread, count); + + if (MMAP(evsel, cpu_map_idx, thread) && + !(read_format & (PERF_FORMAT_ID | PERF_FORMAT_LOST)) && + !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count)) return 0; - if (readn(*fd, count->values, size) <= 0) + if (readn(*fd, buf.values, size) <= 0) return -errno; + perf_evsel__adjust_values(evsel, buf.values, count); return 0; } +static int perf_evsel__ioctl(struct perf_evsel *evsel, int ioc, void *arg, + int cpu_map_idx, int thread) +{ + int *fd = FD(evsel, cpu_map_idx, thread); + + if (fd == NULL || *fd < 0) + return -1; + + return ioctl(*fd, ioc, arg); +} + static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ioc, void *arg, - int cpu) + int cpu_map_idx) { int thread; for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { - int err; - int *fd = FD(evsel, cpu, thread); - - if (fd == NULL || *fd < 0) - return -1; - - err = ioctl(*fd, ioc, arg); + int err = perf_evsel__ioctl(evsel, ioc, arg, cpu_map_idx, thread); if (err) return err; @@ -346,9 +439,24 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, return 0; } -int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu) +int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx) { - return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu); + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx); +} + +int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread) +{ + struct perf_cpu cpu __maybe_unused; + int idx; + int err; + + perf_cpu_map__for_each_cpu(cpu, idx, evsel->cpus) { + err = perf_evsel__ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, idx, thread); + if (err) + return err; + } + + return 0; } int perf_evsel__enable(struct perf_evsel *evsel) @@ -361,9 +469,9 @@ int perf_evsel__enable(struct perf_evsel *evsel) return err; } -int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu) +int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx) { - return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu); + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu_map_idx); } int perf_evsel__disable(struct perf_evsel *evsel) @@ -380,7 +488,7 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter) { int err = 0, i; - for (i = 0; i < evsel->cpus->nr && !err; i++) + for (i = 0; i < perf_cpu_map__nr(evsel->cpus) && !err; i++) err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_SET_FILTER, (void *)filter, i); @@ -407,9 +515,6 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) if (ncpus == 0 || nthreads == 0) return 0; - if (evsel->system_wide) - nthreads = 1; - evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); if (evsel->sample_id == NULL) return -ENOMEM; @@ -431,3 +536,22 @@ void perf_evsel__free_id(struct perf_evsel *evsel) zfree(&evsel->id); evsel->ids = 0; } + +void perf_counts_values__scale(struct perf_counts_values *count, + bool scale, __s8 *pscaled) +{ + s8 scaled = 0; + + if (scale) { + if (count->run == 0) { + scaled = -1; + count->val = 0; + } else if (count->run < count->ena) { + scaled = 1; + count->val = (u64)((double)count->val * count->ena / count->run); + } + } + + if (pscaled) + *pscaled = scaled; +} diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h index 840d4032587b..35dd29642296 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -3,17 +3,28 @@ #define __LIBPERF_INTERNAL_CPUMAP_H #include <linux/refcount.h> +#include <perf/cpumap.h> +/** + * A sized, reference counted, sorted array of integers representing CPU + * numbers. This is commonly used to capture which CPUs a PMU is associated + * with. The indices into the cpumap are frequently used as they avoid having + * gaps if CPU numbers were used. For events associated with a pid, rather than + * a CPU, a single dummy map with an entry of -1 is used. + */ struct perf_cpu_map { refcount_t refcnt; + /** Length of the map array. */ int nr; - int map[]; + /** The CPU values. */ + struct perf_cpu map[]; }; #ifndef MAX_NR_CPUS #define MAX_NR_CPUS 2048 #endif -int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu); +int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu); +bool perf_cpu_map__is_subset(const struct perf_cpu_map *a, const struct perf_cpu_map *b); #endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h index f366dbad6a88..850f07070036 100644 --- a/tools/lib/perf/include/internal/evlist.h +++ b/tools/lib/perf/include/internal/evlist.h @@ -4,6 +4,7 @@ #include <linux/list.h> #include <api/fd/array.h> +#include <internal/cpumap.h> #include <internal/evsel.h> #define PERF_EVLIST__HLIST_BITS 8 @@ -18,7 +19,13 @@ struct perf_evlist { int nr_entries; int nr_groups; bool has_user_cpus; - struct perf_cpu_map *cpus; + bool needs_map_propagation; + /** + * The cpus passed from the command line or all online CPUs by + * default. + */ + struct perf_cpu_map *user_requested_cpus; + /** The union of all evsel cpu maps. */ struct perf_cpu_map *all_cpus; struct perf_thread_map *threads; int nr_mmaps; @@ -32,11 +39,12 @@ struct perf_evlist { }; typedef void -(*perf_evlist_mmap__cb_idx_t)(struct perf_evlist*, struct perf_mmap_param*, int, bool); +(*perf_evlist_mmap__cb_idx_t)(struct perf_evlist*, struct perf_evsel*, + struct perf_mmap_param*, int); typedef struct perf_mmap* (*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int); typedef int -(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, int); +(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, struct perf_cpu); struct perf_evlist_mmap_ops { perf_evlist_mmap__cb_idx_t idx; @@ -127,5 +135,5 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist, void perf_evlist__reset_id_hash(struct perf_evlist *evlist); -void __perf_evlist__set_leader(struct list_head *list); +void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader); #endif /* __LIBPERF_INTERNAL_EVLIST_H */ diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h index 1f3eacbad2e8..a99a75d9e78f 100644 --- a/tools/lib/perf/include/internal/evsel.h +++ b/tools/lib/perf/include/internal/evsel.h @@ -6,8 +6,8 @@ #include <linux/perf_event.h> #include <stdbool.h> #include <sys/types.h> +#include <internal/cpumap.h> -struct perf_cpu_map; struct perf_thread_map; struct xyarray; @@ -27,9 +27,13 @@ struct perf_sample_id { * queue number. */ int idx; - int cpu; + struct perf_cpu cpu; pid_t tid; + /* Guest machine pid and VCPU, valid only if machine_pid is non-zero */ + pid_t machine_pid; + struct perf_cpu vcpu; + /* Holds total ID period value for PERF_SAMPLE_READ processing. */ u64 period; }; @@ -49,7 +53,18 @@ struct perf_evsel { /* parse modifier helper */ int nr_members; + /* + * system_wide is for events that need to be on every CPU, irrespective + * of user requested CPUs or threads. Map propagation will set cpus to + * this event's own_cpus, whereby they will contribute to evlist + * all_cpus. + */ bool system_wide; + /* + * Some events, for example uncore events, require a CPU. + * i.e. it cannot be the 'any CPU' value of -1. + */ + bool requires_cpu; int idx; }; diff --git a/tools/lib/perf/include/internal/lib.h b/tools/lib/perf/include/internal/lib.h index 5175d491b2d4..85471a4b900f 100644 --- a/tools/lib/perf/include/internal/lib.h +++ b/tools/lib/perf/include/internal/lib.h @@ -9,4 +9,6 @@ extern unsigned int page_size; ssize_t readn(int fd, void *buf, size_t n); ssize_t writen(int fd, const void *buf, size_t n); +ssize_t preadn(int fd, void *buf, size_t n, off_t offs); + #endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h index 5e3422f40ed5..5a062af8e9d8 100644 --- a/tools/lib/perf/include/internal/mmap.h +++ b/tools/lib/perf/include/internal/mmap.h @@ -6,6 +6,7 @@ #include <linux/refcount.h> #include <linux/types.h> #include <stdbool.h> +#include <internal/cpumap.h> /* perf sample has 16 bits size limit */ #define PERF_SAMPLE_MAX_SIZE (1 << 16) @@ -24,7 +25,7 @@ struct perf_mmap { void *base; int mask; int fd; - int cpu; + struct perf_cpu cpu; refcount_t refcnt; u64 prev; u64 start; @@ -46,7 +47,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map); void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev, bool overwrite, libperf_unmap_cb_t unmap_cb); int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp, - int fd, int cpu); + int fd, struct perf_cpu cpu); void perf_mmap__munmap(struct perf_mmap *map); void perf_mmap__get(struct perf_mmap *map); void perf_mmap__put(struct perf_mmap *map); diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h index 7c27766ea0bf..03aceb72a783 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -3,10 +3,14 @@ #define __LIBPERF_CPUMAP_H #include <perf/core.h> +#include <perf/cpumap.h> #include <stdio.h> #include <stdbool.h> -struct perf_cpu_map; +/** 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); @@ -16,14 +20,18 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, struct perf_cpu_map *other); LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); -LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); +LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map); -LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map); +LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map); +LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); #define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \ for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx); \ (idx) < perf_cpu_map__nr(cpus); \ (idx)++, (cpu) = perf_cpu_map__cpu(cpus, idx)) +#define perf_cpu_map__for_each_idx(idx, cpus) \ + for ((idx) = 0; (idx) < perf_cpu_map__nr(cpus); (idx)++) + #endif /* __LIBPERF_CPUMAP_H */ diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 75ee385fb078..ad47d7b31046 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -76,7 +76,7 @@ struct perf_record_lost_samples { }; /* - * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID + * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID | PERF_FORMAT_LOST */ struct perf_record_read { struct perf_event_header header; @@ -85,6 +85,7 @@ struct perf_record_read { __u64 time_enabled; __u64 time_running; __u64 id; + __u64 lost; }; struct perf_record_throttle { @@ -95,7 +96,7 @@ struct perf_record_throttle { }; #ifndef KSYM_NAME_LEN -#define KSYM_NAME_LEN 256 +#define KSYM_NAME_LEN 512 #endif struct perf_record_ksymbol { @@ -151,23 +152,75 @@ struct perf_record_header_attr { enum { PERF_CPU_MAP__CPUS = 0, PERF_CPU_MAP__MASK = 1, + PERF_CPU_MAP__RANGE_CPUS = 2, }; +/* + * Array encoding of a perf_cpu_map where nr is the number of entries in cpu[] + * and each entry is a value for a CPU in the map. + */ struct cpu_map_entries { __u16 nr; __u16 cpu[]; }; -struct perf_record_record_cpu_map { +/* Bitmap encoding of a perf_cpu_map where bitmap entries are 32-bit. */ +struct perf_record_mask_cpu_map32 { + /* Number of mask values. */ + __u16 nr; + /* Constant 4. */ + __u16 long_size; + /* Bitmap data. */ + __u32 mask[]; +}; + +/* Bitmap encoding of a perf_cpu_map where bitmap entries are 64-bit. */ +struct perf_record_mask_cpu_map64 { + /* Number of mask values. */ __u16 nr; + /* Constant 8. */ __u16 long_size; - unsigned long mask[]; + /* Legacy padding. */ + char __pad[4]; + /* Bitmap data. */ + __u64 mask[]; +}; + +/* + * 'struct perf_record_cpu_map_data' is packed as unfortunately an earlier + * version had unaligned data and we wish to retain file format compatibility. + * -irogers + */ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpacked" +#pragma GCC diagnostic ignored "-Wattributes" + +/* + * An encoding of a CPU map for a range starting at start_cpu through to + * end_cpu. If any_cpu is 1, an any CPU (-1) value (aka dummy value) is present. + */ +struct perf_record_range_cpu_map { + __u8 any_cpu; + __u8 __pad; + __u16 start_cpu; + __u16 end_cpu; }; struct perf_record_cpu_map_data { __u16 type; - char data[]; -}; + union { + /* Used when type == PERF_CPU_MAP__CPUS. */ + struct cpu_map_entries cpus_data; + /* Used when type == PERF_CPU_MAP__MASK and long_size == 4. */ + struct perf_record_mask_cpu_map32 mask32_data; + /* Used when type == PERF_CPU_MAP__MASK and long_size == 8. */ + struct perf_record_mask_cpu_map64 mask64_data; + /* Used when type == PERF_CPU_MAP__RANGE_CPUS. */ + struct perf_record_range_cpu_map range_cpu_data; + }; +} __attribute__((packed)); + +#pragma GCC diagnostic pop struct perf_record_cpu_map { struct perf_event_header header; @@ -193,7 +246,16 @@ struct perf_record_event_update { struct perf_event_header header; __u64 type; __u64 id; - char data[]; + union { + /* Used when type == PERF_EVENT_UPDATE__SCALE. */ + struct perf_record_event_update_scale scale; + /* Used when type == PERF_EVENT_UPDATE__UNIT. */ + char unit[0]; + /* Used when type == PERF_EVENT_UPDATE__NAME. */ + char name[0]; + /* Used when type == PERF_EVENT_UPDATE__CPUS. */ + struct perf_record_event_update_cpus cpus; + }; }; #define MAX_EVENT_NAME 64 @@ -237,10 +299,15 @@ struct id_index_entry { __u64 tid; }; +struct id_index_entry_2 { + __u64 machine_pid; + __u64 vcpu; +}; + 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 { @@ -274,6 +341,8 @@ struct perf_record_auxtrace_error { __u64 ip; __u64 time; char msg[MAX_AUXTRACE_ERROR_MSG]; + __u32 machine_pid; + __u32 vcpu; }; struct perf_record_aux { @@ -389,6 +458,7 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_TIME_CONV = 79, PERF_RECORD_HEADER_FEATURE = 80, PERF_RECORD_COMPRESSED = 81, + PERF_RECORD_FINISHED_INIT = 82, PERF_RECORD_HEADER_MAX }; diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h index 60eae25076d3..6f92204075c2 100644 --- a/tools/lib/perf/include/perf/evsel.h +++ b/tools/lib/perf/include/perf/evsel.h @@ -4,6 +4,8 @@ #include <stdint.h> #include <perf/core.h> +#include <stdbool.h> +#include <linux/types.h> struct perf_evsel; struct perf_event_attr; @@ -16,8 +18,10 @@ struct perf_counts_values { uint64_t val; uint64_t ena; uint64_t run; + uint64_t id; + uint64_t lost; }; - uint64_t values[3]; + uint64_t values[5]; }; }; @@ -26,18 +30,21 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel); LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads); LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel); -LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); +LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx); LIBPERF_API int perf_evsel__mmap(struct perf_evsel *evsel, int pages); LIBPERF_API void perf_evsel__munmap(struct perf_evsel *evsel); -LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread); -LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, +LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread); +LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count); LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); -LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); +LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx); +LIBPERF_API int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread); LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); -LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); +LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx); LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); +LIBPERF_API void perf_counts_values__scale(struct perf_counts_values *count, + bool scale, __s8 *pscaled); #endif /* __LIBPERF_EVSEL_H */ diff --git a/tools/lib/perf/include/perf/threadmap.h b/tools/lib/perf/include/perf/threadmap.h index a7c50de8d010..8b40e7777cea 100644 --- a/tools/lib/perf/include/perf/threadmap.h +++ b/tools/lib/perf/include/perf/threadmap.h @@ -8,11 +8,12 @@ struct perf_thread_map; LIBPERF_API struct perf_thread_map *perf_thread_map__new_dummy(void); +LIBPERF_API struct perf_thread_map *perf_thread_map__new_array(int nr_threads, pid_t *array); -LIBPERF_API void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid); -LIBPERF_API char *perf_thread_map__comm(struct perf_thread_map *map, int thread); +LIBPERF_API void perf_thread_map__set_pid(struct perf_thread_map *map, int idx, pid_t pid); +LIBPERF_API char *perf_thread_map__comm(struct perf_thread_map *map, int idx); LIBPERF_API int perf_thread_map__nr(struct perf_thread_map *threads); -LIBPERF_API pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread); +LIBPERF_API pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx); LIBPERF_API struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map); LIBPERF_API void perf_thread_map__put(struct perf_thread_map *map); diff --git a/tools/lib/perf/lib.c b/tools/lib/perf/lib.c index 18658931fc71..696fb0ea67c6 100644 --- a/tools/lib/perf/lib.c +++ b/tools/lib/perf/lib.c @@ -38,6 +38,26 @@ ssize_t readn(int fd, void *buf, size_t n) return ion(true, fd, buf, n); } +ssize_t preadn(int fd, void *buf, size_t n, off_t offs) +{ + size_t left = n; + + while (left) { + ssize_t ret = pread(fd, buf, left, offs); + + if (ret < 0 && errno == EINTR) + continue; + if (ret <= 0) + return ret; + + left -= ret; + buf += ret; + offs += ret; + } + + return n; +} + /* * Write exactly 'n' bytes or return an error. */ diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map index 71468606e8a7..190b56ae923a 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; @@ -10,6 +11,8 @@ LIBPERF_0.0.1 { perf_cpu_map__cpu; perf_cpu_map__empty; perf_cpu_map__max; + perf_cpu_map__has; + perf_thread_map__new_array; perf_thread_map__new_dummy; perf_thread_map__set_pid; perf_thread_map__comm; @@ -50,6 +53,7 @@ LIBPERF_0.0.1 { perf_mmap__read_init; perf_mmap__read_done; perf_mmap__read_event; + perf_counts_values__scale; local: *; }; diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c index c89dfa5f67b3..0d1634cedf44 100644 --- a/tools/lib/perf/mmap.c +++ b/tools/lib/perf/mmap.c @@ -13,6 +13,7 @@ #include <internal/lib.h> #include <linux/kernel.h> #include <linux/math64.h> +#include <linux/stringify.h> #include "internal.h" void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev, @@ -32,7 +33,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map) } int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp, - int fd, int cpu) + int fd, struct perf_cpu cpu) { map->prev = 0; map->mask = mp->mask; @@ -294,6 +295,103 @@ static u64 read_timestamp(void) return low | ((u64)high) << 32; } +#elif defined(__aarch64__) +#define read_sysreg(r) ({ \ + u64 __val; \ + asm volatile("mrs %0, " __stringify(r) : "=r" (__val)); \ + __val; \ +}) + +static u64 read_pmccntr(void) +{ + return read_sysreg(pmccntr_el0); +} + +#define PMEVCNTR_READ(idx) \ + static u64 read_pmevcntr_##idx(void) { \ + return read_sysreg(pmevcntr##idx##_el0); \ + } + +PMEVCNTR_READ(0); +PMEVCNTR_READ(1); +PMEVCNTR_READ(2); +PMEVCNTR_READ(3); +PMEVCNTR_READ(4); +PMEVCNTR_READ(5); +PMEVCNTR_READ(6); +PMEVCNTR_READ(7); +PMEVCNTR_READ(8); +PMEVCNTR_READ(9); +PMEVCNTR_READ(10); +PMEVCNTR_READ(11); +PMEVCNTR_READ(12); +PMEVCNTR_READ(13); +PMEVCNTR_READ(14); +PMEVCNTR_READ(15); +PMEVCNTR_READ(16); +PMEVCNTR_READ(17); +PMEVCNTR_READ(18); +PMEVCNTR_READ(19); +PMEVCNTR_READ(20); +PMEVCNTR_READ(21); +PMEVCNTR_READ(22); +PMEVCNTR_READ(23); +PMEVCNTR_READ(24); +PMEVCNTR_READ(25); +PMEVCNTR_READ(26); +PMEVCNTR_READ(27); +PMEVCNTR_READ(28); +PMEVCNTR_READ(29); +PMEVCNTR_READ(30); + +/* + * Read a value direct from PMEVCNTR<idx> + */ +static u64 read_perf_counter(unsigned int counter) +{ + static u64 (* const read_f[])(void) = { + read_pmevcntr_0, + read_pmevcntr_1, + read_pmevcntr_2, + read_pmevcntr_3, + read_pmevcntr_4, + read_pmevcntr_5, + read_pmevcntr_6, + read_pmevcntr_7, + read_pmevcntr_8, + read_pmevcntr_9, + read_pmevcntr_10, + read_pmevcntr_11, + read_pmevcntr_13, + read_pmevcntr_12, + read_pmevcntr_14, + read_pmevcntr_15, + read_pmevcntr_16, + read_pmevcntr_17, + read_pmevcntr_18, + read_pmevcntr_19, + read_pmevcntr_20, + read_pmevcntr_21, + read_pmevcntr_22, + read_pmevcntr_23, + read_pmevcntr_24, + read_pmevcntr_25, + read_pmevcntr_26, + read_pmevcntr_27, + read_pmevcntr_28, + read_pmevcntr_29, + read_pmevcntr_30, + read_pmccntr + }; + + if (counter < ARRAY_SIZE(read_f)) + return (read_f[counter])(); + + return 0; +} + +static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); } + #else static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; } static u64 read_timestamp(void) { return 0; } @@ -353,8 +451,6 @@ int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count count->ena += delta; if (idx) count->run += delta; - - cnt = mul_u64_u64_div64(cnt, count->ena, count->run); } count->val = cnt; 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 ce91a582f0e4..ed616fc19b4f 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> @@ -21,6 +22,9 @@ #include "tests.h" #include <internal/evsel.h> +#define EVENT_NUM 15 +#define WAIT_COUNT 100000000UL + static int libperf_print(enum libperf_print_level level, const char *fmt, va_list ap) { @@ -65,7 +69,7 @@ static int test_stat_cpu(void) perf_evlist__set_maps(evlist, cpus, NULL); err = perf_evlist__open(evlist); - __T("failed to open evsel", err == 0); + __T("failed to open evlist", err == 0); perf_evlist__for_each_evsel(evlist, evsel) { cpus = perf_evsel__cpus(evsel); @@ -126,7 +130,7 @@ static int test_stat_thread(void) perf_evlist__set_maps(evlist, NULL, threads); err = perf_evlist__open(evlist); - __T("failed to open evsel", err == 0); + __T("failed to open evlist", err == 0); perf_evlist__for_each_evsel(evlist, evsel) { perf_evsel__read(evsel, 0, 0, &counts); @@ -183,7 +187,7 @@ static int test_stat_thread_enable(void) perf_evlist__set_maps(evlist, NULL, threads); err = perf_evlist__open(evlist); - __T("failed to open evsel", err == 0); + __T("failed to open evlist", err == 0); perf_evlist__for_each_evsel(evlist, evsel) { perf_evsel__read(evsel, 0, 0, &counts); @@ -331,7 +335,8 @@ static int test_mmap_cpus(void) }; cpu_set_t saved_mask; char path[PATH_MAX]; - int id, err, cpu, tmp; + int id, err, tmp; + struct perf_cpu cpu; union perf_event *event; int count = 0; @@ -374,7 +379,7 @@ static int test_mmap_cpus(void) cpu_set_t mask; CPU_ZERO(&mask); - CPU_SET(cpu, &mask); + CPU_SET(cpu.cpu, &mask); err = sched_setaffinity(0, sizeof(mask), &mask); __T("sched_setaffinity failed", err == 0); @@ -413,6 +418,159 @@ static int test_mmap_cpus(void) return 0; } +static double display_error(long long average, + long long high, + long long low, + long long expected) +{ + double error; + + error = (((double)average - expected) / expected) * 100.0; + + __T_VERBOSE(" Expected: %lld\n", expected); + __T_VERBOSE(" High: %lld Low: %lld Average: %lld\n", + high, low, average); + + __T_VERBOSE(" Average Error = %.2f%%\n", error); + + return error; +} + +static int test_stat_multiplexing(void) +{ + struct perf_counts_values expected_counts = { .val = 0 }; + struct perf_counts_values counts[EVENT_NUM] = {{ .val = 0 },}; + struct perf_thread_map *threads; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_INSTRUCTIONS, + .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED | + PERF_FORMAT_TOTAL_TIME_RUNNING, + .disabled = 1, + }; + int err, i, nonzero = 0; + unsigned long count; + long long max = 0, min = 0, avg = 0; + double error = 0.0; + s8 scaled = 0; + + /* read for non-multiplexing event count */ + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, NULL, threads); + __T("failed to open evsel", err == 0); + + err = perf_evsel__enable(evsel); + __T("failed to enable evsel", err == 0); + + /* wait loop */ + count = WAIT_COUNT; + while (count--) + ; + + perf_evsel__read(evsel, 0, 0, &expected_counts); + __T("failed to read value for evsel", expected_counts.val != 0); + __T("failed to read non-multiplexing event count", + expected_counts.ena == expected_counts.run); + + err = perf_evsel__disable(evsel); + __T("failed to enable evsel", err == 0); + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_thread_map__put(threads); + + /* read for multiplexing event count */ + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + for (i = 0; i < EVENT_NUM; i++) { + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + perf_evlist__add(evlist, evsel); + } + perf_evlist__set_maps(evlist, NULL, threads); + + err = perf_evlist__open(evlist); + __T("failed to open evlist", err == 0); + + perf_evlist__enable(evlist); + + /* wait loop */ + count = WAIT_COUNT; + while (count--) + ; + + i = 0; + perf_evlist__for_each_evsel(evlist, evsel) { + perf_evsel__read(evsel, 0, 0, &counts[i]); + __T("failed to read value for evsel", counts[i].val != 0); + i++; + } + + perf_evlist__disable(evlist); + + min = counts[0].val; + for (i = 0; i < EVENT_NUM; i++) { + __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 = %" PRIu64 " (%.2lf%%, %" PRIu64 "/%" PRIu64 ")\n", + counts[i].val, + (double)counts[i].run / (double)counts[i].ena * 100.0, + counts[i].run, counts[i].ena); + } else if (scaled == -1) { + __T_VERBOSE("\t Not Running\n"); + } else { + __T_VERBOSE("\t Not Scaling\n"); + } + + if (counts[i].val > max) + max = counts[i].val; + + if (counts[i].val < min) + min = counts[i].val; + + avg += counts[i].val; + + if (counts[i].val != 0) + nonzero++; + } + + if (nonzero != 0) + avg = avg / nonzero; + else + avg = 0; + + error = display_error(avg, max, min, expected_counts.val); + + __T("Error out of range!", ((error <= 1.0) && (error >= -1.0))); + + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + + perf_thread_map__put(threads); + + return 0; +} + int test_evlist(int argc, char **argv) { __T_START; @@ -424,6 +582,7 @@ int test_evlist(int argc, char **argv) test_stat_thread_enable(); test_mmap_thread(); test_mmap_cpus(); + test_stat_multiplexing(); __T_END; return tests_failed == 0 ? 0 : -1; diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index 33ae9334861a..a11fc51bfb68 100644 --- a/tools/lib/perf/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c @@ -1,10 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdarg.h> #include <stdio.h> +#include <string.h> #include <linux/perf_event.h> +#include <linux/kernel.h> #include <perf/cpumap.h> #include <perf/threadmap.h> #include <perf/evsel.h> +#include <internal/evsel.h> #include <internal/tests.h> #include "tests.h" @@ -130,6 +133,9 @@ static int test_stat_user_read(int event) struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = event, +#ifdef __aarch64__ + .config1 = 0x2, /* Request user access */ +#endif }; int err, i; @@ -150,7 +156,7 @@ static int test_stat_user_read(int event) pc = perf_evsel__mmap_base(evsel, 0, 0); __T("failed to get mmapped address", pc); -#if defined(__i386__) || defined(__x86_64__) +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) __T("userspace counter access not supported", pc->cap_user_rdpmc); __T("userspace counter access not enabled", pc->index); __T("userspace counter width not set", pc->pmc_width >= 32); @@ -186,6 +192,163 @@ static int test_stat_user_read(int event) return 0; } +static int test_stat_read_format_single(struct perf_event_attr *attr, struct perf_thread_map *threads) +{ + struct perf_evsel *evsel; + struct perf_counts_values counts; + volatile int count = 0x100000; + int err; + + evsel = perf_evsel__new(attr); + __T("failed to create evsel", evsel); + + /* skip old kernels that don't support the format */ + err = perf_evsel__open(evsel, NULL, threads); + if (err < 0) + return 0; + + while (count--) ; + + memset(&counts, -1, sizeof(counts)); + perf_evsel__read(evsel, 0, 0, &counts); + + __T("failed to read value", counts.val); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + __T("failed to read TOTAL_TIME_ENABLED", counts.ena); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + __T("failed to read TOTAL_TIME_RUNNING", counts.run); + if (attr->read_format & PERF_FORMAT_ID) + __T("failed to read ID", counts.id); + if (attr->read_format & PERF_FORMAT_LOST) + __T("failed to read LOST", counts.lost == 0); + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + return 0; +} + +static int test_stat_read_format_group(struct perf_event_attr *attr, struct perf_thread_map *threads) +{ + struct perf_evsel *leader, *member; + struct perf_counts_values counts; + volatile int count = 0x100000; + int err; + + attr->read_format |= PERF_FORMAT_GROUP; + leader = perf_evsel__new(attr); + __T("failed to create leader", leader); + + attr->read_format &= ~PERF_FORMAT_GROUP; + member = perf_evsel__new(attr); + __T("failed to create member", member); + + member->leader = leader; + leader->nr_members = 2; + + /* skip old kernels that don't support the format */ + err = perf_evsel__open(leader, NULL, threads); + if (err < 0) + return 0; + err = perf_evsel__open(member, NULL, threads); + if (err < 0) + return 0; + + while (count--) ; + + memset(&counts, -1, sizeof(counts)); + perf_evsel__read(leader, 0, 0, &counts); + + __T("failed to read leader value", counts.val); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + __T("failed to read leader TOTAL_TIME_ENABLED", counts.ena); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + __T("failed to read leader TOTAL_TIME_RUNNING", counts.run); + if (attr->read_format & PERF_FORMAT_ID) + __T("failed to read leader ID", counts.id); + if (attr->read_format & PERF_FORMAT_LOST) + __T("failed to read leader LOST", counts.lost == 0); + + memset(&counts, -1, sizeof(counts)); + perf_evsel__read(member, 0, 0, &counts); + + __T("failed to read member value", counts.val); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + __T("failed to read member TOTAL_TIME_ENABLED", counts.ena); + if (attr->read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + __T("failed to read member TOTAL_TIME_RUNNING", counts.run); + if (attr->read_format & PERF_FORMAT_ID) + __T("failed to read member ID", counts.id); + if (attr->read_format & PERF_FORMAT_LOST) + __T("failed to read member LOST", counts.lost == 0); + + perf_evsel__close(member); + perf_evsel__close(leader); + perf_evsel__delete(member); + perf_evsel__delete(leader); + return 0; +} + +static int test_stat_read_format(void) +{ + struct perf_thread_map *threads; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + }; + int err, i; + +#define FMT(_fmt) PERF_FORMAT_ ## _fmt +#define FMT_TIME (FMT(TOTAL_TIME_ENABLED) | FMT(TOTAL_TIME_RUNNING)) + + uint64_t test_formats [] = { + 0, + FMT_TIME, + FMT(ID), + FMT(LOST), + FMT_TIME | FMT(ID), + FMT_TIME | FMT(LOST), + FMT_TIME | FMT(ID) | FMT(LOST), + FMT(ID) | FMT(LOST), + }; + +#undef FMT +#undef FMT_TIME + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) { + attr.read_format = test_formats[i]; + __T_VERBOSE("testing single read with read_format: %lx\n", + (unsigned long)test_formats[i]); + + err = test_stat_read_format_single(&attr, threads); + __T("failed to read single format", err == 0); + } + + perf_thread_map__put(threads); + + threads = perf_thread_map__new_array(2, NULL); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + perf_thread_map__set_pid(threads, 1, 0); + + for (i = 0; i < (int)ARRAY_SIZE(test_formats); i++) { + attr.read_format = test_formats[i]; + __T_VERBOSE("testing group read with read_format: %lx\n", + (unsigned long)test_formats[i]); + + err = test_stat_read_format_group(&attr, threads); + __T("failed to read group format", err == 0); + } + + perf_thread_map__put(threads); + return 0; +} + int test_evsel(int argc, char **argv) { __T_START; @@ -197,6 +360,7 @@ int test_evsel(int argc, char **argv) test_stat_thread_enable(); test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS); test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES); + test_stat_read_format(); __T_END; return tests_failed == 0 ? 0 : -1; diff --git a/tools/lib/perf/tests/test-threadmap.c b/tools/lib/perf/tests/test-threadmap.c index 5e2a0291e94c..f728ad7002bb 100644 --- a/tools/lib/perf/tests/test-threadmap.c +++ b/tools/lib/perf/tests/test-threadmap.c @@ -11,9 +11,43 @@ static int libperf_print(enum libperf_print_level level, return vfprintf(stderr, fmt, ap); } +static int test_threadmap_array(int nr, pid_t *array) +{ + struct perf_thread_map *threads; + int i; + + threads = perf_thread_map__new_array(nr, array); + __T("Failed to allocate new thread map", threads); + + __T("Unexpected number of threads", perf_thread_map__nr(threads) == nr); + + for (i = 0; i < nr; i++) { + __T("Unexpected initial value of thread", + perf_thread_map__pid(threads, i) == (array ? array[i] : -1)); + } + + for (i = 1; i < nr; i++) + perf_thread_map__set_pid(threads, i, i * 100); + + __T("Unexpected value of thread 0", + perf_thread_map__pid(threads, 0) == (array ? array[0] : -1)); + + for (i = 1; i < nr; i++) { + __T("Unexpected thread value", + perf_thread_map__pid(threads, i) == i * 100); + } + + perf_thread_map__put(threads); + + return 0; +} + +#define THREADS_NR 10 int test_threadmap(int argc, char **argv) { struct perf_thread_map *threads; + pid_t thr_array[THREADS_NR]; + int i; __T_START; @@ -27,6 +61,13 @@ int test_threadmap(int argc, char **argv) perf_thread_map__put(threads); perf_thread_map__put(threads); + test_threadmap_array(THREADS_NR, NULL); + + for (i = 0; i < THREADS_NR; i++) + thr_array[i] = i + 100; + + test_threadmap_array(THREADS_NR, thr_array); + __T_END; return tests_failed == 0 ? 0 : -1; } diff --git a/tools/lib/perf/threadmap.c b/tools/lib/perf/threadmap.c index e92c368b0a6c..07968f3ea093 100644 --- a/tools/lib/perf/threadmap.c +++ b/tools/lib/perf/threadmap.c @@ -32,28 +32,38 @@ struct perf_thread_map *perf_thread_map__realloc(struct perf_thread_map *map, in #define thread_map__alloc(__nr) perf_thread_map__realloc(NULL, __nr) -void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid) +void perf_thread_map__set_pid(struct perf_thread_map *map, int idx, pid_t pid) { - map->map[thread].pid = pid; + map->map[idx].pid = pid; } -char *perf_thread_map__comm(struct perf_thread_map *map, int thread) +char *perf_thread_map__comm(struct perf_thread_map *map, int idx) { - return map->map[thread].comm; + return map->map[idx].comm; } -struct perf_thread_map *perf_thread_map__new_dummy(void) +struct perf_thread_map *perf_thread_map__new_array(int nr_threads, pid_t *array) { - struct perf_thread_map *threads = thread_map__alloc(1); + struct perf_thread_map *threads = thread_map__alloc(nr_threads); + int i; + + if (!threads) + return NULL; + + for (i = 0; i < nr_threads; i++) + perf_thread_map__set_pid(threads, i, array ? array[i] : -1); + + threads->nr = nr_threads; + refcount_set(&threads->refcnt, 1); - if (threads != NULL) { - perf_thread_map__set_pid(threads, 0, -1); - threads->nr = 1; - refcount_set(&threads->refcnt, 1); - } return threads; } +struct perf_thread_map *perf_thread_map__new_dummy(void) +{ + return perf_thread_map__new_array(1, NULL); +} + static void perf_thread_map__delete(struct perf_thread_map *threads) { if (threads) { @@ -85,7 +95,7 @@ int perf_thread_map__nr(struct perf_thread_map *threads) return threads ? threads->nr : 1; } -pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread) +pid_t perf_thread_map__pid(struct perf_thread_map *map, int idx) { - return map->map[thread].pid; + return map->map[idx].pid; } diff --git a/tools/lib/slab.c b/tools/lib/slab.c new file mode 100644 index 000000000000..959997fb0652 --- /dev/null +++ b/tools/lib/slab.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <string.h> + +#include <urcu/uatomic.h> +#include <linux/slab.h> +#include <malloc.h> +#include <linux/gfp.h> + +int kmalloc_nr_allocated; +int kmalloc_verbose; + +void *kmalloc(size_t size, gfp_t gfp) +{ + void *ret; + + if (!(gfp & __GFP_DIRECT_RECLAIM)) + return NULL; + + ret = malloc(size); + uatomic_inc(&kmalloc_nr_allocated); + if (kmalloc_verbose) + printf("Allocating %p from malloc\n", ret); + if (gfp & __GFP_ZERO) + memset(ret, 0, size); + return ret; +} + +void kfree(void *p) +{ + if (!p) + return; + uatomic_dec(&kmalloc_nr_allocated); + if (kmalloc_verbose) + printf("Freeing %p to malloc\n", p); + free(p); +} diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index 1c777a72bb39..8f1a09cdfd17 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -63,7 +63,7 @@ $(LIBFILE): $(SUBCMD_IN) clean: $(call QUIET_CLEAN, libsubcmd) $(RM) $(LIBFILE); \ - find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) + find $(or $(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) FORCE: diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c index 33e94fb83986..5dbea456973e 100644 --- a/tools/lib/subcmd/exec-cmd.c +++ b/tools/lib/subcmd/exec-cmd.c @@ -24,6 +24,9 @@ void exec_cmd_init(const char *exec_name, const char *prefix, subcmd_config.prefix = prefix; subcmd_config.exec_path = exec_path; subcmd_config.exec_path_env = exec_path_env; + + /* Setup environment variable for invoked shell script. */ + setenv("PREFIX", prefix, 1); } #define is_dir_sep(c) ((c) == '/') diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c index 39ebf6192016..9fa75943f2ed 100644 --- a/tools/lib/subcmd/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -806,9 +806,9 @@ static int option__cmp(const void *va, const void *vb) static struct option *options__order(const struct option *opts) { - int nr_opts = 0, len; + int nr_opts = 0, nr_group = 0, len; const struct option *o = opts; - struct option *ordered; + struct option *opt, *ordered, *group; for (o = opts; o->type != OPTION_END; o++) ++nr_opts; @@ -819,7 +819,18 @@ static struct option *options__order(const struct option *opts) goto out; memcpy(ordered, opts, len); - qsort(ordered, nr_opts, sizeof(*o), option__cmp); + /* sort each option group individually */ + for (opt = group = ordered; opt->type != OPTION_END; opt++) { + if (opt->type == OPTION_GROUP) { + qsort(group, nr_group, sizeof(*opt), option__cmp); + group = opt + 1; + nr_group = 0; + continue; + } + nr_group++; + } + qsort(group, nr_group, sizeof(*opt), option__cmp); + out: return ordered; } 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; } diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h index 72ab9870454b..542f9b059c3b 100644 --- a/tools/lib/symbol/kallsyms.h +++ b/tools/lib/symbol/kallsyms.h @@ -7,7 +7,7 @@ #include <linux/types.h> #ifndef KSYM_NAME_LEN -#define KSYM_NAME_LEN 256 +#define KSYM_NAME_LEN 512 #endif static inline u8 kallsyms2elf_binding(char type) diff --git a/tools/lib/thermal/.gitignore b/tools/lib/thermal/.gitignore new file mode 100644 index 000000000000..5d2aeda80fea --- /dev/null +++ b/tools/lib/thermal/.gitignore @@ -0,0 +1,2 @@ +libthermal.so* +libthermal.pc diff --git a/tools/lib/thermal/Build b/tools/lib/thermal/Build new file mode 100644 index 000000000000..4a892d9e24f9 --- /dev/null +++ b/tools/lib/thermal/Build @@ -0,0 +1,5 @@ +libthermal-y += commands.o +libthermal-y += events.o +libthermal-y += thermal_nl.o +libthermal-y += sampling.o +libthermal-y += thermal.o diff --git a/tools/lib/thermal/Makefile b/tools/lib/thermal/Makefile new file mode 100644 index 000000000000..2d0d255fd0e1 --- /dev/null +++ b/tools/lib/thermal/Makefile @@ -0,0 +1,165 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +# Most of this file is copied from tools/lib/perf/Makefile + +LIBTHERMAL_VERSION = 0 +LIBTHERMAL_PATCHLEVEL = 0 +LIBTHERMAL_EXTRAVERSION = 1 + +MAKEFLAGS += --no-print-directory + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +# $(info Determined 'srctree' to be $(srctree)) +endif + +INSTALL = install + +# Use DESTDIR for installing into a different root directory. +# This is useful for building a package. The program will be +# installed in this directory as if it was the root directory. +# Then the build tool can move it later. +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +include $(srctree)/tools/scripts/Makefile.include +include $(srctree)/tools/scripts/Makefile.arch + +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif + +prefix ?= +libdir = $(prefix)/$(libdir_relative) + +# Shell quotes +libdir_SQ = $(subst ','\'',$(libdir)) +libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) + +ifeq ("$(origin V)", "command line") + VERBOSE = $(V) +endif +ifndef VERBOSE + VERBOSE = 0 +endif + +ifeq ($(VERBOSE),1) + Q = +else + Q = @ +endif + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -Wall +endif + +INCLUDES = \ +-I/usr/include/libnl3 \ +-I$(srctree)/tools/lib/thermal/include \ +-I$(srctree)/tools/lib/ \ +-I$(srctree)/tools/include \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/ \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/uapi \ +-I$(srctree)/tools/include/uapi + +# Append required CFLAGS +override CFLAGS += $(EXTRA_WARNINGS) +override CFLAGS += -Werror -Wall +override CFLAGS += -fPIC +override CFLAGS += $(INCLUDES) +override CFLAGS += -fvisibility=hidden +override CFGLAS += -Wl,-L. +override CFGLAS += -Wl,-lthermal + +all: + +export srctree OUTPUT CC LD CFLAGS V +export DESTDIR DESTDIR_SQ + +include $(srctree)/tools/build/Makefile.include + +VERSION_SCRIPT := libthermal.map + +PATCHLEVEL = $(LIBTHERMAL_PATCHLEVEL) +EXTRAVERSION = $(LIBTHERMAL_EXTRAVERSION) +VERSION = $(LIBTHERMAL_VERSION).$(LIBTHERMAL_PATCHLEVEL).$(LIBTHERMAL_EXTRAVERSION) + +LIBTHERMAL_SO := $(OUTPUT)libthermal.so.$(VERSION) +LIBTHERMAL_A := $(OUTPUT)libthermal.a +LIBTHERMAL_IN := $(OUTPUT)libthermal-in.o +LIBTHERMAL_PC := $(OUTPUT)libthermal.pc +LIBTHERMAL_ALL := $(LIBTHERMAL_A) $(OUTPUT)libthermal.so* + +THERMAL_UAPI := include/uapi/linux/thermal.h + +$(THERMAL_UAPI): FORCE + ln -sf $(srctree)/$@ $(srctree)/tools/$@ + +$(LIBTHERMAL_IN): FORCE + $(Q)$(MAKE) $(build)=libthermal + +$(LIBTHERMAL_A): $(LIBTHERMAL_IN) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBTHERMAL_IN) + +$(LIBTHERMAL_SO): $(LIBTHERMAL_IN) + $(QUIET_LINK)$(CC) --shared -Wl,-soname,libthermal.so \ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@ + @ln -sf $(@F) $(OUTPUT)libthermal.so + @ln -sf $(@F) $(OUTPUT)libthermal.so.$(LIBTHERMAL_VERSION) + + +libs: $(THERMAL_UAPI) $(LIBTHERMAL_A) $(LIBTHERMAL_SO) $(LIBTHERMAL_PC) + +all: fixdep + $(Q)$(MAKE) libs + +clean: + $(call QUIET_CLEAN, libthermal) $(RM) $(LIBTHERMAL_A) \ + *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBTHERMAL_VERSION) .*.d .*.cmd LIBTHERMAL-CFLAGS $(LIBTHERMAL_PC) + +$(LIBTHERMAL_PC): + $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ + -e "s|@LIBDIR@|$(libdir_SQ)|" \ + -e "s|@VERSION@|$(VERSION)|" \ + < libthermal.pc.template > $@ + +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + +define do_install + if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ + fi; \ + $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2' +endef + +install_lib: libs + $(call QUIET_INSTALL, $(LIBTHERMAL_ALL)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIBTHERMAL_ALL) $(DESTDIR)$(libdir_SQ) + +install_headers: + $(call QUIET_INSTALL, headers) \ + $(call do_install,include/thermal.h,$(prefix)/include/thermal,644); \ + +install_pkgconfig: $(LIBTHERMAL_PC) + $(call QUIET_INSTALL, $(LIBTHERMAL_PC)) \ + $(call do_install,$(LIBTHERMAL_PC),$(libdir_SQ)/pkgconfig,644) + +install_doc: + $(Q)$(MAKE) -C Documentation install-man install-html install-examples + +install: install_lib install_headers install_pkgconfig + +FORCE: + +.PHONY: all install clean FORCE diff --git a/tools/lib/thermal/commands.c b/tools/lib/thermal/commands.c new file mode 100644 index 000000000000..73d4d4e8d6ec --- /dev/null +++ b/tools/lib/thermal/commands.c @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <thermal.h> +#include "thermal_nl.h" + +static struct nla_policy thermal_genl_policy[THERMAL_GENL_ATTR_MAX + 1] = { + /* Thermal zone */ + [THERMAL_GENL_ATTR_TZ] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_TZ_ID] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TEMP] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_TZ_TRIP_ID] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP_TEMP] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP_TYPE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_TRIP_HYST] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_MODE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_CDEV_WEIGHT] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_TZ_NAME] = { .type = NLA_STRING }, + + /* Governor(s) */ + [THERMAL_GENL_ATTR_TZ_GOV] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_TZ_GOV_NAME] = { .type = NLA_STRING }, + + /* Cooling devices */ + [THERMAL_GENL_ATTR_CDEV] = { .type = NLA_NESTED }, + [THERMAL_GENL_ATTR_CDEV_ID] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_CDEV_CUR_STATE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_CDEV_MAX_STATE] = { .type = NLA_U32 }, + [THERMAL_GENL_ATTR_CDEV_NAME] = { .type = NLA_STRING }, +}; + +static int parse_tz_get(struct genl_info *info, struct thermal_zone **tz) +{ + struct nlattr *attr; + struct thermal_zone *__tz = NULL; + size_t size = 0; + int rem; + + nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_TZ], rem) { + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_ID) { + + size++; + + __tz = realloc(__tz, sizeof(*__tz) * (size + 2)); + if (!__tz) + return THERMAL_ERROR; + + __tz[size - 1].id = nla_get_u32(attr); + } + + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_NAME) + nla_strlcpy(__tz[size - 1].name, attr, + THERMAL_NAME_LENGTH); + } + + if (__tz) + __tz[size].id = -1; + + *tz = __tz; + + return THERMAL_SUCCESS; +} + +static int parse_cdev_get(struct genl_info *info, struct thermal_cdev **cdev) +{ + struct nlattr *attr; + struct thermal_cdev *__cdev = NULL; + size_t size = 0; + int rem; + + nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_CDEV], rem) { + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_ID) { + + size++; + + __cdev = realloc(__cdev, sizeof(*__cdev) * (size + 2)); + if (!__cdev) + return THERMAL_ERROR; + + __cdev[size - 1].id = nla_get_u32(attr); + } + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_NAME) { + nla_strlcpy(__cdev[size - 1].name, attr, + THERMAL_NAME_LENGTH); + } + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_CUR_STATE) + __cdev[size - 1].cur_state = nla_get_u32(attr); + + if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_MAX_STATE) + __cdev[size - 1].max_state = nla_get_u32(attr); + } + + if (__cdev) + __cdev[size].id = -1; + + *cdev = __cdev; + + return THERMAL_SUCCESS; +} + +static int parse_tz_get_trip(struct genl_info *info, struct thermal_zone *tz) +{ + struct nlattr *attr; + struct thermal_trip *__tt = NULL; + size_t size = 0; + int rem; + + nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_TZ_TRIP], rem) { + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_ID) { + + size++; + + __tt = realloc(__tt, sizeof(*__tt) * (size + 2)); + if (!__tt) + return THERMAL_ERROR; + + __tt[size - 1].id = nla_get_u32(attr); + } + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_TYPE) + __tt[size - 1].type = nla_get_u32(attr); + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_TEMP) + __tt[size - 1].temp = nla_get_u32(attr); + + if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_HYST) + __tt[size - 1].hyst = nla_get_u32(attr); + } + + if (__tt) + __tt[size].id = -1; + + tz->trip = __tt; + + return THERMAL_SUCCESS; +} + +static int parse_tz_get_temp(struct genl_info *info, struct thermal_zone *tz) +{ + int id = -1; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_ID]) + id = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_ID]); + + if (tz->id != id) + return THERMAL_ERROR; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_TEMP]) + tz->temp = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_TEMP]); + + return THERMAL_SUCCESS; +} + +static int parse_tz_get_gov(struct genl_info *info, struct thermal_zone *tz) +{ + int id = -1; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_ID]) + id = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_ID]); + + if (tz->id != id) + return THERMAL_ERROR; + + if (info->attrs[THERMAL_GENL_ATTR_TZ_GOV_NAME]) { + nla_strlcpy(tz->governor, + info->attrs[THERMAL_GENL_ATTR_TZ_GOV_NAME], + THERMAL_NAME_LENGTH); + } + + return THERMAL_SUCCESS; +} + +static int handle_netlink(struct nl_cache_ops *unused, + struct genl_cmd *cmd, + struct genl_info *info, void *arg) +{ + int ret; + + switch (cmd->c_id) { + + case THERMAL_GENL_CMD_TZ_GET_ID: + ret = parse_tz_get(info, arg); + break; + + case THERMAL_GENL_CMD_CDEV_GET: + ret = parse_cdev_get(info, arg); + break; + + case THERMAL_GENL_CMD_TZ_GET_TEMP: + ret = parse_tz_get_temp(info, arg); + break; + + case THERMAL_GENL_CMD_TZ_GET_TRIP: + ret = parse_tz_get_trip(info, arg); + break; + + case THERMAL_GENL_CMD_TZ_GET_GOV: + ret = parse_tz_get_gov(info, arg); + break; + + default: + return THERMAL_ERROR; + } + + return ret; +} + +static struct genl_cmd thermal_cmds[] = { + { + .c_id = THERMAL_GENL_CMD_TZ_GET_ID, + .c_name = (char *)"List thermal zones", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_TZ_GET_GOV, + .c_name = (char *)"Get governor", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_TZ_GET_TEMP, + .c_name = (char *)"Get thermal zone temperature", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_TZ_GET_TRIP, + .c_name = (char *)"Get thermal zone trip points", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, + { + .c_id = THERMAL_GENL_CMD_CDEV_GET, + .c_name = (char *)"Get cooling devices", + .c_msg_parser = handle_netlink, + .c_maxattr = THERMAL_GENL_ATTR_MAX, + .c_attr_policy = thermal_genl_policy, + }, +}; + +static struct genl_ops thermal_cmd_ops = { + .o_name = (char *)"thermal", + .o_cmds = thermal_cmds, + .o_ncmds = ARRAY_SIZE(thermal_cmds), +}; + +static thermal_error_t thermal_genl_auto(struct thermal_handler *th, int id, int cmd, + int flags, void *arg) +{ + struct nl_msg *msg; + void *hdr; + + msg = nlmsg_alloc(); + if (!msg) + return THERMAL_ERROR; + + hdr = genlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, thermal_cmd_ops.o_id, + 0, flags, cmd, THERMAL_GENL_VERSION); + if (!hdr) + return THERMAL_ERROR; + + if (id >= 0 && nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_ID, id)) + return THERMAL_ERROR; + + if (nl_send_msg(th->sk_cmd, th->cb_cmd, msg, genl_handle_msg, arg)) + return THERMAL_ERROR; + + nlmsg_free(msg); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_cmd_get_tz(struct thermal_handler *th, struct thermal_zone **tz) +{ + return thermal_genl_auto(th, -1, THERMAL_GENL_CMD_TZ_GET_ID, + NLM_F_DUMP | NLM_F_ACK, tz); +} + +thermal_error_t thermal_cmd_get_cdev(struct thermal_handler *th, struct thermal_cdev **tc) +{ + return thermal_genl_auto(th, -1, THERMAL_GENL_CMD_CDEV_GET, + NLM_F_DUMP | NLM_F_ACK, tc); +} + +thermal_error_t thermal_cmd_get_trip(struct thermal_handler *th, struct thermal_zone *tz) +{ + return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_TRIP, + 0, tz); +} + +thermal_error_t thermal_cmd_get_governor(struct thermal_handler *th, struct thermal_zone *tz) +{ + return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_GOV, 0, tz); +} + +thermal_error_t thermal_cmd_get_temp(struct thermal_handler *th, struct thermal_zone *tz) +{ + return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_TEMP, 0, tz); +} + +thermal_error_t thermal_cmd_exit(struct thermal_handler *th) +{ + if (genl_unregister_family(&thermal_cmd_ops)) + return THERMAL_ERROR; + + nl_thermal_disconnect(th->sk_cmd, th->cb_cmd); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_cmd_init(struct thermal_handler *th) +{ + int ret; + int family; + + if (nl_thermal_connect(&th->sk_cmd, &th->cb_cmd)) + return THERMAL_ERROR; + + ret = genl_register_family(&thermal_cmd_ops); + if (ret) + return THERMAL_ERROR; + + ret = genl_ops_resolve(th->sk_cmd, &thermal_cmd_ops); + if (ret) + return THERMAL_ERROR; + + family = genl_ctrl_resolve(th->sk_cmd, "nlctrl"); + if (family != GENL_ID_CTRL) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/events.c b/tools/lib/thermal/events.c new file mode 100644 index 000000000000..a7a55d1a0c4c --- /dev/null +++ b/tools/lib/thermal/events.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <linux/netlink.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + + +#include <thermal.h> +#include "thermal_nl.h" + +/* + * Optimization: fill this array to tell which event we do want to pay + * attention to. That happens at init time with the ops + * structure. Each ops will enable the event and the general handler + * will be able to discard the event if there is not ops associated + * with it. + */ +static int enabled_ops[__THERMAL_GENL_EVENT_MAX]; + +static int handle_thermal_event(struct nl_msg *n, void *arg) +{ + struct nlmsghdr *nlh = nlmsg_hdr(n); + struct genlmsghdr *genlhdr = genlmsg_hdr(nlh); + struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1]; + struct thermal_handler_param *thp = arg; + struct thermal_events_ops *ops = &thp->th->ops->events; + + genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL); + + arg = thp->arg; + + /* + * This is an event we don't care of, bail out. + */ + if (!enabled_ops[genlhdr->cmd]) + return THERMAL_SUCCESS; + + switch (genlhdr->cmd) { + + case THERMAL_GENL_EVENT_TZ_CREATE: + return ops->tz_create(nla_get_string(attrs[THERMAL_GENL_ATTR_TZ_NAME]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_DELETE: + return ops->tz_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_ENABLE: + return ops->tz_enable(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_DISABLE: + return ops->tz_disable(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_CHANGE: + return ops->trip_change(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TYPE]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TEMP]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_HYST]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_ADD: + return ops->trip_add(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TYPE]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TEMP]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_HYST]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_DELETE: + return ops->trip_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_UP: + return ops->trip_high(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg); + + case THERMAL_GENL_EVENT_TZ_TRIP_DOWN: + return ops->trip_low(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg); + + case THERMAL_GENL_EVENT_CDEV_ADD: + return ops->cdev_add(nla_get_string(attrs[THERMAL_GENL_ATTR_CDEV_NAME]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_MAX_STATE]), arg); + + case THERMAL_GENL_EVENT_CDEV_DELETE: + return ops->cdev_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]), arg); + + case THERMAL_GENL_EVENT_CDEV_STATE_UPDATE: + return ops->cdev_update(nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_CUR_STATE]), arg); + + case THERMAL_GENL_EVENT_TZ_GOV_CHANGE: + return ops->gov_change(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_string(attrs[THERMAL_GENL_ATTR_GOV_NAME]), arg); + default: + return -1; + } +} + +static void thermal_events_ops_init(struct thermal_events_ops *ops) +{ + enabled_ops[THERMAL_GENL_EVENT_TZ_CREATE] = !!ops->tz_create; + enabled_ops[THERMAL_GENL_EVENT_TZ_DELETE] = !!ops->tz_delete; + enabled_ops[THERMAL_GENL_EVENT_TZ_DISABLE] = !!ops->tz_disable; + enabled_ops[THERMAL_GENL_EVENT_TZ_ENABLE] = !!ops->tz_enable; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_UP] = !!ops->trip_high; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_DOWN] = !!ops->trip_low; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_CHANGE] = !!ops->trip_change; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_ADD] = !!ops->trip_add; + enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_DELETE] = !!ops->trip_delete; + enabled_ops[THERMAL_GENL_EVENT_CDEV_ADD] = !!ops->cdev_add; + enabled_ops[THERMAL_GENL_EVENT_CDEV_DELETE] = !!ops->cdev_delete; + enabled_ops[THERMAL_GENL_EVENT_CDEV_STATE_UPDATE] = !!ops->cdev_update; + enabled_ops[THERMAL_GENL_EVENT_TZ_GOV_CHANGE] = !!ops->gov_change; +} + +thermal_error_t thermal_events_handle(struct thermal_handler *th, void *arg) +{ + struct thermal_handler_param thp = { .th = th, .arg = arg }; + + if (!th) + return THERMAL_ERROR; + + if (nl_cb_set(th->cb_event, NL_CB_VALID, NL_CB_CUSTOM, + handle_thermal_event, &thp)) + return THERMAL_ERROR; + + return nl_recvmsgs(th->sk_event, th->cb_event); +} + +int thermal_events_fd(struct thermal_handler *th) +{ + if (!th) + return -1; + + return nl_socket_get_fd(th->sk_event); +} + +thermal_error_t thermal_events_exit(struct thermal_handler *th) +{ + if (nl_unsubscribe_thermal(th->sk_event, th->cb_event, + THERMAL_GENL_EVENT_GROUP_NAME)) + return THERMAL_ERROR; + + nl_thermal_disconnect(th->sk_event, th->cb_event); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_events_init(struct thermal_handler *th) +{ + thermal_events_ops_init(&th->ops->events); + + if (nl_thermal_connect(&th->sk_event, &th->cb_event)) + return THERMAL_ERROR; + + if (nl_subscribe_thermal(th->sk_event, th->cb_event, + THERMAL_GENL_EVENT_GROUP_NAME)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/include/thermal.h b/tools/lib/thermal/include/thermal.h new file mode 100644 index 000000000000..1abc560602cf --- /dev/null +++ b/tools/lib/thermal/include/thermal.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: LGPL-2.1+ */ +/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */ +#ifndef __LIBTHERMAL_H +#define __LIBTHERMAL_H + +#include <linux/thermal.h> + +#ifndef LIBTHERMAL_API +#define LIBTHERMAL_API __attribute__((visibility("default"))) +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +struct thermal_sampling_ops { + int (*tz_temp)(int tz_id, int temp, void *arg); +}; + +struct thermal_events_ops { + int (*tz_create)(const char *name, int tz_id, void *arg); + int (*tz_delete)(int tz_id, void *arg); + int (*tz_enable)(int tz_id, void *arg); + int (*tz_disable)(int tz_id, void *arg); + int (*trip_high)(int tz_id, int trip_id, int temp, void *arg); + int (*trip_low)(int tz_id, int trip_id, int temp, void *arg); + int (*trip_add)(int tz_id, int trip_id, int type, int temp, int hyst, void *arg); + int (*trip_change)(int tz_id, int trip_id, int type, int temp, int hyst, void *arg); + int (*trip_delete)(int tz_id, int trip_id, void *arg); + int (*cdev_add)(const char *name, int cdev_id, int max_state, void *arg); + int (*cdev_delete)(int cdev_id, void *arg); + int (*cdev_update)(int cdev_id, int cur_state, void *arg); + int (*gov_change)(int tz_id, const char *gov_name, void *arg); +}; + +struct thermal_ops { + struct thermal_sampling_ops sampling; + struct thermal_events_ops events; +}; + +struct thermal_trip { + int id; + int type; + int temp; + int hyst; +}; + +struct thermal_zone { + int id; + int temp; + char name[THERMAL_NAME_LENGTH]; + char governor[THERMAL_NAME_LENGTH]; + struct thermal_trip *trip; +}; + +struct thermal_cdev { + int id; + char name[THERMAL_NAME_LENGTH]; + int max_state; + int min_state; + int cur_state; +}; + +typedef enum { + THERMAL_ERROR = -1, + THERMAL_SUCCESS = 0, +} thermal_error_t; + +struct thermal_handler; + +typedef int (*cb_tz_t)(struct thermal_zone *, void *); + +typedef int (*cb_tt_t)(struct thermal_trip *, void *); + +typedef int (*cb_tc_t)(struct thermal_cdev *, void *); + +LIBTHERMAL_API int for_each_thermal_zone(struct thermal_zone *tz, cb_tz_t cb, void *arg); + +LIBTHERMAL_API int for_each_thermal_trip(struct thermal_trip *tt, cb_tt_t cb, void *arg); + +LIBTHERMAL_API int for_each_thermal_cdev(struct thermal_cdev *cdev, cb_tc_t cb, void *arg); + +LIBTHERMAL_API struct thermal_zone *thermal_zone_find_by_name(struct thermal_zone *tz, + const char *name); + +LIBTHERMAL_API struct thermal_zone *thermal_zone_find_by_id(struct thermal_zone *tz, int id); + +LIBTHERMAL_API struct thermal_zone *thermal_zone_discover(struct thermal_handler *th); + +LIBTHERMAL_API struct thermal_handler *thermal_init(struct thermal_ops *ops); + +LIBTHERMAL_API void thermal_exit(struct thermal_handler *th); + +/* + * Netlink thermal events + */ +LIBTHERMAL_API thermal_error_t thermal_events_exit(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_events_init(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_events_handle(struct thermal_handler *th, void *arg); + +LIBTHERMAL_API int thermal_events_fd(struct thermal_handler *th); + +/* + * Netlink thermal commands + */ +LIBTHERMAL_API thermal_error_t thermal_cmd_exit(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_cmd_init(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_tz(struct thermal_handler *th, + struct thermal_zone **tz); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_cdev(struct thermal_handler *th, + struct thermal_cdev **tc); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_trip(struct thermal_handler *th, + struct thermal_zone *tz); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_governor(struct thermal_handler *th, + struct thermal_zone *tz); + +LIBTHERMAL_API thermal_error_t thermal_cmd_get_temp(struct thermal_handler *th, + struct thermal_zone *tz); + +/* + * Netlink thermal samples + */ +LIBTHERMAL_API thermal_error_t thermal_sampling_exit(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_sampling_init(struct thermal_handler *th); + +LIBTHERMAL_API thermal_error_t thermal_sampling_handle(struct thermal_handler *th, void *arg); + +LIBTHERMAL_API int thermal_sampling_fd(struct thermal_handler *th); + +#endif /* __LIBTHERMAL_H */ + +#ifdef __cplusplus +} +#endif diff --git a/tools/lib/thermal/libthermal.map b/tools/lib/thermal/libthermal.map new file mode 100644 index 000000000000..d5e77738c7a4 --- /dev/null +++ b/tools/lib/thermal/libthermal.map @@ -0,0 +1,25 @@ +LIBTHERMAL_0.0.1 { + global: + thermal_init; + for_each_thermal_zone; + for_each_thermal_trip; + for_each_thermal_cdev; + thermal_zone_find_by_name; + thermal_zone_find_by_id; + thermal_zone_discover; + thermal_init; + thermal_events_init; + thermal_events_handle; + thermal_events_fd; + thermal_cmd_init; + thermal_cmd_get_tz; + thermal_cmd_get_cdev; + thermal_cmd_get_trip; + thermal_cmd_get_governor; + thermal_cmd_get_temp; + thermal_sampling_init; + thermal_sampling_handle; + thermal_sampling_fd; +local: + *; +}; diff --git a/tools/lib/thermal/libthermal.pc.template b/tools/lib/thermal/libthermal.pc.template new file mode 100644 index 000000000000..6f3769731b59 --- /dev/null +++ b/tools/lib/thermal/libthermal.pc.template @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +prefix=@PREFIX@ +libdir=@LIBDIR@ +includedir=${prefix}/include + +Name: libthermal +Description: thermal library +Requires: libnl-3.0 libnl-genl-3.0 +Version: @VERSION@ +Libs: -L${libdir} -lnl-genl-3 -lnl-3 +Cflags: -I${includedir} -I{include}/libnl3 diff --git a/tools/lib/thermal/sampling.c b/tools/lib/thermal/sampling.c new file mode 100644 index 000000000000..ee818f4e9654 --- /dev/null +++ b/tools/lib/thermal/sampling.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <thermal.h> +#include "thermal_nl.h" + +static int handle_thermal_sample(struct nl_msg *n, void *arg) +{ + struct nlmsghdr *nlh = nlmsg_hdr(n); + struct genlmsghdr *genlhdr = genlmsg_hdr(nlh); + struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1]; + struct thermal_handler_param *thp = arg; + struct thermal_handler *th = thp->th; + + genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL); + + switch (genlhdr->cmd) { + + case THERMAL_GENL_SAMPLING_TEMP: + return th->ops->sampling.tz_temp( + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), + nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg); + default: + return THERMAL_ERROR; + } +} + +thermal_error_t thermal_sampling_handle(struct thermal_handler *th, void *arg) +{ + struct thermal_handler_param thp = { .th = th, .arg = arg }; + + if (!th) + return THERMAL_ERROR; + + if (nl_cb_set(th->cb_sampling, NL_CB_VALID, NL_CB_CUSTOM, + handle_thermal_sample, &thp)) + return THERMAL_ERROR; + + return nl_recvmsgs(th->sk_sampling, th->cb_sampling); +} + +int thermal_sampling_fd(struct thermal_handler *th) +{ + if (!th) + return -1; + + return nl_socket_get_fd(th->sk_sampling); +} + +thermal_error_t thermal_sampling_exit(struct thermal_handler *th) +{ + if (nl_unsubscribe_thermal(th->sk_sampling, th->cb_sampling, + THERMAL_GENL_EVENT_GROUP_NAME)) + return THERMAL_ERROR; + + nl_thermal_disconnect(th->sk_sampling, th->cb_sampling); + + return THERMAL_SUCCESS; +} + +thermal_error_t thermal_sampling_init(struct thermal_handler *th) +{ + if (nl_thermal_connect(&th->sk_sampling, &th->cb_sampling)) + return THERMAL_ERROR; + + if (nl_subscribe_thermal(th->sk_sampling, th->cb_sampling, + THERMAL_GENL_SAMPLING_GROUP_NAME)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/thermal.c b/tools/lib/thermal/thermal.c new file mode 100644 index 000000000000..72a76dc205bc --- /dev/null +++ b/tools/lib/thermal/thermal.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <stdio.h> +#include <thermal.h> + +#include "thermal_nl.h" + +int for_each_thermal_cdev(struct thermal_cdev *cdev, cb_tc_t cb, void *arg) +{ + int i, ret = 0; + + if (!cdev) + return 0; + + for (i = 0; cdev[i].id != -1; i++) + ret |= cb(&cdev[i], arg); + + return ret; +} + +int for_each_thermal_trip(struct thermal_trip *tt, cb_tt_t cb, void *arg) +{ + int i, ret = 0; + + if (!tt) + return 0; + + for (i = 0; tt[i].id != -1; i++) + ret |= cb(&tt[i], arg); + + return ret; +} + +int for_each_thermal_zone(struct thermal_zone *tz, cb_tz_t cb, void *arg) +{ + int i, ret = 0; + + if (!tz) + return 0; + + for (i = 0; tz[i].id != -1; i++) + ret |= cb(&tz[i], arg); + + return ret; +} + +struct thermal_zone *thermal_zone_find_by_name(struct thermal_zone *tz, + const char *name) +{ + int i; + + if (!tz || !name) + return NULL; + + for (i = 0; tz[i].id != -1; i++) { + if (!strcmp(tz[i].name, name)) + return &tz[i]; + } + + return NULL; +} + +struct thermal_zone *thermal_zone_find_by_id(struct thermal_zone *tz, int id) +{ + int i; + + if (!tz || id < 0) + return NULL; + + for (i = 0; tz[i].id != -1; i++) { + if (tz[i].id == id) + return &tz[i]; + } + + return NULL; +} + +static int __thermal_zone_discover(struct thermal_zone *tz, void *th) +{ + if (thermal_cmd_get_trip(th, tz) < 0) + return -1; + + if (thermal_cmd_get_governor(th, tz)) + return -1; + + return 0; +} + +struct thermal_zone *thermal_zone_discover(struct thermal_handler *th) +{ + struct thermal_zone *tz; + + if (thermal_cmd_get_tz(th, &tz) < 0) + return NULL; + + if (for_each_thermal_zone(tz, __thermal_zone_discover, th)) + return NULL; + + return tz; +} + +void thermal_exit(struct thermal_handler *th) +{ + thermal_cmd_exit(th); + thermal_events_exit(th); + thermal_sampling_exit(th); + + free(th); +} + +struct thermal_handler *thermal_init(struct thermal_ops *ops) +{ + struct thermal_handler *th; + + th = malloc(sizeof(*th)); + if (!th) + return NULL; + th->ops = ops; + + if (thermal_events_init(th)) + goto out_free; + + if (thermal_sampling_init(th)) + goto out_free; + + if (thermal_cmd_init(th)) + goto out_free; + + return th; + +out_free: + free(th); + + return NULL; +} diff --git a/tools/lib/thermal/thermal_nl.c b/tools/lib/thermal/thermal_nl.c new file mode 100644 index 000000000000..b05cf9569858 --- /dev/null +++ b/tools/lib/thermal/thermal_nl.c @@ -0,0 +1,215 @@ +// SPDX-License-Identifier: LGPL-2.1+ +// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +#include <thermal.h> +#include "thermal_nl.h" + +struct handler_args { + const char *group; + int id; +}; + +static __thread int err; +static __thread int done; + +static int nl_seq_check_handler(struct nl_msg *msg, void *arg) +{ + return NL_OK; +} + +static int nl_error_handler(struct sockaddr_nl *nla, struct nlmsgerr *nl_err, + void *arg) +{ + int *ret = arg; + + if (ret) + *ret = nl_err->error; + + return NL_STOP; +} + +static int nl_finish_handler(struct nl_msg *msg, void *arg) +{ + int *ret = arg; + + if (ret) + *ret = 1; + + return NL_OK; +} + +static int nl_ack_handler(struct nl_msg *msg, void *arg) +{ + int *ret = arg; + + if (ret) + *ret = 1; + + return NL_OK; +} + +int nl_send_msg(struct nl_sock *sock, struct nl_cb *cb, struct nl_msg *msg, + int (*rx_handler)(struct nl_msg *, void *), void *data) +{ + if (!rx_handler) + return THERMAL_ERROR; + + err = nl_send_auto_complete(sock, msg); + if (err < 0) + return err; + + nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, rx_handler, data); + + err = done = 0; + + while (err == 0 && done == 0) + nl_recvmsgs(sock, cb); + + return err; +} + +static int nl_family_handler(struct nl_msg *msg, void *arg) +{ + struct handler_args *grp = arg; + struct nlattr *tb[CTRL_ATTR_MAX + 1]; + struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg)); + struct nlattr *mcgrp; + int rem_mcgrp; + + nla_parse(tb, CTRL_ATTR_MAX, genlmsg_attrdata(gnlh, 0), + genlmsg_attrlen(gnlh, 0), NULL); + + if (!tb[CTRL_ATTR_MCAST_GROUPS]) + return THERMAL_ERROR; + + nla_for_each_nested(mcgrp, tb[CTRL_ATTR_MCAST_GROUPS], rem_mcgrp) { + + struct nlattr *tb_mcgrp[CTRL_ATTR_MCAST_GRP_MAX + 1]; + + nla_parse(tb_mcgrp, CTRL_ATTR_MCAST_GRP_MAX, + nla_data(mcgrp), nla_len(mcgrp), NULL); + + if (!tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME] || + !tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]) + continue; + + if (strncmp(nla_data(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]), + grp->group, + nla_len(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]))) + continue; + + grp->id = nla_get_u32(tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]); + + break; + } + + return THERMAL_SUCCESS; +} + +static int nl_get_multicast_id(struct nl_sock *sock, struct nl_cb *cb, + const char *family, const char *group) +{ + struct nl_msg *msg; + int ret = 0, ctrlid; + struct handler_args grp = { + .group = group, + .id = -ENOENT, + }; + + msg = nlmsg_alloc(); + if (!msg) + return THERMAL_ERROR; + + ctrlid = genl_ctrl_resolve(sock, "nlctrl"); + + genlmsg_put(msg, 0, 0, ctrlid, 0, 0, CTRL_CMD_GETFAMILY, 0); + + nla_put_string(msg, CTRL_ATTR_FAMILY_NAME, family); + + ret = nl_send_msg(sock, cb, msg, nl_family_handler, &grp); + if (ret) + goto nla_put_failure; + + ret = grp.id; + +nla_put_failure: + nlmsg_free(msg); + return ret; +} + +int nl_thermal_connect(struct nl_sock **nl_sock, struct nl_cb **nl_cb) +{ + struct nl_cb *cb; + struct nl_sock *sock; + + cb = nl_cb_alloc(NL_CB_DEFAULT); + if (!cb) + return THERMAL_ERROR; + + sock = nl_socket_alloc(); + if (!sock) + goto out_cb_free; + + if (genl_connect(sock)) + goto out_socket_free; + + if (nl_cb_err(cb, NL_CB_CUSTOM, nl_error_handler, &err) || + nl_cb_set(cb, NL_CB_FINISH, NL_CB_CUSTOM, nl_finish_handler, &done) || + nl_cb_set(cb, NL_CB_ACK, NL_CB_CUSTOM, nl_ack_handler, &done) || + nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM, nl_seq_check_handler, &done)) + return THERMAL_ERROR; + + *nl_sock = sock; + *nl_cb = cb; + + return THERMAL_SUCCESS; + +out_socket_free: + nl_socket_free(sock); +out_cb_free: + nl_cb_put(cb); + return THERMAL_ERROR; +} + +void nl_thermal_disconnect(struct nl_sock *nl_sock, struct nl_cb *nl_cb) +{ + nl_close(nl_sock); + nl_socket_free(nl_sock); + nl_cb_put(nl_cb); +} + +int nl_unsubscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group) +{ + int mcid; + + mcid = nl_get_multicast_id(nl_sock, nl_cb, THERMAL_GENL_FAMILY_NAME, + group); + if (mcid < 0) + return THERMAL_ERROR; + + if (nl_socket_drop_membership(nl_sock, mcid)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} + +int nl_subscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group) +{ + int mcid; + + mcid = nl_get_multicast_id(nl_sock, nl_cb, THERMAL_GENL_FAMILY_NAME, + group); + if (mcid < 0) + return THERMAL_ERROR; + + if (nl_socket_add_membership(nl_sock, mcid)) + return THERMAL_ERROR; + + return THERMAL_SUCCESS; +} diff --git a/tools/lib/thermal/thermal_nl.h b/tools/lib/thermal/thermal_nl.h new file mode 100644 index 000000000000..ddf635642f07 --- /dev/null +++ b/tools/lib/thermal/thermal_nl.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: LGPL-2.1+ */ +/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */ +#ifndef __THERMAL_H +#define __THERMAL_H + +#include <netlink/netlink.h> +#include <netlink/genl/genl.h> +#include <netlink/genl/mngt.h> +#include <netlink/genl/ctrl.h> + +struct thermal_handler { + int done; + int error; + struct thermal_ops *ops; + struct nl_msg *msg; + struct nl_sock *sk_event; + struct nl_sock *sk_sampling; + struct nl_sock *sk_cmd; + struct nl_cb *cb_cmd; + struct nl_cb *cb_event; + struct nl_cb *cb_sampling; +}; + +struct thermal_handler_param { + struct thermal_handler *th; + void *arg; +}; + +/* + * Low level netlink + */ +extern int nl_subscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group); + +extern int nl_unsubscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb, + const char *group); + +extern int nl_thermal_connect(struct nl_sock **nl_sock, struct nl_cb **nl_cb); + +extern void nl_thermal_disconnect(struct nl_sock *nl_sock, struct nl_cb *nl_cb); + +extern int nl_send_msg(struct nl_sock *sock, struct nl_cb *nl_cb, struct nl_msg *msg, + int (*rx_handler)(struct nl_msg *, void *), + void *data); + +#endif /* __THERMAL_H */ diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index fe58843d047c..8e24c4c78c7f 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -1367,6 +1367,14 @@ static int field_is_dynamic(struct tep_format_field *field) return 0; } +static int field_is_relative_dynamic(struct tep_format_field *field) +{ + if (strncmp(field->type, "__rel_loc", 9) == 0) + return 1; + + return 0; +} + static int field_is_long(struct tep_format_field *field) { /* includes long long */ @@ -1622,6 +1630,8 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field ** field->flags |= TEP_FIELD_IS_STRING; if (field_is_dynamic(field)) field->flags |= TEP_FIELD_IS_DYNAMIC; + if (field_is_relative_dynamic(field)) + field->flags |= TEP_FIELD_IS_DYNAMIC | TEP_FIELD_IS_RELATIVE; if (field_is_long(field)) field->flags |= TEP_FIELD_IS_LONG; @@ -2928,7 +2938,7 @@ process_str(struct tep_event *event __maybe_unused, struct tep_print_arg *arg, arg->type = TEP_PRINT_STRING; arg->string.string = token; - arg->string.offset = -1; + arg->string.field = NULL; if (read_expected(TEP_EVENT_DELIM, ")") < 0) goto out_err; @@ -2957,7 +2967,7 @@ process_bitmask(struct tep_event *event __maybe_unused, struct tep_print_arg *ar arg->type = TEP_PRINT_BITMASK; arg->bitmask.bitmask = token; - arg->bitmask.offset = -1; + arg->bitmask.field = NULL; if (read_expected(TEP_EVENT_DELIM, ")") < 0) goto out_err; @@ -3123,19 +3133,23 @@ process_function(struct tep_event *event, struct tep_print_arg *arg, free_token(token); return process_int_array(event, arg, tok); } - if (strcmp(token, "__get_str") == 0) { + if (strcmp(token, "__get_str") == 0 || + strcmp(token, "__get_rel_str") == 0) { free_token(token); return process_str(event, arg, tok); } - if (strcmp(token, "__get_bitmask") == 0) { + if (strcmp(token, "__get_bitmask") == 0 || + strcmp(token, "__get_rel_bitmask") == 0) { free_token(token); return process_bitmask(event, arg, tok); } - if (strcmp(token, "__get_dynamic_array") == 0) { + if (strcmp(token, "__get_dynamic_array") == 0 || + strcmp(token, "__get_rel_dynamic_array") == 0) { free_token(token); return process_dynamic_array(event, arg, tok); } - if (strcmp(token, "__get_dynamic_array_len") == 0) { + if (strcmp(token, "__get_dynamic_array_len") == 0 || + strcmp(token, "__get_rel_dynamic_array_len") == 0) { free_token(token); return process_dynamic_array_len(event, arg, tok); } @@ -4163,14 +4177,16 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, case TEP_PRINT_STRING: { int str_offset; - if (arg->string.offset == -1) { - struct tep_format_field *f; + if (!arg->string.field) + arg->string.field = tep_find_any_field(event, arg->string.string); + if (!arg->string.field) + break; - f = tep_find_any_field(event, arg->string.string); - arg->string.offset = f->offset; - } - str_offset = data2host4(tep, *(unsigned int *)(data + arg->string.offset)); + str_offset = data2host4(tep, + *(unsigned int *)(data + arg->string.field->offset)); str_offset &= 0xffff; + if (arg->string.field->flags & TEP_FIELD_IS_RELATIVE) + str_offset += arg->string.field->offset + arg->string.field->size; print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset); break; } @@ -4181,15 +4197,16 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, int bitmask_offset; int bitmask_size; - if (arg->bitmask.offset == -1) { - struct tep_format_field *f; - - f = tep_find_any_field(event, arg->bitmask.bitmask); - arg->bitmask.offset = f->offset; - } - bitmask_offset = data2host4(tep, *(unsigned int *)(data + arg->bitmask.offset)); + if (!arg->bitmask.field) + arg->bitmask.field = tep_find_any_field(event, arg->bitmask.bitmask); + if (!arg->bitmask.field) + break; + bitmask_offset = data2host4(tep, + *(unsigned int *)(data + arg->bitmask.field->offset)); bitmask_size = bitmask_offset >> 16; bitmask_offset &= 0xffff; + if (arg->bitmask.field->flags & TEP_FIELD_IS_RELATIVE) + bitmask_offset += arg->bitmask.field->offset + arg->bitmask.field->size; print_bitmask_to_seq(tep, s, format, len_arg, data + bitmask_offset, bitmask_size); break; @@ -5109,6 +5126,8 @@ void tep_print_field(struct trace_seq *s, void *data, offset = val; len = offset >> 16; offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } if (field->flags & TEP_FIELD_IS_STRING && is_printable_array(data + offset, len)) { @@ -6987,6 +7006,8 @@ void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event, data + offset, field->size); *len = offset >> 16; offset &= 0xffff; + if (field->flags & TEP_FIELD_IS_RELATIVE) + offset += field->offset + field->size; } else *len = field->size; diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index a67ad9a5b835..41d4f9f6a843 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -125,6 +125,7 @@ enum tep_format_flags { TEP_FIELD_IS_LONG = 32, TEP_FIELD_IS_FLAG = 64, TEP_FIELD_IS_SYMBOLIC = 128, + TEP_FIELD_IS_RELATIVE = 256, }; struct tep_format_field { @@ -153,12 +154,12 @@ struct tep_print_arg_atom { struct tep_print_arg_string { char *string; - int offset; + struct tep_format_field *field; }; struct tep_print_arg_bitmask { char *bitmask; - int offset; + struct tep_format_field *field; }; struct tep_print_arg_field { diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index 368826bb5a57..5df177070d53 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -1712,8 +1712,11 @@ static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record * if (arg->str.field->flags & TEP_FIELD_IS_DYNAMIC) { addr = *(unsigned int *)val; - val = record->data + (addr & 0xffff); size = addr >> 16; + addr &= 0xffff; + if (arg->str.field->flags & TEP_FIELD_IS_RELATIVE) + addr += arg->str.field->offset + arg->str.field->size; + val = record->data + addr; } /* diff --git a/tools/lib/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h index 64e9c57fd792..997723b0bfb2 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/testing/selftests/bpf/xsk.h @@ -9,15 +9,15 @@ * Author(s): Magnus Karlsson <magnus.karlsson@intel.com> */ -#ifndef __LIBBPF_XSK_H -#define __LIBBPF_XSK_H +#ifndef __XSK_H +#define __XSK_H #include <stdio.h> #include <stdint.h> #include <stdbool.h> #include <linux/if_xdp.h> -#include "libbpf.h" +#include <bpf/libbpf.h> #ifdef __cplusplus extern "C" { @@ -251,9 +251,7 @@ static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr) return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr); } -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") int xsk_umem__fd(const struct xsk_umem *umem); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") int xsk_socket__fd(const struct xsk_socket *xsk); #define XSK_RING_CONS__DEFAULT_NUM_DESCS 2048 @@ -271,9 +269,8 @@ struct xsk_umem_config { __u32 flags; }; -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") +int xsk_setup_xdp_prog_xsk(struct xsk_socket *xsk, int *xsks_map_fd); int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd); /* Flags for the libbpf_flags field. */ @@ -288,32 +285,17 @@ struct xsk_socket_config { }; /* Set config to NULL to get the default configuration. */ -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") int xsk_umem__create(struct xsk_umem **umem, void *umem_area, __u64 size, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, const struct xsk_umem_config *config); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_umem__create_v0_0_2(struct xsk_umem **umem, - void *umem_area, __u64 size, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_umem_config *config); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") -int xsk_umem__create_v0_0_4(struct xsk_umem **umem, - void *umem_area, __u64 size, - struct xsk_ring_prod *fill, - struct xsk_ring_cons *comp, - const struct xsk_umem_config *config); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") int xsk_socket__create(struct xsk_socket **xsk, const char *ifname, __u32 queue_id, struct xsk_umem *umem, struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, const struct xsk_socket_config *config); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, const char *ifname, __u32 queue_id, struct xsk_umem *umem, @@ -324,13 +306,11 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, const struct xsk_socket_config *config); /* Returns 0 for success and -EBUSY if the umem is still in use. */ -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") int xsk_umem__delete(struct xsk_umem *umem); -LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp") void xsk_socket__delete(struct xsk_socket *xsk); #ifdef __cplusplus } /* extern "C" */ #endif -#endif /* __LIBBPF_XSK_H */ +#endif /* __XSK_H */ |