diff options
Diffstat (limited to 'tools/lib')
38 files changed, 3048 insertions, 1496 deletions
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index b393b5e82380..f947b61b2107 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -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 @@ -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 diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 725701235fd8..550b4cbb6c99 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -28,6 +28,9 @@ #include <asm/unistd.h> #include <errno.h> #include <linux/bpf.h> +#include <linux/filter.h> +#include <limits.h> +#include <sys/resource.h> #include "bpf.h" #include "libbpf.h" #include "libbpf_internal.h" @@ -49,6 +52,12 @@ # 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 +83,208 @@ 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) +#define PROG_LOAD_ATTEMPTS 5 + +static inline 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/[email protected]/ + * [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper") + */ +int probe_memcg_account(void) +{ + const size_t prog_load_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 = sizeof(insns) / sizeof(insns[0]); + union bpf_attr attr; + int prog_fd; + + /* attempt loading freplace trying to use custom BTF */ + memset(&attr, 0, prog_load_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"); + + prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, prog_load_attr_sz); + if (prog_fd >= 0) { + close(prog_fd); + return 1; + } + return 0; +} + +static bool memlock_bumped; +static rlim_t memlock_rlim = RLIM_INFINITY; + +int libbpf_set_memlock_rlim(size_t memlock_bytes) +{ + if (memlock_bumped) + return libbpf_err(-EBUSY); + + memlock_rlim = memlock_bytes; + return 0; +} + +int bump_rlimit_memlock(void) +{ + struct rlimit rlim; + + /* this the default in libbpf 1.0, but for now user has to opt-in explicitly */ + if (!(libbpf_mode & LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK)) + return 0; + + /* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */ + if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT)) + return 0; + + memlock_bumped = true; + + /* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */ + if (memlock_rlim == 0) + return 0; + + rlim.rlim_cur = rlim.rlim_max = memlock_rlim; + if (setrlimit(RLIMIT_MEMLOCK, &rlim)) + return -errno; + + return 0; +} + +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)); - - 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; + 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) + libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); + attr.key_size = key_size; + attr.value_size = value_size; + attr.max_entries = max_entries; - fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, sizeof(attr)); + 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); + + 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); } int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) { - struct bpf_create_map_params p = {}; + LIBBPF_OPTS(bpf_map_create_opts, 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; + if (create_attr->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; - return libbpf__bpf_create_map_xattr(&p); + return bpf_map_create(create_attr->map_type, create_attr->name, + create_attr->key_size, create_attr->value_size, + create_attr->max_entries, &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) { - 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; + LIBBPF_OPTS(bpf_map_create_opts, opts); + + opts.map_flags = map_flags; if (node >= 0) { - map_attr.numa_node = node; - map_attr.map_flags |= BPF_F_NUMA_NODE; + opts.numa_node = node; + opts.map_flags |= BPF_F_NUMA_NODE; } - return bpf_create_map_xattr(&map_attr); + return bpf_map_create(map_type, name, key_size, value_size, max_entries, &opts); } int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags) { - struct bpf_create_map_attr map_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags); - 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; - - return bpf_create_map_xattr(&map_attr); + return bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts); } 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 = {}; - - 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; + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags); - return bpf_create_map_xattr(&map_attr); + return bpf_map_create(map_type, name, key_size, value_size, max_entries, &opts); } 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) { - union bpf_attr attr; - int fd; - - memset(&attr, '\0', sizeof(attr)); - - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = 4; - attr.inner_map_fd = inner_map_fd; - 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)); + LIBBPF_OPTS(bpf_map_create_opts, opts); + opts.inner_map_fd = inner_map_fd; + opts.map_flags = map_flags; if (node >= 0) { - attr.map_flags |= BPF_F_NUMA_NODE; - attr.numa_node = node; + opts.map_flags |= BPF_F_NUMA_NODE; + opts.numa_node = node; } - fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, sizeof(attr)); - return libbpf_err_errno(fd); + return bpf_map_create(map_type, name, key_size, 4, max_entries, &opts); } 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); + LIBBPF_OPTS(bpf_map_create_opts, opts, + .inner_map_fd = inner_map_fd, + .map_flags = map_flags, + ); + + return bpf_map_create(map_type, name, key_size, 4, max_entries, &opts); } static void * @@ -253,58 +312,95 @@ alloc_zero_tailing_info(const void *orecord, __u32 cnt, return info; } -int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) +DEFAULT_VERSION(bpf_prog_load_v0_6_0, bpf_prog_load, LIBBPF_0.6.0) +int bpf_prog_load_v0_6_0(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) { 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; + + bump_rlimit_memlock(); - if (!load_attr->log_buf != !load_attr->log_buf_sz) + 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; - 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) + 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; - attr.prog_btf_fd = load_attr->prog_btf_fd; - attr.prog_flags = load_attr->prog_flags; + 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.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); + 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.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); + 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); - if (load_attr->name) - memcpy(attr.prog_name, load_attr->name, - min(strlen(load_attr->name), (size_t)BPF_OBJ_NAME_LEN - 1)); + 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); + + attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL)); + + 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, sizeof(attr)); + fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts); if (fd >= 0) return fd; @@ -314,11 +410,11 @@ 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 +422,12 @@ 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 +435,27 @@ 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, sizeof(attr), 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, sizeof(attr), attempts); + } done: /* free() doesn't affect errno, so we don't need to restore it */ free(finfo); @@ -367,17 +463,20 @@ done: return libbpf_err_errno(fd); } +__attribute__((alias("bpf_load_program_xattr2"))) int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, - char *log_buf, size_t log_buf_sz) + char *log_buf, size_t log_buf_sz); + +static int bpf_load_program_xattr2(const struct bpf_load_program_attr *load_attr, + char *log_buf, size_t log_buf_sz) { - struct bpf_prog_load_params p = {}; + LIBBPF_OPTS(bpf_prog_load_opts, 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) { + switch (load_attr->prog_type) { case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_LSM: p.attach_btf_id = load_attr->attach_btf_id; @@ -391,12 +490,9 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, 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.log_size = 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; @@ -404,10 +500,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, 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); + return bpf_prog_load(load_attr->prog_type, load_attr->name, load_attr->license, + load_attr->insns, load_attr->insns_cnt, &p); } int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, @@ -426,7 +522,7 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, load_attr.license = license; load_attr.kern_version = kern_version; - return bpf_load_program_xattr(&load_attr, log_buf, log_buf_sz); + return bpf_load_program_xattr2(&load_attr, log_buf, log_buf_sz); } int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, @@ -437,6 +533,8 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, union bpf_attr attr; int fd; + bump_rlimit_memlock(); + memset(&attr, 0, sizeof(attr)); attr.prog_type = type; attr.insn_cnt = (__u32)insns_cnt; @@ -449,7 +547,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, attr.kern_version = kern_version; attr.prog_flags = prog_flags; - fd = sys_bpf_prog_load(&attr, sizeof(attr)); + fd = sys_bpf_prog_load(&attr, sizeof(attr), PROG_LOAD_ATTEMPTS); return libbpf_err_errno(fd); } @@ -593,11 +691,11 @@ static int bpf_map_batch_common(int cmd, int fd, void *in_batch, 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, @@ -617,11 +715,11 @@ 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) @@ -1028,24 +1126,67 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) 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); + bump_rlimit_memlock(); + + memset(&attr, 0, attr_sz); + + 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 (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; + } -retry: - if (do_log && log_buf && log_buf_size) { - attr.btf_log_level = 1; - attr.btf_log_size = log_buf_size; + 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); +} - fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, sizeof(attr)); +int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, bool do_log) +{ + LIBBPF_OPTS(bpf_btf_load_opts, opts); + int fd; + +retry: + if (do_log && log_buf && log_buf_size) { + opts.log_buf = log_buf; + opts.log_size = log_buf_size; + opts.log_level = 1; + } + fd = bpf_btf_load(btf, btf_size, &opts); if (fd < 0 && !do_log && log_buf && log_buf_size) { do_log = true; goto retry; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 6fffb3cdf39b..14e0d97ad2cf 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -29,11 +29,38 @@ #include <stdint.h> #include "libbpf_common.h" +#include "libbpf_legacy.h" #ifdef __cplusplus extern "C" { #endif +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; +}; +#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_create_map_attr { const char *name; enum bpf_map_type map_type; @@ -52,25 +79,95 @@ struct bpf_create_map_attr { }; }; -LIBBPF_API int -bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") +LIBBPF_API int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") 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_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") 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_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") 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_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") 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_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") 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_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; + + enum bpf_attach_type expected_attach_type; + __u32 prog_btf_fd; + __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 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 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); +/* this "specialization" should go away in libbpf 1.0 */ +LIBBPF_API int bpf_prog_load_v0_6_0(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); + +/* This is an elaborate way to not conflict with deprecated bpf_prog_load() + * API, defined in libbpf.h. Once we hit libbpf 1.0, all this will be gone. + * With this approach, if someone is calling bpf_prog_load() with + * 4 arguments, they will use the deprecated API, which keeps backwards + * compatibility (both source code and binary). If bpf_prog_load() is called + * with 6 arguments, though, it gets redirected to __bpf_prog_load. + * So looking forward to libbpf 1.0 when this hack will be gone and + * __bpf_prog_load() will be called just bpf_prog_load(). + */ +#ifndef bpf_prog_load +#define bpf_prog_load(...) ___libbpf_overload(___bpf_prog_load, __VA_ARGS__) +#define ___bpf_prog_load4(file, type, pobj, prog_fd) \ + bpf_prog_load_deprecated(file, type, pobj, prog_fd) +#define ___bpf_prog_load6(prog_type, prog_name, license, insns, insn_cnt, opts) \ + bpf_prog_load(prog_type, prog_name, license, insns, insn_cnt, opts) +#endif /* bpf_prog_load */ + struct bpf_load_program_attr { enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; @@ -100,15 +197,18 @@ struct bpf_load_program_attr { /* 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_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead") +LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, + char *log_buf, size_t log_buf_sz); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead") 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_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead") LIBBPF_API int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, __u32 prog_flags, @@ -116,6 +216,23 @@ LIBBPF_API int bpf_verify_program(enum bpf_prog_type type, 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_DEPRECATED_SINCE(0, 8, "use bpf_btf_load() instead") +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_map_update_elem(int fd, const void *key, const void *value, __u64 flags); @@ -137,17 +254,128 @@ 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); @@ -243,8 +471,6 @@ 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); 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_tracing.h b/tools/lib/bpf/bpf_tracing.h index db05a5937105..90f56b0f585f 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -66,277 +66,204 @@ #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 #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 + +#endif /* __i386__ */ + +#endif /* __KERNEL__ || __VMLINUX_H__ */ #elif defined(bpf_target_s390) /* 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 #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) /* 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 #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 #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 fp +#define __PT_RC_REG a5 +#define __PT_SP_REG sp +#define __PT_IP_REG epc + +#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) +#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 +290,7 @@ 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) */ +#endif /* defined(bpf_target_defined) */ #ifndef ___bpf_concat #define ___bpf_concat(a, b) a ## b @@ -375,25 +302,23 @@ 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 @@ -426,19 +351,13 @@ ____##name(unsigned long long *ctx, ##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 @@ -464,11 +383,9 @@ typeof(name(0)) name(struct pt_regs *ctx) \ static __attribute__((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 diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 7e4c5586bd87..9aa19c89f758 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -299,6 +299,7 @@ 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); @@ -349,6 +350,7 @@ 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)); @@ -452,7 +454,7 @@ 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; @@ -608,6 +610,7 @@ __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: @@ -649,6 +652,7 @@ 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); @@ -1120,54 +1124,86 @@ 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_into_kernel(struct btf *btf) +{ + return btf_load_into_kernel(btf, NULL, 0, 0); +} + int btf__load(struct btf *) __attribute__((alias("btf__load_into_kernel"))); int btf__fd(const struct btf *btf) @@ -2236,6 +2272,22 @@ 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; @@ -2711,15 +2763,11 @@ void btf_ext__free(struct btf_ext *btf_ext) 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 +2780,10 @@ 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; @@ -2846,8 +2898,7 @@ __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext) 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 +3045,17 @@ 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) + +DEFAULT_VERSION(btf__dedup_v0_6_0, btf__dedup, LIBBPF_0.6.0) +int btf__dedup_v0_6_0(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); @@ -3051,6 +3107,19 @@ done: return libbpf_err(err); } +COMPAT_VERSION(btf__dedup_deprecated, btf__dedup, LIBBPF_0.0.2) +int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *unused_opts) +{ + LIBBPF_OPTS(btf_dedup_opts, opts, .btf_ext = btf_ext); + + if (unused_opts) { + pr_warn("please use new version of btf__dedup() that supports options\n"); + return libbpf_err(-ENOTSUP); + } + + return btf__dedup(btf, &opts); +} + #define BTF_UNPROCESSED_ID ((__u32)-1) #define BTF_IN_PROGRESS_ID ((__u32)-2) @@ -3163,8 +3232,7 @@ 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 +3241,11 @@ 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)) { @@ -3443,8 +3509,8 @@ 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 +3691,7 @@ 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: @@ -3685,6 +3752,7 @@ 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 +3776,6 @@ 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 */ @@ -3817,6 +3883,31 @@ 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 +4019,8 @@ 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 +4029,18 @@ 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 +4055,7 @@ 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 +4081,7 @@ 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_FWD: case BTF_KIND_FLOAT: @@ -3994,6 +4093,7 @@ 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 +4389,7 @@ 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; @@ -4595,6 +4696,7 @@ 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: { diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index bc005ba3ceec..061839f04525 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -157,7 +157,7 @@ LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, __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); @@ -227,6 +227,7 @@ 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 +246,86 @@ 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, const struct btf_dedup_opts *opts); + +LIBBPF_API int btf__dedup_v0_6_0(struct btf *btf, const struct btf_dedup_opts *opts); -LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, - const struct btf_dedup_opts *opts); +LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__dedup() instead") +LIBBPF_API int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *opts); +#define btf__dedup(...) ___libbpf_overload(___btf_dedup, __VA_ARGS__) +#define ___btf_dedup3(btf, btf_ext, opts) btf__dedup_deprecated(btf, btf_ext, opts) +#define ___btf_dedup2(btf, opts) btf__dedup(btf, opts) struct btf_dump; struct btf_dump_opts { - void *ctx; + union { + size_t sz; + void *ctx; /* DEPRECATED: will be gone in v1.0 */ + }; }; 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 struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf, + btf_dump_printf_fn_t printf_fn, + void *ctx, + const struct btf_dump_opts *opts); + +LIBBPF_API struct btf_dump *btf_dump__new_deprecated(const struct btf *btf, + const struct btf_ext *btf_ext, + const struct btf_dump_opts *opts, + btf_dump_printf_fn_t printf_fn); + +/* Choose either btf_dump__new() or btf_dump__new_deprecated() based on the + * type of 4th argument. If it's btf_dump's print callback, use deprecated + * API; otherwise, choose the new btf_dump__new(). ___libbpf_override() + * doesn't work here because both variants have 4 input arguments. + * + * (void *) casts are necessary to avoid compilation warnings about type + * mismatches, because even though __builtin_choose_expr() only ever evaluates + * one side the other side still has to satisfy type constraints (this is + * compiler implementation limitation which might be lifted eventually, + * according to the documentation). So passing struct btf_ext in place of + * btf_dump_printf_fn_t would be generating compilation warning. Casting to + * void * avoids this issue. + * + * Also, two type compatibility checks for a function and function pointer are + * required because passing function reference into btf_dump__new() as + * btf_dump__new(..., my_callback, ...) and as btf_dump__new(..., + * &my_callback, ...) (not explicit ampersand in the latter case) actually + * differs as far as __builtin_types_compatible_p() is concerned. Thus two + * checks are combined to detect callback argument. + * + * The rest works just like in case of ___libbpf_override() usage with symbol + * versioning. + * + * C++ compilers don't support __builtin_types_compatible_p(), so at least + * don't screw up compilation for them and let C++ users pick btf_dump__new + * vs btf_dump__new_deprecated explicitly. + */ +#ifndef __cplusplus +#define btf_dump__new(a1, a2, a3, a4) __builtin_choose_expr( \ + __builtin_types_compatible_p(typeof(a4), btf_dump_printf_fn_t) || \ + __builtin_types_compatible_p(typeof(a4), void(void *, const char *, va_list)), \ + btf_dump__new_deprecated((void *)a1, (void *)a2, (void *)a3, (void *)a4), \ + btf_dump__new((void *)a1, (void *)a2, (void *)a3, (void *)a4)) +#endif + LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); @@ -403,7 +465,8 @@ 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 +499,11 @@ 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 __u8 btf_int_encoding(const struct btf_type *t) { return BTF_INT_ENCODING(*(__u32 *)(t + 1)); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 17db62b5002e..b9a3260c83cb 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; @@ -138,29 +137,32 @@ 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); } 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) +DEFAULT_VERSION(btf_dump__new_v0_6_0, btf_dump__new, LIBBPF_0.6.0) +struct btf_dump *btf_dump__new_v0_6_0(const struct btf *btf, + btf_dump_printf_fn_t printf_fn, + void *ctx, + const struct btf_dump_opts *opts) { struct btf_dump *d; int err; + 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); @@ -186,6 +188,17 @@ err: return libbpf_err_ptr(err); } +COMPAT_VERSION(btf_dump__new_deprecated, btf_dump__new, LIBBPF_0.0.4) +struct btf_dump *btf_dump__new_deprecated(const struct btf *btf, + const struct btf_ext *btf_ext, + const struct btf_dump_opts *opts, + btf_dump_printf_fn_t printf_fn) +{ + if (!printf_fn) + return libbpf_err_ptr(-EINVAL); + return btf_dump__new_v0_6_0(btf, printf_fn, opts ? opts->ctx : NULL, opts); +} + static int btf_dump_resize(struct btf_dump *d) { int err, last_id = btf__type_cnt(d->btf) - 1; @@ -317,6 +330,7 @@ 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; @@ -560,6 +574,7 @@ 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: { @@ -734,6 +749,7 @@ 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: @@ -1154,6 +1170,7 @@ 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: @@ -1322,6 +1339,11 @@ 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; @@ -2194,7 +2216,7 @@ 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) @@ -2299,8 +2321,8 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, if (!opts->indent_str) 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..8ecef1088ba2 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 */ @@ -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, @@ -1040,6 +1067,33 @@ 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/libbpf.c b/tools/lib/bpf/libbpf.c index 7c74342bb668..7f10dd501a52 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -168,39 +168,24 @@ int libbpf_set_strict_mode(enum libbpf_strict_mode mode) 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, @@ -209,19 +194,25 @@ 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 int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_opts *opts, long cookie); typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie); /* stored as sec_def->cookie for all libbpf-supported SEC()s */ @@ -304,7 +295,11 @@ struct bpf_program { struct reloc_desc *reloc_desc; int nr_reloc; - int log_level; + + /* BPF verifier log settings */ + char *log_buf; + size_t log_size; + __u32 log_level; struct { int nr; @@ -400,6 +395,7 @@ struct bpf_map { char *pin_path; bool pinned; bool reused; + bool skipped; __u64 map_extra; }; @@ -546,6 +542,11 @@ struct bpf_object { size_t btf_module_cnt; size_t btf_module_cap; + /* optional log settings passed to BPF_BTF_LOAD and BPF_PROG_LOAD commands */ + char *log_buf; + size_t log_size; + __u32 log_level; + void *priv; bpf_object_clear_priv_t clear_priv; @@ -681,6 +682,9 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, prog->instances.fds = NULL; prog->instances.nr = -1; + /* inherit object's log_level */ + prog->log_level = obj->log_level; + prog->sec_name = strdup(sec_name); if (!prog->sec_name) goto errout; @@ -791,11 +795,36 @@ 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 (access(ubuntu_kver_file, R_OK) == 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; @@ -1161,12 +1190,10 @@ 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; @@ -1318,7 +1345,10 @@ 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; } @@ -2076,6 +2106,7 @@ 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"; default: return "unknown"; } } @@ -2255,6 +2286,9 @@ 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 +2302,8 @@ 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 +2315,30 @@ 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)); @@ -2588,8 +2630,10 @@ 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); - 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; } static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) @@ -2599,6 +2643,7 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) 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); struct btf_type *t; int i, j, vlen; @@ -2657,6 +2702,10 @@ 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); } } } @@ -2752,13 +2801,12 @@ 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; @@ -2972,7 +3020,9 @@ 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 +3241,11 @@ 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; @@ -3271,8 +3321,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } 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 +3357,10 @@ 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 +3391,8 @@ 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); } @@ -3555,7 +3614,7 @@ 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); @@ -4022,7 +4081,7 @@ 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 +4092,9 @@ 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 +4114,23 @@ 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; } @@ -4265,30 +4334,24 @@ int bpf_map__resize(struct bpf_map *map, __u32 max_entries) 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 +4375,19 @@ static int probe_fd(int fd) static int probe_kern_prog_name(void) { - struct bpf_load_program_attr attr; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int ret; + int ret, insn_cnt = ARRAY_SIZE(insns); /* make sure loading with name 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"; - attr.name = "test"; - ret = bpf_load_program_xattr(&attr, NULL, 0); + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "test", "GPL", insns, insn_cnt, NULL); 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 +4395,9 @@ static int probe_kern_global_data(void) BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; - int ret, map; - - 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; + int ret, map, insn_cnt = ARRAY_SIZE(insns); - map = bpf_create_map_xattr(&map_attr); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), 32, 1, NULL); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4361,13 +4408,7 @@ 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 +4509,51 @@ 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, NULL, 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 +4562,22 @@ 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_KPROBE, 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; - - 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; + int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); - map = bpf_create_map_xattr(&map_attr); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), 32, 1, NULL); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4551,13 +4586,7 @@ 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 +4631,14 @@ 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; @@ -4687,14 +4711,20 @@ 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, + }, }; -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. */ @@ -4821,19 +4851,16 @@ 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; + __u32 max_entries; 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; @@ -4847,18 +4874,14 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b return nr_cpus; } pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus); - create_attr.max_entries = nr_cpus; + max_entries = nr_cpus; } else { - create_attr.max_entries = def->max_entries; + 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)) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; @@ -4904,13 +4927,17 @@ 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, 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, + max_entries, &create_attr); } if (map->fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { @@ -4925,7 +4952,9 @@ 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, + max_entries, &create_attr); } err = map->fd < 0 ? -errno : 0; @@ -4940,7 +4969,7 @@ 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 +4981,18 @@ 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 +5005,59 @@ 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 bpf_object__create_maps(struct bpf_object *obj) { @@ -4988,6 +5070,26 @@ 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->skipped = true; + continue; + } + retried = false; retry: if (map->pin_path) { @@ -5024,8 +5126,8 @@ 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; @@ -5097,15 +5199,18 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand, 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(t) != btf_kind(local_t)) continue; targ_name = btf__name_by_offset(targ_btf, t->name_off); @@ -5116,12 +5221,12 @@ 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 +5235,6 @@ 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 +5341,21 @@ 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) @@ -5399,12 +5505,31 @@ static void *u32_as_hash_key(__u32 x) return (void *)(uintptr_t)x; } +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 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) { + 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; @@ -5435,13 +5560,15 @@ static int bpf_core_apply_relo(struct bpf_program *prog, return -EINVAL; if (prog->obj->gen_loader) { - pr_warn("// TODO core_relo: prog %td insn[%d] %s kind %d\n", + const char *spec_str = btf__name_by_offset(local_btf, relo->access_str_off); + + pr_debug("record_relo_core: prog %td insn[%d] %s %s %s final insn_idx %d\n", prog - prog->obj->programs, relo->insn_off / 8, - local_name, relo->kind); - return -ENOTSUP; + btf_kind_str(local_type), local_name, spec_str, insn_idx); + return record_relo_core(prog, relo, insn_idx); } - 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)) { @@ -5457,7 +5584,8 @@ 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_apply_relo_insn(prog_name, insn, insn_idx, relo, + relo_idx, local_btf, cands, specs_scratch); } static int @@ -5587,6 +5715,13 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; insn[0].imm = relo->map_idx; } else { + const struct bpf_map *map = &obj->maps[relo->map_idx]; + + if (map->skipped) { + pr_warn("prog '%s': relo #%d: kernel doesn't support global data\n", + prog->name, i); + return -ENOTSUP; + } insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; insn[0].imm = obj->maps[relo->map_idx].fd; } @@ -5635,6 +5770,9 @@ 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); @@ -5798,6 +5936,8 @@ 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 +5953,9 @@ 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; @@ -6072,6 +6213,35 @@ 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 +6256,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) err); return err; } + if (obj->gen_loader) + bpf_object__sort_relos(obj); } /* Before relocating calls pre-process relocations and mark @@ -6121,6 +6293,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) */ if (prog_is_subprog(obj, prog)) continue; + if (!prog->load) + continue; err = bpf_object__relocate_calls(obj, prog); if (err) { @@ -6134,6 +6308,8 @@ 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->load) + continue; err = bpf_object__relocate_data(obj, prog); if (err) { pr_warn("prog '%s': failed to relocate data references: %d\n", @@ -6156,9 +6332,11 @@ 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 +6363,6 @@ 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 +6384,45 @@ 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 +6453,15 @@ 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 +6494,7 @@ 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; } @@ -6374,16 +6551,16 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac /* 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) + 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_TRACING || prog->type == BPF_PROG_TYPE_LSM || @@ -6402,25 +6579,28 @@ 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 int bpf_object_load_prog_instance(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 +6615,9 @@ 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; @@ -6460,7 +6635,7 @@ 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; @@ -6475,27 +6650,51 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int 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 initiallly 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 +6707,53 @@ 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; 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); + } + if (insns_cnt >= BPF_MAXINSNS) { + pr_warn("prog '%s': program too large (%d insns), at most %d insns\n", + prog->name, insns_cnt, BPF_MAXINSNS); } out: - free(log_buf); + if (own_log_buf) + free(log_buf); return ret; } -static int bpf_program__record_externs(struct bpf_program *prog) +static int bpf_program_record_relos(struct bpf_program *prog) { struct bpf_object *obj = prog->obj; int i; @@ -6584,6 +6775,17 @@ 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; } @@ -6591,11 +6793,12 @@ 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) +static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog, + const char *license, __u32 kern_ver) { int err = 0, fd, i; - if (prog->obj->loaded) { + if (obj->loaded) { pr_warn("prog '%s': can't load after object was loaded\n", prog->name); return libbpf_err(-EINVAL); } @@ -6621,10 +6824,11 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) 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 (obj->gen_loader) + bpf_program_record_relos(prog); + err = bpf_object_load_prog_instance(obj, prog, + prog->insns, prog->insns_cnt, + license, kern_ver, &fd); if (!err) prog->instances.fds[0] = fd; goto out; @@ -6652,8 +6856,9 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) continue; } - err = load_program(prog, result.new_insn_ptr, - result.new_insn_cnt, license, kern_ver, &fd); + err = bpf_object_load_prog_instance(obj, 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); @@ -6670,6 +6875,11 @@ out: return libbpf_err(err); } +int bpf_program__load(struct bpf_program *prog, const char *license, __u32 kern_ver) +{ + return bpf_object_load_prog(prog->obj, prog, license, kern_ver); +} + static int bpf_object__load_progs(struct bpf_object *obj, int log_level) { @@ -6693,7 +6903,7 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) continue; } prog->log_level |= log_level; - err = bpf_program__load(prog, obj->license, obj->kern_version); + err = bpf_object_load_prog(obj, prog, obj->license, obj->kern_version); if (err) return err; } @@ -6744,14 +6954,16 @@ 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 +6986,22 @@ __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) { @@ -6831,7 +7055,7 @@ __bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags) return NULL; pr_debug("loading %s\n", attr->file); - return __bpf_object__open(attr->file, NULL, 0, &opts); + return bpf_object_open(attr->file, NULL, 0, &opts); } struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) @@ -6857,7 +7081,7 @@ 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 * @@ -6867,7 +7091,7 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, 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 libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, opts)); } struct bpf_object * @@ -6884,7 +7108,7 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, if (!obj_buf || obj_buf_sz == 0) return errno = EINVAL, NULL; - 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) @@ -6915,10 +7139,6 @@ 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; } @@ -7241,14 +7461,10 @@ 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 +7474,7 @@ 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 +7483,9 @@ 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 */ @@ -7312,13 +7529,14 @@ out: return libbpf_err(err); } -int bpf_object__load(struct bpf_object *obj) +int bpf_object__load_xattr(struct bpf_object_load_attr *attr) { - struct bpf_object_load_attr attr = { - .obj = obj, - }; + return bpf_object_load(attr->obj, attr->log_level, attr->target_btf_path); +} - return bpf_object__load_xattr(&attr); +int bpf_object__load(struct bpf_object *obj) +{ + return bpf_object_load(obj, 0, NULL); } static int make_parent_dir(const char *path) @@ -7707,6 +7925,9 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) char *pin_path = NULL; char buf[PATH_MAX]; + if (map->skipped) + continue; + if (path) { int len; @@ -7733,7 +7954,7 @@ 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; @@ -7813,7 +8034,7 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) return 0; err_unpin_programs: - while ((prog = bpf_program__prev(prog, obj))) { + while ((prog = bpf_object__prev_program(obj, prog))) { char buf[PATH_MAX]; int len; @@ -8154,9 +8375,11 @@ int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) return 0; } +static int bpf_program_nth_fd(const struct bpf_program *prog, int n); + int bpf_program__fd(const struct bpf_program *prog) { - return bpf_program__nth_fd(prog, 0); + return bpf_program_nth_fd(prog, 0); } size_t bpf_program__size(const struct bpf_program *prog) @@ -8202,7 +8425,10 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, return 0; } -int bpf_program__nth_fd(const struct bpf_program *prog, int n) +__attribute__((alias("bpf_program_nth_fd"))) +int bpf_program__nth_fd(const struct bpf_program *prog, int n); + +static int bpf_program_nth_fd(const struct bpf_program *prog, int n) { int fd; @@ -8281,6 +8507,54 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, prog->expected_attach_type = type; } +__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, \ .prog_type = BPF_PROG_TYPE_##ptype, \ @@ -9028,7 +9302,10 @@ 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; } @@ -9145,21 +9422,12 @@ long libbpf_get_error(const void *ptr) return -errno; } -int bpf_prog_load(const char *file, enum bpf_prog_type type, - struct bpf_object **pobj, int *prog_fd) -{ - struct bpf_prog_load_attr attr; - - memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); - attr.file = file; - attr.prog_type = type; - attr.expected_attach_type = 0; - - return bpf_prog_load_xattr(&attr, pobj, prog_fd); -} - +__attribute__((alias("bpf_prog_load_xattr2"))) int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, - struct bpf_object **pobj, int *prog_fd) + struct bpf_object **pobj, int *prog_fd); + +static int bpf_prog_load_xattr2(const struct bpf_prog_load_attr *attr, + struct bpf_object **pobj, int *prog_fd) { struct bpf_object_open_attr open_attr = {}; struct bpf_program *prog, *first_prog = NULL; @@ -9230,6 +9498,20 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, return 0; } +COMPAT_VERSION(bpf_prog_load_deprecated, bpf_prog_load, LIBBPF_0.0.1) +int bpf_prog_load_deprecated(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd) +{ + struct bpf_prog_load_attr attr; + + memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); + attr.file = file; + attr.prog_type = type; + attr.expected_attach_type = 0; + + return bpf_prog_load_xattr2(&attr, pobj, prog_fd); +} + struct bpf_link { int (*detach)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); @@ -9634,7 +9916,10 @@ static int append_to_file(const char *file, const char *fmt, ...) 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, @@ -9735,7 +10020,7 @@ 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); @@ -10394,10 +10679,10 @@ 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) +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); @@ -10442,6 +10727,12 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, return libbpf_err(ret); } +__attribute__((alias("perf_event_read_simple"))) +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); + struct perf_buffer; struct perf_buffer_params { @@ -10575,11 +10866,18 @@ error: 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, - const struct perf_buffer_opts *opts) +DEFAULT_VERSION(perf_buffer__new_v0_6_0, perf_buffer__new, LIBBPF_0.6.0) +struct perf_buffer *perf_buffer__new_v0_6_0(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) { 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); attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; @@ -10588,29 +10886,62 @@ 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) +COMPAT_VERSION(perf_buffer__new_deprecated, perf_buffer__new, LIBBPF_0.0.4) +struct perf_buffer *perf_buffer__new_deprecated(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts) +{ + return perf_buffer__new_v0_6_0(map_fd, page_cnt, + opts ? opts->sample_cb : NULL, + opts ? opts->lost_cb : NULL, + opts ? opts->ctx : NULL, + NULL); +} + +DEFAULT_VERSION(perf_buffer__new_raw_v0_6_0, perf_buffer__new_raw, LIBBPF_0.6.0) +struct perf_buffer *perf_buffer__new_raw_v0_6_0(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 (page_cnt == 0 || !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)); } +COMPAT_VERSION(perf_buffer__new_raw_deprecated, perf_buffer__new_raw, LIBBPF_0.0.4) +struct perf_buffer *perf_buffer__new_raw_deprecated(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts) +{ + LIBBPF_OPTS(perf_buffer_raw_opts, inner_opts, + .cpu_cnt = opts->cpu_cnt, + .cpus = opts->cpus, + .map_keys = opts->map_keys, + ); + + return perf_buffer__new_raw_v0_6_0(map_fd, page_cnt, opts->attr, + opts->event_cb, opts->ctx, &inner_opts); +} + static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, struct perf_buffer_params *p) { @@ -10810,10 +11141,10 @@ 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; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 9de0f299706b..8b9bc5e90c2b 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, @@ -104,12 +108,73 @@ 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); @@ -149,6 +214,7 @@ struct bpf_object_load_attr { /* Load/unload object into/from kernel */ LIBBPF_API int bpf_object__load(struct bpf_object *obj); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__load() instead") 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); @@ -161,6 +227,7 @@ struct btf; LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__find_program_by_name() instead") LIBBPF_API struct bpf_program * bpf_object__find_program_by_title(const struct bpf_object *obj, const char *title); @@ -262,8 +329,8 @@ 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_DEPRECATED_SINCE(0, 6, "use bpf_object__load() instead") +LIBBPF_API int bpf_program__load(struct bpf_program *prog, const 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, @@ -273,7 +340,31 @@ 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); @@ -344,10 +435,41 @@ struct bpf_uprobe_opts { }; #define bpf_uprobe_opts__last_field retprobe +/** + * @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, @@ -431,7 +553,6 @@ bpf_program__attach_iter(const struct bpf_program *prog, * one instance. In this case bpf_program__fd(prog) is equal to * bpf_program__nth_fd(prog, 0). */ -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. @@ -494,6 +615,18 @@ LIBBPF_API void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type); +LIBBPF_API __u32 bpf_program__flags(const struct bpf_program *prog); +LIBBPF_API int bpf_program__set_flags(struct bpf_program *prog, __u32 flags); + +/* Per-program log level and log buffer getters/setters. + * See bpf_object_open_opts comments regarding log_level and log_buf + * interactions. + */ +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); + LIBBPF_API int bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, const char *attach_func_name); @@ -544,7 +677,8 @@ 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 * +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__find_map_by_name() instead") +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") @@ -611,6 +745,7 @@ 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_DEPRECATED_SINCE(0, 8, "use bpf_map__type() instead") LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); /** @@ -674,10 +809,12 @@ struct bpf_prog_load_attr { int prog_flags; }; +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open() and bpf_object__load() instead") 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); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open() and bpf_object__load() instead") +LIBBPF_API int bpf_prog_load_deprecated(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd); /* XDP related API */ struct xdp_link_info { @@ -775,18 +912,52 @@ 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; + union { + size_t sz; + struct { /* DEPRECATED: will be removed in v1.0 */ + /* 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; + }; + }; }; +#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); +LIBBPF_API struct perf_buffer * +perf_buffer__new_v0_6_0(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); + +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use new variant of perf_buffer__new() instead") +struct perf_buffer *perf_buffer__new_deprecated(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts); + +#define perf_buffer__new(...) ___libbpf_overload(___perf_buffer_new, __VA_ARGS__) +#define ___perf_buffer_new6(map_fd, page_cnt, sample_cb, lost_cb, ctx, opts) \ + perf_buffer__new(map_fd, page_cnt, sample_cb, lost_cb, ctx, opts) +#define ___perf_buffer_new3(map_fd, page_cnt, opts) \ + perf_buffer__new_deprecated(map_fd, page_cnt, opts) + enum bpf_perf_event_ret { LIBBPF_PERF_EVENT_DONE = 0, LIBBPF_PERF_EVENT_ERROR = -1, @@ -800,12 +971,21 @@ 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; + union { + struct { + size_t sz; + long :0; + long :0; + }; + struct { /* DEPRECATED: will be removed in v1.0 */ + /* 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; + }; + }; /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of * max_entries of given PERF_EVENT_ARRAY map) */ @@ -815,11 +995,28 @@ 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 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 struct perf_buffer * +perf_buffer__new_raw_v0_6_0(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 LIBBPF_DEPRECATED_SINCE(0, 7, "use new variant of perf_buffer__new_raw() instead") +struct perf_buffer *perf_buffer__new_raw_deprecated(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts); + +#define perf_buffer__new_raw(...) ___libbpf_overload(___perf_buffer_new_raw, __VA_ARGS__) +#define ___perf_buffer_new_raw6(map_fd, page_cnt, attr, event_cb, ctx, opts) \ + perf_buffer__new_raw(map_fd, page_cnt, attr, event_cb, ctx, opts) +#define ___perf_buffer_new_raw3(map_fd, page_cnt, opts) \ + perf_buffer__new_raw_deprecated(map_fd, page_cnt, opts) + LIBBPF_API void perf_buffer__free(struct perf_buffer *pb); LIBBPF_API int perf_buffer__epoll_fd(const struct perf_buffer *pb); LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms); @@ -831,6 +1028,7 @@ LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_i typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, void *private_data); +LIBBPF_DEPRECATED_SINCE(0, 8, "use perf_buffer__poll() or perf_buffer__consume() instead") 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, @@ -857,13 +1055,57 @@ 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_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_prog_type() instead") +LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex); +LIBBPF_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_map_type() instead") 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_DEPRECATED_SINCE(0, 8, "use libbpf_probe_bpf_helper() instead") +LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, __u32 ifindex); +LIBBPF_DEPRECATED_SINCE(0, 8, "implement your own or use bpftool for feature detection") LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex); +/** + * @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 + * + * 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 + * + * 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 + * + * Make sure the process has required set of CAP_* permissions (or runs as + * root) when performing feature checking. + */ +LIBBPF_API int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, + enum bpf_func_id helper_id, const void *opts); + /* * Get bpf_prog_info in continuous memory * @@ -918,12 +1160,15 @@ struct bpf_prog_info_linear { __u8 data[]; }; +LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper") LIBBPF_API struct bpf_prog_info_linear * bpf_program__get_prog_info_linear(int fd, __u64 arrays); +LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper") LIBBPF_API void bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); +LIBBPF_DEPRECATED_SINCE(0, 6, "use a custom linear prog_info wrapper") LIBBPF_API void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); @@ -965,11 +1210,11 @@ 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; }; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 43580eb47740..529783967793 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -391,14 +391,44 @@ 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_deprecated; + 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__dedup_deprecated; btf__raw_data; btf__type_cnt; + btf_dump__new; + btf_dump__new_deprecated; + libbpf_major_version; + libbpf_minor_version; + libbpf_version_string; + perf_buffer__new; + perf_buffer__new_deprecated; + perf_buffer__new_raw; + perf_buffer__new_raw_deprecated; } LIBBPF_0.5.0; + +LIBBPF_0.7.0 { + global: + bpf_btf_load; + bpf_program__log_buf; + bpf_program__log_level; + bpf_program__set_log_buf; + bpf_program__set_log_level; + libbpf_probe_bpf_helper; + libbpf_probe_bpf_map_type; + libbpf_probe_bpf_prog_type; + libbpf_set_memlock_rlim_max; +}; diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h index aaa1efbf6f51..000e37798ff2 100644 --- a/tools/lib/bpf/libbpf_common.h +++ b/tools/lib/bpf/libbpf_common.h @@ -40,6 +40,23 @@ #else #define __LIBBPF_MARK_DEPRECATED_0_7(X) #endif +#if __LIBBPF_CURRENT_VERSION_GEQ(0, 8) +#define __LIBBPF_MARK_DEPRECATED_0_8(X) X +#else +#define __LIBBPF_MARK_DEPRECATED_0_8(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 * @@ -54,7 +71,7 @@ * 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..1565679eb432 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -73,6 +73,8 @@ 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) @@ -167,10 +169,31 @@ 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 +293,51 @@ 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, + __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, diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index 5ba5c9beccfa..79131f761a27 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -45,7 +45,6 @@ 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 @@ -63,12 +62,24 @@ 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_max() API. + * Note that libbpf_set_memlock_rlim_max() 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, __LIBBPF_STRICT_LAST, }; LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); +#define DECLARE_LIBBPF_OPTS LIBBPF_OPTS #ifdef __cplusplus } /* extern "C" */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 68f2dbf364aa..97b06cede56f 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -48,41 +48,65 @@ static int get_vendor_id(int ifindex) return strtol(buf, NULL, 0); } -static int get_kernel_version(void) +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, + __u32 ifindex) { - 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, + .prog_ifindex = ifindex, + ); + 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: @@ -103,27 +127,42 @@ 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; +} + +int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts) +{ + 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 (opts) + return libbpf_err(-EINVAL); + + ret = probe_prog_load(prog_type, insns, insn_cnt, NULL, 0, 0); + return libbpf_err(ret); } bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex) @@ -133,12 +172,16 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex) BPF_EXIT_INSN() }; + /* prefer libbpf_probe_bpf_prog_type() unless offload is requested */ + if (ifindex == 0) + return libbpf_probe_bpf_prog_type(prog_type, NULL) == 1; + if (ifindex && prog_type == BPF_PROG_TYPE_SCHED_CLS) /* nfp returns -EINVAL on exit(0) with TC offload */ insns[0].imm = 2; errno = 0; - probe_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex); + probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), NULL, 0, ifindex); return errno != EINVAL && errno != EOPNOTSUPP; } @@ -166,7 +209,7 @@ 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 +242,18 @@ 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, __u32 ifindex) { - 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; + + opts.map_ifindex = ifindex; 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 +262,7 @@ 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 +281,25 @@ 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: 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: @@ -266,9 +318,10 @@ 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 || @@ -277,37 +330,102 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) * map-in-map for offload */ if (ifindex) - return false; + goto cleanup; - 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; - } + goto cleanup; + + opts.inner_map_fd = fd_inner; + } - fd = bpf_create_map_xattr(&attr); + 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; +} + +int libbpf_probe_bpf_map_type(enum bpf_map_type map_type, const void *opts) +{ + int ret; + + if (opts) + return libbpf_err(-EINVAL); + + ret = probe_map_create(map_type, 0); + return libbpf_err(ret); +} + +bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) +{ + return probe_map_create(map_type, ifindex) == 1; +} + +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_EMIT_CALL((__u32)helper_id), + BPF_EXIT_INSN(), + }; + const size_t insn_cnt = ARRAY_SIZE(insns); + char buf[4096]; + int ret; + + if (opts) + return libbpf_err(-EINVAL); + + /* 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; + } + + buf[0] = '\0'; + ret = probe_prog_load(prog_type, insns, insn_cnt, buf, sizeof(buf), 0); + 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 */ } bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, @@ -320,8 +438,7 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, char buf[4096] = {}; bool res; - probe_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), - ifindex); + probe_prog_load(prog_type, insns, ARRAY_SIZE(insns), buf, sizeof(buf), ifindex); res = !grep(buf, "invalid func ") && !grep(buf, "unknown func "); if (ifindex) { @@ -353,8 +470,8 @@ bool bpf_probe_large_insn_limit(__u32 ifindex) insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); errno = 0; - probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0, - ifindex); + probe_prog_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0, + ifindex); return errno != E2BIG && errno != EINVAL; } diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index dd56d76f291c..0fefefc3500b 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 0 -#define LIBBPF_MINOR_VERSION 6 +#define LIBBPF_MINOR_VERSION 7 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index f677dccdeae4..9aa016fb55aa 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); } @@ -1999,7 +2000,7 @@ 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 +2033,9 @@ 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 +2654,7 @@ 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 +2691,8 @@ 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/relo_core.c b/tools/lib/bpf/relo_core.c index b5b8956a1be8..910865e29edc 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 +79,25 @@ 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_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 +105,12 @@ 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 +120,10 @@ 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_SIZE: return true; default: return false; @@ -105,8 +133,8 @@ 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; @@ -150,7 +178,7 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) * 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, +static int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, __u32 type_id, const char *spec_str, enum bpf_core_relo_kind relo_kind, @@ -272,8 +300,8 @@ 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, type_id, spec_str, i, id, btf_kind_str(t)); return -EINVAL; } } @@ -346,8 +374,6 @@ 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 +414,7 @@ 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); @@ -571,7 +597,7 @@ 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 +606,11 @@ 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 +618,7 @@ 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 +670,36 @@ 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: + case BPF_CORE_FIELD_SIGNED: /* enums will be assumed unsigned */ *val = btf_is_enum(mt) || (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 +709,14 @@ 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) + __u32 *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 +724,25 @@ 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: *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; } @@ -723,13 +758,13 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, 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); + t = btf_type_by_id(spec->btf, spec->spec[0].type_id); e = btf_enum(t) + spec->spec[0].idx; *val = e->val; break; @@ -805,8 +840,8 @@ 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 +870,8 @@ 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); @@ -1045,7 +1080,7 @@ 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) +static void bpf_core_dump_spec(const char *prog_name, int level, const struct bpf_core_spec *spec) { const struct btf_type *t; const struct btf_enum *e; @@ -1054,7 +1089,7 @@ static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) int i; 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); @@ -1147,9 +1182,12 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, const struct bpf_core_relo *relo, int relo_idx, const struct btf *local_btf, - struct bpf_core_cand_list *cands) + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch) { - struct bpf_core_spec local_spec, cand_spec, targ_spec = {}; + struct bpf_core_spec *local_spec = &specs_scratch[0]; + struct bpf_core_spec *cand_spec = &specs_scratch[1]; + struct bpf_core_spec *targ_spec = &specs_scratch[2]; struct bpf_core_relo_res cand_res, targ_res; const struct btf_type *local_type; const char *local_name; @@ -1158,10 +1196,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, 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; @@ -1170,7 +1205,8 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, 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, local_id, spec_str, + relo->kind, local_spec); if (err) { 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), @@ -1181,15 +1217,17 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, 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); + bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, local_spec); libbpf_print(LIBBPF_DEBUG, "\n"); /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */ - if (relo->kind == BPF_TYPE_ID_LOCAL) { - targ_res.validate = true; + 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; + targ_res.orig_val = local_spec->root_type_id; + targ_res.new_val = local_spec->root_type_id; goto patch_insn; } @@ -1200,40 +1238,39 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, 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); + bpf_core_dump_spec(prog_name, LIBBPF_WARN, cand_spec); libbpf_print(LIBBPF_WARN, ": %d\n", 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); + bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, cand_spec); libbpf_print(LIBBPF_DEBUG, "\n"); 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_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) { /* all candidates should result in the same relocation @@ -1251,7 +1288,7 @@ 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 @@ -1277,7 +1314,7 @@ 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; } diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h index 3b9f8f18346c..17799819ad7c 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; }; @@ -88,11 +17,39 @@ struct bpf_core_cand_list { int len; }; +#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; +}; + int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, int insn_idx, const struct bpf_core_relo *relo, int relo_idx, const struct btf *local_btf, - struct bpf_core_cand_list *cands); + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch); int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id); diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 9cf66702fa8d..0b84d8e6b72a 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -7,6 +7,16 @@ #include <sys/syscall.h> #include <sys/mman.h> +#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. * @@ -65,8 +75,7 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) int map_fd = -1, prog_fd = -1, key = 0, err; union bpf_attr attr; - map_fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, - opts->data_sz, 1, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1, NULL); if (map_fd < 0) { opts->errstr = "failed to create loader map"; err = -errno; diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 81f8fbc85e70..edafe56664f3 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -35,6 +35,11 @@ #include "libbpf_internal.h" #include "xsk.h" +/* entire xsk.h and xsk.c is going away in libbpf 1.0, so ignore all internal + * uses of deprecated APIs + */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + #ifndef SOL_XDP #define SOL_XDP 283 #endif @@ -364,8 +369,6 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, 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[] = { @@ -375,27 +378,15 @@ static enum xsk_prog get_xsk_prog(void) 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; + int prog_fd, map_fd, ret, insn_cnt = ARRAY_SIZE(insns); - map_fd = bpf_create_map_xattr(&map_attr); + map_fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, NULL, sizeof(int), sizeof(int), 1, NULL); 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); + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL); if (prog_fd < 0) { close(map_fd); return detected; @@ -495,10 +486,13 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) }; struct bpf_insn *progs[] = {prog, prog_redirect_flags}; enum xsk_prog option = get_xsk_prog(); + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = log_buf_size, + ); - 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); + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "LGPL-2.1 or BSD-2-Clause", + progs[option], insns_cnt[option], &opts); if (prog_fd < 0) { pr_warn("BPF log buffer:\n%s", log_buf); return prog_fd; @@ -554,8 +548,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) return -errno; ifr.ifr_data = (void *)&channels; - memcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ - 1); - ifr.ifr_name[IFNAMSIZ - 1] = '\0'; + libbpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ); err = ioctl(fd, SIOCETHTOOL, &ifr); if (err && errno != EOPNOTSUPP) { ret = -errno; @@ -590,8 +583,8 @@ static int xsk_create_bpf_maps(struct xsk_socket *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); + fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, "xsks_map", + sizeof(int), sizeof(int), max_queues, NULL); if (fd < 0) return fd; @@ -725,14 +718,12 @@ static int xsk_link_lookup(int ifindex, __u32 *prog_id, int *link_fd) 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; + LIBBPF_OPTS(bpf_link_create_opts, opts, .flags = XDP_FLAGS_SKB_MODE); struct bpf_insn insns[2] = { BPF_MOV64_IMM(BPF_REG_0, XDP_PASS), BPF_EXIT_INSN() }; - int prog_fd, link_fd = -1; + int prog_fd, link_fd = -1, insn_cnt = ARRAY_SIZE(insns); int ifindex_lo = 1; bool ret = false; int err; @@ -744,13 +735,7 @@ static bool xsk_probe_bpf_link(void) 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); + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL); if (prog_fd < 0) return ret; @@ -782,8 +767,7 @@ static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk) } ctx->ifindex = ifindex; - memcpy(ctx->ifname, ifname, IFNAMSIZ -1); - ctx->ifname[IFNAMSIZ - 1] = 0; + libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ); xsk->ctx = ctx; xsk->ctx->has_bpf_link = xsk_probe_bpf_link(); @@ -965,8 +949,7 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk, ctx->refcount = 1; ctx->umem = umem; ctx->queue_id = queue_id; - memcpy(ctx->ifname, ifname, IFNAMSIZ - 1); - ctx->ifname[IFNAMSIZ - 1] = '\0'; + libbpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ); ctx->fill = fill; ctx->comp = comp; diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt index 63ae5e0195ce..32c5051c24eb 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) -- @@ -135,16 +136,16 @@ 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/cpumap.c b/tools/lib/perf/cpumap.c index adaad3dddf6e..ee66760f1e63 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 +304,19 @@ 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(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; } /* @@ -305,7 +330,7 @@ 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; @@ -319,19 +344,19 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, if (!other) return orig; if (orig->nr == other->nr && - !memcmp(orig->map, other->map, orig->nr * sizeof(int))) + !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu))) return orig; 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..9a770bfdc804 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -407,7 +407,7 @@ 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); } @@ -426,7 +426,7 @@ 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 evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx); + struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx); struct perf_evsel *evsel; int revent; @@ -643,14 +643,14 @@ 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 +659,10 @@ 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..7ea86a44eae5 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; @@ -139,21 +144,21 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, perf_evsel__alloc_fd(evsel, cpus->nr, 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); + evsel_fd = FD(evsel, idx, thread); if (evsel_fd == NULL) return -EINVAL; - err = get_group_fd(evsel, cpu, thread, &group_fd); + err = get_group_fd(evsel, idx, thread, &group_fd); if (err < 0) return err; 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; @@ -165,12 +170,12 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, 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 +186,8 @@ 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 +205,29 @@ 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 +237,7 @@ 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 +249,16 @@ 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 +272,14 @@ 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) @@ -303,19 +307,19 @@ int perf_evsel__read_size(struct perf_evsel *evsel) return size; } -int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, +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); 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 (MMAP(evsel, cpu_map_idx, thread) && + !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count)) return 0; if (readn(*fd, count->values, size) <= 0) @@ -326,13 +330,13 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, 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); + int *fd = FD(evsel, cpu_map_idx, thread); if (fd == NULL || *fd < 0) return -1; @@ -346,9 +350,9 @@ 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(struct perf_evsel *evsel) @@ -361,9 +365,9 @@ 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) @@ -431,3 +435,22 @@ 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..581f9ffb4237 100644 --- a/tools/lib/perf/include/internal/cpumap.h +++ b/tools/lib/perf/include/internal/cpumap.h @@ -4,16 +4,30 @@ #include <linux/refcount.h> +/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */ +struct perf_cpu { + int cpu; +}; + +/** + * 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); #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..4cefade540bd 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 @@ -36,7 +37,7 @@ typedef void 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 +128,5 @@ 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..cfc9ebd7968e 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; @@ -27,7 +27,7 @@ struct perf_sample_id { * queue number. */ int idx; - int cpu; + struct perf_cpu cpu; pid_t tid; /* Holds total ID period value for PERF_SAMPLE_READ processing. */ 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..15b8faafd615 100644 --- a/tools/lib/perf/include/perf/cpumap.h +++ b/tools/lib/perf/include/perf/cpumap.h @@ -3,11 +3,10 @@ #define __LIBPERF_CPUMAP_H #include <perf/core.h> +#include <perf/cpumap.h> #include <stdio.h> #include <stdbool.h> -struct perf_cpu_map; - LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void); LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); @@ -16,10 +15,11 @@ 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(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); \ diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h index 60eae25076d3..2a9516b42d15 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; @@ -26,18 +28,20 @@ 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__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/libperf.map b/tools/lib/perf/libperf.map index 71468606e8a7..93696affda2e 100644 --- a/tools/lib/perf/libperf.map +++ b/tools/lib/perf/libperf.map @@ -10,6 +10,7 @@ LIBPERF_0.0.1 { perf_cpu_map__cpu; perf_cpu_map__empty; perf_cpu_map__max; + perf_cpu_map__has; perf_thread_map__new_dummy; perf_thread_map__set_pid; perf_thread_map__comm; @@ -50,6 +51,7 @@ 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..f7ee07cb5818 100644 --- a/tools/lib/perf/mmap.c +++ b/tools/lib/perf/mmap.c @@ -32,7 +32,7 @@ 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; @@ -353,8 +353,6 @@ 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-evlist.c b/tools/lib/perf/tests/test-evlist.c index ce91a582f0e4..b3479dfa9a1c 100644 --- a/tools/lib/perf/tests/test-evlist.c +++ b/tools/lib/perf/tests/test-evlist.c @@ -21,6 +21,9 @@ #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) { @@ -331,7 +334,8 @@ 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 +378,7 @@ 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 +417,159 @@ 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 evsel", 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 = %lu, run = %lu, enable = %lu\n", + i, counts[i].val, counts[i].run, counts[i].ena); + + perf_counts_values__scale(&counts[i], true, &scaled); + if (scaled == 1) { + __T_VERBOSE("\t Scaled count = %lu (%.2lf%%, %lu/%lu)\n", + 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 +581,7 @@ 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/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; } /* |