diff options
Diffstat (limited to 'tools/lib/bpf')
41 files changed, 10893 insertions, 2629 deletions
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 0da84cb9e66d..f02725b123b3 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -5,3 +5,4 @@ TAGS tags cscope.* /bpf_helper_defs.h +fixdep diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 5a3dfb56d78f..c80204bb72a2 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,4 +1,4 @@ -libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ +libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_utils.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ - usdt.o + usdt.o zip.o elf.o features.o btf_iter.o btf_relocate.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index cf7f02c67968..168140f8e646 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -2,7 +2,7 @@ # Most of this file is copied from tools/lib/traceevent/Makefile RM ?= rm -srctree = $(abs_srctree) +srctree := $(realpath $(srctree)) VERSION_SCRIPT := libbpf.map LIBBPF_VERSION := $(shell \ @@ -53,15 +53,9 @@ include $(srctree)/tools/scripts/Makefile.include # copy a bit from Linux kbuild -ifeq ("$(origin V)", "command line") - VERBOSE = $(V) -endif -ifndef VERBOSE - VERBOSE = 0 -endif - INCLUDES = -I$(or $(OUTPUT),.) \ - -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi + -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/arch/$(SRCARCH)/include export prefix libdir src obj @@ -95,12 +89,6 @@ override CFLAGS += $(CLANG_CROSS_FLAGS) # flags specific for shared library SHLIB_FLAGS := -DSHARED -fPIC -ifeq ($(VERBOSE),1) - Q = -else - Q = @ -endif - # Disable command line variables (CFLAGS) override from top # level Makefile (perf), otherwise build Makefile will get # the same command line setup. @@ -108,6 +96,8 @@ MAKEOVERRIDES= all: +OUTPUT ?= ./ +OUTPUT := $(abspath $(OUTPUT))/ export srctree OUTPUT CC LD CFLAGS V include $(srctree)/tools/build/Makefile.include @@ -141,7 +131,10 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force $(BPF_GENERATED) +$(SHARED_OBJDIR) $(STATIC_OBJDIR): + $(Q)mkdir -p $@ + +$(BPF_IN_SHARED): force $(BPF_GENERATED) | $(SHARED_OBJDIR) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -151,9 +144,11 @@ $(BPF_IN_SHARED): force $(BPF_GENERATED) @(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \ (diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true + $(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= OUTPUT=$(SHARED_OBJDIR) $(SHARED_OBJDIR)fixdep $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force $(BPF_GENERATED) +$(BPF_IN_STATIC): force $(BPF_GENERATED) | $(STATIC_OBJDIR) + $(SILENT_MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= OUTPUT=$(STATIC_OBJDIR) $(STATIC_OBJDIR)fixdep $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h @@ -263,7 +258,7 @@ install_pkgconfig: $(PC_FILE) install: install_lib install_pkgconfig install_headers -clean: +clean: fixdep-clean $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED) \ $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ @@ -293,11 +288,11 @@ help: @echo ' HINT: use "V=1" to enable verbose build' @echo ' all - build libraries and pkgconfig' @echo ' clean - remove all generated files' - @echo ' check - check abi and version info' + @echo ' check - check ABI and version info' @echo '' @echo 'libbpf install targets:' @echo ' HINT: use "prefix"(defaults to "/usr/local") or "DESTDIR" (defaults to "/")' - @echo ' to adjust target desitantion, e.g. "make prefix=/usr/local install"' + @echo ' to adjust target destination, e.g. "make prefix=/usr/local install"' @echo ' install - build and install all headers, libraries and pkgconfig' @echo ' install_headers - install only headers to include/bpf' @echo '' diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9aff98f42a3d..b66f5fbfbbb2 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -103,9 +103,9 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts) * [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/ * [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper") */ -int probe_memcg_account(void) +int probe_memcg_account(int token_fd) { - const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd); + const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd); struct bpf_insn insns[] = { BPF_EMIT_CALL(BPF_FUNC_ktime_get_coarse_ns), BPF_EXIT_INSN(), @@ -120,6 +120,9 @@ int probe_memcg_account(void) attr.insns = ptr_to_u64(insns); attr.insn_cnt = insn_cnt; attr.license = ptr_to_u64("GPL"); + attr.prog_token_fd = token_fd; + if (token_fd) + attr.prog_flags |= BPF_F_TOKEN_FD; prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz); if (prog_fd >= 0) { @@ -146,12 +149,12 @@ int bump_rlimit_memlock(void) struct rlimit rlim; /* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */ - if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT)) + if (memlock_bumped || feat_supported(NULL, FEAT_MEMCG_ACCOUNT)) return 0; memlock_bumped = true; - /* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */ + /* zero memlock_rlim disables auto-bumping RLIMIT_MEMLOCK */ if (memlock_rlim == 0) return 0; @@ -169,7 +172,7 @@ int bpf_map_create(enum bpf_map_type map_type, __u32 max_entries, const struct bpf_map_create_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + const size_t attr_sz = offsetofend(union bpf_attr, excl_prog_hash_size); union bpf_attr attr; int fd; @@ -181,7 +184,7 @@ int bpf_map_create(enum bpf_map_type map_type, return libbpf_err(-EINVAL); attr.map_type = map_type; - if (map_name && kernel_supports(NULL, FEAT_PROG_NAME)) + if (map_name && feat_supported(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.key_size = key_size; attr.value_size = value_size; @@ -191,6 +194,7 @@ int bpf_map_create(enum bpf_map_type map_type, 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.value_type_btf_obj_fd = OPTS_GET(opts, value_type_btf_obj_fd, 0); attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0); attr.map_flags = OPTS_GET(opts, map_flags, 0); @@ -198,6 +202,10 @@ int bpf_map_create(enum bpf_map_type map_type, attr.numa_node = OPTS_GET(opts, numa_node, 0); attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); + attr.map_token_fd = OPTS_GET(opts, token_fd, 0); + attr.excl_prog_hash = ptr_to_u64(OPTS_GET(opts, excl_prog_hash, NULL)); + attr.excl_prog_hash_size = OPTS_GET(opts, excl_prog_hash_size, 0); + fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } @@ -230,9 +238,9 @@ alloc_zero_tailing_info(const void *orecord, __u32 cnt, 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) + struct bpf_prog_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, fd_array); + const size_t attr_sz = offsetofend(union bpf_attr, keyring_id); void *finfo = NULL, *linfo = NULL; const char *func_info, *line_info; __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; @@ -261,8 +269,9 @@ int bpf_prog_load(enum bpf_prog_type prog_type, 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.prog_token_fd = OPTS_GET(opts, token_fd, 0); - if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME)) + if (prog_name && feat_supported(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); attr.license = ptr_to_u64(license); @@ -290,10 +299,6 @@ int bpf_prog_load(enum bpf_prog_type prog_type, 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); func_info_rec_size = OPTS_GET(opts, func_info_rec_size, 0); func_info = OPTS_GET(opts, func_info, NULL); @@ -308,6 +313,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.line_info_cnt = OPTS_GET(opts, line_info_cnt, 0); attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL)); + attr.fd_array_cnt = OPTS_GET(opts, fd_array_cnt, 0); if (log_level) { attr.log_buf = ptr_to_u64(log_buf); @@ -316,6 +322,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, } fd = sys_bpf_prog_load(&attr, attr_sz, attempts); + OPTS_SET(opts, log_true_size, attr.log_true_size); if (fd >= 0) return fd; @@ -356,6 +363,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, } fd = sys_bpf_prog_load(&attr, attr_sz, attempts); + OPTS_SET(opts, log_true_size, attr.log_true_size); if (fd >= 0) goto done; } @@ -370,6 +378,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.log_level = 1; fd = sys_bpf_prog_load(&attr, attr_sz, attempts); + OPTS_SET(opts, log_true_size, attr.log_true_size); } done: /* free() doesn't affect errno, so we don't need to restore it */ @@ -573,20 +582,30 @@ int bpf_map_update_batch(int fd, const void *keys, const void *values, __u32 *co (void *)keys, (void *)values, count, opts); } -int bpf_obj_pin(int fd, const char *pathname) +int bpf_obj_pin_opts(int fd, const char *pathname, const struct bpf_obj_pin_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, file_flags); + const size_t attr_sz = offsetofend(union bpf_attr, path_fd); union bpf_attr attr; int ret; + if (!OPTS_VALID(opts, bpf_obj_pin_opts)) + return libbpf_err(-EINVAL); + memset(&attr, 0, attr_sz); + attr.path_fd = OPTS_GET(opts, path_fd, 0); attr.pathname = ptr_to_u64((void *)pathname); + attr.file_flags = OPTS_GET(opts, file_flags, 0); attr.bpf_fd = fd; ret = sys_bpf(BPF_OBJ_PIN, &attr, attr_sz); return libbpf_err_errno(ret); } +int bpf_obj_pin(int fd, const char *pathname) +{ + return bpf_obj_pin_opts(fd, pathname, NULL); +} + int bpf_obj_get(const char *pathname) { return bpf_obj_get_opts(pathname, NULL); @@ -594,7 +613,7 @@ int bpf_obj_get(const char *pathname) int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, file_flags); + const size_t attr_sz = offsetofend(union bpf_attr, path_fd); union bpf_attr attr; int fd; @@ -602,6 +621,7 @@ int bpf_obj_get_opts(const char *pathname, const struct bpf_obj_get_opts *opts) return libbpf_err(-EINVAL); memset(&attr, 0, attr_sz); + attr.path_fd = OPTS_GET(opts, path_fd, 0); attr.pathname = ptr_to_u64((void *)pathname); attr.file_flags = OPTS_GET(opts, file_flags, 0); @@ -619,55 +639,89 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts); } -int bpf_prog_attach_opts(int prog_fd, int target_fd, - enum bpf_attach_type type, - const struct bpf_prog_attach_opts *opts) +int bpf_prog_attach_opts(int prog_fd, int target, enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); + const size_t attr_sz = offsetofend(union bpf_attr, expected_revision); + __u32 relative_id, flags; + int ret, relative_fd; union bpf_attr attr; - int ret; if (!OPTS_VALID(opts, bpf_prog_attach_opts)) return libbpf_err(-EINVAL); + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + flags = OPTS_GET(opts, flags, 0); + + /* validate we don't have unexpected combinations of non-zero fields */ + if (relative_fd && relative_id) + return libbpf_err(-EINVAL); + memset(&attr, 0, attr_sz); - attr.target_fd = target_fd; - attr.attach_bpf_fd = prog_fd; - attr.attach_type = type; - attr.attach_flags = OPTS_GET(opts, flags, 0); - attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0); + attr.target_fd = target; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + attr.replace_bpf_fd = OPTS_GET(opts, replace_fd, 0); + attr.expected_revision = OPTS_GET(opts, expected_revision, 0); + + if (relative_id) { + attr.attach_flags = flags | BPF_F_ID; + attr.relative_id = relative_id; + } else { + attr.attach_flags = flags; + attr.relative_fd = relative_fd; + } ret = sys_bpf(BPF_PROG_ATTACH, &attr, attr_sz); return libbpf_err_errno(ret); } -int bpf_prog_detach(int target_fd, enum bpf_attach_type type) +int bpf_prog_detach_opts(int prog_fd, int target, enum bpf_attach_type type, + const struct bpf_prog_detach_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); + const size_t attr_sz = offsetofend(union bpf_attr, expected_revision); + __u32 relative_id, flags; + int ret, relative_fd; union bpf_attr attr; - int ret; + + if (!OPTS_VALID(opts, bpf_prog_detach_opts)) + return libbpf_err(-EINVAL); + + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + flags = OPTS_GET(opts, flags, 0); + + /* validate we don't have unexpected combinations of non-zero fields */ + if (relative_fd && relative_id) + return libbpf_err(-EINVAL); memset(&attr, 0, attr_sz); - attr.target_fd = target_fd; - attr.attach_type = type; + attr.target_fd = target; + attr.attach_bpf_fd = prog_fd; + attr.attach_type = type; + attr.expected_revision = OPTS_GET(opts, expected_revision, 0); + + if (relative_id) { + attr.attach_flags = flags | BPF_F_ID; + attr.relative_id = relative_id; + } else { + attr.attach_flags = flags; + attr.relative_fd = relative_fd; + } ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz); return libbpf_err_errno(ret); } -int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) +int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { - const size_t attr_sz = offsetofend(union bpf_attr, replace_bpf_fd); - union bpf_attr attr; - int ret; - - memset(&attr, 0, attr_sz); - attr.target_fd = target_fd; - attr.attach_bpf_fd = prog_fd; - attr.attach_type = type; + return bpf_prog_detach_opts(0, target_fd, type, NULL); +} - ret = sys_bpf(BPF_PROG_DETACH, &attr, attr_sz); - return libbpf_err_errno(ret); +int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) +{ + return bpf_prog_detach_opts(prog_fd, target_fd, type, NULL); } int bpf_link_create(int prog_fd, int target_fd, @@ -675,9 +729,9 @@ int bpf_link_create(int prog_fd, int target_fd, const struct bpf_link_create_opts *opts) { const size_t attr_sz = offsetofend(union bpf_attr, link_create); - __u32 target_btf_id, iter_info_len; + __u32 target_btf_id, iter_info_len, relative_id; + int fd, err, relative_fd; union bpf_attr attr; - int fd, err; if (!OPTS_VALID(opts, bpf_link_create_opts)) return libbpf_err(-EINVAL); @@ -715,6 +769,7 @@ int bpf_link_create(int prog_fd, int target_fd, return libbpf_err(-EINVAL); break; case BPF_TRACE_KPROBE_MULTI: + case BPF_TRACE_KPROBE_SESSION: attr.link_create.kprobe_multi.flags = OPTS_GET(opts, kprobe_multi.flags, 0); attr.link_create.kprobe_multi.cnt = OPTS_GET(opts, kprobe_multi.cnt, 0); attr.link_create.kprobe_multi.syms = ptr_to_u64(OPTS_GET(opts, kprobe_multi.syms, 0)); @@ -723,6 +778,19 @@ int bpf_link_create(int prog_fd, int target_fd, if (!OPTS_ZEROED(opts, kprobe_multi)) return libbpf_err(-EINVAL); break; + case BPF_TRACE_UPROBE_MULTI: + case BPF_TRACE_UPROBE_SESSION: + attr.link_create.uprobe_multi.flags = OPTS_GET(opts, uprobe_multi.flags, 0); + attr.link_create.uprobe_multi.cnt = OPTS_GET(opts, uprobe_multi.cnt, 0); + attr.link_create.uprobe_multi.path = ptr_to_u64(OPTS_GET(opts, uprobe_multi.path, 0)); + attr.link_create.uprobe_multi.offsets = ptr_to_u64(OPTS_GET(opts, uprobe_multi.offsets, 0)); + attr.link_create.uprobe_multi.ref_ctr_offsets = ptr_to_u64(OPTS_GET(opts, uprobe_multi.ref_ctr_offsets, 0)); + attr.link_create.uprobe_multi.cookies = ptr_to_u64(OPTS_GET(opts, uprobe_multi.cookies, 0)); + attr.link_create.uprobe_multi.pid = OPTS_GET(opts, uprobe_multi.pid, 0); + if (!OPTS_ZEROED(opts, uprobe_multi)) + return libbpf_err(-EINVAL); + break; + case BPF_TRACE_RAW_TP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_MODIFY_RETURN: @@ -731,6 +799,90 @@ int bpf_link_create(int prog_fd, int target_fd, if (!OPTS_ZEROED(opts, tracing)) return libbpf_err(-EINVAL); break; + case BPF_NETFILTER: + attr.link_create.netfilter.pf = OPTS_GET(opts, netfilter.pf, 0); + attr.link_create.netfilter.hooknum = OPTS_GET(opts, netfilter.hooknum, 0); + attr.link_create.netfilter.priority = OPTS_GET(opts, netfilter.priority, 0); + attr.link_create.netfilter.flags = OPTS_GET(opts, netfilter.flags, 0); + if (!OPTS_ZEROED(opts, netfilter)) + return libbpf_err(-EINVAL); + break; + case BPF_TCX_INGRESS: + case BPF_TCX_EGRESS: + relative_fd = OPTS_GET(opts, tcx.relative_fd, 0); + relative_id = OPTS_GET(opts, tcx.relative_id, 0); + if (relative_fd && relative_id) + return libbpf_err(-EINVAL); + if (relative_id) { + attr.link_create.tcx.relative_id = relative_id; + attr.link_create.flags |= BPF_F_ID; + } else { + attr.link_create.tcx.relative_fd = relative_fd; + } + attr.link_create.tcx.expected_revision = OPTS_GET(opts, tcx.expected_revision, 0); + if (!OPTS_ZEROED(opts, tcx)) + return libbpf_err(-EINVAL); + break; + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: + relative_fd = OPTS_GET(opts, netkit.relative_fd, 0); + relative_id = OPTS_GET(opts, netkit.relative_id, 0); + if (relative_fd && relative_id) + return libbpf_err(-EINVAL); + if (relative_id) { + attr.link_create.netkit.relative_id = relative_id; + attr.link_create.flags |= BPF_F_ID; + } else { + attr.link_create.netkit.relative_fd = relative_fd; + } + attr.link_create.netkit.expected_revision = OPTS_GET(opts, netkit.expected_revision, 0); + if (!OPTS_ZEROED(opts, netkit)) + return libbpf_err(-EINVAL); + break; + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_INET_SOCK_RELEASE: + case BPF_CGROUP_INET4_BIND: + case BPF_CGROUP_INET6_BIND: + case BPF_CGROUP_INET4_POST_BIND: + case BPF_CGROUP_INET6_POST_BIND: + case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: + case BPF_CGROUP_UDP4_RECVMSG: + case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: + case BPF_CGROUP_SOCK_OPS: + case BPF_CGROUP_DEVICE: + case BPF_CGROUP_SYSCTL: + case BPF_CGROUP_GETSOCKOPT: + case BPF_CGROUP_SETSOCKOPT: + case BPF_LSM_CGROUP: + relative_fd = OPTS_GET(opts, cgroup.relative_fd, 0); + relative_id = OPTS_GET(opts, cgroup.relative_id, 0); + if (relative_fd && relative_id) + return libbpf_err(-EINVAL); + if (relative_id) { + attr.link_create.cgroup.relative_id = relative_id; + attr.link_create.flags |= BPF_F_ID; + } else { + attr.link_create.cgroup.relative_fd = relative_fd; + } + attr.link_create.cgroup.expected_revision = + OPTS_GET(opts, cgroup.expected_revision, 0); + if (!OPTS_ZEROED(opts, cgroup)) + return libbpf_err(-EINVAL); + break; default: if (!OPTS_ZEROED(opts, flags)) return libbpf_err(-EINVAL); @@ -794,11 +946,17 @@ int bpf_link_update(int link_fd, int new_prog_fd, if (!OPTS_VALID(opts, bpf_link_update_opts)) return libbpf_err(-EINVAL); + if (OPTS_GET(opts, old_prog_fd, 0) && OPTS_GET(opts, old_map_fd, 0)) + return libbpf_err(-EINVAL); + memset(&attr, 0, attr_sz); attr.link_update.link_fd = link_fd; attr.link_update.new_prog_fd = new_prog_fd; attr.link_update.flags = OPTS_GET(opts, flags, 0); - attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + if (OPTS_GET(opts, old_prog_fd, 0)) + attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + else if (OPTS_GET(opts, old_map_fd, 0)) + attr.link_update.old_map_fd = OPTS_GET(opts, old_map_fd, 0); ret = sys_bpf(BPF_LINK_UPDATE, &attr, attr_sz); return libbpf_err_errno(ret); @@ -817,8 +975,7 @@ int bpf_iter_create(int link_fd) return libbpf_err_errno(fd); } -int bpf_prog_query_opts(int target_fd, - enum bpf_attach_type type, +int bpf_prog_query_opts(int target, enum bpf_attach_type type, struct bpf_prog_query_opts *opts) { const size_t attr_sz = offsetofend(union bpf_attr, query); @@ -829,18 +986,20 @@ int bpf_prog_query_opts(int target_fd, return libbpf_err(-EINVAL); memset(&attr, 0, attr_sz); - - attr.query.target_fd = target_fd; - attr.query.attach_type = type; - attr.query.query_flags = OPTS_GET(opts, query_flags, 0); - attr.query.prog_cnt = OPTS_GET(opts, prog_cnt, 0); - attr.query.prog_ids = ptr_to_u64(OPTS_GET(opts, prog_ids, NULL)); - attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL)); + attr.query.target_fd = target; + attr.query.attach_type = type; + attr.query.query_flags = OPTS_GET(opts, query_flags, 0); + attr.query.count = OPTS_GET(opts, count, 0); + attr.query.prog_ids = ptr_to_u64(OPTS_GET(opts, prog_ids, NULL)); + attr.query.link_ids = ptr_to_u64(OPTS_GET(opts, link_ids, NULL)); + attr.query.prog_attach_flags = ptr_to_u64(OPTS_GET(opts, prog_attach_flags, NULL)); + attr.query.link_attach_flags = ptr_to_u64(OPTS_GET(opts, link_attach_flags, NULL)); ret = sys_bpf(BPF_PROG_QUERY, &attr, attr_sz); OPTS_SET(opts, attach_flags, attr.query.attach_flags); - OPTS_SET(opts, prog_cnt, attr.query.prog_cnt); + OPTS_SET(opts, revision, attr.query.revision); + OPTS_SET(opts, count, attr.query.count); return libbpf_err_errno(ret); } @@ -984,7 +1143,7 @@ int bpf_map_get_fd_by_id(__u32 id) int bpf_btf_get_fd_by_id_opts(__u32 id, const struct bpf_get_fd_by_id_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, open_flags); + const size_t attr_sz = offsetofend(union bpf_attr, fd_by_id_token_fd); union bpf_attr attr; int fd; @@ -994,6 +1153,7 @@ int bpf_btf_get_fd_by_id_opts(__u32 id, memset(&attr, 0, attr_sz); attr.btf_id = id; attr.open_flags = OPTS_GET(opts, open_flags, 0); + attr.fd_by_id_token_fd = OPTS_GET(opts, token_fd, 0); fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, attr_sz); return libbpf_err_errno(fd); @@ -1044,23 +1204,54 @@ int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len) return libbpf_err_errno(err); } -int bpf_raw_tracepoint_open(const char *name, int prog_fd) +int bpf_prog_get_info_by_fd(int prog_fd, struct bpf_prog_info *info, __u32 *info_len) +{ + return bpf_obj_get_info_by_fd(prog_fd, info, info_len); +} + +int bpf_map_get_info_by_fd(int map_fd, struct bpf_map_info *info, __u32 *info_len) +{ + return bpf_obj_get_info_by_fd(map_fd, info, info_len); +} + +int bpf_btf_get_info_by_fd(int btf_fd, struct bpf_btf_info *info, __u32 *info_len) +{ + return bpf_obj_get_info_by_fd(btf_fd, info, info_len); +} + +int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info_len) +{ + return bpf_obj_get_info_by_fd(link_fd, info, info_len); +} + +int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts) { const size_t attr_sz = offsetofend(union bpf_attr, raw_tracepoint); union bpf_attr attr; int fd; + if (!OPTS_VALID(opts, bpf_raw_tp_opts)) + return libbpf_err(-EINVAL); + memset(&attr, 0, attr_sz); - attr.raw_tracepoint.name = ptr_to_u64(name); attr.raw_tracepoint.prog_fd = prog_fd; + attr.raw_tracepoint.name = ptr_to_u64(OPTS_GET(opts, tp_name, NULL)); + attr.raw_tracepoint.cookie = OPTS_GET(opts, cookie, 0); fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, attr_sz); return libbpf_err_errno(fd); } -int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_load_opts *opts) +int bpf_raw_tracepoint_open(const char *name, int prog_fd) { - const size_t attr_sz = offsetofend(union bpf_attr, btf_log_level); + LIBBPF_OPTS(bpf_raw_tp_opts, opts, .tp_name = name); + + return bpf_raw_tracepoint_open_opts(prog_fd, &opts); +} + +int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd); union bpf_attr attr; char *log_buf; size_t log_size; @@ -1085,6 +1276,10 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_loa attr.btf = ptr_to_u64(btf_data); attr.btf_size = btf_size; + + attr.btf_flags = OPTS_GET(opts, btf_flags, 0); + attr.btf_token_fd = OPTS_GET(opts, token_fd, 0); + /* 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 @@ -1103,6 +1298,8 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_loa attr.btf_log_level = 1; fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz); } + + OPTS_SET(opts, log_true_size, attr.btf_log_true_size); return libbpf_err_errno(fd); } @@ -1163,3 +1360,40 @@ int bpf_prog_bind_map(int prog_fd, int map_fd, ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz); return libbpf_err_errno(ret); } + +int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, token_create); + union bpf_attr attr; + int fd; + + if (!OPTS_VALID(opts, bpf_token_create_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.token_create.bpffs_fd = bpffs_fd; + attr.token_create.flags = OPTS_GET(opts, flags, 0); + + fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz); + return libbpf_err_errno(fd); +} + +int bpf_prog_stream_read(int prog_fd, __u32 stream_id, void *buf, __u32 buf_len, + struct bpf_prog_stream_read_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, prog_stream_read); + union bpf_attr attr; + int err; + + if (!OPTS_VALID(opts, bpf_prog_stream_read_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.prog_stream_read.stream_buf = ptr_to_u64(buf); + attr.prog_stream_read.stream_buf_len = buf_len; + attr.prog_stream_read.stream_id = stream_id; + attr.prog_stream_read.prog_fd = prog_fd; + + err = sys_bpf(BPF_PROG_STREAM_READ_BY_FD, &attr, attr_sz); + return libbpf_err_errno(err); +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 7468978d3c27..e983a3e40d61 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ /* - * common eBPF ELF operations. + * Common BPF ELF operations. * * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> @@ -35,7 +35,7 @@ extern "C" { #endif -int libbpf_set_memlock_rlim(size_t memlock_bytes); +LIBBPF_API 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 */ @@ -51,8 +51,15 @@ struct bpf_map_create_opts { __u32 numa_node; __u32 map_ifindex; + __s32 value_type_btf_obj_fd; + + __u32 token_fd; + + const void *excl_prog_hash; + __u32 excl_prog_hash_size; + size_t :0; }; -#define bpf_map_create_opts__last_field map_ifindex +#define bpf_map_create_opts__last_field excl_prog_hash_size LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, const char *map_name, @@ -96,13 +103,24 @@ struct bpf_prog_load_opts { __u32 log_level; __u32 log_size; char *log_buf; + /* output: actual total log contents size (including terminating zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + * If kernel doesn't support this feature, log_size is left unchanged. + */ + __u32 log_true_size; + __u32 token_fd; + + /* if set, provides the length of fd_array */ + __u32 fd_array_cnt; + size_t :0; }; -#define bpf_prog_load_opts__last_field log_buf +#define bpf_prog_load_opts__last_field fd_array_cnt LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name, const char *license, const struct bpf_insn *insns, size_t insn_cnt, - const struct bpf_prog_load_opts *opts); + struct bpf_prog_load_opts *opts); /* Flags to direct loading requirements */ #define MAPS_RELAX_COMPAT 0x01 @@ -117,11 +135,21 @@ struct bpf_btf_load_opts { char *log_buf; __u32 log_level; __u32 log_size; + /* output: actual total log contents size (including terminating zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + * If kernel doesn't support this feature, log_size is left unchanged. + */ + __u32 log_true_size; + + __u32 btf_flags; + __u32 token_fd; + size_t :0; }; -#define bpf_btf_load_opts__last_field log_size +#define bpf_btf_load_opts__last_field token_fd LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, - const struct bpf_btf_load_opts *opts); + struct bpf_btf_load_opts *opts); LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); @@ -168,10 +196,14 @@ LIBBPF_API int bpf_map_delete_batch(int fd, const void *keys, /** * @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 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. Both *in_batch* and *out_batch* must point to memory large enough to + * hold a single key, except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH, + * LRU_HASH, LRU_PERCPU_HASH}**, for which the memory size must be at + * least 4 bytes wide regardless of key size. * * 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* @@ -204,7 +236,10 @@ LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, * * @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* + * get address of the first element in *out_batch*. If not NULL, must be large + * enough to hold a key. For **BPF_MAP_TYPE_{HASH, PERCPU_HASH, LRU_HASH, + * LRU_PERCPU_HASH}**, the memory size must be at least 4 bytes wide regardless + * of key size. * @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 @@ -270,36 +305,96 @@ LIBBPF_API int bpf_map_update_batch(int fd, const void *keys, const void *values __u32 *count, const struct bpf_map_batch_opts *opts); -struct bpf_obj_get_opts { +struct bpf_obj_pin_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 file_flags; + int path_fd; size_t :0; }; -#define bpf_obj_get_opts__last_field file_flags +#define bpf_obj_pin_opts__last_field path_fd LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); -LIBBPF_API int bpf_obj_get(const char *pathname); -LIBBPF_API int bpf_obj_get_opts(const char *pathname, - const struct bpf_obj_get_opts *opts); +LIBBPF_API int bpf_obj_pin_opts(int fd, const char *pathname, + const struct bpf_obj_pin_opts *opts); -struct bpf_prog_attach_opts { +struct bpf_obj_get_opts { size_t sz; /* size of this struct for forward/backward compatibility */ - unsigned int flags; - int replace_prog_fd; + + __u32 file_flags; + int path_fd; + + size_t :0; }; -#define bpf_prog_attach_opts__last_field replace_prog_fd +#define bpf_obj_get_opts__last_field path_fd + +LIBBPF_API int bpf_obj_get(const char *pathname); +LIBBPF_API int bpf_obj_get_opts(const char *pathname, + const struct bpf_obj_get_opts *opts); LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); -LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd, - enum bpf_attach_type type, - const struct bpf_prog_attach_opts *opts); LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); +struct bpf_prog_attach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; + union { + int replace_prog_fd; + int replace_fd; + }; + int relative_fd; + __u32 relative_id; + __u64 expected_revision; + size_t :0; +}; +#define bpf_prog_attach_opts__last_field expected_revision + +struct bpf_prog_detach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; + int relative_fd; + __u32 relative_id; + __u64 expected_revision; + size_t :0; +}; +#define bpf_prog_detach_opts__last_field expected_revision + +/** + * @brief **bpf_prog_attach_opts()** attaches the BPF program corresponding to + * *prog_fd* to a *target* which can represent a file descriptor or netdevice + * ifindex. + * + * @param prog_fd BPF program file descriptor + * @param target attach location file descriptor or ifindex + * @param type attach type for the BPF program + * @param opts options for configuring the attachment + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int target, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); + +/** + * @brief **bpf_prog_detach_opts()** detaches the BPF program corresponding to + * *prog_fd* from a *target* which can represent a file descriptor or netdevice + * ifindex. + * + * @param prog_fd BPF program file descriptor + * @param target detach location file descriptor or ifindex + * @param type detach type for the BPF program + * @param opts options for configuring the detachment + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_prog_detach_opts(int prog_fd, int target, + enum bpf_attach_type type, + const struct bpf_prog_detach_opts *opts); + union bpf_iter_link_info; /* defined in up-to-date linux/bpf.h */ struct bpf_link_create_opts { size_t sz; /* size of this struct for forward/backward compatibility */ @@ -319,12 +414,42 @@ struct bpf_link_create_opts { const __u64 *cookies; } kprobe_multi; struct { + __u32 flags; + __u32 cnt; + const char *path; + const unsigned long *offsets; + const unsigned long *ref_ctr_offsets; + const __u64 *cookies; + __u32 pid; + } uprobe_multi; + struct { __u64 cookie; } tracing; + struct { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + } netfilter; + struct { + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + } tcx; + struct { + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + } netkit; + struct { + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + } cgroup; }; size_t :0; }; -#define bpf_link_create_opts__last_field kprobe_multi.cookies +#define bpf_link_create_opts__last_field uprobe_multi.pid LIBBPF_API int bpf_link_create(int prog_fd, int target_fd, enum bpf_attach_type attach_type, @@ -336,8 +461,9 @@ struct bpf_link_update_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 flags; /* extra flags */ __u32 old_prog_fd; /* expected old program FD */ + __u32 old_map_fd; /* expected old map FD */ }; -#define bpf_link_update_opts__last_field old_prog_fd +#define bpf_link_update_opts__last_field old_map_fd LIBBPF_API int bpf_link_update(int link_fd, int new_prog_fd, const struct bpf_link_update_opts *opts); @@ -369,9 +495,10 @@ LIBBPF_API int bpf_link_get_next_id(__u32 start_id, __u32 *next_id); struct bpf_get_fd_by_id_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 open_flags; /* permissions requested for the operation on fd */ + __u32 token_fd; size_t :0; }; -#define bpf_get_fd_by_id_opts__last_field open_flags +#define bpf_get_fd_by_id_opts__last_field token_fd LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id); LIBBPF_API int bpf_prog_get_fd_by_id_opts(__u32 id, @@ -387,23 +514,130 @@ LIBBPF_API int bpf_link_get_fd_by_id_opts(__u32 id, const struct bpf_get_fd_by_id_opts *opts); LIBBPF_API int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len); +/** + * @brief **bpf_prog_get_info_by_fd()** obtains information about the BPF + * program corresponding to *prog_fd*. + * + * Populates up to *info_len* bytes of *info* and updates *info_len* with the + * actual number of bytes written to *info*. Note that *info* should be + * zero-initialized or initialized as expected by the requested *info* + * type. Failing to (zero-)initialize *info* under certain circumstances can + * result in this helper returning an error. + * + * @param prog_fd BPF program file descriptor + * @param info pointer to **struct bpf_prog_info** that will be populated with + * BPF program information + * @param info_len pointer to the size of *info*; on success updated with the + * number of bytes written to *info* + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_prog_get_info_by_fd(int prog_fd, struct bpf_prog_info *info, __u32 *info_len); + +/** + * @brief **bpf_map_get_info_by_fd()** obtains information about the BPF + * map corresponding to *map_fd*. + * + * Populates up to *info_len* bytes of *info* and updates *info_len* with the + * actual number of bytes written to *info*. Note that *info* should be + * zero-initialized or initialized as expected by the requested *info* + * type. Failing to (zero-)initialize *info* under certain circumstances can + * result in this helper returning an error. + * + * @param map_fd BPF map file descriptor + * @param info pointer to **struct bpf_map_info** that will be populated with + * BPF map information + * @param info_len pointer to the size of *info*; on success updated with the + * number of bytes written to *info* + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_map_get_info_by_fd(int map_fd, struct bpf_map_info *info, __u32 *info_len); + +/** + * @brief **bpf_btf_get_info_by_fd()** obtains information about the + * BTF object corresponding to *btf_fd*. + * + * Populates up to *info_len* bytes of *info* and updates *info_len* with the + * actual number of bytes written to *info*. Note that *info* should be + * zero-initialized or initialized as expected by the requested *info* + * type. Failing to (zero-)initialize *info* under certain circumstances can + * result in this helper returning an error. + * + * @param btf_fd BTF object file descriptor + * @param info pointer to **struct bpf_btf_info** that will be populated with + * BTF object information + * @param info_len pointer to the size of *info*; on success updated with the + * number of bytes written to *info* + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_btf_get_info_by_fd(int btf_fd, struct bpf_btf_info *info, __u32 *info_len); + +/** + * @brief **bpf_btf_get_info_by_fd()** obtains information about the BPF + * link corresponding to *link_fd*. + * + * Populates up to *info_len* bytes of *info* and updates *info_len* with the + * actual number of bytes written to *info*. Note that *info* should be + * zero-initialized or initialized as expected by the requested *info* + * type. Failing to (zero-)initialize *info* under certain circumstances can + * result in this helper returning an error. + * + * @param link_fd BPF link file descriptor + * @param info pointer to **struct bpf_link_info** that will be populated with + * BPF link information + * @param info_len pointer to the size of *info*; on success updated with the + * number of bytes written to *info* + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_link_get_info_by_fd(int link_fd, struct bpf_link_info *info, __u32 *info_len); + struct bpf_prog_query_opts { size_t sz; /* size of this struct for forward/backward compatibility */ __u32 query_flags; __u32 attach_flags; /* output argument */ __u32 *prog_ids; - __u32 prog_cnt; /* input+output argument */ + union { + /* input+output argument */ + __u32 prog_cnt; + __u32 count; + }; __u32 *prog_attach_flags; + __u32 *link_ids; + __u32 *link_attach_flags; + __u64 revision; + size_t :0; }; -#define bpf_prog_query_opts__last_field prog_attach_flags +#define bpf_prog_query_opts__last_field revision -LIBBPF_API int bpf_prog_query_opts(int target_fd, - enum bpf_attach_type type, +/** + * @brief **bpf_prog_query_opts()** queries the BPF programs and BPF links + * which are attached to *target* which can represent a file descriptor or + * netdevice ifindex. + * + * @param target query location file descriptor or ifindex + * @param type attach type for the BPF program + * @param opts options for configuring the query + * @return 0, on success; negative error code, otherwise (errno is also set to + * the error code) + */ +LIBBPF_API int bpf_prog_query_opts(int target, enum bpf_attach_type type, struct bpf_prog_query_opts *opts); LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); +struct bpf_raw_tp_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + const char *tp_name; + __u64 cookie; + size_t :0; +}; +#define bpf_raw_tp_opts__last_field cookie + +LIBBPF_API int bpf_raw_tracepoint_open_opts(int prog_fd, struct bpf_raw_tp_opts *opts); LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd); LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, @@ -454,6 +688,51 @@ struct bpf_test_run_opts { LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts); +struct bpf_token_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; + size_t :0; +}; +#define bpf_token_create_opts__last_field flags + +/** + * @brief **bpf_token_create()** creates a new instance of BPF token derived + * from specified BPF FS mount point. + * + * BPF token created with this API can be passed to bpf() syscall for + * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc. + * + * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token + * instance. + * @param opts optional BPF token creation options, can be NULL + * + * @return BPF token FD > 0, on success; negative error code, otherwise (errno + * is also set to the error code) + */ +LIBBPF_API int bpf_token_create(int bpffs_fd, + struct bpf_token_create_opts *opts); + +struct bpf_prog_stream_read_opts { + size_t sz; + size_t :0; +}; +#define bpf_prog_stream_read_opts__last_field sz +/** + * @brief **bpf_prog_stream_read** reads data from the BPF stream of a given BPF + * program. + * + * @param prog_fd FD for the BPF program whose BPF stream is to be read. + * @param stream_id ID of the BPF stream to be read. + * @param buf Buffer to read data into from the BPF stream. + * @param buf_len Maximum number of bytes to read from the BPF stream. + * @param opts optional options, can be NULL + * + * @return The number of bytes read, on success; negative error code, otherwise + * (errno is also set to the error code) + */ +LIBBPF_API int bpf_prog_stream_read(int prog_fd, __u32 stream_id, void *buf, __u32 buf_len, + struct bpf_prog_stream_read_opts *opts); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index 496e6a8ee0dc..b997c68bd945 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -2,6 +2,8 @@ #ifndef __BPF_CORE_READ_H__ #define __BPF_CORE_READ_H__ +#include "bpf_helpers.h" + /* * enum bpf_field_info_kind is passed as a second argument into * __builtin_preserve_field_info() built-in to get a specific aspect of @@ -44,7 +46,7 @@ enum bpf_enum_value_kind { #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ #define __CORE_BITFIELD_PROBE_READ(dst, src, fld) \ bpf_probe_read_kernel( \ - (void *)dst, \ + (void *)dst, \ __CORE_RELO(src, fld, BYTE_SIZE), \ (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) #else @@ -102,6 +104,7 @@ enum bpf_enum_value_kind { case 2: val = *(const unsigned short *)p; break; \ case 4: val = *(const unsigned int *)p; break; \ case 8: val = *(const unsigned long long *)p; break; \ + default: val = 0; break; \ } \ val <<= __CORE_RELO(s, field, LSHIFT_U64); \ if (__CORE_RELO(s, field, SIGNED)) \ @@ -111,8 +114,61 @@ enum bpf_enum_value_kind { val; \ }) +/* + * Write to a bitfield, identified by s->field. + * This is the inverse of BPF_CORE_WRITE_BITFIELD(). + */ +#define BPF_CORE_WRITE_BITFIELD(s, field, new_val) ({ \ + void *p = (void *)s + __CORE_RELO(s, field, BYTE_OFFSET); \ + unsigned int byte_size = __CORE_RELO(s, field, BYTE_SIZE); \ + unsigned int lshift = __CORE_RELO(s, field, LSHIFT_U64); \ + unsigned int rshift = __CORE_RELO(s, field, RSHIFT_U64); \ + unsigned long long mask, val, nval = new_val; \ + unsigned int rpad = rshift - lshift; \ + \ + asm volatile("" : "+r"(p)); \ + \ + switch (byte_size) { \ + case 1: val = *(unsigned char *)p; break; \ + case 2: val = *(unsigned short *)p; break; \ + case 4: val = *(unsigned int *)p; break; \ + case 8: val = *(unsigned long long *)p; break; \ + } \ + \ + mask = (~0ULL << rshift) >> lshift; \ + val = (val & ~mask) | ((nval << rpad) & mask); \ + \ + switch (byte_size) { \ + case 1: *(unsigned char *)p = val; break; \ + case 2: *(unsigned short *)p = val; break; \ + case 4: *(unsigned int *)p = val; break; \ + case 8: *(unsigned long long *)p = val; break; \ + } \ +}) + +/* Differentiator between compilers builtin implementations. This is a + * requirement due to the compiler parsing differences where GCC optimizes + * early in parsing those constructs of type pointers to the builtin specific + * type, resulting in not being possible to collect the required type + * information in the builtin expansion. + */ +#ifdef __clang__ +#define ___bpf_typeof(type) ((typeof(type) *) 0) +#else +#define ___bpf_typeof1(type, NR) ({ \ + extern typeof(type) *___concat(bpf_type_tmp_, NR); \ + ___concat(bpf_type_tmp_, NR); \ +}) +#define ___bpf_typeof(type) ___bpf_typeof1(type, __COUNTER__) +#endif + +#ifdef __clang__ #define ___bpf_field_ref1(field) (field) -#define ___bpf_field_ref2(type, field) (((typeof(type) *)0)->field) +#define ___bpf_field_ref2(type, field) (___bpf_typeof(type)->field) +#else +#define ___bpf_field_ref1(field) (&(field)) +#define ___bpf_field_ref2(type, field) (&(___bpf_typeof(type)->field)) +#endif #define ___bpf_field_ref(args...) \ ___bpf_apply(___bpf_field_ref, ___bpf_narg(args))(args) @@ -162,7 +218,7 @@ enum bpf_enum_value_kind { * BTF. Always succeeds. */ #define bpf_core_type_id_local(type) \ - __builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_LOCAL) + __builtin_btf_type_id(*___bpf_typeof(type), BPF_TYPE_ID_LOCAL) /* * Convenience macro to get BTF type ID of a target kernel's type that matches @@ -172,7 +228,7 @@ enum bpf_enum_value_kind { * - 0, if no matching type was found in a target kernel BTF. */ #define bpf_core_type_id_kernel(type) \ - __builtin_btf_type_id(*(typeof(type) *)0, BPF_TYPE_ID_TARGET) + __builtin_btf_type_id(*___bpf_typeof(type), BPF_TYPE_ID_TARGET) /* * Convenience macro to check that provided named type @@ -182,7 +238,7 @@ enum bpf_enum_value_kind { * 0, if no matching type is found. */ #define bpf_core_type_exists(type) \ - __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_EXISTS) + __builtin_preserve_type_info(*___bpf_typeof(type), BPF_TYPE_EXISTS) /* * Convenience macro to check that provided named type @@ -192,7 +248,7 @@ enum bpf_enum_value_kind { * 0, if the type does not match any in the target kernel */ #define bpf_core_type_matches(type) \ - __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_MATCHES) + __builtin_preserve_type_info(*___bpf_typeof(type), BPF_TYPE_MATCHES) /* * Convenience macro to get the byte size of a provided named type @@ -202,7 +258,7 @@ enum bpf_enum_value_kind { * 0, if no matching type is found. */ #define bpf_core_type_size(type) \ - __builtin_preserve_type_info(*(typeof(type) *)0, BPF_TYPE_SIZE) + __builtin_preserve_type_info(*___bpf_typeof(type), BPF_TYPE_SIZE) /* * Convenience macro to check that provided enumerator value is defined in @@ -212,8 +268,13 @@ enum bpf_enum_value_kind { * kernel's BTF; * 0, if no matching enum and/or enum value within that enum is found. */ +#ifdef __clang__ #define bpf_core_enum_value_exists(enum_type, enum_value) \ __builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_EXISTS) +#else +#define bpf_core_enum_value_exists(enum_type, enum_value) \ + __builtin_preserve_enum_value(___bpf_typeof(enum_type), enum_value, BPF_ENUMVAL_EXISTS) +#endif /* * Convenience macro to get the integer value of an enumerator value in @@ -223,8 +284,13 @@ enum bpf_enum_value_kind { * present in target kernel's BTF; * 0, if no matching enum and/or enum value within that enum is found. */ +#ifdef __clang__ #define bpf_core_enum_value(enum_type, enum_value) \ __builtin_preserve_enum_value(*(typeof(enum_type) *)enum_value, BPF_ENUMVAL_VALUE) +#else +#define bpf_core_enum_value(enum_type, enum_value) \ + __builtin_preserve_enum_value(___bpf_typeof(enum_type), enum_value, BPF_ENUMVAL_VALUE) +#endif /* * bpf_core_read() abstracts away bpf_probe_read_kernel() call and captures @@ -236,7 +302,7 @@ enum bpf_enum_value_kind { * a relocation, which records BTF type ID describing root struct/union and an * accessor string which describes exact embedded field that was used to take * an address. See detailed description of this relocation format and - * semantics in comments to struct bpf_field_reloc in libbpf_internal.h. + * semantics in comments to struct bpf_core_relo in include/uapi/linux/bpf.h. * * This relocation allows libbpf to adjust BPF instruction to use correct * actual field offset, based on target kernel BTF type that matches original @@ -260,6 +326,17 @@ enum bpf_enum_value_kind { #define bpf_core_read_user_str(dst, sz, src) \ bpf_probe_read_user_str(dst, sz, (const void *)__builtin_preserve_access_index(src)) +extern void *bpf_rdonly_cast(const void *obj, __u32 btf_id) __ksym __weak; + +/* + * Cast provided pointer *ptr* into a pointer to a specified *type* in such + * a way that BPF verifier will become aware of associated kernel-side BTF + * type. This allows to access members of kernel types directly without the + * need to use BPF_CORE_READ() macros. + */ +#define bpf_core_cast(ptr, type) \ + ((typeof(type) *)bpf_rdonly_cast((ptr), bpf_core_type_id_kernel(type))) + #define ___concat(a, b) a ## b #define ___apply(fn, n) ___concat(fn, n) #define ___nth(_1, _2, _3, _4, _5, _6, _7, _8, _9, _10, __11, N, ...) N @@ -311,7 +388,13 @@ enum bpf_enum_value_kind { #define ___arrow10(a, b, c, d, e, f, g, h, i, j) a->b->c->d->e->f->g->h->i->j #define ___arrow(...) ___apply(___arrow, ___narg(__VA_ARGS__))(__VA_ARGS__) +#if defined(__clang__) && (__clang_major__ >= 19) +#define ___type(...) __typeof_unqual__(___arrow(__VA_ARGS__)) +#elif defined(__GNUC__) && (__GNUC__ >= 14) +#define ___type(...) __typeof_unqual__(___arrow(__VA_ARGS__)) +#else #define ___type(...) typeof(___arrow(__VA_ARGS__)) +#endif #define ___read(read_fn, dst, src_type, src, accessor) \ read_fn((void *)(dst), sizeof(*(dst)), &((src_type)(src))->accessor) @@ -364,7 +447,7 @@ enum bpf_enum_value_kind { /* Non-CO-RE variant of BPF_CORE_READ_INTO() */ #define BPF_PROBE_READ_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read, bpf_probe_read, \ + ___core_read(bpf_probe_read_kernel, bpf_probe_read_kernel, \ dst, (src), a, ##__VA_ARGS__) \ }) @@ -400,7 +483,7 @@ enum bpf_enum_value_kind { /* Non-CO-RE variant of BPF_CORE_READ_STR_INTO() */ #define BPF_PROBE_READ_STR_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read_str, bpf_probe_read, \ + ___core_read(bpf_probe_read_kernel_str, bpf_probe_read_kernel, \ dst, (src), a, ##__VA_ARGS__) \ }) diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index 223308931d55..49af4260b8e6 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -4,6 +4,7 @@ #define __BPF_GEN_INTERNAL_H #include "bpf.h" +#include "libbpf_internal.h" struct ksym_relo_desc { const char *name; @@ -11,6 +12,7 @@ struct ksym_relo_desc { int insn_idx; bool is_weak; bool is_typeless; + bool is_ld64; }; struct ksym_desc { @@ -24,6 +26,7 @@ struct ksym_desc { bool typeless; }; int insn; + bool is_ld64; }; struct bpf_gen { @@ -32,6 +35,7 @@ struct bpf_gen { void *data_cur; void *insn_start; void *insn_cur; + bool swapped_endian; ssize_t cleanup_label; __u32 nr_progs; __u32 nr_maps; @@ -47,6 +51,7 @@ struct bpf_gen { __u32 nr_ksyms; int fd_array; int nr_fd_array; + int hash_insn_offset[SHA256_DWORD_SIZE]; }; void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps); @@ -65,7 +70,7 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u 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); + bool is_typeless, bool is_ld64, 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); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index d37c4fe2849d..d4e4e388e625 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -13,6 +13,15 @@ #define __uint(name, val) int (*name)[val] #define __type(name, val) typeof(val) *name #define __array(name, val) typeof(val) *name[] +#define __ulong(name, val) enum { ___bpf_concat(__unique_value, __COUNTER__) = val } name + +#ifndef likely +#define likely(x) (__builtin_expect(!!(x), 1)) +#endif + +#ifndef unlikely +#define unlikely(x) (__builtin_expect(!!(x), 0)) +#endif /* * Helper macro to place programs, maps, license in @@ -77,16 +86,21 @@ /* * Helper macros to manipulate data structures */ -#ifndef offsetof -#define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER) -#endif -#ifndef container_of + +/* offsetof() definition that uses __builtin_offset() might not preserve field + * offset CO-RE relocation properly, so force-redefine offsetof() using + * old-school approach which works with CO-RE correctly + */ +#undef offsetof +#define offsetof(type, member) ((unsigned long)&((type *)0)->member) + +/* redefined container_of() to ensure we use the above offsetof() macro */ +#undef container_of #define container_of(ptr, type, member) \ ({ \ void *__mptr = (void *)(ptr); \ ((type *)(__mptr - offsetof(type, member))); \ }) -#endif /* * Compiler (optimization) barrier. @@ -109,7 +123,7 @@ * This is a variable-specific variant of more global barrier(). */ #ifndef barrier_var -#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var)) +#define barrier_var(var) asm volatile("" : "+r"(var)) #endif /* @@ -131,7 +145,8 @@ /* * Helper function to perform a tail call with a constant/immediate map slot. */ -#if __clang_major__ >= 8 && defined(__bpf__) +#if (defined(__clang__) && __clang_major__ >= 8) || (!defined(__clang__) && __GNUC__ > 12) +#if defined(__bpf__) static __always_inline void bpf_tail_call_static(void *ctx, const void *map, const __u32 slot) { @@ -159,6 +174,7 @@ bpf_tail_call_static(void *ctx, const void *map, const __u32 slot) : "r0", "r1", "r2", "r3", "r4", "r5"); } #endif +#endif enum libbpf_pin_type { LIBBPF_PIN_NONE, @@ -174,8 +190,33 @@ enum libbpf_tristate { #define __kconfig __attribute__((section(".kconfig"))) #define __ksym __attribute__((section(".ksyms"))) +#define __kptr_untrusted __attribute__((btf_type_tag("kptr_untrusted"))) #define __kptr __attribute__((btf_type_tag("kptr"))) -#define __kptr_ref __attribute__((btf_type_tag("kptr_ref"))) +#define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr"))) +#define __uptr __attribute__((btf_type_tag("uptr"))) + +#if defined (__clang__) +#define bpf_ksym_exists(sym) ({ \ + _Static_assert(!__builtin_constant_p(!!sym), \ + #sym " should be marked as __weak"); \ + !!sym; \ +}) +#elif __GNUC__ > 8 +#define bpf_ksym_exists(sym) ({ \ + _Static_assert(__builtin_has_attribute (*sym, __weak__), \ + #sym " should be marked as __weak"); \ + !!sym; \ +}) +#else +#define bpf_ksym_exists(sym) !!sym +#endif + +#define __arg_ctx __attribute__((btf_decl_tag("arg:ctx"))) +#define __arg_nonnull __attribute((btf_decl_tag("arg:nonnull"))) +#define __arg_nullable __attribute((btf_decl_tag("arg:nullable"))) +#define __arg_trusted __attribute((btf_decl_tag("arg:trusted"))) +#define __arg_untrusted __attribute((btf_decl_tag("arg:untrusted"))) +#define __arg_arena __attribute((btf_decl_tag("arg:arena"))) #ifndef ___bpf_concat #define ___bpf_concat(a, b) a ## b @@ -274,6 +315,22 @@ enum libbpf_tristate { ___param, sizeof(___param)); \ }) +extern int bpf_stream_vprintk_impl(int stream_id, const char *fmt__str, const void *args, + __u32 len__sz, void *aux__prog) __weak __ksym; + +#define bpf_stream_printk(stream_id, fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_stream_vprintk_impl(stream_id, ___fmt, ___param, sizeof(___param), NULL); \ +}) + /* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args * Otherwise use __bpf_vprintk */ @@ -286,4 +343,107 @@ enum libbpf_tristate { /* Helper macro to print out debug messages */ #define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args) +struct bpf_iter_num; + +extern int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end) __weak __ksym; +extern int *bpf_iter_num_next(struct bpf_iter_num *it) __weak __ksym; +extern void bpf_iter_num_destroy(struct bpf_iter_num *it) __weak __ksym; + +#ifndef bpf_for_each +/* bpf_for_each(iter_type, cur_elem, args...) provides generic construct for + * using BPF open-coded iterators without having to write mundane explicit + * low-level loop logic. Instead, it provides for()-like generic construct + * that can be used pretty naturally. E.g., for some hypothetical cgroup + * iterator, you'd write: + * + * struct cgroup *cg, *parent_cg = <...>; + * + * bpf_for_each(cgroup, cg, parent_cg, CG_ITER_CHILDREN) { + * bpf_printk("Child cgroup id = %d", cg->cgroup_id); + * if (cg->cgroup_id == 123) + * break; + * } + * + * I.e., it looks almost like high-level for each loop in other languages, + * supports continue/break, and is verifiable by BPF verifier. + * + * For iterating integers, the difference between bpf_for_each(num, i, N, M) + * and bpf_for(i, N, M) is in that bpf_for() provides additional proof to + * verifier that i is in [N, M) range, and in bpf_for_each() case i is `int + * *`, not just `int`. So for integers bpf_for() is more convenient. + * + * Note: this macro relies on C99 feature of allowing to declare variables + * inside for() loop, bound to for() loop lifetime. It also utilizes GCC + * extension: __attribute__((cleanup(<func>))), supported by both GCC and + * Clang. + */ +#define bpf_for_each(type, cur, args...) for ( \ + /* initialize and define destructor */ \ + struct bpf_iter_##type ___it __attribute__((aligned(8), /* enforce, just in case */, \ + cleanup(bpf_iter_##type##_destroy))), \ + /* ___p pointer is just to call bpf_iter_##type##_new() *once* to init ___it */ \ + *___p __attribute__((unused)) = ( \ + bpf_iter_##type##_new(&___it, ##args), \ + /* this is a workaround for Clang bug: it currently doesn't emit BTF */ \ + /* for bpf_iter_##type##_destroy() when used from cleanup() attribute */ \ + (void)bpf_iter_##type##_destroy, (void *)0); \ + /* iteration and termination check */ \ + (((cur) = bpf_iter_##type##_next(&___it))); \ +) +#endif /* bpf_for_each */ + +#ifndef bpf_for +/* bpf_for(i, start, end) implements a for()-like looping construct that sets + * provided integer variable *i* to values starting from *start* through, + * but not including, *end*. It also proves to BPF verifier that *i* belongs + * to range [start, end), so this can be used for accessing arrays without + * extra checks. + * + * Note: *start* and *end* are assumed to be expressions with no side effects + * and whose values do not change throughout bpf_for() loop execution. They do + * not have to be statically known or constant, though. + * + * Note: similarly to bpf_for_each(), it relies on C99 feature of declaring for() + * loop bound variables and cleanup attribute, supported by GCC and Clang. + */ +#define bpf_for(i, start, end) for ( \ + /* initialize and define destructor */ \ + struct bpf_iter_num ___it __attribute__((aligned(8), /* enforce, just in case */ \ + cleanup(bpf_iter_num_destroy))), \ + /* ___p pointer is necessary to call bpf_iter_num_new() *once* to init ___it */ \ + *___p __attribute__((unused)) = ( \ + bpf_iter_num_new(&___it, (start), (end)), \ + /* this is a workaround for Clang bug: it currently doesn't emit BTF */ \ + /* for bpf_iter_num_destroy() when used from cleanup() attribute */ \ + (void)bpf_iter_num_destroy, (void *)0); \ + ({ \ + /* iteration step */ \ + int *___t = bpf_iter_num_next(&___it); \ + /* termination and bounds check */ \ + (___t && ((i) = *___t, (i) >= (start) && (i) < (end))); \ + }); \ +) +#endif /* bpf_for */ + +#ifndef bpf_repeat +/* bpf_repeat(N) performs N iterations without exposing iteration number + * + * Note: similarly to bpf_for_each(), it relies on C99 feature of declaring for() + * loop bound variables and cleanup attribute, supported by GCC and Clang. + */ +#define bpf_repeat(N) for ( \ + /* initialize and define destructor */ \ + struct bpf_iter_num ___it __attribute__((aligned(8), /* enforce, just in case */ \ + cleanup(bpf_iter_num_destroy))), \ + /* ___p pointer is necessary to call bpf_iter_num_new() *once* to init ___it */ \ + *___p __attribute__((unused)) = ( \ + bpf_iter_num_new(&___it, 0, (N)), \ + /* this is a workaround for Clang bug: it currently doesn't emit BTF */ \ + /* for bpf_iter_num_destroy() when used from cleanup() attribute */ \ + (void)bpf_iter_num_destroy, (void *)0); \ + bpf_iter_num_next(&___it); \ + /* nothing here */ \ +) +#endif /* bpf_repeat */ + #endif diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 2972dc25ff72..dbe32a5d02cd 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -2,7 +2,7 @@ #ifndef __BPF_TRACING_H__ #define __BPF_TRACING_H__ -#include <bpf/bpf_helpers.h> +#include "bpf_helpers.h" /* Scan the ARCH passed in from ARCH env variable (see Makefile) */ #if defined(__TARGET_ARCH_x86) @@ -32,6 +32,9 @@ #elif defined(__TARGET_ARCH_arc) #define bpf_target_arc #define bpf_target_defined +#elif defined(__TARGET_ARCH_loongarch) + #define bpf_target_loongarch + #define bpf_target_defined #else /* Fall back to what the compiler says */ @@ -62,6 +65,9 @@ #elif defined(__arc__) #define bpf_target_arc #define bpf_target_defined +#elif defined(__loongarch__) + #define bpf_target_loongarch + #define bpf_target_defined #endif /* no compiler target */ #endif @@ -72,6 +78,10 @@ #if defined(bpf_target_x86) +/* + * https://en.wikipedia.org/wiki/X86_calling_conventions#System_V_AMD64_ABI + */ + #if defined(__KERNEL__) || defined(__VMLINUX_H__) #define __PT_PARM1_REG di @@ -79,25 +89,40 @@ #define __PT_PARM3_REG dx #define __PT_PARM4_REG cx #define __PT_PARM5_REG r8 +#define __PT_PARM6_REG r9 +/* + * Syscall uses r10 for PARM4. See arch/x86/entry/entry_64.S:entry_SYSCALL_64 + * comments in Linux sources. And refer to syscall(2) manpage. + */ +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG r10 +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + #define __PT_RET_REG sp #define __PT_FP_REG bp #define __PT_RC_REG ax #define __PT_SP_REG sp #define __PT_IP_REG ip -/* syscall uses r10 for PARM4 */ -#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) -#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) #else #ifdef __i386__ +/* i386 kernel is built with -mregparm=3 */ #define __PT_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__ +/* i386 syscall ABI is very different, refer to syscall(2) manpage */ +#define __PT_PARM1_SYSCALL_REG ebx +#define __PT_PARM2_SYSCALL_REG ecx +#define __PT_PARM3_SYSCALL_REG edx +#define __PT_PARM4_SYSCALL_REG esi +#define __PT_PARM5_SYSCALL_REG edi +#define __PT_PARM6_SYSCALL_REG ebp + #define __PT_RET_REG esp #define __PT_FP_REG ebp #define __PT_RC_REG eax @@ -111,14 +136,20 @@ #define __PT_PARM3_REG rdx #define __PT_PARM4_REG rcx #define __PT_PARM5_REG r8 +#define __PT_PARM6_REG r9 + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG r10 +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + #define __PT_RET_REG rsp #define __PT_FP_REG rbp #define __PT_RC_REG rax #define __PT_SP_REG rsp #define __PT_IP_REG rip -/* syscall uses r10 for PARM4 */ -#define PT_REGS_PARM4_SYSCALL(x) ((x)->r10) -#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(x, r10) #endif /* __i386__ */ @@ -126,9 +157,13 @@ #elif defined(bpf_target_s390) +/* + * https://github.com/IBM/s390x-abi/releases/download/v1.6/lzsabi_s390x.pdf + */ + struct pt_regs___s390 { unsigned long orig_gpr2; -}; +} __attribute__((preserve_access_index)); /* s390 provides user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const user_pt_regs *)(x)) @@ -137,21 +172,42 @@ struct pt_regs___s390 { #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_PARM1_SYSCALL_REG orig_gpr2 +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG gprs[7] +#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___s390 *)(x))->__PT_PARM1_SYSCALL_REG) +#define PT_REGS_PARM1_CORE_SYSCALL(x) \ + BPF_CORE_READ((const struct pt_regs___s390 *)(x), __PT_PARM1_SYSCALL_REG) + +#define __PT_RET_REG gprs[14] #define __PT_FP_REG gprs[11] /* Works only with CONFIG_FRAME_POINTER */ #define __PT_RC_REG gprs[2] #define __PT_SP_REG gprs[15] #define __PT_IP_REG psw.addr -#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) -#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2) #elif defined(bpf_target_arm) +/* + * https://github.com/ARM-software/abi-aa/blob/main/aapcs32/aapcs32.rst#machine-registers + */ + #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_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG uregs[4] +#define __PT_PARM6_SYSCALL_REG uregs[5] +#define __PT_PARM7_SYSCALL_REG uregs[6] + #define __PT_RET_REG uregs[14] #define __PT_FP_REG uregs[11] /* Works only with CONFIG_FRAME_POINTER */ #define __PT_RC_REG uregs[0] @@ -160,9 +216,13 @@ struct pt_regs___s390 { #elif defined(bpf_target_arm64) +/* + * https://github.com/ARM-software/abi-aa/blob/main/aapcs64/aapcs64.rst#machine-registers + */ + struct pt_regs___arm64 { unsigned long orig_x0; -}; +} __attribute__((preserve_access_index)); /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) @@ -171,21 +231,49 @@ struct pt_regs___arm64 { #define __PT_PARM3_REG regs[2] #define __PT_PARM4_REG regs[3] #define __PT_PARM5_REG regs[4] +#define __PT_PARM6_REG regs[5] +#define __PT_PARM7_REG regs[6] +#define __PT_PARM8_REG regs[7] + +#define __PT_PARM1_SYSCALL_REG orig_x0 +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG +#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___arm64 *)(x))->__PT_PARM1_SYSCALL_REG) +#define PT_REGS_PARM1_CORE_SYSCALL(x) \ + BPF_CORE_READ((const struct pt_regs___arm64 *)(x), __PT_PARM1_SYSCALL_REG) + #define __PT_RET_REG regs[30] #define __PT_FP_REG regs[29] /* Works only with CONFIG_FRAME_POINTER */ #define __PT_RC_REG regs[0] #define __PT_SP_REG sp #define __PT_IP_REG pc -#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1_CORE_SYSCALL(x) -#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0) #elif defined(bpf_target_mips) +/* + * N64 ABI is assumed right now. + * https://en.wikipedia.org/wiki/MIPS_architecture#Calling_conventions + */ + #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_PARM6_REG regs[9] +#define __PT_PARM7_REG regs[10] +#define __PT_PARM8_REG regs[11] + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG /* only N32/N64 */ +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG /* only N32/N64 */ + #define __PT_RET_REG regs[31] #define __PT_FP_REG regs[30] /* Works only with CONFIG_FRAME_POINTER */ #define __PT_RC_REG regs[2] @@ -194,26 +282,58 @@ struct pt_regs___arm64 { #elif defined(bpf_target_powerpc) +/* + * http://refspecs.linux-foundation.org/elf/elfspec_ppc.pdf (page 3-14, + * section "Function Calling Sequence") + */ + #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_PARM6_REG gpr[8] +#define __PT_PARM7_REG gpr[9] +#define __PT_PARM8_REG gpr[10] + +/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx +#define __PT_PARM1_SYSCALL_REG orig_gpr3 +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG +#if !defined(__arch64__) +#define __PT_PARM7_SYSCALL_REG __PT_PARM7_REG /* only powerpc (not powerpc64) */ +#endif + #define __PT_RET_REG regs[31] #define __PT_FP_REG __unsupported__ #define __PT_RC_REG gpr[3] -#define __PT_SP_REG sp +#define __PT_SP_REG gpr[1] #define __PT_IP_REG nip -/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */ -#define PT_REGS_SYSCALL_REGS(ctx) ctx #elif defined(bpf_target_sparc) +/* + * https://en.wikipedia.org/wiki/Calling_convention#SPARC + */ + #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_PARM6_REG u_regs[UREG_I5] + +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + #define __PT_RET_REG u_regs[UREG_I7] #define __PT_FP_REG __unsupported__ #define __PT_RC_REG u_regs[UREG_I0] @@ -227,36 +347,106 @@ struct pt_regs___arm64 { #elif defined(bpf_target_riscv) +/* + * https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-cc.adoc#risc-v-calling-conventions + */ + +struct pt_regs___riscv { + unsigned long orig_a0; +} __attribute__((preserve_access_index)); + +/* riscv provides struct user_regs_struct instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG a0 #define __PT_PARM2_REG a1 #define __PT_PARM3_REG a2 #define __PT_PARM4_REG a3 #define __PT_PARM5_REG a4 +#define __PT_PARM6_REG a5 +#define __PT_PARM7_REG a6 +#define __PT_PARM8_REG a7 + +#define __PT_PARM1_SYSCALL_REG orig_a0 +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG +#define PT_REGS_PARM1_SYSCALL(x) (((const struct pt_regs___riscv *)(x))->__PT_PARM1_SYSCALL_REG) +#define PT_REGS_PARM1_CORE_SYSCALL(x) \ + BPF_CORE_READ((const struct pt_regs___riscv *)(x), __PT_PARM1_SYSCALL_REG) + #define __PT_RET_REG ra #define __PT_FP_REG s0 #define __PT_RC_REG a0 #define __PT_SP_REG sp #define __PT_IP_REG pc -/* riscv does not select ARCH_HAS_SYSCALL_WRAPPER. */ -#define PT_REGS_SYSCALL_REGS(ctx) ctx #elif defined(bpf_target_arc) -/* arc provides struct user_pt_regs instead of struct pt_regs to userspace */ +/* + * Section "Function Calling Sequence" (page 24): + * https://raw.githubusercontent.com/wiki/foss-for-synopsys-dwc-arc-processors/toolchain/files/ARCv2_ABI.pdf + */ + +/* arc provides struct user_regs_struct instead of struct pt_regs to userspace */ #define __PT_REGS_CAST(x) ((const struct user_regs_struct *)(x)) #define __PT_PARM1_REG scratch.r0 #define __PT_PARM2_REG scratch.r1 #define __PT_PARM3_REG scratch.r2 #define __PT_PARM4_REG scratch.r3 #define __PT_PARM5_REG scratch.r4 +#define __PT_PARM6_REG scratch.r5 +#define __PT_PARM7_REG scratch.r6 +#define __PT_PARM8_REG scratch.r7 + +/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */ +#define PT_REGS_SYSCALL_REGS(ctx) ctx +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + #define __PT_RET_REG scratch.blink -#define __PT_FP_REG __unsupported__ +#define __PT_FP_REG scratch.fp #define __PT_RC_REG scratch.r0 #define __PT_SP_REG scratch.sp #define __PT_IP_REG scratch.ret -/* arc does not select ARCH_HAS_SYSCALL_WRAPPER. */ + +#elif defined(bpf_target_loongarch) + +/* + * https://docs.kernel.org/loongarch/introduction.html + * https://loongson.github.io/LoongArch-Documentation/LoongArch-ELF-ABI-EN.html + */ + +/* loongarch provides struct user_pt_regs instead of struct pt_regs to userspace */ +#define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x)) +#define __PT_PARM1_REG regs[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_PARM6_REG regs[9] +#define __PT_PARM7_REG regs[10] +#define __PT_PARM8_REG regs[11] + +/* loongarch does not select ARCH_HAS_SYSCALL_WRAPPER. */ #define PT_REGS_SYSCALL_REGS(ctx) ctx +#define __PT_PARM1_SYSCALL_REG __PT_PARM1_REG +#define __PT_PARM2_SYSCALL_REG __PT_PARM2_REG +#define __PT_PARM3_SYSCALL_REG __PT_PARM3_REG +#define __PT_PARM4_SYSCALL_REG __PT_PARM4_REG +#define __PT_PARM5_SYSCALL_REG __PT_PARM5_REG +#define __PT_PARM6_SYSCALL_REG __PT_PARM6_REG + +#define __PT_RET_REG regs[1] +#define __PT_FP_REG regs[22] +#define __PT_RC_REG regs[4] +#define __PT_SP_REG regs[3] +#define __PT_IP_REG csr_era #endif @@ -264,16 +454,49 @@ struct pt_regs___arm64 { struct pt_regs; -/* allow some architecutres to override `struct pt_regs` */ +/* allow some architectures to override `struct pt_regs` */ #ifndef __PT_REGS_CAST #define __PT_REGS_CAST(x) (x) #endif +/* + * Different architectures support different number of arguments passed + * through registers. i386 supports just 3, some arches support up to 8. + */ +#ifndef __PT_PARM4_REG +#define __PT_PARM4_REG __unsupported__ +#endif +#ifndef __PT_PARM5_REG +#define __PT_PARM5_REG __unsupported__ +#endif +#ifndef __PT_PARM6_REG +#define __PT_PARM6_REG __unsupported__ +#endif +#ifndef __PT_PARM7_REG +#define __PT_PARM7_REG __unsupported__ +#endif +#ifndef __PT_PARM8_REG +#define __PT_PARM8_REG __unsupported__ +#endif +/* + * Similarly, syscall-specific conventions might differ between function call + * conventions within each architecture. All supported architectures pass + * either 6 or 7 syscall arguments in registers. + * + * See syscall(2) manpage for succinct table with information on each arch. + */ +#ifndef __PT_PARM7_SYSCALL_REG +#define __PT_PARM7_SYSCALL_REG __unsupported__ +#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_PARM6(x) (__PT_REGS_CAST(x)->__PT_PARM6_REG) +#define PT_REGS_PARM7(x) (__PT_REGS_CAST(x)->__PT_PARM7_REG) +#define PT_REGS_PARM8(x) (__PT_REGS_CAST(x)->__PT_PARM8_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) @@ -285,6 +508,9 @@ struct pt_regs; #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_PARM6_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM6_REG) +#define PT_REGS_PARM7_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM7_REG) +#define PT_REGS_PARM8_CORE(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM8_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) @@ -296,7 +522,7 @@ struct pt_regs; #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP -#elif defined(bpf_target_sparc) +#elif defined(bpf_target_sparc) || defined(bpf_target_arm64) #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP @@ -311,24 +537,33 @@ struct pt_regs; #endif #ifndef PT_REGS_PARM1_SYSCALL -#define PT_REGS_PARM1_SYSCALL(x) PT_REGS_PARM1(x) +#define PT_REGS_PARM1_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM1_SYSCALL_REG) +#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM1_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM2_SYSCALL +#define PT_REGS_PARM2_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM2_SYSCALL_REG) +#define PT_REGS_PARM2_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM2_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM3_SYSCALL +#define PT_REGS_PARM3_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM3_SYSCALL_REG) +#define PT_REGS_PARM3_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM3_SYSCALL_REG) #endif -#define PT_REGS_PARM2_SYSCALL(x) PT_REGS_PARM2(x) -#define PT_REGS_PARM3_SYSCALL(x) PT_REGS_PARM3(x) #ifndef PT_REGS_PARM4_SYSCALL -#define PT_REGS_PARM4_SYSCALL(x) PT_REGS_PARM4(x) +#define PT_REGS_PARM4_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM4_SYSCALL_REG) +#define PT_REGS_PARM4_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM4_SYSCALL_REG) #endif -#define PT_REGS_PARM5_SYSCALL(x) PT_REGS_PARM5(x) - -#ifndef PT_REGS_PARM1_CORE_SYSCALL -#define PT_REGS_PARM1_CORE_SYSCALL(x) PT_REGS_PARM1_CORE(x) +#ifndef PT_REGS_PARM5_SYSCALL +#define PT_REGS_PARM5_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM5_SYSCALL_REG) +#define PT_REGS_PARM5_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM5_SYSCALL_REG) #endif -#define PT_REGS_PARM2_CORE_SYSCALL(x) PT_REGS_PARM2_CORE(x) -#define PT_REGS_PARM3_CORE_SYSCALL(x) PT_REGS_PARM3_CORE(x) -#ifndef PT_REGS_PARM4_CORE_SYSCALL -#define PT_REGS_PARM4_CORE_SYSCALL(x) PT_REGS_PARM4_CORE(x) +#ifndef PT_REGS_PARM6_SYSCALL +#define PT_REGS_PARM6_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM6_SYSCALL_REG) +#define PT_REGS_PARM6_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM6_SYSCALL_REG) +#endif +#ifndef PT_REGS_PARM7_SYSCALL +#define PT_REGS_PARM7_SYSCALL(x) (__PT_REGS_CAST(x)->__PT_PARM7_SYSCALL_REG) +#define PT_REGS_PARM7_CORE_SYSCALL(x) BPF_CORE_READ(__PT_REGS_CAST(x), __PT_PARM7_SYSCALL_REG) #endif -#define PT_REGS_PARM5_CORE_SYSCALL(x) PT_REGS_PARM5_CORE(x) #else /* defined(bpf_target_defined) */ @@ -337,6 +572,9 @@ struct pt_regs; #define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM8(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) @@ -348,6 +586,9 @@ struct pt_regs; #define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM8_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) @@ -362,12 +603,16 @@ struct pt_regs; #define PT_REGS_PARM3_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM4_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM5_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM1_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM2_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM3_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM4_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #define PT_REGS_PARM5_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM6_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM7_CORE_SYSCALL(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) #endif /* defined(bpf_target_defined) */ @@ -395,25 +640,25 @@ struct pt_regs; #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_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_cast1(x) ___bpf_ctx_cast0(), ctx[0] +#define ___bpf_ctx_cast2(x, args...) ___bpf_ctx_cast1(args), ctx[1] +#define ___bpf_ctx_cast3(x, args...) ___bpf_ctx_cast2(args), ctx[2] +#define ___bpf_ctx_cast4(x, args...) ___bpf_ctx_cast3(args), ctx[3] +#define ___bpf_ctx_cast5(x, args...) ___bpf_ctx_cast4(args), ctx[4] +#define ___bpf_ctx_cast6(x, args...) ___bpf_ctx_cast5(args), ctx[5] +#define ___bpf_ctx_cast7(x, args...) ___bpf_ctx_cast6(args), ctx[6] +#define ___bpf_ctx_cast8(x, args...) ___bpf_ctx_cast7(args), ctx[7] +#define ___bpf_ctx_cast9(x, args...) ___bpf_ctx_cast8(args), ctx[8] +#define ___bpf_ctx_cast10(x, args...) ___bpf_ctx_cast9(args), ctx[9] +#define ___bpf_ctx_cast11(x, args...) ___bpf_ctx_cast10(args), ctx[10] +#define ___bpf_ctx_cast12(x, args...) ___bpf_ctx_cast11(args), ctx[11] #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 * similar kinds of BPF programs, that accept input arguments as a single * pointer to untyped u64 array, where each u64 can actually be a typed - * pointer or integer of different size. Instead of requring user to write + * pointer or integer of different size. Instead of requiring user to write * manual casts and work with array elements by index, BPF_PROG macro * allows user to declare a list of named and typed input arguments in the * same syntax as for normal C function. All the casting is hidden and @@ -548,11 +793,14 @@ ____##name(unsigned long long *ctx ___bpf_ctx_decl(args)) struct pt_regs; #define ___bpf_kprobe_args0() ctx -#define ___bpf_kprobe_args1(x) ___bpf_kprobe_args0(), (void *)PT_REGS_PARM1(ctx) -#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (void *)PT_REGS_PARM2(ctx) -#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (void *)PT_REGS_PARM3(ctx) -#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (void *)PT_REGS_PARM4(ctx) -#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (void *)PT_REGS_PARM5(ctx) +#define ___bpf_kprobe_args1(x) ___bpf_kprobe_args0(), (unsigned long long)PT_REGS_PARM1(ctx) +#define ___bpf_kprobe_args2(x, args...) ___bpf_kprobe_args1(args), (unsigned long long)PT_REGS_PARM2(ctx) +#define ___bpf_kprobe_args3(x, args...) ___bpf_kprobe_args2(args), (unsigned long long)PT_REGS_PARM3(ctx) +#define ___bpf_kprobe_args4(x, args...) ___bpf_kprobe_args3(args), (unsigned long long)PT_REGS_PARM4(ctx) +#define ___bpf_kprobe_args5(x, args...) ___bpf_kprobe_args4(args), (unsigned long long)PT_REGS_PARM5(ctx) +#define ___bpf_kprobe_args6(x, args...) ___bpf_kprobe_args5(args), (unsigned long long)PT_REGS_PARM6(ctx) +#define ___bpf_kprobe_args7(x, args...) ___bpf_kprobe_args6(args), (unsigned long long)PT_REGS_PARM7(ctx) +#define ___bpf_kprobe_args8(x, args...) ___bpf_kprobe_args7(args), (unsigned long long)PT_REGS_PARM8(ctx) #define ___bpf_kprobe_args(args...) ___bpf_apply(___bpf_kprobe_args, ___bpf_narg(args))(args) /* @@ -560,7 +808,7 @@ struct pt_regs; * tp_btf/fentry/fexit BPF programs. It hides the underlying platform-specific * low-level way of getting kprobe input arguments from struct pt_regs, and * provides a familiar typed and named function arguments syntax and - * semantics of accessing kprobe input paremeters. + * semantics of accessing kprobe input parameters. * * Original struct pt_regs* context is preserved as 'ctx' argument. This might * be necessary when using BPF helpers like bpf_perf_event_output(). @@ -580,7 +828,7 @@ static __always_inline typeof(name(0)) \ ____##name(struct pt_regs *ctx, ##args) #define ___bpf_kretprobe_args0() ctx -#define ___bpf_kretprobe_args1(x) ___bpf_kretprobe_args0(), (void *)PT_REGS_RC(ctx) +#define ___bpf_kretprobe_args1(x) ___bpf_kretprobe_args0(), (unsigned long long)PT_REGS_RC(ctx) #define ___bpf_kretprobe_args(args...) ___bpf_apply(___bpf_kretprobe_args, ___bpf_narg(args))(args) /* @@ -604,20 +852,24 @@ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) /* If kernel has CONFIG_ARCH_HAS_SYSCALL_WRAPPER, read pt_regs directly */ #define ___bpf_syscall_args0() ctx -#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (void *)PT_REGS_PARM1_SYSCALL(regs) -#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (void *)PT_REGS_PARM2_SYSCALL(regs) -#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (void *)PT_REGS_PARM3_SYSCALL(regs) -#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (void *)PT_REGS_PARM4_SYSCALL(regs) -#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (void *)PT_REGS_PARM5_SYSCALL(regs) +#define ___bpf_syscall_args1(x) ___bpf_syscall_args0(), (unsigned long long)PT_REGS_PARM1_SYSCALL(regs) +#define ___bpf_syscall_args2(x, args...) ___bpf_syscall_args1(args), (unsigned long long)PT_REGS_PARM2_SYSCALL(regs) +#define ___bpf_syscall_args3(x, args...) ___bpf_syscall_args2(args), (unsigned long long)PT_REGS_PARM3_SYSCALL(regs) +#define ___bpf_syscall_args4(x, args...) ___bpf_syscall_args3(args), (unsigned long long)PT_REGS_PARM4_SYSCALL(regs) +#define ___bpf_syscall_args5(x, args...) ___bpf_syscall_args4(args), (unsigned long long)PT_REGS_PARM5_SYSCALL(regs) +#define ___bpf_syscall_args6(x, args...) ___bpf_syscall_args5(args), (unsigned long long)PT_REGS_PARM6_SYSCALL(regs) +#define ___bpf_syscall_args7(x, args...) ___bpf_syscall_args6(args), (unsigned long long)PT_REGS_PARM7_SYSCALL(regs) #define ___bpf_syscall_args(args...) ___bpf_apply(___bpf_syscall_args, ___bpf_narg(args))(args) /* If kernel doesn't have CONFIG_ARCH_HAS_SYSCALL_WRAPPER, we have to BPF_CORE_READ from pt_regs */ #define ___bpf_syswrap_args0() ctx -#define ___bpf_syswrap_args1(x) ___bpf_syswrap_args0(), (void *)PT_REGS_PARM1_CORE_SYSCALL(regs) -#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (void *)PT_REGS_PARM2_CORE_SYSCALL(regs) -#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (void *)PT_REGS_PARM3_CORE_SYSCALL(regs) -#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (void *)PT_REGS_PARM4_CORE_SYSCALL(regs) -#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (void *)PT_REGS_PARM5_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args1(x) ___bpf_syswrap_args0(), (unsigned long long)PT_REGS_PARM1_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args2(x, args...) ___bpf_syswrap_args1(args), (unsigned long long)PT_REGS_PARM2_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args3(x, args...) ___bpf_syswrap_args2(args), (unsigned long long)PT_REGS_PARM3_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args4(x, args...) ___bpf_syswrap_args3(args), (unsigned long long)PT_REGS_PARM4_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args5(x, args...) ___bpf_syswrap_args4(args), (unsigned long long)PT_REGS_PARM5_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args6(x, args...) ___bpf_syswrap_args5(args), (unsigned long long)PT_REGS_PARM6_CORE_SYSCALL(regs) +#define ___bpf_syswrap_args7(x, args...) ___bpf_syswrap_args6(args), (unsigned long long)PT_REGS_PARM7_CORE_SYSCALL(regs) #define ___bpf_syswrap_args(args...) ___bpf_apply(___bpf_syswrap_args, ___bpf_narg(args))(args) /* @@ -667,4 +919,11 @@ ____##name(struct pt_regs *ctx, ##args) #define BPF_KPROBE_SYSCALL BPF_KSYSCALL +/* BPF_UPROBE and BPF_URETPROBE are identical to BPF_KPROBE and BPF_KRETPROBE, + * but are named way less confusingly for SEC("uprobe") and SEC("uretprobe") + * use cases. + */ +#define BPF_UPROBE(name, args...) BPF_KPROBE(name, ##args) +#define BPF_URETPROBE(name, args...) BPF_KRETPROBE(name, ##args) + #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 71e165b09ed5..84a4b0abc8be 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -12,6 +12,7 @@ #include <sys/utsname.h> #include <sys/param.h> #include <sys/stat.h> +#include <sys/mman.h> #include <linux/kernel.h> #include <linux/err.h> #include <linux/btf.h> @@ -116,6 +117,12 @@ struct btf { /* whether strings are already deduplicated */ bool strs_deduped; + /* whether base_btf should be freed in btf_free for this instance */ + bool owns_base; + + /* whether raw_data is a (read-only) mmap */ + bool raw_data_is_mmap; + /* BTF object FD, if loaded into kernel */ int fd; @@ -279,7 +286,7 @@ static int btf_parse_str_sec(struct btf *btf) return -EINVAL; } if (!btf->base_btf && start[0]) { - pr_debug("Invalid BTF string section\n"); + pr_debug("Malformed BTF string section, did you forget to provide base BTF?\n"); return -EINVAL; } return 0; @@ -448,6 +455,165 @@ static int btf_parse_type_sec(struct btf *btf) return 0; } +static int btf_validate_str(const struct btf *btf, __u32 str_off, const char *what, __u32 type_id) +{ + const char *s; + + s = btf__str_by_offset(btf, str_off); + if (!s) { + pr_warn("btf: type [%u]: invalid %s (string offset %u)\n", type_id, what, str_off); + return -EINVAL; + } + + return 0; +} + +static int btf_validate_id(const struct btf *btf, __u32 id, __u32 ctx_id) +{ + const struct btf_type *t; + + t = btf__type_by_id(btf, id); + if (!t) { + pr_warn("btf: type [%u]: invalid referenced type ID %u\n", ctx_id, id); + return -EINVAL; + } + + return 0; +} + +static int btf_validate_type(const struct btf *btf, const struct btf_type *t, __u32 id) +{ + __u32 kind = btf_kind(t); + int err, i, n; + + err = btf_validate_str(btf, t->name_off, "type name", id); + if (err) + return err; + + switch (kind) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FWD: + case BTF_KIND_FLOAT: + break; + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VAR: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: + err = btf_validate_id(btf, t->type, id); + if (err) + return err; + break; + case BTF_KIND_ARRAY: { + const struct btf_array *a = btf_array(t); + + err = btf_validate_id(btf, a->type, id); + err = err ?: btf_validate_id(btf, a->index_type, id); + if (err) + return err; + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + + n = btf_vlen(t); + for (i = 0; i < n; i++, m++) { + err = btf_validate_str(btf, m->name_off, "field name", id); + err = err ?: btf_validate_id(btf, m->type, id); + if (err) + return err; + } + break; + } + case BTF_KIND_ENUM: { + const struct btf_enum *m = btf_enum(t); + + n = btf_vlen(t); + for (i = 0; i < n; i++, m++) { + err = btf_validate_str(btf, m->name_off, "enum name", id); + if (err) + return err; + } + break; + } + case BTF_KIND_ENUM64: { + const struct btf_enum64 *m = btf_enum64(t); + + n = btf_vlen(t); + for (i = 0; i < n; i++, m++) { + err = btf_validate_str(btf, m->name_off, "enum name", id); + if (err) + return err; + } + break; + } + case BTF_KIND_FUNC: { + const struct btf_type *ft; + + err = btf_validate_id(btf, t->type, id); + if (err) + return err; + ft = btf__type_by_id(btf, t->type); + if (btf_kind(ft) != BTF_KIND_FUNC_PROTO) { + pr_warn("btf: type [%u]: referenced type [%u] is not FUNC_PROTO\n", id, t->type); + return -EINVAL; + } + break; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *m = btf_params(t); + + n = btf_vlen(t); + for (i = 0; i < n; i++, m++) { + err = btf_validate_str(btf, m->name_off, "param name", id); + err = err ?: btf_validate_id(btf, m->type, id); + if (err) + return err; + } + break; + } + case BTF_KIND_DATASEC: { + const struct btf_var_secinfo *m = btf_var_secinfos(t); + + n = btf_vlen(t); + for (i = 0; i < n; i++, m++) { + err = btf_validate_id(btf, m->type, id); + if (err) + return err; + } + break; + } + default: + pr_warn("btf: type [%u]: unrecognized kind %u\n", id, kind); + return -EINVAL; + } + return 0; +} + +/* Validate basic sanity of BTF. It's intentionally less thorough than + * kernel's validation and validates only properties of BTF that libbpf relies + * on to be correct (e.g., valid type IDs, valid string offsets, etc) + */ +static int btf_sanity_check(const struct btf *btf) +{ + const struct btf_type *t; + __u32 i, n = btf__type_cnt(btf); + int err; + + for (i = btf->start_id; i < n; i++) { + t = btf_type_by_id(btf, i); + err = btf_validate_type(btf, t, i); + if (err) + return err; + } + return 0; +} + __u32 btf__type_cnt(const struct btf *btf) { return btf->start_id + btf->nr_types; @@ -688,8 +854,21 @@ int btf__align_of(const struct btf *btf, __u32 id) if (align <= 0) return libbpf_err(align); max_align = max(max_align, align); + + /* if field offset isn't aligned according to field + * type's alignment, then struct must be packed + */ + if (btf_member_bitfield_size(t, i) == 0 && + (m->offset % (8 * align)) != 0) + return 1; } + /* if struct/union size isn't a multiple of its alignment, + * then struct must be packed + */ + if ((t->size % max_align) != 0) + return 1; + return max_align; } default: @@ -775,6 +954,17 @@ static bool btf_is_modifiable(const struct btf *btf) return (void *)btf->hdr != btf->raw_data; } +static void btf_free_raw_data(struct btf *btf) +{ + if (btf->raw_data_is_mmap) { + munmap(btf->raw_data, btf->raw_size); + btf->raw_data_is_mmap = false; + } else { + free(btf->raw_data); + } + btf->raw_data = NULL; +} + void btf__free(struct btf *btf) { if (IS_ERR_OR_NULL(btf)) @@ -794,9 +984,11 @@ void btf__free(struct btf *btf) free(btf->types_data); strset__free(btf->strs_set); } - free(btf->raw_data); + btf_free_raw_data(btf); free(btf->raw_data_swapped); free(btf->type_offs); + if (btf->owns_base) + btf__free(btf->base_btf); free(btf); } @@ -818,7 +1010,8 @@ static struct btf *btf_new_empty(struct btf *base_btf) if (base_btf) { btf->base_btf = base_btf; btf->start_id = btf__type_cnt(base_btf); - btf->start_str_off = base_btf->hdr->str_len; + btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off; + btf->swapped_endian = base_btf->swapped_endian; } /* +1 for empty string at offset 0 */ @@ -851,7 +1044,7 @@ struct btf *btf__new_empty_split(struct btf *base_btf) return libbpf_ptr(btf_new_empty(base_btf)); } -static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) +static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf, bool is_mmap) { struct btf *btf; int err; @@ -868,15 +1061,21 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) if (base_btf) { btf->base_btf = base_btf; btf->start_id = btf__type_cnt(base_btf); - btf->start_str_off = base_btf->hdr->str_len; + btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off; } - btf->raw_data = malloc(size); - if (!btf->raw_data) { - err = -ENOMEM; - goto done; + if (is_mmap) { + btf->raw_data = (void *)data; + btf->raw_data_is_mmap = true; + } else { + btf->raw_data = malloc(size); + if (!btf->raw_data) { + err = -ENOMEM; + goto done; + } + memcpy(btf->raw_data, data, size); } - memcpy(btf->raw_data, data, size); + btf->raw_size = size; btf->hdr = btf->raw_data; @@ -889,6 +1088,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) err = btf_parse_str_sec(btf); err = err ?: btf_parse_type_sec(btf); + err = err ?: btf_sanity_check(btf); if (err) goto done; @@ -903,56 +1103,46 @@ done: struct btf *btf__new(const void *data, __u32 size) { - return libbpf_ptr(btf_new(data, size, NULL)); + return libbpf_ptr(btf_new(data, size, NULL, false)); } -static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, - struct btf_ext **btf_ext) +struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf) +{ + return libbpf_ptr(btf_new(data, size, base_btf, false)); +} + +struct btf_elf_secs { + Elf_Data *btf_data; + Elf_Data *btf_ext_data; + Elf_Data *btf_base_data; +}; + +static int btf_find_elf_sections(Elf *elf, const char *path, struct btf_elf_secs *secs) { - Elf_Data *btf_data = NULL, *btf_ext_data = NULL; - int err = 0, fd = -1, idx = 0; - struct btf *btf = NULL; Elf_Scn *scn = NULL; - Elf *elf = NULL; + Elf_Data *data; GElf_Ehdr ehdr; size_t shstrndx; + int idx = 0; - if (elf_version(EV_CURRENT) == EV_NONE) { - pr_warn("failed to init libelf for %s\n", path); - return ERR_PTR(-LIBBPF_ERRNO__LIBELF); - } - - fd = open(path, O_RDONLY | O_CLOEXEC); - if (fd < 0) { - err = -errno; - pr_warn("failed to open %s: %s\n", path, strerror(errno)); - return ERR_PTR(err); - } - - err = -LIBBPF_ERRNO__FORMAT; - - elf = elf_begin(fd, ELF_C_READ, NULL); - if (!elf) { - pr_warn("failed to open %s as ELF file\n", path); - goto done; - } if (!gelf_getehdr(elf, &ehdr)) { pr_warn("failed to get EHDR from %s\n", path); - goto done; + goto err; } if (elf_getshdrstrndx(elf, &shstrndx)) { pr_warn("failed to get section names section index for %s\n", path); - goto done; + goto err; } if (!elf_rawdata(elf_getscn(elf, shstrndx), NULL)) { pr_warn("failed to get e_shstrndx from %s\n", path); - goto done; + goto err; } while ((scn = elf_nextscn(elf, scn)) != NULL) { + Elf_Data **field; GElf_Shdr sh; char *name; @@ -960,44 +1150,110 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, if (gelf_getshdr(scn, &sh) != &sh) { pr_warn("failed to get section(%d) header from %s\n", idx, path); - goto done; + goto err; } name = elf_strptr(elf, shstrndx, sh.sh_name); if (!name) { pr_warn("failed to get section(%d) name from %s\n", idx, path); - goto done; + goto err; } - if (strcmp(name, BTF_ELF_SEC) == 0) { - btf_data = elf_getdata(scn, 0); - if (!btf_data) { - pr_warn("failed to get section(%d, %s) data from %s\n", - idx, name, path); - goto done; - } - continue; - } else if (btf_ext && strcmp(name, BTF_EXT_ELF_SEC) == 0) { - btf_ext_data = elf_getdata(scn, 0); - if (!btf_ext_data) { - pr_warn("failed to get section(%d, %s) data from %s\n", - idx, name, path); - goto done; - } + + if (strcmp(name, BTF_ELF_SEC) == 0) + field = &secs->btf_data; + else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) + field = &secs->btf_ext_data; + else if (strcmp(name, BTF_BASE_ELF_SEC) == 0) + field = &secs->btf_base_data; + else continue; + + if (sh.sh_type != SHT_PROGBITS) { + pr_warn("unexpected section type (%d) of section(%d, %s) from %s\n", + sh.sh_type, idx, name, path); + goto err; + } + + data = elf_getdata(scn, 0); + if (!data) { + pr_warn("failed to get section(%d, %s) data from %s\n", + idx, name, path); + goto err; } + *field = data; + } + + return 0; + +err: + return -LIBBPF_ERRNO__FORMAT; +} + +static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, + struct btf_ext **btf_ext) +{ + struct btf_elf_secs secs = {}; + struct btf *dist_base_btf = NULL; + struct btf *btf = NULL; + int err = 0, fd = -1; + Elf *elf = NULL; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn("failed to init libelf for %s\n", path); + return ERR_PTR(-LIBBPF_ERRNO__LIBELF); } - err = 0; + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + err = -errno; + pr_warn("failed to open %s: %s\n", path, errstr(err)); + return ERR_PTR(err); + } - if (!btf_data) { - err = -ENOENT; + elf = elf_begin(fd, ELF_C_READ, NULL); + if (!elf) { + err = -LIBBPF_ERRNO__FORMAT; + pr_warn("failed to open %s as ELF file\n", path); goto done; } - btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf); - err = libbpf_get_error(btf); + + err = btf_find_elf_sections(elf, path, &secs); if (err) goto done; + if (!secs.btf_data) { + pr_warn("failed to find '%s' ELF section in %s\n", BTF_ELF_SEC, path); + err = -ENODATA; + goto done; + } + + if (secs.btf_base_data) { + dist_base_btf = btf_new(secs.btf_base_data->d_buf, secs.btf_base_data->d_size, + NULL, false); + if (IS_ERR(dist_base_btf)) { + err = PTR_ERR(dist_base_btf); + dist_base_btf = NULL; + goto done; + } + } + + btf = btf_new(secs.btf_data->d_buf, secs.btf_data->d_size, + dist_base_btf ?: base_btf, false); + if (IS_ERR(btf)) { + err = PTR_ERR(btf); + goto done; + } + if (dist_base_btf && base_btf) { + err = btf__relocate(btf, base_btf); + if (err) + goto done; + btf__free(dist_base_btf); + dist_base_btf = NULL; + } + + if (dist_base_btf) + btf->owns_base = true; + switch (gelf_getclass(elf)) { case ELFCLASS32: btf__set_pointer_size(btf, 4); @@ -1010,11 +1266,12 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, break; } - if (btf_ext && btf_ext_data) { - *btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); - err = libbpf_get_error(*btf_ext); - if (err) + if (btf_ext && secs.btf_ext_data) { + *btf_ext = btf_ext__new(secs.btf_ext_data->d_buf, secs.btf_ext_data->d_size); + if (IS_ERR(*btf_ext)) { + err = PTR_ERR(*btf_ext); goto done; + } } else if (btf_ext) { *btf_ext = NULL; } @@ -1028,6 +1285,7 @@ done: if (btf_ext) btf_ext__free(*btf_ext); + btf__free(dist_base_btf); btf__free(btf); return ERR_PTR(err); @@ -1052,7 +1310,7 @@ static struct btf *btf_parse_raw(const char *path, struct btf *base_btf) int err = 0; long sz; - f = fopen(path, "rb"); + f = fopen(path, "rbe"); if (!f) { err = -errno; goto err_out; @@ -1097,7 +1355,7 @@ static struct btf *btf_parse_raw(const char *path, struct btf *base_btf) } /* finally parse BTF data */ - btf = btf_new(data, sz, base_btf); + btf = btf_new(data, sz, base_btf, false); err_out: free(data); @@ -1116,6 +1374,37 @@ struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf) return libbpf_ptr(btf_parse_raw(path, base_btf)); } +static struct btf *btf_parse_raw_mmap(const char *path, struct btf *base_btf) +{ + struct stat st; + void *data; + struct btf *btf; + int fd, err; + + fd = open(path, O_RDONLY); + if (fd < 0) + return ERR_PTR(-errno); + + if (fstat(fd, &st) < 0) { + err = -errno; + close(fd); + return ERR_PTR(err); + } + + data = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0); + err = -errno; + close(fd); + + if (data == MAP_FAILED) + return ERR_PTR(err); + + btf = btf_new(data, st.st_size, base_btf, true); + if (IS_ERR(btf)) + munmap(data, st.st_size); + + return btf; +} + static struct btf *btf_parse(const char *path, struct btf *base_btf, struct btf_ext **btf_ext) { struct btf *btf; @@ -1145,7 +1434,9 @@ 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, char *log_buf, size_t log_sz, __u32 log_level) +int btf_load_into_kernel(struct btf *btf, + char *log_buf, size_t log_sz, __u32 log_level, + int token_fd) { LIBBPF_OPTS(bpf_btf_load_opts, opts); __u32 buf_sz = 0, raw_size; @@ -1195,6 +1486,10 @@ retry_load: opts.log_level = log_level; } + opts.token_fd = token_fd; + if (token_fd) + opts.btf_flags |= BPF_F_TOKEN_FD; + btf->fd = bpf_btf_load(raw_data, raw_size, &opts); if (btf->fd < 0) { /* time to turn on verbose mode and try again */ @@ -1209,7 +1504,7 @@ retry_load: goto retry_load; err = -errno; - pr_warn("BTF loading error: %d\n", err); + pr_warn("BTF loading error: %s\n", errstr(err)); /* don't print out contents of custom log_buf */ if (!log_buf && buf[0]) pr_warn("-- BEGIN BTF LOAD LOG ---\n%s\n-- END BTF LOAD LOG --\n", buf); @@ -1222,7 +1517,7 @@ done: int btf__load_into_kernel(struct btf *btf) { - return btf_load_into_kernel(btf, NULL, 0, 0); + return btf_load_into_kernel(btf, NULL, 0, 0, 0); } int btf__fd(const struct btf *btf) @@ -1336,9 +1631,9 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) void *ptr; int err; - /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so + /* we won't know btf_size until we call bpf_btf_get_info_by_fd(). so * let's start with a sane default - 4KiB here - and resize it only if - * bpf_obj_get_info_by_fd() needs a bigger buffer. + * bpf_btf_get_info_by_fd() needs a bigger buffer. */ last_size = 4096; ptr = malloc(last_size); @@ -1348,7 +1643,7 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) memset(&btf_info, 0, sizeof(btf_info)); btf_info.btf = ptr_to_u64(ptr); btf_info.btf_size = last_size; - err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + err = bpf_btf_get_info_by_fd(btf_fd, &btf_info, &len); if (!err && btf_info.btf_size > last_size) { void *temp_ptr; @@ -1366,7 +1661,7 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) btf_info.btf = ptr_to_u64(ptr); btf_info.btf_size = last_size; - err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); + err = bpf_btf_get_info_by_fd(btf_fd, &btf_info, &len); } if (err || btf_info.btf_size > last_size) { @@ -1374,19 +1669,25 @@ struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) goto exit_free; } - btf = btf_new(ptr, btf_info.btf_size, base_btf); + btf = btf_new(ptr, btf_info.btf_size, base_btf, false); exit_free: free(ptr); return btf; } -struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf) +struct btf *btf_load_from_kernel(__u32 id, struct btf *base_btf, int token_fd) { struct btf *btf; int btf_fd; + LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts); - btf_fd = bpf_btf_get_fd_by_id(id); + if (token_fd) { + opts.open_flags |= BPF_F_TOKEN_FD; + opts.token_fd = token_fd; + } + + btf_fd = bpf_btf_get_fd_by_id_opts(id, &opts); if (btf_fd < 0) return libbpf_err_ptr(-errno); @@ -1396,6 +1697,11 @@ struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf) return libbpf_ptr(btf); } +struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf) +{ + return btf_load_from_kernel(id, base_btf, 0); +} + struct btf *btf__load_from_kernel_by_id(__u32 id) { return btf__load_from_kernel_by_id_split(id, NULL); @@ -1403,10 +1709,8 @@ struct btf *btf__load_from_kernel_by_id(__u32 id) static void btf_invalidate_raw_data(struct btf *btf) { - if (btf->raw_data) { - free(btf->raw_data); - btf->raw_data = NULL; - } + if (btf->raw_data) + btf_free_raw_data(btf); if (btf->raw_data_swapped) { free(btf->raw_data_swapped); btf->raw_data_swapped = NULL; @@ -1556,9 +1860,8 @@ struct btf_pipe { struct hashmap *str_off_map; /* map string offsets from src to dst */ }; -static int btf_rewrite_str(__u32 *str_off, void *ctx) +static int btf_rewrite_str(struct btf_pipe *p, __u32 *str_off) { - struct btf_pipe *p = ctx; long mapped_off; int off, err; @@ -1588,10 +1891,11 @@ static int btf_rewrite_str(__u32 *str_off, void *ctx) return 0; } -int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_type *src_type) +static int btf_add_type(struct btf_pipe *p, const struct btf_type *src_type) { - struct btf_pipe p = { .src = src_btf, .dst = btf }; + struct btf_field_iter it; struct btf_type *t; + __u32 *str_off; int sz, err; sz = btf_type_size(src_type); @@ -1599,35 +1903,33 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t return libbpf_err(sz); /* deconstruct BTF, if necessary, and invalidate raw_data */ - if (btf_ensure_modifiable(btf)) + if (btf_ensure_modifiable(p->dst)) return libbpf_err(-ENOMEM); - t = btf_add_type_mem(btf, sz); + t = btf_add_type_mem(p->dst, sz); if (!t) return libbpf_err(-ENOMEM); memcpy(t, src_type, sz); - err = btf_type_visit_str_offs(t, btf_rewrite_str, &p); + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS); if (err) return libbpf_err(err); - return btf_commit_type(btf, sz); + while ((str_off = btf_field_iter_next(&it))) { + err = btf_rewrite_str(p, str_off); + if (err) + return libbpf_err(err); + } + + return btf_commit_type(p->dst, sz); } -static int btf_rewrite_type_ids(__u32 *type_id, void *ctx) +int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_type *src_type) { - struct btf *btf = ctx; - - if (!*type_id) /* nothing to do for VOID references */ - return 0; + struct btf_pipe p = { .src = src_btf, .dst = btf }; - /* we haven't updated btf's type count yet, so - * btf->start_id + btf->nr_types - 1 is the type ID offset we should - * add to all newly added BTF types - */ - *type_id += btf->start_id + btf->nr_types - 1; - return 0; + return btf_add_type(&p, src_type); } static size_t btf_dedup_identity_hash_fn(long key, void *ctx); @@ -1675,6 +1977,9 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) memcpy(t, src_btf->types_data, data_sz); for (i = 0; i < cnt; i++) { + struct btf_field_iter it; + __u32 *type_id, *str_off; + sz = btf_type_size(t); if (sz < 0) { /* unlikely, has to be corrupted src_btf */ @@ -1686,15 +1991,31 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) *off = t - btf->types_data; /* add, dedup, and remap strings referenced by this BTF type */ - err = btf_type_visit_str_offs(t, btf_rewrite_str, &p); + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS); if (err) goto err_out; + while ((str_off = btf_field_iter_next(&it))) { + err = btf_rewrite_str(&p, str_off); + if (err) + goto err_out; + } /* remap all type IDs referenced from this BTF type */ - err = btf_type_visit_type_ids(t, btf_rewrite_type_ids, btf); + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); if (err) goto err_out; + while ((type_id = btf_field_iter_next(&it))) { + if (!*type_id) /* nothing to do for VOID references */ + continue; + + /* we haven't updated btf's type count yet, so + * btf->start_id + btf->nr_types - 1 is the type ID offset we should + * add to all newly added BTF types + */ + *type_id += btf->start_id + btf->nr_types - 1; + } + /* go to next type data and type offset index entry */ t += sz; off++; @@ -1835,7 +2156,7 @@ static int validate_type_id(int id) } /* generic append function for PTR, TYPEDEF, CONST/VOLATILE/RESTRICT */ -static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id) +static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref_type_id, int kflag) { struct btf_type *t; int sz, name_off = 0; @@ -1858,7 +2179,7 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref } t->name_off = name_off; - t->info = btf_type_info(kind, 0, 0); + t->info = btf_type_info(kind, 0, kflag); t->type = ref_type_id; return btf_commit_type(btf, sz); @@ -1873,7 +2194,7 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref */ int btf__add_ptr(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_PTR, NULL, ref_type_id, 0); } /* @@ -2251,7 +2572,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind) struct btf_type *t; int id; - id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0); + id = btf_add_ref_kind(btf, BTF_KIND_FWD, name, 0, 0); if (id <= 0) return id; t = btf_type_by_id(btf, id); @@ -2281,7 +2602,7 @@ int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id) if (!name || !name[0]) return libbpf_err(-EINVAL); - return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id, 0); } /* @@ -2293,7 +2614,7 @@ int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id) */ int btf__add_volatile(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_VOLATILE, NULL, ref_type_id, 0); } /* @@ -2305,7 +2626,7 @@ int btf__add_volatile(struct btf *btf, int ref_type_id) */ int btf__add_const(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_CONST, NULL, ref_type_id, 0); } /* @@ -2317,7 +2638,7 @@ int btf__add_const(struct btf *btf, int ref_type_id) */ int btf__add_restrict(struct btf *btf, int ref_type_id) { - return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_RESTRICT, NULL, ref_type_id, 0); } /* @@ -2333,7 +2654,24 @@ int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id) if (!value || !value[0]) return libbpf_err(-EINVAL); - return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id); + return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id, 0); +} + +/* + * Append new BTF_KIND_TYPE_TAG type with: + * - *value*, non-empty/non-NULL tag value; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * Set info->kflag to 1, indicating this tag is an __attribute__ + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_type_attr(struct btf *btf, const char *value, int ref_type_id) +{ + if (!value || !value[0]) + return libbpf_err(-EINVAL); + + return btf_add_ref_kind(btf, BTF_KIND_TYPE_TAG, value, ref_type_id, 1); } /* @@ -2355,7 +2693,7 @@ int btf__add_func(struct btf *btf, const char *name, linkage != BTF_FUNC_EXTERN) return libbpf_err(-EINVAL); - id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id); + id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id, 0); if (id > 0) { struct btf_type *t = btf_type_by_id(btf, id); @@ -2590,18 +2928,8 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ return 0; } -/* - * Append new BTF_KIND_DECL_TAG type with: - * - *value* - non-empty/non-NULL string; - * - *ref_type_id* - referenced type ID, it might not exist yet; - * - *component_idx* - -1 for tagging reference type, otherwise struct/union - * member or function argument index; - * Returns: - * - >0, type ID of newly added BTF type; - * - <0, on error. - */ -int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, - int component_idx) +static int btf_add_decl_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx, int kflag) { struct btf_type *t; int sz, value_off; @@ -2625,14 +2953,47 @@ int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, return value_off; t->name_off = value_off; - t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false); + t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, kflag); t->type = ref_type_id; btf_decl_tag(t)->component_idx = component_idx; return btf_commit_type(btf, sz); } -struct btf_ext_sec_setup_param { +/* + * Append new BTF_KIND_DECL_TAG type with: + * - *value* - non-empty/non-NULL string; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * - *component_idx* - -1 for tagging reference type, otherwise struct/union + * member or function argument index; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx) +{ + return btf_add_decl_tag(btf, value, ref_type_id, component_idx, 0); +} + +/* + * Append new BTF_KIND_DECL_TAG type with: + * - *value* - non-empty/non-NULL string; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * - *component_idx* - -1 for tagging reference type, otherwise struct/union + * member or function argument index; + * Set info->kflag to 1, indicating this tag is an __attribute__ + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_decl_attr(struct btf *btf, const char *value, int ref_type_id, + int component_idx) +{ + return btf_add_decl_tag(btf, value, ref_type_id, component_idx, 1); +} + +struct btf_ext_sec_info_param { __u32 off; __u32 len; __u32 min_rec_size; @@ -2640,14 +3001,20 @@ struct btf_ext_sec_setup_param { const char *desc; }; -static int btf_ext_setup_info(struct btf_ext *btf_ext, - struct btf_ext_sec_setup_param *ext_sec) +/* + * Parse a single info subsection of the BTF.ext info data: + * - validate subsection structure and elements + * - save info subsection start and sizing details in struct btf_ext + * - endian-independent operation, for calling before byte-swapping + */ +static int btf_ext_parse_sec_info(struct btf_ext *btf_ext, + struct btf_ext_sec_info_param *ext_sec, + bool is_native) { const struct btf_ext_info_sec *sinfo; struct btf_ext_info *ext_info; __u32 info_left, record_size; size_t sec_cnt = 0; - /* The start of the info sec (including the __u32 record_size). */ void *info; if (ext_sec->len == 0) @@ -2659,6 +3026,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return -EINVAL; } + /* The start of the info sec (including the __u32 record_size). */ info = btf_ext->data + btf_ext->hdr->hdr_len + ext_sec->off; info_left = ext_sec->len; @@ -2674,9 +3042,13 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return -EINVAL; } - /* The record size needs to meet the minimum standard */ - record_size = *(__u32 *)info; + /* The record size needs to meet either the minimum standard or, when + * handling non-native endianness data, the exact standard so as + * to allow safe byte-swapping. + */ + record_size = is_native ? *(__u32 *)info : bswap_32(*(__u32 *)info); if (record_size < ext_sec->min_rec_size || + (!is_native && record_size != ext_sec->min_rec_size) || record_size & 0x03) { pr_debug("%s section in .BTF.ext has invalid record size %u\n", ext_sec->desc, record_size); @@ -2688,7 +3060,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, /* If no records, return failure now so .BTF.ext won't be used. */ if (!info_left) { - pr_debug("%s section in .BTF.ext has no records", ext_sec->desc); + pr_debug("%s section in .BTF.ext has no records\n", ext_sec->desc); return -EINVAL; } @@ -2703,7 +3075,7 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return -EINVAL; } - num_records = sinfo->num_info; + num_records = is_native ? sinfo->num_info : bswap_32(sinfo->num_info); if (num_records == 0) { pr_debug("%s section has incorrect num_records in .BTF.ext\n", ext_sec->desc); @@ -2731,64 +3103,157 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, return 0; } -static int btf_ext_setup_func_info(struct btf_ext *btf_ext) +/* Parse all info secs in the BTF.ext info data */ +static int btf_ext_parse_info(struct btf_ext *btf_ext, bool is_native) { - struct btf_ext_sec_setup_param param = { + struct btf_ext_sec_info_param func_info = { .off = btf_ext->hdr->func_info_off, .len = btf_ext->hdr->func_info_len, .min_rec_size = sizeof(struct bpf_func_info_min), .ext_info = &btf_ext->func_info, .desc = "func_info" }; - - return btf_ext_setup_info(btf_ext, ¶m); -} - -static int btf_ext_setup_line_info(struct btf_ext *btf_ext) -{ - struct btf_ext_sec_setup_param param = { + struct btf_ext_sec_info_param line_info = { .off = btf_ext->hdr->line_info_off, .len = btf_ext->hdr->line_info_len, .min_rec_size = sizeof(struct bpf_line_info_min), .ext_info = &btf_ext->line_info, .desc = "line_info", }; - - return btf_ext_setup_info(btf_ext, ¶m); -} - -static int btf_ext_setup_core_relos(struct btf_ext *btf_ext) -{ - struct btf_ext_sec_setup_param param = { - .off = btf_ext->hdr->core_relo_off, - .len = btf_ext->hdr->core_relo_len, + struct btf_ext_sec_info_param core_relo = { .min_rec_size = sizeof(struct bpf_core_relo), .ext_info = &btf_ext->core_relo_info, .desc = "core_relo", }; + int err; + + err = btf_ext_parse_sec_info(btf_ext, &func_info, is_native); + if (err) + return err; + + err = btf_ext_parse_sec_info(btf_ext, &line_info, is_native); + if (err) + return err; + + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + return 0; /* skip core relos parsing */ + + core_relo.off = btf_ext->hdr->core_relo_off; + core_relo.len = btf_ext->hdr->core_relo_len; + err = btf_ext_parse_sec_info(btf_ext, &core_relo, is_native); + if (err) + return err; + + return 0; +} - return btf_ext_setup_info(btf_ext, ¶m); +/* Swap byte-order of BTF.ext header with any endianness */ +static void btf_ext_bswap_hdr(struct btf_ext_header *h) +{ + bool is_native = h->magic == BTF_MAGIC; + __u32 hdr_len; + + hdr_len = is_native ? h->hdr_len : bswap_32(h->hdr_len); + + h->magic = bswap_16(h->magic); + h->hdr_len = bswap_32(h->hdr_len); + h->func_info_off = bswap_32(h->func_info_off); + h->func_info_len = bswap_32(h->func_info_len); + h->line_info_off = bswap_32(h->line_info_off); + h->line_info_len = bswap_32(h->line_info_len); + + if (hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + return; + + h->core_relo_off = bswap_32(h->core_relo_off); + h->core_relo_len = bswap_32(h->core_relo_len); +} + +/* Swap byte-order of generic info subsection */ +static void btf_ext_bswap_info_sec(void *info, __u32 len, bool is_native, + info_rec_bswap_fn bswap_fn) +{ + struct btf_ext_info_sec *sec; + __u32 info_left, rec_size, *rs; + + if (len == 0) + return; + + rs = info; /* info record size */ + rec_size = is_native ? *rs : bswap_32(*rs); + *rs = bswap_32(*rs); + + sec = info + sizeof(__u32); /* info sec #1 */ + info_left = len - sizeof(__u32); + while (info_left) { + unsigned int sec_hdrlen = sizeof(struct btf_ext_info_sec); + __u32 i, num_recs; + void *p; + + num_recs = is_native ? sec->num_info : bswap_32(sec->num_info); + sec->sec_name_off = bswap_32(sec->sec_name_off); + sec->num_info = bswap_32(sec->num_info); + p = sec->data; /* info rec #1 */ + for (i = 0; i < num_recs; i++, p += rec_size) + bswap_fn(p); + sec = p; + info_left -= sec_hdrlen + (__u64)rec_size * num_recs; + } +} + +/* + * Swap byte-order of all info data in a BTF.ext section + * - requires BTF.ext hdr in native endianness + */ +static void btf_ext_bswap_info(struct btf_ext *btf_ext, void *data) +{ + const bool is_native = btf_ext->swapped_endian; + const struct btf_ext_header *h = data; + void *info; + + /* Swap func_info subsection byte-order */ + info = data + h->hdr_len + h->func_info_off; + btf_ext_bswap_info_sec(info, h->func_info_len, is_native, + (info_rec_bswap_fn)bpf_func_info_bswap); + + /* Swap line_info subsection byte-order */ + info = data + h->hdr_len + h->line_info_off; + btf_ext_bswap_info_sec(info, h->line_info_len, is_native, + (info_rec_bswap_fn)bpf_line_info_bswap); + + /* Swap core_relo subsection byte-order (if present) */ + if (h->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + return; + + info = data + h->hdr_len + h->core_relo_off; + btf_ext_bswap_info_sec(info, h->core_relo_len, is_native, + (info_rec_bswap_fn)bpf_core_relo_bswap); } -static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) +/* Parse hdr data and info sections: check and convert to native endianness */ +static int btf_ext_parse(struct btf_ext *btf_ext) { - const struct btf_ext_header *hdr = (struct btf_ext_header *)data; + __u32 hdr_len, data_size = btf_ext->data_size; + struct btf_ext_header *hdr = btf_ext->hdr; + bool swapped_endian = false; + int err; - if (data_size < offsetofend(struct btf_ext_header, hdr_len) || - data_size < hdr->hdr_len) { - pr_debug("BTF.ext header not found"); + if (data_size < offsetofend(struct btf_ext_header, hdr_len)) { + pr_debug("BTF.ext header too short\n"); return -EINVAL; } + hdr_len = hdr->hdr_len; if (hdr->magic == bswap_16(BTF_MAGIC)) { - pr_warn("BTF.ext in non-native endianness is not supported\n"); - return -ENOTSUP; + swapped_endian = true; + hdr_len = bswap_32(hdr_len); } else if (hdr->magic != BTF_MAGIC) { pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic); return -EINVAL; } - if (hdr->version != BTF_VERSION) { + /* Ensure known version of structs, current BTF_VERSION == 1 */ + if (hdr->version != 1) { pr_debug("Unsupported BTF.ext version:%u\n", hdr->version); return -ENOTSUP; } @@ -2798,11 +3263,39 @@ static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) return -ENOTSUP; } - if (data_size == hdr->hdr_len) { + if (data_size < hdr_len) { + pr_debug("BTF.ext header not found\n"); + return -EINVAL; + } else if (data_size == hdr_len) { pr_debug("BTF.ext has no data\n"); return -EINVAL; } + /* Verify mandatory hdr info details present */ + if (hdr_len < offsetofend(struct btf_ext_header, line_info_len)) { + pr_warn("BTF.ext header missing func_info, line_info\n"); + return -EINVAL; + } + + /* Keep hdr native byte-order in memory for introspection */ + if (swapped_endian) + btf_ext_bswap_hdr(btf_ext->hdr); + + /* Validate info subsections and cache key metadata */ + err = btf_ext_parse_info(btf_ext, !swapped_endian); + if (err) + return err; + + /* Keep infos native byte-order in memory for introspection */ + if (swapped_endian) + btf_ext_bswap_info(btf_ext, btf_ext->data); + + /* + * Set btf_ext->swapped_endian only after all header and info data has + * been swapped, helping bswap functions determine if their data are + * in native byte-order when called. + */ + btf_ext->swapped_endian = swapped_endian; return 0; } @@ -2814,6 +3307,7 @@ void btf_ext__free(struct btf_ext *btf_ext) free(btf_ext->line_info.sec_idxs); free(btf_ext->core_relo_info.sec_idxs); free(btf_ext->data); + free(btf_ext->data_swapped); free(btf_ext); } @@ -2834,29 +3328,7 @@ struct btf_ext *btf_ext__new(const __u8 *data, __u32 size) } memcpy(btf_ext->data, data, size); - err = btf_ext_parse_hdr(btf_ext->data, size); - if (err) - goto done; - - if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) { - err = -EINVAL; - goto done; - } - - err = btf_ext_setup_func_info(btf_ext); - if (err) - goto done; - - err = btf_ext_setup_line_info(btf_ext); - if (err) - goto done; - - if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) - goto done; /* skip core relos parsing */ - - err = btf_ext_setup_core_relos(btf_ext); - if (err) - goto done; + err = btf_ext_parse(btf_ext); done: if (err) { @@ -2867,10 +3339,65 @@ done: return btf_ext; } -const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size) +static void *btf_ext_raw_data(const struct btf_ext *btf_ext_ro, bool swap_endian) { + struct btf_ext *btf_ext = (struct btf_ext *)btf_ext_ro; + const __u32 data_sz = btf_ext->data_size; + void *data; + + /* Return native data (always present) or swapped data if present */ + if (!swap_endian) + return btf_ext->data; + else if (btf_ext->data_swapped) + return btf_ext->data_swapped; + + /* Recreate missing swapped data, then cache and return */ + data = calloc(1, data_sz); + if (!data) + return NULL; + memcpy(data, btf_ext->data, data_sz); + + btf_ext_bswap_info(btf_ext, data); + btf_ext_bswap_hdr(data); + btf_ext->data_swapped = data; + return data; +} + +const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size) +{ + void *data; + + data = btf_ext_raw_data(btf_ext, btf_ext->swapped_endian); + if (!data) + return errno = ENOMEM, NULL; + *size = btf_ext->data_size; - return btf_ext->data; + return data; +} + +__attribute__((alias("btf_ext__raw_data"))) +const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size); + +enum btf_endianness btf_ext__endianness(const struct btf_ext *btf_ext) +{ + if (is_host_big_endian()) + return btf_ext->swapped_endian ? BTF_LITTLE_ENDIAN : BTF_BIG_ENDIAN; + else + return btf_ext->swapped_endian ? BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN; +} + +int btf_ext__set_endianness(struct btf_ext *btf_ext, enum btf_endianness endian) +{ + if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN) + return libbpf_err(-EINVAL); + + btf_ext->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN); + + if (!btf_ext->swapped_endian) { + free(btf_ext->data_swapped); + btf_ext->data_swapped = NULL; + } + return 0; } struct btf_dedup; @@ -3034,7 +3561,7 @@ int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts) d = btf_dedup_new(btf, opts); if (IS_ERR(d)) { - pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d)); + pr_debug("btf_dedup_new failed: %ld\n", PTR_ERR(d)); return libbpf_err(-EINVAL); } @@ -3045,42 +3572,42 @@ int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts) err = btf_dedup_prep(d); if (err) { - pr_debug("btf_dedup_prep failed:%d\n", err); + pr_debug("btf_dedup_prep failed: %s\n", errstr(err)); goto done; } err = btf_dedup_strings(d); if (err < 0) { - pr_debug("btf_dedup_strings failed:%d\n", err); + pr_debug("btf_dedup_strings failed: %s\n", errstr(err)); goto done; } err = btf_dedup_prim_types(d); if (err < 0) { - pr_debug("btf_dedup_prim_types failed:%d\n", err); + pr_debug("btf_dedup_prim_types failed: %s\n", errstr(err)); goto done; } err = btf_dedup_struct_types(d); if (err < 0) { - pr_debug("btf_dedup_struct_types failed:%d\n", err); + pr_debug("btf_dedup_struct_types failed: %s\n", errstr(err)); goto done; } err = btf_dedup_resolve_fwds(d); if (err < 0) { - pr_debug("btf_dedup_resolve_fwds failed:%d\n", err); + pr_debug("btf_dedup_resolve_fwds failed: %s\n", errstr(err)); goto done; } err = btf_dedup_ref_types(d); if (err < 0) { - pr_debug("btf_dedup_ref_types failed:%d\n", err); + pr_debug("btf_dedup_ref_types failed: %s\n", errstr(err)); goto done; } err = btf_dedup_compact_types(d); if (err < 0) { - pr_debug("btf_dedup_compact_types failed:%d\n", err); + pr_debug("btf_dedup_compact_types failed: %s\n", errstr(err)); goto done; } err = btf_dedup_remap_types(d); if (err < 0) { - pr_debug("btf_dedup_remap_types failed:%d\n", err); + pr_debug("btf_dedup_remap_types failed: %s\n", errstr(err)); goto done; } @@ -3128,7 +3655,7 @@ struct btf_dedup { struct strset *strs_set; }; -static long hash_combine(long h, long value) +static unsigned long hash_combine(unsigned long h, unsigned long value) { return h * 31 + value; } @@ -3266,11 +3793,19 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_visit_fn fn, void * int i, r; for (i = 0; i < d->btf->nr_types; i++) { + struct btf_field_iter it; struct btf_type *t = btf_type_by_id(d->btf, d->btf->start_id + i); + __u32 *str_off; - r = btf_type_visit_str_offs(t, fn, ctx); + r = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS); if (r) return r; + + while ((str_off = btf_field_iter_next(&it))) { + r = fn(str_off, ctx); + if (r) + return r; + } } if (!d->btf_ext) @@ -3366,6 +3901,20 @@ err_out: return err; } +/* + * Calculate type signature hash of TYPEDEF, ignoring referenced type IDs, + * as referenced type IDs equivalence is established separately during type + * graph equivalence check algorithm. + */ +static long btf_hash_typedef(struct btf_type *t) +{ + long h; + + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info); + return h; +} + static long btf_hash_common(struct btf_type *t) { long h; @@ -3383,6 +3932,13 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) t1->size == t2->size; } +/* Check structural compatibility of two TYPEDEF. */ +static bool btf_equal_typedef(struct btf_type *t1, struct btf_type *t2) +{ + return t1->name_off == t2->name_off && + t1->info == t2->info; +} + /* Calculate type signature hash of INT or TAG. */ static long btf_hash_int_decl_tag(struct btf_type *t) { @@ -3870,46 +4426,109 @@ static inline __u16 btf_fwd_kind(struct btf_type *t) return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT; } -/* Check if given two types are identical ARRAY definitions */ -static bool btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2) +static bool btf_dedup_identical_types(struct btf_dedup *d, __u32 id1, __u32 id2, int depth) { struct btf_type *t1, *t2; + int k1, k2; +recur: + if (depth <= 0) + return false; t1 = btf_type_by_id(d->btf, id1); t2 = btf_type_by_id(d->btf, id2); - if (!btf_is_array(t1) || !btf_is_array(t2)) + + k1 = btf_kind(t1); + k2 = btf_kind(t2); + if (k1 != k2) return false; - return btf_equal_array(t1, t2); -} + switch (k1) { + case BTF_KIND_UNKN: /* VOID */ + return true; + case BTF_KIND_INT: + return btf_equal_int_tag(t1, t2); + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + return btf_compat_enum(t1, t2); + case BTF_KIND_FWD: + case BTF_KIND_FLOAT: + return btf_equal_common(t1, t2); + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_TYPE_TAG: + if (t1->info != t2->info || t1->name_off != t2->name_off) + return false; + id1 = t1->type; + id2 = t2->type; + goto recur; + case BTF_KIND_ARRAY: { + struct btf_array *a1, *a2; -/* Check if given two types are identical STRUCT/UNION definitions */ -static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id2) -{ - const struct btf_member *m1, *m2; - struct btf_type *t1, *t2; - int n, i; + if (!btf_compat_array(t1, t2)) + return false; - t1 = btf_type_by_id(d->btf, id1); - t2 = btf_type_by_id(d->btf, id2); + a1 = btf_array(t1); + a2 = btf_array(t1); - if (!btf_is_composite(t1) || btf_kind(t1) != btf_kind(t2)) - return false; + if (a1->index_type != a2->index_type && + !btf_dedup_identical_types(d, a1->index_type, a2->index_type, depth - 1)) + return false; - if (!btf_shallow_equal_struct(t1, t2)) - return false; + if (a1->type != a2->type && + !btf_dedup_identical_types(d, a1->type, a2->type, depth - 1)) + return false; - m1 = btf_members(t1); - m2 = btf_members(t2); - for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) { - if (m1->type != m2->type && - !btf_dedup_identical_arrays(d, m1->type, m2->type) && - !btf_dedup_identical_structs(d, m1->type, m2->type)) + return true; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m1, *m2; + int i, n; + + if (!btf_shallow_equal_struct(t1, t2)) + return false; + + m1 = btf_members(t1); + m2 = btf_members(t2); + for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) { + if (m1->type == m2->type) + continue; + if (!btf_dedup_identical_types(d, m1->type, m2->type, depth - 1)) + return false; + } + return true; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p1, *p2; + int i, n; + + if (!btf_compat_fnproto(t1, t2)) + return false; + + if (t1->type != t2->type && + !btf_dedup_identical_types(d, t1->type, t2->type, depth - 1)) return false; + + p1 = btf_params(t1); + p2 = btf_params(t2); + for (i = 0, n = btf_vlen(t1); i < n; i++, p1++, p2++) { + if (p1->type == p2->type) + continue; + if (!btf_dedup_identical_types(d, p1->type, p2->type, depth - 1)) + return false; + } + return true; + } + default: + return false; } - return true; } + /* * Check equivalence of BTF type graph formed by candidate struct/union (we'll * call it "candidate graph" in this description for brevity) to a type graph @@ -3927,7 +4546,7 @@ static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id * and canonical graphs are not compatible structurally, whole graphs are * incompatible. If types are structurally equivalent (i.e., all information * except referenced type IDs is exactly the same), a mapping from `canon_id` to - * a `cand_id` is recored in hypothetical mapping (`btf_dedup->hypot_map`). + * a `cand_id` is recoded in hypothetical mapping (`btf_dedup->hypot_map`). * If a type references other types, then those referenced types are checked * for equivalence recursively. * @@ -3965,7 +4584,7 @@ static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id * consists of portions of the graph that come from multiple compilation units. * This is due to the fact that types within single compilation unit are always * deduplicated and FWDs are already resolved, if referenced struct/union - * definiton is available. So, if we had unresolved FWD and found corresponding + * definition is available. So, if we had unresolved FWD and found corresponding * STRUCT/UNION, they will be from different compilation units. This * consequently means that when we "link" FWD to corresponding STRUCT/UNION, * type graph will likely have at least two different BTF types that describe @@ -4028,19 +4647,13 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, * different fields within the *same* struct. This breaks type * equivalence check, which makes an assumption that candidate * types sub-graph has a consistent and deduped-by-compiler - * types within a single CU. So work around that by explicitly - * allowing identical array types here. - */ - 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. + * types within a single CU. And similar situation can happen + * with struct/union sometimes, and event with pointers. + * So accommodate cases like this doing a structural + * comparison recursively, but avoiding being stuck in endless + * loops by limiting the depth up to which we check. */ - if (btf_dedup_identical_structs(d, hypot_type_id, cand_id)) + if (btf_dedup_identical_types(d, hypot_type_id, cand_id, 16)) return 1; return 0; } @@ -4252,13 +4865,30 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d) } } +static inline long btf_hash_by_kind(struct btf_type *t, __u16 kind) +{ + if (kind == BTF_KIND_TYPEDEF) + return btf_hash_typedef(t); + else + return btf_hash_struct(t); +} + +static inline bool btf_equal_by_kind(struct btf_type *t1, struct btf_type *t2, __u16 kind) +{ + if (kind == BTF_KIND_TYPEDEF) + return btf_equal_typedef(t1, t2); + else + return btf_shallow_equal_struct(t1, t2); +} + /* - * Deduplicate struct/union types. + * Deduplicate struct/union and typedef types. * * For each struct/union type its type signature hash is calculated, taking * into account type's name, size, number, order and names of fields, but * ignoring type ID's referenced from fields, because they might not be deduped - * completely until after reference types deduplication phase. This type hash + * completely until after reference types deduplication phase. For each typedef + * type, the hash is computed based on the type’s name and size. This type hash * is used to iterate over all potential canonical types, sharing same hash. * For each canonical candidate we check whether type graphs that they form * (through referenced types in fields and so on) are equivalent using algorithm @@ -4290,18 +4920,20 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) t = btf_type_by_id(d->btf, type_id); kind = btf_kind(t); - if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) + if (kind != BTF_KIND_STRUCT && + kind != BTF_KIND_UNION && + kind != BTF_KIND_TYPEDEF) return 0; - h = btf_hash_struct(t); + h = btf_hash_by_kind(t, kind); for_each_dedup_cand(d, hash_entry, h) { __u32 cand_id = hash_entry->value; int eq; /* * Even though btf_dedup_is_equiv() checks for - * btf_shallow_equal_struct() internally when checking two - * structs (unions) for equivalence, we need to guard here + * btf_equal_by_kind() internally when checking two + * structs (unions) or typedefs for equivalence, we need to guard here * from picking matching FWD type as a dedup candidate. * This can happen due to hash collision. In such case just * relying on btf_dedup_is_equiv() would lead to potentially @@ -4309,7 +4941,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) * FWD and compatible STRUCT/UNION are considered equivalent. */ cand_type = btf_type_by_id(d->btf, cand_id); - if (!btf_shallow_equal_struct(t, cand_type)) + if (!btf_equal_by_kind(t, cand_type, kind)) continue; btf_dedup_clear_hypot_map(d); @@ -4347,18 +4979,18 @@ static int btf_dedup_struct_types(struct btf_dedup *d) /* * Deduplicate reference type. * - * Once all primitive and struct/union types got deduplicated, we can easily + * Once all primitive, struct/union and typedef types got deduplicated, we can easily * deduplicate all other (reference) BTF types. This is done in two steps: * * 1. Resolve all referenced type IDs into their canonical type IDs. This - * resolution can be done either immediately for primitive or struct/union types - * (because they were deduped in previous two phases) or recursively for + * resolution can be done either immediately for primitive, struct/union, and typedef + * types (because they were deduped in previous two phases) or recursively for * reference types. Recursion will always terminate at either primitive or - * struct/union type, at which point we can "unwind" chain of reference types - * one by one. There is no danger of encountering cycles because in C type - * system the only way to form type cycle is through struct/union, so any chain - * of reference types, even those taking part in a type cycle, will inevitably - * reach struct/union at some point. + * struct/union and typedef types, at which point we can "unwind" chain of reference + * types one by one. There is no danger of encountering cycles in C, as the only way to + * form a type cycle is through struct or union types. Go can form such cycles through + * typedef. Thus, any chain of reference types, even those taking part in a type cycle, + * will inevitably reach a struct/union or typedef type at some point. * * 2. Once all referenced type IDs are resolved into canonical ones, BTF type * becomes "stable", in the sense that no further deduplication will cause @@ -4390,7 +5022,6 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: case BTF_KIND_PTR: - case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_TYPE_TAG: ref_type_id = btf_dedup_ref_type(d, t->type); @@ -4732,10 +5363,23 @@ static int btf_dedup_remap_types(struct btf_dedup *d) for (i = 0; i < d->btf->nr_types; i++) { struct btf_type *t = btf_type_by_id(d->btf, d->btf->start_id + i); + struct btf_field_iter it; + __u32 *type_id; - r = btf_type_visit_type_ids(t, btf_dedup_remap_type_id, d); + r = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); if (r) return r; + + while ((type_id = btf_field_iter_next(&it))) { + __u32 resolved_id, new_id; + + resolved_id = resolve_type_id(d, *type_id); + new_id = d->hypot_map[resolved_id]; + if (new_id > BTF_MAX_NR_TYPES) + return -EINVAL; + + *type_id = new_id; + } } if (!d->btf_ext) @@ -4754,10 +5398,9 @@ static int btf_dedup_remap_types(struct btf_dedup *d) */ struct btf *btf__load_vmlinux_btf(void) { + const char *sysfs_btf_path = "/sys/kernel/btf/vmlinux"; + /* fall back locations, trying to find vmlinux on disk */ const char *locations[] = { - /* try canonical vmlinux BTF through sysfs first */ - "/sys/kernel/btf/vmlinux", - /* fall back to trying to find vmlinux on disk otherwise */ "/boot/vmlinux-%1$s", "/lib/modules/%1$s/vmlinux-%1$s", "/lib/modules/%1$s/build/vmlinux", @@ -4771,8 +5414,27 @@ struct btf *btf__load_vmlinux_btf(void) struct btf *btf; int i, err; - uname(&buf); + /* is canonical sysfs location accessible? */ + if (faccessat(AT_FDCWD, sysfs_btf_path, F_OK, AT_EACCESS) < 0) { + pr_warn("kernel BTF is missing at '%s', was CONFIG_DEBUG_INFO_BTF enabled?\n", + sysfs_btf_path); + } else { + btf = btf_parse_raw_mmap(sysfs_btf_path, NULL); + if (IS_ERR(btf)) + btf = btf__parse(sysfs_btf_path, NULL); + + if (!btf) { + err = -errno; + pr_warn("failed to read kernel BTF from '%s': %s\n", + sysfs_btf_path, errstr(err)); + return libbpf_err_ptr(err); + } + pr_debug("loaded kernel BTF from '%s'\n", sysfs_btf_path); + return btf; + } + /* try fallback locations */ + uname(&buf); for (i = 0; i < ARRAY_SIZE(locations); i++) { snprintf(path, PATH_MAX, locations[i], buf.release); @@ -4781,7 +5443,7 @@ struct btf *btf__load_vmlinux_btf(void) btf = btf__parse(path, NULL); err = libbpf_get_error(btf); - pr_debug("loading kernel BTF '%s': %d\n", path, err); + pr_debug("loading kernel BTF '%s': %s\n", path, errstr(err)); if (err) continue; @@ -4802,136 +5464,6 @@ struct btf *btf__load_module_btf(const char *module_name, struct btf *vmlinux_bt return btf__parse_split(path, vmlinux_btf); } -int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx) -{ - int i, n, err; - - switch (btf_kind(t)) { - case BTF_KIND_INT: - case BTF_KIND_FLOAT: - case BTF_KIND_ENUM: - case BTF_KIND_ENUM64: - return 0; - - case BTF_KIND_FWD: - case BTF_KIND_CONST: - case BTF_KIND_VOLATILE: - case BTF_KIND_RESTRICT: - case BTF_KIND_PTR: - case BTF_KIND_TYPEDEF: - case BTF_KIND_FUNC: - case BTF_KIND_VAR: - case BTF_KIND_DECL_TAG: - case BTF_KIND_TYPE_TAG: - return visit(&t->type, ctx); - - case BTF_KIND_ARRAY: { - struct btf_array *a = btf_array(t); - - err = visit(&a->type, ctx); - err = err ?: visit(&a->index_type, ctx); - return err; - } - - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: { - struct btf_member *m = btf_members(t); - - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->type, ctx); - if (err) - return err; - } - return 0; - } - - case BTF_KIND_FUNC_PROTO: { - struct btf_param *m = btf_params(t); - - err = visit(&t->type, ctx); - if (err) - return err; - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->type, ctx); - if (err) - return err; - } - return 0; - } - - case BTF_KIND_DATASEC: { - struct btf_var_secinfo *m = btf_var_secinfos(t); - - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->type, ctx); - if (err) - return err; - } - return 0; - } - - default: - return -EINVAL; - } -} - -int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx) -{ - int i, n, err; - - err = visit(&t->name_off, ctx); - if (err) - return err; - - switch (btf_kind(t)) { - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: { - struct btf_member *m = btf_members(t); - - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->name_off, ctx); - if (err) - return err; - } - break; - } - case BTF_KIND_ENUM: { - struct btf_enum *m = btf_enum(t); - - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->name_off, ctx); - if (err) - return err; - } - break; - } - case BTF_KIND_ENUM64: { - struct btf_enum64 *m = btf_enum64(t); - - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->name_off, ctx); - if (err) - return err; - } - break; - } - case BTF_KIND_FUNC_PROTO: { - struct btf_param *m = btf_params(t); - - for (i = 0, n = btf_vlen(t); i < n; i++, m++) { - err = visit(&m->name_off, ctx); - if (err) - return err; - } - break; - } - default: - break; - } - - return 0; -} - int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx) { const struct btf_ext_info *seg; @@ -5011,3 +5543,328 @@ int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void return 0; } + +struct btf_distill { + struct btf_pipe pipe; + int *id_map; + unsigned int split_start_id; + unsigned int split_start_str; + int diff_id; +}; + +static int btf_add_distilled_type_ids(struct btf_distill *dist, __u32 i) +{ + struct btf_type *split_t = btf_type_by_id(dist->pipe.src, i); + struct btf_field_iter it; + __u32 *id; + int err; + + err = btf_field_iter_init(&it, split_t, BTF_FIELD_ITER_IDS); + if (err) + return err; + while ((id = btf_field_iter_next(&it))) { + struct btf_type *base_t; + + if (!*id) + continue; + /* split BTF id, not needed */ + if (*id >= dist->split_start_id) + continue; + /* already added ? */ + if (dist->id_map[*id] > 0) + continue; + + /* only a subset of base BTF types should be referenced from + * split BTF; ensure nothing unexpected is referenced. + */ + base_t = btf_type_by_id(dist->pipe.src, *id); + switch (btf_kind(base_t)) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_FWD: + case BTF_KIND_ARRAY: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_TYPEDEF: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + case BTF_KIND_PTR: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VOLATILE: + case BTF_KIND_FUNC_PROTO: + case BTF_KIND_TYPE_TAG: + dist->id_map[*id] = *id; + break; + default: + pr_warn("unexpected reference to base type[%u] of kind [%u] when creating distilled base BTF.\n", + *id, btf_kind(base_t)); + return -EINVAL; + } + /* If a base type is used, ensure types it refers to are + * marked as used also; so for example if we find a PTR to INT + * we need both the PTR and INT. + * + * The only exception is named struct/unions, since distilled + * base BTF composite types have no members. + */ + if (btf_is_composite(base_t) && base_t->name_off) + continue; + err = btf_add_distilled_type_ids(dist, *id); + if (err) + return err; + } + return 0; +} + +static int btf_add_distilled_types(struct btf_distill *dist) +{ + bool adding_to_base = dist->pipe.dst->start_id == 1; + int id = btf__type_cnt(dist->pipe.dst); + struct btf_type *t; + int i, err = 0; + + + /* Add types for each of the required references to either distilled + * base or split BTF, depending on type characteristics. + */ + for (i = 1; i < dist->split_start_id; i++) { + const char *name; + int kind; + + if (!dist->id_map[i]) + continue; + t = btf_type_by_id(dist->pipe.src, i); + kind = btf_kind(t); + name = btf__name_by_offset(dist->pipe.src, t->name_off); + + switch (kind) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_FWD: + /* Named int, float, fwd are added to base. */ + if (!adding_to_base) + continue; + err = btf_add_type(&dist->pipe, t); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + /* Named struct/union are added to base as 0-vlen + * struct/union of same size. Anonymous struct/unions + * are added to split BTF as-is. + */ + if (adding_to_base) { + if (!t->name_off) + continue; + err = btf_add_composite(dist->pipe.dst, kind, name, t->size); + } else { + if (t->name_off) + continue; + err = btf_add_type(&dist->pipe, t); + } + break; + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + /* Named enum[64]s are added to base as a sized + * enum; relocation will match with appropriately-named + * and sized enum or enum64. + * + * Anonymous enums are added to split BTF as-is. + */ + if (adding_to_base) { + if (!t->name_off) + continue; + err = btf__add_enum(dist->pipe.dst, name, t->size); + } else { + if (t->name_off) + continue; + err = btf_add_type(&dist->pipe, t); + } + break; + case BTF_KIND_ARRAY: + case BTF_KIND_TYPEDEF: + case BTF_KIND_PTR: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VOLATILE: + case BTF_KIND_FUNC_PROTO: + case BTF_KIND_TYPE_TAG: + /* All other types are added to split BTF. */ + if (adding_to_base) + continue; + err = btf_add_type(&dist->pipe, t); + break; + default: + pr_warn("unexpected kind when adding base type '%s'[%u] of kind [%u] to distilled base BTF.\n", + name, i, kind); + return -EINVAL; + + } + if (err < 0) + break; + dist->id_map[i] = id++; + } + return err; +} + +/* Split BTF ids without a mapping will be shifted downwards since distilled + * base BTF is smaller than the original base BTF. For those that have a + * mapping (either to base or updated split BTF), update the id based on + * that mapping. + */ +static int btf_update_distilled_type_ids(struct btf_distill *dist, __u32 i) +{ + struct btf_type *t = btf_type_by_id(dist->pipe.dst, i); + struct btf_field_iter it; + __u32 *id; + int err; + + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); + if (err) + return err; + while ((id = btf_field_iter_next(&it))) { + if (dist->id_map[*id]) + *id = dist->id_map[*id]; + else if (*id >= dist->split_start_id) + *id -= dist->diff_id; + } + return 0; +} + +/* Create updated split BTF with distilled base BTF; distilled base BTF + * consists of BTF information required to clarify the types that split + * BTF refers to, omitting unneeded details. Specifically it will contain + * base types and memberless definitions of named structs, unions and enumerated + * types. Associated reference types like pointers, arrays and anonymous + * structs, unions and enumerated types will be added to split BTF. + * Size is recorded for named struct/unions to help guide matching to the + * target base BTF during later relocation. + * + * The only case where structs, unions or enumerated types are fully represented + * is when they are anonymous; in such cases, the anonymous type is added to + * split BTF in full. + * + * We return newly-created split BTF where the split BTF refers to a newly-created + * distilled base BTF. Both must be freed separately by the caller. + */ +int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf, + struct btf **new_split_btf) +{ + struct btf *new_base = NULL, *new_split = NULL; + const struct btf *old_base; + unsigned int n = btf__type_cnt(src_btf); + struct btf_distill dist = {}; + struct btf_type *t; + int i, err = 0; + + /* src BTF must be split BTF. */ + old_base = btf__base_btf(src_btf); + if (!new_base_btf || !new_split_btf || !old_base) + return libbpf_err(-EINVAL); + + new_base = btf__new_empty(); + if (!new_base) + return libbpf_err(-ENOMEM); + + btf__set_endianness(new_base, btf__endianness(src_btf)); + + dist.id_map = calloc(n, sizeof(*dist.id_map)); + if (!dist.id_map) { + err = -ENOMEM; + goto done; + } + dist.pipe.src = src_btf; + dist.pipe.dst = new_base; + dist.pipe.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL); + if (IS_ERR(dist.pipe.str_off_map)) { + err = -ENOMEM; + goto done; + } + dist.split_start_id = btf__type_cnt(old_base); + dist.split_start_str = old_base->hdr->str_len; + + /* Pass over src split BTF; generate the list of base BTF type ids it + * references; these will constitute our distilled BTF set to be + * distributed over base and split BTF as appropriate. + */ + for (i = src_btf->start_id; i < n; i++) { + err = btf_add_distilled_type_ids(&dist, i); + if (err < 0) + goto done; + } + /* Next add types for each of the required references to base BTF and split BTF + * in turn. + */ + err = btf_add_distilled_types(&dist); + if (err < 0) + goto done; + + /* Create new split BTF with distilled base BTF as its base; the final + * state is split BTF with distilled base BTF that represents enough + * about its base references to allow it to be relocated with the base + * BTF available. + */ + new_split = btf__new_empty_split(new_base); + if (!new_split) { + err = -errno; + goto done; + } + dist.pipe.dst = new_split; + /* First add all split types */ + for (i = src_btf->start_id; i < n; i++) { + t = btf_type_by_id(src_btf, i); + err = btf_add_type(&dist.pipe, t); + if (err < 0) + goto done; + } + /* Now add distilled types to split BTF that are not added to base. */ + err = btf_add_distilled_types(&dist); + if (err < 0) + goto done; + + /* All split BTF ids will be shifted downwards since there are less base + * BTF ids in distilled base BTF. + */ + dist.diff_id = dist.split_start_id - btf__type_cnt(new_base); + + n = btf__type_cnt(new_split); + /* Now update base/split BTF ids. */ + for (i = 1; i < n; i++) { + err = btf_update_distilled_type_ids(&dist, i); + if (err < 0) + break; + } +done: + free(dist.id_map); + hashmap__free(dist.pipe.str_off_map); + if (err) { + btf__free(new_split); + btf__free(new_base); + return libbpf_err(err); + } + *new_base_btf = new_base; + *new_split_btf = new_split; + + return 0; +} + +const struct btf_header *btf_header(const struct btf *btf) +{ + return btf->hdr; +} + +void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) +{ + btf->base_btf = (struct btf *)base_btf; + btf->start_id = btf__type_cnt(base_btf); + btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off; +} + +int btf__relocate(struct btf *btf, const struct btf *base_btf) +{ + int err = btf_relocate(btf, base_btf, NULL); + + if (!err) + btf->owns_base = false; + return libbpf_err(err); +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 8e6880d91c84..cc01494d6210 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -18,6 +18,7 @@ extern "C" { #define BTF_ELF_SEC ".BTF" #define BTF_EXT_ELF_SEC ".BTF.ext" +#define BTF_BASE_ELF_SEC ".BTF.base" #define MAPS_ELF_SEC ".maps" struct btf; @@ -93,6 +94,7 @@ LIBBPF_API struct btf *btf__new_empty(void); * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an * ELF BTF section except with a base BTF on top of which split BTF should be * based + * @param base_btf base BTF object * @return new BTF object instance which has to be eventually freed with * **btf__free()** * @@ -107,6 +109,31 @@ LIBBPF_API struct btf *btf__new_empty(void); */ LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf); +/** + * @brief **btf__distill_base()** creates new versions of the split BTF + * *src_btf* and its base BTF. The new base BTF will only contain the types + * needed to improve robustness of the split BTF to small changes in base BTF. + * When that split BTF is loaded against a (possibly changed) base, this + * distilled base BTF will help update references to that (possibly changed) + * base BTF. + * @param src_btf source split BTF object + * @param new_base_btf pointer to where the new base BTF object pointer will be stored + * @param new_split_btf pointer to where the new split BTF object pointer will be stored + * @return 0 on success; negative error code, otherwise + * + * Both the new split and its associated new base BTF must be freed by + * the caller. + * + * If successful, 0 is returned and **new_base_btf** and **new_split_btf** + * will point at new base/split BTF. Both the new split and its associated + * new base BTF must be freed by the caller. + * + * A negative value is returned on error and the thread-local `errno` variable + * is set to the error code as well. + */ +LIBBPF_API int btf__distill_base(const struct btf *src_btf, struct btf **new_base_btf, + struct btf **new_split_btf); + LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext); LIBBPF_API struct btf *btf__parse_split(const char *path, struct btf *base_btf); LIBBPF_API struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext); @@ -145,6 +172,9 @@ LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset); LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size); LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); LIBBPF_API const void *btf_ext__raw_data(const struct btf_ext *btf_ext, __u32 *size); +LIBBPF_API enum btf_endianness btf_ext__endianness(const struct btf_ext *btf_ext); +LIBBPF_API int btf_ext__set_endianness(struct btf_ext *btf_ext, + enum btf_endianness endian); LIBBPF_API int btf__find_str(struct btf *btf, const char *s); LIBBPF_API int btf__add_str(struct btf *btf, const char *s); @@ -202,6 +232,7 @@ LIBBPF_API int btf__add_volatile(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_const(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_restrict(struct btf *btf, int ref_type_id); LIBBPF_API int btf__add_type_tag(struct btf *btf, const char *value, int ref_type_id); +LIBBPF_API int btf__add_type_attr(struct btf *btf, const char *value, int ref_type_id); /* func and func_proto construction APIs */ LIBBPF_API int btf__add_func(struct btf *btf, const char *name, @@ -218,6 +249,8 @@ LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, /* tag construction API */ LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, int component_idx); +LIBBPF_API int btf__add_decl_attr(struct btf *btf, const char *value, int ref_type_id, + int component_idx); struct btf_dedup_opts { size_t sz; @@ -231,6 +264,23 @@ struct btf_dedup_opts { LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts); +/** + * @brief **btf__relocate()** will check the split BTF *btf* for references + * to base BTF kinds, and verify those references are compatible with + * *base_btf*; if they are, *btf* is adjusted such that is re-parented to + * *base_btf* and type ids and strings are adjusted to accommodate this. + * @param btf split BTF object to relocate + * @param base_btf base BTF object + * @return 0 on success; negative error code, otherwise + * + * If successful, 0 is returned and **btf** now has **base_btf** as its + * base. + * + * A negative value is returned on error and the thread-local `errno` variable + * is set to the error code as well. + */ +LIBBPF_API int btf__relocate(struct btf *btf, const struct btf *base_btf); + struct btf_dump; struct btf_dump_opts { @@ -250,7 +300,7 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); struct btf_dump_emit_type_decl_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; /* optional field name for type declaration, e.g.: * - struct my_struct <FNAME> @@ -284,9 +334,10 @@ struct btf_dump_type_data_opts { bool compact; /* no newlines/indentation */ bool skip_names; /* skip member/type names */ bool emit_zeroes; /* show 0-valued fields */ + bool emit_strings; /* print char arrays as strings */ size_t :0; }; -#define btf_dump_type_data_opts__last_field emit_zeroes +#define btf_dump_type_data_opts__last_field emit_strings LIBBPF_API int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index deb2bc9a0a7b..6388392f49a0 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -13,6 +13,7 @@ #include <ctype.h> #include <endian.h> #include <errno.h> +#include <limits.h> #include <linux/err.h> #include <linux/btf.h> #include <linux/kernel.h> @@ -66,6 +67,7 @@ struct btf_dump_data { bool compact; bool skip_names; bool emit_zeroes; + bool emit_strings; __u8 indent_lvl; /* base indent level */ char indent_str[BTF_DATA_INDENT_STR_LEN]; /* below are used during iteration */ @@ -224,6 +226,9 @@ static void btf_dump_free_names(struct hashmap *map) size_t bkt; struct hashmap_entry *cur; + if (!map) + return; + hashmap__for_each_entry(map, cur, bkt) free((void *)cur->pkey); @@ -303,7 +308,7 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id) * definition, in which case they have to be declared inline as part of field * type declaration; or as a top-level anonymous enum, typically used for * declaring global constants. It's impossible to distinguish between two - * without knowning whether given enum type was referenced from other type: + * without knowing whether given enum type was referenced from other type: * top-level anonymous enum won't be referenced by anything, while embedded * one will. */ @@ -833,14 +838,9 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, const struct btf_type *t) { const struct btf_member *m; - int align, i, bit_sz; + int max_align = 1, align, i, bit_sz; __u16 vlen; - align = btf__align_of(btf, id); - /* size of a non-packed struct has to be a multiple of its alignment*/ - if (align && t->size % align) - return true; - m = btf_members(t); vlen = btf_vlen(t); /* all non-bitfield fields have to be naturally aligned */ @@ -849,8 +849,11 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, bit_sz = btf_member_bitfield_size(t, i); if (align && bit_sz == 0 && m->offset % (8 * align) != 0) return true; + max_align = max(align, max_align); } - + /* size of a non-packed struct has to be a multiple of its alignment */ + if (t->size % max_align != 0) + return true; /* * if original struct was marked as packed, but its layout is * naturally aligned, we'll detect that it's not packed @@ -858,44 +861,97 @@ static bool btf_is_struct_packed(const struct btf *btf, __u32 id, return false; } -static int chip_away_bits(int total, int at_most) -{ - return total % at_most ? : at_most; -} - static void btf_dump_emit_bit_padding(const struct btf_dump *d, - int cur_off, int m_off, int m_bit_sz, - int align, int lvl) + int cur_off, int next_off, int next_align, + bool in_bitfield, int lvl) { - int off_diff = m_off - cur_off; - int ptr_bits = d->ptr_sz * 8; + const struct { + const char *name; + int bits; + } pads[] = { + {"long", d->ptr_sz * 8}, {"int", 32}, {"short", 16}, {"char", 8} + }; + int new_off = 0, pad_bits = 0, bits, i; + const char *pad_type = NULL; + + if (cur_off >= next_off) + return; /* no gap */ + + /* For filling out padding we want to take advantage of + * natural alignment rules to minimize unnecessary explicit + * padding. First, we find the largest type (among long, int, + * short, or char) that can be used to force naturally aligned + * boundary. Once determined, we'll use such type to fill in + * the remaining padding gap. In some cases we can rely on + * compiler filling some gaps, but sometimes we need to force + * alignment to close natural alignment with markers like + * `long: 0` (this is always the case for bitfields). Note + * that even if struct itself has, let's say 4-byte alignment + * (i.e., it only uses up to int-aligned types), using `long: + * X;` explicit padding doesn't actually change struct's + * overall alignment requirements, but compiler does take into + * account that type's (long, in this example) natural + * alignment requirements when adding implicit padding. We use + * this fact heavily and don't worry about ruining correct + * struct alignment requirement. + */ + for (i = 0; i < ARRAY_SIZE(pads); i++) { + pad_bits = pads[i].bits; + pad_type = pads[i].name; - if (off_diff <= 0) - /* no gap */ - return; - if (m_bit_sz == 0 && off_diff < align * 8) - /* natural padding will take care of a gap */ - return; + new_off = roundup(cur_off, pad_bits); + if (new_off <= next_off) + break; + } - while (off_diff > 0) { - const char *pad_type; - int pad_bits; - - if (ptr_bits > 32 && off_diff > 32) { - pad_type = "long"; - pad_bits = chip_away_bits(off_diff, ptr_bits); - } else if (off_diff > 16) { - pad_type = "int"; - pad_bits = chip_away_bits(off_diff, 32); - } else if (off_diff > 8) { - pad_type = "short"; - pad_bits = chip_away_bits(off_diff, 16); - } else { - pad_type = "char"; - pad_bits = chip_away_bits(off_diff, 8); + if (new_off > cur_off && new_off <= next_off) { + /* We need explicit `<type>: 0` aligning mark if next + * field is right on alignment offset and its + * alignment requirement is less strict than <type>'s + * alignment (so compiler won't naturally align to the + * offset we expect), or if subsequent `<type>: X`, + * will actually completely fit in the remaining hole, + * making compiler basically ignore `<type>: X` + * completely. + */ + if (in_bitfield || + (new_off == next_off && roundup(cur_off, next_align * 8) != new_off) || + (new_off != next_off && next_off - new_off <= new_off - cur_off)) + /* but for bitfields we'll emit explicit bit count */ + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, + in_bitfield ? new_off - cur_off : 0); + cur_off = new_off; + } + + /* Now we know we start at naturally aligned offset for a chosen + * padding type (long, int, short, or char), and so the rest is just + * a straightforward filling of remaining padding gap with full + * `<type>: sizeof(<type>);` markers, except for the last one, which + * might need smaller than sizeof(<type>) padding. + */ + while (cur_off != next_off) { + bits = min(next_off - cur_off, pad_bits); + if (bits == pad_bits) { + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits); + cur_off += bits; + continue; + } + /* For the remainder padding that doesn't cover entire + * pad_type bit length, we pick the smallest necessary type. + * This is pure aesthetics, we could have just used `long`, + * but having smallest necessary one communicates better the + * scale of the padding gap. + */ + for (i = ARRAY_SIZE(pads) - 1; i >= 0; i--) { + pad_type = pads[i].name; + pad_bits = pads[i].bits; + if (pad_bits < bits) + continue; + + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, bits); + cur_off += bits; + break; } - btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits); - off_diff -= pad_bits; } } @@ -915,9 +971,11 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, { const struct btf_member *m = btf_members(t); bool is_struct = btf_is_struct(t); - int align, i, packed, off = 0; + bool packed, prev_bitfield = false; + int align, i, off = 0; __u16 vlen = btf_vlen(t); + align = btf__align_of(d->btf, id); packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; btf_dump_printf(d, "%s%s%s {", @@ -927,41 +985,47 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, for (i = 0; i < vlen; i++, m++) { const char *fname; - int m_off, m_sz; + int m_off, m_sz, m_align; + bool in_bitfield; fname = btf_name_of(d, m->name_off); m_sz = btf_member_bitfield_size(t, i); m_off = btf_member_bit_offset(t, i); - align = packed ? 1 : btf__align_of(d->btf, m->type); + m_align = packed ? 1 : btf__align_of(d->btf, m->type); - btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, lvl + 1); + in_bitfield = prev_bitfield && m_sz != 0; + + btf_dump_emit_bit_padding(d, off, m_off, m_align, in_bitfield, lvl + 1); btf_dump_printf(d, "\n%s", pfx(lvl + 1)); btf_dump_emit_type_decl(d, m->type, fname, lvl + 1); if (m_sz) { btf_dump_printf(d, ": %d", m_sz); off = m_off + m_sz; + prev_bitfield = true; } else { m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type)); off = m_off + m_sz * 8; + prev_bitfield = false; } + btf_dump_printf(d, ";"); } /* pad at the end, if necessary */ - if (is_struct) { - align = packed ? 1 : btf__align_of(d->btf, id); - btf_dump_emit_bit_padding(d, off, t->size * 8, 0, align, - lvl + 1); - } + if (is_struct) + btf_dump_emit_bit_padding(d, off, t->size * 8, align, false, lvl + 1); /* * Keep `struct empty {}` on a single line, * only print newline when there are regular or padding fields. */ - if (vlen || t->size) + if (vlen || t->size) { btf_dump_printf(d, "\n"); - btf_dump_printf(d, "%s}", pfx(lvl)); + btf_dump_printf(d, "%s}", pfx(lvl)); + } else { + btf_dump_printf(d, "}"); + } if (packed) btf_dump_printf(d, " __attribute__((packed))"); } @@ -1073,6 +1137,43 @@ static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, else btf_dump_emit_enum64_val(d, t, lvl, vlen); btf_dump_printf(d, "\n%s}", pfx(lvl)); + + /* special case enums with special sizes */ + if (t->size == 1) { + /* one-byte enums can be forced with mode(byte) attribute */ + btf_dump_printf(d, " __attribute__((mode(byte)))"); + } else if (t->size == 8 && d->ptr_sz == 8) { + /* enum can be 8-byte sized if one of the enumerator values + * doesn't fit in 32-bit integer, or by adding mode(word) + * attribute (but probably only on 64-bit architectures); do + * our best here to try to satisfy the contract without adding + * unnecessary attributes + */ + bool needs_word_mode; + + if (btf_is_enum(t)) { + /* enum can't represent 64-bit values, so we need word mode */ + needs_word_mode = true; + } else { + /* enum64 needs mode(word) if none of its values has + * non-zero upper 32-bits (which means that all values + * fit in 32-bit integers and won't cause compiler to + * bump enum to be 64-bit naturally + */ + int i; + + needs_word_mode = true; + for (i = 0; i < vlen; i++) { + if (btf_enum64(t)[i].val_hi32 != 0) { + needs_word_mode = false; + break; + } + } + } + if (needs_word_mode) + btf_dump_printf(d, " __attribute__((mode(word)))"); + } + } static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, @@ -1207,7 +1308,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, * chain, restore stack, emit warning, and try to * proceed nevertheless */ - pr_warn("not enough memory for decl stack:%d", err); + pr_warn("not enough memory for decl stack: %s\n", errstr(err)); d->decl_stack_cnt = stack_start; return; } @@ -1396,7 +1497,10 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, case BTF_KIND_TYPE_TAG: btf_dump_emit_mods(d, decls); name = btf_name_of(d, t->name_off); - btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name); + if (btf_kflag(t)) + btf_dump_printf(d, " __attribute__((%s))", name); + else + btf_dump_printf(d, " __attribute__((btf_type_tag(\"%s\")))", name); break; case BTF_KIND_ARRAY: { const struct btf_array *a = btf_array(t); @@ -1462,10 +1566,12 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, * Clang for BPF target generates func_proto with no * args as a func_proto with a single void arg (e.g., * `int (*f)(void)` vs just `int (*f)()`). We are - * going to pretend there are no args for such case. + * going to emit valid empty args (void) syntax for + * such case. Similarly and conveniently, valid + * no args case can be special-cased here as well. */ - if (vlen == 1 && p->type == 0) { - btf_dump_printf(d, ")"); + if (vlen == 0 || (vlen == 1 && p->type == 0)) { + btf_dump_printf(d, "void)"); return; } @@ -1832,6 +1938,7 @@ static int btf_dump_int_data(struct btf_dump *d, if (d->typed_dump->is_array_terminated) break; if (*(char *)data == '\0') { + btf_dump_type_values(d, "'\\0'"); d->typed_dump->is_array_terminated = true; break; } @@ -1924,6 +2031,52 @@ static int btf_dump_var_data(struct btf_dump *d, return btf_dump_dump_type_data(d, NULL, t, type_id, data, 0, 0); } +static int btf_dump_string_data(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data) +{ + const struct btf_array *array = btf_array(t); + const char *chars = data; + __u32 i; + + /* Make sure it is a NUL-terminated string. */ + for (i = 0; i < array->nelems; i++) { + if ((void *)(chars + i) >= d->typed_dump->data_end) + return -E2BIG; + if (chars[i] == '\0') + break; + } + if (i == array->nelems) { + /* The caller will print this as a regular array. */ + return -EINVAL; + } + + btf_dump_data_pfx(d); + btf_dump_printf(d, "\""); + + for (i = 0; i < array->nelems; i++) { + char c = chars[i]; + + if (c == '\0') { + /* + * When printing character arrays as strings, NUL bytes + * are always treated as string terminators; they are + * never printed. + */ + break; + } + if (isprint(c)) + btf_dump_printf(d, "%c", c); + else + btf_dump_printf(d, "\\x%02x", (__u8)c); + } + + btf_dump_printf(d, "\""); + + return 0; +} + static int btf_dump_array_data(struct btf_dump *d, const struct btf_type *t, __u32 id, @@ -1934,6 +2087,7 @@ static int btf_dump_array_data(struct btf_dump *d, __u32 i, elem_type_id; __s64 elem_size; bool is_array_member; + bool is_array_terminated; elem_type_id = array->type; elem_type = skip_mods_and_typedefs(d->btf, elem_type_id, NULL); @@ -1950,8 +2104,13 @@ static int btf_dump_array_data(struct btf_dump *d, * char arrays, so if size is 1 and element is * printable as a char, we'll do that. */ - if (elem_size == 1) + if (elem_size == 1) { + if (d->typed_dump->emit_strings && + btf_dump_string_data(d, t, id, data) == 0) { + return 0; + } d->typed_dump->is_array_char = true; + } } /* note that we increment depth before calling btf_dump_print() below; @@ -1969,12 +2128,15 @@ static int btf_dump_array_data(struct btf_dump *d, */ is_array_member = d->typed_dump->is_array_member; d->typed_dump->is_array_member = true; + is_array_terminated = d->typed_dump->is_array_terminated; + d->typed_dump->is_array_terminated = false; for (i = 0; i < array->nelems; i++, data += elem_size) { if (d->typed_dump->is_array_terminated) break; btf_dump_dump_type_data(d, NULL, elem_type, elem_type_id, data, 0, 0); } d->typed_dump->is_array_member = is_array_member; + d->typed_dump->is_array_terminated = is_array_terminated; d->typed_dump->depth--; btf_dump_data_pfx(d); btf_dump_type_values(d, "]"); @@ -2153,9 +2315,25 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d, const struct btf_type *t, __u32 id, const void *data, - __u8 bits_offset) + __u8 bits_offset, + __u8 bit_sz) { - __s64 size = btf__resolve_size(d->btf, id); + __s64 size; + + if (bit_sz) { + /* bits_offset is at most 7. bit_sz is at most 128. */ + __u8 nr_bytes = (bits_offset + bit_sz + 7) / 8; + + /* When bit_sz is non zero, it is called from + * btf_dump_struct_data() where it only cares about + * negative error value. + * Return nr_bytes in success case to make it + * consistent as the regular integer case below. + */ + return data + nr_bytes > d->typed_dump->data_end ? -E2BIG : nr_bytes; + } + + size = btf__resolve_size(d->btf, id); if (size < 0 || size >= INT_MAX) { pr_warn("unexpected size [%zu] for id [%u]\n", @@ -2310,7 +2488,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, { int size, err = 0; - size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset); + size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset, bit_sz); if (size < 0) return size; err = btf_dump_type_data_check_zero(d, t, id, data, bits_offset, bit_sz); @@ -2420,6 +2598,7 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, d->typed_dump->compact = OPTS_GET(opts, compact, false); d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false); d->typed_dump->emit_zeroes = OPTS_GET(opts, emit_zeroes, false); + d->typed_dump->emit_strings = OPTS_GET(opts, emit_strings, false); ret = btf_dump_dump_type_data(d, NULL, t, id, data, 0, 0); diff --git a/tools/lib/bpf/btf_iter.c b/tools/lib/bpf/btf_iter.c new file mode 100644 index 000000000000..9a6c822c2294 --- /dev/null +++ b/tools/lib/bpf/btf_iter.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2021 Facebook */ +/* Copyright (c) 2024, Oracle and/or its affiliates. */ + +#ifdef __KERNEL__ +#include <linux/bpf.h> +#include <linux/btf.h> + +#define btf_var_secinfos(t) (struct btf_var_secinfo *)btf_type_var_secinfo(t) + +#else +#include "btf.h" +#include "libbpf_internal.h" +#endif + +int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, + enum btf_field_iter_kind iter_kind) +{ + it->p = NULL; + it->m_idx = -1; + it->off_idx = 0; + it->vlen = 0; + + switch (iter_kind) { + case BTF_FIELD_ITER_IDS: + switch (btf_kind(t)) { + case BTF_KIND_UNKN: + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + it->desc = (struct btf_field_desc) {}; + break; + case BTF_KIND_FWD: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: + it->desc = (struct btf_field_desc) { 1, {offsetof(struct btf_type, type)} }; + break; + case BTF_KIND_ARRAY: + it->desc = (struct btf_field_desc) { + 2, {sizeof(struct btf_type) + offsetof(struct btf_array, type), + sizeof(struct btf_type) + offsetof(struct btf_array, index_type)} + }; + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + it->desc = (struct btf_field_desc) { + 0, {}, + sizeof(struct btf_member), + 1, {offsetof(struct btf_member, type)} + }; + break; + case BTF_KIND_FUNC_PROTO: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, type)}, + sizeof(struct btf_param), + 1, {offsetof(struct btf_param, type)} + }; + break; + case BTF_KIND_DATASEC: + it->desc = (struct btf_field_desc) { + 0, {}, + sizeof(struct btf_var_secinfo), + 1, {offsetof(struct btf_var_secinfo, type)} + }; + break; + default: + return -EINVAL; + } + break; + case BTF_FIELD_ITER_STRS: + switch (btf_kind(t)) { + case BTF_KIND_UNKN: + it->desc = (struct btf_field_desc) {}; + break; + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_FWD: + case BTF_KIND_ARRAY: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: + case BTF_KIND_DATASEC: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, name_off)} + }; + break; + case BTF_KIND_ENUM: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, name_off)}, + sizeof(struct btf_enum), + 1, {offsetof(struct btf_enum, name_off)} + }; + break; + case BTF_KIND_ENUM64: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, name_off)}, + sizeof(struct btf_enum64), + 1, {offsetof(struct btf_enum64, name_off)} + }; + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, name_off)}, + sizeof(struct btf_member), + 1, {offsetof(struct btf_member, name_off)} + }; + break; + case BTF_KIND_FUNC_PROTO: + it->desc = (struct btf_field_desc) { + 1, {offsetof(struct btf_type, name_off)}, + sizeof(struct btf_param), + 1, {offsetof(struct btf_param, name_off)} + }; + break; + default: + return -EINVAL; + } + break; + default: + return -EINVAL; + } + + if (it->desc.m_sz) + it->vlen = btf_vlen(t); + + it->p = t; + return 0; +} + +__u32 *btf_field_iter_next(struct btf_field_iter *it) +{ + if (!it->p) + return NULL; + + if (it->m_idx < 0) { + if (it->off_idx < it->desc.t_off_cnt) + return it->p + it->desc.t_offs[it->off_idx++]; + /* move to per-member iteration */ + it->m_idx = 0; + it->p += sizeof(struct btf_type); + it->off_idx = 0; + } + + /* if type doesn't have members, stop */ + if (it->desc.m_sz == 0) { + it->p = NULL; + return NULL; + } + + if (it->off_idx >= it->desc.m_off_cnt) { + /* exhausted this member's fields, go to the next member */ + it->m_idx++; + it->p += it->desc.m_sz; + it->off_idx = 0; + } + + if (it->m_idx < it->vlen) + return it->p + it->desc.m_offs[it->off_idx++]; + + it->p = NULL; + return NULL; +} diff --git a/tools/lib/bpf/btf_relocate.c b/tools/lib/bpf/btf_relocate.c new file mode 100644 index 000000000000..53d1f3541bce --- /dev/null +++ b/tools/lib/bpf/btf_relocate.c @@ -0,0 +1,519 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2024, Oracle and/or its affiliates. */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif + +#ifdef __KERNEL__ +#include <linux/bpf.h> +#include <linux/bsearch.h> +#include <linux/btf.h> +#include <linux/sort.h> +#include <linux/string.h> +#include <linux/bpf_verifier.h> + +#define btf_type_by_id (struct btf_type *)btf_type_by_id +#define btf__type_cnt btf_nr_types +#define btf__base_btf btf_base_btf +#define btf__name_by_offset btf_name_by_offset +#define btf__str_by_offset btf_str_by_offset +#define btf_kflag btf_type_kflag + +#define calloc(nmemb, sz) kvcalloc(nmemb, sz, GFP_KERNEL | __GFP_NOWARN) +#define free(ptr) kvfree(ptr) +#define qsort(base, num, sz, cmp) sort(base, num, sz, cmp, NULL) + +#else + +#include "btf.h" +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" + +#endif /* __KERNEL__ */ + +struct btf; + +struct btf_relocate { + struct btf *btf; + const struct btf *base_btf; + const struct btf *dist_base_btf; + unsigned int nr_base_types; + unsigned int nr_split_types; + unsigned int nr_dist_base_types; + int dist_str_len; + int base_str_len; + __u32 *id_map; + __u32 *str_map; +}; + +/* Set temporarily in relocation id_map if distilled base struct/union is + * embedded in a split BTF struct/union; in such a case, size information must + * match between distilled base BTF and base BTF representation of type. + */ +#define BTF_IS_EMBEDDED ((__u32)-1) + +/* <name, size, id> triple used in sorting/searching distilled base BTF. */ +struct btf_name_info { + const char *name; + /* set when search requires a size match */ + bool needs_size: 1; + unsigned int size: 31; + __u32 id; +}; + +static int btf_relocate_rewrite_type_id(struct btf_relocate *r, __u32 i) +{ + struct btf_type *t = btf_type_by_id(r->btf, i); + struct btf_field_iter it; + __u32 *id; + int err; + + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); + if (err) + return err; + + while ((id = btf_field_iter_next(&it))) + *id = r->id_map[*id]; + return 0; +} + +/* Simple string comparison used for sorting within BTF, since all distilled + * types are named. If strings match, and size is non-zero for both elements + * fall back to using size for ordering. + */ +static int cmp_btf_name_size(const void *n1, const void *n2) +{ + const struct btf_name_info *ni1 = n1; + const struct btf_name_info *ni2 = n2; + int name_diff = strcmp(ni1->name, ni2->name); + + if (!name_diff && ni1->needs_size && ni2->needs_size) + return ni2->size - ni1->size; + return name_diff; +} + +/* Binary search with a small twist; find leftmost element that matches + * so that we can then iterate through all exact matches. So for example + * searching { "a", "bb", "bb", "c" } we would always match on the + * leftmost "bb". + */ +static struct btf_name_info *search_btf_name_size(struct btf_name_info *key, + struct btf_name_info *vals, + int nelems) +{ + struct btf_name_info *ret = NULL; + int high = nelems - 1; + int low = 0; + + while (low <= high) { + int mid = (low + high)/2; + struct btf_name_info *val = &vals[mid]; + int diff = cmp_btf_name_size(key, val); + + if (diff == 0) + ret = val; + /* even if found, keep searching for leftmost match */ + if (diff <= 0) + high = mid - 1; + else + low = mid + 1; + } + return ret; +} + +/* If a member of a split BTF struct/union refers to a base BTF + * struct/union, mark that struct/union id temporarily in the id_map + * with BTF_IS_EMBEDDED. Members can be const/restrict/volatile/typedef + * reference types, but if a pointer is encountered, the type is no longer + * considered embedded. + */ +static int btf_mark_embedded_composite_type_ids(struct btf_relocate *r, __u32 i) +{ + struct btf_type *t = btf_type_by_id(r->btf, i); + struct btf_field_iter it; + __u32 *id; + int err; + + if (!btf_is_composite(t)) + return 0; + + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); + if (err) + return err; + + while ((id = btf_field_iter_next(&it))) { + __u32 next_id = *id; + + while (next_id) { + t = btf_type_by_id(r->btf, next_id); + switch (btf_kind(t)) { + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_VOLATILE: + case BTF_KIND_TYPEDEF: + case BTF_KIND_TYPE_TAG: + next_id = t->type; + break; + case BTF_KIND_ARRAY: { + struct btf_array *a = btf_array(t); + + next_id = a->type; + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + if (next_id < r->nr_dist_base_types) + r->id_map[next_id] = BTF_IS_EMBEDDED; + next_id = 0; + break; + default: + next_id = 0; + break; + } + } + } + + return 0; +} + +/* Build a map from distilled base BTF ids to base BTF ids. To do so, iterate + * through base BTF looking up distilled type (using binary search) equivalents. + */ +static int btf_relocate_map_distilled_base(struct btf_relocate *r) +{ + struct btf_name_info *info, *info_end; + struct btf_type *base_t, *dist_t; + __u8 *base_name_cnt = NULL; + int err = 0; + __u32 id; + + /* generate a sort index array of name/type ids sorted by name for + * distilled base BTF to speed name-based lookups. + */ + info = calloc(r->nr_dist_base_types, sizeof(*info)); + if (!info) { + err = -ENOMEM; + goto done; + } + info_end = info + r->nr_dist_base_types; + for (id = 0; id < r->nr_dist_base_types; id++) { + dist_t = btf_type_by_id(r->dist_base_btf, id); + info[id].name = btf__name_by_offset(r->dist_base_btf, dist_t->name_off); + info[id].id = id; + info[id].size = dist_t->size; + info[id].needs_size = true; + } + qsort(info, r->nr_dist_base_types, sizeof(*info), cmp_btf_name_size); + + /* Mark distilled base struct/union members of split BTF structs/unions + * in id_map with BTF_IS_EMBEDDED; this signals that these types + * need to match both name and size, otherwise embedding the base + * struct/union in the split type is invalid. + */ + for (id = r->nr_dist_base_types; id < r->nr_dist_base_types + r->nr_split_types; id++) { + err = btf_mark_embedded_composite_type_ids(r, id); + if (err) + goto done; + } + + /* Collect name counts for composite types in base BTF. If multiple + * instances of a struct/union of the same name exist, we need to use + * size to determine which to map to since name alone is ambiguous. + */ + base_name_cnt = calloc(r->base_str_len, sizeof(*base_name_cnt)); + if (!base_name_cnt) { + err = -ENOMEM; + goto done; + } + for (id = 1; id < r->nr_base_types; id++) { + base_t = btf_type_by_id(r->base_btf, id); + if (!btf_is_composite(base_t) || !base_t->name_off) + continue; + if (base_name_cnt[base_t->name_off] < 255) + base_name_cnt[base_t->name_off]++; + } + + /* Now search base BTF for matching distilled base BTF types. */ + for (id = 1; id < r->nr_base_types; id++) { + struct btf_name_info *dist_info, base_info = {}; + int dist_kind, base_kind; + + base_t = btf_type_by_id(r->base_btf, id); + /* distilled base consists of named types only. */ + if (!base_t->name_off) + continue; + base_kind = btf_kind(base_t); + base_info.id = id; + base_info.name = btf__name_by_offset(r->base_btf, base_t->name_off); + switch (base_kind) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_ENUM64: + /* These types should match both name and size */ + base_info.needs_size = true; + base_info.size = base_t->size; + break; + case BTF_KIND_FWD: + /* No size considerations for fwds. */ + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + /* Size only needs to be used for struct/union if there + * are multiple types in base BTF with the same name. + * If there are multiple _distilled_ types with the same + * name (a very unlikely scenario), that doesn't matter + * unless corresponding _base_ types to match them are + * missing. + */ + base_info.needs_size = base_name_cnt[base_t->name_off] > 1; + base_info.size = base_t->size; + break; + default: + continue; + } + /* iterate over all matching distilled base types */ + for (dist_info = search_btf_name_size(&base_info, info, r->nr_dist_base_types); + dist_info != NULL && dist_info < info_end && + cmp_btf_name_size(&base_info, dist_info) == 0; + dist_info++) { + if (!dist_info->id || dist_info->id >= r->nr_dist_base_types) { + pr_warn("base BTF id [%d] maps to invalid distilled base BTF id [%d]\n", + id, dist_info->id); + err = -EINVAL; + goto done; + } + dist_t = btf_type_by_id(r->dist_base_btf, dist_info->id); + dist_kind = btf_kind(dist_t); + + /* Validate that the found distilled type is compatible. + * Do not error out on mismatch as another match may + * occur for an identically-named type. + */ + switch (dist_kind) { + case BTF_KIND_FWD: + switch (base_kind) { + case BTF_KIND_FWD: + if (btf_kflag(dist_t) != btf_kflag(base_t)) + continue; + break; + case BTF_KIND_STRUCT: + if (btf_kflag(base_t)) + continue; + break; + case BTF_KIND_UNION: + if (!btf_kflag(base_t)) + continue; + break; + default: + continue; + } + break; + case BTF_KIND_INT: + if (dist_kind != base_kind || + btf_int_encoding(base_t) != btf_int_encoding(dist_t)) + continue; + break; + case BTF_KIND_FLOAT: + if (dist_kind != base_kind) + continue; + break; + case BTF_KIND_ENUM: + /* ENUM and ENUM64 are encoded as sized ENUM in + * distilled base BTF. + */ + if (base_kind != dist_kind && base_kind != BTF_KIND_ENUM64) + continue; + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + /* size verification is required for embedded + * struct/unions. + */ + if (r->id_map[dist_info->id] == BTF_IS_EMBEDDED && + base_t->size != dist_t->size) + continue; + break; + default: + continue; + } + if (r->id_map[dist_info->id] && + r->id_map[dist_info->id] != BTF_IS_EMBEDDED) { + /* we already have a match; this tells us that + * multiple base types of the same name + * have the same size, since for cases where + * multiple types have the same name we match + * on name and size. In this case, we have + * no way of determining which to relocate + * to in base BTF, so error out. + */ + pr_warn("distilled base BTF type '%s' [%u], size %u has multiple candidates of the same size (ids [%u, %u]) in base BTF\n", + base_info.name, dist_info->id, + base_t->size, id, r->id_map[dist_info->id]); + err = -EINVAL; + goto done; + } + /* map id and name */ + r->id_map[dist_info->id] = id; + r->str_map[dist_t->name_off] = base_t->name_off; + } + } + /* ensure all distilled BTF ids now have a mapping... */ + for (id = 1; id < r->nr_dist_base_types; id++) { + const char *name; + + if (r->id_map[id] && r->id_map[id] != BTF_IS_EMBEDDED) + continue; + dist_t = btf_type_by_id(r->dist_base_btf, id); + name = btf__name_by_offset(r->dist_base_btf, dist_t->name_off); + pr_warn("distilled base BTF type '%s' [%d] is not mapped to base BTF id\n", + name, id); + err = -EINVAL; + break; + } +done: + free(base_name_cnt); + free(info); + return err; +} + +/* distilled base should only have named int/float/enum/fwd/struct/union types. */ +static int btf_relocate_validate_distilled_base(struct btf_relocate *r) +{ + unsigned int i; + + for (i = 1; i < r->nr_dist_base_types; i++) { + struct btf_type *t = btf_type_by_id(r->dist_base_btf, i); + int kind = btf_kind(t); + + switch (kind) { + case BTF_KIND_INT: + case BTF_KIND_FLOAT: + case BTF_KIND_ENUM: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_FWD: + if (t->name_off) + break; + pr_warn("type [%d], kind [%d] is invalid for distilled base BTF; it is anonymous\n", + i, kind); + return -EINVAL; + default: + pr_warn("type [%d] in distilled based BTF has unexpected kind [%d]\n", + i, kind); + return -EINVAL; + } + } + return 0; +} + +static int btf_relocate_rewrite_strs(struct btf_relocate *r, __u32 i) +{ + struct btf_type *t = btf_type_by_id(r->btf, i); + struct btf_field_iter it; + __u32 *str_off; + int off, err; + + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS); + if (err) + return err; + + while ((str_off = btf_field_iter_next(&it))) { + if (!*str_off) + continue; + if (*str_off >= r->dist_str_len) { + *str_off += r->base_str_len - r->dist_str_len; + } else { + off = r->str_map[*str_off]; + if (!off) { + pr_warn("string '%s' [offset %u] is not mapped to base BTF\n", + btf__str_by_offset(r->btf, off), *str_off); + return -ENOENT; + } + *str_off = off; + } + } + return 0; +} + +/* If successful, output of relocation is updated BTF with base BTF pointing + * at base_btf, and type ids, strings adjusted accordingly. + */ +int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **id_map) +{ + unsigned int nr_types = btf__type_cnt(btf); + const struct btf_header *dist_base_hdr; + const struct btf_header *base_hdr; + struct btf_relocate r = {}; + int err = 0; + __u32 id, i; + + r.dist_base_btf = btf__base_btf(btf); + if (!base_btf || r.dist_base_btf == base_btf) + return -EINVAL; + + r.nr_dist_base_types = btf__type_cnt(r.dist_base_btf); + r.nr_base_types = btf__type_cnt(base_btf); + r.nr_split_types = nr_types - r.nr_dist_base_types; + r.btf = btf; + r.base_btf = base_btf; + + r.id_map = calloc(nr_types, sizeof(*r.id_map)); + r.str_map = calloc(btf_header(r.dist_base_btf)->str_len, sizeof(*r.str_map)); + dist_base_hdr = btf_header(r.dist_base_btf); + base_hdr = btf_header(r.base_btf); + r.dist_str_len = dist_base_hdr->str_len; + r.base_str_len = base_hdr->str_len; + if (!r.id_map || !r.str_map) { + err = -ENOMEM; + goto err_out; + } + + err = btf_relocate_validate_distilled_base(&r); + if (err) + goto err_out; + + /* Split BTF ids need to be adjusted as base and distilled base + * have different numbers of types, changing the start id of split + * BTF. + */ + for (id = r.nr_dist_base_types; id < nr_types; id++) + r.id_map[id] = id + r.nr_base_types - r.nr_dist_base_types; + + /* Build a map from distilled base ids to actual base BTF ids; it is used + * to update split BTF id references. Also build a str_map mapping from + * distilled base BTF names to base BTF names. + */ + err = btf_relocate_map_distilled_base(&r); + if (err) + goto err_out; + + /* Next, rewrite type ids in split BTF, replacing split ids with updated + * ids based on number of types in base BTF, and base ids with + * relocated ids from base_btf. + */ + for (i = 0, id = r.nr_dist_base_types; i < r.nr_split_types; i++, id++) { + err = btf_relocate_rewrite_type_id(&r, id); + if (err) + goto err_out; + } + /* String offsets now need to be updated using the str_map. */ + for (i = 0; i < r.nr_split_types; i++) { + err = btf_relocate_rewrite_strs(&r, i + r.nr_dist_base_types); + if (err) + goto err_out; + } + /* Finally reset base BTF to be base_btf */ + btf_set_base_btf(btf, base_btf); + + if (id_map) { + *id_map = r.id_map; + r.id_map = NULL; + } +err_out: + free(r.id_map); + free(r.str_map); + return err; +} diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c new file mode 100644 index 000000000000..295dbda24580 --- /dev/null +++ b/tools/lib/bpf/elf.c @@ -0,0 +1,558 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <libelf.h> +#include <gelf.h> +#include <fcntl.h> +#include <linux/kernel.h> + +#include "libbpf_internal.h" + +/* A SHT_GNU_versym section holds 16-bit words. This bit is set if + * the symbol is hidden and can only be seen when referenced using an + * explicit version number. This is a GNU extension. + */ +#define VERSYM_HIDDEN 0x8000 + +/* This is the mask for the rest of the data in a word read from a + * SHT_GNU_versym section. + */ +#define VERSYM_VERSION 0x7fff + +int elf_open(const char *binary_path, struct elf_fd *elf_fd) +{ + int fd, ret; + Elf *elf; + + elf_fd->elf = NULL; + elf_fd->fd = -1; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn("elf: failed to init libelf for %s\n", binary_path); + return -LIBBPF_ERRNO__LIBELF; + } + fd = open(binary_path, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + ret = -errno; + pr_warn("elf: failed to open %s: %s\n", binary_path, errstr(ret)); + return ret; + } + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) { + pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1)); + close(fd); + return -LIBBPF_ERRNO__FORMAT; + } + elf_fd->fd = fd; + elf_fd->elf = elf; + return 0; +} + +void elf_close(struct elf_fd *elf_fd) +{ + if (!elf_fd) + return; + elf_end(elf_fd->elf); + close(elf_fd->fd); +} + +/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */ +static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn) +{ + while ((scn = elf_nextscn(elf, scn)) != NULL) { + GElf_Shdr sh; + + if (!gelf_getshdr(scn, &sh)) + continue; + if (sh.sh_type == sh_type) + return scn; + } + return NULL; +} + +struct elf_sym { + const char *name; + GElf_Sym sym; + GElf_Shdr sh; + int ver; + bool hidden; +}; + +struct elf_sym_iter { + Elf *elf; + Elf_Data *syms; + Elf_Data *versyms; + Elf_Data *verdefs; + size_t nr_syms; + size_t strtabidx; + size_t verdef_strtabidx; + size_t next_sym_idx; + struct elf_sym sym; + int st_type; +}; + +static int elf_sym_iter_new(struct elf_sym_iter *iter, + Elf *elf, const char *binary_path, + int sh_type, int st_type) +{ + Elf_Scn *scn = NULL; + GElf_Ehdr ehdr; + GElf_Shdr sh; + + memset(iter, 0, sizeof(*iter)); + + if (!gelf_getehdr(elf, &ehdr)) { + pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1)); + return -EINVAL; + } + + scn = elf_find_next_scn_by_type(elf, sh_type, NULL); + if (!scn) { + pr_debug("elf: failed to find symbol table ELF sections in '%s'\n", + binary_path); + return -ENOENT; + } + + if (!gelf_getshdr(scn, &sh)) + return -EINVAL; + + iter->strtabidx = sh.sh_link; + iter->syms = elf_getdata(scn, 0); + if (!iter->syms) { + pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n", + binary_path, elf_errmsg(-1)); + return -EINVAL; + } + iter->nr_syms = iter->syms->d_size / sh.sh_entsize; + iter->elf = elf; + iter->st_type = st_type; + + /* Version symbol table is meaningful to dynsym only */ + if (sh_type != SHT_DYNSYM) + return 0; + + scn = elf_find_next_scn_by_type(elf, SHT_GNU_versym, NULL); + if (!scn) + return 0; + iter->versyms = elf_getdata(scn, 0); + + scn = elf_find_next_scn_by_type(elf, SHT_GNU_verdef, NULL); + if (!scn) + return 0; + + iter->verdefs = elf_getdata(scn, 0); + if (!iter->verdefs || !gelf_getshdr(scn, &sh)) { + pr_warn("elf: failed to get verdef ELF section in '%s'\n", binary_path); + return -EINVAL; + } + iter->verdef_strtabidx = sh.sh_link; + + return 0; +} + +static struct elf_sym *elf_sym_iter_next(struct elf_sym_iter *iter) +{ + struct elf_sym *ret = &iter->sym; + GElf_Sym *sym = &ret->sym; + const char *name = NULL; + GElf_Versym versym; + Elf_Scn *sym_scn; + size_t idx; + + for (idx = iter->next_sym_idx; idx < iter->nr_syms; idx++) { + if (!gelf_getsym(iter->syms, idx, sym)) + continue; + if (GELF_ST_TYPE(sym->st_info) != iter->st_type) + continue; + name = elf_strptr(iter->elf, iter->strtabidx, sym->st_name); + if (!name) + continue; + sym_scn = elf_getscn(iter->elf, sym->st_shndx); + if (!sym_scn) + continue; + if (!gelf_getshdr(sym_scn, &ret->sh)) + continue; + + iter->next_sym_idx = idx + 1; + ret->name = name; + ret->ver = 0; + ret->hidden = false; + + if (iter->versyms) { + if (!gelf_getversym(iter->versyms, idx, &versym)) + continue; + ret->ver = versym & VERSYM_VERSION; + ret->hidden = versym & VERSYM_HIDDEN; + } + return ret; + } + + return NULL; +} + +static const char *elf_get_vername(struct elf_sym_iter *iter, int ver) +{ + GElf_Verdaux verdaux; + GElf_Verdef verdef; + int offset; + + if (!iter->verdefs) + return NULL; + + offset = 0; + while (gelf_getverdef(iter->verdefs, offset, &verdef)) { + if (verdef.vd_ndx != ver) { + if (!verdef.vd_next) + break; + + offset += verdef.vd_next; + continue; + } + + if (!gelf_getverdaux(iter->verdefs, offset + verdef.vd_aux, &verdaux)) + break; + + return elf_strptr(iter->elf, iter->verdef_strtabidx, verdaux.vda_name); + + } + return NULL; +} + +static bool symbol_match(struct elf_sym_iter *iter, int sh_type, struct elf_sym *sym, + const char *name, size_t name_len, const char *lib_ver) +{ + const char *ver_name; + + /* Symbols are in forms of func, func@LIB_VER or func@@LIB_VER + * make sure the func part matches the user specified name + */ + if (strncmp(sym->name, name, name_len) != 0) + return false; + + /* ...but we don't want a search for "foo" to match 'foo2" also, so any + * additional characters in sname should be of the form "@@LIB". + */ + if (sym->name[name_len] != '\0' && sym->name[name_len] != '@') + return false; + + /* If user does not specify symbol version, then we got a match */ + if (!lib_ver) + return true; + + /* If user specifies symbol version, for dynamic symbols, + * get version name from ELF verdef section for comparison. + */ + if (sh_type == SHT_DYNSYM) { + ver_name = elf_get_vername(iter, sym->ver); + if (!ver_name) + return false; + return strcmp(ver_name, lib_ver) == 0; + } + + /* For normal symbols, it is already in form of func@LIB_VER */ + return strcmp(sym->name, name) == 0; +} + +/* Transform symbol's virtual address (absolute for binaries and relative + * for shared libs) into file offset, which is what kernel is expecting + * for uprobe/uretprobe attachment. + * See Documentation/trace/uprobetracer.rst for more details. This is done + * by looking up symbol's containing section's header and using iter's virtual + * address (sh_addr) and corresponding file offset (sh_offset) to transform + * sym.st_value (virtual address) into desired final file offset. + */ +static unsigned long elf_sym_offset(struct elf_sym *sym) +{ + return sym->sym.st_value - sym->sh.sh_addr + sym->sh.sh_offset; +} + +/* Find offset of function name in the provided ELF object. "binary_path" is + * the path to the ELF binary represented by "elf", and only used for error + * reporting matters. "name" matches symbol name or name@@LIB for library + * functions. + */ +long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name) +{ + int i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB }; + const char *at_symbol, *lib_ver; + bool is_shared_lib; + long ret = -ENOENT; + size_t name_len; + GElf_Ehdr ehdr; + + if (!gelf_getehdr(elf, &ehdr)) { + pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1)); + ret = -LIBBPF_ERRNO__FORMAT; + goto out; + } + /* for shared lib case, we do not need to calculate relative offset */ + is_shared_lib = ehdr.e_type == ET_DYN; + + /* Does name specify "@@LIB_VER" or "@LIB_VER" ? */ + at_symbol = strchr(name, '@'); + if (at_symbol) { + name_len = at_symbol - name; + /* skip second @ if it's @@LIB_VER case */ + if (at_symbol[1] == '@') + at_symbol++; + lib_ver = at_symbol + 1; + } else { + name_len = strlen(name); + lib_ver = NULL; + } + + /* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if + * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically + * linked binary may not have SHT_DYMSYM, so absence of a section should not be + * reported as a warning/error. + */ + for (i = 0; i < ARRAY_SIZE(sh_types); i++) { + struct elf_sym_iter iter; + struct elf_sym *sym; + int last_bind = -1; + int cur_bind; + + ret = elf_sym_iter_new(&iter, elf, binary_path, sh_types[i], STT_FUNC); + if (ret == -ENOENT) + continue; + if (ret) + goto out; + + while ((sym = elf_sym_iter_next(&iter))) { + if (!symbol_match(&iter, sh_types[i], sym, name, name_len, lib_ver)) + continue; + + cur_bind = GELF_ST_BIND(sym->sym.st_info); + + if (ret > 0) { + /* handle multiple matches */ + if (elf_sym_offset(sym) == ret) { + /* same offset, no problem */ + continue; + } else if (last_bind != STB_WEAK && cur_bind != STB_WEAK) { + /* Only accept one non-weak bind. */ + pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n", + sym->name, name, binary_path); + ret = -LIBBPF_ERRNO__FORMAT; + goto out; + } else if (cur_bind == STB_WEAK) { + /* already have a non-weak bind, and + * this is a weak bind, so ignore. + */ + continue; + } + } + + ret = elf_sym_offset(sym); + last_bind = cur_bind; + } + if (ret > 0) + break; + } + + if (ret > 0) { + pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path, + ret); + } else { + if (ret == 0) { + pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path, + is_shared_lib ? "should not be 0 in a shared library" : + "try using shared library path instead"); + ret = -ENOENT; + } else { + pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path); + } + } +out: + return ret; +} + +/* Find offset of function name in ELF object specified by path. "name" matches + * symbol name or name@@LIB for library functions. + */ +long elf_find_func_offset_from_file(const char *binary_path, const char *name) +{ + struct elf_fd elf_fd; + long ret = -ENOENT; + + ret = elf_open(binary_path, &elf_fd); + if (ret) + return ret; + ret = elf_find_func_offset(elf_fd.elf, binary_path, name); + elf_close(&elf_fd); + return ret; +} + +struct symbol { + const char *name; + int bind; + int idx; +}; + +static int symbol_cmp(const void *a, const void *b) +{ + const struct symbol *sym_a = a; + const struct symbol *sym_b = b; + + return strcmp(sym_a->name, sym_b->name); +} + +/* + * Return offsets in @poffsets for symbols specified in @syms array argument. + * On success returns 0 and offsets are returned in allocated array with @cnt + * size, that needs to be released by the caller. + */ +int elf_resolve_syms_offsets(const char *binary_path, int cnt, + const char **syms, unsigned long **poffsets, + int st_type) +{ + int sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB }; + int err = 0, i, cnt_done = 0; + unsigned long *offsets; + struct symbol *symbols; + struct elf_fd elf_fd; + + err = elf_open(binary_path, &elf_fd); + if (err) + return err; + + offsets = calloc(cnt, sizeof(*offsets)); + symbols = calloc(cnt, sizeof(*symbols)); + + if (!offsets || !symbols) { + err = -ENOMEM; + goto out; + } + + for (i = 0; i < cnt; i++) { + symbols[i].name = syms[i]; + symbols[i].idx = i; + } + + qsort(symbols, cnt, sizeof(*symbols), symbol_cmp); + + for (i = 0; i < ARRAY_SIZE(sh_types); i++) { + struct elf_sym_iter iter; + struct elf_sym *sym; + + err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], st_type); + if (err == -ENOENT) + continue; + if (err) + goto out; + + while ((sym = elf_sym_iter_next(&iter))) { + unsigned long sym_offset = elf_sym_offset(sym); + int bind = GELF_ST_BIND(sym->sym.st_info); + struct symbol *found, tmp = { + .name = sym->name, + }; + unsigned long *offset; + + found = bsearch(&tmp, symbols, cnt, sizeof(*symbols), symbol_cmp); + if (!found) + continue; + + offset = &offsets[found->idx]; + if (*offset > 0) { + /* same offset, no problem */ + if (*offset == sym_offset) + continue; + /* handle multiple matches */ + if (found->bind != STB_WEAK && bind != STB_WEAK) { + /* Only accept one non-weak bind. */ + pr_warn("elf: ambiguous match found '%s@%lu' in '%s' previous offset %lu\n", + sym->name, sym_offset, binary_path, *offset); + err = -ESRCH; + goto out; + } else if (bind == STB_WEAK) { + /* already have a non-weak bind, and + * this is a weak bind, so ignore. + */ + continue; + } + } else { + cnt_done++; + } + *offset = sym_offset; + found->bind = bind; + } + } + + if (cnt != cnt_done) { + err = -ENOENT; + goto out; + } + + *poffsets = offsets; + +out: + free(symbols); + if (err) + free(offsets); + elf_close(&elf_fd); + return err; +} + +/* + * Return offsets in @poffsets for symbols specified by @pattern argument. + * On success returns 0 and offsets are returned in allocated @poffsets + * array with the @pctn size, that needs to be released by the caller. + */ +int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern, + unsigned long **poffsets, size_t *pcnt) +{ + int sh_types[2] = { SHT_SYMTAB, SHT_DYNSYM }; + unsigned long *offsets = NULL; + size_t cap = 0, cnt = 0; + struct elf_fd elf_fd; + int err = 0, i; + + err = elf_open(binary_path, &elf_fd); + if (err) + return err; + + for (i = 0; i < ARRAY_SIZE(sh_types); i++) { + struct elf_sym_iter iter; + struct elf_sym *sym; + + err = elf_sym_iter_new(&iter, elf_fd.elf, binary_path, sh_types[i], STT_FUNC); + if (err == -ENOENT) + continue; + if (err) + goto out; + + while ((sym = elf_sym_iter_next(&iter))) { + if (!glob_match(sym->name, pattern)) + continue; + + err = libbpf_ensure_mem((void **) &offsets, &cap, sizeof(*offsets), + cnt + 1); + if (err) + goto out; + + offsets[cnt++] = elf_sym_offset(sym); + } + + /* If we found anything in the first symbol section, + * do not search others to avoid duplicates. + */ + if (cnt) + break; + } + + if (cnt) { + *poffsets = offsets; + *pcnt = cnt; + } else { + err = -ENOENT; + } + +out: + if (err) + free(offsets); + elf_close(&elf_fd); + return err; +} diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c new file mode 100644 index 000000000000..b842b83e2480 --- /dev/null +++ b/tools/lib/bpf/features.c @@ -0,0 +1,609 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <linux/kernel.h> +#include <linux/filter.h> +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_common.h" +#include "libbpf_internal.h" + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +int probe_fd(int fd) +{ + if (fd >= 0) + close(fd); + return fd >= 0; +} + +static int probe_kern_prog_name(int token_fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.license = ptr_to_u64("GPL"); + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)ARRAY_SIZE(insns); + attr.prog_token_fd = token_fd; + if (token_fd) + attr.prog_flags |= BPF_F_TOKEN_FD; + libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); + + /* make sure loading with name works */ + ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); + return probe_fd(ret); +} + +static int probe_kern_global_data(int token_fd) +{ + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_map_create_opts, map_opts, + .token_fd = token_fd, + .map_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + int ret, map, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts); + if (map < 0) { + ret = -errno; + pr_warn("Error in %s(): %s. Couldn't create simple array map.\n", + __func__, errstr(ret)); + return ret; + } + + insns[0].imm = map; + + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts); + close(map); + return probe_fd(ret); +} + +static int probe_kern_btf(int token_fd) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_func(int token_fd) +{ + static const char strs[] = "\0int\0x\0a"; + /* void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_func_global(int token_fd) +{ + static const char strs[] = "\0int\0x\0a"; + /* static void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_datasec(int token_fd) +{ + static const char strs[] = "\0x\0.data"; + /* static int a; */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* DATASEC val */ /* [3] */ + BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_qmark_datasec(int token_fd) +{ + static const char strs[] = "\0x\0?.data"; + /* static int a; */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* DATASEC ?.data */ /* [3] */ + BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_float(int token_fd) +{ + static const char strs[] = "\0float"; + __u32 types[] = { + /* float */ + BTF_TYPE_FLOAT_ENC(1, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_decl_tag(int token_fd) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* attr */ + BTF_TYPE_DECL_TAG_ENC(1, 2, -1), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_type_tag(int token_fd) +{ + 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(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_array_mmap(int token_fd) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, + .map_flags = BPF_F_MMAPABLE | (token_fd ? BPF_F_TOKEN_FD : 0), + .token_fd = token_fd, + ); + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); + return probe_fd(fd); +} + +static int probe_kern_exp_attach_type(int token_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + /* 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 + */ + 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(int token_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + 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 */ + BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ + BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ + 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); + + fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(fd); +} + +static int probe_prog_bind_map(int token_fd) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_map_create_opts, map_opts, + .token_fd = token_fd, + .map_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts); + if (map < 0) { + ret = -errno; + pr_warn("Error in %s(): %s. Couldn't create simple array map.\n", + __func__, errstr(ret)); + return ret; + } + + prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts); + if (prog < 0) { + close(map); + return 0; + } + + ret = bpf_prog_bind_map(prog, map, NULL); + + close(map); + close(prog); + + return ret >= 0; +} + +static int probe_module_btf(int token_fd) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + struct bpf_btf_info info; + __u32 len = sizeof(info); + char name[16]; + int fd, err; + + fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd); + if (fd < 0) + return 0; /* BTF not supported at all */ + + memset(&info, 0, sizeof(info)); + info.name = ptr_to_u64(name); + info.name_len = sizeof(name); + + /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; + * kernel's module BTF support coincides with support for + * name/name_len fields in struct bpf_btf_info. + */ + err = bpf_btf_get_info_by_fd(fd, &info, &len); + close(fd); + return !err; +} + +static int probe_perf_link(int token_fd) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + int prog_fd, link_fd, err; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", + insns, ARRAY_SIZE(insns), &opts); + if (prog_fd < 0) + return -errno; + + /* use invalid perf_event FD to get EBADF, if link is supported; + * otherwise EINVAL should be returned + */ + link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + +static int probe_uprobe_multi_link(int token_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, load_opts, + .expected_attach_type = BPF_TRACE_UPROBE_MULTI, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + LIBBPF_OPTS(bpf_link_create_opts, link_opts); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, link_fd, err; + unsigned long offset = 0; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", + insns, ARRAY_SIZE(insns), &load_opts); + if (prog_fd < 0) + return -errno; + + /* Creating uprobe in '/' binary should fail with -EBADF. */ + link_opts.uprobe_multi.path = "/"; + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0 || err != -EBADF) { + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + return 0; + } + + /* Initial multi-uprobe support in kernel didn't handle PID filtering + * correctly (it was doing thread filtering, not process filtering). + * So now we'll detect if PID filtering logic was fixed, and, if not, + * we'll pretend multi-uprobes are not supported, if not. + * Multi-uprobes are used in USDT attachment logic, and we need to be + * conservative here, because multi-uprobe selection happens early at + * load time, while the use of PID filtering is known late at + * attachment time, at which point it's too late to undo multi-uprobe + * selection. + * + * Creating uprobe with pid == -1 for (invalid) '/' binary will fail + * early with -EINVAL on kernels with fixed PID filtering logic; + * otherwise -ESRCH would be returned if passed correct binary path + * (but we'll just get -BADF, of course). + */ + link_opts.uprobe_multi.pid = -1; /* invalid PID */ + link_opts.uprobe_multi.path = "/"; /* invalid path */ + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EINVAL; +} + +static int probe_kern_bpf_cookie(int token_fd) +{ + struct bpf_insn insns[] = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + int ret, insn_cnt = ARRAY_SIZE(insns); + + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(ret); +} + +static int probe_kern_btf_enum64(int token_fd) +{ + static const char strs[] = "\0enum64"; + __u32 types[] = { + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_arg_ctx_tag(int token_fd) +{ + static const char strs[] = "\0a\0b\0arg:ctx\0"; + const __u32 types[] = { + /* [1] INT */ + BTF_TYPE_INT_ENC(1 /* "a" */, BTF_INT_SIGNED, 0, 32, 4), + /* [2] PTR -> VOID */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + /* [3] FUNC_PROTO `int(void *a)` */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1), + BTF_PARAM_ENC(1 /* "a" */, 2), + /* [4] FUNC 'a' -> FUNC_PROTO (main prog) */ + BTF_TYPE_ENC(1 /* "a" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 3), + /* [5] FUNC_PROTO `int(void *b __arg_ctx)` */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 1), + BTF_PARAM_ENC(3 /* "b" */, 2), + /* [6] FUNC 'b' -> FUNC_PROTO (subprog) */ + BTF_TYPE_ENC(3 /* "b" */, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 5), + /* [7] DECL_TAG 'arg:ctx' -> func 'b' arg 'b' */ + BTF_TYPE_DECL_TAG_ENC(5 /* "arg:ctx" */, 6, 0), + }; + const struct bpf_insn insns[] = { + /* main prog */ + BPF_CALL_REL(+1), + BPF_EXIT_INSN(), + /* global subprog */ + BPF_EMIT_CALL(BPF_FUNC_get_func_ip), /* needs PTR_TO_CTX */ + BPF_EXIT_INSN(), + }; + const struct bpf_func_info_min func_infos[] = { + { 0, 4 }, /* main prog -> FUNC 'a' */ + { 2, 6 }, /* subprog -> FUNC 'b' */ + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .token_fd = token_fd, + .prog_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); + int prog_fd, btf_fd, insn_cnt = ARRAY_SIZE(insns); + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd); + if (btf_fd < 0) + return 0; + + opts.prog_btf_fd = btf_fd; + opts.func_info = &func_infos; + opts.func_info_cnt = ARRAY_SIZE(func_infos); + opts.func_info_rec_size = sizeof(func_infos[0]); + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, "det_arg_ctx", + "GPL", insns, insn_cnt, &opts); + close(btf_fd); + + return probe_fd(prog_fd); +} + +typedef int (*feature_probe_fn)(int /* token_fd */); + +static struct kern_feature_cache feature_cache; + +static struct kern_feature_desc { + const char *desc; + feature_probe_fn probe; +} feature_probes[__FEAT_CNT] = { + [FEAT_PROG_NAME] = { + "BPF program name", probe_kern_prog_name, + }, + [FEAT_GLOBAL_DATA] = { + "global variables", probe_kern_global_data, + }, + [FEAT_BTF] = { + "minimal BTF", probe_kern_btf, + }, + [FEAT_BTF_FUNC] = { + "BTF functions", probe_kern_btf_func, + }, + [FEAT_BTF_GLOBAL_FUNC] = { + "BTF global function", probe_kern_btf_func_global, + }, + [FEAT_BTF_DATASEC] = { + "BTF data section and variable", probe_kern_btf_datasec, + }, + [FEAT_ARRAY_MMAP] = { + "ARRAY map mmap()", probe_kern_array_mmap, + }, + [FEAT_EXP_ATTACH_TYPE] = { + "BPF_PROG_LOAD expected_attach_type attribute", + probe_kern_exp_attach_type, + }, + [FEAT_PROBE_READ_KERN] = { + "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, + }, + [FEAT_PROG_BIND_MAP] = { + "BPF_PROG_BIND_MAP support", probe_prog_bind_map, + }, + [FEAT_MODULE_BTF] = { + "module BTF support", probe_module_btf, + }, + [FEAT_BTF_FLOAT] = { + "BTF_KIND_FLOAT support", probe_kern_btf_float, + }, + [FEAT_PERF_LINK] = { + "BPF perf link support", probe_perf_link, + }, + [FEAT_BTF_DECL_TAG] = { + "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, + }, + [FEAT_BTF_TYPE_TAG] = { + "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, + }, + [FEAT_MEMCG_ACCOUNT] = { + "memcg-based memory accounting", probe_memcg_account, + }, + [FEAT_BPF_COOKIE] = { + "BPF cookie support", probe_kern_bpf_cookie, + }, + [FEAT_BTF_ENUM64] = { + "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, + }, + [FEAT_SYSCALL_WRAPPER] = { + "Kernel using syscall wrapper", probe_kern_syscall_wrapper, + }, + [FEAT_UPROBE_MULTI_LINK] = { + "BPF multi-uprobe link support", probe_uprobe_multi_link, + }, + [FEAT_ARG_CTX_TAG] = { + "kernel-side __arg_ctx tag", probe_kern_arg_ctx_tag, + }, + [FEAT_BTF_QMARK_DATASEC] = { + "BTF DATASEC names starting from '?'", probe_kern_btf_qmark_datasec, + }, +}; + +bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id) +{ + struct kern_feature_desc *feat = &feature_probes[feat_id]; + int ret; + + /* assume global feature cache, unless custom one is provided */ + if (!cache) + cache = &feature_cache; + + if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) { + ret = feat->probe(cache->token_fd); + if (ret > 0) { + WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED); + } else if (ret == 0) { + WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); + } else { + pr_warn("Detection of kernel %s support failed: %s\n", + feat->desc, errstr(ret)); + WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); + } + } + + return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED; +} diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 23f5c46708f8..cd5c2543f54d 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -4,6 +4,7 @@ #include <stdlib.h> #include <string.h> #include <errno.h> +#include <asm/byteorder.h> #include <linux/filter.h> #include <sys/param.h> #include "btf.h" @@ -13,7 +14,6 @@ #include "hashmap.h" #include "bpf_gen_internal.h" #include "skel_internal.h" -#include <asm/byteorder.h> #define MAX_USED_MAPS 64 #define MAX_USED_PROGS 32 @@ -109,6 +109,7 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in static int add_data(struct bpf_gen *gen, const void *data, __u32 size); static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off); +static void emit_signature_match(struct bpf_gen *gen); void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps) { @@ -151,6 +152,8 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps /* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */ emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); emit(gen, BPF_EXIT_INSN()); + if (OPTS_GET(gen->opts, gen_hash, false)) + emit_signature_match(gen); } static int add_data(struct bpf_gen *gen, const void *data, __u32 size) @@ -367,6 +370,8 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off) __emit_sys_close(gen); } +static void compute_sha_update_offsets(struct bpf_gen *gen); + int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) { int i; @@ -393,7 +398,10 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) blob_fd_array_off(gen, i)); emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0)); emit(gen, BPF_EXIT_INSN()); - pr_debug("gen: finish %d\n", gen->error); + if (OPTS_GET(gen->opts, gen_hash, false)) + compute_sha_update_offsets(gen); + + pr_debug("gen: finish %s\n", errstr(gen->error)); if (!gen->error) { struct gen_loader_opts *opts = gen->opts; @@ -401,6 +409,15 @@ int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) opts->insns_sz = gen->insn_cur - gen->insn_start; opts->data = gen->data_start; opts->data_sz = gen->data_cur - gen->data_start; + + /* use target endianness for embedded loader */ + if (gen->swapped_endian) { + struct bpf_insn *insn = (struct bpf_insn *)opts->insns; + int insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); + + for (i = 0; i < insn_cnt; i++) + bpf_insn_bswap(insn++); + } } return gen->error; } @@ -414,6 +431,44 @@ void bpf_gen__free(struct bpf_gen *gen) free(gen); } +/* + * Fields of bpf_attr are set to values in native byte-order before being + * written to the target-bound data blob, and may need endian conversion. + * This macro allows providing the correct value in situ more simply than + * writing a separate converter for *all fields* of *all records* included + * in union bpf_attr. Note that sizeof(rval) should match the assignment + * target to avoid runtime problems. + */ +#define tgt_endian(rval) ({ \ + typeof(rval) _val = (rval); \ + if (gen->swapped_endian) { \ + switch (sizeof(_val)) { \ + case 1: break; \ + case 2: _val = bswap_16(_val); break; \ + case 4: _val = bswap_32(_val); break; \ + case 8: _val = bswap_64(_val); break; \ + default: pr_warn("unsupported bswap size!\n"); \ + } \ + } \ + _val; \ +}) + +static void compute_sha_update_offsets(struct bpf_gen *gen) +{ + __u64 sha[SHA256_DWORD_SIZE]; + __u64 sha_dw; + int i; + + libbpf_sha256(gen->data_start, gen->data_cur - gen->data_start, (__u8 *)sha); + for (i = 0; i < SHA256_DWORD_SIZE; i++) { + struct bpf_insn *insn = + (struct bpf_insn *)(gen->insn_start + gen->hash_insn_offset[i]); + sha_dw = tgt_endian(sha[i]); + insn[0].imm = (__u32)sha_dw; + insn[1].imm = sha_dw >> 32; + } +} + void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, __u32 btf_raw_size) { @@ -422,11 +477,12 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: load_btf: size %d\n", btf_raw_size); btf_data = add_data(gen, btf_raw_data, btf_raw_size); - attr.btf_size = btf_raw_size; + attr.btf_size = tgt_endian(btf_raw_size); btf_load_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: load_btf: off %d size %d, attr: off %d size %d\n", + btf_data, btf_raw_size, btf_load_attr, attr_size); /* populate union bpf_attr with user provided log details */ move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_level), 4, @@ -457,28 +513,29 @@ void bpf_gen__map_create(struct bpf_gen *gen, union bpf_attr attr; memset(&attr, 0, attr_size); - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = value_size; - attr.map_flags = map_attr->map_flags; - attr.map_extra = map_attr->map_extra; + attr.map_type = tgt_endian(map_type); + attr.key_size = tgt_endian(key_size); + attr.value_size = tgt_endian(value_size); + attr.map_flags = tgt_endian(map_attr->map_flags); + attr.map_extra = tgt_endian(map_attr->map_extra); if (map_name) libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); - attr.numa_node = map_attr->numa_node; - attr.map_ifindex = map_attr->map_ifindex; - attr.max_entries = max_entries; - attr.btf_key_type_id = map_attr->btf_key_type_id; - attr.btf_value_type_id = map_attr->btf_value_type_id; - - pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n", - attr.map_name, map_idx, map_type, attr.btf_value_type_id); + attr.numa_node = tgt_endian(map_attr->numa_node); + attr.map_ifindex = tgt_endian(map_attr->map_ifindex); + attr.max_entries = tgt_endian(max_entries); + attr.btf_key_type_id = tgt_endian(map_attr->btf_key_type_id); + attr.btf_value_type_id = tgt_endian(map_attr->btf_value_type_id); map_create_attr = add_data(gen, &attr, attr_size); - if (attr.btf_value_type_id) + pr_debug("gen: map_create: %s idx %d type %d value_type_id %d, attr: off %d size %d\n", + map_name, map_idx, map_type, map_attr->btf_value_type_id, + map_create_attr, attr_size); + + if (map_attr->btf_value_type_id) /* populate union bpf_attr with btf_fd saved in the stack earlier */ move_stack2blob(gen, attr_field(map_create_attr, btf_fd), 4, stack_off(btf_fd)); - switch (attr.map_type) { + switch (map_type) { case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: move_stack2blob(gen, attr_field(map_create_attr, inner_map_fd), 4, @@ -498,8 +555,8 @@ void bpf_gen__map_create(struct bpf_gen *gen, /* emit MAP_CREATE command */ emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size); debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d", - attr.map_name, map_idx, map_type, value_size, - attr.btf_value_type_id); + map_name, map_idx, map_type, value_size, + map_attr->btf_value_type_id); emit_check_err(gen); /* remember map_fd in the stack, if successful */ if (map_idx < 0) { @@ -523,6 +580,29 @@ void bpf_gen__map_create(struct bpf_gen *gen, emit_sys_close_stack(gen, stack_off(inner_map_fd)); } +static void emit_signature_match(struct bpf_gen *gen) +{ + __s64 off; + int i; + + for (i = 0; i < SHA256_DWORD_SIZE; i++) { + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX, + 0, 0, 0, 0)); + emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, i * sizeof(__u64))); + gen->hash_insn_offset[i] = gen->insn_cur - gen->insn_start; + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_3, 0, 0, 0, 0, 0)); + + off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1; + if (is_simm16(off)) { + emit(gen, BPF_MOV64_IMM(BPF_REG_7, -EINVAL)); + emit(gen, BPF_JMP_REG(BPF_JNE, BPF_REG_2, BPF_REG_3, off)); + } else { + gen->error = -ERANGE; + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1)); + } + } +} + void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name, enum bpf_attach_type type) { @@ -560,7 +640,7 @@ static void emit_find_attach_target(struct bpf_gen *gen) } void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, - bool is_typeless, int kind, int insn_idx) + bool is_typeless, bool is_ld64, int kind, int insn_idx) { struct ksym_relo_desc *relo; @@ -574,6 +654,7 @@ void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, relo->name = name; relo->is_weak = is_weak; relo->is_typeless = is_typeless; + relo->is_ld64 = is_ld64; relo->kind = kind; relo->insn_idx = insn_idx; gen->relo_cnt++; @@ -586,9 +667,11 @@ static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_des int 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]; + kdesc = &gen->ksyms[i]; + if (kdesc->kind == relo->kind && kdesc->is_ld64 == relo->is_ld64 && + !strcmp(kdesc->name, relo->name)) { + kdesc->ref++; + return kdesc; } } kdesc = libbpf_reallocarray(gen->ksyms, gen->nr_ksyms + 1, sizeof(*kdesc)); @@ -603,6 +686,7 @@ static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_des kdesc->ref = 1; kdesc->off = 0; kdesc->insn = 0; + kdesc->is_ld64 = relo->is_ld64; return kdesc; } @@ -699,17 +783,17 @@ static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo /* 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))); - /* store BTF fd in slot */ + /* store BTF fd in slot, 0 for vmlinux */ emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0)); + /* jump to insn[insn_idx].off 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, 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: @@ -780,12 +864,12 @@ log: emit_ksym_relo_log(gen, relo, kdesc->ref); } -static __u32 src_reg_mask(void) +static __u32 src_reg_mask(struct bpf_gen *gen) { -#if defined(__LITTLE_ENDIAN_BITFIELD) - return 0x0f; /* src_reg,dst_reg,... */ -#elif defined(__BIG_ENDIAN_BITFIELD) - return 0xf0; /* dst_reg,src_reg,... */ +#if defined(__LITTLE_ENDIAN_BITFIELD) /* src_reg,dst_reg,... */ + return gen->swapped_endian ? 0xf0 : 0x0f; +#elif defined(__BIG_ENDIAN_BITFIELD) /* dst_reg,src_reg,... */ + return gen->swapped_endian ? 0x0f : 0xf0; #else #error "Unsupported bit endianness, cannot proceed" #endif @@ -804,11 +888,13 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, return; /* try to copy from existing ldimm64 insn */ if (kdesc->ref > 1) { - move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4, - 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)); - /* jump over src_reg adjustment if imm is not 0, reuse BPF_REG_0 from move_blob2blob */ + move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4, + kdesc->insn + offsetof(struct bpf_insn, imm)); + /* jump over src_reg adjustment if imm (btf_id) is not 0, reuse BPF_REG_0 from move_blob2blob + * If btf_id is zero, clear BPF_PSEUDO_BTF_ID flag in src_reg of ld_imm64 insn + */ emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3)); goto clear_src_reg; } @@ -831,10 +917,10 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, 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)); + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 3)); clear_src_reg: /* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */ - reg_mask = src_reg_mask(); + reg_mask = src_reg_mask(gen); emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code))); emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask)); emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code))); @@ -862,23 +948,17 @@ static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn { int insn; - pr_debug("gen: emit_relo (%d): %s at %d\n", relo->kind, relo->name, relo->insn_idx); + pr_debug("gen: emit_relo (%d): %s at %d %s\n", + relo->kind, relo->name, relo->insn_idx, relo->is_ld64 ? "ld64" : "call"); insn = insns + sizeof(struct bpf_insn) * relo->insn_idx; emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_8, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, insn)); - switch (relo->kind) { - case BTF_KIND_VAR: + if (relo->is_ld64) { if (relo->is_typeless) emit_relo_ksym_typeless(gen, relo, insn); else emit_relo_ksym_btf(gen, relo, insn); - break; - case BTF_KIND_FUNC: + } else { emit_relo_kfunc_btf(gen, relo, insn); - break; - default: - pr_warn("Unknown relocation kind '%d'\n", relo->kind); - gen->error = -EDOM; - return; } } @@ -901,18 +981,20 @@ static void cleanup_core_relo(struct bpf_gen *gen) static void cleanup_relos(struct bpf_gen *gen, int insns) { + struct ksym_desc *kdesc; int i, insn; for (i = 0; i < gen->nr_ksyms; i++) { + kdesc = &gen->ksyms[i]; /* only close fds for typed ksyms and kfuncs */ - if (gen->ksyms[i].kind == BTF_KIND_VAR && !gen->ksyms[i].typeless) { + if (kdesc->is_ld64 && !kdesc->typeless) { /* close fd recorded in insn[insn_idx + 1].imm */ - insn = gen->ksyms[i].insn; + insn = kdesc->insn; insn += sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm); emit_sys_close_blob(gen, insn); - } else if (gen->ksyms[i].kind == BTF_KIND_FUNC) { - emit_sys_close_blob(gen, blob_fd_array_off(gen, gen->ksyms[i].off)); - if (gen->ksyms[i].off < MAX_FD_ARRAY_SZ) + } else if (!kdesc->is_ld64) { + emit_sys_close_blob(gen, blob_fd_array_off(gen, kdesc->off)); + if (kdesc->off < MAX_FD_ARRAY_SZ) gen->nr_fd_array--; } } @@ -929,48 +1011,94 @@ static void cleanup_relos(struct bpf_gen *gen, int insns) cleanup_core_relo(gen); } +/* Convert func, line, and core relo info blobs to target endianness */ +static void info_blob_bswap(struct bpf_gen *gen, int func_info, int line_info, + int core_relos, struct bpf_prog_load_opts *load_attr) +{ + struct bpf_func_info *fi = gen->data_start + func_info; + struct bpf_line_info *li = gen->data_start + line_info; + struct bpf_core_relo *cr = gen->data_start + core_relos; + int i; + + for (i = 0; i < load_attr->func_info_cnt; i++) + bpf_func_info_bswap(fi++); + + for (i = 0; i < load_attr->line_info_cnt; i++) + bpf_line_info_bswap(li++); + + for (i = 0; i < gen->core_relo_cnt; i++) + bpf_core_relo_bswap(cr++); +} + void bpf_gen__prog_load(struct bpf_gen *gen, enum bpf_prog_type prog_type, const char *prog_name, const char *license, struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *load_attr, int prog_idx) { + int func_info_tot_sz = load_attr->func_info_cnt * + load_attr->func_info_rec_size; + int line_info_tot_sz = load_attr->line_info_cnt * + load_attr->line_info_rec_size; + int core_relo_tot_sz = gen->core_relo_cnt * + sizeof(struct bpf_core_relo); int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos; int attr_size = offsetofend(union bpf_attr, core_relo_rec_size); union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n", - prog_type, insn_cnt, prog_idx); /* add license string to blob of bytes */ license_off = add_data(gen, license, strlen(license) + 1); /* add insns to blob of bytes */ insns_off = add_data(gen, insns, insn_cnt * sizeof(struct bpf_insn)); + pr_debug("gen: prog_load: prog_idx %d type %d insn off %d insns_cnt %zd license off %d\n", + prog_idx, prog_type, insns_off, insn_cnt, license_off); - attr.prog_type = prog_type; - attr.expected_attach_type = load_attr->expected_attach_type; - attr.attach_btf_id = load_attr->attach_btf_id; - attr.prog_ifindex = load_attr->prog_ifindex; - attr.kern_version = 0; - attr.insn_cnt = (__u32)insn_cnt; - attr.prog_flags = load_attr->prog_flags; + /* convert blob insns to target endianness */ + if (gen->swapped_endian) { + struct bpf_insn *insn = gen->data_start + insns_off; + int i; - attr.func_info_rec_size = load_attr->func_info_rec_size; - attr.func_info_cnt = load_attr->func_info_cnt; - func_info = add_data(gen, load_attr->func_info, - attr.func_info_cnt * attr.func_info_rec_size); - - attr.line_info_rec_size = load_attr->line_info_rec_size; - attr.line_info_cnt = load_attr->line_info_cnt; - line_info = add_data(gen, load_attr->line_info, - attr.line_info_cnt * attr.line_info_rec_size); + for (i = 0; i < insn_cnt; i++, insn++) + bpf_insn_bswap(insn); + } - attr.core_relo_rec_size = sizeof(struct bpf_core_relo); - attr.core_relo_cnt = gen->core_relo_cnt; - core_relos = add_data(gen, gen->core_relos, - attr.core_relo_cnt * attr.core_relo_rec_size); + attr.prog_type = tgt_endian(prog_type); + attr.expected_attach_type = tgt_endian(load_attr->expected_attach_type); + attr.attach_btf_id = tgt_endian(load_attr->attach_btf_id); + attr.prog_ifindex = tgt_endian(load_attr->prog_ifindex); + attr.kern_version = 0; + attr.insn_cnt = tgt_endian((__u32)insn_cnt); + attr.prog_flags = tgt_endian(load_attr->prog_flags); + + attr.func_info_rec_size = tgt_endian(load_attr->func_info_rec_size); + attr.func_info_cnt = tgt_endian(load_attr->func_info_cnt); + func_info = add_data(gen, load_attr->func_info, func_info_tot_sz); + pr_debug("gen: prog_load: func_info: off %d cnt %d rec size %d\n", + func_info, load_attr->func_info_cnt, + load_attr->func_info_rec_size); + + attr.line_info_rec_size = tgt_endian(load_attr->line_info_rec_size); + attr.line_info_cnt = tgt_endian(load_attr->line_info_cnt); + line_info = add_data(gen, load_attr->line_info, line_info_tot_sz); + pr_debug("gen: prog_load: line_info: off %d cnt %d rec size %d\n", + line_info, load_attr->line_info_cnt, + load_attr->line_info_rec_size); + + attr.core_relo_rec_size = tgt_endian((__u32)sizeof(struct bpf_core_relo)); + attr.core_relo_cnt = tgt_endian(gen->core_relo_cnt); + core_relos = add_data(gen, gen->core_relos, core_relo_tot_sz); + pr_debug("gen: prog_load: core_relos: off %d cnt %d rec size %zd\n", + core_relos, gen->core_relo_cnt, + sizeof(struct bpf_core_relo)); + + /* convert all info blobs to target endianness */ + if (gen->swapped_endian) + info_blob_bswap(gen, func_info, line_info, core_relos, load_attr); libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); prog_load_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: prog_load: attr: off %d size %d\n", + prog_load_attr, attr_size); /* populate union bpf_attr with a pointer to license */ emit_rel_store(gen, attr_field(prog_load_attr, license), license_off); @@ -1038,7 +1166,6 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, int zero = 0; memset(&attr, 0, attr_size); - pr_debug("gen: map_update_elem: idx %d\n", map_idx); value = add_data(gen, pvalue, value_size); key = add_data(gen, &zero, sizeof(zero)); @@ -1066,6 +1193,8 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); map_update_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: map_update_elem: idx %d, value: off %d size %d, attr: off %d size %d\n", + map_idx, value, value_size, map_update_attr, attr_size); move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, blob_fd_array_off(gen, map_idx)); emit_rel_store(gen, attr_field(map_update_attr, key), key); @@ -1082,14 +1211,16 @@ void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slo int attr_size = offsetofend(union bpf_attr, flags); int map_update_attr, key; union bpf_attr attr; + int tgt_slot; memset(&attr, 0, attr_size); - pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n", - outer_map_idx, slot, inner_map_idx); - key = add_data(gen, &slot, sizeof(slot)); + tgt_slot = tgt_endian(slot); + key = add_data(gen, &tgt_slot, sizeof(tgt_slot)); map_update_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: populate_outer_map: outer %d key %d inner %d, attr: off %d size %d\n", + outer_map_idx, slot, inner_map_idx, map_update_attr, attr_size); move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, blob_fd_array_off(gen, outer_map_idx)); emit_rel_store(gen, attr_field(map_update_attr, key), key); @@ -1110,8 +1241,9 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx) union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: map_freeze: idx %d\n", map_idx); map_freeze_attr = add_data(gen, &attr, attr_size); + pr_debug("gen: map_freeze: idx %d, attr: off %d size %d\n", + map_idx, map_freeze_attr, attr_size); move_blob2blob(gen, attr_field(map_freeze_attr, map_fd), 4, blob_fd_array_off(gen, map_idx)); /* emit MAP_FREEZE command */ diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index 0a5bf1937a7c..0c4f155e8eb7 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -80,16 +80,6 @@ struct hashmap { size_t sz; }; -#define HASHMAP_INIT(hash_fn, equal_fn, ctx) { \ - .hash_fn = (hash_fn), \ - .equal_fn = (equal_fn), \ - .ctx = (ctx), \ - .buckets = NULL, \ - .cap = 0, \ - .cap_bits = 0, \ - .sz = 0, \ -} - void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn, hashmap_equal_fn equal_fn, void *ctx); struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, @@ -176,8 +166,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value); * @bkt: integer used as a bucket loop cursor */ #define hashmap__for_each_entry(map, cur, bkt) \ - for (bkt = 0; bkt < map->cap; bkt++) \ - for (cur = map->buckets[bkt]; cur; cur = cur->next) + for (bkt = 0; bkt < (map)->cap; bkt++) \ + for (cur = (map)->buckets[bkt]; cur; cur = cur->next) /* * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe @@ -188,8 +178,8 @@ bool hashmap_find(const struct hashmap *map, long key, long *value); * @bkt: integer used as a bucket loop cursor */ #define hashmap__for_each_entry_safe(map, cur, tmp, bkt) \ - for (bkt = 0; bkt < map->cap; bkt++) \ - for (cur = map->buckets[bkt]; \ + for (bkt = 0; bkt < (map)->cap; bkt++) \ + for (cur = (map)->buckets[bkt]; \ cur && ({tmp = cur->next; true; }); \ cur = tmp) @@ -200,19 +190,19 @@ bool hashmap_find(const struct hashmap *map, long key, long *value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = map->buckets \ - ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + for (cur = (map)->buckets \ + ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \ : NULL; \ cur; \ cur = cur->next) \ - if (map->equal_fn(cur->key, (_key), map->ctx)) + if ((map)->equal_fn(cur->key, (_key), (map)->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = map->buckets \ - ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + for (cur = (map)->buckets \ + ? (map)->buckets[hash_bits((map)->hash_fn((_key), (map)->ctx), (map)->cap_bits)] \ : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ - if (map->equal_fn(cur->key, (_key), map->ctx)) + if ((map)->equal_fn(cur->key, (_key), (map)->ctx)) #endif /* __LIBBPF_HASHMAP_H */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 2a82f49ce16f..3dc8a8078815 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -33,8 +33,8 @@ #include <linux/filter.h> #include <linux/limits.h> #include <linux/perf_event.h> +#include <linux/bpf_perf_event.h> #include <linux/ring_buffer.h> -#include <linux/version.h> #include <sys/epoll.h> #include <sys/ioctl.h> #include <sys/mman.h> @@ -50,15 +50,19 @@ #include "libbpf.h" #include "bpf.h" #include "btf.h" -#include "str_error.h" #include "libbpf_internal.h" #include "hashmap.h" #include "bpf_gen_internal.h" +#include "zip.h" #ifndef BPF_FS_MAGIC #define BPF_FS_MAGIC 0xcafe4a11 #endif +#define MAX_EVENT_NAME_LEN 64 + +#define BPF_FS_DEFAULT_PATH "/sys/fs/bpf" + #define BPF_INSN_SZ (sizeof(struct bpf_insn)) /* vsprintf() in __base_pr() uses nonliteral format string. It may break @@ -70,6 +74,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog); +static int map_set_def_max_entries(struct bpf_map *map); static const char * const attach_type_name[] = { [BPF_CGROUP_INET_INGRESS] = "cgroup_inet_ingress", @@ -82,17 +87,22 @@ static const char * const attach_type_name[] = { [BPF_CGROUP_INET6_BIND] = "cgroup_inet6_bind", [BPF_CGROUP_INET4_CONNECT] = "cgroup_inet4_connect", [BPF_CGROUP_INET6_CONNECT] = "cgroup_inet6_connect", + [BPF_CGROUP_UNIX_CONNECT] = "cgroup_unix_connect", [BPF_CGROUP_INET4_POST_BIND] = "cgroup_inet4_post_bind", [BPF_CGROUP_INET6_POST_BIND] = "cgroup_inet6_post_bind", [BPF_CGROUP_INET4_GETPEERNAME] = "cgroup_inet4_getpeername", [BPF_CGROUP_INET6_GETPEERNAME] = "cgroup_inet6_getpeername", + [BPF_CGROUP_UNIX_GETPEERNAME] = "cgroup_unix_getpeername", [BPF_CGROUP_INET4_GETSOCKNAME] = "cgroup_inet4_getsockname", [BPF_CGROUP_INET6_GETSOCKNAME] = "cgroup_inet6_getsockname", + [BPF_CGROUP_UNIX_GETSOCKNAME] = "cgroup_unix_getsockname", [BPF_CGROUP_UDP4_SENDMSG] = "cgroup_udp4_sendmsg", [BPF_CGROUP_UDP6_SENDMSG] = "cgroup_udp6_sendmsg", + [BPF_CGROUP_UNIX_SENDMSG] = "cgroup_unix_sendmsg", [BPF_CGROUP_SYSCTL] = "cgroup_sysctl", [BPF_CGROUP_UDP4_RECVMSG] = "cgroup_udp4_recvmsg", [BPF_CGROUP_UDP6_RECVMSG] = "cgroup_udp6_recvmsg", + [BPF_CGROUP_UNIX_RECVMSG] = "cgroup_unix_recvmsg", [BPF_CGROUP_GETSOCKOPT] = "cgroup_getsockopt", [BPF_CGROUP_SETSOCKOPT] = "cgroup_setsockopt", [BPF_SK_SKB_STREAM_PARSER] = "sk_skb_stream_parser", @@ -116,6 +126,15 @@ static const char * const attach_type_name[] = { [BPF_SK_REUSEPORT_SELECT_OR_MIGRATE] = "sk_reuseport_select_or_migrate", [BPF_PERF_EVENT] = "perf_event", [BPF_TRACE_KPROBE_MULTI] = "trace_kprobe_multi", + [BPF_STRUCT_OPS] = "struct_ops", + [BPF_NETFILTER] = "netfilter", + [BPF_TCX_INGRESS] = "tcx_ingress", + [BPF_TCX_EGRESS] = "tcx_egress", + [BPF_TRACE_UPROBE_MULTI] = "trace_uprobe_multi", + [BPF_NETKIT_PRIMARY] = "netkit_primary", + [BPF_NETKIT_PEER] = "netkit_peer", + [BPF_TRACE_KPROBE_SESSION] = "trace_kprobe_session", + [BPF_TRACE_UPROBE_SESSION] = "trace_uprobe_session", }; static const char * const link_type_name[] = { @@ -129,6 +148,11 @@ static const char * const link_type_name[] = { [BPF_LINK_TYPE_PERF_EVENT] = "perf_event", [BPF_LINK_TYPE_KPROBE_MULTI] = "kprobe_multi", [BPF_LINK_TYPE_STRUCT_OPS] = "struct_ops", + [BPF_LINK_TYPE_NETFILTER] = "netfilter", + [BPF_LINK_TYPE_TCX] = "tcx", + [BPF_LINK_TYPE_UPROBE_MULTI] = "uprobe_multi", + [BPF_LINK_TYPE_NETKIT] = "netkit", + [BPF_LINK_TYPE_SOCKMAP] = "sockmap", }; static const char * const map_type_name[] = { @@ -165,6 +189,8 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter", [BPF_MAP_TYPE_USER_RINGBUF] = "user_ringbuf", [BPF_MAP_TYPE_CGRP_STORAGE] = "cgrp_storage", + [BPF_MAP_TYPE_ARENA] = "arena", + [BPF_MAP_TYPE_INSN_ARRAY] = "insn_array", }; static const char * const prog_type_name[] = { @@ -200,12 +226,36 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_LSM] = "lsm", [BPF_PROG_TYPE_SK_LOOKUP] = "sk_lookup", [BPF_PROG_TYPE_SYSCALL] = "syscall", + [BPF_PROG_TYPE_NETFILTER] = "netfilter", }; static int __base_pr(enum libbpf_print_level level, const char *format, va_list args) { - if (level == LIBBPF_DEBUG) + const char *env_var = "LIBBPF_LOG_LEVEL"; + static enum libbpf_print_level min_level = LIBBPF_INFO; + static bool initialized; + + if (!initialized) { + char *verbosity; + + initialized = true; + verbosity = getenv(env_var); + if (verbosity) { + if (strcasecmp(verbosity, "warn") == 0) + min_level = LIBBPF_WARN; + else if (strcasecmp(verbosity, "debug") == 0) + min_level = LIBBPF_DEBUG; + else if (strcasecmp(verbosity, "info") == 0) + min_level = LIBBPF_INFO; + else + fprintf(stderr, "libbpf: unrecognized '%s' envvar value: '%s', should be one of 'warn', 'debug', or 'info'.\n", + env_var, verbosity); + } + } + + /* if too verbose, skip logging */ + if (level > min_level) return 0; return vfprintf(stderr, format, args); @@ -215,9 +265,10 @@ static libbpf_print_fn_t __libbpf_pr = __base_pr; libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn) { - libbpf_print_fn_t old_print_fn = __libbpf_pr; + libbpf_print_fn_t old_print_fn; + + old_print_fn = __atomic_exchange_n(&__libbpf_pr, fn, __ATOMIC_RELAXED); - __libbpf_pr = fn; return old_print_fn; } @@ -226,14 +277,16 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...) { va_list args; int old_errno; + libbpf_print_fn_t print_fn; - if (!__libbpf_pr) + print_fn = __atomic_load_n(&__libbpf_pr, __ATOMIC_RELAXED); + if (!print_fn) return; old_errno = errno; va_start(args, format); - __libbpf_pr(level, format, args); + print_fn(level, format, args); va_end(args); errno = old_errno; @@ -265,8 +318,6 @@ static void pr_perm_msg(int err) buf); } -#define STRERR_BUFSIZE 128 - /* Copied from tools/perf/util/util.h */ #ifndef zfree # define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) @@ -315,10 +366,11 @@ enum reloc_type { RELO_LD64, RELO_CALL, RELO_DATA, - RELO_EXTERN_VAR, - RELO_EXTERN_FUNC, + RELO_EXTERN_LD64, + RELO_EXTERN_CALL, RELO_SUBPROG_ADDR, RELO_CORE, + RELO_INSN_ARRAY, }; struct reloc_desc { @@ -329,6 +381,16 @@ struct reloc_desc { struct { int map_idx; int sym_off; + /* + * The following two fields can be unionized, as the + * ext_idx field is used for extern symbols, and the + * sym_size is used for jump tables, which are never + * extern + */ + union { + int ext_idx; + int sym_size; + }; }; }; }; @@ -354,6 +416,8 @@ enum sec_def_flags { SEC_SLEEPABLE = 8, /* BPF program support non-linear XDP buffer */ SEC_XDP_FRAGS = 16, + /* Setup proper attach type for usdt probes. */ + SEC_USDT = 32, }; struct bpf_sec_def { @@ -368,6 +432,11 @@ struct bpf_sec_def { libbpf_prog_attach_fn_t prog_attach_fn; }; +struct bpf_light_subprog { + __u32 sec_insn_off; + __u32 sub_insn_off; +}; + /* * bpf_prog should be a better name but it has been used in * linux/filter.h. @@ -421,9 +490,11 @@ struct bpf_program { int fd; bool autoload; bool autoattach; + bool sym_global; bool mark_btf_static; enum bpf_prog_type type; enum bpf_attach_type expected_attach_type; + int exception_cb_idx; int prog_ifindex; __u32 attach_btf_obj_fd; @@ -438,11 +509,13 @@ struct bpf_program { __u32 line_info_rec_size; __u32 line_info_cnt; __u32 prog_flags; + __u8 hash[SHA256_DIGEST_LENGTH]; + + struct bpf_light_subprog *subprogs; + __u32 subprog_cnt; }; struct bpf_struct_ops { - const char *tname; - const struct btf_type *type; struct bpf_program **progs; __u32 *kern_func_off; /* e.g. struct tcp_congestion_ops in bpf_prog's btf format */ @@ -467,6 +540,8 @@ struct bpf_struct_ops { #define KCONFIG_SEC ".kconfig" #define KSYMS_SEC ".ksyms" #define STRUCT_OPS_SEC ".struct_ops" +#define STRUCT_OPS_LINK_SEC ".struct_ops.link" +#define ARENA_SEC ".addr_space.1" enum libbpf_map_type { LIBBPF_MAP_UNSPEC, @@ -501,6 +576,7 @@ struct bpf_map { struct bpf_map_def def; __u32 numa_node; __u32 btf_var_idx; + int mod_btf_fd; __u32 btf_key_type_id; __u32 btf_value_type_id; __u32 btf_vmlinux_value_type_id; @@ -514,7 +590,9 @@ struct bpf_map { bool pinned; bool reused; bool autocreate; + bool autoattach; __u64 map_extra; + struct bpf_program *excl_prog; }; enum extern_type { @@ -537,7 +615,8 @@ struct extern_desc { int sym_idx; int btf_id; int sec_btf_id; - const char *name; + char *name; + char *essent_name; bool is_set; bool is_weak; union { @@ -580,6 +659,7 @@ enum sec_type { SEC_BSS, SEC_DATA, SEC_RODATA, + SEC_ST_OPS, }; struct elf_sec_desc { @@ -595,7 +675,7 @@ struct elf_state { Elf *elf; Elf64_Ehdr *ehdr; Elf_Data *symbols; - Elf_Data *st_ops_data; + Elf_Data *arena_data; size_t shstrndx; /* section index for section name strings */ size_t strtabidx; struct elf_sec_desc *secs; @@ -604,16 +684,25 @@ struct elf_state { __u32 btf_maps_sec_btf_id; int text_shndx; int symbols_shndx; - int st_ops_shndx; + bool has_st_ops; + int arena_data_shndx; + int jumptables_data_shndx; }; struct usdt_manager; +enum bpf_object_state { + OBJ_OPEN, + OBJ_PREPARED, + OBJ_LOADED, +}; + struct bpf_object { char name[BPF_OBJ_NAME_LEN]; char license[64]; __u32 kern_version; + enum bpf_object_state state; struct bpf_program *programs; size_t nr_programs; struct bpf_map *maps; @@ -625,7 +714,6 @@ struct bpf_object { int nr_extern; int kconfig_map_idx; - bool loaded; bool has_subcalls; bool has_rodata; @@ -634,6 +722,8 @@ struct bpf_object { /* Information when doing ELF related work. Only valid if efile.elf is not NULL */ struct elf_state efile; + unsigned char byteorder; + struct btf *btf; struct btf_ext *btf_ext; @@ -664,6 +754,24 @@ struct bpf_object { struct usdt_manager *usdt_man; + int arena_map_idx; + void *arena_data; + size_t arena_data_sz; + + void *jumptables_data; + size_t jumptables_data_sz; + + struct { + struct bpf_program *prog; + int sym_off; + int fd; + } *jumptable_maps; + size_t jumptable_map_cnt; + + struct kern_feature_cache *feat_cache; + char *token_path; + int token_fd; + char path[]; }; @@ -686,6 +794,7 @@ void bpf_program__unload(struct bpf_program *prog) zfree(&prog->func_info); zfree(&prog->line_info); + zfree(&prog->subprogs); } static void bpf_program__exit(struct bpf_program *prog) @@ -746,6 +855,7 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, prog->type = BPF_PROG_TYPE_UNSPEC; prog->fd = -1; + prog->exception_cb_idx = -1; /* libbpf's convention for SEC("?abc...") is that it's just like * SEC("abc...") but the corresponding bpf_program starts out with @@ -799,7 +909,6 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, progs = obj->programs; nr_progs = obj->nr_programs; nr_syms = symbols->d_size / sizeof(Elf64_Sym); - sec_off = 0; for (i = 0; i < nr_syms; i++) { sym = elf_sym_by_idx(obj, i); @@ -819,7 +928,7 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return -LIBBPF_ERRNO__FORMAT; } - if (sec_off + prog_sz > sec_sz) { + if (sec_off + prog_sz > sec_sz || sec_off + prog_sz < sec_off) { pr_warn("sec '%s': program at offset %zu crosses section boundary\n", sec_name, sec_off); return -LIBBPF_ERRNO__FORMAT; @@ -853,14 +962,16 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, if (err) return err; + if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL) + prog->sym_global = true; + /* if function is a global/weak symbol, but has restricted * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF FUNC * as static to enable more permissive BPF verification mode * with more outside context available to BPF verifier */ - if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL - && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN - || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL)) + if (prog->sym_global && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN + || ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL)) prog->mark_btf_static = true; nr_progs++; @@ -870,40 +981,18 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return 0; } -__u32 get_kernel_version(void) +static void bpf_object_bswap_progs(struct bpf_object *obj) { - /* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release, - * but Ubuntu provides /proc/version_signature file, as described at - * https://ubuntu.com/kernel, with an example contents below, which we - * can use to get a proper LINUX_VERSION_CODE. - * - * Ubuntu 5.4.0-12.15-generic 5.4.8 - * - * In the above, 5.4.8 is what kernel is actually expecting, while - * uname() call will return 5.4.0 in info.release. - */ - const char *ubuntu_kver_file = "/proc/version_signature"; - __u32 major, minor, patch; - struct utsname info; - - if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) == 0) { - FILE *f; - - f = fopen(ubuntu_kver_file, "r"); - if (f) { - if (fscanf(f, "%*s %*s %d.%d.%d\n", &major, &minor, &patch) == 3) { - fclose(f); - return KERNEL_VERSION(major, minor, patch); - } - fclose(f); - } - /* something went wrong, fall back to uname() approach */ - } + struct bpf_program *prog = obj->programs; + struct bpf_insn *insn; + int p, i; - uname(&info); - if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) - return 0; - return KERNEL_VERSION(major, minor, patch); + for (p = 0; p < obj->nr_programs; p++, prog++) { + insn = prog->insns; + for (i = 0; i < prog->insns_cnt; i++, insn++) + bpf_insn_bswap(insn); + } + pr_debug("converted %zu BPF programs to native byte order\n", obj->nr_programs); } static const struct btf_member * @@ -935,43 +1024,52 @@ find_member_by_name(const struct btf *btf, const struct btf_type *t, return NULL; } +static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name, + __u16 kind, struct btf **res_btf, + struct module_btf **res_mod_btf); + #define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_" static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, const char *name, __u32 kind); static int -find_struct_ops_kern_types(const struct btf *btf, const char *tname, +find_struct_ops_kern_types(struct bpf_object *obj, const char *tname_raw, + struct module_btf **mod_btf, const struct btf_type **type, __u32 *type_id, const struct btf_type **vtype, __u32 *vtype_id, const struct btf_member **data_member) { const struct btf_type *kern_type, *kern_vtype; const struct btf_member *kern_data_member; + struct btf *btf = NULL; __s32 kern_vtype_id, kern_type_id; + char tname[192], stname[256]; __u32 i; - kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); - if (kern_type_id < 0) { - pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", - tname); - return kern_type_id; - } - kern_type = btf__type_by_id(btf, kern_type_id); + snprintf(tname, sizeof(tname), "%.*s", + (int)bpf_core_essential_name_len(tname_raw), tname_raw); + + snprintf(stname, sizeof(stname), "%s%s", STRUCT_OPS_VALUE_PREFIX, tname); - /* Find the corresponding "map_value" type that will be used - * in map_update(BPF_MAP_TYPE_STRUCT_OPS). For example, - * find "struct bpf_struct_ops_tcp_congestion_ops" from the - * btf_vmlinux. + /* Look for the corresponding "map_value" type that will be used + * in map_update(BPF_MAP_TYPE_STRUCT_OPS) first, figure out the btf + * and the mod_btf. + * For example, find "struct bpf_struct_ops_tcp_congestion_ops". */ - kern_vtype_id = find_btf_by_prefix_kind(btf, STRUCT_OPS_VALUE_PREFIX, - tname, BTF_KIND_STRUCT); + kern_vtype_id = find_ksym_btf_id(obj, stname, BTF_KIND_STRUCT, &btf, mod_btf); if (kern_vtype_id < 0) { - pr_warn("struct_ops init_kern: struct %s%s is not found in kernel BTF\n", - STRUCT_OPS_VALUE_PREFIX, tname); + pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", stname); return kern_vtype_id; } kern_vtype = btf__type_by_id(btf, kern_vtype_id); + kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); + if (kern_type_id < 0) { + pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", tname); + return kern_type_id; + } + kern_type = btf__type_by_id(btf, kern_type_id); + /* Find "struct tcp_congestion_ops" from * struct bpf_struct_ops_tcp_congestion_ops { * [ ... ] @@ -984,8 +1082,8 @@ find_struct_ops_kern_types(const struct btf *btf, const char *tname, break; } if (i == btf_vlen(kern_vtype)) { - pr_warn("struct_ops init_kern: struct %s data is not found in struct %s%s\n", - tname, STRUCT_OPS_VALUE_PREFIX, tname); + pr_warn("struct_ops init_kern: struct %s data is not found in struct %s\n", + tname, stname); return -EINVAL; } @@ -1003,32 +1101,95 @@ static bool bpf_map__is_struct_ops(const struct bpf_map *map) return map->def.type == BPF_MAP_TYPE_STRUCT_OPS; } +static bool is_valid_st_ops_program(struct bpf_object *obj, + const struct bpf_program *prog) +{ + int i; + + for (i = 0; i < obj->nr_programs; i++) { + if (&obj->programs[i] == prog) + return prog->type == BPF_PROG_TYPE_STRUCT_OPS; + } + + return false; +} + +/* For each struct_ops program P, referenced from some struct_ops map M, + * enable P.autoload if there are Ms for which M.autocreate is true, + * disable P.autoload if for all Ms M.autocreate is false. + * Don't change P.autoload for programs that are not referenced from any maps. + */ +static int bpf_object_adjust_struct_ops_autoload(struct bpf_object *obj) +{ + struct bpf_program *prog, *slot_prog; + struct bpf_map *map; + int i, j, k, vlen; + + for (i = 0; i < obj->nr_programs; ++i) { + int should_load = false; + int use_cnt = 0; + + prog = &obj->programs[i]; + if (prog->type != BPF_PROG_TYPE_STRUCT_OPS) + continue; + + for (j = 0; j < obj->nr_maps; ++j) { + const struct btf_type *type; + + map = &obj->maps[j]; + if (!bpf_map__is_struct_ops(map)) + continue; + + type = btf__type_by_id(obj->btf, map->st_ops->type_id); + vlen = btf_vlen(type); + for (k = 0; k < vlen; ++k) { + slot_prog = map->st_ops->progs[k]; + if (prog != slot_prog) + continue; + + use_cnt++; + if (map->autocreate) + should_load = true; + } + } + if (use_cnt) + prog->autoload = should_load; + } + + return 0; +} + /* Init the map's fields that depend on kern_btf */ -static int bpf_map__init_kern_struct_ops(struct bpf_map *map, - const struct btf *btf, - const struct btf *kern_btf) +static int bpf_map__init_kern_struct_ops(struct bpf_map *map) { const struct btf_member *member, *kern_member, *kern_data_member; const struct btf_type *type, *kern_type, *kern_vtype; __u32 i, kern_type_id, kern_vtype_id, kern_data_off; + struct bpf_object *obj = map->obj; + const struct btf *btf = obj->btf; struct bpf_struct_ops *st_ops; + const struct btf *kern_btf; + struct module_btf *mod_btf = NULL; void *data, *kern_data; const char *tname; int err; st_ops = map->st_ops; - type = st_ops->type; - tname = st_ops->tname; - err = find_struct_ops_kern_types(kern_btf, tname, + type = btf__type_by_id(btf, st_ops->type_id); + tname = btf__name_by_offset(btf, type->name_off); + err = find_struct_ops_kern_types(obj, tname, &mod_btf, &kern_type, &kern_type_id, &kern_vtype, &kern_vtype_id, &kern_data_member); if (err) return err; + kern_btf = mod_btf ? mod_btf->btf : obj->btf_vmlinux; + pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n", map->name, st_ops->type_id, kern_type_id, kern_vtype_id); + map->mod_btf_fd = mod_btf ? mod_btf->fd : -1; map->def.value_size = kern_vtype->size; map->btf_vmlinux_value_type_id = kern_vtype_id; @@ -1045,17 +1206,46 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, const struct btf_type *mtype, *kern_mtype; __u32 mtype_id, kern_mtype_id; void *mdata, *kern_mdata; + struct bpf_program *prog; __s64 msize, kern_msize; __u32 moff, kern_moff; __u32 kern_member_idx; const char *mname; mname = btf__name_by_offset(btf, member->name_off); + moff = member->offset / 8; + mdata = data + moff; + msize = btf__resolve_size(btf, member->type); + if (msize < 0) { + pr_warn("struct_ops init_kern %s: failed to resolve the size of member %s\n", + map->name, mname); + return msize; + } + kern_member = find_member_by_name(kern_btf, kern_type, mname); if (!kern_member) { - pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n", + if (!libbpf_is_mem_zeroed(mdata, msize)) { + pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n", + map->name, mname); + return -ENOTSUP; + } + + if (st_ops->progs[i]) { + /* If we had declaratively set struct_ops callback, we need to + * force its autoload to false, because it doesn't have + * a chance of succeeding from POV of the current struct_ops map. + * If this program is still referenced somewhere else, though, + * then bpf_object_adjust_struct_ops_autoload() will update its + * autoload accordingly. + */ + st_ops->progs[i]->autoload = false; + st_ops->progs[i] = NULL; + } + + /* Skip all-zero/NULL fields if they are not present in the kernel BTF */ + pr_info("struct_ops %s: member %s not found in kernel, skipping it as it's set to zero\n", map->name, mname); - return -ENOTSUP; + continue; } kern_member_idx = kern_member - btf_members(kern_type); @@ -1066,10 +1256,7 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, return -ENOTSUP; } - moff = member->offset / 8; kern_moff = kern_member->offset / 8; - - mdata = data + moff; kern_mdata = kern_data + kern_moff; mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id); @@ -1084,12 +1271,25 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, } if (btf_is_ptr(mtype)) { - struct bpf_program *prog; + prog = *(void **)mdata; + /* just like for !kern_member case above, reset declaratively + * set (at compile time) program's autload to false, + * if user replaced it with another program or NULL + */ + if (st_ops->progs[i] && st_ops->progs[i] != prog) + st_ops->progs[i]->autoload = false; - prog = st_ops->progs[i]; + /* Update the value from the shadow type */ + st_ops->progs[i] = prog; if (!prog) continue; + if (!is_valid_st_ops_program(obj, prog)) { + pr_warn("struct_ops init_kern %s: member %s is not a struct_ops program\n", + map->name, mname); + return -ENOTSUP; + } + kern_mtype = skip_mods_and_typedefs(kern_btf, kern_mtype->type, &kern_mtype_id); @@ -1104,8 +1304,34 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, return -ENOTSUP; } - prog->attach_btf_id = kern_type_id; - prog->expected_attach_type = kern_member_idx; + if (mod_btf) + prog->attach_btf_obj_fd = mod_btf->fd; + + /* if we haven't yet processed this BPF program, record proper + * attach_btf_id and member_idx + */ + if (!prog->attach_btf_id) { + prog->attach_btf_id = kern_type_id; + prog->expected_attach_type = kern_member_idx; + } + + /* struct_ops BPF prog can be re-used between multiple + * .struct_ops & .struct_ops.link as long as it's the + * same struct_ops struct definition and the same + * function pointer field + */ + if (prog->attach_btf_id != kern_type_id) { + pr_warn("struct_ops init_kern %s func ptr %s: invalid reuse of prog %s in sec %s with type %u: attach_btf_id %u != kern_type_id %u\n", + map->name, mname, prog->name, prog->sec_name, prog->type, + prog->attach_btf_id, kern_type_id); + return -EINVAL; + } + if (prog->expected_attach_type != kern_member_idx) { + pr_warn("struct_ops init_kern %s func ptr %s: invalid reuse of prog %s in sec %s with type %u: expected_attach_type %u != kern_member_idx %u\n", + map->name, mname, prog->name, prog->sec_name, prog->type, + prog->expected_attach_type, kern_member_idx); + return -EINVAL; + } st_ops->kern_func_off[i] = kern_data_off + kern_moff; @@ -1116,9 +1342,8 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map, continue; } - msize = btf__resolve_size(btf, mtype_id); kern_msize = btf__resolve_size(kern_btf, kern_mtype_id); - if (msize < 0 || kern_msize < 0 || msize != kern_msize) { + if (kern_msize < 0 || msize != kern_msize) { pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n", map->name, mname, (ssize_t)msize, (ssize_t)kern_msize); @@ -1146,8 +1371,10 @@ static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj) if (!bpf_map__is_struct_ops(map)) continue; - err = bpf_map__init_kern_struct_ops(map, obj->btf, - obj->btf_vmlinux); + if (!map->autocreate) + continue; + + err = bpf_map__init_kern_struct_ops(map); if (err) return err; } @@ -1155,7 +1382,8 @@ static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj) return 0; } -static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) +static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name, + int shndx, Elf_Data *data) { const struct btf_type *type, *datasec; const struct btf_var_secinfo *vsi; @@ -1166,15 +1394,15 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) struct bpf_map *map; __u32 i; - if (obj->efile.st_ops_shndx == -1) + if (shndx == -1) return 0; btf = obj->btf; - datasec_id = btf__find_by_name_kind(btf, STRUCT_OPS_SEC, + datasec_id = btf__find_by_name_kind(btf, sec_name, BTF_KIND_DATASEC); if (datasec_id < 0) { pr_warn("struct_ops init: DATASEC %s not found\n", - STRUCT_OPS_SEC); + sec_name); return -EINVAL; } @@ -1187,7 +1415,7 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) type_id = btf__resolve_type(obj->btf, vsi->type); if (type_id < 0) { pr_warn("struct_ops init: Cannot resolve var type_id %u in DATASEC %s\n", - vsi->type, STRUCT_OPS_SEC); + vsi->type, sec_name); return -EINVAL; } @@ -1206,16 +1434,28 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) if (IS_ERR(map)) return PTR_ERR(map); - map->sec_idx = obj->efile.st_ops_shndx; + map->sec_idx = shndx; map->sec_offset = vsi->offset; map->name = strdup(var_name); if (!map->name) return -ENOMEM; + map->btf_value_type_id = type_id; + + /* Follow same convention as for programs autoload: + * SEC("?.struct_ops") means map is not created by default. + */ + if (sec_name[0] == '?') { + map->autocreate = false; + /* from now on forget there was ? in section name */ + sec_name++; + } map->def.type = BPF_MAP_TYPE_STRUCT_OPS; map->def.key_size = sizeof(int); map->def.value_size = type->size; map->def.max_entries = 1; + map->def.map_flags = strcmp(sec_name, STRUCT_OPS_LINK_SEC) == 0 ? BPF_F_LINK : 0; + map->autoattach = true; map->st_ops = calloc(1, sizeof(*map->st_ops)); if (!map->st_ops) @@ -1228,17 +1468,15 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off) return -ENOMEM; - if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) { + if (vsi->offset + type->size > data->d_size) { pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n", - var_name, STRUCT_OPS_SEC); + var_name, sec_name); return -EINVAL; } memcpy(st_ops->data, - obj->efile.st_ops_data->d_buf + vsi->offset, + data->d_buf + vsi->offset, type->size); - st_ops->tname = tname; - st_ops->type = type; st_ops->type_id = type_id; pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n", @@ -1248,6 +1486,29 @@ static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) return 0; } +static int bpf_object_init_struct_ops(struct bpf_object *obj) +{ + const char *sec_name; + int sec_idx, err; + + for (sec_idx = 0; sec_idx < obj->efile.sec_cnt; ++sec_idx) { + struct elf_sec_desc *desc = &obj->efile.secs[sec_idx]; + + if (desc->sec_type != SEC_ST_OPS) + continue; + + sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx)); + if (!sec_name) + return -LIBBPF_ERRNO__FORMAT; + + err = init_struct_ops_maps(obj, sec_name, sec_idx, desc->data); + if (err) + return err; + } + + return 0; +} + static struct bpf_object *bpf_object__new(const char *path, const void *obj_buf, size_t obj_buf_sz, @@ -1283,11 +1544,11 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.btf_maps_shndx = -1; - obj->efile.st_ops_shndx = -1; obj->kconfig_map_idx = -1; + obj->arena_map_idx = -1; obj->kern_version = get_kernel_version(); - obj->loaded = false; + obj->state = OBJ_OPEN; return obj; } @@ -1299,8 +1560,9 @@ static void bpf_object__elf_finish(struct bpf_object *obj) elf_end(obj->efile.elf); obj->efile.elf = NULL; + obj->efile.ehdr = NULL; obj->efile.symbols = NULL; - obj->efile.st_ops_data = NULL; + obj->efile.arena_data = NULL; zfree(&obj->efile.secs); obj->efile.sec_cnt = 0; @@ -1326,11 +1588,8 @@ static int bpf_object__elf_init(struct bpf_object *obj) } else { obj->efile.fd = open(obj->path, O_RDONLY | O_CLOEXEC); if (obj->efile.fd < 0) { - char errmsg[STRERR_BUFSIZE], *cp; - err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("elf: failed to open %s: %s\n", obj->path, cp); + pr_warn("elf: failed to open %s: %s\n", obj->path, errstr(err)); return err; } @@ -1364,6 +1623,16 @@ static int bpf_object__elf_init(struct bpf_object *obj) goto errout; } + /* Validate ELF object endianness... */ + if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB && + ehdr->e_ident[EI_DATA] != ELFDATA2MSB) { + err = -LIBBPF_ERRNO__ENDIAN; + pr_warn("elf: '%s' has unknown byte order\n", obj->path); + goto errout; + } + /* and save after bpf_object_open() frees ELF data */ + obj->byteorder = ehdr->e_ident[EI_DATA]; + if (elf_getshdrstrndx(elf, &obj->efile.shstrndx)) { pr_warn("elf: failed to get section names section index for %s: %s\n", obj->path, elf_errmsg(-1)); @@ -1371,7 +1640,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) goto errout; } - /* Elf is corrupted/truncated, avoid calling elf_strptr. */ + /* ELF is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, obj->efile.shstrndx), NULL)) { pr_warn("elf: failed to get section names strings from %s: %s\n", obj->path, elf_errmsg(-1)); @@ -1392,19 +1661,15 @@ errout: return err; } -static int bpf_object__check_endianness(struct bpf_object *obj) +static bool is_native_endianness(struct bpf_object *obj) { #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ - if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2LSB) - return 0; + return obj->byteorder == ELFDATA2LSB; #elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2MSB) - return 0; + return obj->byteorder == ELFDATA2MSB; #else # error "Unrecognized __BYTE_ORDER__" #endif - pr_warn("elf: endianness mismatch in %s.\n", obj->path); - return -LIBBPF_ERRNO__ENDIAN; } static int @@ -1491,6 +1756,32 @@ static Elf64_Sym *find_elf_var_sym(const struct bpf_object *obj, const char *nam return ERR_PTR(-ENOENT); } +#ifndef MFD_CLOEXEC +#define MFD_CLOEXEC 0x0001U +#endif +#ifndef MFD_NOEXEC_SEAL +#define MFD_NOEXEC_SEAL 0x0008U +#endif + +static int create_placeholder_fd(void) +{ + unsigned int flags = MFD_CLOEXEC | MFD_NOEXEC_SEAL; + const char *name = "libbpf-placeholder-fd"; + int fd; + + fd = ensure_good_fd(sys_memfd_create(name, flags)); + if (fd >= 0) + return fd; + else if (errno != EINVAL) + return -errno; + + /* Possibly running on kernel without MFD_NOEXEC_SEAL */ + fd = ensure_good_fd(sys_memfd_create(name, flags & ~MFD_NOEXEC_SEAL)); + if (fd < 0) + return -errno; + return fd; +} + static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) { struct bpf_map *map; @@ -1503,23 +1794,71 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) map = &obj->maps[obj->nr_maps++]; map->obj = obj; - map->fd = -1; + /* Preallocate map FD without actually creating BPF map just yet. + * These map FD "placeholders" will be reused later without changing + * FD value when map is actually created in the kernel. + * + * This is useful to be able to perform BPF program relocations + * without having to create BPF maps before that step. This allows us + * to finalize and load BTF very late in BPF object's loading phase, + * right before BPF maps have to be created and BPF programs have to + * be loaded. By having these map FD placeholders we can perform all + * the sanitizations, relocations, and any other adjustments before we + * start creating actual BPF kernel objects (BTF, maps, progs). + */ + map->fd = create_placeholder_fd(); + if (map->fd < 0) + return ERR_PTR(map->fd); map->inner_map_fd = -1; map->autocreate = true; return map; } -static size_t bpf_map_mmap_sz(const struct bpf_map *map) +static size_t array_map_mmap_sz(unsigned int value_sz, unsigned int max_entries) { - long page_sz = sysconf(_SC_PAGE_SIZE); + const long page_sz = sysconf(_SC_PAGE_SIZE); size_t map_sz; - map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries; + map_sz = (size_t)roundup(value_sz, 8) * max_entries; map_sz = roundup(map_sz, page_sz); return map_sz; } +static size_t bpf_map_mmap_sz(const struct bpf_map *map) +{ + const long page_sz = sysconf(_SC_PAGE_SIZE); + + switch (map->def.type) { + case BPF_MAP_TYPE_ARRAY: + return array_map_mmap_sz(map->def.value_size, map->def.max_entries); + case BPF_MAP_TYPE_ARENA: + return page_sz * map->def.max_entries; + default: + return 0; /* not supported */ + } +} + +static int bpf_map_mmap_resize(struct bpf_map *map, size_t old_sz, size_t new_sz) +{ + void *mmaped; + + if (!map->mmaped) + return -EINVAL; + + if (old_sz == new_sz) + return 0; + + mmaped = mmap(NULL, new_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (mmaped == MAP_FAILED) + return -errno; + + memcpy(mmaped, map->mmaped, min(old_sz, new_sz)); + munmap(map->mmaped, old_sz); + map->mmaped = mmaped; + return 0; +} + static char *internal_map_name(struct bpf_object *obj, const char *real_name) { char map_name[BPF_OBJ_NAME_LEN], *p; @@ -1570,7 +1909,7 @@ static char *internal_map_name(struct bpf_object *obj, const char *real_name) snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name, sfx_len, real_name); - /* sanitise map name to characters allowed by kernel */ + /* sanities map name to characters allowed by kernel */ for (p = map_name; *p && p < map_name + sizeof(map_name); p++) if (!isalnum(*p) && *p != '_' && *p != '.') *p = '_'; @@ -1618,6 +1957,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, { struct bpf_map_def *def; struct bpf_map *map; + size_t mmap_sz; int err; map = bpf_object__add_map(obj); @@ -1641,7 +1981,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, def->value_size = data_sz; def->max_entries = 1; def->map_flags = type == LIBBPF_MAP_RODATA || type == LIBBPF_MAP_KCONFIG - ? BPF_F_RDONLY_PROG : 0; + ? BPF_F_RDONLY_PROG : 0; /* failures are fine because of maps like .rodata.str1.1 */ (void) map_fill_btf_type_info(obj, map); @@ -1652,13 +1992,13 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, pr_debug("map '%s' (global data): at sec_idx %d, offset %zu, flags %x.\n", map->name, map->sec_idx, map->sec_offset, def->map_flags); - map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, + mmap_sz = bpf_map_mmap_sz(map); + map->mmaped = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); if (map->mmaped == MAP_FAILED) { err = -errno; map->mmaped = NULL; - pr_warn("failed to alloc map '%s' content buffer: %d\n", - map->name, err); + pr_warn("failed to alloc map '%s' content buffer: %s\n", map->name, errstr(err)); zfree(&map->real_name); zfree(&map->name); return err; @@ -1733,6 +2073,20 @@ static struct extern_desc *find_extern_by_name(const struct bpf_object *obj, return NULL; } +static struct extern_desc *find_extern_by_name_with_len(const struct bpf_object *obj, + const void *name, int len) +{ + const char *ext_name; + int i; + + for (i = 0; i < obj->nr_extern; i++) { + ext_name = obj->externs[i].name; + if (strlen(ext_name) == len && strncmp(ext_name, name, len) == 0) + return &obj->externs[i]; + } + return NULL; +} + static int set_kcfg_value_tri(struct extern_desc *ext, void *ext_val, char value) { @@ -1780,7 +2134,7 @@ static int set_kcfg_value_str(struct extern_desc *ext, char *ext_val, } len = strlen(value); - if (value[len - 1] != '"') { + if (len < 2 || value[len - 1] != '"') { pr_warn("extern (kcfg) '%s': invalid string config '%s'\n", ext->name, value); return -EINVAL; @@ -1808,7 +2162,7 @@ static int parse_u64(const char *value, __u64 *res) *res = strtoull(value, &value_end, 0); if (errno) { err = -errno; - pr_warn("failed to parse '%s' as integer: %d\n", value, err); + pr_warn("failed to parse '%s': %s\n", value, errstr(err)); return err; } if (*value_end) { @@ -1962,9 +2316,9 @@ static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data) return -ENAMETOOLONG; /* gzopen also accepts uncompressed files. */ - file = gzopen(buf, "r"); + file = gzopen(buf, "re"); if (!file) - file = gzopen("/proc/config.gz", "r"); + file = gzopen("/proc/config.gz", "re"); if (!file) { pr_warn("failed to open system Kconfig\n"); @@ -1974,8 +2328,8 @@ static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data) while (gzgets(file, buf, sizeof(buf))) { err = bpf_object__process_kconfig_line(obj, buf, data); if (err) { - pr_warn("error parsing system Kconfig line '%s': %d\n", - buf, err); + pr_warn("error parsing system Kconfig line '%s': %s\n", + buf, errstr(err)); goto out; } } @@ -1995,15 +2349,15 @@ static int bpf_object__read_kconfig_mem(struct bpf_object *obj, file = fmemopen((void *)config, strlen(config), "r"); if (!file) { err = -errno; - pr_warn("failed to open in-memory Kconfig: %d\n", err); + pr_warn("failed to open in-memory Kconfig: %s\n", errstr(err)); return err; } while (fgets(buf, sizeof(buf), file)) { err = bpf_object__process_kconfig_line(obj, buf, data); if (err) { - pr_warn("error parsing in-memory Kconfig line '%s': %d\n", - buf, err); + pr_warn("error parsing in-memory Kconfig line '%s': %s\n", + buf, errstr(err)); break; } } @@ -2139,6 +2493,46 @@ static bool get_map_field_int(const char *map_name, const struct btf *btf, return true; } +static bool get_map_field_long(const char *map_name, const struct btf *btf, + const struct btf_member *m, __u64 *res) +{ + const struct btf_type *t = skip_mods_and_typedefs(btf, m->type, NULL); + const char *name = btf__name_by_offset(btf, m->name_off); + + if (btf_is_ptr(t)) { + __u32 res32; + bool ret; + + ret = get_map_field_int(map_name, btf, m, &res32); + if (ret) + *res = (__u64)res32; + return ret; + } + + if (!btf_is_enum(t) && !btf_is_enum64(t)) { + pr_warn("map '%s': attr '%s': expected ENUM or ENUM64, got %s.\n", + map_name, name, btf_kind_str(t)); + return false; + } + + if (btf_vlen(t) != 1) { + pr_warn("map '%s': attr '%s': invalid __ulong\n", + map_name, name); + return false; + } + + if (btf_is_enum(t)) { + const struct btf_enum *e = btf_enum(t); + + *res = e->val; + } else { + const struct btf_enum64 *e = btf_enum64(t); + + *res = btf_enum64_value(e); + } + return true; +} + static int pathname_concat(char *buf, size_t buf_sz, const char *path, const char *name) { int len; @@ -2158,7 +2552,7 @@ static int build_map_pin_path(struct bpf_map *map, const char *path) int err; if (!path) - path = "/sys/fs/bpf"; + path = BPF_FS_DEFAULT_PATH; err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); if (err) @@ -2372,9 +2766,9 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, map_def->pinning = val; map_def->parts |= MAP_DEF_PINNING; } else if (strcmp(name, "map_extra") == 0) { - __u32 map_extra; + __u64 map_extra; - if (!get_map_field_int(map_name, btf, m, &map_extra)) + if (!get_map_field_long(map_name, btf, m, &map_extra)) return -EINVAL; map_def->map_extra = map_extra; map_def->parts |= MAP_DEF_MAP_EXTRA; @@ -2573,7 +2967,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, map->inner_map = calloc(1, sizeof(*map->inner_map)); if (!map->inner_map) return -ENOMEM; - map->inner_map->fd = -1; + map->inner_map->fd = create_placeholder_fd(); + if (map->inner_map->fd < 0) + return map->inner_map->fd; map->inner_map->sec_idx = sec_idx; map->inner_map->name = malloc(strlen(map_name) + sizeof(".inner") + 1); if (!map->inner_map->name) @@ -2590,6 +2986,32 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, return 0; } +static int init_arena_map_data(struct bpf_object *obj, struct bpf_map *map, + const char *sec_name, int sec_idx, + void *data, size_t data_sz) +{ + const long page_sz = sysconf(_SC_PAGE_SIZE); + size_t mmap_sz; + + mmap_sz = bpf_map_mmap_sz(map); + if (roundup(data_sz, page_sz) > mmap_sz) { + pr_warn("elf: sec '%s': declared ARENA map size (%zu) is too small to hold global __arena variables of size %zu\n", + sec_name, mmap_sz, data_sz); + return -E2BIG; + } + + obj->arena_data = malloc(data_sz); + if (!obj->arena_data) + return -ENOMEM; + memcpy(obj->arena_data, data, data_sz); + obj->arena_data_sz = data_sz; + + /* make bpf_map__init_value() work for ARENA maps */ + map->mmaped = obj->arena_data; + + return 0; +} + static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, const char *pin_root_path) { @@ -2605,7 +3027,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, scn = elf_sec_by_idx(obj, obj->efile.btf_maps_shndx); data = elf_sec_data(obj, scn); - if (!scn || !data) { + if (!data) { pr_warn("elf: failed to get %s map definitions for %s\n", MAPS_ELF_SEC, obj->path); return -EINVAL; @@ -2639,6 +3061,33 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, return err; } + for (i = 0; i < obj->nr_maps; i++) { + struct bpf_map *map = &obj->maps[i]; + + if (map->def.type != BPF_MAP_TYPE_ARENA) + continue; + + if (obj->arena_map_idx >= 0) { + pr_warn("map '%s': only single ARENA map is supported (map '%s' is also ARENA)\n", + map->name, obj->maps[obj->arena_map_idx].name); + return -EINVAL; + } + obj->arena_map_idx = i; + + if (obj->efile.arena_data) { + err = init_arena_map_data(obj, map, ARENA_SEC, obj->efile.arena_data_shndx, + obj->efile.arena_data->d_buf, + obj->efile.arena_data->d_size); + if (err) + return err; + } + } + if (obj->efile.arena_data && obj->arena_map_idx < 0) { + pr_warn("elf: sec '%s': to use global __arena variables the ARENA map should be explicitly declared in SEC(\".maps\")\n", + ARENA_SEC); + return -ENOENT; + } + return 0; } @@ -2652,10 +3101,10 @@ static int bpf_object__init_maps(struct bpf_object *obj, strict = !OPTS_GET(opts, relaxed_maps, false); pin_root_path = OPTS_GET(opts, pin_root_path, NULL); - err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path); + err = bpf_object__init_user_btf_maps(obj, strict, pin_root_path); err = err ?: bpf_object__init_global_data_maps(obj); err = err ?: bpf_object__init_kconfig_map(obj); - err = err ?: bpf_object__init_struct_ops_maps(obj); + err = err ?: bpf_object_init_struct_ops(obj); return err; } @@ -2671,6 +3120,11 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) return sh->sh_flags & SHF_EXECINSTR; } +static bool starts_with_qmark(const char *s) +{ + return s && s[0] == '?'; +} + static bool btf_needs_sanitization(struct bpf_object *obj) { bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC); @@ -2680,9 +3134,10 @@ static bool btf_needs_sanitization(struct bpf_object *obj) bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); bool has_type_tag = kernel_supports(obj, FEAT_BTF_TYPE_TAG); bool has_enum64 = kernel_supports(obj, FEAT_BTF_ENUM64); + bool has_qmark_datasec = kernel_supports(obj, FEAT_BTF_QMARK_DATASEC); return !has_func || !has_datasec || !has_func_global || !has_float || - !has_decl_tag || !has_type_tag || !has_enum64; + !has_decl_tag || !has_type_tag || !has_enum64 || !has_qmark_datasec; } static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) @@ -2694,6 +3149,7 @@ static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); bool has_type_tag = kernel_supports(obj, FEAT_BTF_TYPE_TAG); bool has_enum64 = kernel_supports(obj, FEAT_BTF_ENUM64); + bool has_qmark_datasec = kernel_supports(obj, FEAT_BTF_QMARK_DATASEC); int enum64_placeholder_id = 0; struct btf_type *t; int i, j, vlen; @@ -2720,7 +3176,7 @@ static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) name = (char *)btf__name_by_offset(btf, t->name_off); while (*name) { - if (*name == '.') + if (*name == '.' || *name == '?') *name = '_'; name++; } @@ -2735,6 +3191,14 @@ static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) vt = (void *)btf__type_by_id(btf, v->type); m->name_off = vt->name_off; } + } else if (!has_qmark_datasec && btf_is_datasec(t) && + starts_with_qmark(btf__name_by_offset(btf, t->name_off))) { + /* replace '?' prefix with '_' for DATASEC names */ + char *name; + + name = (char *)btf__name_by_offset(btf, t->name_off); + if (name[0] == '?') + name[0] = '_'; } else if (!has_func && btf_is_func_proto(t)) { /* replace FUNC_PROTO with ENUM */ vlen = btf_vlen(t); @@ -2788,13 +3252,13 @@ static int bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) static bool libbpf_needs_btf(const struct bpf_object *obj) { return obj->efile.btf_maps_shndx >= 0 || - obj->efile.st_ops_shndx >= 0 || + obj->efile.has_st_ops || obj->nr_extern > 0; } static bool kernel_needs_btf(const struct bpf_object *obj) { - return obj->efile.st_ops_shndx >= 0; + return obj->efile.has_st_ops; } static int bpf_object__init_btf(struct bpf_object *obj, @@ -2808,7 +3272,7 @@ static int bpf_object__init_btf(struct bpf_object *obj, err = libbpf_get_error(obj->btf); if (err) { obj->btf = NULL; - pr_warn("Error loading ELF section %s: %d.\n", BTF_ELF_SEC, err); + pr_warn("Error loading ELF section %s: %s.\n", BTF_ELF_SEC, errstr(err)); goto out; } /* enforce 8-byte pointers for BPF-targeted BTFs */ @@ -2826,8 +3290,8 @@ static int bpf_object__init_btf(struct bpf_object *obj, obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); err = libbpf_get_error(obj->btf_ext); if (err) { - pr_warn("Error loading ELF section %s: %d. Ignored and continue.\n", - BTF_EXT_ELF_SEC, err); + pr_warn("Error loading ELF section %s: %s. Ignored and continue.\n", + BTF_EXT_ELF_SEC, errstr(err)); obj->btf_ext = NULL; goto out; } @@ -2919,8 +3383,8 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, if (t->size == 0) { err = find_elf_sec_sz(obj, sec_name, &size); if (err || !size) { - pr_debug("sec '%s': failed to determine size from ELF: size %u, err %d\n", - sec_name, size, err); + pr_debug("sec '%s': failed to determine size from ELF: size %u, err %s\n", + sec_name, size, errstr(err)); return -ENOENT; } @@ -3019,9 +3483,15 @@ static bool prog_needs_vmlinux_btf(struct bpf_program *prog) return false; } +static bool map_needs_vmlinux_btf(struct bpf_map *map) +{ + return bpf_map__is_struct_ops(map); +} + static bool obj_needs_vmlinux_btf(const struct bpf_object *obj) { struct bpf_program *prog; + struct bpf_map *map; int i; /* CO-RE relocations need kernel BTF, only when btf_custom_path @@ -3046,6 +3516,11 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj) return true; } + bpf_object__for_each_map(map, obj) { + if (map_needs_vmlinux_btf(map)) + return true; + } + return false; } @@ -3063,7 +3538,7 @@ static int bpf_object__load_vmlinux_btf(struct bpf_object *obj, bool force) obj->btf_vmlinux = btf__load_vmlinux_btf(); err = libbpf_get_error(obj->btf_vmlinux); if (err) { - pr_warn("Error loading vmlinux BTF: %d\n", err); + pr_warn("Error loading vmlinux BTF: %s\n", errstr(err)); obj->btf_vmlinux = NULL; return err; } @@ -3153,7 +3628,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) } else { /* 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); + obj->log_level ? 1 : 0, obj->token_fd); } if (sanitize) { if (!err) { @@ -3166,11 +3641,14 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) report: if (err) { btf_mandatory = kernel_needs_btf(obj); - pr_warn("Error loading .BTF into kernel: %d. %s\n", err, - btf_mandatory ? "BTF is mandatory, can't proceed." - : "BTF is optional, ignoring."); - if (!btf_mandatory) + if (btf_mandatory) { + pr_warn("Error loading .BTF into kernel: %s. BTF is mandatory, can't proceed.\n", + errstr(err)); + } else { + pr_info("Error loading .BTF into kernel: %s. BTF is optional, ignoring.\n", + errstr(err)); err = 0; + } } return err; } @@ -3484,9 +3962,24 @@ static int bpf_object__elf_collect(struct bpf_object *obj) sec_desc->sec_type = SEC_RODATA; sec_desc->shdr = sh; sec_desc->data = data; - } else if (strcmp(name, STRUCT_OPS_SEC) == 0) { - obj->efile.st_ops_data = data; - obj->efile.st_ops_shndx = idx; + } else if (strcmp(name, STRUCT_OPS_SEC) == 0 || + strcmp(name, STRUCT_OPS_LINK_SEC) == 0 || + strcmp(name, "?" STRUCT_OPS_SEC) == 0 || + strcmp(name, "?" STRUCT_OPS_LINK_SEC) == 0) { + sec_desc->sec_type = SEC_ST_OPS; + sec_desc->shdr = sh; + sec_desc->data = data; + obj->efile.has_st_ops = true; + } else if (strcmp(name, ARENA_SEC) == 0) { + obj->efile.arena_data = data; + obj->efile.arena_data_shndx = idx; + } else if (strcmp(name, JUMPTABLES_SEC) == 0) { + obj->jumptables_data = malloc(data->d_size); + if (!obj->jumptables_data) + return -ENOMEM; + memcpy(obj->jumptables_data, data->d_buf, data->d_size); + obj->jumptables_data_sz = data->d_size; + obj->efile.jumptables_data_shndx = idx; } else { pr_info("elf: skipping unrecognized data section(%d) %s\n", idx, name); @@ -3501,6 +3994,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj) /* Only do relo for section with exec instructions */ if (!section_have_execinstr(obj, targ_sec_idx) && strcmp(name, ".rel" STRUCT_OPS_SEC) && + strcmp(name, ".rel" STRUCT_OPS_LINK_SEC) && + strcmp(name, ".rel?" STRUCT_OPS_SEC) && + strcmp(name, ".rel?" STRUCT_OPS_LINK_SEC) && strcmp(name, ".rel" MAPS_ELF_SEC)) { pr_info("elf: skipping relo section(%d) %s for section(%d) %s\n", idx, name, targ_sec_idx, @@ -3527,6 +4023,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj) return -LIBBPF_ERRNO__FORMAT; } + /* change BPF program insns to native endianness for introspection */ + if (!is_native_endianness(obj)) + bpf_object_bswap_progs(obj); + /* sort BPF programs by section name and in-section instruction offset * for faster search */ @@ -3559,7 +4059,7 @@ static bool sym_is_subprog(const Elf64_Sym *sym, int text_shndx) return true; /* global function */ - return bind == STB_GLOBAL && type == STT_FUNC; + return (bind == STB_GLOBAL || bind == STB_WEAK) && type == STT_FUNC; } static int find_extern_btf_id(const struct btf *btf, const char *ext_name) @@ -3749,6 +4249,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj) struct extern_desc *ext; int i, n, off, dummy_var_btf_id; const char *ext_name, *sec_name; + size_t ext_essent_len; Elf_Scn *scn; Elf64_Shdr *sh; @@ -3794,10 +4295,20 @@ static int bpf_object__collect_externs(struct bpf_object *obj) return ext->btf_id; } t = btf__type_by_id(obj->btf, ext->btf_id); - ext->name = btf__name_by_offset(obj->btf, t->name_off); + ext->name = strdup(btf__name_by_offset(obj->btf, t->name_off)); + if (!ext->name) + return -ENOMEM; ext->sym_idx = i; ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK; + ext_essent_len = bpf_core_essential_name_len(ext->name); + ext->essent_name = NULL; + if (ext_essent_len != strlen(ext->name)) { + ext->essent_name = strndup(ext->name, ext_essent_len); + if (!ext->essent_name) + return -ENOMEM; + } + ext->sec_btf_id = find_extern_sec_btf_id(obj->btf, ext->btf_id); if (ext->sec_btf_id <= 0) { pr_warn("failed to find BTF for extern '%s' [%d] section: %d\n", @@ -3954,7 +4465,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj) static bool prog_is_subprog(const struct bpf_object *obj, const struct bpf_program *prog) { - return prog->sec_idx == obj->efile.text_shndx && obj->nr_programs > 1; + return prog->sec_idx == obj->efile.text_shndx; } struct bpf_program * @@ -4009,6 +4520,44 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) } } +static int bpf_prog_compute_hash(struct bpf_program *prog) +{ + struct bpf_insn *purged; + int i, err = 0; + + purged = calloc(prog->insns_cnt, BPF_INSN_SZ); + if (!purged) + return -ENOMEM; + + /* If relocations have been done, the map_fd needs to be + * discarded for the digest calculation. + */ + for (i = 0; i < prog->insns_cnt; i++) { + purged[i] = prog->insns[i]; + if (purged[i].code == (BPF_LD | BPF_IMM | BPF_DW) && + (purged[i].src_reg == BPF_PSEUDO_MAP_FD || + purged[i].src_reg == BPF_PSEUDO_MAP_VALUE)) { + purged[i].imm = 0; + i++; + if (i >= prog->insns_cnt || + prog->insns[i].code != 0 || + prog->insns[i].dst_reg != 0 || + prog->insns[i].src_reg != 0 || + prog->insns[i].off != 0) { + err = -EINVAL; + goto out; + } + purged[i] = prog->insns[i]; + purged[i].imm = 0; + } + } + libbpf_sha256(purged, prog->insns_cnt * sizeof(struct bpf_insn), + prog->hash); +out: + free(purged); + return err; +} + static int bpf_program__record_reloc(struct bpf_program *prog, struct reloc_desc *reloc_desc, __u32 insn_idx, const char *sym_name, @@ -4046,11 +4595,11 @@ static int bpf_program__record_reloc(struct bpf_program *prog, pr_debug("prog '%s': found extern #%d '%s' (sym %d) for insn #%u\n", prog->name, i, ext->name, ext->sym_idx, insn_idx); if (insn->code == (BPF_JMP | BPF_CALL)) - reloc_desc->type = RELO_EXTERN_FUNC; + reloc_desc->type = RELO_EXTERN_CALL; else - reloc_desc->type = RELO_EXTERN_VAR; + reloc_desc->type = RELO_EXTERN_LD64; reloc_desc->insn_idx = insn_idx; - reloc_desc->sym_off = i; /* sym_off stores extern index */ + reloc_desc->ext_idx = i; return 0; } @@ -4104,6 +4653,35 @@ static int bpf_program__record_reloc(struct bpf_program *prog, type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); sym_sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, shdr_idx)); + /* arena data relocation */ + if (shdr_idx == obj->efile.arena_data_shndx) { + if (obj->arena_map_idx < 0) { + pr_warn("prog '%s': bad arena data relocation at insn %u, no arena maps defined\n", + prog->name, insn_idx); + return -LIBBPF_ERRNO__RELOC; + } + reloc_desc->type = RELO_DATA; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = obj->arena_map_idx; + reloc_desc->sym_off = sym->st_value; + + map = &obj->maps[obj->arena_map_idx]; + pr_debug("prog '%s': found arena map %d (%s, sec %d, off %zu) for insn %u\n", + prog->name, obj->arena_map_idx, map->name, map->sec_idx, + map->sec_offset, insn_idx); + return 0; + } + + /* jump table data relocation */ + if (shdr_idx == obj->efile.jumptables_data_shndx) { + reloc_desc->type = RELO_INSN_ARRAY; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = -1; + reloc_desc->sym_off = sym->st_value; + reloc_desc->sym_size = sym->st_size; + return 0; + } + /* generic map reference relocation */ if (type == LIBBPF_MAP_UNSPEC) { if (!bpf_object__shndx_is_maps(obj, shdr_idx)) { @@ -4216,6 +4794,8 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Dat scn = elf_sec_by_idx(obj, sec_idx); scn_data = elf_sec_data(obj, scn); + if (!scn_data) + return -LIBBPF_ERRNO__FORMAT; relo_sec_name = elf_sec_str(obj, shdr->sh_name); sec_name = elf_sec_name(obj, scn); @@ -4334,11 +4914,11 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) snprintf(file, sizeof(file), "/proc/%d/fdinfo/%d", getpid(), fd); memset(info, 0, sizeof(*info)); - fp = fopen(file, "r"); + fp = fopen(file, "re"); if (!fp) { err = -errno; - pr_warn("failed to open %s: %d. No procfs support?\n", file, - err); + pr_warn("failed to open %s: %s. No procfs support?\n", file, + errstr(err)); return err; } @@ -4360,6 +4940,11 @@ static int bpf_get_map_info_from_fdinfo(int fd, struct bpf_map_info *info) return 0; } +static bool map_is_created(const struct bpf_map *map) +{ + return map->obj->state >= OBJ_PREPARED || map->reused; +} + bool bpf_map__autocreate(const struct bpf_map *map) { return map->autocreate; @@ -4367,13 +4952,27 @@ bool bpf_map__autocreate(const struct bpf_map *map) int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate) { - if (map->obj->loaded) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->autocreate = autocreate; return 0; } +int bpf_map__set_autoattach(struct bpf_map *map, bool autoattach) +{ + if (!bpf_map__is_struct_ops(map)) + return libbpf_err(-EINVAL); + + map->autoattach = autoattach; + return 0; +} + +bool bpf_map__autoattach(const struct bpf_map *map) +{ + return map->autoattach; +} + int bpf_map__reuse_fd(struct bpf_map *map, int fd) { struct bpf_map_info info; @@ -4382,7 +4981,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) char *new_name; memset(&info, 0, len); - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_map_get_info_by_fd(fd, &info, &len); if (err && errno == EINVAL) err = bpf_get_map_info_from_fdinfo(fd, &info); if (err) @@ -4397,26 +4996,23 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) if (!new_name) return libbpf_err(-errno); - new_fd = open("/", O_RDONLY | O_CLOEXEC); + /* + * Like dup(), but make sure new FD is >= 3 and has O_CLOEXEC set. + * This is similar to what we do in ensure_good_fd(), but without + * closing original FD. + */ + new_fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); if (new_fd < 0) { err = -errno; goto err_free_new_name; } - new_fd = dup3(fd, new_fd, O_CLOEXEC); - if (new_fd < 0) { - err = -errno; - goto err_close_new_fd; - } + err = reuse_fd(map->fd, new_fd); + if (err) + goto err_free_new_name; - err = zclose(map->fd); - if (err) { - err = -errno; - goto err_close_new_fd; - } free(map->name); - map->fd = new_fd; map->name = new_name; map->def.type = info.type; map->def.key_size = info.key_size; @@ -4430,8 +5026,6 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) return 0; -err_close_new_fd: - close(new_fd); err_free_new_name: free(new_name); return libbpf_err(err); @@ -4452,7 +5046,7 @@ struct bpf_map *bpf_map__inner_map(struct bpf_map *map) int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) { - if (map->obj->loaded) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->def.max_entries = max_entries; @@ -4464,34 +5058,87 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) return 0; } +static int bpf_object_prepare_token(struct bpf_object *obj) +{ + const char *bpffs_path; + int bpffs_fd = -1, token_fd, err; + bool mandatory; + enum libbpf_print_level level; + + /* token is explicitly prevented */ + if (obj->token_path && obj->token_path[0] == '\0') { + pr_debug("object '%s': token is prevented, skipping...\n", obj->name); + return 0; + } + + mandatory = obj->token_path != NULL; + level = mandatory ? LIBBPF_WARN : LIBBPF_DEBUG; + + bpffs_path = obj->token_path ?: BPF_FS_DEFAULT_PATH; + bpffs_fd = open(bpffs_path, O_DIRECTORY, O_RDWR); + if (bpffs_fd < 0) { + err = -errno; + __pr(level, "object '%s': failed (%s) to open BPF FS mount at '%s'%s\n", + obj->name, errstr(err), bpffs_path, + mandatory ? "" : ", skipping optional step..."); + return mandatory ? err : 0; + } + + token_fd = bpf_token_create(bpffs_fd, 0); + close(bpffs_fd); + if (token_fd < 0) { + if (!mandatory && token_fd == -ENOENT) { + pr_debug("object '%s': BPF FS at '%s' doesn't have BPF token delegation set up, skipping...\n", + obj->name, bpffs_path); + return 0; + } + __pr(level, "object '%s': failed (%d) to create BPF token from '%s'%s\n", + obj->name, token_fd, bpffs_path, + mandatory ? "" : ", skipping optional step..."); + return mandatory ? token_fd : 0; + } + + obj->feat_cache = calloc(1, sizeof(*obj->feat_cache)); + if (!obj->feat_cache) { + close(token_fd); + return -ENOMEM; + } + + obj->token_fd = token_fd; + obj->feat_cache->token_fd = token_fd; + + return 0; +} + static int bpf_object__probe_loading(struct bpf_object *obj) { - char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }; int ret, insn_cnt = ARRAY_SIZE(insns); + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .token_fd = obj->token_fd, + .prog_flags = obj->token_fd ? BPF_F_TOKEN_FD : 0, + ); if (obj->gen_loader) return 0; ret = bump_rlimit_memlock(); if (ret) - pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret); + pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %s), you might need to do it explicitly!\n", + errstr(ret)); /* make sure basic loading works */ - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &opts); if (ret < 0) - ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); if (ret < 0) { ret = errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't load trivial BPF " - "program. Make sure your kernel supports BPF " - "(CONFIG_BPF_SYSCALL=y) and/or that RLIMIT_MEMLOCK is " - "set to big enough value.\n", __func__, cp, ret); + pr_warn("Error in %s(): %s. Couldn't load trivial BPF program. Make sure your kernel supports BPF (CONFIG_BPF_SYSCALL=y) and/or that RLIMIT_MEMLOCK is set to big enough value.\n", + __func__, errstr(ret)); return -ret; } close(ret); @@ -4499,445 +5146,46 @@ bpf_object__probe_loading(struct bpf_object *obj) return 0; } -static int probe_fd(int fd) -{ - if (fd >= 0) - close(fd); - return fd >= 0; -} - -static int probe_kern_prog_name(void) -{ - const size_t attr_sz = offsetofend(union bpf_attr, prog_name); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - union bpf_attr attr; - int ret; - - memset(&attr, 0, attr_sz); - attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.license = ptr_to_u64("GPL"); - attr.insns = ptr_to_u64(insns); - attr.insn_cnt = (__u32)ARRAY_SIZE(insns); - libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); - - /* make sure loading with name works */ - ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); - return probe_fd(ret); -} - -static int probe_kern_global_data(void) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - struct bpf_insn insns[] = { - BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), - BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int ret, map, insn_cnt = ARRAY_SIZE(insns); - - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL); - if (map < 0) { - ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); - return ret; - } - - insns[0].imm = map; - - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); - close(map); - return probe_fd(ret); -} - -static int probe_kern_btf(void) -{ - static const char strs[] = "\0int"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_func(void) -{ - static const char strs[] = "\0int\0x\0a"; - /* void x(int a) {} */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* FUNC_PROTO */ /* [2] */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), - BTF_PARAM_ENC(7, 1), - /* FUNC x */ /* [3] */ - BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_func_global(void) -{ - static const char strs[] = "\0int\0x\0a"; - /* static void x(int a) {} */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* FUNC_PROTO */ /* [2] */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), - BTF_PARAM_ENC(7, 1), - /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ - BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_datasec(void) -{ - static const char strs[] = "\0x\0.data"; - /* static int a; */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* VAR x */ /* [2] */ - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), - BTF_VAR_STATIC, - /* DATASEC val */ /* [3] */ - BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), - BTF_VAR_SECINFO_ENC(2, 0, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_float(void) -{ - static const char strs[] = "\0float"; - __u32 types[] = { - /* float */ - BTF_TYPE_FLOAT_ENC(1, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_decl_tag(void) -{ - static const char strs[] = "\0tag"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* VAR x */ /* [2] */ - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), - BTF_VAR_STATIC, - /* attr */ - BTF_TYPE_DECL_TAG_ENC(1, 2, -1), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_type_tag(void) -{ - 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(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_array_mmap(void) -{ - LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); - int fd; - - fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); - return probe_fd(fd); -} - -static int probe_kern_exp_attach_type(void) -{ - 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); - - /* 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 - */ - 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_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 */ - BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ - BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ - 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); - - fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); - return probe_fd(fd); -} - -static int probe_prog_bind_map(void) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); - - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL); - if (map < 0) { - ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); - return ret; - } - - prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); - if (prog < 0) { - close(map); - return 0; - } - - ret = bpf_prog_bind_map(prog, map, NULL); - - close(map); - close(prog); - - return ret >= 0; -} - -static int probe_module_btf(void) -{ - static const char strs[] = "\0int"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), - }; - struct bpf_btf_info info; - __u32 len = sizeof(info); - char name[16]; - int fd, err; - - fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); - if (fd < 0) - return 0; /* BTF not supported at all */ - - memset(&info, 0, sizeof(info)); - info.name = ptr_to_u64(name); - info.name_len = sizeof(name); - - /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; - * kernel's module BTF support coincides with support for - * name/name_len fields in struct bpf_btf_info. - */ - err = bpf_obj_get_info_by_fd(fd, &info, &len); - close(fd); - return !err; -} - -static int probe_perf_link(void) -{ - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int prog_fd, link_fd, err; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", - insns, ARRAY_SIZE(insns), NULL); - if (prog_fd < 0) - return -errno; - - /* use invalid perf_event FD to get EBADF, if link is supported; - * otherwise EINVAL should be returned - */ - link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); - err = -errno; /* close() can clobber errno */ - - if (link_fd >= 0) - close(link_fd); - close(prog_fd); - - return link_fd < 0 && err == -EBADF; -} - -static int probe_kern_bpf_cookie(void) -{ - struct bpf_insn insns[] = { - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), - BPF_EXIT_INSN(), - }; - int ret, insn_cnt = ARRAY_SIZE(insns); - - ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL); - return probe_fd(ret); -} - -static int probe_kern_btf_enum64(void) -{ - static const char strs[] = "\0enum64"; - __u32 types[] = { - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_syscall_wrapper(void); - -enum kern_feature_result { - FEAT_UNKNOWN = 0, - FEAT_SUPPORTED = 1, - FEAT_MISSING = 2, -}; - -typedef int (*feature_probe_fn)(void); - -static struct kern_feature_desc { - const char *desc; - feature_probe_fn probe; - enum kern_feature_result res; -} feature_probes[__FEAT_CNT] = { - [FEAT_PROG_NAME] = { - "BPF program name", probe_kern_prog_name, - }, - [FEAT_GLOBAL_DATA] = { - "global variables", probe_kern_global_data, - }, - [FEAT_BTF] = { - "minimal BTF", probe_kern_btf, - }, - [FEAT_BTF_FUNC] = { - "BTF functions", probe_kern_btf_func, - }, - [FEAT_BTF_GLOBAL_FUNC] = { - "BTF global function", probe_kern_btf_func_global, - }, - [FEAT_BTF_DATASEC] = { - "BTF data section and variable", probe_kern_btf_datasec, - }, - [FEAT_ARRAY_MMAP] = { - "ARRAY map mmap()", probe_kern_array_mmap, - }, - [FEAT_EXP_ATTACH_TYPE] = { - "BPF_PROG_LOAD expected_attach_type attribute", - probe_kern_exp_attach_type, - }, - [FEAT_PROBE_READ_KERN] = { - "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, - }, - [FEAT_PROG_BIND_MAP] = { - "BPF_PROG_BIND_MAP support", probe_prog_bind_map, - }, - [FEAT_MODULE_BTF] = { - "module BTF support", probe_module_btf, - }, - [FEAT_BTF_FLOAT] = { - "BTF_KIND_FLOAT support", probe_kern_btf_float, - }, - [FEAT_PERF_LINK] = { - "BPF perf link support", probe_perf_link, - }, - [FEAT_BTF_DECL_TAG] = { - "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, - }, - [FEAT_BTF_TYPE_TAG] = { - "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, - }, - [FEAT_MEMCG_ACCOUNT] = { - "memcg-based memory accounting", probe_memcg_account, - }, - [FEAT_BPF_COOKIE] = { - "BPF cookie support", probe_kern_bpf_cookie, - }, - [FEAT_BTF_ENUM64] = { - "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, - }, - [FEAT_SYSCALL_WRAPPER] = { - "Kernel using syscall wrapper", probe_kern_syscall_wrapper, - }, -}; - 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 && obj->gen_loader) + if (obj->gen_loader) /* To generate loader program assume the latest kernel * to avoid doing extra prog_load, map_create syscalls. */ return true; - if (READ_ONCE(feat->res) == FEAT_UNKNOWN) { - ret = feat->probe(); - if (ret > 0) { - WRITE_ONCE(feat->res, FEAT_SUPPORTED); - } else if (ret == 0) { - WRITE_ONCE(feat->res, FEAT_MISSING); - } else { - pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); - WRITE_ONCE(feat->res, FEAT_MISSING); - } - } + if (obj->token_fd) + return feat_supported(obj->feat_cache, feat_id); - return READ_ONCE(feat->res) == FEAT_SUPPORTED; + return feat_supported(NULL, feat_id); } static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) { struct bpf_map_info map_info; - char msg[STRERR_BUFSIZE]; __u32 map_info_len = sizeof(map_info); int err; memset(&map_info, 0, map_info_len); - err = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len); + err = bpf_map_get_info_by_fd(map_fd, &map_info, &map_info_len); if (err && errno == EINVAL) err = bpf_get_map_info_from_fdinfo(map_fd, &map_info); if (err) { pr_warn("failed to get map info for map FD %d: %s\n", map_fd, - libbpf_strerror_r(errno, msg, sizeof(msg))); + errstr(err)); return false; } + /* + * bpf_get_map_info_by_fd() for DEVMAP will always return flags with + * BPF_F_RDONLY_PROG set, but it generally is not set at map creation time. + * Thus, ignore the BPF_F_RDONLY_PROG flag in the flags returned from + * bpf_get_map_info_by_fd() when checking for compatibility with an + * existing DEVMAP. + */ + if (map->def.type == BPF_MAP_TYPE_DEVMAP || map->def.type == BPF_MAP_TYPE_DEVMAP_HASH) + map_info.map_flags &= ~BPF_F_RDONLY_PROG; + return (map_info.type == map->def.type && map_info.key_size == map->def.key_size && map_info.value_size == map->def.value_size && @@ -4949,7 +5197,6 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) static int bpf_object__reuse_map(struct bpf_map *map) { - char *cp, errmsg[STRERR_BUFSIZE]; int err, pin_fd; pin_fd = bpf_obj_get(map->pin_path); @@ -4961,9 +5208,8 @@ bpf_object__reuse_map(struct bpf_map *map) return 0; } - cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); pr_warn("couldn't retrieve pinned map '%s': %s\n", - map->pin_path, cp); + map->pin_path, errstr(err)); return err; } @@ -4989,8 +5235,8 @@ static int bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) { enum libbpf_map_type map_type = map->libbpf_type; - char *cp, errmsg[STRERR_BUFSIZE]; int err, zero = 0; + size_t mmap_sz; if (obj->gen_loader) { bpf_gen__map_update_elem(obj->gen_loader, map - obj->maps, @@ -4999,12 +5245,12 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) bpf_gen__map_freeze(obj->gen_loader, map - obj->maps); return 0; } + err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0); if (err) { err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("Error setting initial map(%s) contents: %s\n", - map->name, cp); + pr_warn("map '%s': failed to set initial contents: %s\n", + bpf_map__name(map), errstr(err)); return err; } @@ -5013,12 +5259,43 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) err = bpf_map_freeze(map->fd); if (err) { err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("Error freezing map(%s) as read-only: %s\n", - map->name, cp); + pr_warn("map '%s': failed to freeze as read-only: %s\n", + bpf_map__name(map), errstr(err)); return err; } } + + /* Remap anonymous mmap()-ed "map initialization image" as + * a BPF map-backed mmap()-ed memory, but preserving the same + * memory address. This will cause kernel to change process' + * page table to point to a different piece of kernel memory, + * but from userspace point of view memory address (and its + * contents, being identical at this point) will stay the + * same. This mapping will be released by bpf_object__close() + * as per normal clean up procedure. + */ + mmap_sz = bpf_map_mmap_sz(map); + if (map->def.map_flags & BPF_F_MMAPABLE) { + void *mmaped; + int prot; + + if (map->def.map_flags & BPF_F_RDONLY_PROG) + prot = PROT_READ; + else + prot = PROT_READ | PROT_WRITE; + mmaped = mmap(map->mmaped, mmap_sz, prot, MAP_SHARED | MAP_FIXED, map->fd, 0); + if (mmaped == MAP_FAILED) { + err = -errno; + pr_warn("map '%s': failed to re-mmap() contents: %s\n", + bpf_map__name(map), errstr(err)); + return err; + } + map->mmaped = mmaped; + } else if (map->mmaped) { + munmap(map->mmaped, mmap_sz); + map->mmaped = NULL; + } + return 0; } @@ -5029,7 +5306,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b LIBBPF_OPTS(bpf_map_create_opts, create_attr); struct bpf_map_def *def = &map->def; const char *map_name = NULL; - int err = 0; + int err = 0, map_fd; if (kernel_supports(obj, FEAT_PROG_NAME)) map_name = map->name; @@ -5037,9 +5314,25 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.map_flags = def->map_flags; create_attr.numa_node = map->numa_node; create_attr.map_extra = map->map_extra; + create_attr.token_fd = obj->token_fd; + if (obj->token_fd) + create_attr.map_flags |= BPF_F_TOKEN_FD; + if (map->excl_prog) { + err = bpf_prog_compute_hash(map->excl_prog); + if (err) + return err; + + create_attr.excl_prog_hash = map->excl_prog->hash; + create_attr.excl_prog_hash_size = SHA256_DIGEST_LENGTH; + } - if (bpf_map__is_struct_ops(map)) + if (bpf_map__is_struct_ops(map)) { create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->mod_btf_fd >= 0) { + create_attr.value_type_btf_obj_fd = map->mod_btf_fd; + create_attr.map_flags |= BPF_F_VTYPE_BTF_OBJ_FD; + } + } if (obj->btf && btf__fd(obj->btf) >= 0) { create_attr.btf_fd = btf__fd(obj->btf); @@ -5049,13 +5342,16 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b if (bpf_map_type__is_map_in_map(def->type)) { if (map->inner_map) { + err = map_set_def_max_entries(map->inner_map); + if (err) + return err; err = bpf_object__create_map(obj, map->inner_map, true); if (err) { - pr_warn("map '%s': failed to create inner map: %d\n", - map->name, err); + pr_warn("map '%s': failed to create inner map: %s\n", + map->name, errstr(err)); return err; } - map->inner_map_fd = bpf_map__fd(map->inner_map); + map->inner_map_fd = map->inner_map->fd; } if (map->inner_map_fd >= 0) create_attr.inner_map_fd = map->inner_map_fd; @@ -5075,11 +5371,16 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_ARENA: create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; map->btf_key_type_id = 0; map->btf_value_type_id = 0; + break; + case BPF_MAP_TYPE_STRUCT_OPS: + create_attr.btf_value_type_id = 0; + break; default: break; } @@ -5088,35 +5389,32 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b bpf_gen__map_create(obj->gen_loader, def->type, map_name, def->key_size, def->value_size, def->max_entries, &create_attr, is_inner ? -1 : map - obj->maps); - /* Pretend to have valid FD to pass various fd >= 0 checks. - * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. + /* We keep pretenting we have valid FD to pass various fd >= 0 + * checks by just keeping original placeholder FDs in place. + * See bpf_object__add_map() comment. + * This placeholder fd will not be used with any syscall and + * will be reset to -1 eventually. */ - map->fd = 0; + map_fd = map->fd; } else { - map->fd = bpf_map_create(def->type, map_name, - def->key_size, def->value_size, - def->max_entries, &create_attr); + map_fd = bpf_map_create(def->type, map_name, + def->key_size, def->value_size, + def->max_entries, &create_attr); } - if (map->fd < 0 && (create_attr.btf_key_type_id || - create_attr.btf_value_type_id)) { - char *cp, errmsg[STRERR_BUFSIZE]; - + if (map_fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", - map->name, cp, err); + pr_warn("Error in bpf_create_map_xattr(%s): %s. Retrying without BTF.\n", + map->name, errstr(err)); create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; map->btf_key_type_id = 0; map->btf_value_type_id = 0; - map->fd = bpf_map_create(def->type, map_name, - def->key_size, def->value_size, - def->max_entries, &create_attr); + map_fd = bpf_map_create(def->type, map_name, + def->key_size, def->value_size, + def->max_entries, &create_attr); } - err = map->fd < 0 ? -errno : 0; - if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) { if (obj->gen_loader) map->inner_map->fd = -1; @@ -5124,7 +5422,19 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b zfree(&map->inner_map); } - return err; + if (map_fd < 0) + return map_fd; + + /* obj->gen_loader case, prevent reuse_fd() from closing map_fd */ + if (map->fd == map_fd) + return 0; + + /* Keep placeholder FD value but now point it to the BPF map object. + * This way everything that relied on this map's FD (e.g., relocated + * ldimm64 instructions) will stay valid and won't need adjustments. + * map->fd stays valid but now point to what map_fd points to. + */ + return reuse_fd(map->fd, map_fd); } static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map) @@ -5138,7 +5448,7 @@ static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map) continue; targ_map = map->init_slots[i]; - fd = bpf_map__fd(targ_map); + fd = targ_map->fd; if (obj->gen_loader) { bpf_gen__populate_outer_map(obj->gen_loader, @@ -5149,8 +5459,8 @@ static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map) } if (err) { err = -errno; - pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", - map->name, i, targ_map->name, fd, err); + pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %s\n", + map->name, i, targ_map->name, fd, errstr(err)); return err; } pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n", @@ -5182,8 +5492,8 @@ static int init_prog_array_slots(struct bpf_object *obj, struct bpf_map *map) err = bpf_map_update_elem(map->fd, &i, &fd, 0); if (err) { err = -errno; - pr_warn("map '%s': failed to initialize slot [%d] to prog '%s' fd=%d: %d\n", - map->name, i, targ_prog->name, fd, err); + pr_warn("map '%s': failed to initialize slot [%d] to prog '%s' fd=%d: %s\n", + map->name, i, targ_prog->name, fd, errstr(err)); return err; } pr_debug("map '%s': slot [%d] set to prog '%s' fd=%d\n", @@ -5208,10 +5518,8 @@ static int bpf_object_init_prog_arrays(struct bpf_object *obj) continue; err = init_prog_array_slots(obj, map); - if (err < 0) { - zclose(map->fd); + if (err < 0) return err; - } } return 0; } @@ -5238,7 +5546,6 @@ static int bpf_object__create_maps(struct bpf_object *obj) { struct bpf_map *map; - char *cp, errmsg[STRERR_BUFSIZE]; unsigned int i, j; int err; bool retried; @@ -5289,7 +5596,7 @@ retry: } } - if (map->fd >= 0) { + if (map->reused) { pr_debug("map '%s': skipping creation (preset fd=%d)\n", map->name, map->fd); } else { @@ -5302,31 +5609,41 @@ retry: if (bpf_map__is_internal(map)) { err = bpf_object__populate_internal_map(obj, map); - if (err < 0) { - zclose(map->fd); + if (err < 0) goto err_out; + } else if (map->def.type == BPF_MAP_TYPE_ARENA) { + map->mmaped = mmap((void *)(long)map->map_extra, + bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, + map->map_extra ? MAP_SHARED | MAP_FIXED : MAP_SHARED, + map->fd, 0); + if (map->mmaped == MAP_FAILED) { + err = -errno; + map->mmaped = NULL; + pr_warn("map '%s': failed to mmap arena: %s\n", + map->name, errstr(err)); + return err; + } + if (obj->arena_data) { + memcpy(map->mmaped, obj->arena_data, obj->arena_data_sz); + zfree(&obj->arena_data); } } - 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); + if (err < 0) goto err_out; - } } } if (map->pin_path && !map->pinned) { err = bpf_map__pin(map, NULL); if (err) { - zclose(map->fd); if (!retried && err == -EEXIST) { retried = true; goto retry; } - pr_warn("map '%s': failed to auto-pin at '%s': %d\n", - map->name, map->pin_path, err); + pr_warn("map '%s': failed to auto-pin at '%s': %s\n", + map->name, map->pin_path, errstr(err)); goto err_out; } } @@ -5335,8 +5652,7 @@ retry: return 0; err_out: - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("map '%s': failed to create: %s(%d)\n", map->name, cp, err); + pr_warn("map '%s': failed to create: %s\n", map->name, errstr(err)); pr_perm_msg(err); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); @@ -5454,9 +5770,13 @@ static int load_module_btfs(struct bpf_object *obj) err = bpf_btf_get_next_id(id, &id); if (err && errno == ENOENT) return 0; + if (err && errno == EPERM) { + pr_debug("skipping module BTFs loading, missing privileges\n"); + return 0; + } if (err) { err = -errno; - pr_warn("failed to iterate BTF objects: %d\n", err); + pr_warn("failed to iterate BTF objects: %s\n", errstr(err)); return err; } @@ -5465,7 +5785,7 @@ static int load_module_btfs(struct bpf_object *obj) if (errno == ENOENT) continue; /* expected race: BTF was unloaded */ err = -errno; - pr_warn("failed to get BTF object #%d FD: %d\n", id, err); + pr_warn("failed to get BTF object #%d FD: %s\n", id, errstr(err)); return err; } @@ -5474,10 +5794,10 @@ static int load_module_btfs(struct bpf_object *obj) info.name = ptr_to_u64(name); info.name_len = sizeof(name); - err = bpf_obj_get_info_by_fd(fd, &info, &len); + err = bpf_btf_get_info_by_fd(fd, &info, &len); if (err) { err = -errno; - pr_warn("failed to get BTF object #%d info: %d\n", id, err); + pr_warn("failed to get BTF object #%d info: %s\n", id, errstr(err)); goto err_out; } @@ -5490,8 +5810,8 @@ static int load_module_btfs(struct bpf_object *obj) btf = btf_get_from_fd(fd, obj->btf_vmlinux); err = libbpf_get_error(btf); if (err) { - pr_warn("failed to load module [%s]'s BTF object #%d: %d\n", - name, id, err); + pr_warn("failed to load module [%s]'s BTF object #%d: %s\n", + name, id, errstr(err)); goto err_out; } @@ -5720,7 +6040,7 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) obj->btf_vmlinux_override = btf__parse(targ_btf_path, NULL); err = libbpf_get_error(obj->btf_vmlinux_override); if (err) { - pr_warn("failed to parse target BTF: %d\n", err); + pr_warn("failed to parse target BTF: %s\n", errstr(err)); return err; } } @@ -5780,8 +6100,8 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) err = record_relo_core(prog, rec, insn_idx); if (err) { - pr_warn("prog '%s': relo #%d: failed to record relocation: %d\n", - prog->name, i, err); + pr_warn("prog '%s': relo #%d: failed to record relocation: %s\n", + prog->name, i, errstr(err)); goto out; } @@ -5790,15 +6110,15 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) err = bpf_core_resolve_relo(prog, rec, i, obj->btf, cand_cache, &targ_res); if (err) { - pr_warn("prog '%s': relo #%d: failed to relocate: %d\n", - prog->name, i, err); + pr_warn("prog '%s': relo #%d: failed to relocate: %s\n", + prog->name, i, errstr(err)); goto out; } err = bpf_core_patch_insn(prog->name, insn, insn_idx, rec, i, &targ_res); if (err) { - pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %d\n", - prog->name, i, insn_idx, err); + pr_warn("prog '%s': relo #%d: failed to patch insn #%u: %s\n", + prog->name, i, insn_idx, errstr(err)); goto out; } } @@ -5819,8 +6139,8 @@ out: } /* base map load ldimm64 special constant, used also for log fixup logic */ -#define MAP_LDIMM64_POISON_BASE 2001000000 -#define MAP_LDIMM64_POISON_PFX "200100" +#define POISON_LDIMM64_MAP_BASE 2001000000 +#define POISON_LDIMM64_MAP_PFX "200100" static void poison_map_ldimm64(struct bpf_program *prog, int relo_idx, int insn_idx, struct bpf_insn *insn, @@ -5842,12 +6162,187 @@ static void poison_map_ldimm64(struct bpf_program *prog, int relo_idx, * invalid func unknown#2001000123 * where lower 123 is map index into obj->maps[] array */ - insn->imm = MAP_LDIMM64_POISON_BASE + map_idx; + insn->imm = POISON_LDIMM64_MAP_BASE + map_idx; insn++; } } +/* unresolved kfunc call special constant, used also for log fixup logic */ +#define POISON_CALL_KFUNC_BASE 2002000000 +#define POISON_CALL_KFUNC_PFX "2002" + +static void poison_kfunc_call(struct bpf_program *prog, int relo_idx, + int insn_idx, struct bpf_insn *insn, + int ext_idx, const struct extern_desc *ext) +{ + pr_debug("prog '%s': relo #%d: poisoning insn #%d that calls kfunc '%s'\n", + prog->name, relo_idx, insn_idx, ext->name); + + /* we turn kfunc call into invalid helper call with identifiable constant */ + insn->code = BPF_JMP | BPF_CALL; + insn->dst_reg = 0; + insn->src_reg = 0; + insn->off = 0; + /* if this instruction is reachable (not a dead code), + * verifier will complain with something like: + * invalid func unknown#2001000123 + * where lower 123 is extern index into obj->externs[] array + */ + insn->imm = POISON_CALL_KFUNC_BASE + ext_idx; +} + +static int find_jt_map(struct bpf_object *obj, struct bpf_program *prog, int sym_off) +{ + size_t i; + + for (i = 0; i < obj->jumptable_map_cnt; i++) { + /* + * This might happen that same offset is used for two different + * programs (as jump tables can be the same). However, for + * different programs different maps should be created. + */ + if (obj->jumptable_maps[i].sym_off == sym_off && + obj->jumptable_maps[i].prog == prog) + return obj->jumptable_maps[i].fd; + } + + return -ENOENT; +} + +static int add_jt_map(struct bpf_object *obj, struct bpf_program *prog, int sym_off, int map_fd) +{ + size_t cnt = obj->jumptable_map_cnt; + size_t size = sizeof(obj->jumptable_maps[0]); + void *tmp; + + tmp = libbpf_reallocarray(obj->jumptable_maps, cnt + 1, size); + if (!tmp) + return -ENOMEM; + + obj->jumptable_maps = tmp; + obj->jumptable_maps[cnt].prog = prog; + obj->jumptable_maps[cnt].sym_off = sym_off; + obj->jumptable_maps[cnt].fd = map_fd; + obj->jumptable_map_cnt++; + + return 0; +} + +static int find_subprog_idx(struct bpf_program *prog, int insn_idx) +{ + int i; + + for (i = prog->subprog_cnt - 1; i >= 0; i--) { + if (insn_idx >= prog->subprogs[i].sub_insn_off) + return i; + } + + return -1; +} + +static int create_jt_map(struct bpf_object *obj, struct bpf_program *prog, struct reloc_desc *relo) +{ + const __u32 jt_entry_size = 8; + int sym_off = relo->sym_off; + int jt_size = relo->sym_size; + __u32 max_entries = jt_size / jt_entry_size; + __u32 value_size = sizeof(struct bpf_insn_array_value); + struct bpf_insn_array_value val = {}; + int subprog_idx; + int map_fd, err; + __u64 insn_off; + __u64 *jt; + __u32 i; + + map_fd = find_jt_map(obj, prog, sym_off); + if (map_fd >= 0) + return map_fd; + + if (sym_off % jt_entry_size) { + pr_warn("map '.jumptables': jumptable start %d should be multiple of %u\n", + sym_off, jt_entry_size); + return -EINVAL; + } + + if (jt_size % jt_entry_size) { + pr_warn("map '.jumptables': jumptable size %d should be multiple of %u\n", + jt_size, jt_entry_size); + return -EINVAL; + } + + map_fd = bpf_map_create(BPF_MAP_TYPE_INSN_ARRAY, ".jumptables", + 4, value_size, max_entries, NULL); + if (map_fd < 0) + return map_fd; + + if (!obj->jumptables_data) { + pr_warn("map '.jumptables': ELF file is missing jump table data\n"); + err = -EINVAL; + goto err_close; + } + if (sym_off + jt_size > obj->jumptables_data_sz) { + pr_warn("map '.jumptables': jumptables_data size is %zd, trying to access %d\n", + obj->jumptables_data_sz, sym_off + jt_size); + err = -EINVAL; + goto err_close; + } + + subprog_idx = -1; /* main program */ + if (relo->insn_idx < 0 || relo->insn_idx >= prog->insns_cnt) { + pr_warn("map '.jumptables': invalid instruction index %d\n", relo->insn_idx); + err = -EINVAL; + goto err_close; + } + if (prog->subprogs) + subprog_idx = find_subprog_idx(prog, relo->insn_idx); + + jt = (__u64 *)(obj->jumptables_data + sym_off); + for (i = 0; i < max_entries; i++) { + /* + * The offset should be made to be relative to the beginning of + * the main function, not the subfunction. + */ + insn_off = jt[i]/sizeof(struct bpf_insn); + if (subprog_idx >= 0) { + insn_off -= prog->subprogs[subprog_idx].sec_insn_off; + insn_off += prog->subprogs[subprog_idx].sub_insn_off; + } else { + insn_off -= prog->sec_insn_off; + } + + /* + * LLVM-generated jump tables contain u64 records, however + * should contain values that fit in u32. + */ + if (insn_off > UINT32_MAX) { + pr_warn("map '.jumptables': invalid jump table value 0x%llx at offset %d\n", + (long long)jt[i], sym_off + i * jt_entry_size); + err = -EINVAL; + goto err_close; + } + + val.orig_off = insn_off; + err = bpf_map_update_elem(map_fd, &i, &val, 0); + if (err) + goto err_close; + } + + err = bpf_map_freeze(map_fd); + if (err) + goto err_close; + + err = add_jt_map(obj, prog, sym_off, map_fd); + if (err) + goto err_close; + + return map_fd; + +err_close: + close(map_fd); + return err; +} + /* Relocate data references within program code: * - map references; * - global variable references; @@ -5892,8 +6387,8 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) relo->map_idx, map); } break; - case RELO_EXTERN_VAR: - ext = &obj->externs[relo->sym_off]; + case RELO_EXTERN_LD64: + ext = &obj->externs[relo->ext_idx]; if (ext->type == EXT_KCFG) { if (obj->gen_loader) { insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; @@ -5914,15 +6409,15 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) } } break; - case RELO_EXTERN_FUNC: - ext = &obj->externs[relo->sym_off]; + case RELO_EXTERN_CALL: + ext = &obj->externs[relo->ext_idx]; insn[0].src_reg = BPF_PSEUDO_KFUNC_CALL; if (ext->is_set) { insn[0].imm = ext->ksym.kernel_btf_id; insn[0].off = ext->ksym.btf_fd_idx; - } else { /* unresolved weak kfunc */ - insn[0].imm = 0; - insn[0].off = 0; + } else { /* unresolved weak kfunc call */ + poison_kfunc_call(prog, i, relo->insn_idx, insn, + relo->ext_idx, ext); } break; case RELO_SUBPROG_ADDR: @@ -5939,6 +6434,20 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) case RELO_CORE: /* will be handled by bpf_program_record_relos() */ break; + case RELO_INSN_ARRAY: { + int map_fd; + + map_fd = create_jt_map(obj, prog, relo); + if (map_fd < 0) { + pr_warn("prog '%s': relo #%d: can't create jump table: sym_off %u\n", + prog->name, i, relo->sym_off); + return map_fd; + } + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn->imm = map_fd; + insn->off = 0; + } + break; default: pr_warn("prog '%s': relo #%d: bad relo type %d\n", prog->name, i, relo->type); @@ -6025,7 +6534,7 @@ reloc_prog_func_and_line_info(const struct bpf_object *obj, int err; /* no .BTF.ext relocation if .BTF.ext is missing or kernel doesn't - * supprot func/line info + * support func/line info */ if (!obj->btf_ext || !kernel_supports(obj, FEAT_BTF_FUNC)) return 0; @@ -6042,8 +6551,8 @@ reloc_prog_func_and_line_info(const struct bpf_object *obj, &main_prog->func_info_rec_size); if (err) { if (err != -ENOENT) { - pr_warn("prog '%s': error relocating .BTF.ext function info: %d\n", - prog->name, err); + pr_warn("prog '%s': error relocating .BTF.ext function info: %s\n", + prog->name, errstr(err)); return err; } if (main_prog->func_info) { @@ -6070,8 +6579,8 @@ line_info: &main_prog->line_info_rec_size); if (err) { if (err != -ENOENT) { - pr_warn("prog '%s': error relocating .BTF.ext line info: %d\n", - prog->name, err); + pr_warn("prog '%s': error relocating .BTF.ext line info: %s\n", + prog->name, errstr(err)); return err; } if (main_prog->line_info) { @@ -6116,7 +6625,11 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra if (main_prog == subprog) return 0; relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos)); - if (!relos) + /* if new count is zero, reallocarray can return a valid NULL result; + * in this case the previous pointer will be freed, so we *have to* + * reassign old pointer to the new value (even if it's NULL) + */ + if (!relos && new_cnt) return -ENOMEM; if (subprog->nr_reloc) memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, @@ -6132,14 +6645,72 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra return 0; } +static int save_subprog_offsets(struct bpf_program *main_prog, struct bpf_program *subprog) +{ + size_t size = sizeof(main_prog->subprogs[0]); + int cnt = main_prog->subprog_cnt; + void *tmp; + + tmp = libbpf_reallocarray(main_prog->subprogs, cnt + 1, size); + if (!tmp) + return -ENOMEM; + + main_prog->subprogs = tmp; + main_prog->subprogs[cnt].sec_insn_off = subprog->sec_insn_off; + main_prog->subprogs[cnt].sub_insn_off = subprog->sub_insn_off; + main_prog->subprog_cnt++; + + return 0; +} + +static int +bpf_object__append_subprog_code(struct bpf_object *obj, struct bpf_program *main_prog, + struct bpf_program *subprog) +{ + struct bpf_insn *insns; + size_t new_cnt; + int err; + + subprog->sub_insn_off = main_prog->insns_cnt; + + new_cnt = main_prog->insns_cnt + subprog->insns_cnt; + insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns)); + if (!insns) { + pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name); + return -ENOMEM; + } + main_prog->insns = insns; + main_prog->insns_cnt = new_cnt; + + memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns, + subprog->insns_cnt * sizeof(*insns)); + + pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", + main_prog->name, subprog->insns_cnt, subprog->name); + + /* The subprog insns are now appended. Append its relos too. */ + err = append_subprog_relos(main_prog, subprog); + if (err) + return err; + + err = save_subprog_offsets(main_prog, subprog); + if (err) { + pr_warn("prog '%s': failed to add subprog offsets: %s\n", + main_prog->name, errstr(err)); + return err; + } + + return 0; +} + static int bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, struct bpf_program *prog) { - size_t sub_insn_idx, insn_idx, new_cnt; + size_t sub_insn_idx, insn_idx; struct bpf_program *subprog; - struct bpf_insn *insns, *insn; struct reloc_desc *relo; + struct bpf_insn *insn; int err; err = reloc_prog_func_and_line_info(obj, main_prog, prog); @@ -6152,7 +6723,7 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, continue; relo = find_prog_insn_relo(prog, insn_idx); - if (relo && relo->type == RELO_EXTERN_FUNC) + if (relo && relo->type == RELO_EXTERN_CALL) /* kfunc relocations will be handled later * in bpf_object__relocate_data() */ @@ -6214,25 +6785,7 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, * and relocate. */ if (subprog->sub_insn_off == 0) { - subprog->sub_insn_off = main_prog->insns_cnt; - - new_cnt = main_prog->insns_cnt + subprog->insns_cnt; - insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns)); - if (!insns) { - pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name); - return -ENOMEM; - } - main_prog->insns = insns; - main_prog->insns_cnt = new_cnt; - - memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns, - subprog->insns_cnt * sizeof(*insns)); - - pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", - main_prog->name, subprog->insns_cnt, subprog->name); - - /* The subprog insns are now appended. Append its relos too. */ - err = append_subprog_relos(main_prog, subprog); + err = bpf_object__append_subprog_code(obj, main_prog, subprog); if (err) return err; err = bpf_object__reloc_code(obj, main_prog, subprog); @@ -6407,8 +6960,408 @@ static void bpf_object__sort_relos(struct bpf_object *obj) } } -static int -bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) +static int bpf_prog_assign_exc_cb(struct bpf_object *obj, struct bpf_program *prog) +{ + const char *str = "exception_callback:"; + size_t pfx_len = strlen(str); + int i, j, n; + + if (!obj->btf || !kernel_supports(obj, FEAT_BTF_DECL_TAG)) + return 0; + + n = btf__type_cnt(obj->btf); + for (i = 1; i < n; i++) { + const char *name; + struct btf_type *t; + + t = btf_type_by_id(obj->btf, i); + if (!btf_is_decl_tag(t) || btf_decl_tag(t)->component_idx != -1) + continue; + + name = btf__str_by_offset(obj->btf, t->name_off); + if (strncmp(name, str, pfx_len) != 0) + continue; + + t = btf_type_by_id(obj->btf, t->type); + if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) { + pr_warn("prog '%s': exception_callback:<value> decl tag not applied to the main program\n", + prog->name); + return -EINVAL; + } + if (strcmp(prog->name, btf__str_by_offset(obj->btf, t->name_off)) != 0) + continue; + /* Multiple callbacks are specified for the same prog, + * the verifier will eventually return an error for this + * case, hence simply skip appending a subprog. + */ + if (prog->exception_cb_idx >= 0) { + prog->exception_cb_idx = -1; + break; + } + + name += pfx_len; + if (str_is_empty(name)) { + pr_warn("prog '%s': exception_callback:<value> decl tag contains empty value\n", + prog->name); + return -EINVAL; + } + + for (j = 0; j < obj->nr_programs; j++) { + struct bpf_program *subprog = &obj->programs[j]; + + if (!prog_is_subprog(obj, subprog)) + continue; + if (strcmp(name, subprog->name) != 0) + continue; + /* Enforce non-hidden, as from verifier point of + * view it expects global functions, whereas the + * mark_btf_static fixes up linkage as static. + */ + if (!subprog->sym_global || subprog->mark_btf_static) { + pr_warn("prog '%s': exception callback %s must be a global non-hidden function\n", + prog->name, subprog->name); + return -EINVAL; + } + /* Let's see if we already saw a static exception callback with the same name */ + if (prog->exception_cb_idx >= 0) { + pr_warn("prog '%s': multiple subprogs with same name as exception callback '%s'\n", + prog->name, subprog->name); + return -EINVAL; + } + prog->exception_cb_idx = j; + break; + } + + if (prog->exception_cb_idx >= 0) + continue; + + pr_warn("prog '%s': cannot find exception callback '%s'\n", prog->name, name); + return -ENOENT; + } + + return 0; +} + +static struct { + enum bpf_prog_type prog_type; + const char *ctx_name; +} global_ctx_map[] = { + { BPF_PROG_TYPE_CGROUP_DEVICE, "bpf_cgroup_dev_ctx" }, + { BPF_PROG_TYPE_CGROUP_SKB, "__sk_buff" }, + { BPF_PROG_TYPE_CGROUP_SOCK, "bpf_sock" }, + { BPF_PROG_TYPE_CGROUP_SOCK_ADDR, "bpf_sock_addr" }, + { BPF_PROG_TYPE_CGROUP_SOCKOPT, "bpf_sockopt" }, + { BPF_PROG_TYPE_CGROUP_SYSCTL, "bpf_sysctl" }, + { BPF_PROG_TYPE_FLOW_DISSECTOR, "__sk_buff" }, + { BPF_PROG_TYPE_KPROBE, "bpf_user_pt_regs_t" }, + { BPF_PROG_TYPE_LWT_IN, "__sk_buff" }, + { BPF_PROG_TYPE_LWT_OUT, "__sk_buff" }, + { BPF_PROG_TYPE_LWT_SEG6LOCAL, "__sk_buff" }, + { BPF_PROG_TYPE_LWT_XMIT, "__sk_buff" }, + { BPF_PROG_TYPE_NETFILTER, "bpf_nf_ctx" }, + { BPF_PROG_TYPE_PERF_EVENT, "bpf_perf_event_data" }, + { BPF_PROG_TYPE_RAW_TRACEPOINT, "bpf_raw_tracepoint_args" }, + { BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, "bpf_raw_tracepoint_args" }, + { BPF_PROG_TYPE_SCHED_ACT, "__sk_buff" }, + { BPF_PROG_TYPE_SCHED_CLS, "__sk_buff" }, + { BPF_PROG_TYPE_SK_LOOKUP, "bpf_sk_lookup" }, + { BPF_PROG_TYPE_SK_MSG, "sk_msg_md" }, + { BPF_PROG_TYPE_SK_REUSEPORT, "sk_reuseport_md" }, + { BPF_PROG_TYPE_SK_SKB, "__sk_buff" }, + { BPF_PROG_TYPE_SOCK_OPS, "bpf_sock_ops" }, + { BPF_PROG_TYPE_SOCKET_FILTER, "__sk_buff" }, + { BPF_PROG_TYPE_XDP, "xdp_md" }, + /* all other program types don't have "named" context structs */ +}; + +/* forward declarations for arch-specific underlying types of bpf_user_pt_regs_t typedef, + * for below __builtin_types_compatible_p() checks; + * with this approach we don't need any extra arch-specific #ifdef guards + */ +struct pt_regs; +struct user_pt_regs; +struct user_regs_struct; + +static bool need_func_arg_type_fixup(const struct btf *btf, const struct bpf_program *prog, + const char *subprog_name, int arg_idx, + int arg_type_id, const char *ctx_name) +{ + const struct btf_type *t; + const char *tname; + + /* check if existing parameter already matches verifier expectations */ + t = skip_mods_and_typedefs(btf, arg_type_id, NULL); + if (!btf_is_ptr(t)) + goto out_warn; + + /* typedef bpf_user_pt_regs_t is a special PITA case, valid for kprobe + * and perf_event programs, so check this case early on and forget + * about it for subsequent checks + */ + while (btf_is_mod(t)) + t = btf__type_by_id(btf, t->type); + if (btf_is_typedef(t) && + (prog->type == BPF_PROG_TYPE_KPROBE || prog->type == BPF_PROG_TYPE_PERF_EVENT)) { + tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>"; + if (strcmp(tname, "bpf_user_pt_regs_t") == 0) + return false; /* canonical type for kprobe/perf_event */ + } + + /* now we can ignore typedefs moving forward */ + t = skip_mods_and_typedefs(btf, t->type, NULL); + + /* if it's `void *`, definitely fix up BTF info */ + if (btf_is_void(t)) + return true; + + /* if it's already proper canonical type, no need to fix up */ + tname = btf__str_by_offset(btf, t->name_off) ?: "<anon>"; + if (btf_is_struct(t) && strcmp(tname, ctx_name) == 0) + return false; + + /* special cases */ + switch (prog->type) { + case BPF_PROG_TYPE_KPROBE: + /* `struct pt_regs *` is expected, but we need to fix up */ + if (btf_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return true; + break; + case BPF_PROG_TYPE_PERF_EVENT: + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct pt_regs) && + btf_is_struct(t) && strcmp(tname, "pt_regs") == 0) + return true; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_pt_regs) && + btf_is_struct(t) && strcmp(tname, "user_pt_regs") == 0) + return true; + if (__builtin_types_compatible_p(bpf_user_pt_regs_t, struct user_regs_struct) && + btf_is_struct(t) && strcmp(tname, "user_regs_struct") == 0) + return true; + break; + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: + /* allow u64* as ctx */ + if (btf_is_int(t) && t->size == 8) + return true; + break; + default: + break; + } + +out_warn: + pr_warn("prog '%s': subprog '%s' arg#%d is expected to be of `struct %s *` type\n", + prog->name, subprog_name, arg_idx, ctx_name); + return false; +} + +static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_program *prog) +{ + int fn_id, fn_proto_id, ret_type_id, orig_proto_id; + int i, err, arg_cnt, fn_name_off, linkage; + struct btf_type *fn_t, *fn_proto_t, *t; + struct btf_param *p; + + /* caller already validated FUNC -> FUNC_PROTO validity */ + fn_t = btf_type_by_id(btf, orig_fn_id); + fn_proto_t = btf_type_by_id(btf, fn_t->type); + + /* Note that each btf__add_xxx() operation invalidates + * all btf_type and string pointers, so we need to be + * very careful when cloning BTF types. BTF type + * pointers have to be always refetched. And to avoid + * problems with invalidated string pointers, we + * add empty strings initially, then just fix up + * name_off offsets in place. Offsets are stable for + * existing strings, so that works out. + */ + fn_name_off = fn_t->name_off; /* we are about to invalidate fn_t */ + linkage = btf_func_linkage(fn_t); + orig_proto_id = fn_t->type; /* original FUNC_PROTO ID */ + ret_type_id = fn_proto_t->type; /* fn_proto_t will be invalidated */ + arg_cnt = btf_vlen(fn_proto_t); + + /* clone FUNC_PROTO and its params */ + fn_proto_id = btf__add_func_proto(btf, ret_type_id); + if (fn_proto_id < 0) + return -EINVAL; + + for (i = 0; i < arg_cnt; i++) { + int name_off; + + /* copy original parameter data */ + t = btf_type_by_id(btf, orig_proto_id); + p = &btf_params(t)[i]; + name_off = p->name_off; + + err = btf__add_func_param(btf, "", p->type); + if (err) + return err; + + fn_proto_t = btf_type_by_id(btf, fn_proto_id); + p = &btf_params(fn_proto_t)[i]; + p->name_off = name_off; /* use remembered str offset */ + } + + /* clone FUNC now, btf__add_func() enforces non-empty name, so use + * entry program's name as a placeholder, which we replace immediately + * with original name_off + */ + fn_id = btf__add_func(btf, prog->name, linkage, fn_proto_id); + if (fn_id < 0) + return -EINVAL; + + fn_t = btf_type_by_id(btf, fn_id); + fn_t->name_off = fn_name_off; /* reuse original string */ + + return fn_id; +} + +/* Check if main program or global subprog's function prototype has `arg:ctx` + * argument tags, and, if necessary, substitute correct type to match what BPF + * verifier would expect, taking into account specific program type. This + * allows to support __arg_ctx tag transparently on old kernels that don't yet + * have a native support for it in the verifier, making user's life much + * easier. + */ +static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_program *prog) +{ + const char *ctx_name = NULL, *ctx_tag = "arg:ctx", *fn_name; + struct bpf_func_info_min *func_rec; + struct btf_type *fn_t, *fn_proto_t; + struct btf *btf = obj->btf; + const struct btf_type *t; + struct btf_param *p; + int ptr_id = 0, struct_id, tag_id, orig_fn_id; + int i, n, arg_idx, arg_cnt, err, rec_idx; + int *orig_ids; + + /* no .BTF.ext, no problem */ + if (!obj->btf_ext || !prog->func_info) + return 0; + + /* don't do any fix ups if kernel natively supports __arg_ctx */ + if (kernel_supports(obj, FEAT_ARG_CTX_TAG)) + return 0; + + /* some BPF program types just don't have named context structs, so + * this fallback mechanism doesn't work for them + */ + for (i = 0; i < ARRAY_SIZE(global_ctx_map); i++) { + if (global_ctx_map[i].prog_type != prog->type) + continue; + ctx_name = global_ctx_map[i].ctx_name; + break; + } + if (!ctx_name) + return 0; + + /* remember original func BTF IDs to detect if we already cloned them */ + orig_ids = calloc(prog->func_info_cnt, sizeof(*orig_ids)); + if (!orig_ids) + return -ENOMEM; + for (i = 0; i < prog->func_info_cnt; i++) { + func_rec = prog->func_info + prog->func_info_rec_size * i; + orig_ids[i] = func_rec->type_id; + } + + /* go through each DECL_TAG with "arg:ctx" and see if it points to one + * of our subprogs; if yes and subprog is global and needs adjustment, + * clone and adjust FUNC -> FUNC_PROTO combo + */ + for (i = 1, n = btf__type_cnt(btf); i < n; i++) { + /* only DECL_TAG with "arg:ctx" value are interesting */ + t = btf__type_by_id(btf, i); + if (!btf_is_decl_tag(t)) + continue; + if (strcmp(btf__str_by_offset(btf, t->name_off), ctx_tag) != 0) + continue; + + /* only global funcs need adjustment, if at all */ + orig_fn_id = t->type; + fn_t = btf_type_by_id(btf, orig_fn_id); + if (!btf_is_func(fn_t) || btf_func_linkage(fn_t) != BTF_FUNC_GLOBAL) + continue; + + /* sanity check FUNC -> FUNC_PROTO chain, just in case */ + fn_proto_t = btf_type_by_id(btf, fn_t->type); + if (!fn_proto_t || !btf_is_func_proto(fn_proto_t)) + continue; + + /* find corresponding func_info record */ + func_rec = NULL; + for (rec_idx = 0; rec_idx < prog->func_info_cnt; rec_idx++) { + if (orig_ids[rec_idx] == t->type) { + func_rec = prog->func_info + prog->func_info_rec_size * rec_idx; + break; + } + } + /* current main program doesn't call into this subprog */ + if (!func_rec) + continue; + + /* some more sanity checking of DECL_TAG */ + arg_cnt = btf_vlen(fn_proto_t); + arg_idx = btf_decl_tag(t)->component_idx; + if (arg_idx < 0 || arg_idx >= arg_cnt) + continue; + + /* check if we should fix up argument type */ + p = &btf_params(fn_proto_t)[arg_idx]; + fn_name = btf__str_by_offset(btf, fn_t->name_off) ?: "<anon>"; + if (!need_func_arg_type_fixup(btf, prog, fn_name, arg_idx, p->type, ctx_name)) + continue; + + /* clone fn/fn_proto, unless we already did it for another arg */ + if (func_rec->type_id == orig_fn_id) { + int fn_id; + + fn_id = clone_func_btf_info(btf, orig_fn_id, prog); + if (fn_id < 0) { + err = fn_id; + goto err_out; + } + + /* point func_info record to a cloned FUNC type */ + func_rec->type_id = fn_id; + } + + /* create PTR -> STRUCT type chain to mark PTR_TO_CTX argument; + * we do it just once per main BPF program, as all global + * funcs share the same program type, so need only PTR -> + * STRUCT type chain + */ + if (ptr_id == 0) { + struct_id = btf__add_struct(btf, ctx_name, 0); + ptr_id = btf__add_ptr(btf, struct_id); + if (ptr_id < 0 || struct_id < 0) { + err = -EINVAL; + goto err_out; + } + } + + /* for completeness, clone DECL_TAG and point it to cloned param */ + tag_id = btf__add_decl_tag(btf, ctx_tag, func_rec->type_id, arg_idx); + if (tag_id < 0) { + err = -EINVAL; + goto err_out; + } + + /* all the BTF manipulations invalidated pointers, refetch them */ + fn_t = btf_type_by_id(btf, func_rec->type_id); + fn_proto_t = btf_type_by_id(btf, fn_t->type); + + /* fix up type ID pointed to by param */ + p = &btf_params(fn_proto_t)[arg_idx]; + p->type = ptr_id; + } + + free(orig_ids); + return 0; +err_out: + free(orig_ids); + return err; +} + +static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { struct bpf_program *prog; size_t i, j; @@ -6417,8 +7370,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) if (obj->btf_ext) { err = bpf_object__relocate_core(obj, targ_btf_path); if (err) { - pr_warn("failed to perform CO-RE relocations: %d\n", - err); + pr_warn("failed to perform CO-RE relocations: %s\n", + errstr(err)); return err; } bpf_object__sort_relos(obj); @@ -6462,22 +7415,53 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) err = bpf_object__relocate_calls(obj, prog); if (err) { - pr_warn("prog '%s': failed to relocate calls: %d\n", - prog->name, err); + pr_warn("prog '%s': failed to relocate calls: %s\n", + prog->name, errstr(err)); return err; } + + err = bpf_prog_assign_exc_cb(obj, prog); + if (err) + return err; + /* Now, also append exception callback if it has not been done already. */ + if (prog->exception_cb_idx >= 0) { + struct bpf_program *subprog = &obj->programs[prog->exception_cb_idx]; + + /* Calling exception callback directly is disallowed, which the + * verifier will reject later. In case it was processed already, + * we can skip this step, otherwise for all other valid cases we + * have to append exception callback now. + */ + if (subprog->sub_insn_off == 0) { + err = bpf_object__append_subprog_code(obj, prog, subprog); + if (err) + return err; + err = bpf_object__reloc_code(obj, prog, subprog); + if (err) + return err; + } + } } - /* Process data relos for main programs */ for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; if (prog_is_subprog(obj, prog)) continue; if (!prog->autoload) continue; + + /* Process data relos for main programs */ err = bpf_object__relocate_data(obj, prog); if (err) { - pr_warn("prog '%s': failed to relocate data references: %d\n", - prog->name, err); + pr_warn("prog '%s': failed to relocate data references: %s\n", + prog->name, errstr(err)); + return err; + } + + /* Fix up .BTF.ext information, if necessary */ + err = bpf_program_fixup_func_info(obj, prog); + if (err) { + pr_warn("prog '%s': failed to perform .BTF.ext fix ups: %s\n", + prog->name, errstr(err)); return err; } } @@ -6642,12 +7626,12 @@ static int bpf_object__collect_relos(struct bpf_object *obj) data = sec_desc->data; idx = shdr->sh_info; - if (shdr->sh_type != SHT_REL) { + if (shdr->sh_type != SHT_REL || idx < 0 || idx >= obj->efile.sec_cnt) { pr_warn("internal error at %d\n", __LINE__); return -LIBBPF_ERRNO__INTERNAL; } - if (idx == obj->efile.st_ops_shndx) + if (obj->efile.secs[idx].sec_type == SEC_ST_OPS) err = bpf_object__collect_st_ops_relos(obj, shdr, data); else if (idx == obj->efile.btf_maps_shndx) err = bpf_object__collect_map_relos(obj, shdr, data); @@ -6728,6 +7712,16 @@ static int libbpf_prepare_prog_load(struct bpf_program *prog, if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS)) opts->prog_flags |= BPF_F_XDP_HAS_FRAGS; + /* special check for usdt to use uprobe_multi link */ + if ((def & SEC_USDT) && kernel_supports(prog->obj, FEAT_UPROBE_MULTI_LINK)) { + /* for BPF_TRACE_UPROBE_MULTI, user might want to query expected_attach_type + * in prog, and expected_attach_type we set in kernel is from opts, so we + * update both. + */ + prog->expected_attach_type = BPF_TRACE_UPROBE_MULTI; + opts->expected_attach_type = BPF_TRACE_UPROBE_MULTI; + } + if ((def & SEC_ATTACH_BTF) && !prog->attach_btf_id) { int btf_obj_fd = 0, btf_type_id = 0, err; const char *attach_name; @@ -6776,14 +7770,17 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog { LIBBPF_OPTS(bpf_prog_load_opts, load_attr); const char *prog_name = NULL; - char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; char *log_buf = NULL, *tmp; - int btf_fd, ret, err; bool own_log_buf = true; __u32 log_level = prog->log_level; + int ret, err; - if (prog->type == BPF_PROG_TYPE_UNSPEC) { + /* Be more helpful by rejecting programs that can't be validated early + * with more meaningful and actionable error message. + */ + switch (prog->type) { + case BPF_PROG_TYPE_UNSPEC: /* * The program type must be set. Most likely we couldn't find a proper * section definition at load time, and thus we didn't infer the type. @@ -6791,12 +7788,20 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog pr_warn("prog '%s': missing BPF prog type, check ELF section name '%s'\n", prog->name, prog->sec_name); return -EINVAL; + case BPF_PROG_TYPE_STRUCT_OPS: + if (prog->attach_btf_id == 0) { + pr_warn("prog '%s': SEC(\"struct_ops\") program isn't referenced anywhere, did you forget to use it?\n", + prog->name); + return -EINVAL; + } + break; + default: + break; } if (!insns || !insns_cnt) return -EINVAL; - load_attr.expected_attach_type = prog->expected_attach_type; if (kernel_supports(obj, FEAT_PROG_NAME)) prog_name = prog->name; load_attr.attach_prog_fd = prog->attach_prog_fd; @@ -6804,11 +7809,11 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog load_attr.attach_btf_id = prog->attach_btf_id; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; + load_attr.expected_attach_type = prog->expected_attach_type; /* specify func_info/line_info only if kernel supports them */ - btf_fd = bpf_object__btf_fd(obj); - if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) { - load_attr.prog_btf_fd = btf_fd; + if (obj->btf && btf__fd(obj->btf) >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) { + load_attr.prog_btf_fd = btf__fd(obj->btf); load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; load_attr.func_info_cnt = prog->func_info_cnt; @@ -6820,12 +7825,16 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog load_attr.prog_flags = prog->prog_flags; load_attr.fd_array = obj->fd_array; + load_attr.token_fd = obj->token_fd; + if (obj->token_fd) + load_attr.prog_flags |= BPF_F_TOKEN_FD; + /* adjust load_attr if sec_def provides custom preload callback */ if (prog->sec_def && prog->sec_def->prog_prepare_load_fn) { err = prog->sec_def->prog_prepare_load_fn(prog, &load_attr, prog->sec_def->cookie); if (err < 0) { - pr_warn("prog '%s': failed to prepare load attributes: %d\n", - prog->name, err); + pr_warn("prog '%s': failed to prepare load attributes: %s\n", + prog->name, errstr(err)); return err; } insns = prog->insns; @@ -6888,10 +7897,9 @@ retry_load: if (map->libbpf_type != LIBBPF_MAP_RODATA) continue; - if (bpf_prog_bind_map(ret, bpf_map__fd(map), NULL)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + if (bpf_prog_bind_map(ret, map->fd, NULL)) { pr_warn("prog '%s': failed to bind map '%s': %s\n", - prog->name, map->real_name, cp); + prog->name, map->real_name, errstr(errno)); /* Don't fail hard if can't bind rodata. */ } } @@ -6921,8 +7929,7 @@ retry_load: /* post-process verifier log to improve error descriptions */ fixup_verifier_log(prog, log_buf, log_buf_size); - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("prog '%s': BPF program load failed: %s\n", prog->name, cp); + pr_warn("prog '%s': BPF program load failed: %s\n", prog->name, errstr(errno)); pr_perm_msg(ret); if (own_log_buf && log_buf && log_buf[0] != '\0') { @@ -7030,13 +8037,13 @@ static void fixup_log_missing_map_load(struct bpf_program *prog, char *buf, size_t buf_sz, size_t log_sz, char *line1, char *line2, char *line3) { - /* Expected log for failed and not properly guarded CO-RE relocation: + /* Expected log for failed and not properly guarded map reference: * line1 -> 123: (85) call unknown#2001000345 * line2 -> invalid func unknown#2001000345 * line3 -> <anything else or end of buffer> * * "123" is the index of the instruction that was poisoned. - * "345" in "2001000345" are map index in obj->maps to fetch map name. + * "345" in "2001000345" is a map index in obj->maps to fetch map name. */ struct bpf_object *obj = prog->obj; const struct bpf_map *map; @@ -7046,7 +8053,7 @@ static void fixup_log_missing_map_load(struct bpf_program *prog, if (sscanf(line1, "%d: (%*d) call unknown#%d\n", &insn_idx, &map_idx) != 2) return; - map_idx -= MAP_LDIMM64_POISON_BASE; + map_idx -= POISON_LDIMM64_MAP_BASE; if (map_idx < 0 || map_idx >= obj->nr_maps) return; map = &obj->maps[map_idx]; @@ -7059,6 +8066,39 @@ static void fixup_log_missing_map_load(struct bpf_program *prog, patch_log(buf, buf_sz, log_sz, line1, line3 - line1, patch); } +static void fixup_log_missing_kfunc_call(struct bpf_program *prog, + char *buf, size_t buf_sz, size_t log_sz, + char *line1, char *line2, char *line3) +{ + /* Expected log for failed and not properly guarded kfunc call: + * line1 -> 123: (85) call unknown#2002000345 + * line2 -> invalid func unknown#2002000345 + * line3 -> <anything else or end of buffer> + * + * "123" is the index of the instruction that was poisoned. + * "345" in "2002000345" is an extern index in obj->externs to fetch kfunc name. + */ + struct bpf_object *obj = prog->obj; + const struct extern_desc *ext; + int insn_idx, ext_idx; + char patch[128]; + + if (sscanf(line1, "%d: (%*d) call unknown#%d\n", &insn_idx, &ext_idx) != 2) + return; + + ext_idx -= POISON_CALL_KFUNC_BASE; + if (ext_idx < 0 || ext_idx >= obj->nr_extern) + return; + ext = &obj->externs[ext_idx]; + + snprintf(patch, sizeof(patch), + "%d: <invalid kfunc call>\n" + "kfunc '%s' is referenced but wasn't resolved\n", + insn_idx, ext->name); + + patch_log(buf, buf_sz, log_sz, line1, line3 - line1, patch); +} + static void fixup_verifier_log(struct bpf_program *prog, char *buf, size_t buf_sz) { /* look for familiar error patterns in last N lines of the log */ @@ -7078,23 +8118,33 @@ static void fixup_verifier_log(struct bpf_program *prog, char *buf, size_t buf_s if (!cur_line) return; - /* failed CO-RE relocation case */ if (str_has_pfx(cur_line, "invalid func unknown#195896080\n")) { prev_line = find_prev_line(buf, cur_line); if (!prev_line) continue; + /* failed CO-RE relocation case */ fixup_log_failed_core_relo(prog, buf, buf_sz, log_sz, prev_line, cur_line, next_line); return; - } else if (str_has_pfx(cur_line, "invalid func unknown#"MAP_LDIMM64_POISON_PFX)) { + } else if (str_has_pfx(cur_line, "invalid func unknown#"POISON_LDIMM64_MAP_PFX)) { prev_line = find_prev_line(buf, cur_line); if (!prev_line) continue; + /* reference to uncreated BPF map */ fixup_log_missing_map_load(prog, buf, buf_sz, log_sz, prev_line, cur_line, next_line); return; + } else if (str_has_pfx(cur_line, "invalid func unknown#"POISON_CALL_KFUNC_PFX)) { + prev_line = find_prev_line(buf, cur_line); + if (!prev_line) + continue; + + /* reference to unresolved kfunc */ + fixup_log_missing_kfunc_call(prog, buf, buf_sz, log_sz, + prev_line, cur_line, next_line); + return; } } } @@ -7106,19 +8156,22 @@ static int bpf_program_record_relos(struct bpf_program *prog) for (i = 0; i < prog->nr_reloc; i++) { struct reloc_desc *relo = &prog->reloc_desc[i]; - struct extern_desc *ext = &obj->externs[relo->sym_off]; + struct extern_desc *ext = &obj->externs[relo->ext_idx]; + int kind; switch (relo->type) { - case RELO_EXTERN_VAR: + case RELO_EXTERN_LD64: if (ext->type != EXT_KSYM) continue; + kind = btf_is_var(btf__type_by_id(obj->btf, ext->btf_id)) ? + BTF_KIND_VAR : BTF_KIND_FUNC; bpf_gen__record_extern(obj->gen_loader, ext->name, ext->is_weak, !ext->ksym.type_id, - BTF_KIND_VAR, relo->insn_idx); + true, kind, relo->insn_idx); break; - case RELO_EXTERN_FUNC: + case RELO_EXTERN_CALL: bpf_gen__record_extern(obj->gen_loader, ext->name, - ext->is_weak, false, BTF_KIND_FUNC, + ext->is_weak, false, false, BTF_KIND_FUNC, relo->insn_idx); break; case RELO_CORE: { @@ -7148,13 +8201,6 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; - err = bpf_object__sanitize_prog(obj, prog); - if (err) - return err; - } - - for (i = 0; i < obj->nr_programs; i++) { - prog = &obj->programs[i]; if (prog_is_subprog(obj, prog)) continue; if (!prog->autoload) { @@ -7169,7 +8215,7 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) err = bpf_object_load_prog(obj, prog, prog->insns, prog->insns_cnt, obj->license, obj->kern_version, &prog->fd); if (err) { - pr_warn("prog '%s': failed to load: %d\n", prog->name, err); + pr_warn("prog '%s': failed to load: %s\n", prog->name, errstr(err)); return err; } } @@ -7178,6 +8224,21 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) return 0; } +static int bpf_object_prepare_progs(struct bpf_object *obj) +{ + struct bpf_program *prog; + size_t i; + int err; + + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + err = bpf_object__sanitize_prog(obj, prog); + if (err) + return err; + } + return 0; +} + static const struct bpf_sec_def *find_sec_def(const char *sec_name); static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts) @@ -7203,8 +8264,8 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object if (prog->sec_def->prog_setup_fn) { err = prog->sec_def->prog_setup_fn(prog, prog->sec_def->cookie); if (err < 0) { - pr_warn("prog '%s': failed to initialize: %d\n", - prog->name, err); + pr_warn("prog '%s': failed to initialize: %s\n", + prog->name, errstr(err)); return err; } } @@ -7214,16 +8275,19 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object } static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz, + const char *obj_name, const struct bpf_object_open_opts *opts) { - const char *obj_name, *kconfig, *btf_tmp_path; + const char *kconfig, *btf_tmp_path, *token_path; struct bpf_object *obj; - char tmp_name[64]; int err; char *log_buf; size_t log_size; __u32 log_level; + if (obj_buf && !obj_name) + return ERR_PTR(-EINVAL); + if (elf_version(EV_CURRENT) == EV_NONE) { pr_warn("failed to init libelf for %s\n", path ? : "(mem buf)"); @@ -7233,16 +8297,12 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, if (!OPTS_VALID(opts, bpf_object_open_opts)) return ERR_PTR(-EINVAL); - obj_name = OPTS_GET(opts, object_name, NULL); + obj_name = OPTS_GET(opts, object_name, NULL) ?: obj_name; if (obj_buf) { - if (!obj_name) { - snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx", - (unsigned long)obj_buf, - (unsigned long)obj_buf_sz); - obj_name = tmp_name; - } path = obj_name; pr_debug("loading object '%s' from buffer\n", obj_name); + } else { + pr_debug("loading object from %s\n", path); } log_buf = OPTS_GET(opts, kernel_log_buf, NULL); @@ -7253,6 +8313,16 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, if (log_size && !log_buf) return ERR_PTR(-EINVAL); + token_path = OPTS_GET(opts, bpf_token_path, NULL); + /* if user didn't specify bpf_token_path explicitly, check if + * LIBBPF_BPF_TOKEN_PATH envvar was set and treat it as bpf_token_path + * option + */ + if (!token_path) + token_path = getenv("LIBBPF_BPF_TOKEN_PATH"); + if (token_path && strlen(token_path) >= PATH_MAX) + return ERR_PTR(-ENAMETOOLONG); + obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); if (IS_ERR(obj)) return obj; @@ -7261,6 +8331,14 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, obj->log_size = log_size; obj->log_level = log_level; + if (token_path) { + obj->token_path = strdup(token_path); + if (!obj->token_path) { + err = -ENOMEM; + goto out; + } + } + btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL); if (btf_tmp_path) { if (strlen(btf_tmp_path) >= PATH_MAX) { @@ -7284,7 +8362,6 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, } err = bpf_object__elf_init(obj); - err = err ? : bpf_object__check_endianness(obj); err = err ? : bpf_object__elf_collect(obj); err = err ? : bpf_object__collect_externs(obj); err = err ? : bpf_object_fixup_btf(obj); @@ -7308,9 +8385,7 @@ bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) if (!path) return libbpf_err_ptr(-EINVAL); - pr_debug("loading %s\n", path); - - return libbpf_ptr(bpf_object_open(path, NULL, 0, opts)); + return libbpf_ptr(bpf_object_open(path, NULL, 0, NULL, opts)); } struct bpf_object *bpf_object__open(const char *path) @@ -7322,10 +8397,15 @@ struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts) { + char tmp_name[64]; + if (!obj_buf || obj_buf_sz == 0) return libbpf_err_ptr(-EINVAL); - return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, opts)); + /* create a (quite useless) default "name" for this memory buffer object */ + snprintf(tmp_name, sizeof(tmp_name), "%lx-%zx", (unsigned long)obj_buf, obj_buf_sz); + + return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, tmp_name, opts)); } static int bpf_object_unload(struct bpf_object *obj) @@ -7355,23 +8435,26 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) if (!bpf_map__is_internal(m)) continue; if (!kernel_supports(obj, FEAT_ARRAY_MMAP)) - m->def.map_flags ^= BPF_F_MMAPABLE; + m->def.map_flags &= ~BPF_F_MMAPABLE; } return 0; } -int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) +typedef int (*kallsyms_cb_t)(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx); + +static int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *ctx) { char sym_type, sym_name[500]; unsigned long long sym_addr; int ret, err = 0; FILE *f; - f = fopen("/proc/kallsyms", "r"); + f = fopen("/proc/kallsyms", "re"); if (!f) { err = -errno; - pr_warn("failed to open /proc/kallsyms: %d\n", err); + pr_warn("failed to open /proc/kallsyms: %s\n", errstr(err)); return err; } @@ -7401,8 +8484,13 @@ static int kallsyms_cb(unsigned long long sym_addr, char sym_type, struct bpf_object *obj = ctx; const struct btf_type *t; struct extern_desc *ext; + char *res; - ext = find_extern_by_name(obj, sym_name); + res = strstr(sym_name, ".llvm."); + if (sym_type == 'd' && res) + ext = find_extern_by_name_with_len(obj, sym_name, res - sym_name); + else + ext = find_extern_by_name(obj, sym_name); if (!ext || ext->type != EXT_KSYM) return 0; @@ -7526,7 +8614,8 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, local_func_proto_id = ext->ksym.type_id; - kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC, &kern_btf, &mod_btf); + kfunc_id = find_ksym_btf_id(obj, ext->essent_name ?: ext->name, BTF_KIND_FUNC, &kern_btf, + &mod_btf); if (kfunc_id < 0) { if (kfunc_id == -ESRCH && ext->is_weak) return 0; @@ -7541,8 +8630,12 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, ret = bpf_core_types_are_compat(obj->btf, local_func_proto_id, kern_btf, kfunc_proto_id); if (ret <= 0) { - pr_warn("extern (func ksym) '%s': func_proto [%d] incompatible with kernel [%d]\n", - ext->name, local_func_proto_id, kfunc_proto_id); + if (ext->is_weak) + return 0; + + pr_warn("extern (func ksym) '%s': func_proto [%d] incompatible with %s [%d]\n", + ext->name, local_func_proto_id, + mod_btf ? mod_btf->name : "vmlinux", kfunc_proto_id); return -EINVAL; } @@ -7570,8 +8663,14 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj, ext->is_set = true; ext->ksym.kernel_btf_id = kfunc_id; ext->ksym.btf_fd_idx = mod_btf ? mod_btf->fd_array_idx : 0; - pr_debug("extern (func ksym) '%s': resolved to kernel [%d]\n", - ext->name, kfunc_id); + /* Also set kernel_btf_obj_fd to make sure that bpf_object__relocate_data() + * populates FD into ld_imm64 insn when it's used to point to kfunc. + * {kernel_btf_id, btf_fd_idx} -> fixup bpf_call. + * {kernel_btf_id, kernel_btf_obj_fd} -> fixup ld_imm64. + */ + ext->ksym.kernel_btf_obj_fd = mod_btf ? mod_btf->fd : 0; + pr_debug("extern (func ksym) '%s': resolved to %s [%d]\n", + ext->name, mod_btf ? mod_btf->name : "vmlinux", kfunc_id); return 0; } @@ -7714,42 +8813,62 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, return 0; } -static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path) +static void bpf_map_prepare_vdata(const struct bpf_map *map) { - int err, i; + const struct btf_type *type; + struct bpf_struct_ops *st_ops; + __u32 i; - if (!obj) - return libbpf_err(-EINVAL); + st_ops = map->st_ops; + type = btf__type_by_id(map->obj->btf, st_ops->type_id); + for (i = 0; i < btf_vlen(type); i++) { + struct bpf_program *prog = st_ops->progs[i]; + void *kern_data; + int prog_fd; - if (obj->loaded) { - pr_warn("object '%s': load can't be attempted twice\n", obj->name); - return libbpf_err(-EINVAL); + if (!prog) + continue; + + prog_fd = bpf_program__fd(prog); + kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i]; + *(unsigned long *)kern_data = prog_fd; } +} - if (obj->gen_loader) - bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); +static int bpf_object_prepare_struct_ops(struct bpf_object *obj) +{ + struct bpf_map *map; + int i; - err = bpf_object__probe_loading(obj); - err = err ? : bpf_object__load_vmlinux_btf(obj, false); - err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); - err = err ? : bpf_object__sanitize_and_load_btf(obj); - 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 ? : target_btf_path); - err = err ? : bpf_object__load_progs(obj, extra_log_level); - err = err ? : bpf_object_init_prog_arrays(obj); + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; - if (obj->gen_loader) { - /* reset FDs */ - if (obj->btf) - btf__set_fd(obj->btf, -1); - for (i = 0; i < obj->nr_maps; i++) - obj->maps[i].fd = -1; - if (!err) - err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps); + if (!bpf_map__is_struct_ops(map)) + continue; + + if (!map->autocreate) + continue; + + bpf_map_prepare_vdata(map); } + return 0; +} + +static void bpf_object_unpin(struct bpf_object *obj) +{ + int i; + + /* unpin any maps that were auto-pinned during load */ + for (i = 0; i < obj->nr_maps; i++) + if (obj->maps[i].pinned && !obj->maps[i].reused) + bpf_map__unpin(&obj->maps[i], NULL); +} + +static void bpf_object_post_load_cleanup(struct bpf_object *obj) +{ + int i; + /* clean up fd_array */ zfree(&obj->fd_array); @@ -7759,27 +8878,101 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch btf__free(obj->btf_modules[i].btf); free(obj->btf_modules[i].name); } - free(obj->btf_modules); + obj->btf_module_cnt = 0; + zfree(&obj->btf_modules); /* clean up vmlinux BTF */ btf__free(obj->btf_vmlinux); obj->btf_vmlinux = NULL; +} - obj->loaded = true; /* doesn't matter if successfully or not */ +static int bpf_object_prepare(struct bpf_object *obj, const char *target_btf_path) +{ + int err; - if (err) - goto out; + if (obj->state >= OBJ_PREPARED) { + pr_warn("object '%s': prepare loading can't be attempted twice\n", obj->name); + return -EINVAL; + } + + err = bpf_object_prepare_token(obj); + err = err ? : bpf_object__probe_loading(obj); + err = err ? : bpf_object__load_vmlinux_btf(obj, false); + err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); + err = err ? : bpf_object__sanitize_maps(obj); + err = err ? : bpf_object__init_kern_struct_ops_maps(obj); + err = err ? : bpf_object_adjust_struct_ops_autoload(obj); + err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path); + err = err ? : bpf_object__sanitize_and_load_btf(obj); + err = err ? : bpf_object__create_maps(obj); + err = err ? : bpf_object_prepare_progs(obj); + if (err) { + bpf_object_unpin(obj); + bpf_object_unload(obj); + obj->state = OBJ_LOADED; + return err; + } + + obj->state = OBJ_PREPARED; return 0; -out: - /* unpin any maps that were auto-pinned during load */ - for (i = 0; i < obj->nr_maps; i++) - if (obj->maps[i].pinned && !obj->maps[i].reused) - bpf_map__unpin(&obj->maps[i], NULL); +} - bpf_object_unload(obj); - pr_warn("failed to load object '%s'\n", obj->path); - return libbpf_err(err); +static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path) +{ + int err; + + if (!obj) + return libbpf_err(-EINVAL); + + if (obj->state >= OBJ_LOADED) { + pr_warn("object '%s': load can't be attempted twice\n", obj->name); + return libbpf_err(-EINVAL); + } + + /* Disallow kernel loading programs of non-native endianness but + * permit cross-endian creation of "light skeleton". + */ + if (obj->gen_loader) { + bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); + } else if (!is_native_endianness(obj)) { + pr_warn("object '%s': loading non-native endianness is unsupported\n", obj->name); + return libbpf_err(-LIBBPF_ERRNO__ENDIAN); + } + + if (obj->state < OBJ_PREPARED) { + err = bpf_object_prepare(obj, target_btf_path); + if (err) + return libbpf_err(err); + } + err = bpf_object__load_progs(obj, extra_log_level); + err = err ? : bpf_object_init_prog_arrays(obj); + err = err ? : bpf_object_prepare_struct_ops(obj); + + if (obj->gen_loader) { + /* reset FDs */ + if (obj->btf) + btf__set_fd(obj->btf, -1); + if (!err) + err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps); + } + + bpf_object_post_load_cleanup(obj); + obj->state = OBJ_LOADED; /* doesn't matter if successfully or not */ + + if (err) { + bpf_object_unpin(obj); + bpf_object_unload(obj); + pr_warn("failed to load object '%s'\n", obj->path); + return libbpf_err(err); + } + + return 0; +} + +int bpf_object__prepare(struct bpf_object *obj) +{ + return libbpf_err(bpf_object_prepare(obj, NULL)); } int bpf_object__load(struct bpf_object *obj) @@ -7789,7 +8982,6 @@ int bpf_object__load(struct bpf_object *obj) static int make_parent_dir(const char *path) { - char *cp, errmsg[STRERR_BUFSIZE]; char *dname, *dir; int err = 0; @@ -7803,15 +8995,13 @@ static int make_parent_dir(const char *path) free(dname); if (err) { - cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); - pr_warn("failed to mkdir %s: %s\n", path, cp); + pr_warn("failed to mkdir %s: %s\n", path, errstr(err)); } return err; } static int check_path(const char *path) { - char *cp, errmsg[STRERR_BUFSIZE]; struct statfs st_fs; char *dname, *dir; int err = 0; @@ -7825,8 +9015,7 @@ static int check_path(const char *path) dir = dirname(dname); if (statfs(dir, &st_fs)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("failed to statfs %s: %s\n", dir, cp); + pr_warn("failed to statfs %s: %s\n", dir, errstr(errno)); err = -errno; } free(dname); @@ -7841,7 +9030,6 @@ static int check_path(const char *path) int bpf_program__pin(struct bpf_program *prog, const char *path) { - char *cp, errmsg[STRERR_BUFSIZE]; int err; if (prog->fd < 0) { @@ -7859,8 +9047,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path) if (bpf_obj_pin(prog->fd, path)) { err = -errno; - cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warn("prog '%s': failed to pin at '%s': %s\n", prog->name, path, cp); + pr_warn("prog '%s': failed to pin at '%s': %s\n", prog->name, path, errstr(err)); return libbpf_err(err); } @@ -7891,7 +9078,6 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path) int bpf_map__pin(struct bpf_map *map, const char *path) { - char *cp, errmsg[STRERR_BUFSIZE]; int err; if (map == NULL) { @@ -7899,6 +9085,11 @@ int bpf_map__pin(struct bpf_map *map, const char *path) return libbpf_err(-EINVAL); } + if (map->fd < 0) { + pr_warn("map '%s': can't pin BPF map without FD (was it created?)\n", map->name); + return libbpf_err(-EINVAL); + } + if (map->pin_path) { if (path && strcmp(path, map->pin_path)) { pr_warn("map '%s' already has pin path '%s' different from '%s'\n", @@ -7945,8 +9136,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path) return 0; out_err: - cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); - pr_warn("failed to pin map: %s\n", cp); + pr_warn("failed to pin map: %s\n", errstr(err)); return libbpf_err(err); } @@ -8032,7 +9222,7 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) if (!obj) return libbpf_err(-ENOENT); - if (!obj->loaded) { + if (obj->state < OBJ_PREPARED) { pr_warn("object not yet loaded; load it first\n"); return libbpf_err(-ENOENT); } @@ -8111,7 +9301,7 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) if (!obj) return libbpf_err(-ENOENT); - if (!obj->loaded) { + if (obj->state < OBJ_LOADED) { pr_warn("object not yet loaded; load it first\n"); return libbpf_err(-ENOENT); } @@ -8179,6 +9369,21 @@ int bpf_object__pin(struct bpf_object *obj, const char *path) return 0; } +int bpf_object__unpin(struct bpf_object *obj, const char *path) +{ + int err; + + err = bpf_object__unpin_programs(obj, path); + if (err) + return libbpf_err(err); + + err = bpf_object__unpin_maps(obj, path); + if (err) + return libbpf_err(err); + + return 0; +} + static void bpf_map__destroy(struct bpf_map *map) { if (map->inner_map) { @@ -8189,10 +9394,9 @@ static void bpf_map__destroy(struct bpf_map *map) zfree(&map->init_slots); map->init_slots_sz = 0; - if (map->mmaped) { + if (map->mmaped && map->mmaped != map->obj->arena_data) munmap(map->mmaped, bpf_map_mmap_sz(map)); - map->mmaped = NULL; - } + map->mmaped = NULL; if (map->st_ops) { zfree(&map->st_ops->data); @@ -8216,6 +9420,13 @@ void bpf_object__close(struct bpf_object *obj) if (IS_ERR_OR_NULL(obj)) return; + /* + * if user called bpf_object__prepare() without ever getting to + * bpf_object__load(), we need to clean up stuff that is normally + * cleaned up at the end of loading step + */ + bpf_object_post_load_cleanup(obj); + usdt_manager_free(obj->usdt_man); obj->usdt_man = NULL; @@ -8223,6 +9434,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object_unload(obj); btf__free(obj->btf); + btf__free(obj->btf_vmlinux); btf_ext__free(obj->btf_ext); for (i = 0; i < obj->nr_maps; i++) @@ -8230,6 +9442,12 @@ void bpf_object__close(struct bpf_object *obj) zfree(&obj->btf_custom_path); zfree(&obj->kconfig); + + for (i = 0; i < obj->nr_extern; i++) { + zfree(&obj->externs[i].name); + zfree(&obj->externs[i].essent_name); + } + zfree(&obj->externs); obj->nr_extern = 0; @@ -8242,6 +9460,20 @@ void bpf_object__close(struct bpf_object *obj) } zfree(&obj->programs); + zfree(&obj->feat_cache); + zfree(&obj->token_path); + if (obj->token_fd > 0) + close(obj->token_fd); + + zfree(&obj->arena_data); + + zfree(&obj->jumptables_data); + obj->jumptables_data_sz = 0; + + for (i = 0; i < obj->jumptable_map_cnt; i++) + close(obj->jumptable_maps[i].fd); + zfree(&obj->jumptable_maps); + free(obj); } @@ -8255,6 +9487,11 @@ unsigned int bpf_object__kversion(const struct bpf_object *obj) return obj ? obj->kern_version : 0; } +int bpf_object__token_fd(const struct bpf_object *obj) +{ + return obj->token_fd ?: -1; +} + struct btf *bpf_object__btf(const struct bpf_object *obj) { return obj ? obj->btf : NULL; @@ -8267,7 +9504,7 @@ int bpf_object__btf_fd(const struct bpf_object *obj) int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version) { - if (obj->loaded) + if (obj->state >= OBJ_LOADED) return libbpf_err(-EINVAL); obj->kern_version = kern_version; @@ -8280,13 +9517,14 @@ int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts) struct bpf_gen *gen; if (!opts) - return -EFAULT; + return libbpf_err(-EFAULT); if (!OPTS_VALID(opts, gen_loader_opts)) - return -EINVAL; - gen = calloc(sizeof(*gen), 1); + return libbpf_err(-EINVAL); + gen = calloc(1, sizeof(*gen)); if (!gen) - return -ENOMEM; + return libbpf_err(-ENOMEM); gen->opts = opts; + gen->swapped_endian = !is_native_endianness(obj); obj->gen_loader = gen; return 0; } @@ -8363,7 +9601,7 @@ bool bpf_program__autoload(const struct bpf_program *prog) int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EINVAL); prog->autoload = autoload; @@ -8395,13 +9633,14 @@ int bpf_program__set_insns(struct bpf_program *prog, { struct bpf_insn *insns; - if (prog->obj->loaded) - return -EBUSY; + if (prog->obj->state >= OBJ_LOADED) + return libbpf_err(-EBUSY); insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns)); - if (!insns) { + /* NULL is a valid return from reallocarray if the new count is zero */ + if (!insns && new_insn_cnt) { pr_warn("prog '%s': failed to realloc prog code\n", prog->name); - return -ENOMEM; + return libbpf_err(-ENOMEM); } memcpy(insns, new_insns, new_insn_cnt * sizeof(*insns)); @@ -8429,12 +9668,31 @@ enum bpf_prog_type bpf_program__type(const struct bpf_program *prog) return prog->type; } +static size_t custom_sec_def_cnt; +static struct bpf_sec_def *custom_sec_defs; +static struct bpf_sec_def custom_fallback_def; +static bool has_custom_fallback_def; +static int last_custom_sec_def_handler_id; + int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); + /* if type is not changed, do nothing */ + if (prog->type == type) + return 0; + prog->type = type; + + /* If a program type was changed, we need to reset associated SEC() + * handler, as it will be invalid now. The only exception is a generic + * fallback handler, which by definition is program type-agnostic and + * is a catch-all custom handler, optionally set by the application, + * so should be able to handle any type of BPF program. + */ + if (prog->sec_def != &custom_fallback_def) + prog->sec_def = NULL; return 0; } @@ -8449,7 +9707,7 @@ enum bpf_attach_type bpf_program__expected_attach_type(const struct bpf_program int bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); prog->expected_attach_type = type; @@ -8463,7 +9721,7 @@ __u32 bpf_program__flags(const struct bpf_program *prog) int bpf_program__set_flags(struct bpf_program *prog, __u32 flags) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); prog->prog_flags = flags; @@ -8477,7 +9735,7 @@ __u32 bpf_program__log_level(const struct bpf_program *prog) int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level) { - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EBUSY); prog->log_level = log_level; @@ -8493,17 +9751,41 @@ const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_siz int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size) { if (log_size && !log_buf) - return -EINVAL; + return libbpf_err(-EINVAL); if (prog->log_size > UINT_MAX) - return -EINVAL; - if (prog->obj->loaded) - return -EBUSY; + return libbpf_err(-EINVAL); + if (prog->obj->state >= OBJ_LOADED) + return libbpf_err(-EBUSY); prog->log_buf = log_buf; prog->log_size = log_size; return 0; } +struct bpf_func_info *bpf_program__func_info(const struct bpf_program *prog) +{ + if (prog->func_info_rec_size != sizeof(struct bpf_func_info)) + return libbpf_err_ptr(-EOPNOTSUPP); + return prog->func_info; +} + +__u32 bpf_program__func_info_cnt(const struct bpf_program *prog) +{ + return prog->func_info_cnt; +} + +struct bpf_line_info *bpf_program__line_info(const struct bpf_program *prog) +{ + if (prog->line_info_rec_size != sizeof(struct bpf_line_info)) + return libbpf_err_ptr(-EOPNOTSUPP); + return prog->line_info; +} + +__u32 bpf_program__line_info_cnt(const struct bpf_program *prog) +{ + return prog->line_info_cnt; +} + #define SEC_DEF(sec_pfx, ptype, atype, flags, ...) { \ .sec = (char *)sec_pfx, \ .prog_type = BPF_PROG_TYPE_##ptype, \ @@ -8521,6 +9803,8 @@ static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_lin static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_trace(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_kprobe_session(const struct bpf_program *prog, long cookie, struct bpf_link **link); +static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_link **link); static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_link **link); @@ -8536,12 +9820,26 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("uretprobe.s+", KPROBE, 0, SEC_SLEEPABLE, attach_uprobe), SEC_DEF("kprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), SEC_DEF("kretprobe.multi+", KPROBE, BPF_TRACE_KPROBE_MULTI, SEC_NONE, attach_kprobe_multi), + SEC_DEF("kprobe.session+", KPROBE, BPF_TRACE_KPROBE_SESSION, SEC_NONE, attach_kprobe_session), + SEC_DEF("uprobe.multi+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi), + SEC_DEF("uretprobe.multi+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_NONE, attach_uprobe_multi), + SEC_DEF("uprobe.session+", KPROBE, BPF_TRACE_UPROBE_SESSION, SEC_NONE, attach_uprobe_multi), + SEC_DEF("uprobe.multi.s+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi), + SEC_DEF("uretprobe.multi.s+", KPROBE, BPF_TRACE_UPROBE_MULTI, SEC_SLEEPABLE, attach_uprobe_multi), + SEC_DEF("uprobe.session.s+", KPROBE, BPF_TRACE_UPROBE_SESSION, SEC_SLEEPABLE, attach_uprobe_multi), SEC_DEF("ksyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), SEC_DEF("kretsyscall+", KPROBE, 0, SEC_NONE, attach_ksyscall), - SEC_DEF("usdt+", KPROBE, 0, SEC_NONE, attach_usdt), - SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), - SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), + SEC_DEF("usdt+", KPROBE, 0, SEC_USDT, attach_usdt), + SEC_DEF("usdt.s+", KPROBE, 0, SEC_USDT | SEC_SLEEPABLE, attach_usdt), + SEC_DEF("tc/ingress", SCHED_CLS, BPF_TCX_INGRESS, SEC_NONE), /* alias for tcx */ + SEC_DEF("tc/egress", SCHED_CLS, BPF_TCX_EGRESS, SEC_NONE), /* alias for tcx */ + SEC_DEF("tcx/ingress", SCHED_CLS, BPF_TCX_INGRESS, SEC_NONE), + SEC_DEF("tcx/egress", SCHED_CLS, BPF_TCX_EGRESS, SEC_NONE), + SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */ + SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */ + SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), /* deprecated / legacy, use tcx */ + SEC_DEF("netkit/primary", SCHED_CLS, BPF_NETKIT_PRIMARY, SEC_NONE), + SEC_DEF("netkit/peer", SCHED_CLS, BPF_NETKIT_PEER, SEC_NONE), SEC_DEF("tracepoint+", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("tp+", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("raw_tracepoint+", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), @@ -8576,6 +9874,7 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT), SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT), SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT), + SEC_DEF("sk_skb/verdict", SK_SKB, BPF_SK_SKB_VERDICT, SEC_ATTACHABLE_OPT), SEC_DEF("sk_skb", SK_SKB, 0, SEC_NONE), SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT), SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT), @@ -8592,29 +9891,29 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE), SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE), SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE), + SEC_DEF("cgroup/connect_unix", CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_CONNECT, SEC_ATTACHABLE), SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE), SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/sendmsg_unix", CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_SENDMSG, SEC_ATTACHABLE), SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE), SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE), + SEC_DEF("cgroup/recvmsg_unix", CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_RECVMSG, SEC_ATTACHABLE), SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE), SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getpeername_unix", CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_GETPEERNAME, SEC_ATTACHABLE), SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE), SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE), + SEC_DEF("cgroup/getsockname_unix", CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_GETSOCKNAME, SEC_ATTACHABLE), SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE), SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE), SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE), SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT), SEC_DEF("struct_ops+", STRUCT_OPS, 0, SEC_NONE), + SEC_DEF("struct_ops.s+", STRUCT_OPS, 0, SEC_SLEEPABLE), SEC_DEF("sk_lookup", SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE), + SEC_DEF("netfilter", NETFILTER, BPF_NETFILTER, SEC_NONE), }; -static size_t custom_sec_def_cnt; -static struct bpf_sec_def *custom_sec_defs; -static struct bpf_sec_def custom_fallback_def; -static bool has_custom_fallback_def; - -static int last_custom_sec_def_handler_id; - int libbpf_register_prog_handler(const char *sec, enum bpf_prog_type prog_type, enum bpf_attach_type exp_attach_type, @@ -8694,7 +9993,11 @@ int libbpf_unregister_prog_handler(int handler_id) /* try to shrink the array, but it's ok if we couldn't */ sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs)); - if (sec_defs) + /* if new count is zero, reallocarray can return a valid NULL result; + * in this case the previous pointer will be freed, so we *have to* + * reassign old pointer to the new value (even if it's NULL) + */ + if (sec_defs || custom_sec_def_cnt == 0) custom_sec_defs = sec_defs; return 0; @@ -8847,6 +10150,7 @@ const char *libbpf_bpf_prog_type_str(enum bpf_prog_type t) } static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, + int sec_idx, size_t offset) { struct bpf_map *map; @@ -8856,7 +10160,8 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, map = &obj->maps[i]; if (!bpf_map__is_struct_ops(map)) continue; - if (map->sec_offset <= offset && + if (map->sec_idx == sec_idx && + map->sec_offset <= offset && offset - map->sec_offset < map->def.value_size) return map; } @@ -8864,10 +10169,13 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, return NULL; } -/* Collect the reloc from ELF and populate the st_ops->progs[] */ +/* Collect the reloc from ELF, populate the st_ops->progs[], and update + * st_ops->data for shadow type. + */ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Data *data) { + const struct btf_type *type; const struct btf_member *member; struct bpf_struct_ops *st_ops; struct bpf_program *prog; @@ -8898,7 +10206,7 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, } name = elf_sym_str(obj, sym->st_name) ?: "<?>"; - map = find_struct_ops_map_by_offset(obj, rel->r_offset); + map = find_struct_ops_map_by_offset(obj, shdr->sh_info, rel->r_offset); if (!map) { pr_warn("struct_ops reloc: cannot find map at rel->r_offset %zu\n", (size_t)rel->r_offset); @@ -8927,13 +10235,14 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, } insn_idx = sym->st_value / BPF_INSN_SZ; - member = find_member_by_offset(st_ops->type, moff * 8); + type = btf__type_by_id(btf, st_ops->type_id); + member = find_member_by_offset(type, moff * 8); if (!member) { pr_warn("struct_ops reloc %s: cannot find member at moff %u\n", map->name, moff); return -EINVAL; } - member_idx = member - btf_members(st_ops->type); + member_idx = member - btf_members(type); name = btf__name_by_offset(btf, member->name_off); if (!resolve_func_ptr(btf, member->type, NULL)) { @@ -8956,27 +10265,15 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, return -EINVAL; } - /* if we haven't yet processed this BPF program, record proper - * attach_btf_id and member_idx - */ - if (!prog->attach_btf_id) { - prog->attach_btf_id = st_ops->type_id; - prog->expected_attach_type = member_idx; - } + st_ops->progs[member_idx] = prog; - /* struct_ops BPF prog can be re-used between multiple - * .struct_ops as long as it's the same struct_ops struct - * definition and the same function pointer field + /* st_ops->data will be exposed to users, being returned by + * bpf_map__initial_value() as a pointer to the shadow + * type. All function pointers in the original struct type + * should be converted to a pointer to struct bpf_program + * in the shadow type. */ - if (prog->attach_btf_id != st_ops->type_id || - prog->expected_attach_type != member_idx) { - pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", - map->name, prog->name, prog->sec_name, prog->type, - prog->attach_btf_id, prog->expected_attach_type, name); - return -EINVAL; - } - - st_ops->progs[member_idx] = prog; + *((struct bpf_program **)(st_ops->data + moff)) = prog; } return 0; @@ -9058,7 +10355,7 @@ int libbpf_find_vmlinux_btf_id(const char *name, return libbpf_err(err); } -static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) +static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd, int token_fd) { struct bpf_prog_info info; __u32 info_len = sizeof(info); @@ -9066,10 +10363,10 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) int err; memset(&info, 0, info_len); - err = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len); + err = bpf_prog_get_info_by_fd(attach_prog_fd, &info, &info_len); if (err) { - pr_warn("failed bpf_obj_get_info_by_fd for FD %d: %d\n", - attach_prog_fd, err); + pr_warn("failed bpf_prog_get_info_by_fd for FD %d: %s\n", + attach_prog_fd, errstr(err)); return err; } @@ -9078,10 +10375,10 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) pr_warn("The target program doesn't have BTF\n"); goto out; } - btf = btf__load_from_kernel_by_id(info.btf_id); + btf = btf_load_from_kernel(info.btf_id, NULL, token_fd); err = libbpf_get_error(btf); if (err) { - pr_warn("Failed to get BTF %d of the program: %d\n", info.btf_id, err); + pr_warn("Failed to get BTF %d of the program: %s\n", info.btf_id, errstr(err)); goto out; } err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); @@ -9098,16 +10395,28 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, enum bpf_attach_type attach_type, int *btf_obj_fd, int *btf_type_id) { - int ret, i; + int ret, i, mod_len = 0; + const char *fn_name, *mod_name = NULL; - ret = find_attach_btf_id(obj->btf_vmlinux, attach_name, attach_type); - if (ret > 0) { - *btf_obj_fd = 0; /* vmlinux BTF */ - *btf_type_id = ret; - return 0; + fn_name = strchr(attach_name, ':'); + if (fn_name) { + mod_name = attach_name; + mod_len = fn_name - mod_name; + fn_name++; + } + + if (!mod_name || strncmp(mod_name, "vmlinux", mod_len) == 0) { + ret = find_attach_btf_id(obj->btf_vmlinux, + mod_name ? fn_name : attach_name, + attach_type); + if (ret > 0) { + *btf_obj_fd = 0; /* vmlinux BTF */ + *btf_type_id = ret; + return 0; + } + if (ret != -ENOENT) + return ret; } - if (ret != -ENOENT) - return ret; ret = load_module_btfs(obj); if (ret) @@ -9116,7 +10425,12 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, for (i = 0; i < obj->btf_module_cnt; i++) { const struct module_btf *mod = &obj->btf_modules[i]; - ret = find_attach_btf_id(mod->btf, attach_name, attach_type); + if (mod_name && strncmp(mod->name, mod_name, mod_len) != 0) + continue; + + ret = find_attach_btf_id(mod->btf, + mod_name ? fn_name : attach_name, + attach_type); if (ret > 0) { *btf_obj_fd = mod->fd; *btf_type_id = ret; @@ -9144,10 +10458,10 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac pr_warn("prog '%s': attach program FD is not set\n", prog->name); return -EINVAL; } - err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd); + err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd, prog->obj->token_fd); if (err < 0) { - pr_warn("prog '%s': failed to find BPF program (FD %d) BTF ID for '%s': %d\n", - prog->name, attach_prog_fd, attach_name, err); + pr_warn("prog '%s': failed to find BPF program (FD %d) BTF ID for '%s': %s\n", + prog->name, attach_prog_fd, attach_name, errstr(err)); return err; } *btf_obj_fd = 0; @@ -9161,11 +10475,13 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attac *btf_obj_fd = 0; *btf_type_id = 1; } else { - err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); + err = find_kernel_btf_id(prog->obj, attach_name, + attach_type, btf_obj_fd, + btf_type_id); } if (err) { - pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %d\n", - prog->name, attach_name, err); + pr_warn("prog '%s': failed to find kernel BTF type ID of '%s': %s\n", + prog->name, attach_name, errstr(err)); return err; } return 0; @@ -9203,7 +10519,11 @@ int libbpf_attach_type_by_name(const char *name, int bpf_map__fd(const struct bpf_map *map) { - return map ? map->fd : libbpf_err(-EINVAL); + if (!map) + return libbpf_err(-EINVAL); + if (!map_is_created(map)) + return -1; + return map->fd; } static bool map_uses_real_name(const struct bpf_map *map) @@ -9239,7 +10559,7 @@ enum bpf_map_type bpf_map__type(const struct bpf_map *map) int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type) { - if (map->fd >= 0) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->def.type = type; return 0; @@ -9252,7 +10572,7 @@ __u32 bpf_map__map_flags(const struct bpf_map *map) int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags) { - if (map->fd >= 0) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->def.map_flags = flags; return 0; @@ -9265,7 +10585,7 @@ __u64 bpf_map__map_extra(const struct bpf_map *map) int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra) { - if (map->fd >= 0) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->map_extra = map_extra; return 0; @@ -9278,7 +10598,7 @@ __u32 bpf_map__numa_node(const struct bpf_map *map) int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node) { - if (map->fd >= 0) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->numa_node = numa_node; return 0; @@ -9291,7 +10611,7 @@ __u32 bpf_map__key_size(const struct bpf_map *map) int bpf_map__set_key_size(struct bpf_map *map, __u32 size) { - if (map->fd >= 0) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->def.key_size = size; return 0; @@ -9302,10 +10622,106 @@ __u32 bpf_map__value_size(const struct bpf_map *map) return map->def.value_size; } +static int map_btf_datasec_resize(struct bpf_map *map, __u32 size) +{ + struct btf *btf; + struct btf_type *datasec_type, *var_type; + struct btf_var_secinfo *var; + const struct btf_type *array_type; + const struct btf_array *array; + int vlen, element_sz, new_array_id; + __u32 nr_elements; + + /* check btf existence */ + btf = bpf_object__btf(map->obj); + if (!btf) + return -ENOENT; + + /* verify map is datasec */ + datasec_type = btf_type_by_id(btf, bpf_map__btf_value_type_id(map)); + if (!btf_is_datasec(datasec_type)) { + pr_warn("map '%s': cannot be resized, map value type is not a datasec\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify datasec has at least one var */ + vlen = btf_vlen(datasec_type); + if (vlen == 0) { + pr_warn("map '%s': cannot be resized, map value datasec is empty\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify last var in the datasec is an array */ + var = &btf_var_secinfos(datasec_type)[vlen - 1]; + var_type = btf_type_by_id(btf, var->type); + array_type = skip_mods_and_typedefs(btf, var_type->type, NULL); + if (!btf_is_array(array_type)) { + pr_warn("map '%s': cannot be resized, last var must be an array\n", + bpf_map__name(map)); + return -EINVAL; + } + + /* verify request size aligns with array */ + array = btf_array(array_type); + element_sz = btf__resolve_size(btf, array->type); + if (element_sz <= 0 || (size - var->offset) % element_sz != 0) { + pr_warn("map '%s': cannot be resized, element size (%d) doesn't align with new total size (%u)\n", + bpf_map__name(map), element_sz, size); + return -EINVAL; + } + + /* create a new array based on the existing array, but with new length */ + nr_elements = (size - var->offset) / element_sz; + new_array_id = btf__add_array(btf, array->index_type, array->type, nr_elements); + if (new_array_id < 0) + return new_array_id; + + /* adding a new btf type invalidates existing pointers to btf objects, + * so refresh pointers before proceeding + */ + datasec_type = btf_type_by_id(btf, map->btf_value_type_id); + var = &btf_var_secinfos(datasec_type)[vlen - 1]; + var_type = btf_type_by_id(btf, var->type); + + /* finally update btf info */ + datasec_type->size = size; + var->size = size - var->offset; + var_type->type = new_array_id; + + return 0; +} + int bpf_map__set_value_size(struct bpf_map *map, __u32 size) { - if (map->fd >= 0) + if (map_is_created(map)) return libbpf_err(-EBUSY); + + if (map->mmaped) { + size_t mmap_old_sz, mmap_new_sz; + int err; + + if (map->def.type != BPF_MAP_TYPE_ARRAY) + return libbpf_err(-EOPNOTSUPP); + + mmap_old_sz = bpf_map_mmap_sz(map); + mmap_new_sz = array_map_mmap_sz(size, map->def.max_entries); + err = bpf_map_mmap_resize(map, mmap_old_sz, mmap_new_sz); + if (err) { + pr_warn("map '%s': failed to resize memory-mapped region: %s\n", + bpf_map__name(map), errstr(err)); + return libbpf_err(err); + } + err = map_btf_datasec_resize(map, size); + if (err && err != -ENOENT) { + pr_warn("map '%s': failed to adjust resized BTF, clearing BTF key/value info: %s\n", + bpf_map__name(map), errstr(err)); + map->btf_value_type_id = 0; + map->btf_key_type_id = 0; + } + } + map->def.value_size = size; return 0; } @@ -9323,19 +10739,41 @@ __u32 bpf_map__btf_value_type_id(const struct bpf_map *map) int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size) { - if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG || - size != map->def.value_size || map->fd >= 0) + size_t actual_sz; + + if (map_is_created(map)) + return libbpf_err(-EBUSY); + + if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG) + return libbpf_err(-EINVAL); + + if (map->def.type == BPF_MAP_TYPE_ARENA) + actual_sz = map->obj->arena_data_sz; + else + actual_sz = map->def.value_size; + if (size != actual_sz) return libbpf_err(-EINVAL); memcpy(map->mmaped, data, size); return 0; } -const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) +void *bpf_map__initial_value(const struct bpf_map *map, size_t *psize) { + if (bpf_map__is_struct_ops(map)) { + if (psize) + *psize = map->def.value_size; + return map->st_ops->data; + } + if (!map->mmaped) return NULL; - *psize = map->def.value_size; + + if (map->def.type == BPF_MAP_TYPE_ARENA) + *psize = map->obj->arena_data_sz; + else + *psize = map->def.value_size; + return map->mmaped; } @@ -9351,7 +10789,7 @@ __u32 bpf_map__ifindex(const struct bpf_map *map) int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) { - if (map->fd >= 0) + if (map_is_created(map)) return libbpf_err(-EBUSY); map->map_ifindex = ifindex; return 0; @@ -9375,6 +10813,27 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) return 0; } +int bpf_map__set_exclusive_program(struct bpf_map *map, struct bpf_program *prog) +{ + if (map_is_created(map)) { + pr_warn("exclusive programs must be set before map creation\n"); + return libbpf_err(-EINVAL); + } + + if (map->obj != prog->obj) { + pr_warn("excl_prog and map must be from the same bpf object\n"); + return libbpf_err(-EINVAL); + } + + map->excl_prog = prog; + return 0; +} + +struct bpf_program *bpf_map__exclusive_program(struct bpf_map *map) +{ + return map->excl_prog; +} + static struct bpf_map * __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) { @@ -9402,7 +10861,7 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) struct bpf_map * bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev) { - if (prev == NULL) + if (prev == NULL && obj != NULL) return obj->maps; return __bpf_map__iter(prev, obj, 1); @@ -9411,7 +10870,7 @@ bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev) struct bpf_map * bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *next) { - if (next == NULL) { + if (next == NULL && obj != NULL) { if (!obj->nr_maps) return NULL; return obj->maps + obj->nr_maps - 1; @@ -9456,7 +10915,7 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name) static int validate_map_op(const struct bpf_map *map, size_t key_sz, size_t value_sz, bool check_value_sz) { - if (map->fd <= 0) + if (!map_is_created(map)) /* map is not yet created */ return -ENOENT; if (map->def.key_size != key_sz) { @@ -9465,6 +10924,11 @@ static int validate_map_op(const struct bpf_map *map, size_t key_sz, return -EINVAL; } + if (map->fd < 0) { + pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name); + return -EINVAL; + } + if (!check_value_sz) return 0; @@ -9577,8 +11041,15 @@ long libbpf_get_error(const void *ptr) int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog) { int ret; + int prog_fd = bpf_program__fd(prog); - ret = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL); + if (prog_fd < 0) { + pr_warn("prog '%s': can't use BPF program without FD (was it loaded?)\n", + prog->name); + return libbpf_err(-EINVAL); + } + + ret = bpf_link_update(bpf_link__fd(link), prog_fd, NULL); return libbpf_err_errno(ret); } @@ -9757,9 +11228,9 @@ static void bpf_link_perf_dealloc(struct bpf_link *link) struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, const struct bpf_perf_event_opts *opts) { - char errmsg[STRERR_BUFSIZE]; struct bpf_link_perf *link; int prog_fd, link_fd = -1, err; + bool force_ioctl_attach; if (!OPTS_VALID(opts, bpf_perf_event_opts)) return libbpf_err_ptr(-EINVAL); @@ -9771,7 +11242,7 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p } prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { - pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n", + pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n", prog->name); return libbpf_err_ptr(-EINVAL); } @@ -9783,16 +11254,16 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p link->link.dealloc = &bpf_link_perf_dealloc; link->perf_event_fd = pfd; - if (kernel_supports(prog->obj, FEAT_PERF_LINK)) { + force_ioctl_attach = OPTS_GET(opts, force_ioctl_attach, false); + if (kernel_supports(prog->obj, FEAT_PERF_LINK) && !force_ioctl_attach) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_opts, .perf_event.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0)); link_fd = bpf_link_create(prog_fd, pfd, BPF_PERF_EVENT, &link_opts); if (link_fd < 0) { err = -errno; - pr_warn("prog '%s': failed to create BPF link for perf_event FD %d: %d (%s)\n", - prog->name, pfd, - err, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + pr_warn("prog '%s': failed to create BPF link for perf_event FD %d: %s\n", + prog->name, pfd, errstr(err)); goto err_out; } link->link.fd = link_fd; @@ -9806,7 +11277,7 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { err = -errno; pr_warn("prog '%s': failed to attach to perf_event FD %d: %s\n", - prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + prog->name, pfd, errstr(err)); if (err == -EPROTO) pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n", prog->name, pfd); @@ -9814,11 +11285,14 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p } link->link.fd = pfd; } - if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) { - err = -errno; - pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n", - prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - goto err_out; + + if (!OPTS_GET(opts, dont_enable, false)) { + if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) { + err = -errno; + pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n", + prog->name, pfd, errstr(err)); + goto err_out; + } } return &link->link; @@ -9841,22 +11315,19 @@ struct bpf_link *bpf_program__attach_perf_event(const struct bpf_program *prog, */ static int parse_uint_from_file(const char *file, const char *fmt) { - char buf[STRERR_BUFSIZE]; int err, ret; FILE *f; - f = fopen(file, "r"); + f = fopen(file, "re"); if (!f) { err = -errno; - pr_debug("failed to open '%s': %s\n", file, - libbpf_strerror_r(err, buf, sizeof(buf))); + pr_debug("failed to open '%s': %s\n", file, errstr(err)); return err; } err = fscanf(f, fmt, &ret); if (err != 1) { err = err == EOF ? -EIO : -errno; - pr_debug("failed to parse '%s': %s\n", file, - libbpf_strerror_r(err, buf, sizeof(buf))); + pr_debug("failed to parse '%s': %s\n", file, errstr(err)); fclose(f); return err; } @@ -9900,10 +11371,9 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, { const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_event_attr attr; - char errmsg[STRERR_BUFSIZE]; int type, pfd; - if (ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS)) + if ((__u64)ref_ctr_off >= (1ULL << PERF_UPROBE_REF_CTR_OFFSET_BITS)) return -EINVAL; memset(&attr, 0, attr_sz); @@ -9913,7 +11383,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, if (type < 0) { pr_warn("failed to determine %s perf type: %s\n", uprobe ? "uprobe" : "kprobe", - libbpf_strerror_r(type, errmsg, sizeof(errmsg))); + errstr(type)); return type; } if (retprobe) { @@ -9923,7 +11393,7 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, if (bit < 0) { pr_warn("failed to determine %s retprobe bit: %s\n", uprobe ? "uprobe" : "kprobe", - libbpf_strerror_r(bit, errmsg, sizeof(errmsg))); + errstr(bit)); return bit; } attr.config |= 1 << bit; @@ -9946,16 +11416,20 @@ static int append_to_file(const char *file, const char *fmt, ...) { int fd, n, err = 0; va_list ap; + char buf[1024]; + + va_start(ap, fmt); + n = vsnprintf(buf, sizeof(buf), fmt, ap); + va_end(ap); + + if (n < 0 || n >= sizeof(buf)) + return -EINVAL; fd = open(file, O_WRONLY | O_APPEND | O_CLOEXEC, 0); if (fd < 0) return -errno; - va_start(ap, fmt); - n = vdprintf(fd, fmt, ap); - va_end(ap); - - if (n < 0) + if (write(fd, buf, n) < 0) err = -errno; close(fd); @@ -9990,13 +11464,32 @@ static const char *tracefs_uprobe_events(void) return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events"; } -static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz, - const char *kfunc_name, size_t offset) +static const char *tracefs_available_filter_functions(void) +{ + return use_debugfs() ? DEBUGFS"/available_filter_functions" + : TRACEFS"/available_filter_functions"; +} + +static const char *tracefs_available_filter_functions_addrs(void) +{ + return use_debugfs() ? DEBUGFS"/available_filter_functions_addrs" + : TRACEFS"/available_filter_functions_addrs"; +} + +static void gen_probe_legacy_event_name(char *buf, size_t buf_sz, + const char *name, size_t offset) { static int index = 0; + int i; - snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx_%d", getpid(), kfunc_name, offset, - __sync_fetch_and_add(&index, 1)); + snprintf(buf, buf_sz, "libbpf_%u_%d_%s_0x%zx", getpid(), + __sync_fetch_and_add(&index, 1), name, offset); + + /* sanitize name in the probe name */ + for (i = 0; buf[i]; i++) { + if (!isalnum(buf[i])) + buf[i] = '_'; + } } static int add_kprobe_event_legacy(const char *probe_name, bool retprobe, @@ -10029,14 +11522,13 @@ static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, { const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_event_attr attr; - char errmsg[STRERR_BUFSIZE]; int type, pfd, err; err = add_kprobe_event_legacy(probe_name, retprobe, kfunc_name, offset); if (err < 0) { pr_warn("failed to add legacy kprobe event for '%s+0x%zx': %s\n", kfunc_name, offset, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); return err; } type = determine_kprobe_perf_type_legacy(probe_name, retprobe); @@ -10044,7 +11536,7 @@ static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, err = type; pr_warn("failed to determine legacy kprobe event id for '%s+0x%zx': %s\n", kfunc_name, offset, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); goto err_clean_legacy; } @@ -10060,7 +11552,7 @@ static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe, if (pfd < 0) { err = -errno; pr_warn("legacy kprobe perf_event_open() failed: %s\n", - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); goto err_clean_legacy; } return pfd; @@ -10079,8 +11571,6 @@ static const char *arch_specific_syscall_pfx(void) return "ia32"; #elif defined(__s390x__) return "s390x"; -#elif defined(__s390__) - return "s390"; #elif defined(__arm__) return "arm"; #elif defined(__aarch64__) @@ -10098,7 +11588,7 @@ static const char *arch_specific_syscall_pfx(void) #endif } -static int probe_kern_syscall_wrapper(void) +int probe_kern_syscall_wrapper(int token_fd) { char syscall_name[64]; const char *ksys_pfx; @@ -10118,9 +11608,9 @@ static int probe_kern_syscall_wrapper(void) return pfd >= 0 ? 1 : 0; } else { /* legacy mode */ - char probe_name[128]; + char probe_name[MAX_EVENT_NAME_LEN]; - gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0); + gen_probe_legacy_event_name(probe_name, sizeof(probe_name), syscall_name, 0); if (add_kprobe_event_legacy(probe_name, false, syscall_name, 0) < 0) return 0; @@ -10135,7 +11625,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, const struct bpf_kprobe_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); - char errmsg[STRERR_BUFSIZE]; + enum probe_attach_mode attach_mode; char *legacy_probe = NULL; struct bpf_link *link; size_t offset; @@ -10145,20 +11635,41 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, if (!OPTS_VALID(opts, bpf_kprobe_opts)) return libbpf_err_ptr(-EINVAL); + attach_mode = OPTS_GET(opts, attach_mode, PROBE_ATTACH_MODE_DEFAULT); retprobe = OPTS_GET(opts, retprobe, false); offset = OPTS_GET(opts, offset, 0); pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); legacy = determine_kprobe_perf_type() < 0; + switch (attach_mode) { + case PROBE_ATTACH_MODE_LEGACY: + legacy = true; + pe_opts.force_ioctl_attach = true; + break; + case PROBE_ATTACH_MODE_PERF: + if (legacy) + return libbpf_err_ptr(-ENOTSUP); + pe_opts.force_ioctl_attach = true; + break; + case PROBE_ATTACH_MODE_LINK: + if (legacy || !kernel_supports(prog->obj, FEAT_PERF_LINK)) + return libbpf_err_ptr(-ENOTSUP); + break; + case PROBE_ATTACH_MODE_DEFAULT: + break; + default: + return libbpf_err_ptr(-EINVAL); + } + if (!legacy) { pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name, offset, -1 /* pid */, 0 /* ref_ctr_off */); } else { - char probe_name[256]; + char probe_name[MAX_EVENT_NAME_LEN]; - gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name), - func_name, offset); + gen_probe_legacy_event_name(probe_name, sizeof(probe_name), + func_name, offset); legacy_probe = strdup(probe_name); if (!legacy_probe) @@ -10172,7 +11683,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, pr_warn("prog '%s': failed to create %s '%s+0x%zx' perf event: %s\n", prog->name, retprobe ? "kretprobe" : "kprobe", func_name, offset, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); goto err_out; } link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); @@ -10182,7 +11693,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog, pr_warn("prog '%s': failed to attach to %s '%s+0x%zx': %s\n", prog->name, retprobe ? "kretprobe" : "kprobe", func_name, offset, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); goto err_clean_legacy; } if (legacy) { @@ -10243,7 +11754,7 @@ struct bpf_link *bpf_program__attach_ksyscall(const struct bpf_program *prog, } /* Adapted from perf/util/string.c */ -static bool glob_match(const char *str, const char *pat) +bool glob_match(const char *str, const char *pat) { while (*str && *pat && *pat != '*') { if (*pat == '?') { /* Matches any single character */ @@ -10276,25 +11787,182 @@ struct kprobe_multi_resolve { size_t cnt; }; -static int -resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type, - const char *sym_name, void *ctx) +struct avail_kallsyms_data { + char **syms; + size_t cnt; + struct kprobe_multi_resolve *res; +}; + +static int avail_func_cmp(const void *a, const void *b) +{ + return strcmp(*(const char **)a, *(const char **)b); +} + +static int avail_kallsyms_cb(unsigned long long sym_addr, char sym_type, + const char *sym_name, void *ctx) { - struct kprobe_multi_resolve *res = ctx; + struct avail_kallsyms_data *data = ctx; + struct kprobe_multi_resolve *res = data->res; int err; if (!glob_match(sym_name, res->pattern)) return 0; - err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long), - res->cnt + 1); + if (!bsearch(&sym_name, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp)) { + /* Some versions of kernel strip out .llvm.<hash> suffix from + * function names reported in available_filter_functions, but + * don't do so for kallsyms. While this is clearly a kernel + * bug (fixed by [0]) we try to accommodate that in libbpf to + * make multi-kprobe usability a bit better: if no match is + * found, we will strip .llvm. suffix and try one more time. + * + * [0] fb6a421fb615 ("kallsyms: Match symbols exactly with CONFIG_LTO_CLANG") + */ + char sym_trim[256], *psym_trim = sym_trim, *sym_sfx; + + if (!(sym_sfx = strstr(sym_name, ".llvm."))) + return 0; + + /* psym_trim vs sym_trim dance is done to avoid pointer vs array + * coercion differences and get proper `const char **` pointer + * which avail_func_cmp() expects + */ + snprintf(sym_trim, sizeof(sym_trim), "%.*s", (int)(sym_sfx - sym_name), sym_name); + if (!bsearch(&psym_trim, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp)) + return 0; + } + + err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, sizeof(*res->addrs), res->cnt + 1); if (err) return err; - res->addrs[res->cnt++] = (unsigned long) sym_addr; + res->addrs[res->cnt++] = (unsigned long)sym_addr; return 0; } +static int libbpf_available_kallsyms_parse(struct kprobe_multi_resolve *res) +{ + const char *available_functions_file = tracefs_available_filter_functions(); + struct avail_kallsyms_data data; + char sym_name[500]; + FILE *f; + int err = 0, ret, i; + char **syms = NULL; + size_t cap = 0, cnt = 0; + + f = fopen(available_functions_file, "re"); + if (!f) { + err = -errno; + pr_warn("failed to open %s: %s\n", available_functions_file, errstr(err)); + return err; + } + + while (true) { + char *name; + + ret = fscanf(f, "%499s%*[^\n]\n", sym_name); + if (ret == EOF && feof(f)) + break; + + if (ret != 1) { + pr_warn("failed to parse available_filter_functions entry: %d\n", ret); + err = -EINVAL; + goto cleanup; + } + + if (!glob_match(sym_name, res->pattern)) + continue; + + err = libbpf_ensure_mem((void **)&syms, &cap, sizeof(*syms), cnt + 1); + if (err) + goto cleanup; + + name = strdup(sym_name); + if (!name) { + err = -errno; + goto cleanup; + } + + syms[cnt++] = name; + } + + /* no entries found, bail out */ + if (cnt == 0) { + err = -ENOENT; + goto cleanup; + } + + /* sort available functions */ + qsort(syms, cnt, sizeof(*syms), avail_func_cmp); + + data.syms = syms; + data.res = res; + data.cnt = cnt; + libbpf_kallsyms_parse(avail_kallsyms_cb, &data); + + if (res->cnt == 0) + err = -ENOENT; + +cleanup: + for (i = 0; i < cnt; i++) + free((char *)syms[i]); + free(syms); + + fclose(f); + return err; +} + +static bool has_available_filter_functions_addrs(void) +{ + return access(tracefs_available_filter_functions_addrs(), R_OK) != -1; +} + +static int libbpf_available_kprobes_parse(struct kprobe_multi_resolve *res) +{ + const char *available_path = tracefs_available_filter_functions_addrs(); + char sym_name[500]; + FILE *f; + int ret, err = 0; + unsigned long long sym_addr; + + f = fopen(available_path, "re"); + if (!f) { + err = -errno; + pr_warn("failed to open %s: %s\n", available_path, errstr(err)); + return err; + } + + while (true) { + ret = fscanf(f, "%llx %499s%*[^\n]\n", &sym_addr, sym_name); + if (ret == EOF && feof(f)) + break; + + if (ret != 2) { + pr_warn("failed to parse available_filter_functions_addrs entry: %d\n", + ret); + err = -EINVAL; + goto cleanup; + } + + if (!glob_match(sym_name, res->pattern)) + continue; + + err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, + sizeof(*res->addrs), res->cnt + 1); + if (err) + goto cleanup; + + res->addrs[res->cnt++] = (unsigned long)sym_addr; + } + + if (res->cnt == 0) + err = -ENOENT; + +cleanup: + fclose(f); + return err; +} + struct bpf_link * bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, const char *pattern, @@ -10304,22 +11972,30 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, struct kprobe_multi_resolve res = { .pattern = pattern, }; + enum bpf_attach_type attach_type; struct bpf_link *link = NULL; - char errmsg[STRERR_BUFSIZE]; const unsigned long *addrs; int err, link_fd, prog_fd; + bool retprobe, session, unique_match; const __u64 *cookies; const char **syms; - bool retprobe; size_t cnt; if (!OPTS_VALID(opts, bpf_kprobe_multi_opts)) return libbpf_err_ptr(-EINVAL); + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + syms = OPTS_GET(opts, syms, false); addrs = OPTS_GET(opts, addrs, false); cnt = OPTS_GET(opts, cnt, false); cookies = OPTS_GET(opts, cookies, false); + unique_match = OPTS_GET(opts, unique_match, false); if (!pattern && !addrs && !syms) return libbpf_err_ptr(-EINVAL); @@ -10327,22 +12003,37 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, return libbpf_err_ptr(-EINVAL); if (!pattern && !cnt) return libbpf_err_ptr(-EINVAL); + if (!pattern && unique_match) + return libbpf_err_ptr(-EINVAL); if (addrs && syms) return libbpf_err_ptr(-EINVAL); if (pattern) { - err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res); + if (has_available_filter_functions_addrs()) + err = libbpf_available_kprobes_parse(&res); + else + err = libbpf_available_kallsyms_parse(&res); if (err) goto error; - if (!res.cnt) { - err = -ENOENT; + + if (unique_match && res.cnt != 1) { + pr_warn("prog '%s': failed to find a unique match for '%s' (%zu matches)\n", + prog->name, pattern, res.cnt); + err = -EINVAL; goto error; } + addrs = res.addrs; cnt = res.cnt; } retprobe = OPTS_GET(opts, retprobe, false); + session = OPTS_GET(opts, session, false); + + if (retprobe && session) + return libbpf_err_ptr(-EINVAL); + + attach_type = session ? BPF_TRACE_KPROBE_SESSION : BPF_TRACE_KPROBE_MULTI; lopts.kprobe_multi.syms = syms; lopts.kprobe_multi.addrs = addrs; @@ -10357,12 +12048,11 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, } link->detach = &bpf_link__detach_fd; - prog_fd = bpf_program__fd(prog); - link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_KPROBE_MULTI, &lopts); + link_fd = bpf_link_create(prog_fd, 0, attach_type, &lopts); if (link_fd < 0) { err = -errno; pr_warn("prog '%s': failed to attach: %s\n", - prog->name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + prog->name, errstr(err)); goto error; } link->fd = link_fd; @@ -10455,7 +12145,7 @@ static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, stru n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern); if (n < 1) { - pr_warn("kprobe multi pattern is invalid: %s\n", pattern); + pr_warn("kprobe multi pattern is invalid: %s\n", spec); return -EINVAL; } @@ -10464,18 +12154,63 @@ static int attach_kprobe_multi(const struct bpf_program *prog, long cookie, stru return libbpf_get_error(*link); } -static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz, - const char *binary_path, uint64_t offset) +static int attach_kprobe_session(const struct bpf_program *prog, long cookie, + struct bpf_link **link) { - int i; + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts, .session = true); + const char *spec; + char *pattern; + int n; - snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), binary_path, (size_t)offset); + *link = NULL; - /* sanitize binary_path in the probe name */ - for (i = 0; buf[i]; i++) { - if (!isalnum(buf[i])) - buf[i] = '_'; + /* no auto-attach for SEC("kprobe.session") */ + if (strcmp(prog->sec_name, "kprobe.session") == 0) + return 0; + + spec = prog->sec_name + sizeof("kprobe.session/") - 1; + n = sscanf(spec, "%m[a-zA-Z0-9_.*?]", &pattern); + if (n < 1) { + pr_warn("kprobe session pattern is invalid: %s\n", spec); + return -EINVAL; + } + + *link = bpf_program__attach_kprobe_multi_opts(prog, pattern, &opts); + free(pattern); + return *link ? 0 : -errno; +} + +static int attach_uprobe_multi(const struct bpf_program *prog, long cookie, struct bpf_link **link) +{ + char *probe_type = NULL, *binary_path = NULL, *func_name = NULL; + LIBBPF_OPTS(bpf_uprobe_multi_opts, opts); + int n, ret = -EINVAL; + + *link = NULL; + + n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[^\n]", + &probe_type, &binary_path, &func_name); + switch (n) { + case 1: + /* handle SEC("u[ret]probe") - format is valid, but auto-attach is impossible. */ + ret = 0; + break; + case 3: + opts.session = str_has_pfx(probe_type, "uprobe.session"); + opts.retprobe = str_has_pfx(probe_type, "uretprobe.multi"); + + *link = bpf_program__attach_uprobe_multi(prog, -1, binary_path, func_name, &opts); + ret = libbpf_get_error(*link); + break; + default: + pr_warn("prog '%s': invalid format of section definition '%s'\n", prog->name, + prog->sec_name); + break; } + free(probe_type); + free(binary_path); + free(func_name); + return ret; } static inline int add_uprobe_event_legacy(const char *probe_name, bool retprobe, @@ -10512,15 +12247,15 @@ static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, err = add_uprobe_event_legacy(probe_name, retprobe, binary_path, offset); if (err < 0) { - pr_warn("failed to add legacy uprobe event for %s:0x%zx: %d\n", - binary_path, (size_t)offset, err); + pr_warn("failed to add legacy uprobe event for %s:0x%zx: %s\n", + binary_path, (size_t)offset, errstr(err)); return err; } type = determine_uprobe_perf_type_legacy(probe_name, retprobe); if (type < 0) { err = type; - pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %d\n", - binary_path, offset, err); + pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %s\n", + binary_path, offset, errstr(err)); goto err_clean_legacy; } @@ -10535,7 +12270,7 @@ static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe, -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); if (pfd < 0) { err = -errno; - pr_warn("legacy uprobe perf_event_open() failed: %d\n", err); + pr_warn("legacy uprobe perf_event_open() failed: %s\n", errstr(err)); goto err_clean_legacy; } return pfd; @@ -10546,173 +12281,65 @@ err_clean_legacy: return err; } -/* Return next ELF section of sh_type after scn, or first of that type if scn is NULL. */ -static Elf_Scn *elf_find_next_scn_by_type(Elf *elf, int sh_type, Elf_Scn *scn) -{ - while ((scn = elf_nextscn(elf, scn)) != NULL) { - GElf_Shdr sh; - - if (!gelf_getshdr(scn, &sh)) - continue; - if (sh.sh_type == sh_type) - return scn; - } - return NULL; -} - -/* Find offset of function name in object specified by path. "name" matches - * symbol name or name@@LIB for library functions. +/* Find offset of function name in archive specified by path. Currently + * supported are .zip files that do not compress their contents, as used on + * Android in the form of APKs, for example. "file_name" is the name of the ELF + * file inside the archive. "func_name" matches symbol name or name@@LIB for + * library functions. + * + * An overview of the APK format specifically provided here: + * https://en.wikipedia.org/w/index.php?title=Apk_(file_format)&oldid=1139099120#Package_contents */ -static long elf_find_func_offset(const char *binary_path, const char *name) -{ - int fd, i, sh_types[2] = { SHT_DYNSYM, SHT_SYMTAB }; - bool is_shared_lib, is_name_qualified; - char errmsg[STRERR_BUFSIZE]; - long ret = -ENOENT; - size_t name_len; - GElf_Ehdr ehdr; +static long elf_find_func_offset_from_archive(const char *archive_path, const char *file_name, + const char *func_name) +{ + struct zip_archive *archive; + struct zip_entry entry; + long ret; Elf *elf; - fd = open(binary_path, O_RDONLY | O_CLOEXEC); - if (fd < 0) { - ret = -errno; - pr_warn("failed to open %s: %s\n", binary_path, - libbpf_strerror_r(ret, errmsg, sizeof(errmsg))); + archive = zip_archive_open(archive_path); + if (IS_ERR(archive)) { + ret = PTR_ERR(archive); + pr_warn("zip: failed to open %s: %ld\n", archive_path, ret); return ret; } - elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); - if (!elf) { - pr_warn("elf: could not read elf from %s: %s\n", binary_path, elf_errmsg(-1)); - close(fd); - return -LIBBPF_ERRNO__FORMAT; + + ret = zip_archive_find_entry(archive, file_name, &entry); + if (ret) { + pr_warn("zip: could not find archive member %s in %s: %ld\n", file_name, + archive_path, ret); + goto out; } - if (!gelf_getehdr(elf, &ehdr)) { - pr_warn("elf: failed to get ehdr from %s: %s\n", binary_path, elf_errmsg(-1)); + pr_debug("zip: found entry for %s in %s at 0x%lx\n", file_name, archive_path, + (unsigned long)entry.data_offset); + + if (entry.compression) { + pr_warn("zip: entry %s of %s is compressed and cannot be handled\n", file_name, + archive_path); ret = -LIBBPF_ERRNO__FORMAT; goto out; } - /* for shared lib case, we do not need to calculate relative offset */ - is_shared_lib = ehdr.e_type == ET_DYN; - - name_len = strlen(name); - /* Does name specify "@@LIB"? */ - is_name_qualified = strstr(name, "@@") != NULL; - - /* Search SHT_DYNSYM, SHT_SYMTAB for symbol. This search order is used because if - * a binary is stripped, it may only have SHT_DYNSYM, and a fully-statically - * linked binary may not have SHT_DYMSYM, so absence of a section should not be - * reported as a warning/error. - */ - for (i = 0; i < ARRAY_SIZE(sh_types); i++) { - size_t nr_syms, strtabidx, idx; - Elf_Data *symbols = NULL; - Elf_Scn *scn = NULL; - int last_bind = -1; - const char *sname; - GElf_Shdr sh; - - scn = elf_find_next_scn_by_type(elf, sh_types[i], NULL); - if (!scn) { - pr_debug("elf: failed to find symbol table ELF sections in '%s'\n", - binary_path); - continue; - } - if (!gelf_getshdr(scn, &sh)) - continue; - strtabidx = sh.sh_link; - symbols = elf_getdata(scn, 0); - if (!symbols) { - pr_warn("elf: failed to get symbols for symtab section in '%s': %s\n", - binary_path, elf_errmsg(-1)); - ret = -LIBBPF_ERRNO__FORMAT; - goto out; - } - nr_syms = symbols->d_size / sh.sh_entsize; - - for (idx = 0; idx < nr_syms; idx++) { - int curr_bind; - GElf_Sym sym; - Elf_Scn *sym_scn; - GElf_Shdr sym_sh; - - if (!gelf_getsym(symbols, idx, &sym)) - continue; - - if (GELF_ST_TYPE(sym.st_info) != STT_FUNC) - continue; - sname = elf_strptr(elf, strtabidx, sym.st_name); - if (!sname) - continue; - - curr_bind = GELF_ST_BIND(sym.st_info); - - /* User can specify func, func@@LIB or func@@LIB_VERSION. */ - if (strncmp(sname, name, name_len) != 0) - continue; - /* ...but we don't want a search for "foo" to match 'foo2" also, so any - * additional characters in sname should be of the form "@@LIB". - */ - if (!is_name_qualified && sname[name_len] != '\0' && sname[name_len] != '@') - continue; - - if (ret >= 0) { - /* handle multiple matches */ - if (last_bind != STB_WEAK && curr_bind != STB_WEAK) { - /* Only accept one non-weak bind. */ - pr_warn("elf: ambiguous match for '%s', '%s' in '%s'\n", - sname, name, binary_path); - ret = -LIBBPF_ERRNO__FORMAT; - goto out; - } else if (curr_bind == STB_WEAK) { - /* already have a non-weak bind, and - * this is a weak bind, so ignore. - */ - continue; - } - } - - /* Transform symbol's virtual address (absolute for - * binaries and relative for shared libs) into file - * offset, which is what kernel is expecting for - * uprobe/uretprobe attachment. - * See Documentation/trace/uprobetracer.rst for more - * details. - * This is done by looking up symbol's containing - * section's header and using it's virtual address - * (sh_addr) and corresponding file offset (sh_offset) - * to transform sym.st_value (virtual address) into - * desired final file offset. - */ - sym_scn = elf_getscn(elf, sym.st_shndx); - if (!sym_scn) - continue; - if (!gelf_getshdr(sym_scn, &sym_sh)) - continue; - - ret = sym.st_value - sym_sh.sh_addr + sym_sh.sh_offset; - last_bind = curr_bind; - } - if (ret > 0) - break; + elf = elf_memory((void *)entry.data, entry.data_length); + if (!elf) { + pr_warn("elf: could not read elf file %s from %s: %s\n", file_name, archive_path, + elf_errmsg(-1)); + ret = -LIBBPF_ERRNO__LIBELF; + goto out; } + ret = elf_find_func_offset(elf, file_name, func_name); if (ret > 0) { - pr_debug("elf: symbol address match for '%s' in '%s': 0x%lx\n", name, binary_path, - ret); - } else { - if (ret == 0) { - pr_warn("elf: '%s' is 0 in symtab for '%s': %s\n", name, binary_path, - is_shared_lib ? "should not be 0 in a shared library" : - "try using shared library path instead"); - ret = -ENOENT; - } else { - pr_warn("elf: failed to find symbol '%s' in '%s'\n", name, binary_path); - } + pr_debug("elf: symbol address match for %s of %s in %s: 0x%x + 0x%lx = 0x%lx\n", + func_name, file_name, archive_path, entry.data_offset, ret, + ret + entry.data_offset); + ret += entry.data_offset; } -out: elf_end(elf); - close(fd); + +out: + zip_archive_close(archive); return ret; } @@ -10730,8 +12357,6 @@ static const char *arch_specific_lib_paths(void) return "/lib/i386-linux-gnu"; #elif defined(__s390x__) return "/lib/s390x-linux-gnu"; -#elif defined(__s390__) - return "/lib/s390-linux-gnu"; #elif defined(__arm__) && defined(__SOFTFP__) return "/lib/arm-linux-gnueabi"; #elif defined(__arm__) && !defined(__SOFTFP__) @@ -10796,14 +12421,144 @@ static int resolve_full_path(const char *file, char *result, size_t result_sz) return -ENOENT; } +struct bpf_link * +bpf_program__attach_uprobe_multi(const struct bpf_program *prog, + pid_t pid, + const char *path, + const char *func_pattern, + const struct bpf_uprobe_multi_opts *opts) +{ + const unsigned long *ref_ctr_offsets = NULL, *offsets = NULL; + LIBBPF_OPTS(bpf_link_create_opts, lopts); + unsigned long *resolved_offsets = NULL; + enum bpf_attach_type attach_type; + int err = 0, link_fd, prog_fd; + struct bpf_link *link = NULL; + char full_path[PATH_MAX]; + bool retprobe, session; + const __u64 *cookies; + const char **syms; + size_t cnt; + + if (!OPTS_VALID(opts, bpf_uprobe_multi_opts)) + return libbpf_err_ptr(-EINVAL); + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + syms = OPTS_GET(opts, syms, NULL); + offsets = OPTS_GET(opts, offsets, NULL); + ref_ctr_offsets = OPTS_GET(opts, ref_ctr_offsets, NULL); + cookies = OPTS_GET(opts, cookies, NULL); + cnt = OPTS_GET(opts, cnt, 0); + retprobe = OPTS_GET(opts, retprobe, false); + session = OPTS_GET(opts, session, false); + + /* + * User can specify 2 mutually exclusive set of inputs: + * + * 1) use only path/func_pattern/pid arguments + * + * 2) use path/pid with allowed combinations of: + * syms/offsets/ref_ctr_offsets/cookies/cnt + * + * - syms and offsets are mutually exclusive + * - ref_ctr_offsets and cookies are optional + * + * Any other usage results in error. + */ + + if (!path) + return libbpf_err_ptr(-EINVAL); + if (!func_pattern && cnt == 0) + return libbpf_err_ptr(-EINVAL); + + if (func_pattern) { + if (syms || offsets || ref_ctr_offsets || cookies || cnt) + return libbpf_err_ptr(-EINVAL); + } else { + if (!!syms == !!offsets) + return libbpf_err_ptr(-EINVAL); + } + + if (retprobe && session) + return libbpf_err_ptr(-EINVAL); + + if (func_pattern) { + if (!strchr(path, '/')) { + err = resolve_full_path(path, full_path, sizeof(full_path)); + if (err) { + pr_warn("prog '%s': failed to resolve full path for '%s': %s\n", + prog->name, path, errstr(err)); + return libbpf_err_ptr(err); + } + path = full_path; + } + + err = elf_resolve_pattern_offsets(path, func_pattern, + &resolved_offsets, &cnt); + if (err < 0) + return libbpf_err_ptr(err); + offsets = resolved_offsets; + } else if (syms) { + err = elf_resolve_syms_offsets(path, cnt, syms, &resolved_offsets, STT_FUNC); + if (err < 0) + return libbpf_err_ptr(err); + offsets = resolved_offsets; + } + + attach_type = session ? BPF_TRACE_UPROBE_SESSION : BPF_TRACE_UPROBE_MULTI; + + lopts.uprobe_multi.path = path; + lopts.uprobe_multi.offsets = offsets; + lopts.uprobe_multi.ref_ctr_offsets = ref_ctr_offsets; + lopts.uprobe_multi.cookies = cookies; + lopts.uprobe_multi.cnt = cnt; + lopts.uprobe_multi.flags = retprobe ? BPF_F_UPROBE_MULTI_RETURN : 0; + + if (pid == 0) + pid = getpid(); + if (pid > 0) + lopts.uprobe_multi.pid = pid; + + link = calloc(1, sizeof(*link)); + if (!link) { + err = -ENOMEM; + goto error; + } + link->detach = &bpf_link__detach_fd; + + link_fd = bpf_link_create(prog_fd, 0, attach_type, &lopts); + if (link_fd < 0) { + err = -errno; + pr_warn("prog '%s': failed to attach multi-uprobe: %s\n", + prog->name, errstr(err)); + goto error; + } + link->fd = link_fd; + free(resolved_offsets); + return link; + +error: + free(resolved_offsets); + free(link); + return libbpf_err_ptr(err); +} + LIBBPF_API struct bpf_link * bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, const struct bpf_uprobe_opts *opts) { + const char *archive_path = NULL, *archive_sep = NULL; + char *legacy_probe = NULL; DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); - char errmsg[STRERR_BUFSIZE], *legacy_probe = NULL; - char full_binary_path[PATH_MAX]; + enum probe_attach_mode attach_mode; + char full_path[PATH_MAX]; struct bpf_link *link; size_t ref_ctr_off; int pfd, err; @@ -10813,6 +12568,7 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, if (!OPTS_VALID(opts, bpf_uprobe_opts)) return libbpf_err_ptr(-EINVAL); + attach_mode = OPTS_GET(opts, attach_mode, PROBE_ATTACH_MODE_DEFAULT); retprobe = OPTS_GET(opts, retprobe, false); ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0); pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); @@ -10820,38 +12576,72 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, if (!binary_path) return libbpf_err_ptr(-EINVAL); - if (!strchr(binary_path, '/')) { - err = resolve_full_path(binary_path, full_binary_path, - sizeof(full_binary_path)); + /* Check if "binary_path" refers to an archive. */ + archive_sep = strstr(binary_path, "!/"); + if (archive_sep) { + full_path[0] = '\0'; + libbpf_strlcpy(full_path, binary_path, + min(sizeof(full_path), (size_t)(archive_sep - binary_path + 1))); + archive_path = full_path; + binary_path = archive_sep + 2; + } else if (!strchr(binary_path, '/')) { + err = resolve_full_path(binary_path, full_path, sizeof(full_path)); if (err) { - pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", - prog->name, binary_path, err); + pr_warn("prog '%s': failed to resolve full path for '%s': %s\n", + prog->name, binary_path, errstr(err)); return libbpf_err_ptr(err); } - binary_path = full_binary_path; + binary_path = full_path; } func_name = OPTS_GET(opts, func_name, NULL); if (func_name) { long sym_off; - sym_off = elf_find_func_offset(binary_path, func_name); + if (archive_path) { + sym_off = elf_find_func_offset_from_archive(archive_path, binary_path, + func_name); + binary_path = archive_path; + } else { + sym_off = elf_find_func_offset_from_file(binary_path, func_name); + } if (sym_off < 0) return libbpf_err_ptr(sym_off); func_offset += sym_off; } legacy = determine_uprobe_perf_type() < 0; + switch (attach_mode) { + case PROBE_ATTACH_MODE_LEGACY: + legacy = true; + pe_opts.force_ioctl_attach = true; + break; + case PROBE_ATTACH_MODE_PERF: + if (legacy) + return libbpf_err_ptr(-ENOTSUP); + pe_opts.force_ioctl_attach = true; + break; + case PROBE_ATTACH_MODE_LINK: + if (legacy || !kernel_supports(prog->obj, FEAT_PERF_LINK)) + return libbpf_err_ptr(-ENOTSUP); + break; + case PROBE_ATTACH_MODE_DEFAULT: + break; + default: + return libbpf_err_ptr(-EINVAL); + } + if (!legacy) { pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, func_offset, pid, ref_ctr_off); } else { - char probe_name[PATH_MAX + 64]; + char probe_name[MAX_EVENT_NAME_LEN]; if (ref_ctr_off) return libbpf_err_ptr(-EINVAL); - gen_uprobe_legacy_event_name(probe_name, sizeof(probe_name), - binary_path, func_offset); + gen_probe_legacy_event_name(probe_name, sizeof(probe_name), + strrchr(binary_path, '/') ? : binary_path, + func_offset); legacy_probe = strdup(probe_name); if (!legacy_probe) @@ -10865,7 +12655,7 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n", prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); goto err_out; } @@ -10876,7 +12666,7 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, pr_warn("prog '%s': failed to attach to %s '%s:0x%zx': %s\n", prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); goto err_clean_legacy; } if (legacy) { @@ -10909,14 +12699,14 @@ err_out: static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf_link **link) { DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts); - char *probe_type = NULL, *binary_path = NULL, *func_name = NULL; - int n, ret = -EINVAL; + char *probe_type = NULL, *binary_path = NULL, *func_name = NULL, *func_off; + int n, c, ret = -EINVAL; long offset = 0; *link = NULL; - n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[a-zA-Z0-9_.]+%li", - &probe_type, &binary_path, &func_name, &offset); + n = sscanf(prog->sec_name, "%m[^/]/%m[^:]:%m[^\n]", + &probe_type, &binary_path, &func_name); switch (n) { case 1: /* handle SEC("u[ret]probe") - format is valid, but auto-attach is impossible. */ @@ -10927,7 +12717,17 @@ static int attach_uprobe(const struct bpf_program *prog, long cookie, struct bpf prog->name, prog->sec_name); break; case 3: - case 4: + /* check if user specifies `+offset`, if yes, this should be + * the last part of the string, make sure sscanf read to EOL + */ + func_off = strrchr(func_name, '+'); + if (func_off) { + n = sscanf(func_off, "+%li%n", &offset, &c); + if (n == 1 && *(func_off + c) == '\0') + func_off[0] = '\0'; + else + offset = 0; + } opts.retprobe = strcmp(probe_type, "uretprobe") == 0 || strcmp(probe_type, "uretprobe.s") == 0; if (opts.retprobe && offset != 0) { @@ -10976,7 +12776,7 @@ struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog, return libbpf_err_ptr(-EINVAL); if (bpf_program__fd(prog) < 0) { - pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n", + pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n", prog->name); return libbpf_err_ptr(-EINVAL); } @@ -10987,8 +12787,8 @@ struct bpf_link *bpf_program__attach_usdt(const struct bpf_program *prog, if (!strchr(binary_path, '/')) { err = resolve_full_path(binary_path, resolved_path, sizeof(resolved_path)); if (err) { - pr_warn("prog '%s': failed to resolve full path for '%s': %d\n", - prog->name, binary_path, err); + pr_warn("prog '%s': failed to resolve full path for '%s': %s\n", + prog->name, binary_path, errstr(err)); return libbpf_err_ptr(err); } binary_path = resolved_path; @@ -11066,14 +12866,13 @@ static int perf_event_open_tracepoint(const char *tp_category, { const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_event_attr attr; - char errmsg[STRERR_BUFSIZE]; int tp_id, pfd, err; tp_id = determine_tracepoint_id(tp_category, tp_name); if (tp_id < 0) { pr_warn("failed to determine tracepoint '%s/%s' perf event ID: %s\n", tp_category, tp_name, - libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg))); + errstr(tp_id)); return tp_id; } @@ -11088,7 +12887,7 @@ static int perf_event_open_tracepoint(const char *tp_category, err = -errno; pr_warn("tracepoint '%s/%s' perf_event_open() failed: %s\n", tp_category, tp_name, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); return err; } return pfd; @@ -11100,7 +12899,6 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *p const struct bpf_tracepoint_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); - char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int pfd, err; @@ -11113,7 +12911,7 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *p if (pfd < 0) { pr_warn("prog '%s': failed to create tracepoint '%s/%s' perf event: %s\n", prog->name, tp_category, tp_name, - libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + errstr(pfd)); return libbpf_err_ptr(pfd); } link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts); @@ -11122,7 +12920,7 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *p close(pfd); pr_warn("prog '%s': failed to attach to tracepoint '%s/%s': %s\n", prog->name, tp_category, tp_name, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + errstr(err)); return libbpf_err_ptr(err); } return link; @@ -11167,13 +12965,18 @@ static int attach_tp(const struct bpf_program *prog, long cookie, struct bpf_lin return libbpf_get_error(*link); } -struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, - const char *tp_name) +struct bpf_link * +bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog, + const char *tp_name, + struct bpf_raw_tracepoint_opts *opts) { - char errmsg[STRERR_BUFSIZE]; + LIBBPF_OPTS(bpf_raw_tp_opts, raw_opts); struct bpf_link *link; int prog_fd, pfd; + if (!OPTS_VALID(opts, bpf_raw_tracepoint_opts)) + return libbpf_err_ptr(-EINVAL); + prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { pr_warn("prog '%s': can't attach before loaded\n", prog->name); @@ -11185,18 +12988,26 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_fd; - pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); + raw_opts.tp_name = tp_name; + raw_opts.cookie = OPTS_GET(opts, cookie, 0); + pfd = bpf_raw_tracepoint_open_opts(prog_fd, &raw_opts); if (pfd < 0) { pfd = -errno; free(link); pr_warn("prog '%s': failed to attach to raw tracepoint '%s': %s\n", - prog->name, tp_name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + prog->name, tp_name, errstr(pfd)); return libbpf_err_ptr(pfd); } link->fd = pfd; return link; } +struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, + const char *tp_name) +{ + return bpf_program__attach_raw_tracepoint_opts(prog, tp_name, NULL); +} + static int attach_raw_tp(const struct bpf_program *prog, long cookie, struct bpf_link **link) { static const char *const prefixes[] = { @@ -11243,7 +13054,6 @@ static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *pro const struct bpf_trace_opts *opts) { LIBBPF_OPTS(bpf_link_create_opts, link_opts); - char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int prog_fd, pfd; @@ -11268,7 +13078,7 @@ static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *pro pfd = -errno; free(link); pr_warn("prog '%s': failed to attach: %s\n", - prog->name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + prog->name, errstr(pfd)); return libbpf_err_ptr(pfd); } link->fd = pfd; @@ -11304,13 +13114,11 @@ static int attach_lsm(const struct bpf_program *prog, long cookie, struct bpf_li } static struct bpf_link * -bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id, - const char *target_name) +bpf_program_attach_fd(const struct bpf_program *prog, + int target_fd, const char *target_name, + const struct bpf_link_create_opts *opts) { - DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts, - .target_btf_id = btf_id); enum bpf_attach_type attach_type; - char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int prog_fd, link_fd; @@ -11326,13 +13134,13 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id link->detach = &bpf_link__detach_fd; attach_type = bpf_program__expected_attach_type(prog); - link_fd = bpf_link_create(prog_fd, target_fd, attach_type, &opts); + link_fd = bpf_link_create(prog_fd, target_fd, attach_type, opts); if (link_fd < 0) { link_fd = -errno; free(link); pr_warn("prog '%s': failed to attach to %s: %s\n", prog->name, target_name, - libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + errstr(link_fd)); return libbpf_err_ptr(link_fd); } link->fd = link_fd; @@ -11342,19 +13150,122 @@ bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id struct bpf_link * bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd) { - return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup"); + return bpf_program_attach_fd(prog, cgroup_fd, "cgroup", NULL); } struct bpf_link * bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd) { - return bpf_program__attach_fd(prog, netns_fd, 0, "netns"); + return bpf_program_attach_fd(prog, netns_fd, "netns", NULL); +} + +struct bpf_link * +bpf_program__attach_sockmap(const struct bpf_program *prog, int map_fd) +{ + return bpf_program_attach_fd(prog, map_fd, "sockmap", NULL); } struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex) { /* target_fd/target_ifindex use the same field in LINK_CREATE */ - return bpf_program__attach_fd(prog, ifindex, 0, "xdp"); + return bpf_program_attach_fd(prog, ifindex, "xdp", NULL); +} + +struct bpf_link * +bpf_program__attach_cgroup_opts(const struct bpf_program *prog, int cgroup_fd, + const struct bpf_cgroup_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); + __u32 relative_id; + int relative_fd; + + if (!OPTS_VALID(opts, bpf_cgroup_opts)) + return libbpf_err_ptr(-EINVAL); + + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + + if (relative_fd && relative_id) { + pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link_create_opts.cgroup.expected_revision = OPTS_GET(opts, expected_revision, 0); + link_create_opts.cgroup.relative_fd = relative_fd; + link_create_opts.cgroup.relative_id = relative_id; + link_create_opts.flags = OPTS_GET(opts, flags, 0); + + return bpf_program_attach_fd(prog, cgroup_fd, "cgroup", &link_create_opts); +} + +struct bpf_link * +bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex, + const struct bpf_tcx_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); + __u32 relative_id; + int relative_fd; + + if (!OPTS_VALID(opts, bpf_tcx_opts)) + return libbpf_err_ptr(-EINVAL); + + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + + /* validate we don't have unexpected combinations of non-zero fields */ + if (!ifindex) { + pr_warn("prog '%s': target netdevice ifindex cannot be zero\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + if (relative_fd && relative_id) { + pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link_create_opts.tcx.expected_revision = OPTS_GET(opts, expected_revision, 0); + link_create_opts.tcx.relative_fd = relative_fd; + link_create_opts.tcx.relative_id = relative_id; + link_create_opts.flags = OPTS_GET(opts, flags, 0); + + /* target_fd/target_ifindex use the same field in LINK_CREATE */ + return bpf_program_attach_fd(prog, ifindex, "tcx", &link_create_opts); +} + +struct bpf_link * +bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex, + const struct bpf_netkit_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); + __u32 relative_id; + int relative_fd; + + if (!OPTS_VALID(opts, bpf_netkit_opts)) + return libbpf_err_ptr(-EINVAL); + + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + + /* validate we don't have unexpected combinations of non-zero fields */ + if (!ifindex) { + pr_warn("prog '%s': target netdevice ifindex cannot be zero\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + if (relative_fd && relative_id) { + pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link_create_opts.netkit.expected_revision = OPTS_GET(opts, expected_revision, 0); + link_create_opts.netkit.relative_fd = relative_fd; + link_create_opts.netkit.relative_id = relative_id; + link_create_opts.flags = OPTS_GET(opts, flags, 0); + + return bpf_program_attach_fd(prog, ifindex, "netkit", &link_create_opts); } struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, @@ -11370,17 +13281,22 @@ struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, } if (prog->type != BPF_PROG_TYPE_EXT) { - pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace", + pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace\n", prog->name); return libbpf_err_ptr(-EINVAL); } if (target_fd) { - btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd); + LIBBPF_OPTS(bpf_link_create_opts, target_opts); + + btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd, prog->obj->token_fd); if (btf_id < 0) return libbpf_err_ptr(btf_id); - return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace"); + target_opts.target_btf_id = btf_id; + + return bpf_program_attach_fd(prog, target_fd, "freplace", + &target_opts); } else { /* no target, so use raw_tracepoint_open for compatibility * with old kernels @@ -11394,7 +13310,6 @@ bpf_program__attach_iter(const struct bpf_program *prog, const struct bpf_iter_attach_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); - char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; int prog_fd, link_fd; __u32 target_fd = 0; @@ -11422,7 +13337,7 @@ bpf_program__attach_iter(const struct bpf_program *prog, link_fd = -errno; free(link); pr_warn("prog '%s': failed to attach to iterator: %s\n", - prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); + prog->name, errstr(link_fd)); return libbpf_err_ptr(link_fd); } link->fd = link_fd; @@ -11435,6 +13350,46 @@ static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_l return libbpf_get_error(*link); } +struct bpf_link *bpf_program__attach_netfilter(const struct bpf_program *prog, + const struct bpf_netfilter_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, lopts); + struct bpf_link *link; + int prog_fd, link_fd; + + if (!OPTS_VALID(opts, bpf_netfilter_opts)) + return libbpf_err_ptr(-EINVAL); + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("prog '%s': can't attach before loaded\n", prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link = calloc(1, sizeof(*link)); + if (!link) + return libbpf_err_ptr(-ENOMEM); + + link->detach = &bpf_link__detach_fd; + + lopts.netfilter.pf = OPTS_GET(opts, pf, 0); + lopts.netfilter.hooknum = OPTS_GET(opts, hooknum, 0); + lopts.netfilter.priority = OPTS_GET(opts, priority, 0); + lopts.netfilter.flags = OPTS_GET(opts, flags, 0); + + link_fd = bpf_link_create(prog_fd, 0, BPF_NETFILTER, &lopts); + if (link_fd < 0) { + link_fd = -errno; + free(link); + pr_warn("prog '%s': failed to attach to netfilter: %s\n", + prog->name, errstr(link_fd)); + return libbpf_err_ptr(link_fd); + } + link->fd = link_fd; + + return link; +} + struct bpf_link *bpf_program__attach(const struct bpf_program *prog) { struct bpf_link *link = NULL; @@ -11443,6 +13398,12 @@ struct bpf_link *bpf_program__attach(const struct bpf_program *prog) if (!prog->sec_def || !prog->sec_def->prog_attach_fn) return libbpf_err_ptr(-EOPNOTSUPP); + if (bpf_program__fd(prog) < 0) { + pr_warn("prog '%s': can't attach BPF program without FD (was it loaded?)\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, &link); if (err) return libbpf_err_ptr(err); @@ -11458,55 +13419,116 @@ struct bpf_link *bpf_program__attach(const struct bpf_program *prog) return link; } +struct bpf_link_struct_ops { + struct bpf_link link; + int map_fd; +}; + static int bpf_link__detach_struct_ops(struct bpf_link *link) { + struct bpf_link_struct_ops *st_link; __u32 zero = 0; - if (bpf_map_delete_elem(link->fd, &zero)) - return -errno; + st_link = container_of(link, struct bpf_link_struct_ops, link); - return 0; + if (st_link->map_fd < 0) + /* w/o a real link */ + return bpf_map_delete_elem(link->fd, &zero); + + return close(link->fd); } struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) { - struct bpf_struct_ops *st_ops; - struct bpf_link *link; - __u32 i, zero = 0; - int err; + struct bpf_link_struct_ops *link; + __u32 zero = 0; + int err, fd; - if (!bpf_map__is_struct_ops(map) || map->fd == -1) + if (!bpf_map__is_struct_ops(map)) { + pr_warn("map '%s': can't attach non-struct_ops map\n", map->name); return libbpf_err_ptr(-EINVAL); + } + + if (map->fd < 0) { + pr_warn("map '%s': can't attach BPF map without FD (was it created?)\n", map->name); + return libbpf_err_ptr(-EINVAL); + } link = calloc(1, sizeof(*link)); if (!link) return libbpf_err_ptr(-EINVAL); - st_ops = map->st_ops; - for (i = 0; i < btf_vlen(st_ops->type); i++) { - struct bpf_program *prog = st_ops->progs[i]; - void *kern_data; - int prog_fd; + /* kern_vdata should be prepared during the loading phase. */ + err = bpf_map_update_elem(map->fd, &zero, map->st_ops->kern_vdata, 0); + /* It can be EBUSY if the map has been used to create or + * update a link before. We don't allow updating the value of + * a struct_ops once it is set. That ensures that the value + * never changed. So, it is safe to skip EBUSY. + */ + if (err && (!(map->def.map_flags & BPF_F_LINK) || err != -EBUSY)) { + free(link); + return libbpf_err_ptr(err); + } - if (!prog) - continue; + link->link.detach = bpf_link__detach_struct_ops; - prog_fd = bpf_program__fd(prog); - kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i]; - *(unsigned long *)kern_data = prog_fd; + if (!(map->def.map_flags & BPF_F_LINK)) { + /* w/o a real link */ + link->link.fd = map->fd; + link->map_fd = -1; + return &link->link; } - err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0); - if (err) { - err = -errno; + fd = bpf_link_create(map->fd, 0, BPF_STRUCT_OPS, NULL); + if (fd < 0) { free(link); - return libbpf_err_ptr(err); + return libbpf_err_ptr(fd); } - link->detach = bpf_link__detach_struct_ops; - link->fd = map->fd; + link->link.fd = fd; + link->map_fd = map->fd; - return link; + return &link->link; +} + +/* + * Swap the back struct_ops of a link with a new struct_ops map. + */ +int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map) +{ + struct bpf_link_struct_ops *st_ops_link; + __u32 zero = 0; + int err; + + if (!bpf_map__is_struct_ops(map)) + return libbpf_err(-EINVAL); + + if (map->fd < 0) { + pr_warn("map '%s': can't use BPF map without FD (was it created?)\n", map->name); + return libbpf_err(-EINVAL); + } + + st_ops_link = container_of(link, struct bpf_link_struct_ops, link); + /* Ensure the type of a link is correct */ + if (st_ops_link->map_fd < 0) + return libbpf_err(-EINVAL); + + err = bpf_map_update_elem(map->fd, &zero, map->st_ops->kern_vdata, 0); + /* It can be EBUSY if the map has been used to create or + * update a link before. We don't allow updating the value of + * a struct_ops once it is set. That ensures that the value + * never changed. So, it is safe to skip EBUSY. + */ + if (err && err != -EBUSY) + return err; + + err = bpf_link_update(link->fd, map->fd, NULL); + if (err < 0) + return err; + + st_ops_link->map_fd = map->fd; + + return 0; } typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, @@ -11645,7 +13667,6 @@ perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, int cpu, int map_key) { struct perf_cpu_buf *cpu_buf; - char msg[STRERR_BUFSIZE]; int err; cpu_buf = calloc(1, sizeof(*cpu_buf)); @@ -11661,7 +13682,7 @@ perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, if (cpu_buf->fd < 0) { err = -errno; pr_warn("failed to open perf buffer event on cpu #%d: %s\n", - cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + cpu, errstr(err)); goto error; } @@ -11672,14 +13693,14 @@ perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, cpu_buf->base = NULL; err = -errno; pr_warn("failed to mmap perf buffer on cpu #%d: %s\n", - cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + cpu, errstr(err)); goto error; } if (ioctl(cpu_buf->fd, PERF_EVENT_IOC_ENABLE, 0) < 0) { err = -errno; pr_warn("failed to enable perf buffer event on cpu #%d: %s\n", - cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + cpu, errstr(err)); goto error; } @@ -11702,17 +13723,21 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_buffer_params p = {}; struct perf_event_attr attr; + __u32 sample_period; if (!OPTS_VALID(opts, perf_buffer_opts)) return libbpf_err_ptr(-EINVAL); + sample_period = OPTS_GET(opts, sample_period, 1); + if (!sample_period) + sample_period = 1; + memset(&attr, 0, attr_sz); attr.size = attr_sz; attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; attr.sample_type = PERF_SAMPLE_RAW; - attr.sample_period = 1; - attr.wakeup_events = 1; + attr.wakeup_events = sample_period; p.attr = &attr; p.sample_cb = sample_cb; @@ -11750,7 +13775,6 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, { const char *online_cpus_file = "/sys/devices/system/cpu/online"; struct bpf_map_info map; - char msg[STRERR_BUFSIZE]; struct perf_buffer *pb; bool *online = NULL; __u32 map_info_len; @@ -11765,7 +13789,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, /* best-effort sanity checks */ memset(&map, 0, sizeof(map)); map_info_len = sizeof(map); - err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len); + err = bpf_map_get_info_by_fd(map_fd, &map, &map_info_len); if (err) { err = -errno; /* if BPF_OBJ_GET_INFO_BY_FD is supported, will return @@ -11773,7 +13797,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, */ if (err != -EINVAL) { pr_warn("failed to get map info for map FD %d: %s\n", - map_fd, libbpf_strerror_r(err, msg, sizeof(msg))); + map_fd, errstr(err)); return ERR_PTR(err); } pr_debug("failed to get map info for FD %d; API not supported? Ignoring...\n", @@ -11803,7 +13827,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, if (pb->epoll_fd < 0) { err = -errno; pr_warn("failed to create epoll instance: %s\n", - libbpf_strerror_r(err, msg, sizeof(msg))); + errstr(err)); goto error; } @@ -11834,7 +13858,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, err = parse_cpu_mask_file(online_cpus_file, &online, &n); if (err) { - pr_warn("failed to get online CPU mask: %d\n", err); + pr_warn("failed to get online CPU mask: %s\n", errstr(err)); goto error; } @@ -11865,7 +13889,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, err = -errno; pr_warn("failed to set cpu #%d, key %d -> perf FD %d: %s\n", cpu, map_key, cpu_buf->fd, - libbpf_strerror_r(err, msg, sizeof(msg))); + errstr(err)); goto error; } @@ -11876,7 +13900,7 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, err = -errno; pr_warn("failed to epoll_ctl cpu #%d perf FD %d: %s\n", cpu, cpu_buf->fd, - libbpf_strerror_r(err, msg, sizeof(msg))); + errstr(err)); goto error; } j++; @@ -11971,7 +13995,7 @@ int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) err = perf_buffer__process_records(pb, cpu_buf); if (err) { - pr_warn("error while processing records: %d\n", err); + pr_warn("error while processing records: %s\n", errstr(err)); return libbpf_err(err); } } @@ -12055,7 +14079,8 @@ int perf_buffer__consume(struct perf_buffer *pb) err = perf_buffer__process_records(pb, cpu_buf); if (err) { - pr_warn("perf_buffer: failed to process records in buffer #%d: %d\n", i, err); + pr_warn("perf_buffer: failed to process records in buffer #%d: %s\n", + i, errstr(err)); return libbpf_err(err); } } @@ -12071,12 +14096,12 @@ int bpf_program__set_attach_target(struct bpf_program *prog, if (!prog || attach_prog_fd < 0) return libbpf_err(-EINVAL); - if (prog->obj->loaded) + if (prog->obj->state >= OBJ_LOADED) return libbpf_err(-EINVAL); if (attach_prog_fd && !attach_func_name) { - /* remember attach_prog_fd and let bpf_program__load() find - * BTF ID during the program load + /* Store attach_prog_fd. The BTF ID will be resolved later during + * the normal object/program load phase. */ prog->attach_prog_fd = attach_prog_fd; return 0; @@ -12084,7 +14109,7 @@ int bpf_program__set_attach_target(struct bpf_program *prog, if (attach_prog_fd) { btf_id = libbpf_find_prog_btf_id(attach_func_name, - attach_prog_fd); + attach_prog_fd, prog->obj->token_fd); if (btf_id < 0) return libbpf_err(btf_id); } else { @@ -12166,14 +14191,14 @@ int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz) fd = open(fcpu, O_RDONLY | O_CLOEXEC); if (fd < 0) { err = -errno; - pr_warn("Failed to open cpu mask file %s: %d\n", fcpu, err); + pr_warn("Failed to open cpu mask file %s: %s\n", fcpu, errstr(err)); return err; } len = read(fd, buf, sizeof(buf)); close(fd); if (len <= 0) { err = len ? -errno : -EINVAL; - pr_warn("Failed to read cpu mask from %s: %d\n", fcpu, err); + pr_warn("Failed to read cpu mask from %s: %s\n", fcpu, errstr(err)); return err; } if (len >= sizeof(buf)) { @@ -12213,14 +14238,15 @@ int libbpf_num_possible_cpus(void) static int populate_skeleton_maps(const struct bpf_object *obj, struct bpf_map_skeleton *maps, - size_t map_cnt) + size_t map_cnt, size_t map_skel_sz) { int i; for (i = 0; i < map_cnt; i++) { - struct bpf_map **map = maps[i].map; - const char *name = maps[i].name; - void **mmaped = maps[i].mmaped; + struct bpf_map_skeleton *map_skel = (void *)maps + i * map_skel_sz; + struct bpf_map **map = map_skel->map; + const char *name = map_skel->name; + void **mmaped = map_skel->mmaped; *map = bpf_object__find_map_by_name(obj, name); if (!*map) { @@ -12237,13 +14263,14 @@ static int populate_skeleton_maps(const struct bpf_object *obj, static int populate_skeleton_progs(const struct bpf_object *obj, struct bpf_prog_skeleton *progs, - size_t prog_cnt) + size_t prog_cnt, size_t prog_skel_sz) { int i; for (i = 0; i < prog_cnt; i++) { - struct bpf_program **prog = progs[i].prog; - const char *name = progs[i].name; + struct bpf_prog_skeleton *prog_skel = (void *)progs + i * prog_skel_sz; + struct bpf_program **prog = prog_skel->prog; + const char *name = prog_skel->name; *prog = bpf_object__find_program_by_name(obj, name); if (!*prog) { @@ -12257,42 +14284,27 @@ static int populate_skeleton_progs(const struct bpf_object *obj, int bpf_object__open_skeleton(struct bpf_object_skeleton *s, const struct bpf_object_open_opts *opts) { - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts, - .object_name = s->name, - ); struct bpf_object *obj; int err; - /* Attempt to preserve opts->object_name, unless overriden by user - * explicitly. Overwriting object name for skeletons is discouraged, - * as it breaks global data maps, because they contain object name - * prefix as their own map name prefix. When skeleton is generated, - * bpftool is making an assumption that this name will stay the same. - */ - if (opts) { - memcpy(&skel_opts, opts, sizeof(*opts)); - if (!opts->object_name) - skel_opts.object_name = s->name; - } - - obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts); - err = libbpf_get_error(obj); - if (err) { - pr_warn("failed to initialize skeleton BPF object '%s': %d\n", - s->name, err); + obj = bpf_object_open(NULL, s->data, s->data_sz, s->name, opts); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + pr_warn("failed to initialize skeleton BPF object '%s': %s\n", + s->name, errstr(err)); return libbpf_err(err); } *s->obj = obj; - err = populate_skeleton_maps(obj, s->maps, s->map_cnt); + err = populate_skeleton_maps(obj, s->maps, s->map_cnt, s->map_skel_sz); if (err) { - pr_warn("failed to populate skeleton maps for '%s': %d\n", s->name, err); + pr_warn("failed to populate skeleton maps for '%s': %s\n", s->name, errstr(err)); return libbpf_err(err); } - err = populate_skeleton_progs(obj, s->progs, s->prog_cnt); + err = populate_skeleton_progs(obj, s->progs, s->prog_cnt, s->prog_skel_sz); if (err) { - pr_warn("failed to populate skeleton progs for '%s': %d\n", s->name, err); + pr_warn("failed to populate skeleton progs for '%s': %s\n", s->name, errstr(err)); return libbpf_err(err); } @@ -12320,26 +14332,26 @@ int bpf_object__open_subskeleton(struct bpf_object_subskeleton *s) return libbpf_err(-errno); } - err = populate_skeleton_maps(s->obj, s->maps, s->map_cnt); + err = populate_skeleton_maps(s->obj, s->maps, s->map_cnt, s->map_skel_sz); if (err) { - pr_warn("failed to populate subskeleton maps: %d\n", err); + pr_warn("failed to populate subskeleton maps: %s\n", errstr(err)); return libbpf_err(err); } - err = populate_skeleton_progs(s->obj, s->progs, s->prog_cnt); + err = populate_skeleton_progs(s->obj, s->progs, s->prog_cnt, s->prog_skel_sz); if (err) { - pr_warn("failed to populate subskeleton maps: %d\n", err); + pr_warn("failed to populate subskeleton maps: %s\n", errstr(err)); return libbpf_err(err); } for (var_idx = 0; var_idx < s->var_cnt; var_idx++) { - var_skel = &s->vars[var_idx]; + var_skel = (void *)s->vars + var_idx * s->var_skel_sz; map = *var_skel->map; map_type_id = bpf_map__btf_value_type_id(map); map_type = btf__type_by_id(btf, map_type_id); if (!btf_is_datasec(map_type)) { - pr_warn("type for map '%1$s' is not a datasec: %2$s", + pr_warn("type for map '%1$s' is not a datasec: %2$s\n", bpf_map__name(map), __btf_kind_str(btf_kind(map_type))); return libbpf_err(-EINVAL); @@ -12375,48 +14387,18 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) err = bpf_object__load(*s->obj); if (err) { - pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err); + pr_warn("failed to load BPF skeleton '%s': %s\n", s->name, errstr(err)); return libbpf_err(err); } for (i = 0; i < s->map_cnt; i++) { - struct bpf_map *map = *s->maps[i].map; - size_t mmap_sz = bpf_map_mmap_sz(map); - int prot, map_fd = bpf_map__fd(map); - void **mmaped = s->maps[i].mmaped; + struct bpf_map_skeleton *map_skel = (void *)s->maps + i * s->map_skel_sz; + struct bpf_map *map = *map_skel->map; - if (!mmaped) + if (!map_skel->mmaped) continue; - if (!(map->def.map_flags & BPF_F_MMAPABLE)) { - *mmaped = NULL; - continue; - } - - if (map->def.map_flags & BPF_F_RDONLY_PROG) - prot = PROT_READ; - else - prot = PROT_READ | PROT_WRITE; - - /* Remap anonymous mmap()-ed "map initialization image" as - * a BPF map-backed mmap()-ed memory, but preserving the same - * memory address. This will cause kernel to change process' - * page table to point to a different piece of kernel memory, - * but from userspace point of view memory address (and its - * contents, being identical at this point) will stay the - * same. This mapping will be released by bpf_object__close() - * as per normal clean up procedure, so we don't need to worry - * about it from skeleton's clean up perspective. - */ - *mmaped = mmap(map->mmaped, mmap_sz, prot, - MAP_SHARED | MAP_FIXED, map_fd, 0); - if (*mmaped == MAP_FAILED) { - err = -errno; - *mmaped = NULL; - pr_warn("failed to re-mmap() map '%s': %d\n", - bpf_map__name(map), err); - return libbpf_err(err); - } + *map_skel->mmaped = map->mmaped; } return 0; @@ -12427,8 +14409,9 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) int i, err; for (i = 0; i < s->prog_cnt; i++) { - struct bpf_program *prog = *s->progs[i].prog; - struct bpf_link **link = s->progs[i].link; + struct bpf_prog_skeleton *prog_skel = (void *)s->progs + i * s->prog_skel_sz; + struct bpf_program *prog = *prog_skel->prog; + struct bpf_link **link = prog_skel->link; if (!prog->autoload || !prog->autoattach) continue; @@ -12443,8 +14426,8 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) err = prog->sec_def->prog_attach_fn(prog, prog->sec_def->cookie, link); if (err) { - pr_warn("prog '%s': failed to auto-attach: %d\n", - bpf_program__name(prog), err); + pr_warn("prog '%s': failed to auto-attach: %s\n", + bpf_program__name(prog), errstr(err)); return libbpf_err(err); } @@ -12460,6 +14443,45 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) */ } + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map_skeleton *map_skel = (void *)s->maps + i * s->map_skel_sz; + struct bpf_map *map = *map_skel->map; + struct bpf_link **link; + + if (!map->autocreate || !map->autoattach) + continue; + + /* only struct_ops maps can be attached */ + if (!bpf_map__is_struct_ops(map)) + continue; + + /* skeleton is created with earlier version of bpftool, notify user */ + if (s->map_skel_sz < offsetofend(struct bpf_map_skeleton, link)) { + pr_warn("map '%s': BPF skeleton version is old, skipping map auto-attachment...\n", + bpf_map__name(map)); + continue; + } + + link = map_skel->link; + if (!link) { + pr_warn("map '%s': BPF map skeleton link is uninitialized\n", + bpf_map__name(map)); + continue; + } + + if (*link) + continue; + + *link = bpf_map__attach_struct_ops(map); + if (!*link) { + err = -errno; + pr_warn("map '%s': failed to auto-attach: %s\n", + bpf_map__name(map), errstr(err)); + return libbpf_err(err); + } + } + return 0; } @@ -12468,11 +14490,25 @@ void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) int i; for (i = 0; i < s->prog_cnt; i++) { - struct bpf_link **link = s->progs[i].link; + struct bpf_prog_skeleton *prog_skel = (void *)s->progs + i * s->prog_skel_sz; + struct bpf_link **link = prog_skel->link; bpf_link__destroy(*link); *link = NULL; } + + if (s->map_skel_sz < sizeof(struct bpf_map_skeleton)) + return; + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map_skeleton *map_skel = (void *)s->maps + i * s->map_skel_sz; + struct bpf_link **link = map_skel->link; + + if (link) { + bpf_link__destroy(*link); + *link = NULL; + } + } } void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) @@ -12480,8 +14516,7 @@ void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) if (!s) return; - if (s->progs) - bpf_object__detach_skeleton(s); + bpf_object__detach_skeleton(s); if (s->obj) bpf_object__close(*s->obj); free(s->maps); diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index eee883f007f9..65e68e964b89 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -24,8 +24,25 @@ extern "C" { #endif +/** + * @brief **libbpf_major_version()** provides the major version of libbpf. + * @return An integer, the major version number + */ LIBBPF_API __u32 libbpf_major_version(void); + +/** + * @brief **libbpf_minor_version()** provides the minor version of libbpf. + * @return An integer, the minor version number + */ LIBBPF_API __u32 libbpf_minor_version(void); + +/** + * @brief **libbpf_version_string()** provides the version of libbpf in a + * human-readable form, e.g., "v1.7". + * @return Pointer to a static string containing the version + * + * The format is *not* a part of a stable API and may change in the future. + */ LIBBPF_API const char *libbpf_version_string(void); enum libbpf_errno { @@ -49,6 +66,14 @@ enum libbpf_errno { __LIBBPF_ERRNO__END, }; +/** + * @brief **libbpf_strerror()** converts the provided error code into a + * human-readable string. + * @param err The error code to convert + * @param buf Pointer to a buffer where the error message will be stored + * @param size The number of bytes in the buffer + * @return 0, on success; negative error code, otherwise + */ LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size); /** @@ -96,6 +121,17 @@ enum libbpf_print_level { typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, const char *, va_list ap); +/** + * @brief **libbpf_set_print()** sets user-provided log callback function to + * be used for libbpf warnings and informational messages. If the user callback + * is not set, messages are logged to stderr by default. The verbosity of these + * messages can be controlled by setting the environment variable + * LIBBPF_LOG_LEVEL to either warn, info, or debug. + * @param fn The log print function. If NULL, libbpf won't print anything. + * @return Pointer to old print function. + * + * This function is thread-safe. + */ LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); /* Hide internal to user */ @@ -141,7 +177,7 @@ struct bpf_object_open_opts { * log_buf and log_level settings. * * If specified, this log buffer will be passed for: - * - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden + * - each BPF progral load (BPF_PROG_LOAD) attempt, unless overridden * with bpf_program__set_log() on per-program level, to get * BPF verifier log output. * - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get @@ -169,11 +205,38 @@ struct bpf_object_open_opts { * logs through its print callback. */ __u32 kernel_log_level; + /* Path to BPF FS mount point to derive BPF token from. + * + * Created BPF token will be used for all bpf() syscall operations + * that accept BPF token (e.g., map creation, BTF and program loads, + * etc) automatically within instantiated BPF object. + * + * If bpf_token_path is not specified, libbpf will consult + * LIBBPF_BPF_TOKEN_PATH environment variable. If set, it will be + * taken as a value of bpf_token_path option and will force libbpf to + * either create BPF token from provided custom BPF FS path, or will + * disable implicit BPF token creation, if envvar value is an empty + * string. bpf_token_path overrides LIBBPF_BPF_TOKEN_PATH, if both are + * set at the same time. + * + * Setting bpf_token_path option to empty string disables libbpf's + * automatic attempt to create BPF token from default BPF FS mount + * point (/sys/fs/bpf), in case this default behavior is undesirable. + */ + const char *bpf_token_path; size_t :0; }; -#define bpf_object_open_opts__last_field kernel_log_level +#define bpf_object_open_opts__last_field bpf_token_path +/** + * @brief **bpf_object__open()** 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. + * @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(const char *path); /** @@ -203,16 +266,59 @@ 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); -/* Load/unload object into/from kernel */ +/** + * @brief **bpf_object__prepare()** prepares BPF object for loading: + * performs ELF processing, relocations, prepares final state of BPF program + * instructions (accessible with bpf_program__insns()), creates and + * (potentially) pins maps. Leaves BPF object in the state ready for program + * loading. + * @param obj Pointer to a valid BPF object instance returned by + * **bpf_object__open*()** API + * @return 0, on success; negative error code, otherwise, error code is + * stored in errno + */ +LIBBPF_API int bpf_object__prepare(struct bpf_object *obj); + +/** + * @brief **bpf_object__load()** loads BPF object into kernel. + * @param obj Pointer to a valid BPF object instance returned by + * **bpf_object__open*()** APIs + * @return 0, on success; negative error code, otherwise, error code is + * stored in errno + */ LIBBPF_API int bpf_object__load(struct bpf_object *obj); -LIBBPF_API void bpf_object__close(struct bpf_object *object); +/** + * @brief **bpf_object__close()** closes a BPF object and releases all + * resources. + * @param obj Pointer to a valid BPF object + */ +LIBBPF_API void bpf_object__close(struct bpf_object *obj); -/* pin_maps and unpin_maps can both be called with a NULL path, in which case - * they will use the pin_path attribute of each map (and ignore all maps that - * don't have a pin_path set). +/** + * @brief **bpf_object__pin_maps()** pins each map contained within + * the BPF object at the passed directory. + * @param obj Pointer to a valid BPF object + * @param path A directory where maps should be pinned. + * @return 0, on success; negative error code, otherwise + * + * If `path` is NULL `bpf_map__pin` (which is being used on each map) + * will use the pin_path attribute of each map. In this case, maps that + * don't have a pin_path set will be ignored. */ LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path); + +/** + * @brief **bpf_object__unpin_maps()** unpins each map contained within + * the BPF object found in the passed directory. + * @param obj Pointer to a valid BPF object + * @param path A directory where pinned maps should be searched for. + * @return 0, on success; negative error code, otherwise + * + * If `path` is NULL `bpf_map__unpin` (which is being used on each map) + * will use the pin_path attribute of each map. In this case, maps that + * don't have a pin_path set will be ignored. + */ LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj, const char *path); LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj, @@ -220,11 +326,20 @@ LIBBPF_API int bpf_object__pin_programs(struct bpf_object *obj, LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj, const char *path); LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path); +LIBBPF_API int bpf_object__unpin(struct bpf_object *object, const char *path); LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); LIBBPF_API int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version); +/** + * @brief **bpf_object__token_fd** is an accessor for BPF token FD associated + * with BPF object. + * @param obj Pointer to a valid BPF object + * @return BPF token FD or -1, if it wasn't set + */ +LIBBPF_API int bpf_object__token_fd(const struct bpf_object *obj); + struct btf; LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); @@ -333,7 +448,7 @@ LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); /** * @brief **bpf_program__unpin()** unpins the BPF program from a file - * in the BPFFS specified by a path. This decrements the programs + * in the BPFFS specified by a path. This decrements program's in-kernel * reference count. * * The file pinning the BPF program can also be unlinked by a different @@ -366,14 +481,12 @@ LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path); /** * @brief **bpf_link__unpin()** unpins the BPF link from a file - * in the BPFFS specified by a path. This decrements the links - * reference count. + * in the BPFFS. This decrements link's in-kernel reference count. * * The file pinning the BPF link can also be unlinked by a different * process in which case this function will return an error. * - * @param prog BPF program to unpin - * @param path file path to the pin in a BPF file system + * @param link BPF link to unpin * @return 0, on success; negative error code, otherwise */ LIBBPF_API int bpf_link__unpin(struct bpf_link *link); @@ -386,7 +499,7 @@ LIBBPF_API int bpf_link__destroy(struct bpf_link *link); /** * @brief **bpf_program__attach()** is a generic function for attaching * a BPF program based on auto-detection of program type, attach type, - * and extra paremeters, where applicable. + * and extra parameters, where applicable. * * @param prog BPF program to attach * @return Reference to the newly created BPF link; or NULL is returned on error, @@ -403,12 +516,17 @@ LIBBPF_API struct bpf_link * bpf_program__attach(const struct bpf_program *prog); struct bpf_perf_event_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; /* custom user-provided value fetchable through bpf_get_attach_cookie() */ __u64 bpf_cookie; + /* don't use BPF link when attach BPF program */ + bool force_ioctl_attach; + /* don't automatically enable the event */ + bool dont_enable; + size_t :0; }; -#define bpf_perf_event_opts__last_field bpf_cookie +#define bpf_perf_event_opts__last_field dont_enable LIBBPF_API struct bpf_link * bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd); @@ -417,8 +535,25 @@ LIBBPF_API struct bpf_link * bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, const struct bpf_perf_event_opts *opts); +/** + * enum probe_attach_mode - the mode to attach kprobe/uprobe + * + * force libbpf to attach kprobe/uprobe in specific mode, -ENOTSUP will + * be returned if it is not supported by the kernel. + */ +enum probe_attach_mode { + /* attach probe in latest supported mode by kernel */ + PROBE_ATTACH_MODE_DEFAULT = 0, + /* attach probe in legacy mode, using debugfs/tracefs */ + PROBE_ATTACH_MODE_LEGACY, + /* create perf event with perf_event_open() syscall */ + PROBE_ATTACH_MODE_PERF, + /* attach probe with BPF link */ + PROBE_ATTACH_MODE_LINK, +}; + struct bpf_kprobe_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; /* custom user-provided value fetchable through bpf_get_attach_cookie() */ __u64 bpf_cookie; @@ -426,9 +561,11 @@ struct bpf_kprobe_opts { size_t offset; /* kprobe is return probe */ bool retprobe; + /* kprobe attach mode */ + enum probe_attach_mode attach_mode; size_t :0; }; -#define bpf_kprobe_opts__last_field retprobe +#define bpf_kprobe_opts__last_field attach_mode LIBBPF_API struct bpf_link * bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe, @@ -451,18 +588,75 @@ struct bpf_kprobe_multi_opts { size_t cnt; /* create return kprobes */ bool retprobe; + /* create session kprobes */ + bool session; + /* enforce unique match */ + bool unique_match; size_t :0; }; -#define bpf_kprobe_multi_opts__last_field retprobe +#define bpf_kprobe_multi_opts__last_field unique_match LIBBPF_API struct bpf_link * bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog, const char *pattern, const struct bpf_kprobe_multi_opts *opts); +struct bpf_uprobe_multi_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + /* array of function symbols to attach to */ + const char **syms; + /* array of function addresses to attach to */ + const unsigned long *offsets; + /* optional, array of associated ref counter offsets */ + const unsigned long *ref_ctr_offsets; + /* optional, array of associated BPF cookies */ + const __u64 *cookies; + /* number of elements in syms/addrs/cookies arrays */ + size_t cnt; + /* create return uprobes */ + bool retprobe; + /* create session kprobes */ + bool session; + size_t :0; +}; + +#define bpf_uprobe_multi_opts__last_field session + +/** + * @brief **bpf_program__attach_uprobe_multi()** attaches a BPF program + * to multiple uprobes with uprobe_multi link. + * + * User can specify 2 mutually exclusive set of inputs: + * + * 1) use only path/func_pattern/pid arguments + * + * 2) use path/pid with allowed combinations of + * syms/offsets/ref_ctr_offsets/cookies/cnt + * + * - syms and offsets are mutually exclusive + * - ref_ctr_offsets and cookies are optional + * + * + * @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 + * @param func_pattern Regular expression to specify functions to attach + * BPF program to + * @param opts Additional options (see **struct bpf_uprobe_multi_opts**) + * @return 0, on success; negative error code, otherwise + */ +LIBBPF_API struct bpf_link * +bpf_program__attach_uprobe_multi(const struct bpf_program *prog, + pid_t pid, + const char *binary_path, + const char *func_pattern, + const struct bpf_uprobe_multi_opts *opts); + struct bpf_ksyscall_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; /* custom user-provided value fetchable through bpf_get_attach_cookie() */ __u64 bpf_cookie; @@ -508,7 +702,7 @@ bpf_program__attach_ksyscall(const struct bpf_program *prog, const struct bpf_ksyscall_opts *opts); struct bpf_uprobe_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; /* offset of kernel reference counted USDT semaphore, added in * a6ca88b241d5 ("trace_uprobe: support reference counter in fd-based uprobe") @@ -526,14 +720,16 @@ struct bpf_uprobe_opts { * binary_path. */ const char *func_name; + /* uprobe attach mode */ + enum probe_attach_mode attach_mode; size_t :0; }; -#define bpf_uprobe_opts__last_field func_name +#define bpf_uprobe_opts__last_field attach_mode /** * @brief **bpf_program__attach_uprobe()** attaches a BPF program * to the userspace function which is found by binary path and - * offset. You can optionally specify a particular proccess to attach + * offset. You can optionally specify a particular process to attach * to. You can also optionally attach the program to the function * exit instead of entry. * @@ -602,7 +798,7 @@ bpf_program__attach_usdt(const struct bpf_program *prog, const struct bpf_usdt_opts *opts); struct bpf_tracepoint_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; /* custom user-provided value fetchable through bpf_get_attach_cookie() */ __u64 bpf_cookie; @@ -619,9 +815,20 @@ bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, const char *tp_name, const struct bpf_tracepoint_opts *opts); +struct bpf_raw_tracepoint_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u64 cookie; + size_t :0; +}; +#define bpf_raw_tracepoint_opts__last_field cookie + LIBBPF_API struct bpf_link * bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, const char *tp_name); +LIBBPF_API struct bpf_link * +bpf_program__attach_raw_tracepoint_opts(const struct bpf_program *prog, + const char *tp_name, + struct bpf_raw_tracepoint_opts *opts); struct bpf_trace_opts { /* size of this struct, for forward/backward compatibility */ @@ -643,14 +850,77 @@ bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd); LIBBPF_API struct bpf_link * bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd); LIBBPF_API struct bpf_link * +bpf_program__attach_sockmap(const struct bpf_program *prog, int map_fd); +LIBBPF_API struct bpf_link * bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex); LIBBPF_API struct bpf_link * bpf_program__attach_freplace(const struct bpf_program *prog, int target_fd, const char *attach_func_name); +struct bpf_netfilter_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; +}; +#define bpf_netfilter_opts__last_field flags + +LIBBPF_API struct bpf_link * +bpf_program__attach_netfilter(const struct bpf_program *prog, + const struct bpf_netfilter_opts *opts); + +struct bpf_tcx_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + __u32 flags; + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + size_t :0; +}; +#define bpf_tcx_opts__last_field expected_revision + +LIBBPF_API struct bpf_link * +bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex, + const struct bpf_tcx_opts *opts); + +struct bpf_netkit_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + __u32 flags; + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + size_t :0; +}; +#define bpf_netkit_opts__last_field expected_revision + +LIBBPF_API struct bpf_link * +bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex, + const struct bpf_netkit_opts *opts); + +struct bpf_cgroup_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + __u32 flags; + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + size_t :0; +}; +#define bpf_cgroup_opts__last_field expected_revision + +LIBBPF_API struct bpf_link * +bpf_program__attach_cgroup_opts(const struct bpf_program *prog, int cgroup_fd, + const struct bpf_cgroup_opts *opts); + struct bpf_map; LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map); +LIBBPF_API int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map); struct bpf_iter_attach_opts { size_t sz; /* size of this struct for forward/backward compatibility */ @@ -710,6 +980,12 @@ LIBBPF_API int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_le LIBBPF_API const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size); LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size); +LIBBPF_API struct bpf_func_info *bpf_program__func_info(const struct bpf_program *prog); +LIBBPF_API __u32 bpf_program__func_info_cnt(const struct bpf_program *prog); + +LIBBPF_API struct bpf_line_info *bpf_program__line_info(const struct bpf_program *prog); +LIBBPF_API __u32 bpf_program__line_info_cnt(const struct bpf_program *prog); + /** * @brief **bpf_program__set_attach_target()** sets BTF-based attach target * for supported BPF program types: @@ -717,8 +993,13 @@ LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, * - fentry/fexit/fmod_ret; * - lsm; * - freplace. - * @param prog BPF program to set the attach type for - * @param type attach type to set the BPF map to have + * @param prog BPF program to configure; must be not yet loaded. + * @param attach_prog_fd FD of target BPF program (for freplace/extension). + * If >0 and func name omitted, defers BTF ID resolution. + * @param attach_func_name Target function name. Used either with + * attach_prog_fd to find destination BTF type ID in that BPF program, or + * alone (no attach_prog_fd) to resolve kernel (vmlinux/module) BTF ID. + * Must be provided if attach_prog_fd is 0. * @return error code; or 0 if no error occurred. */ LIBBPF_API int @@ -774,6 +1055,23 @@ LIBBPF_API int bpf_map__set_autocreate(struct bpf_map *map, bool autocreate); LIBBPF_API bool bpf_map__autocreate(const struct bpf_map *map); /** + * @brief **bpf_map__set_autoattach()** sets whether libbpf has to auto-attach + * map during BPF skeleton attach phase. + * @param map the BPF map instance + * @param autoattach whether to attach map during BPF skeleton attach phase + * @return 0 on success; negative error code, otherwise + */ +LIBBPF_API int bpf_map__set_autoattach(struct bpf_map *map, bool autoattach); + +/** + * @brief **bpf_map__autoattach()** returns whether BPF map is configured to + * auto-attach during BPF skeleton attach phase. + * @param map the BPF map instance + * @return true if map is set to auto-attach during skeleton attach phase; false, otherwise + */ +LIBBPF_API bool bpf_map__autoattach(const struct bpf_map *map); + +/** * @brief **bpf_map__fd()** gets the file descriptor of the passed * BPF map * @param map the BPF map instance @@ -798,8 +1096,23 @@ LIBBPF_API int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node); /* get/set map key size */ LIBBPF_API __u32 bpf_map__key_size(const struct bpf_map *map); LIBBPF_API int bpf_map__set_key_size(struct bpf_map *map, __u32 size); -/* get/set map value size */ +/* get map value size */ LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map); +/** + * @brief **bpf_map__set_value_size()** sets map value size. + * @param map the BPF map instance + * @param size the new value size + * @return 0, on success; negative error, otherwise + * + * There is a special case for maps with associated memory-mapped regions, like + * the global data section maps (bss, data, rodata). When this function is used + * on such a map, the mapped region is resized. Afterward, an attempt is made to + * adjust the corresponding BTF info. This attempt is best-effort and can only + * succeed if the last variable of the data section map is an array. The array + * BTF type is replaced by a new BTF array type with a different length. + * Any previously existing pointers returned from bpf_map__initial_value() or + * corresponding data section skeleton pointer must be reinitialized. + */ LIBBPF_API int bpf_map__set_value_size(struct bpf_map *map, __u32 size); /* get map key/value BTF type IDs */ LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); @@ -813,7 +1126,7 @@ LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); -LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); +LIBBPF_API void *bpf_map__initial_value(const struct bpf_map *map, size_t *psize); /** * @brief **bpf_map__is_internal()** tells the caller whether or not the @@ -823,10 +1136,57 @@ LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize * @return true, if the map is an internal map; false, otherwise */ LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); + +/** + * @brief **bpf_map__set_pin_path()** sets the path attribute that tells where the + * BPF map should be pinned. This does not actually create the 'pin'. + * @param map The bpf_map + * @param path The path + * @return 0, on success; negative error, otherwise + */ LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); + +/** + * @brief **bpf_map__pin_path()** gets the path attribute that tells where the + * BPF map should be pinned. + * @param map The bpf_map + * @return The path string; which can be NULL + */ LIBBPF_API const char *bpf_map__pin_path(const struct bpf_map *map); + +/** + * @brief **bpf_map__is_pinned()** tells the caller whether or not the + * passed map has been pinned via a 'pin' file. + * @param map The bpf_map + * @return true, if the map is pinned; false, otherwise + */ LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map); + +/** + * @brief **bpf_map__pin()** creates a file that serves as a 'pin' + * for the BPF map. This increments the reference count on the + * BPF map which will keep the BPF map loaded even after the + * userspace process which loaded it has exited. + * @param map The bpf_map to pin + * @param path A file path for the 'pin' + * @return 0, on success; negative error, otherwise + * + * If `path` is NULL the maps `pin_path` attribute will be used. If this is + * also NULL, an error will be returned and the map will not be pinned. + */ LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); + +/** + * @brief **bpf_map__unpin()** removes the file that serves as a + * 'pin' for the BPF map. + * @param map The bpf_map to unpin + * @param path A file path for the 'pin' + * @return 0, on success; negative error, otherwise + * + * The `path` parameter can be NULL, in which case the `pin_path` + * map attribute is unpinned. If both the `path` parameter and + * `pin_path` map attribute are set, they must be equal. + */ LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd); @@ -846,7 +1206,7 @@ LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); * per-CPU values value size has to be aligned up to closest 8 bytes for * alignment reasons, so expected size is: `round_up(value_size, 8) * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__lookup_elem()** is high-level equivalent of @@ -870,7 +1230,7 @@ LIBBPF_API int bpf_map__lookup_elem(const struct bpf_map *map, * per-CPU values value size has to be aligned up to closest 8 bytes for * alignment reasons, so expected size is: `round_up(value_size, 8) * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__update_elem()** is high-level equivalent of @@ -886,7 +1246,7 @@ LIBBPF_API int bpf_map__update_elem(const struct bpf_map *map, * @param map BPF map to delete element from * @param key pointer to memory containing bytes of the key * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__delete_elem()** is high-level equivalent of @@ -909,7 +1269,7 @@ LIBBPF_API int bpf_map__delete_elem(const struct bpf_map *map, * per-CPU values value size has to be aligned up to closest 8 bytes for * alignment reasons, so expected size is: `round_up(value_size, 8) * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__lookup_and_delete_elem()** is high-level equivalent of @@ -935,6 +1295,28 @@ LIBBPF_API int bpf_map__lookup_and_delete_elem(const struct bpf_map *map, */ LIBBPF_API int bpf_map__get_next_key(const struct bpf_map *map, const void *cur_key, void *next_key, size_t key_sz); +/** + * @brief **bpf_map__set_exclusive_program()** sets a map to be exclusive to the + * specified program. This must be called *before* the map is created. + * + * @param map BPF map to make exclusive. + * @param prog BPF program to be the exclusive user of the map. Must belong + * to the same bpf_object as the map. + * @return 0 on success; a negative error code otherwise. + * + * This function must be called after the BPF object is opened but before + * it is loaded. Once the object is loaded, only the specified program + * will be able to access the map's contents. + */ +LIBBPF_API int bpf_map__set_exclusive_program(struct bpf_map *map, struct bpf_program *prog); + +/** + * @brief **bpf_map__exclusive_program()** returns the exclusive program + * that is registered with the map (if any). + * @param map BPF map to which the exclusive program is registered. + * @return the registered exclusive program. + */ +LIBBPF_API struct bpf_program *bpf_map__exclusive_program(struct bpf_map *map); struct bpf_xdp_set_link_opts { size_t sz; @@ -957,9 +1339,11 @@ struct bpf_xdp_query_opts { __u32 hw_prog_id; /* output */ __u32 skb_prog_id; /* output */ __u8 attach_mode; /* output */ + __u64 feature_flags; /* output */ + __u32 xdp_zc_max_segs; /* output */ size_t :0; }; -#define bpf_xdp_query_opts__last_field attach_mode +#define bpf_xdp_query_opts__last_field xdp_zc_max_segs LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts); @@ -973,6 +1357,7 @@ enum bpf_tc_attach_point { BPF_TC_INGRESS = 1 << 0, BPF_TC_EGRESS = 1 << 1, BPF_TC_CUSTOM = 1 << 2, + BPF_TC_QDISC = 1 << 3, }; #define BPF_TC_PARENT(a, b) \ @@ -987,9 +1372,11 @@ struct bpf_tc_hook { int ifindex; enum bpf_tc_attach_point attach_point; __u32 parent; + __u32 handle; + const char *qdisc; size_t :0; }; -#define bpf_tc_hook__last_field parent +#define bpf_tc_hook__last_field qdisc struct bpf_tc_opts { size_t sz; @@ -1013,12 +1400,13 @@ LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook, /* Ring buffer APIs */ struct ring_buffer; +struct ring; struct user_ring_buffer; typedef int (*ring_buffer_sample_fn)(void *ctx, void *data, size_t size); struct ring_buffer_opts { - size_t sz; /* size of this struct, for forward/backward compatiblity */ + size_t sz; /* size of this struct, for forward/backward compatibility */ }; #define ring_buffer_opts__last_field sz @@ -1031,15 +1419,100 @@ LIBBPF_API int ring_buffer__add(struct ring_buffer *rb, int map_fd, ring_buffer_sample_fn sample_cb, void *ctx); LIBBPF_API int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms); LIBBPF_API int ring_buffer__consume(struct ring_buffer *rb); +LIBBPF_API int ring_buffer__consume_n(struct ring_buffer *rb, size_t n); LIBBPF_API int ring_buffer__epoll_fd(const struct ring_buffer *rb); +/** + * @brief **ring_buffer__ring()** returns the ringbuffer object inside a given + * ringbuffer manager representing a single BPF_MAP_TYPE_RINGBUF map instance. + * + * @param rb A ringbuffer manager object. + * @param idx An index into the ringbuffers contained within the ringbuffer + * manager object. The index is 0-based and corresponds to the order in which + * ring_buffer__add was called. + * @return A ringbuffer object on success; NULL and errno set if the index is + * invalid. + */ +LIBBPF_API struct ring *ring_buffer__ring(struct ring_buffer *rb, + unsigned int idx); + +/** + * @brief **ring__consumer_pos()** returns the current consumer position in the + * given ringbuffer. + * + * @param r A ringbuffer object. + * @return The current consumer position. + */ +LIBBPF_API unsigned long ring__consumer_pos(const struct ring *r); + +/** + * @brief **ring__producer_pos()** returns the current producer position in the + * given ringbuffer. + * + * @param r A ringbuffer object. + * @return The current producer position. + */ +LIBBPF_API unsigned long ring__producer_pos(const struct ring *r); + +/** + * @brief **ring__avail_data_size()** returns the number of bytes in the + * ringbuffer not yet consumed. This has no locking associated with it, so it + * can be inaccurate if operations are ongoing while this is called. However, it + * should still show the correct trend over the long-term. + * + * @param r A ringbuffer object. + * @return The number of bytes not yet consumed. + */ +LIBBPF_API size_t ring__avail_data_size(const struct ring *r); + +/** + * @brief **ring__size()** returns the total size of the ringbuffer's map data + * area (excluding special producer/consumer pages). Effectively this gives the + * amount of usable bytes of data inside the ringbuffer. + * + * @param r A ringbuffer object. + * @return The total size of the ringbuffer map data area. + */ +LIBBPF_API size_t ring__size(const struct ring *r); + +/** + * @brief **ring__map_fd()** returns the file descriptor underlying the given + * ringbuffer. + * + * @param r A ringbuffer object. + * @return The underlying ringbuffer file descriptor + */ +LIBBPF_API int ring__map_fd(const struct ring *r); + +/** + * @brief **ring__consume()** consumes available ringbuffer data without event + * polling. + * + * @param r A ringbuffer object. + * @return The number of records consumed (or INT_MAX, whichever is less), or + * a negative number if any of the callbacks return an error. + */ +LIBBPF_API int ring__consume(struct ring *r); + +/** + * @brief **ring__consume_n()** consumes up to a requested amount of items from + * a ringbuffer without event polling. + * + * @param r A ringbuffer object. + * @param n Maximum amount of items to consume. + * @return The number of items consumed, or a negative number if any of the + * callbacks return an error. + */ +LIBBPF_API int ring__consume_n(struct ring *r, size_t n); + struct user_ring_buffer_opts { size_t sz; /* size of this struct, for forward/backward compatibility */ }; #define user_ring_buffer_opts__last_field sz -/* @brief **user_ring_buffer__new()** creates a new instance of a user ring +/** + * @brief **user_ring_buffer__new()** creates a new instance of a user ring * buffer. * * @param map_fd A file descriptor to a BPF_MAP_TYPE_USER_RINGBUF map. @@ -1050,7 +1523,8 @@ struct user_ring_buffer_opts { LIBBPF_API struct user_ring_buffer * user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts); -/* @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the +/** + * @brief **user_ring_buffer__reserve()** reserves a pointer to a sample in the * user ring buffer. * @param rb A pointer to a user ring buffer. * @param size The size of the sample, in bytes. @@ -1070,7 +1544,8 @@ user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts); */ LIBBPF_API void *user_ring_buffer__reserve(struct user_ring_buffer *rb, __u32 size); -/* @brief **user_ring_buffer__reserve_blocking()** reserves a record in the +/** + * @brief **user_ring_buffer__reserve_blocking()** reserves a record in the * ring buffer, possibly blocking for up to @timeout_ms until a sample becomes * available. * @param rb The user ring buffer. @@ -1114,7 +1589,8 @@ LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, __u32 size, int timeout_ms); -/* @brief **user_ring_buffer__submit()** submits a previously reserved sample +/** + * @brief **user_ring_buffer__submit()** submits a previously reserved sample * into the ring buffer. * @param rb The user ring buffer. * @param sample A reserved sample. @@ -1124,7 +1600,8 @@ LIBBPF_API void *user_ring_buffer__reserve_blocking(struct user_ring_buffer *rb, */ LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *sample); -/* @brief **user_ring_buffer__discard()** discards a previously reserved sample. +/** + * @brief **user_ring_buffer__discard()** discards a previously reserved sample. * @param rb The user ring buffer. * @param sample A reserved sample. * @@ -1133,7 +1610,8 @@ LIBBPF_API void user_ring_buffer__submit(struct user_ring_buffer *rb, void *samp */ LIBBPF_API void user_ring_buffer__discard(struct user_ring_buffer *rb, void *sample); -/* @brief **user_ring_buffer__free()** frees a ring buffer that was previously +/** + * @brief **user_ring_buffer__free()** frees a ring buffer that was previously * created with **user_ring_buffer__new()**. * @param rb The user ring buffer being freed. */ @@ -1149,8 +1627,10 @@ typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); /* common use perf buffer options */ struct perf_buffer_opts { size_t sz; + __u32 sample_period; + size_t :0; }; -#define perf_buffer_opts__last_field sz +#define perf_buffer_opts__last_field sample_period /** * @brief **perf_buffer__new()** creates BPF perfbuf manager for a specified @@ -1161,6 +1641,7 @@ struct perf_buffer_opts { * @param sample_cb function called on each received data record * @param lost_cb function called when record loss has occurred * @param ctx user-provided extra context passed into *sample_cb* and *lost_cb* + * @param opts optional parameters for the perf buffer, can be null * @return a new instance of struct perf_buffer on success, NULL on error with * *errno* containing an error code */ @@ -1215,11 +1696,11 @@ LIBBPF_API int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_i * memory region of the ring buffer. * This ring buffer can be used to implement a custom events consumer. * The ring buffer starts with the *struct perf_event_mmap_page*, which - * holds the ring buffer managment fields, when accessing the header + * holds the ring buffer management fields, when accessing the header * structure it's important to be SMP aware. * You can refer to *perf_event_read_simple* for a simple example. * @param pb the perf buffer structure - * @param buf_idx the buffer index to retreive + * @param buf_idx the buffer index to retrieve * @param buf (out) gets the base pointer of the mmap()'ed memory * @param buf_size (out) gets the size of the mmap()'ed region * @return 0 on success, negative error code for failure @@ -1311,6 +1792,7 @@ struct bpf_map_skeleton { const char *name; struct bpf_map **map; void **mmaped; + struct bpf_link **link; }; struct bpf_prog_skeleton { @@ -1375,14 +1857,15 @@ LIBBPF_API void bpf_object__destroy_subskeleton(struct bpf_object_subskeleton *s); struct gen_loader_opts { - size_t sz; /* size of this struct, for forward/backward compatiblity */ + size_t sz; /* size of this struct, for forward/backward compatibility */ const char *data; const char *insns; __u32 data_sz; __u32 insns_sz; + bool gen_hash; }; -#define gen_loader_opts__last_field insns_sz +#define gen_loader_opts__last_field gen_hash LIBBPF_API int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts); @@ -1393,13 +1876,13 @@ enum libbpf_tristate { }; struct bpf_linker_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; }; #define bpf_linker_opts__last_field sz struct bpf_linker_file_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; }; #define bpf_linker_file_opts__last_field sz @@ -1407,9 +1890,14 @@ struct bpf_linker_file_opts { struct bpf_linker; LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts); +LIBBPF_API struct bpf_linker *bpf_linker__new_fd(int fd, struct bpf_linker_opts *opts); LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, const struct bpf_linker_file_opts *opts); +LIBBPF_API int bpf_linker__add_fd(struct bpf_linker *linker, int fd, + const struct bpf_linker_file_opts *opts); +LIBBPF_API int bpf_linker__add_buf(struct bpf_linker *linker, void *buf, size_t buf_sz, + const struct bpf_linker_file_opts *opts); LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker); LIBBPF_API void bpf_linker__free(struct bpf_linker *linker); @@ -1442,7 +1930,7 @@ typedef int (*libbpf_prog_attach_fn_t)(const struct bpf_program *prog, long cook struct bpf_link **link); struct libbpf_prog_handler_opts { - /* size of this struct, for forward/backward compatiblity */ + /* size of this struct, for forward/backward compatibility */ size_t sz; /* User-provided value that is passed to prog_setup_fn, * prog_prepare_load_fn, and prog_attach_fn callbacks. Allows user to diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 71bf5691a689..8ed8749907d4 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -245,7 +245,6 @@ LIBBPF_0.3.0 { btf__parse_raw_split; btf__parse_split; btf__new_empty_split; - btf__new_split; ring_buffer__epoll_fd; } LIBBPF_0.2.0; @@ -326,7 +325,6 @@ LIBBPF_0.7.0 { bpf_xdp_detach; bpf_xdp_query; bpf_xdp_query_id; - btf_ext__raw_data; libbpf_probe_bpf_helper; libbpf_probe_bpf_map_type; libbpf_probe_bpf_prog_type; @@ -382,3 +380,75 @@ LIBBPF_1.1.0 { user_ring_buffer__reserve_blocking; user_ring_buffer__submit; } LIBBPF_1.0.0; + +LIBBPF_1.2.0 { + global: + bpf_btf_get_info_by_fd; + bpf_link__update_map; + bpf_link_get_info_by_fd; + bpf_map_get_info_by_fd; + bpf_prog_get_info_by_fd; +} LIBBPF_1.1.0; + +LIBBPF_1.3.0 { + global: + bpf_obj_pin_opts; + bpf_object__unpin; + bpf_prog_detach_opts; + bpf_program__attach_netfilter; + bpf_program__attach_netkit; + bpf_program__attach_tcx; + bpf_program__attach_uprobe_multi; + ring__avail_data_size; + ring__consume; + ring__consumer_pos; + ring__map_fd; + ring__producer_pos; + ring__size; + ring_buffer__ring; +} LIBBPF_1.2.0; + +LIBBPF_1.4.0 { + global: + bpf_program__attach_raw_tracepoint_opts; + bpf_raw_tracepoint_open_opts; + bpf_token_create; + btf__new_split; + btf_ext__raw_data; +} LIBBPF_1.3.0; + +LIBBPF_1.5.0 { + global: + btf__distill_base; + btf__relocate; + btf_ext__endianness; + btf_ext__set_endianness; + bpf_map__autoattach; + bpf_map__set_autoattach; + bpf_object__token_fd; + bpf_program__attach_sockmap; + ring__consume_n; + ring_buffer__consume_n; +} LIBBPF_1.4.0; + +LIBBPF_1.6.0 { + global: + bpf_linker__add_buf; + bpf_linker__add_fd; + bpf_linker__new_fd; + bpf_object__prepare; + bpf_prog_stream_read; + bpf_program__attach_cgroup_opts; + bpf_program__func_info; + bpf_program__func_info_cnt; + bpf_program__line_info; + bpf_program__line_info_cnt; + btf__add_decl_attr; + btf__add_type_attr; +} LIBBPF_1.5.0; + +LIBBPF_1.7.0 { + global: + bpf_map__set_exclusive_program; + bpf_map__exclusive_program; +} LIBBPF_1.6.0; diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h index 9a7937f339df..8fe248e14eb6 100644 --- a/tools/lib/bpf/libbpf_common.h +++ b/tools/lib/bpf/libbpf_common.h @@ -70,4 +70,23 @@ }; \ }) +/* Helper macro to clear and optionally reinitialize libbpf options struct + * + * Small helper macro to reset all fields and to reinitialize the common + * structure size member. Values provided by users in struct initializer- + * syntax as varargs can be provided as well to reinitialize options struct + * specific members. + */ +#define LIBBPF_OPTS_RESET(NAME, ...) \ + do { \ + typeof(NAME) ___##NAME = ({ \ + memset(&___##NAME, 0, sizeof(NAME)); \ + (typeof(NAME)) { \ + .sz = sizeof(NAME), \ + __VA_ARGS__ \ + }; \ + }); \ + memcpy(&NAME, &___##NAME, sizeof(NAME)); \ + } while (0) + #endif /* __LIBBPF_LIBBPF_COMMON_H */ diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c deleted file mode 100644 index 96f67a772a1b..000000000000 --- a/tools/lib/bpf/libbpf_errno.c +++ /dev/null @@ -1,67 +0,0 @@ -// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) - -/* - * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> - * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> - * Copyright (C) 2015 Huawei Inc. - * Copyright (C) 2017 Nicira, Inc. - */ - -#undef _GNU_SOURCE -#include <stdio.h> -#include <string.h> - -#include "libbpf.h" -#include "libbpf_internal.h" - -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - -#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START) -#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c) -#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START) - -static const char *libbpf_strerror_table[NR_ERRNO] = { - [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf", - [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid", - [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost", - [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch", - [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf", - [ERRCODE_OFFSET(RELOC)] = "Relocation failed", - [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading", - [ERRCODE_OFFSET(PROG2BIG)] = "Program too big", - [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version", - [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type", - [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message", - [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence", - [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing", -}; - -int libbpf_strerror(int err, char *buf, size_t size) -{ - if (!buf || !size) - return libbpf_err(-EINVAL); - - err = err > 0 ? err : -err; - - if (err < __LIBBPF_ERRNO__START) { - int ret; - - ret = strerror_r(err, buf, size); - buf[size - 1] = '\0'; - return libbpf_err_errno(ret); - } - - if (err < __LIBBPF_ERRNO__END) { - const char *msg; - - msg = libbpf_strerror_table[ERRNO_OFFSET(err)]; - snprintf(buf, size, "%s", msg); - buf[size - 1] = '\0'; - return 0; - } - - snprintf(buf, size, "Unknown libbpf error %d", err); - buf[size - 1] = '\0'; - return libbpf_err(-ENOENT); -} diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 377642ff51fc..fc59b21b51b5 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -10,13 +10,30 @@ #define __LIBBPF_LIBBPF_INTERNAL_H #include <stdlib.h> +#include <byteswap.h> #include <limits.h> #include <errno.h> #include <linux/err.h> #include <fcntl.h> #include <unistd.h> +#include <sys/syscall.h> +#include <libelf.h> #include "relo_core.h" +/* Android's libc doesn't support AT_EACCESS in faccessat() implementation + * ([0]), and just returns -EINVAL even if file exists and is accessible. + * See [1] for issues caused by this. + * + * So just redefine it to 0 on Android. + * + * [0] https://android.googlesource.com/platform/bionic/+/refs/heads/android13-release/libc/bionic/faccessat.cpp#50 + * [1] https://github.com/libbpf/libbpf-bootstrap/issues/250#issuecomment-1911324250 + */ +#ifdef __ANDROID__ +#undef AT_EACCESS +#define AT_EACCESS 0 +#endif + /* make sure libbpf doesn't use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 @@ -57,6 +74,8 @@ #define ELF64_ST_VISIBILITY(o) ((o) & 0x03) #endif +#define JUMPTABLES_SEC ".jumptables" + #define BTF_INFO_ENC(kind, kind_flag, vlen) \ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) @@ -155,6 +174,16 @@ do { \ #define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) #define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) +/** + * @brief **libbpf_errstr()** returns string corresponding to numeric errno + * @param err negative numeric errno + * @return pointer to string representation of the errno, that is invalidated + * upon the next call. + */ +const char *libbpf_errstr(int err); + +#define errstr(err) libbpf_errstr(err) + #ifndef __has_builtin #define __has_builtin(x) 0 #endif @@ -218,6 +247,9 @@ struct btf_type; 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); +const struct btf_header *btf_header(const struct btf *btf); +void btf_set_base_btf(struct btf *btf, const struct btf *base_btf); +int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **id_map); static inline enum btf_func_linkage btf_func_linkage(const struct btf_type *t) { @@ -354,18 +386,42 @@ enum kern_feature_id { FEAT_BTF_ENUM64, /* Kernel uses syscall wrapper (CONFIG_ARCH_HAS_SYSCALL_WRAPPER) */ FEAT_SYSCALL_WRAPPER, + /* BPF multi-uprobe link support */ + FEAT_UPROBE_MULTI_LINK, + /* Kernel supports arg:ctx tag (__arg_ctx) for global subprogs natively */ + FEAT_ARG_CTX_TAG, + /* Kernel supports '?' at the front of datasec names */ + FEAT_BTF_QMARK_DATASEC, __FEAT_CNT, }; -int probe_memcg_account(void); +enum kern_feature_result { + FEAT_UNKNOWN = 0, + FEAT_SUPPORTED = 1, + FEAT_MISSING = 2, +}; + +struct kern_feature_cache { + enum kern_feature_result res[__FEAT_CNT]; + int token_fd; +}; + +bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id); bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); + +int probe_kern_syscall_wrapper(int token_fd); +int probe_memcg_account(int token_fd); 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); -int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level); + const char *str_sec, size_t str_len, + int token_fd); +int btf_load_into_kernel(struct btf *btf, + char *log_buf, size_t log_sz, __u32 log_level, + int token_fd); +struct btf *btf_load_from_kernel(__u32 id, struct btf *base_btf, int token_fd); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, @@ -406,11 +462,11 @@ struct btf_ext_info { * * The func_info subsection layout: * record size for struct bpf_func_info in the func_info subsection - * struct btf_sec_func_info for section #1 + * struct btf_ext_info_sec for section #1 * a list of bpf_func_info records for section #1 * where struct bpf_func_info mimics one in include/uapi/linux/bpf.h * but may not be identical - * struct btf_sec_func_info for section #2 + * struct btf_ext_info_sec for section #2 * a list of bpf_func_info records for section #2 * ...... * @@ -442,6 +498,8 @@ struct btf_ext { struct btf_ext_header *hdr; void *data; }; + void *data_swapped; + bool swapped_endian; struct btf_ext_info func_info; struct btf_ext_info line_info; struct btf_ext_info core_relo_info; @@ -469,21 +527,64 @@ struct bpf_line_info_min { __u32 line_col; }; +/* Functions to byte-swap info records */ + +typedef void (*info_rec_bswap_fn)(void *); + +static inline void bpf_func_info_bswap(struct bpf_func_info *i) +{ + i->insn_off = bswap_32(i->insn_off); + i->type_id = bswap_32(i->type_id); +} + +static inline void bpf_line_info_bswap(struct bpf_line_info *i) +{ + i->insn_off = bswap_32(i->insn_off); + i->file_name_off = bswap_32(i->file_name_off); + i->line_off = bswap_32(i->line_off); + i->line_col = bswap_32(i->line_col); +} + +static inline void bpf_core_relo_bswap(struct bpf_core_relo *i) +{ + i->insn_off = bswap_32(i->insn_off); + i->type_id = bswap_32(i->type_id); + i->access_str_off = bswap_32(i->access_str_off); + i->kind = bswap_32(i->kind); +} + +enum btf_field_iter_kind { + BTF_FIELD_ITER_IDS, + BTF_FIELD_ITER_STRS, +}; + +struct btf_field_desc { + /* once-per-type offsets */ + int t_off_cnt, t_offs[2]; + /* member struct size, or zero, if no members */ + int m_sz; + /* repeated per-member offsets */ + int m_off_cnt, m_offs[1]; +}; + +struct btf_field_iter { + struct btf_field_desc desc; + void *p; + int m_idx; + int off_idx; + int vlen; +}; + +int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, enum btf_field_iter_kind iter_kind); +__u32 *btf_field_iter_next(struct btf_field_iter *it); typedef int (*type_id_visit_fn)(__u32 *type_id, void *ctx); typedef int (*str_off_visit_fn)(__u32 *str_off, void *ctx); -int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx); -int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx); int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx); int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx); __s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name, __u32 kind); -typedef int (*kallsyms_cb_t)(unsigned long long sym_addr, char sym_type, - const char *sym_name, void *ctx); - -int libbpf_kallsyms_parse(kallsyms_cb_t cb, void *arg); - /* handle direct returned errors */ static inline int libbpf_err(int ret) { @@ -529,6 +630,27 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn) return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } +static inline void bpf_insn_bswap(struct bpf_insn *insn) +{ + __u8 tmp_reg = insn->dst_reg; + + insn->dst_reg = insn->src_reg; + insn->src_reg = tmp_reg; + insn->off = bswap_16(insn->off); + insn->imm = bswap_32(insn->imm); +} + +/* Unconditionally dup FD, ensuring it doesn't use [0, 2] range. + * Original FD is not closed or altered in any other way. + * Preserves original FD value, if it's invalid (negative). + */ +static inline int dup_good_fd(int fd) +{ + if (fd < 0) + return fd; + return fcntl(fd, F_DUPFD_CLOEXEC, 3); +} + /* if fd is stdin, stdout, or stderr, dup to a fd greater than 2 * Takes ownership of the fd passed in, and closes it if calling * fcntl(fd, F_DUPFD_CLOEXEC, 3). @@ -540,9 +662,10 @@ static inline int ensure_good_fd(int fd) if (fd < 0) return fd; if (fd < 3) { - fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); + fd = dup_good_fd(fd); saved_errno = errno; close(old_fd); + errno = saved_errno; if (fd < 0) { pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno); errno = saved_errno; @@ -551,6 +674,34 @@ static inline int ensure_good_fd(int fd) return fd; } +static inline int sys_dup3(int oldfd, int newfd, int flags) +{ + return syscall(__NR_dup3, oldfd, newfd, flags); +} + +/* Some versions of Android don't provide memfd_create() in their libc + * implementation, so avoid complications and just go straight to Linux + * syscall. + */ +static inline int sys_memfd_create(const char *name, unsigned flags) +{ + return syscall(__NR_memfd_create, name, flags); +} + +/* Point *fixed_fd* to the same file that *tmp_fd* points to. + * Regardless of success, *tmp_fd* is closed. + * Whatever *fixed_fd* pointed to is closed silently. + */ +static inline int reuse_fd(int fixed_fd, int tmp_fd) +{ + int err; + + err = sys_dup3(tmp_fd, fixed_fd, O_CLOEXEC); + err = err < 0 ? -errno : 0; + close(tmp_fd); /* clean up temporary FD */ + return err; +} + /* The following two functions are exposed to bpftool */ int bpf_core_add_cands(struct bpf_core_cand *local_cand, size_t local_essent_len, @@ -573,7 +724,37 @@ static inline bool is_pow_of_2(size_t x) return x && (x & (x - 1)) == 0; } +static inline __u32 ror32(__u32 v, int bits) +{ + return (v >> bits) | (v << (32 - bits)); +} + #define PROG_LOAD_ATTEMPTS 5 int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts); +bool glob_match(const char *str, const char *pat); + +long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name); +long elf_find_func_offset_from_file(const char *binary_path, const char *name); + +struct elf_fd { + Elf *elf; + int fd; +}; + +int elf_open(const char *binary_path, struct elf_fd *elf_fd); +void elf_close(struct elf_fd *elf_fd); + +int elf_resolve_syms_offsets(const char *binary_path, int cnt, + const char **syms, unsigned long **poffsets, + int st_type); +int elf_resolve_pattern_offsets(const char *binary_path, const char *pattern, + unsigned long **poffsets, size_t *pcnt); + +int probe_fd(int fd); + +#define SHA256_DIGEST_LENGTH 32 +#define SHA256_DWORD_SIZE SHA256_DIGEST_LENGTH / sizeof(__u64) + +void libbpf_sha256(const void *data, size_t len, __u8 out[SHA256_DIGEST_LENGTH]); #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index 1e1be467bede..60b2600be88a 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -76,7 +76,7 @@ enum libbpf_strict_mode { * first BPF program or map creation operation. This is done only if * kernel is too old to support memcg-based memory accounting for BPF * subsystem. By default, RLIMIT_MEMLOCK limit is set to RLIM_INFINITY, - * but it can be overriden with libbpf_set_memlock_rlim() API. + * but it can be overridden with libbpf_set_memlock_rlim() API. * Note that libbpf_set_memlock_rlim() needs to be called before * the very first bpf_prog_load(), bpf_map_create() or bpf_object__load() * operation. @@ -97,7 +97,7 @@ LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); * @brief **libbpf_get_error()** extracts the error code from the passed * pointer * @param ptr pointer returned from libbpf API function - * @return error code; or 0 if no error occured + * @return error code; or 0 if no error occurred * * Note, as of libbpf 1.0 this function is not necessary and not recommended * to be used. Libbpf doesn't return error code embedded into the pointer diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index b44fcbb4b42e..bccf4bb747e1 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -12,11 +12,94 @@ #include <linux/btf.h> #include <linux/filter.h> #include <linux/kernel.h> +#include <linux/version.h> #include "bpf.h" #include "libbpf.h" #include "libbpf_internal.h" +/* 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. + */ +static __u32 get_ubuntu_kernel_version(void) +{ + const char *ubuntu_kver_file = "/proc/version_signature"; + __u32 major, minor, patch; + int ret; + FILE *f; + + if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) != 0) + return 0; + + f = fopen(ubuntu_kver_file, "re"); + if (!f) + return 0; + + ret = fscanf(f, "%*s %*s %u.%u.%u\n", &major, &minor, &patch); + fclose(f); + if (ret != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + +/* On Debian LINUX_VERSION_CODE doesn't correspond to info.release. + * Instead, it is provided in info.version. An example content of + * Debian 10 looks like the below. + * + * utsname::release 4.19.0-22-amd64 + * utsname::version #1 SMP Debian 4.19.260-1 (2022-09-29) + * + * In the above, 4.19.260 is what kernel is actually expecting, while + * uname() call will return 4.19.0 in info.release. + */ +static __u32 get_debian_kernel_version(struct utsname *info) +{ + __u32 major, minor, patch; + char *p; + + p = strstr(info->version, "Debian "); + if (!p) { + /* This is not a Debian kernel. */ + return 0; + } + + if (sscanf(p, "Debian %u.%u.%u", &major, &minor, &patch) != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + +__u32 get_kernel_version(void) +{ + __u32 major, minor, patch, version; + struct utsname info; + + /* Check if this is an Ubuntu kernel. */ + version = get_ubuntu_kernel_version(); + if (version != 0) + return version; + + uname(&info); + + /* Check if this is a Debian kernel. */ + version = get_debian_kernel_version(&info); + if (version != 0) + return version; + + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + 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) @@ -98,6 +181,9 @@ static int probe_prog_load(enum bpf_prog_type prog_type, case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: break; + case BPF_PROG_TYPE_NETFILTER: + opts.expected_attach_type = BPF_NETFILTER; + break; default: return -EOPNOTSUPP; } @@ -133,7 +219,8 @@ int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts) } int libbpf__load_raw_btf(const char *raw_types, size_t types_len, - const char *str_sec, size_t str_len) + const char *str_sec, size_t str_len, + int token_fd) { struct btf_header hdr = { .magic = BTF_MAGIC, @@ -143,6 +230,10 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, .str_off = types_len, .str_len = str_len, }; + LIBBPF_OPTS(bpf_btf_load_opts, opts, + .token_fd = token_fd, + .btf_flags = token_fd ? BPF_F_TOKEN_FD : 0, + ); int btf_fd, btf_len; __u8 *raw_btf; @@ -155,7 +246,7 @@ 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_btf_load(raw_btf, btf_len, NULL); + btf_fd = bpf_btf_load(raw_btf, btf_len, &opts); free(raw_btf); return btf_fd; @@ -185,7 +276,7 @@ static int load_local_storage_btf(void) }; return libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs)); + strs, sizeof(strs), 0); } static int probe_map_create(enum bpf_map_type map_type) @@ -240,12 +331,20 @@ static int probe_map_create(enum bpf_map_type map_type) 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; + opts.value_type_btf_obj_fd = -1; exp_err = -524; /* -ENOTSUPP */ break; case BPF_MAP_TYPE_BLOOM_FILTER: key_size = 0; max_entries = 1; break; + case BPF_MAP_TYPE_ARENA: + key_size = 0; + value_size = 0; + max_entries = 1; /* one page */ + opts.map_extra = 0; /* can mmap() at any address */ + opts.map_flags = BPF_F_MMAPABLE; + break; case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PROG_ARRAY: @@ -265,6 +364,10 @@ static int probe_map_create(enum bpf_map_type map_type) case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: break; + case BPF_MAP_TYPE_INSN_ARRAY: + key_size = sizeof(__u32); + value_size = sizeof(struct bpf_insn_array_value); + break; case BPF_MAP_TYPE_UNSPEC: default: return -EOPNOTSUPP; @@ -349,7 +452,8 @@ int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helpe /* 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". + * given BPF program type, it will emit "unknown func bpf_sys_bpf#166" + * or "program of this type cannot use helper 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., @@ -358,7 +462,8 @@ int libbpf_probe_bpf_helper(enum bpf_prog_type prog_type, enum bpf_func_id helpe * 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 "))) + if (ret == 0 && (strstr(buf, "invalid func ") || strstr(buf, "unknown func ") || + strstr(buf, "program of this type cannot use helper "))) return 0; return 1; /* assume supported */ } diff --git a/tools/lib/bpf/libbpf_utils.c b/tools/lib/bpf/libbpf_utils.c new file mode 100644 index 000000000000..ac3beae54cf6 --- /dev/null +++ b/tools/lib/bpf/libbpf_utils.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + * Copyright (C) 2017 Nicira, Inc. + */ + +#undef _GNU_SOURCE +#include <stdio.h> +#include <string.h> +#include <errno.h> +#include <inttypes.h> +#include <linux/kernel.h> + +#include "libbpf.h" +#include "libbpf_internal.h" + +#ifndef ENOTSUPP +#define ENOTSUPP 524 +#endif + +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + +#define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START) +#define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c) +#define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START) + +static const char *libbpf_strerror_table[NR_ERRNO] = { + [ERRCODE_OFFSET(LIBELF)] = "Something wrong in libelf", + [ERRCODE_OFFSET(FORMAT)] = "BPF object format invalid", + [ERRCODE_OFFSET(KVERSION)] = "'version' section incorrect or lost", + [ERRCODE_OFFSET(ENDIAN)] = "Endian mismatch", + [ERRCODE_OFFSET(INTERNAL)] = "Internal error in libbpf", + [ERRCODE_OFFSET(RELOC)] = "Relocation failed", + [ERRCODE_OFFSET(VERIFY)] = "Kernel verifier blocks program loading", + [ERRCODE_OFFSET(PROG2BIG)] = "Program too big", + [ERRCODE_OFFSET(KVER)] = "Incorrect kernel version", + [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type", + [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message", + [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence", + [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing", +}; + +int libbpf_strerror(int err, char *buf, size_t size) +{ + int ret; + + if (!buf || !size) + return libbpf_err(-EINVAL); + + err = err > 0 ? err : -err; + + if (err < __LIBBPF_ERRNO__START) { + ret = strerror_r(err, buf, size); + buf[size - 1] = '\0'; + return libbpf_err_errno(ret); + } + + if (err < __LIBBPF_ERRNO__END) { + const char *msg; + + msg = libbpf_strerror_table[ERRNO_OFFSET(err)]; + ret = snprintf(buf, size, "%s", msg); + buf[size - 1] = '\0'; + /* The length of the buf and msg is positive. + * A negative number may be returned only when the + * size exceeds INT_MAX. Not likely to appear. + */ + if (ret >= size) + return libbpf_err(-ERANGE); + return 0; + } + + ret = snprintf(buf, size, "Unknown libbpf error %d", err); + buf[size - 1] = '\0'; + if (ret >= size) + return libbpf_err(-ERANGE); + return libbpf_err(-ENOENT); +} + +const char *libbpf_errstr(int err) +{ + static __thread char buf[12]; + + if (err > 0) + err = -err; + + switch (err) { + case -E2BIG: return "-E2BIG"; + case -EACCES: return "-EACCES"; + case -EADDRINUSE: return "-EADDRINUSE"; + case -EADDRNOTAVAIL: return "-EADDRNOTAVAIL"; + case -EAGAIN: return "-EAGAIN"; + case -EALREADY: return "-EALREADY"; + case -EBADF: return "-EBADF"; + case -EBADFD: return "-EBADFD"; + case -EBUSY: return "-EBUSY"; + case -ECANCELED: return "-ECANCELED"; + case -ECHILD: return "-ECHILD"; + case -EDEADLK: return "-EDEADLK"; + case -EDOM: return "-EDOM"; + case -EEXIST: return "-EEXIST"; + case -EFAULT: return "-EFAULT"; + case -EFBIG: return "-EFBIG"; + case -EILSEQ: return "-EILSEQ"; + case -EINPROGRESS: return "-EINPROGRESS"; + case -EINTR: return "-EINTR"; + case -EINVAL: return "-EINVAL"; + case -EIO: return "-EIO"; + case -EISDIR: return "-EISDIR"; + case -ELOOP: return "-ELOOP"; + case -EMFILE: return "-EMFILE"; + case -EMLINK: return "-EMLINK"; + case -EMSGSIZE: return "-EMSGSIZE"; + case -ENAMETOOLONG: return "-ENAMETOOLONG"; + case -ENFILE: return "-ENFILE"; + case -ENODATA: return "-ENODATA"; + case -ENODEV: return "-ENODEV"; + case -ENOENT: return "-ENOENT"; + case -ENOEXEC: return "-ENOEXEC"; + case -ENOLINK: return "-ENOLINK"; + case -ENOMEM: return "-ENOMEM"; + case -ENOSPC: return "-ENOSPC"; + case -ENOTBLK: return "-ENOTBLK"; + case -ENOTDIR: return "-ENOTDIR"; + case -ENOTSUPP: return "-ENOTSUPP"; + case -ENOTTY: return "-ENOTTY"; + case -ENXIO: return "-ENXIO"; + case -EOPNOTSUPP: return "-EOPNOTSUPP"; + case -EOVERFLOW: return "-EOVERFLOW"; + case -EPERM: return "-EPERM"; + case -EPIPE: return "-EPIPE"; + case -EPROTO: return "-EPROTO"; + case -EPROTONOSUPPORT: return "-EPROTONOSUPPORT"; + case -ERANGE: return "-ERANGE"; + case -EROFS: return "-EROFS"; + case -ESPIPE: return "-ESPIPE"; + case -ESRCH: return "-ESRCH"; + case -ETXTBSY: return "-ETXTBSY"; + case -EUCLEAN: return "-EUCLEAN"; + case -EXDEV: return "-EXDEV"; + default: + snprintf(buf, sizeof(buf), "%d", err); + return buf; + } +} + +static inline __u32 get_unaligned_be32(const void *p) +{ + __be32 val; + + memcpy(&val, p, sizeof(val)); + return be32_to_cpu(val); +} + +static inline void put_unaligned_be32(__u32 val, void *p) +{ + __be32 be_val = cpu_to_be32(val); + + memcpy(p, &be_val, sizeof(be_val)); +} + +#define SHA256_BLOCK_LENGTH 64 +#define Ch(x, y, z) (((x) & (y)) ^ (~(x) & (z))) +#define Maj(x, y, z) (((x) & (y)) ^ ((x) & (z)) ^ ((y) & (z))) +#define Sigma_0(x) (ror32((x), 2) ^ ror32((x), 13) ^ ror32((x), 22)) +#define Sigma_1(x) (ror32((x), 6) ^ ror32((x), 11) ^ ror32((x), 25)) +#define sigma_0(x) (ror32((x), 7) ^ ror32((x), 18) ^ ((x) >> 3)) +#define sigma_1(x) (ror32((x), 17) ^ ror32((x), 19) ^ ((x) >> 10)) + +static const __u32 sha256_K[64] = { + 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1, + 0x923f82a4, 0xab1c5ed5, 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, + 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174, 0xe49b69c1, 0xefbe4786, + 0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da, + 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147, + 0x06ca6351, 0x14292967, 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13, + 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85, 0xa2bfe8a1, 0xa81a664b, + 0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070, + 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a, + 0x5b9cca4f, 0x682e6ff3, 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208, + 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2, +}; + +#define SHA256_ROUND(i, a, b, c, d, e, f, g, h) \ + { \ + __u32 tmp = h + Sigma_1(e) + Ch(e, f, g) + sha256_K[i] + w[i]; \ + d += tmp; \ + h = tmp + Sigma_0(a) + Maj(a, b, c); \ + } + +static void sha256_blocks(__u32 state[8], const __u8 *data, size_t nblocks) +{ + while (nblocks--) { + __u32 a = state[0]; + __u32 b = state[1]; + __u32 c = state[2]; + __u32 d = state[3]; + __u32 e = state[4]; + __u32 f = state[5]; + __u32 g = state[6]; + __u32 h = state[7]; + __u32 w[64]; + int i; + + for (i = 0; i < 16; i++) + w[i] = get_unaligned_be32(&data[4 * i]); + for (; i < ARRAY_SIZE(w); i++) + w[i] = sigma_1(w[i - 2]) + w[i - 7] + + sigma_0(w[i - 15]) + w[i - 16]; + for (i = 0; i < ARRAY_SIZE(w); i += 8) { + SHA256_ROUND(i + 0, a, b, c, d, e, f, g, h); + SHA256_ROUND(i + 1, h, a, b, c, d, e, f, g); + SHA256_ROUND(i + 2, g, h, a, b, c, d, e, f); + SHA256_ROUND(i + 3, f, g, h, a, b, c, d, e); + SHA256_ROUND(i + 4, e, f, g, h, a, b, c, d); + SHA256_ROUND(i + 5, d, e, f, g, h, a, b, c); + SHA256_ROUND(i + 6, c, d, e, f, g, h, a, b); + SHA256_ROUND(i + 7, b, c, d, e, f, g, h, a); + } + state[0] += a; + state[1] += b; + state[2] += c; + state[3] += d; + state[4] += e; + state[5] += f; + state[6] += g; + state[7] += h; + data += SHA256_BLOCK_LENGTH; + } +} + +void libbpf_sha256(const void *data, size_t len, __u8 out[SHA256_DIGEST_LENGTH]) +{ + __u32 state[8] = { 0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a, + 0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19 }; + const __be64 bitcount = cpu_to_be64((__u64)len * 8); + __u8 final_data[2 * SHA256_BLOCK_LENGTH] = { 0 }; + size_t final_len = len % SHA256_BLOCK_LENGTH; + int i; + + sha256_blocks(state, data, len / SHA256_BLOCK_LENGTH); + + memcpy(final_data, data + len - final_len, final_len); + final_data[final_len] = 0x80; + final_len = roundup(final_len + 9, SHA256_BLOCK_LENGTH); + memcpy(&final_data[final_len - 8], &bitcount, 8); + + sha256_blocks(state, final_data, final_len / SHA256_BLOCK_LENGTH); + + for (i = 0; i < ARRAY_SIZE(state); i++) + put_unaligned_be32(state[i], &out[4 * i]); +} diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index e944f5bce728..99331e317dee 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 1 -#define LIBBPF_MINOR_VERSION 1 +#define LIBBPF_MINOR_VERSION 7 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 4ac02c28e152..f4403e3cf994 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -4,6 +4,10 @@ * * Copyright (c) 2021 Facebook */ +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif + #include <stdbool.h> #include <stddef.h> #include <stdio.h> @@ -16,6 +20,7 @@ #include <elf.h> #include <libelf.h> #include <fcntl.h> +#include <sys/mman.h> #include "libbpf.h" #include "btf.h" #include "libbpf_internal.h" @@ -135,6 +140,7 @@ struct bpf_linker { int fd; Elf *elf; Elf64_Ehdr *elf_hdr; + bool swapped_endian; /* Output sections metadata */ struct dst_sec *secs; @@ -150,15 +156,19 @@ struct bpf_linker { /* global (including extern) ELF symbols */ int glob_sym_cnt; struct glob_sym *glob_syms; + + bool fd_is_owned; }; #define pr_warn_elf(fmt, ...) \ libbpf_print(LIBBPF_WARN, "libbpf: " fmt ": %s\n", ##__VA_ARGS__, elf_errmsg(-1)) -static int init_output_elf(struct bpf_linker *linker, const char *file); +static int init_output_elf(struct bpf_linker *linker); + +static int bpf_linker_add_file(struct bpf_linker *linker, int fd, + const char *filename); -static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, - const struct bpf_linker_file_opts *opts, +static int linker_load_obj_file(struct bpf_linker *linker, struct src_obj *obj); static int linker_sanity_check_elf(struct src_obj *obj); static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec); @@ -189,7 +199,7 @@ void bpf_linker__free(struct bpf_linker *linker) if (linker->elf) elf_end(linker->elf); - if (linker->fd >= 0) + if (linker->fd >= 0 && linker->fd_is_owned) close(linker->fd); strset__free(linker->strtab_strs); @@ -231,9 +241,63 @@ struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts if (!linker) return errno = ENOMEM, NULL; - linker->fd = -1; + linker->filename = strdup(filename); + if (!linker->filename) { + err = -ENOMEM; + goto err_out; + } - err = init_output_elf(linker, filename); + linker->fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644); + if (linker->fd < 0) { + err = -errno; + pr_warn("failed to create '%s': %d\n", filename, err); + goto err_out; + } + linker->fd_is_owned = true; + + err = init_output_elf(linker); + if (err) + goto err_out; + + return linker; + +err_out: + bpf_linker__free(linker); + return errno = -err, NULL; +} + +struct bpf_linker *bpf_linker__new_fd(int fd, struct bpf_linker_opts *opts) +{ + struct bpf_linker *linker; + char filename[32]; + int err; + + if (fd < 0) + return errno = EINVAL, NULL; + + if (!OPTS_VALID(opts, bpf_linker_opts)) + return errno = EINVAL, NULL; + + if (elf_version(EV_CURRENT) == EV_NONE) { + pr_warn_elf("libelf initialization failed"); + return errno = EINVAL, NULL; + } + + linker = calloc(1, sizeof(*linker)); + if (!linker) + return errno = ENOMEM, NULL; + + snprintf(filename, sizeof(filename), "fd:%d", fd); + linker->filename = strdup(filename); + if (!linker->filename) { + err = -ENOMEM; + goto err_out; + } + + linker->fd = fd; + linker->fd_is_owned = false; + + err = init_output_elf(linker); if (err) goto err_out; @@ -292,23 +356,12 @@ static Elf64_Sym *add_new_sym(struct bpf_linker *linker, size_t *sym_idx) return sym; } -static int init_output_elf(struct bpf_linker *linker, const char *file) +static int init_output_elf(struct bpf_linker *linker) { int err, str_off; Elf64_Sym *init_sym; struct dst_sec *sec; - linker->filename = strdup(file); - if (!linker->filename) - return -ENOMEM; - - linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644); - if (linker->fd < 0) { - err = -errno; - pr_warn("failed to create '%s': %d\n", file, err); - return err; - } - linker->elf = elf_begin(linker->fd, ELF_C_WRITE, NULL); if (!linker->elf) { pr_warn_elf("failed to create ELF object"); @@ -324,13 +377,8 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) linker->elf_hdr->e_machine = EM_BPF; linker->elf_hdr->e_type = ET_REL; -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ - linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB; -#else -#error "Unknown __BYTE_ORDER__" -#endif + /* Set unknown ELF endianness, assign later from input files */ + linker->elf_hdr->e_ident[EI_DATA] = ELFDATANONE; /* STRTAB */ /* initialize strset with an empty string to conform to ELF */ @@ -396,6 +444,8 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) pr_warn_elf("failed to create SYMTAB data"); return -EINVAL; } + /* Ensure libelf translates byte-order of symbol records */ + sec->data->d_type = ELF_T_SYM; str_off = strset__add_str(linker->strtab_strs, sec->sec_name); if (str_off < 0) @@ -437,19 +487,16 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) return 0; } -int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, - const struct bpf_linker_file_opts *opts) +static int bpf_linker_add_file(struct bpf_linker *linker, int fd, + const char *filename) { struct src_obj obj = {}; int err = 0; - if (!OPTS_VALID(opts, bpf_linker_file_opts)) - return libbpf_err(-EINVAL); - - if (!linker->elf) - return libbpf_err(-EINVAL); + obj.filename = filename; + obj.fd = fd; - err = err ?: linker_load_obj_file(linker, filename, opts, &obj); + err = err ?: linker_load_obj_file(linker, &obj); err = err ?: linker_append_sec_data(linker, &obj); err = err ?: linker_append_elf_syms(linker, &obj); err = err ?: linker_append_elf_relos(linker, &obj); @@ -464,12 +511,91 @@ int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, free(obj.sym_map); if (obj.elf) elf_end(obj.elf); - if (obj.fd >= 0) - close(obj.fd); + return err; +} + +int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts) +{ + int fd, err; + + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); + + if (!linker->elf) + return libbpf_err(-EINVAL); + + fd = open(filename, O_RDONLY | O_CLOEXEC); + if (fd < 0) { + err = -errno; + pr_warn("failed to open file '%s': %s\n", filename, errstr(err)); + return libbpf_err(err); + } + + err = bpf_linker_add_file(linker, fd, filename); + close(fd); return libbpf_err(err); } +int bpf_linker__add_fd(struct bpf_linker *linker, int fd, + const struct bpf_linker_file_opts *opts) +{ + char filename[32]; + int err; + + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); + + if (!linker->elf) + return libbpf_err(-EINVAL); + + if (fd < 0) + return libbpf_err(-EINVAL); + + snprintf(filename, sizeof(filename), "fd:%d", fd); + err = bpf_linker_add_file(linker, fd, filename); + return libbpf_err(err); +} + +int bpf_linker__add_buf(struct bpf_linker *linker, void *buf, size_t buf_sz, + const struct bpf_linker_file_opts *opts) +{ + char filename[32]; + int fd, written, ret; + + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); + + if (!linker->elf) + return libbpf_err(-EINVAL); + + snprintf(filename, sizeof(filename), "mem:%p+%zu", buf, buf_sz); + + fd = sys_memfd_create(filename, 0); + if (fd < 0) { + ret = -errno; + pr_warn("failed to create memfd '%s': %s\n", filename, errstr(ret)); + return libbpf_err(ret); + } + + written = 0; + while (written < buf_sz) { + ret = write(fd, buf, buf_sz); + if (ret < 0) { + ret = -errno; + pr_warn("failed to write '%s': %s\n", filename, errstr(ret)); + goto err_out; + } + written += ret; + } + + ret = bpf_linker_add_file(linker, fd, filename); +err_out: + close(fd); + return libbpf_err(ret); +} + static bool is_dwarf_sec_name(const char *name) { /* approximation, but the actual list is too long */ @@ -535,65 +661,69 @@ static struct src_sec *add_src_sec(struct src_obj *obj, const char *sec_name) return sec; } -static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, - const struct bpf_linker_file_opts *opts, +static int linker_load_obj_file(struct bpf_linker *linker, struct src_obj *obj) { -#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ - const int host_endianness = ELFDATA2LSB; -#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ - const int host_endianness = ELFDATA2MSB; -#else -#error "Unknown __BYTE_ORDER__" -#endif int err = 0; Elf_Scn *scn; Elf_Data *data; Elf64_Ehdr *ehdr; Elf64_Shdr *shdr; struct src_sec *sec; + unsigned char obj_byteorder; + unsigned char link_byteorder = linker->elf_hdr->e_ident[EI_DATA]; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + const unsigned char host_byteorder = ELFDATA2LSB; +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + const unsigned char host_byteorder = ELFDATA2MSB; +#else +#error "Unknown __BYTE_ORDER__" +#endif - pr_debug("linker: adding object file '%s'...\n", filename); - - obj->filename = filename; + pr_debug("linker: adding object file '%s'...\n", obj->filename); - obj->fd = open(filename, O_RDONLY | O_CLOEXEC); - if (obj->fd < 0) { - err = -errno; - pr_warn("failed to open file '%s': %d\n", filename, err); - return err; - } obj->elf = elf_begin(obj->fd, ELF_C_READ_MMAP, NULL); if (!obj->elf) { - err = -errno; - pr_warn_elf("failed to parse ELF file '%s'", filename); - return err; + pr_warn_elf("failed to parse ELF file '%s'", obj->filename); + return -EINVAL; } /* Sanity check ELF file high-level properties */ ehdr = elf64_getehdr(obj->elf); if (!ehdr) { - err = -errno; - pr_warn_elf("failed to get ELF header for %s", filename); + pr_warn_elf("failed to get ELF header for %s", obj->filename); + return -EINVAL; + } + + /* Linker output endianness set by first input object */ + obj_byteorder = ehdr->e_ident[EI_DATA]; + if (obj_byteorder != ELFDATA2LSB && obj_byteorder != ELFDATA2MSB) { + err = -EOPNOTSUPP; + pr_warn("unknown byte order of ELF file %s\n", obj->filename); return err; } - if (ehdr->e_ident[EI_DATA] != host_endianness) { + if (link_byteorder == ELFDATANONE) { + linker->elf_hdr->e_ident[EI_DATA] = obj_byteorder; + linker->swapped_endian = obj_byteorder != host_byteorder; + pr_debug("linker: set %s-endian output byte order\n", + obj_byteorder == ELFDATA2MSB ? "big" : "little"); + } else if (link_byteorder != obj_byteorder) { err = -EOPNOTSUPP; - pr_warn_elf("unsupported byte order of ELF file %s", filename); + pr_warn("byte order mismatch with ELF file %s\n", obj->filename); return err; } + if (ehdr->e_type != ET_REL || ehdr->e_machine != EM_BPF || ehdr->e_ident[EI_CLASS] != ELFCLASS64) { err = -EOPNOTSUPP; - pr_warn_elf("unsupported kind of ELF file %s", filename); + pr_warn_elf("unsupported kind of ELF file %s", obj->filename); return err; } if (elf_getshdrstrndx(obj->elf, &obj->shstrs_sec_idx)) { - err = -errno; - pr_warn_elf("failed to get SHSTRTAB section index for %s", filename); - return err; + pr_warn_elf("failed to get SHSTRTAB section index for %s", obj->filename); + return -EINVAL; } scn = NULL; @@ -603,26 +733,23 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, shdr = elf64_getshdr(scn); if (!shdr) { - err = -errno; pr_warn_elf("failed to get section #%zu header for %s", - sec_idx, filename); - return err; + sec_idx, obj->filename); + return -EINVAL; } sec_name = elf_strptr(obj->elf, obj->shstrs_sec_idx, shdr->sh_name); if (!sec_name) { - err = -errno; pr_warn_elf("failed to get section #%zu name for %s", - sec_idx, filename); - return err; + sec_idx, obj->filename); + return -EINVAL; } data = elf_getdata(scn, 0); if (!data) { - err = -errno; pr_warn_elf("failed to get section #%zu (%s) data from %s", - sec_idx, sec_name, filename); - return err; + sec_idx, sec_name, obj->filename); + return -EINVAL; } sec = add_src_sec(obj, sec_name); @@ -656,7 +783,8 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, obj->btf = btf__new(data->d_buf, shdr->sh_size); err = libbpf_get_error(obj->btf); if (err) { - pr_warn("failed to parse .BTF from %s: %d\n", filename, err); + pr_warn("failed to parse .BTF from %s: %s\n", + obj->filename, errstr(err)); return err; } sec->skipped = true; @@ -666,7 +794,8 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, obj->btf_ext = btf_ext__new(data->d_buf, shdr->sh_size); err = libbpf_get_error(obj->btf_ext); if (err) { - pr_warn("failed to parse .BTF.ext from '%s': %d\n", filename, err); + pr_warn("failed to parse .BTF.ext from '%s': %s\n", + obj->filename, errstr(err)); return err; } sec->skipped = true; @@ -683,7 +812,7 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, break; default: pr_warn("unrecognized section #%zu (%s) in %s\n", - sec_idx, sec_name, filename); + sec_idx, sec_name, obj->filename); err = -EINVAL; return err; } @@ -719,13 +848,28 @@ static int linker_sanity_check_elf(struct src_obj *obj) return -EINVAL; } - if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) + if (is_dwarf_sec_name(sec->sec_name)) + continue; + + if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) { + pr_warn("ELF section #%zu alignment %llu is non pow-of-2 alignment in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign, + obj->filename); return -EINVAL; - if (sec->shdr->sh_addralign != sec->data->d_align) + } + if (sec->shdr->sh_addralign != sec->data->d_align) { + pr_warn("ELF section #%zu has inconsistent alignment addr=%llu != d=%llu in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign, + (long long unsigned)sec->data->d_align, obj->filename); return -EINVAL; + } - if (sec->shdr->sh_size != sec->data->d_size) + if (sec->shdr->sh_size != sec->data->d_size) { + pr_warn("ELF section #%zu has inconsistent section size sh=%llu != d=%llu in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_size, + (long long unsigned)sec->data->d_size, obj->filename); return -EINVAL; + } switch (sec->shdr->sh_type) { case SHT_SYMTAB: @@ -737,8 +881,12 @@ static int linker_sanity_check_elf(struct src_obj *obj) break; case SHT_PROGBITS: if (sec->shdr->sh_flags & SHF_EXECINSTR) { - if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) + if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) { + pr_warn("ELF section #%zu has unexpected size alignment %llu in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_size, + obj->filename); return -EINVAL; + } } break; case SHT_NOBITS: @@ -938,19 +1086,33 @@ static int check_btf_str_off(__u32 *str_off, void *ctx) static int linker_sanity_check_btf(struct src_obj *obj) { struct btf_type *t; - int i, n, err = 0; + int i, n, err; if (!obj->btf) return 0; n = btf__type_cnt(obj->btf); for (i = 1; i < n; i++) { + struct btf_field_iter it; + __u32 *type_id, *str_off; + t = btf_type_by_id(obj->btf, i); - err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf); - err = err ?: btf_type_visit_str_offs(t, check_btf_str_off, obj->btf); + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_IDS); + if (err) + return err; + while ((type_id = btf_field_iter_next(&it))) { + if (*type_id >= n) + return -EINVAL; + } + + err = btf_field_iter_init(&it, t, BTF_FIELD_ITER_STRS); if (err) return err; + while ((str_off = btf_field_iter_next(&it))) { + if (!btf__str_by_offset(obj->btf, *str_off)) + return -EINVAL; + } } return 0; @@ -1076,6 +1238,24 @@ static bool sec_content_is_same(struct dst_sec *dst_sec, struct src_sec *src_sec return true; } +static bool is_exec_sec(struct dst_sec *sec) +{ + if (!sec || sec->ephemeral) + return false; + return (sec->shdr->sh_type == SHT_PROGBITS) && + (sec->shdr->sh_flags & SHF_EXECINSTR); +} + +static void exec_sec_bswap(void *raw_data, int size) +{ + const int insn_cnt = size / sizeof(struct bpf_insn); + struct bpf_insn *insn = raw_data; + int i; + + for (i = 0; i < insn_cnt; i++, insn++) + bpf_insn_bswap(insn); +} + static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src_sec *src) { void *tmp; @@ -1115,7 +1295,19 @@ static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src if (src->shdr->sh_type != SHT_NOBITS) { tmp = realloc(dst->raw_data, dst_final_sz); - if (!tmp) + /* If dst_align_sz == 0, realloc() behaves in a special way: + * 1. When dst->raw_data is NULL it returns: + * "either NULL or a pointer suitable to be passed to free()" [1]. + * 2. When dst->raw_data is not-NULL it frees dst->raw_data and returns NULL, + * thus invalidating any "pointer suitable to be passed to free()" obtained + * at step (1). + * + * The dst_align_sz > 0 check avoids error exit after (2), otherwise + * dst->raw_data would be freed again in bpf_linker__free(). + * + * [1] man 3 realloc + */ + if (!tmp && dst_align_sz > 0) return -ENOMEM; dst->raw_data = tmp; @@ -1123,6 +1315,10 @@ static int extend_sec(struct bpf_linker *linker, struct dst_sec *dst, struct src memset(dst->raw_data + dst->sec_sz, 0, dst_align_sz - dst->sec_sz); /* now copy src data at a properly aligned offset */ memcpy(dst->raw_data + dst_align_sz, src->data->d_buf, src->shdr->sh_size); + + /* convert added bpf insns to native byte-order */ + if (linker->swapped_endian && is_exec_sec(dst)) + exec_sec_bswap(dst->raw_data + dst_align_sz, src->shdr->sh_size); } dst->sec_sz = dst_final_sz; @@ -1179,7 +1375,7 @@ static int linker_append_sec_data(struct bpf_linker *linker, struct src_obj *obj } else { if (!secs_match(dst_sec, src_sec)) { pr_warn("ELF sections %s are incompatible\n", src_sec->sec_name); - return -1; + return -EINVAL; } /* "license" and "version" sections are deduped */ @@ -1368,7 +1564,7 @@ recur: return true; case BTF_KIND_PTR: /* just validate overall shape of the referenced type, so no - * contents comparison for struct/union, and allowd fwd vs + * contents comparison for struct/union, and allowed fwd vs * struct/union */ exact = false; @@ -1829,6 +2025,9 @@ static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj, obj->sym_map[src_sym_idx] = dst_sec->sec_sym_idx; return 0; } + + if (strcmp(src_sec->sec_name, JUMPTABLES_SEC) == 0) + goto add_sym; } if (sym_bind == STB_LOCAL) @@ -1917,7 +2116,7 @@ static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj, /* If existing symbol is a strong resolved symbol, bail out, * because we lost resolution battle have nothing to - * contribute. We already checked abover that there is no + * contribute. We already checked above that there is no * strong-strong conflict. We also already tightened binding * and visibility, so nothing else to contribute at that point. */ @@ -1966,7 +2165,7 @@ add_sym: obj->sym_map[src_sym_idx] = dst_sym_idx; - if (sym_type == STT_SECTION && dst_sym) { + if (sym_type == STT_SECTION && dst_sec) { dst_sec->sec_sym_idx = dst_sym_idx; dst_sym->st_value = 0; } @@ -1997,7 +2196,6 @@ 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; int i, err; for (i = 1; i < obj->sec_cnt; i++) { @@ -2027,12 +2225,9 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob } } else if (!secs_match(dst_sec, src_sec)) { pr_warn("sections %s are not compatible\n", src_sec->sec_name); - return -1; + return -EINVAL; } - /* 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; @@ -2049,16 +2244,13 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob dst_rel = dst_sec->raw_data + src_sec->dst_off; n = src_sec->shdr->sh_size / src_sec->shdr->sh_entsize; for (j = 0; j < n; j++, src_rel++, dst_rel++) { - size_t src_sym_idx = ELF64_R_SYM(src_rel->r_info); - size_t sym_type = ELF64_R_TYPE(src_rel->r_info); - Elf64_Sym *src_sym, *dst_sym; - size_t dst_sym_idx; + size_t src_sym_idx, dst_sym_idx, sym_type; + Elf64_Sym *src_sym; src_sym_idx = ELF64_R_SYM(src_rel->r_info); src_sym = src_symtab->data->d_buf + sizeof(*src_sym) * src_sym_idx; dst_sym_idx = obj->sym_map[src_sym_idx]; - dst_sym = dst_symtab->raw_data + sizeof(*dst_sym) * dst_sym_idx; dst_rel->r_offset += src_linked_sec->dst_off; sym_type = ELF64_R_TYPE(src_rel->r_info); dst_rel->r_info = ELF64_R_INFO(dst_sym_idx, sym_type); @@ -2189,10 +2381,17 @@ static int linker_fixup_btf(struct src_obj *obj) vi = btf_var_secinfos(t); for (j = 0, m = btf_vlen(t); j < m; j++, vi++) { const struct btf_type *vt = btf__type_by_id(obj->btf, vi->type); - const char *var_name = btf__str_by_offset(obj->btf, vt->name_off); - int var_linkage = btf_var(vt)->linkage; + const char *var_name; + int var_linkage; Elf64_Sym *sym; + /* could be a variable or function */ + if (!btf_is_var(vt)) + continue; + + var_name = btf__str_by_offset(obj->btf, vt->name_off); + var_linkage = btf_var(vt)->linkage; + /* no need to patch up static or extern vars */ if (var_linkage != BTF_VAR_GLOBAL_ALLOCATED) continue; @@ -2210,26 +2409,10 @@ static int linker_fixup_btf(struct src_obj *obj) return 0; } -static int remap_type_id(__u32 *type_id, void *ctx) -{ - int *id_map = ctx; - int new_id = id_map[*type_id]; - - /* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */ - if (new_id == 0 && *type_id != 0) { - pr_warn("failed to find new ID mapping for original BTF type ID %u\n", *type_id); - return -EINVAL; - } - - *type_id = id_map[*type_id]; - - return 0; -} - static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) { const struct btf_type *t; - int i, j, n, start_id, id; + int i, j, n, start_id, id, err; const char *name; if (!obj->btf) @@ -2300,9 +2483,25 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) n = btf__type_cnt(linker->btf); for (i = start_id; i < n; i++) { struct btf_type *dst_t = btf_type_by_id(linker->btf, i); + struct btf_field_iter it; + __u32 *type_id; - if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map)) - return -EINVAL; + err = btf_field_iter_init(&it, dst_t, BTF_FIELD_ITER_IDS); + if (err) + return err; + + while ((type_id = btf_field_iter_next(&it))) { + int new_id = obj->btf_type_map[*type_id]; + + /* Error out if the type wasn't remapped. Ignore VOID which stays VOID. */ + if (new_id == 0 && *type_id != 0) { + pr_warn("failed to find new ID mapping for original BTF type ID %u\n", + *type_id); + return -EINVAL; + } + + *type_id = obj->btf_type_map[*type_id]; + } } /* Rewrite VAR/FUNC underlying types (i.e., FUNC's FUNC_PROTO and VAR's @@ -2370,6 +2569,10 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj) if (glob_sym && glob_sym->var_idx >= 0) { __s64 sz; + /* FUNCs don't have size, nothing to update */ + if (btf_is_func(t)) + continue; + dst_var = &dst_sec->sec_vars[glob_sym->var_idx]; /* Because underlying BTF type might have * changed, so might its size have changed, so @@ -2583,27 +2786,32 @@ int bpf_linker__finalize(struct bpf_linker *linker) if (!sec->scn) continue; + /* restore sections with bpf insns to target byte-order */ + if (linker->swapped_endian && is_exec_sec(sec)) + exec_sec_bswap(sec->raw_data, sec->sec_sz); + sec->data->d_buf = sec->raw_data; } /* Finalize ELF layout */ if (elf_update(linker->elf, ELF_C_NULL) < 0) { - err = -errno; + err = -EINVAL; pr_warn_elf("failed to finalize ELF layout"); return libbpf_err(err); } /* Write out final ELF contents */ if (elf_update(linker->elf, ELF_C_WRITE) < 0) { - err = -errno; + err = -EINVAL; pr_warn_elf("failed to write ELF contents"); return libbpf_err(err); } elf_end(linker->elf); - close(linker->fd); - linker->elf = NULL; + + if (linker->fd_is_owned) + close(linker->fd); linker->fd = -1; return 0; @@ -2651,6 +2859,7 @@ static int emit_elf_data_sec(struct bpf_linker *linker, const char *sec_name, static int finalize_btf(struct bpf_linker *linker) { + enum btf_endianness link_endianness; LIBBPF_OPTS(btf_dedup_opts, opts); struct btf *btf = linker->btf; const void *raw_data; @@ -2684,17 +2893,24 @@ static int finalize_btf(struct bpf_linker *linker) err = finalize_btf_ext(linker); if (err) { - pr_warn(".BTF.ext generation failed: %d\n", err); + pr_warn(".BTF.ext generation failed: %s\n", errstr(err)); return err; } opts.btf_ext = linker->btf_ext; err = btf__dedup(linker->btf, &opts); if (err) { - pr_warn("BTF dedup failed: %d\n", err); + pr_warn("BTF dedup failed: %s\n", errstr(err)); return err; } + /* Set .BTF and .BTF.ext output byte order */ + link_endianness = linker->elf_hdr->e_ident[EI_DATA] == ELFDATA2MSB ? + BTF_BIG_ENDIAN : BTF_LITTLE_ENDIAN; + btf__set_endianness(linker->btf, link_endianness); + if (linker->btf_ext) + btf_ext__set_endianness(linker->btf_ext, link_endianness); + /* Emit .BTF section */ raw_data = btf__raw_data(linker->btf, &raw_sz); if (!raw_data) @@ -2702,19 +2918,19 @@ static int finalize_btf(struct bpf_linker *linker) err = emit_elf_data_sec(linker, BTF_ELF_SEC, 8, raw_data, raw_sz); if (err) { - pr_warn("failed to write out .BTF ELF section: %d\n", err); + pr_warn("failed to write out .BTF ELF section: %s\n", errstr(err)); return err; } /* Emit .BTF.ext section */ if (linker->btf_ext) { - raw_data = btf_ext__get_raw_data(linker->btf_ext, &raw_sz); + raw_data = btf_ext__raw_data(linker->btf_ext, &raw_sz); if (!raw_data) return -ENOMEM; err = emit_elf_data_sec(linker, BTF_EXT_ELF_SEC, 8, raw_data, raw_sz); if (err) { - pr_warn("failed to write out .BTF.ext ELF section: %d\n", err); + pr_warn("failed to write out .BTF.ext ELF section: %s\n", errstr(err)); return err; } } @@ -2890,7 +3106,7 @@ static int finalize_btf_ext(struct bpf_linker *linker) err = libbpf_get_error(linker->btf_ext); if (err) { linker->btf_ext = NULL; - pr_warn("failed to parse final .BTF.ext data: %d\n", err); + pr_warn("failed to parse final .BTF.ext data: %s\n", errstr(err)); goto out; } diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 35104580870c..c997e69d507f 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -9,6 +9,7 @@ #include <linux/if_ether.h> #include <linux/pkt_cls.h> #include <linux/rtnetlink.h> +#include <linux/netdev.h> #include <sys/socket.h> #include <errno.h> #include <time.h> @@ -39,9 +40,16 @@ struct xdp_id_md { int ifindex; __u32 flags; struct xdp_link_info info; + __u64 feature_flags; }; -static int libbpf_netlink_open(__u32 *nl_pid) +struct xdp_features_md { + int ifindex; + __u32 xdp_zc_max_segs; + __u64 flags; +}; + +static int libbpf_netlink_open(__u32 *nl_pid, int proto) { struct sockaddr_nl sa; socklen_t addrlen; @@ -51,7 +59,7 @@ static int libbpf_netlink_open(__u32 *nl_pid) memset(&sa, 0, sizeof(sa)); sa.nl_family = AF_NETLINK; - sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE); + sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, proto); if (sock < 0) return -errno; @@ -212,14 +220,14 @@ done: } static int libbpf_netlink_send_recv(struct libbpf_nla_req *req, - __dump_nlmsg_t parse_msg, + int proto, __dump_nlmsg_t parse_msg, libbpf_dump_nlmsg_t parse_attr, void *cookie) { __u32 nl_pid = 0; int sock, ret; - sock = libbpf_netlink_open(&nl_pid); + sock = libbpf_netlink_open(&nl_pid, proto); if (sock < 0) return sock; @@ -238,6 +246,43 @@ out: return ret; } +static int parse_genl_family_id(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct genlmsghdr *gnl = NLMSG_DATA(nh); + struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN); + struct nlattr *tb[CTRL_ATTR_FAMILY_ID + 1]; + __u16 *id = cookie; + + libbpf_nla_parse(tb, CTRL_ATTR_FAMILY_ID, na, + NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL); + if (!tb[CTRL_ATTR_FAMILY_ID]) + return NL_CONT; + + *id = libbpf_nla_getattr_u16(tb[CTRL_ATTR_FAMILY_ID]); + return NL_DONE; +} + +static int libbpf_netlink_resolve_genl_family_id(const char *name, + __u16 len, __u16 *id) +{ + struct libbpf_nla_req req = { + .nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN), + .nh.nlmsg_type = GENL_ID_CTRL, + .nh.nlmsg_flags = NLM_F_REQUEST, + .gnl.cmd = CTRL_CMD_GETFAMILY, + .gnl.version = 2, + }; + int err; + + err = nlattr_add(&req, CTRL_ATTR_FAMILY_NAME, name, len); + if (err < 0) + return err; + + return libbpf_netlink_send_recv(&req, NETLINK_GENERIC, + parse_genl_family_id, NULL, id); +} + static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, __u32 flags) { @@ -271,7 +316,7 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, } nlattr_end_nested(&req, nla); - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts) @@ -357,6 +402,32 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } +static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct genlmsghdr *gnl = NLMSG_DATA(nh); + struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN); + struct nlattr *tb[NETDEV_CMD_MAX + 1]; + struct xdp_features_md *md = cookie; + __u32 ifindex; + + libbpf_nla_parse(tb, NETDEV_CMD_MAX, na, + NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL); + + if (!tb[NETDEV_A_DEV_IFINDEX] || !tb[NETDEV_A_DEV_XDP_FEATURES]) + return NL_CONT; + + ifindex = libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_IFINDEX]); + if (ifindex != md->ifindex) + return NL_CONT; + + md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]); + if (tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS]) + md->xdp_zc_max_segs = + libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_XDP_ZC_MAX_SEGS]); + return NL_DONE; +} + int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) { struct libbpf_nla_req req = { @@ -366,6 +437,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) .ifinfo.ifi_family = AF_PACKET, }; struct xdp_id_md xdp_id = {}; + struct xdp_features_md md = { + .ifindex = ifindex, + }; + __u16 id; int err; if (!OPTS_VALID(opts, bpf_xdp_query_opts)) @@ -382,7 +457,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) xdp_id.ifindex = ifindex; xdp_id.flags = xdp_flags; - err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, + err = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, __dump_link_nlmsg, get_xdp_info, &xdp_id); if (err) return libbpf_err(err); @@ -393,6 +468,38 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id); OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode); + if (!OPTS_HAS(opts, feature_flags)) + return 0; + + err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id); + if (err < 0) { + if (err == -ENOENT) { + opts->feature_flags = 0; + goto skip_feature_flags; + } + return libbpf_err(err); + } + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + req.nh.nlmsg_flags = NLM_F_REQUEST; + req.nh.nlmsg_type = id; + req.gnl.cmd = NETDEV_CMD_DEV_GET; + req.gnl.version = 2; + + err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex)); + if (err < 0) + return libbpf_err(err); + + err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC, + parse_xdp_features, NULL, &md); + if (err) + return libbpf_err(err); + + OPTS_SET(opts, feature_flags, md.flags); + OPTS_SET(opts, xdp_zc_max_segs, md.xdp_zc_max_segs); + +skip_feature_flags: return 0; } @@ -422,9 +529,9 @@ int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id) } -typedef int (*qdisc_config_t)(struct libbpf_nla_req *req); +typedef int (*qdisc_config_t)(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook); -static int clsact_config(struct libbpf_nla_req *req) +static int clsact_config(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook) { req->tc.tcm_parent = TC_H_CLSACT; req->tc.tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0); @@ -432,6 +539,16 @@ static int clsact_config(struct libbpf_nla_req *req) return nlattr_add(req, TCA_KIND, "clsact", sizeof("clsact")); } +static int qdisc_config(struct libbpf_nla_req *req, const struct bpf_tc_hook *hook) +{ + const char *qdisc = OPTS_GET(hook, qdisc, NULL); + + req->tc.tcm_parent = OPTS_GET(hook, parent, TC_H_ROOT); + req->tc.tcm_handle = OPTS_GET(hook, handle, 0); + + return nlattr_add(req, TCA_KIND, qdisc, strlen(qdisc) + 1); +} + static int attach_point_to_config(struct bpf_tc_hook *hook, qdisc_config_t *config) { @@ -445,6 +562,9 @@ static int attach_point_to_config(struct bpf_tc_hook *hook, return 0; case BPF_TC_CUSTOM: return -EOPNOTSUPP; + case BPF_TC_QDISC: + *config = &qdisc_config; + return 0; default: return -EINVAL; } @@ -489,11 +609,11 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags) req.tc.tcm_family = AF_UNSPEC; req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0); - ret = config(&req); + ret = config(&req, hook); if (ret < 0) return ret; - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } static int tc_qdisc_create_excl(struct bpf_tc_hook *hook) @@ -532,6 +652,7 @@ int bpf_tc_hook_destroy(struct bpf_tc_hook *hook) case BPF_TC_INGRESS: case BPF_TC_EGRESS: return libbpf_err(__bpf_tc_detach(hook, NULL, true)); + case BPF_TC_QDISC: case BPF_TC_INGRESS | BPF_TC_EGRESS: return libbpf_err(tc_qdisc_delete(hook)); case BPF_TC_CUSTOM: @@ -593,7 +714,7 @@ static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd) int len, ret; memset(&info, 0, info_len); - ret = bpf_obj_get_info_by_fd(fd, &info, &info_len); + ret = bpf_prog_get_info_by_fd(fd, &info, &info_len); if (ret < 0) return ret; @@ -673,7 +794,8 @@ int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) info.opts = opts; - ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL, + &info); if (ret < 0) return libbpf_err(ret); if (!info.processed) @@ -739,7 +861,7 @@ static int __bpf_tc_detach(const struct bpf_tc_hook *hook, return ret; } - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } int bpf_tc_detach(const struct bpf_tc_hook *hook, @@ -804,7 +926,8 @@ int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) info.opts = opts; - ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL, + &info); if (ret < 0) return libbpf_err(ret); if (!info.processed) diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index 3900d052ed19..06663f9ea581 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -63,16 +63,16 @@ static int validate_nla(struct nlattr *nla, int maxtype, minlen = nla_attr_minlen[pt->type]; if (libbpf_nla_len(nla) < minlen) - return -1; + return -EINVAL; if (pt->maxlen && libbpf_nla_len(nla) > pt->maxlen) - return -1; + return -EINVAL; if (pt->type == LIBBPF_NLA_STRING) { char *data = libbpf_nla_data(nla); if (data[libbpf_nla_len(nla) - 1] != '\0') - return -1; + return -EINVAL; } return 0; @@ -118,19 +118,18 @@ int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, if (policy) { err = validate_nla(nla, maxtype, policy); if (err < 0) - goto errout; + return err; } - if (tb[type]) + if (tb[type]) { pr_warn("Attribute of type %#x found multiple times in message, " "previous attribute is being ignored.\n", type); + } tb[type] = nla; } - err = 0; -errout: - return err; + return 0; } /** @@ -178,7 +177,7 @@ int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh) hlen += nlmsg_len(&err->msg); attr = (struct nlattr *) ((void *) err + hlen); - alen = nlh->nlmsg_len - hlen; + alen = (void *)nlh + nlh->nlmsg_len - (void *)attr; if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) { diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h index 4d15ae2ff812..d92d1c1de700 100644 --- a/tools/lib/bpf/nlattr.h +++ b/tools/lib/bpf/nlattr.h @@ -14,6 +14,7 @@ #include <errno.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> +#include <linux/genetlink.h> /* avoid multiple definition of netlink features */ #define __LINUX_NETLINK_H @@ -58,6 +59,7 @@ struct libbpf_nla_req { union { struct ifinfomsg ifinfo; struct tcmsg tc; + struct genlmsghdr gnl; }; char buf[128]; }; @@ -89,11 +91,21 @@ static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla) return *(uint8_t *)libbpf_nla_data(nla); } +static inline uint16_t libbpf_nla_getattr_u16(const struct nlattr *nla) +{ + return *(uint16_t *)libbpf_nla_data(nla); +} + static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla) { return *(uint32_t *)libbpf_nla_data(nla); } +static inline uint64_t libbpf_nla_getattr_u64(const struct nlattr *nla) +{ + return *(uint64_t *)libbpf_nla_data(nla); +} + static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla) { return (const char *)libbpf_nla_data(nla); diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index c4b0e81ae293..6eea5edba58a 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -64,7 +64,6 @@ enum libbpf_print_level { #include "libbpf.h" #include "bpf.h" #include "btf.h" -#include "str_error.h" #include "libbpf_internal.h" #endif @@ -683,7 +682,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, { const struct bpf_core_accessor *acc; const struct btf_type *t; - __u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id; + __u32 byte_off, byte_sz, bit_off, bit_sz, field_type_id, elem_id; const struct btf_member *m; const struct btf_type *mt; bool bitfield; @@ -706,8 +705,14 @@ static int bpf_core_calc_field_relo(const char *prog_name, if (!acc->name) { if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) { *val = spec->bit_offset / 8; - /* remember field size for load/store mem size */ - sz = btf__resolve_size(spec->btf, acc->type_id); + /* remember field size for load/store mem size; + * note, for arrays we care about individual element + * sizes, not the overall array size + */ + t = skip_mods_and_typedefs(spec->btf, acc->type_id, &elem_id); + while (btf_is_array(t)) + t = skip_mods_and_typedefs(spec->btf, btf_array(t)->type, &elem_id); + sz = btf__resolve_size(spec->btf, elem_id); if (sz < 0) return -EINVAL; *field_sz = sz; @@ -767,7 +772,17 @@ static int bpf_core_calc_field_relo(const char *prog_name, case BPF_CORE_FIELD_BYTE_OFFSET: *val = byte_off; if (!bitfield) { - *field_sz = byte_sz; + /* remember field size for load/store mem size; + * note, for arrays we care about individual element + * sizes, not the overall array size + */ + t = skip_mods_and_typedefs(spec->btf, field_type_id, &elem_id); + while (btf_is_array(t)) + t = skip_mods_and_typedefs(spec->btf, btf_array(t)->type, &elem_id); + sz = btf__resolve_size(spec->btf, elem_id); + if (sz < 0) + return -EINVAL; + *field_sz = sz; *type_id = field_type_id; } break; @@ -776,7 +791,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, break; case BPF_CORE_FIELD_SIGNED: *val = (btf_is_any_enum(mt) && BTF_INFO_KFLAG(mt->info)) || - (btf_int_encoding(mt) & BTF_INT_SIGNED); + (btf_is_int(mt) && (btf_int_encoding(mt) & BTF_INT_SIGNED)); if (validate) *validate = true; /* signedness is never ambiguous */ break; @@ -1339,7 +1354,7 @@ int bpf_core_calc_relo_insn(const char *prog_name, cands->cands[i].id, cand_spec); if (err < 0) { bpf_core_format_spec(spec_buf, sizeof(spec_buf), cand_spec); - pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n ", + pr_warn("prog '%s': relo #%d: error matching candidate #%d %s: %d\n", prog_name, relo_idx, i, spec_buf, err); return err; } @@ -1551,9 +1566,6 @@ int __bpf_core_types_match(const struct btf *local_btf, __u32 local_id, const st if (level <= 0) return -EINVAL; - local_t = btf_type_by_id(local_btf, local_id); - targ_t = btf_type_by_id(targ_btf, targ_id); - recur: depth--; if (depth < 0) diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 47855af25f3b..00ec4837a06d 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -34,7 +34,7 @@ struct ring { struct ring_buffer { struct epoll_event *events; - struct ring *rings; + struct ring **rings; size_t page_size; int epoll_fd; int ring_cnt; @@ -57,7 +57,7 @@ struct ringbuf_hdr { __u32 pad; }; -static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r) +static void ringbuf_free_ring(struct ring_buffer *rb, struct ring *r) { if (r->consumer_pos) { munmap(r->consumer_pos, rb->page_size); @@ -67,6 +67,8 @@ static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r) munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1)); r->producer_pos = NULL; } + + free(r); } /* Add extra RINGBUF maps to this ring buffer manager */ @@ -83,11 +85,11 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(map_fd, &info, &len); + err = bpf_map_get_info_by_fd(map_fd, &info, &len); if (err) { err = -errno; - pr_warn("ringbuf: failed to get map info for fd=%d: %d\n", - map_fd, err); + pr_warn("ringbuf: failed to get map info for fd=%d: %s\n", + map_fd, errstr(err)); return libbpf_err(err); } @@ -107,8 +109,10 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, return libbpf_err(-ENOMEM); rb->events = tmp; - r = &rb->rings[rb->ring_cnt]; - memset(r, 0, sizeof(*r)); + r = calloc(1, sizeof(*r)); + if (!r) + return libbpf_err(-ENOMEM); + rb->rings[rb->ring_cnt] = r; r->map_fd = map_fd; r->sample_cb = sample_cb; @@ -119,9 +123,9 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0); if (tmp == MAP_FAILED) { err = -errno; - pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n", - map_fd, err); - return libbpf_err(err); + pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %s\n", + map_fd, errstr(err)); + goto err_out; } r->consumer_pos = tmp; @@ -131,16 +135,16 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, */ mmap_sz = rb->page_size + 2 * (__u64)info.max_entries; if (mmap_sz != (__u64)(size_t)mmap_sz) { + err = -E2BIG; pr_warn("ringbuf: ring buffer size (%u) is too big\n", info.max_entries); - return libbpf_err(-E2BIG); + goto err_out; } tmp = mmap(NULL, (size_t)mmap_sz, PROT_READ, MAP_SHARED, map_fd, rb->page_size); if (tmp == MAP_FAILED) { err = -errno; - ringbuf_unmap_ring(rb, r); - pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n", - map_fd, err); - return libbpf_err(err); + pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %s\n", + map_fd, errstr(err)); + goto err_out; } r->producer_pos = tmp; r->data = tmp + rb->page_size; @@ -152,14 +156,17 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, e->data.fd = rb->ring_cnt; if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) { err = -errno; - ringbuf_unmap_ring(rb, r); - pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n", - map_fd, err); - return libbpf_err(err); + pr_warn("ringbuf: failed to epoll add map fd=%d: %s\n", + map_fd, errstr(err)); + goto err_out; } rb->ring_cnt++; return 0; + +err_out: + ringbuf_free_ring(rb, r); + return libbpf_err(err); } void ring_buffer__free(struct ring_buffer *rb) @@ -170,7 +177,7 @@ void ring_buffer__free(struct ring_buffer *rb) return; for (i = 0; i < rb->ring_cnt; ++i) - ringbuf_unmap_ring(rb, &rb->rings[i]); + ringbuf_free_ring(rb, rb->rings[i]); if (rb->epoll_fd >= 0) close(rb->epoll_fd); @@ -198,7 +205,7 @@ ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx, rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); if (rb->epoll_fd < 0) { err = -errno; - pr_warn("ringbuf: failed to create epoll instance: %d\n", err); + pr_warn("ringbuf: failed to create epoll instance: %s\n", errstr(err)); goto err_out; } @@ -224,7 +231,7 @@ static inline int roundup_len(__u32 len) return (len + 7) / 8 * 8; } -static int64_t ringbuf_process_ring(struct ring *r) +static int64_t ringbuf_process_ring(struct ring *r, size_t n) { int *len_ptr, len, err; /* 64-bit to avoid overflow in case of extreme application behavior */ @@ -261,12 +268,42 @@ static int64_t ringbuf_process_ring(struct ring *r) } smp_store_release(r->consumer_pos, cons_pos); + + if (cnt >= n) + goto done; } } while (got_new_data); done: return cnt; } +/* Consume available ring buffer(s) data without event polling, up to n + * records. + * + * Returns number of records consumed across all registered ring buffers (or + * n, whichever is less), or negative number if any of the callbacks return + * error. + */ +int ring_buffer__consume_n(struct ring_buffer *rb, size_t n) +{ + int64_t err, res = 0; + int i; + + for (i = 0; i < rb->ring_cnt; i++) { + struct ring *ring = rb->rings[i]; + + err = ringbuf_process_ring(ring, n); + if (err < 0) + return libbpf_err(err); + res += err; + n -= err; + + if (n == 0) + break; + } + return res > INT_MAX ? INT_MAX : res; +} + /* Consume available ring buffer(s) data without event polling. * Returns number of records consumed across all registered ring buffers (or * INT_MAX, whichever is less), or negative number if any of the callbacks @@ -278,15 +315,17 @@ int ring_buffer__consume(struct ring_buffer *rb) int i; for (i = 0; i < rb->ring_cnt; i++) { - struct ring *ring = &rb->rings[i]; + struct ring *ring = rb->rings[i]; - err = ringbuf_process_ring(ring); + err = ringbuf_process_ring(ring, INT_MAX); if (err < 0) return libbpf_err(err); res += err; + if (res > INT_MAX) { + res = INT_MAX; + break; + } } - if (res > INT_MAX) - return INT_MAX; return res; } @@ -305,15 +344,15 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms) for (i = 0; i < cnt; i++) { __u32 ring_id = rb->events[i].data.fd; - struct ring *ring = &rb->rings[ring_id]; + struct ring *ring = rb->rings[ring_id]; - err = ringbuf_process_ring(ring); + err = ringbuf_process_ring(ring, INT_MAX); if (err < 0) return libbpf_err(err); res += err; } if (res > INT_MAX) - return INT_MAX; + res = INT_MAX; return res; } @@ -323,6 +362,63 @@ int ring_buffer__epoll_fd(const struct ring_buffer *rb) return rb->epoll_fd; } +struct ring *ring_buffer__ring(struct ring_buffer *rb, unsigned int idx) +{ + if (idx >= rb->ring_cnt) + return errno = ERANGE, NULL; + + return rb->rings[idx]; +} + +unsigned long ring__consumer_pos(const struct ring *r) +{ + /* Synchronizes with smp_store_release() in ringbuf_process_ring(). */ + return smp_load_acquire(r->consumer_pos); +} + +unsigned long ring__producer_pos(const struct ring *r) +{ + /* Synchronizes with smp_store_release() in __bpf_ringbuf_reserve() in + * the kernel. + */ + return smp_load_acquire(r->producer_pos); +} + +size_t ring__avail_data_size(const struct ring *r) +{ + unsigned long cons_pos, prod_pos; + + cons_pos = ring__consumer_pos(r); + prod_pos = ring__producer_pos(r); + return prod_pos - cons_pos; +} + +size_t ring__size(const struct ring *r) +{ + return r->mask + 1; +} + +int ring__map_fd(const struct ring *r) +{ + return r->map_fd; +} + +int ring__consume_n(struct ring *r, size_t n) +{ + int64_t res; + + res = ringbuf_process_ring(r, n); + if (res < 0) + return libbpf_err(res); + + return res > INT_MAX ? INT_MAX : res; +} + +int ring__consume(struct ring *r) +{ + return ring__consume_n(r, INT_MAX); +} + static void user_ringbuf_unmap_ring(struct user_ring_buffer *rb) { if (rb->consumer_pos) { @@ -359,10 +455,11 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) memset(&info, 0, sizeof(info)); - err = bpf_obj_get_info_by_fd(map_fd, &info, &len); + err = bpf_map_get_info_by_fd(map_fd, &info, &len); if (err) { err = -errno; - pr_warn("user ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err); + pr_warn("user ringbuf: failed to get map info for fd=%d: %s\n", + map_fd, errstr(err)); return err; } @@ -378,8 +475,8 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) tmp = mmap(NULL, rb->page_size, PROT_READ, MAP_SHARED, map_fd, 0); if (tmp == MAP_FAILED) { err = -errno; - pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %d\n", - map_fd, err); + pr_warn("user ringbuf: failed to mmap consumer page for map fd=%d: %s\n", + map_fd, errstr(err)); return err; } rb->consumer_pos = tmp; @@ -398,8 +495,8 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) map_fd, rb->page_size); if (tmp == MAP_FAILED) { err = -errno; - pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %d\n", - map_fd, err); + pr_warn("user ringbuf: failed to mmap data pages for map fd=%d: %s\n", + map_fd, errstr(err)); return err; } @@ -410,7 +507,7 @@ static int user_ringbuf_map(struct user_ring_buffer *rb, int map_fd) rb_epoll->events = EPOLLOUT; if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, rb_epoll) < 0) { err = -errno; - pr_warn("user ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err); + pr_warn("user ringbuf: failed to epoll add map fd=%d: %s\n", map_fd, errstr(err)); return err; } @@ -435,7 +532,7 @@ user_ring_buffer__new(int map_fd, const struct user_ring_buffer_opts *opts) rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); if (rb->epoll_fd < 0) { err = -errno; - pr_warn("user ringbuf: failed to create epoll instance: %d\n", err); + pr_warn("user ringbuf: failed to create epoll instance: %s\n", errstr(err)); goto err_out; } diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 1e82ab06c3eb..6a8f5c7a02eb 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -13,10 +13,15 @@ #include <unistd.h> #include <sys/syscall.h> #include <sys/mman.h> +#include <linux/keyctl.h> #include <stdlib.h> #include "bpf.h" #endif +#ifndef SHA256_DIGEST_LENGTH +#define SHA256_DIGEST_LENGTH 32 +#endif + #ifndef __NR_bpf # if defined(__mips__) && defined(_ABIO32) # define __NR_bpf 4355 @@ -64,6 +69,11 @@ struct bpf_load_and_run_opts { __u32 data_sz; __u32 insns_sz; const char *errstr; + void *signature; + __u32 signature_sz; + __s32 keyring_id; + void *excl_prog_hash; + __u32 excl_prog_hash_sz; }; long kern_sys_bpf(__u32 cmd, void *attr, __u32 attr_size); @@ -107,7 +117,7 @@ static inline void skel_free(const void *p) * The loader program will perform probe_read_kernel() from maps.rodata.initial_value. * skel_finalize_map_data() sets skel->rodata to point to actual value in a bpf map and * does maps.rodata.initial_value = ~0ULL to signal skel_free_map_data() that kvfree - * is not nessary. + * is not necessary. * * For user space: * skel_prep_map_data() mmaps anon memory into skel->rodata that can be accessed directly. @@ -220,14 +230,19 @@ static inline int skel_map_create(enum bpf_map_type map_type, const char *map_name, __u32 key_size, __u32 value_size, - __u32 max_entries) + __u32 max_entries, + const void *excl_prog_hash, + __u32 excl_prog_hash_sz) { - const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + const size_t attr_sz = offsetofend(union bpf_attr, excl_prog_hash_size); union bpf_attr attr; memset(&attr, 0, attr_sz); attr.map_type = map_type; + attr.excl_prog_hash = (unsigned long) excl_prog_hash; + attr.excl_prog_hash_size = excl_prog_hash_sz; + strncpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.key_size = key_size; attr.value_size = value_size; @@ -300,6 +315,35 @@ static inline int skel_link_create(int prog_fd, int target_fd, return skel_sys_bpf(BPF_LINK_CREATE, &attr, attr_sz); } +static inline int skel_obj_get_info_by_fd(int fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, info); + __u8 sha[SHA256_DIGEST_LENGTH]; + struct bpf_map_info info; + __u32 info_len = sizeof(info); + union bpf_attr attr; + + memset(&info, 0, sizeof(info)); + info.hash = (long) &sha; + info.hash_size = SHA256_DIGEST_LENGTH; + + memset(&attr, 0, attr_sz); + attr.info.bpf_fd = fd; + attr.info.info = (long) &info; + attr.info.info_len = info_len; + return skel_sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, attr_sz); +} + +static inline int skel_map_freeze(int fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, map_fd); + union bpf_attr attr; + + memset(&attr, 0, attr_sz); + attr.map_fd = fd; + + return skel_sys_bpf(BPF_MAP_FREEZE, &attr, attr_sz); +} #ifdef __KERNEL__ #define set_err #else @@ -308,12 +352,13 @@ static inline int skel_link_create(int prog_fd, int target_fd, static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) { - const size_t prog_load_attr_sz = offsetofend(union bpf_attr, fd_array); + const size_t prog_load_attr_sz = offsetofend(union bpf_attr, keyring_id); const size_t test_run_attr_sz = offsetofend(union bpf_attr, test); int map_fd = -1, prog_fd = -1, key = 0, err; union bpf_attr attr; - err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1); + err = map_fd = skel_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1, + opts->excl_prog_hash, opts->excl_prog_hash_sz); if (map_fd < 0) { opts->errstr = "failed to create loader map"; set_err; @@ -327,11 +372,34 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) goto out; } +#ifndef __KERNEL__ + err = skel_map_freeze(map_fd); + if (err < 0) { + opts->errstr = "failed to freeze map"; + set_err; + goto out; + } + err = skel_obj_get_info_by_fd(map_fd); + if (err < 0) { + opts->errstr = "failed to fetch obj info"; + set_err; + goto out; + } +#endif + memset(&attr, 0, prog_load_attr_sz); attr.prog_type = BPF_PROG_TYPE_SYSCALL; attr.insns = (long) opts->insns; attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); attr.license = (long) "Dual BSD/GPL"; +#ifndef __KERNEL__ + attr.signature = (long) opts->signature; + attr.signature_size = opts->signature_sz; +#else + if (opts->signature || opts->signature_sz) + pr_warn("signatures are not supported from bpf_preload\n"); +#endif + attr.keyring_id = opts->keyring_id; memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog")); attr.fd_array = (long) &map_fd; attr.log_level = opts->ctx->log_level; @@ -351,10 +419,11 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) attr.test.ctx_size_in = opts->ctx->sz; err = skel_sys_bpf(BPF_PROG_RUN, &attr, test_run_attr_sz); if (err < 0 || (int)attr.test.retval < 0) { - opts->errstr = "failed to execute loader prog"; if (err < 0) { + opts->errstr = "failed to execute loader prog"; set_err; } else { + opts->errstr = "error returned by loader prog"; err = (int)attr.test.retval; #ifndef __KERNEL__ errno = -err; diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c deleted file mode 100644 index 146da01979c7..000000000000 --- a/tools/lib/bpf/str_error.c +++ /dev/null @@ -1,21 +0,0 @@ -// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) -#undef _GNU_SOURCE -#include <string.h> -#include <stdio.h> -#include "str_error.h" - -/* make sure libbpf doesn't use kernel-only integer typedefs */ -#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 - -/* - * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl - * libc, while checking strerror_r() return to avoid having to check this in - * all places calling it. - */ -char *libbpf_strerror_r(int err, char *dst, int len) -{ - int ret = strerror_r(err < 0 ? -err : err, dst, len); - if (ret) - snprintf(dst, len, "ERROR: strerror_r(%d)=%d", err, ret); - return dst; -} diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h deleted file mode 100644 index a139334d57b6..000000000000 --- a/tools/lib/bpf/str_error.h +++ /dev/null @@ -1,6 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#ifndef __LIBBPF_STR_ERROR_H -#define __LIBBPF_STR_ERROR_H - -char *libbpf_strerror_r(int err, char *dst, int len); -#endif /* __LIBBPF_STR_ERROR_H */ diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index fdfd235e52c4..43deb05a5197 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -4,8 +4,8 @@ #define __USDT_BPF_H__ #include <linux/errno.h> -#include <bpf/bpf_helpers.h> -#include <bpf/bpf_tracing.h> +#include "bpf_helpers.h" +#include "bpf_tracing.h" /* Below types and maps are internal implementation details of libbpf's USDT * support and are subjects to change. Also, bpf_usdt_xxx() API helpers should @@ -34,13 +34,32 @@ enum __bpf_usdt_arg_type { BPF_USDT_ARG_CONST, BPF_USDT_ARG_REG, BPF_USDT_ARG_REG_DEREF, + BPF_USDT_ARG_SIB, }; +/* + * This struct layout is designed specifically to be backwards/forward + * compatible between libbpf versions for ARG_CONST, ARG_REG, and + * ARG_REG_DEREF modes. ARG_SIB requires libbpf v1.7+. + */ struct __bpf_usdt_arg_spec { /* u64 scalar interpreted depending on arg_type, see below */ __u64 val_off; - /* arg location case, see bpf_udst_arg() for details */ - enum __bpf_usdt_arg_type arg_type; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + /* arg location case, see bpf_usdt_arg() for details */ + enum __bpf_usdt_arg_type arg_type: 8; + /* index register offset within struct pt_regs */ + __u16 idx_reg_off: 12; + /* scale factor for index register (1, 2, 4, or 8) */ + __u16 scale_bitshift: 4; + /* reserved for future use, keeps reg_off offset stable */ + __u8 __reserved: 8; +#else + __u8 __reserved: 8; + __u16 idx_reg_off: 12; + __u16 scale_bitshift: 4; + enum __bpf_usdt_arg_type arg_type: 8; +#endif /* offset of referenced register within struct pt_regs */ short reg_off; /* whether arg should be interpreted as signed value */ @@ -108,6 +127,38 @@ int bpf_usdt_arg_cnt(struct pt_regs *ctx) return spec->arg_cnt; } +/* Returns the size in bytes of the #*arg_num* (zero-indexed) USDT argument. + * Returns negative error if argument is not found or arg_num is invalid. + */ +static __always_inline +int bpf_usdt_arg_size(struct pt_regs *ctx, __u64 arg_num) +{ + struct __bpf_usdt_arg_spec *arg_spec; + struct __bpf_usdt_spec *spec; + int spec_id; + + spec_id = __bpf_usdt_spec_id(ctx); + if (spec_id < 0) + return -ESRCH; + + spec = bpf_map_lookup_elem(&__bpf_usdt_specs, &spec_id); + if (!spec) + return -ESRCH; + + if (arg_num >= BPF_USDT_MAX_ARG_CNT) + return -ENOENT; + barrier_var(arg_num); + if (arg_num >= spec->arg_cnt) + return -ENOENT; + + arg_spec = &spec->args[arg_num]; + + /* arg_spec->arg_bitshift = 64 - arg_sz * 8 + * so: arg_sz = (64 - arg_spec->arg_bitshift) / 8 + */ + return (unsigned int)(64 - arg_spec->arg_bitshift) / 8; +} + /* Fetch USDT argument #*arg_num* (zero-indexed) and put its value into *res. * Returns 0 on success; negative error, otherwise. * On error *res is guaranteed to be set to zero. @@ -117,7 +168,7 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) { struct __bpf_usdt_spec *spec; struct __bpf_usdt_arg_spec *arg_spec; - unsigned long val; + unsigned long val, idx; int err, spec_id; *res = 0; @@ -130,7 +181,10 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) if (!spec) return -ESRCH; - if (arg_num >= BPF_USDT_MAX_ARG_CNT || arg_num >= spec->arg_cnt) + if (arg_num >= BPF_USDT_MAX_ARG_CNT) + return -ENOENT; + barrier_var(arg_num); + if (arg_num >= spec->arg_cnt) return -ENOENT; arg_spec = &spec->args[arg_num]; @@ -169,6 +223,27 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) val >>= arg_spec->arg_bitshift; #endif break; + case BPF_USDT_ARG_SIB: + /* Arg is in memory addressed by SIB (Scale-Index-Base) mode + * (e.g., "-1@-96(%rbp,%rax,8)" in USDT arg spec). We first + * fetch the base register contents and the index register + * contents from pt_regs. Then we calculate the final address + * as base + (index * scale) + offset, and do a user-space + * probe read to fetch the argument value. + */ + err = bpf_probe_read_kernel(&val, sizeof(val), (void *)ctx + arg_spec->reg_off); + if (err) + return err; + err = bpf_probe_read_kernel(&idx, sizeof(idx), (void *)ctx + arg_spec->idx_reg_off); + if (err) + return err; + err = bpf_probe_read_user(&val, sizeof(val), (void *)(val + (idx << arg_spec->scale_bitshift) + arg_spec->val_off)); + if (err) + return err; +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + val >>= arg_spec->arg_bitshift; +#endif + break; default: return -EINVAL; } @@ -211,18 +286,18 @@ long bpf_usdt_cookie(struct pt_regs *ctx) /* we rely on ___bpf_apply() and ___bpf_narg() macros already defined in bpf_tracing.h */ #define ___bpf_usdt_args0() ctx -#define ___bpf_usdt_args1(x) ___bpf_usdt_args0(), ({ long _x; bpf_usdt_arg(ctx, 0, &_x); (void *)_x; }) -#define ___bpf_usdt_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); (void *)_x; }) -#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); (void *)_x; }) -#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); (void *)_x; }) -#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); (void *)_x; }) -#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); (void *)_x; }) -#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); (void *)_x; }) -#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); (void *)_x; }) -#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); (void *)_x; }) -#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); (void *)_x; }) -#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); (void *)_x; }) -#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); (void *)_x; }) +#define ___bpf_usdt_args1(x) ___bpf_usdt_args0(), ({ long _x; bpf_usdt_arg(ctx, 0, &_x); _x; }) +#define ___bpf_usdt_args2(x, args...) ___bpf_usdt_args1(args), ({ long _x; bpf_usdt_arg(ctx, 1, &_x); _x; }) +#define ___bpf_usdt_args3(x, args...) ___bpf_usdt_args2(args), ({ long _x; bpf_usdt_arg(ctx, 2, &_x); _x; }) +#define ___bpf_usdt_args4(x, args...) ___bpf_usdt_args3(args), ({ long _x; bpf_usdt_arg(ctx, 3, &_x); _x; }) +#define ___bpf_usdt_args5(x, args...) ___bpf_usdt_args4(args), ({ long _x; bpf_usdt_arg(ctx, 4, &_x); _x; }) +#define ___bpf_usdt_args6(x, args...) ___bpf_usdt_args5(args), ({ long _x; bpf_usdt_arg(ctx, 5, &_x); _x; }) +#define ___bpf_usdt_args7(x, args...) ___bpf_usdt_args6(args), ({ long _x; bpf_usdt_arg(ctx, 6, &_x); _x; }) +#define ___bpf_usdt_args8(x, args...) ___bpf_usdt_args7(args), ({ long _x; bpf_usdt_arg(ctx, 7, &_x); _x; }) +#define ___bpf_usdt_args9(x, args...) ___bpf_usdt_args8(args), ({ long _x; bpf_usdt_arg(ctx, 8, &_x); _x; }) +#define ___bpf_usdt_args10(x, args...) ___bpf_usdt_args9(args), ({ long _x; bpf_usdt_arg(ctx, 9, &_x); _x; }) +#define ___bpf_usdt_args11(x, args...) ___bpf_usdt_args10(args), ({ long _x; bpf_usdt_arg(ctx, 10, &_x); _x; }) +#define ___bpf_usdt_args12(x, args...) ___bpf_usdt_args11(args), ({ long _x; bpf_usdt_arg(ctx, 11, &_x); _x; }) #define ___bpf_usdt_args(args...) ___bpf_apply(___bpf_usdt_args, ___bpf_narg(args))(args) /* diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c index 75b411fc2c77..d1524f6f54ae 100644 --- a/tools/lib/bpf/usdt.c +++ b/tools/lib/bpf/usdt.c @@ -58,7 +58,7 @@ * * STAP_PROBE3(my_usdt_provider, my_usdt_probe_name, 123, x, &y); * - * USDT is identified by it's <provider-name>:<probe-name> pair of names. Each + * USDT is identified by its <provider-name>:<probe-name> pair of names. Each * individual USDT has a fixed number of arguments (3 in the above example) * and specifies values of each argument as if it was a function call. * @@ -80,7 +80,7 @@ * NOP instruction that kernel can replace with an interrupt instruction to * trigger instrumentation code (BPF program for all that we care about). * - * Semaphore above is and optional feature. It records an address of a 2-byte + * Semaphore above is an optional feature. It records an address of a 2-byte * refcount variable (normally in '.probes' ELF section) used for signaling if * there is anything that is attached to USDT. This is useful for user * applications if, for example, they need to prepare some arguments that are @@ -120,7 +120,7 @@ * a uprobe BPF program (which for kernel, at least currently, is just a kprobe * program, so BPF_PROG_TYPE_KPROBE program type). With the only difference * that uprobe is usually attached at the function entry, while USDT will - * normally will be somewhere inside the function. But it should always be + * normally be somewhere inside the function. But it should always be * pointing to NOP instruction, which makes such uprobes the fastest uprobe * kind. * @@ -150,7 +150,7 @@ * libbpf sets to spec ID during attach time, or, if kernel is too old to * support BPF cookie, through IP-to-spec-ID map that libbpf maintains in such * case. The latter means that some modes of operation can't be supported - * without BPF cookie. Such mode is attaching to shared library "generically", + * without BPF cookie. Such a mode is attaching to shared library "generically", * without specifying target process. In such case, it's impossible to * calculate absolute IP addresses for IP-to-spec-ID map, and thus such mode * is not supported without BPF cookie support. @@ -184,7 +184,7 @@ * as even if USDT spec string is the same, USDT cookie value can be * different. It was deemed excessive to try to deduplicate across independent * USDT attachments by taking into account USDT spec string *and* USDT cookie - * value, which would complicated spec ID accounting significantly for little + * value, which would complicate spec ID accounting significantly for little * gain. */ @@ -199,12 +199,23 @@ enum usdt_arg_type { USDT_ARG_CONST, USDT_ARG_REG, USDT_ARG_REG_DEREF, + USDT_ARG_SIB, }; /* should match exactly struct __bpf_usdt_arg_spec from usdt.bpf.h */ struct usdt_arg_spec { __u64 val_off; - enum usdt_arg_type arg_type; +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + enum usdt_arg_type arg_type: 8; + __u16 idx_reg_off: 12; + __u16 scale_bitshift: 4; + __u8 __reserved: 8; /* keep reg_off offset stable */ +#else + __u8 __reserved: 8; /* keep reg_off offset stable */ + __u16 idx_reg_off: 12; + __u16 scale_bitshift: 4; + enum usdt_arg_type arg_type: 8; +#endif short reg_off; bool arg_signed; char arg_bitshift; @@ -250,6 +261,7 @@ struct usdt_manager { bool has_bpf_cookie; bool has_sema_refcnt; + bool has_uprobe_multi; }; struct usdt_manager *usdt_manager_new(struct bpf_object *obj) @@ -284,6 +296,11 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj) */ man->has_sema_refcnt = faccessat(AT_FDCWD, ref_ctr_sysfs_path, F_OK, AT_EACCESS) == 0; + /* + * Detect kernel support for uprobe multi link to be used for attaching + * usdt probes. + */ + man->has_uprobe_multi = kernel_supports(obj, FEAT_UPROBE_MULTI_LINK); return man; } @@ -459,18 +476,18 @@ static int parse_vma_segs(int pid, const char *lib_path, struct elf_seg **segs, goto proceed; if (!realpath(lib_path, path)) { - pr_warn("usdt: failed to get absolute path of '%s' (err %d), using path as is...\n", - lib_path, -errno); + pr_warn("usdt: failed to get absolute path of '%s' (err %s), using path as is...\n", + lib_path, errstr(-errno)); libbpf_strlcpy(path, lib_path, sizeof(path)); } proceed: sprintf(line, "/proc/%d/maps", pid); - f = fopen(line, "r"); + f = fopen(line, "re"); if (!f) { err = -errno; - pr_warn("usdt: failed to open '%s' to get base addr of '%s': %d\n", - line, lib_path, err); + pr_warn("usdt: failed to open '%s' to get base addr of '%s': %s\n", + line, lib_path, errstr(err)); return err; } @@ -563,9 +580,8 @@ static struct elf_seg *find_vma_seg(struct elf_seg *segs, size_t seg_cnt, long o return NULL; } -static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, - const char *data, size_t name_off, size_t desc_off, - struct usdt_note *usdt_note); +static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off, + size_t desc_off, struct usdt_note *usdt_note); static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie); @@ -600,7 +616,8 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * err = parse_elf_segs(elf, path, &segs, &seg_cnt); if (err) { - pr_warn("usdt: failed to process ELF program segments for '%s': %d\n", path, err); + pr_warn("usdt: failed to process ELF program segments for '%s': %s\n", + path, errstr(err)); goto err_out; } @@ -618,7 +635,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * struct elf_seg *seg = NULL; void *tmp; - err = parse_usdt_note(elf, path, &nhdr, data->d_buf, name_off, desc_off, ¬e); + err = parse_usdt_note(&nhdr, data->d_buf, name_off, desc_off, ¬e); if (err) goto err_out; @@ -653,7 +670,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * * [0] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation */ usdt_abs_ip = note.loc_addr; - if (base_addr) + if (base_addr && note.base_addr) usdt_abs_ip += base_addr - note.base_addr; /* When attaching uprobes (which is what USDTs basically are) @@ -702,8 +719,8 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * if (vma_seg_cnt == 0) { err = parse_vma_segs(pid, path, &vma_segs, &vma_seg_cnt); if (err) { - pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %d\n", - pid, path, err); + pr_warn("usdt: failed to get memory segments in PID %d for shared library '%s': %s\n", + pid, path, errstr(err)); goto err_out; } } @@ -771,7 +788,7 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char * target->rel_ip = usdt_rel_ip; target->sema_off = usdt_sema_off; - /* notes.args references strings from Elf itself, so they can + /* notes.args references strings from ELF itself, so they can * be referenced safely until elf_end() call */ target->spec_str = note.args; @@ -808,6 +825,8 @@ struct bpf_link_usdt { long abs_ip; struct bpf_link *link; } *uprobes; + + struct bpf_link *multi_link; }; static int bpf_link_usdt_detach(struct bpf_link *link) @@ -816,6 +835,9 @@ static int bpf_link_usdt_detach(struct bpf_link *link) struct usdt_manager *man = usdt_link->usdt_man; int i; + bpf_link__destroy(usdt_link->multi_link); + + /* When having multi_link, uprobe_cnt is 0 */ for (i = 0; i < usdt_link->uprobe_cnt; i++) { /* detach underlying uprobe link */ bpf_link__destroy(usdt_link->uprobes[i].link); @@ -852,8 +874,11 @@ static int bpf_link_usdt_detach(struct bpf_link *link) * system is so exhausted on memory, it's the least of user's * concerns, probably. * So just do our best here to return those IDs to usdt_manager. + * Another edge case when we can legitimately get NULL is when + * new_cnt is zero, which can happen in some edge cases, so we + * need to be careful about that. */ - if (new_free_ids) { + if (new_free_ids || new_cnt == 0) { memcpy(new_free_ids + man->free_spec_cnt, usdt_link->spec_ids, usdt_link->spec_cnt * sizeof(*usdt_link->spec_ids)); man->free_spec_ids = new_free_ids; @@ -943,33 +968,24 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct const char *usdt_provider, const char *usdt_name, __u64 usdt_cookie) { - int i, fd, err, spec_map_fd, ip_map_fd; + unsigned long *offsets = NULL, *ref_ctr_offsets = NULL; + int i, err, spec_map_fd, ip_map_fd; LIBBPF_OPTS(bpf_uprobe_opts, opts); struct hashmap *specs_hash = NULL; struct bpf_link_usdt *link = NULL; struct usdt_target *targets = NULL; + __u64 *cookies = NULL; + struct elf_fd elf_fd; size_t target_cnt; - Elf *elf; spec_map_fd = bpf_map__fd(man->specs_map); ip_map_fd = bpf_map__fd(man->ip_to_spec_id_map); - /* TODO: perform path resolution similar to uprobe's */ - fd = open(path, O_RDONLY); - if (fd < 0) { - err = -errno; - pr_warn("usdt: failed to open ELF binary '%s': %d\n", path, err); + err = elf_open(path, &elf_fd); + if (err) return libbpf_err_ptr(err); - } - - elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); - if (!elf) { - err = -EBADF; - pr_warn("usdt: failed to parse ELF binary '%s': %s\n", path, elf_errmsg(-1)); - goto err_out; - } - err = sanity_check_usdt_elf(elf, path); + err = sanity_check_usdt_elf(elf_fd.elf, path); if (err) goto err_out; @@ -982,7 +998,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct /* discover USDT in given binary, optionally limiting * activations to a given PID, if pid > 0 */ - err = collect_usdt_targets(man, elf, path, pid, usdt_provider, usdt_name, + err = collect_usdt_targets(man, elf_fd.elf, path, pid, usdt_provider, usdt_name, usdt_cookie, &targets, &target_cnt); if (err <= 0) { err = (err == 0) ? -ENOENT : err; @@ -1005,10 +1021,21 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct link->link.detach = &bpf_link_usdt_detach; link->link.dealloc = &bpf_link_usdt_dealloc; - link->uprobes = calloc(target_cnt, sizeof(*link->uprobes)); - if (!link->uprobes) { - err = -ENOMEM; - goto err_out; + if (man->has_uprobe_multi) { + offsets = calloc(target_cnt, sizeof(*offsets)); + cookies = calloc(target_cnt, sizeof(*cookies)); + ref_ctr_offsets = calloc(target_cnt, sizeof(*ref_ctr_offsets)); + + if (!offsets || !ref_ctr_offsets || !cookies) { + err = -ENOMEM; + goto err_out; + } + } else { + link->uprobes = calloc(target_cnt, sizeof(*link->uprobes)); + if (!link->uprobes) { + err = -ENOMEM; + goto err_out; + } } for (i = 0; i < target_cnt; i++) { @@ -1031,8 +1058,8 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct if (is_new && bpf_map_update_elem(spec_map_fd, &spec_id, &target->spec, BPF_ANY)) { err = -errno; - pr_warn("usdt: failed to set USDT spec #%d for '%s:%s' in '%s': %d\n", - spec_id, usdt_provider, usdt_name, path, err); + pr_warn("usdt: failed to set USDT spec #%d for '%s:%s' in '%s': %s\n", + spec_id, usdt_provider, usdt_name, path, errstr(err)); goto err_out; } if (!man->has_bpf_cookie && @@ -1042,52 +1069,79 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct pr_warn("usdt: IP collision detected for spec #%d for '%s:%s' in '%s'\n", spec_id, usdt_provider, usdt_name, path); } else { - pr_warn("usdt: failed to map IP 0x%lx to spec #%d for '%s:%s' in '%s': %d\n", + pr_warn("usdt: failed to map IP 0x%lx to spec #%d for '%s:%s' in '%s': %s\n", target->abs_ip, spec_id, usdt_provider, usdt_name, - path, err); + path, errstr(err)); } goto err_out; } - opts.ref_ctr_offset = target->sema_off; - opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0; - uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path, - target->rel_ip, &opts); - err = libbpf_get_error(uprobe_link); - if (err) { - pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %d\n", - i, usdt_provider, usdt_name, path, err); + if (man->has_uprobe_multi) { + offsets[i] = target->rel_ip; + ref_ctr_offsets[i] = target->sema_off; + cookies[i] = spec_id; + } else { + opts.ref_ctr_offset = target->sema_off; + opts.bpf_cookie = man->has_bpf_cookie ? spec_id : 0; + uprobe_link = bpf_program__attach_uprobe_opts(prog, pid, path, + target->rel_ip, &opts); + err = libbpf_get_error(uprobe_link); + if (err) { + pr_warn("usdt: failed to attach uprobe #%d for '%s:%s' in '%s': %s\n", + i, usdt_provider, usdt_name, path, errstr(err)); + goto err_out; + } + + link->uprobes[i].link = uprobe_link; + link->uprobes[i].abs_ip = target->abs_ip; + link->uprobe_cnt++; + } + } + + if (man->has_uprobe_multi) { + LIBBPF_OPTS(bpf_uprobe_multi_opts, opts_multi, + .ref_ctr_offsets = ref_ctr_offsets, + .offsets = offsets, + .cookies = cookies, + .cnt = target_cnt, + ); + + link->multi_link = bpf_program__attach_uprobe_multi(prog, pid, path, + NULL, &opts_multi); + if (!link->multi_link) { + err = -errno; + pr_warn("usdt: failed to attach uprobe multi for '%s:%s' in '%s': %s\n", + usdt_provider, usdt_name, path, errstr(err)); goto err_out; } - link->uprobes[i].link = uprobe_link; - link->uprobes[i].abs_ip = target->abs_ip; - link->uprobe_cnt++; + free(offsets); + free(ref_ctr_offsets); + free(cookies); } free(targets); hashmap__free(specs_hash); - elf_end(elf); - close(fd); - + elf_close(&elf_fd); return &link->link; err_out: + free(offsets); + free(ref_ctr_offsets); + free(cookies); + if (link) bpf_link__destroy(&link->link); free(targets); hashmap__free(specs_hash); - if (elf) - elf_end(elf); - close(fd); + elf_close(&elf_fd); return libbpf_err_ptr(err); } /* Parse out USDT ELF note from '.note.stapsdt' section. * Logic inspired by perf's code. */ -static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, - const char *data, size_t name_off, size_t desc_off, +static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off, size_t desc_off, struct usdt_note *note) { const char *provider, *name, *args; @@ -1141,12 +1195,13 @@ static int parse_usdt_note(Elf *elf, const char *path, GElf_Nhdr *nhdr, return 0; } -static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg); +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz); static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie) { + struct usdt_arg_spec *arg; const char *s; - int len; + int arg_sz, len; spec->usdt_cookie = usdt_cookie; spec->arg_cnt = 0; @@ -1159,10 +1214,25 @@ static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, return -E2BIG; } - len = parse_usdt_arg(s, spec->arg_cnt, &spec->args[spec->arg_cnt]); + arg = &spec->args[spec->arg_cnt]; + len = parse_usdt_arg(s, spec->arg_cnt, arg, &arg_sz); if (len < 0) return len; + arg->arg_signed = arg_sz < 0; + if (arg_sz < 0) + arg_sz = -arg_sz; + + switch (arg_sz) { + case 1: case 2: case 4: case 8: + arg->arg_bitshift = 64 - arg_sz * 8; + break; + default: + pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", + spec->arg_cnt, s, arg_sz); + return -EINVAL; + } + s += len; spec->arg_cnt++; } @@ -1219,13 +1289,53 @@ static int calc_pt_regs_off(const char *reg_name) return -ENOENT; } -static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz) { - char reg_name[16]; - int arg_sz, len, reg_off; - long off; + char reg_name[16] = {0}, idx_reg_name[16] = {0}; + int len, reg_off, idx_reg_off, scale = 1; + long off = 0; + + if (sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^,] , %d ) %n", + arg_sz, &off, reg_name, idx_reg_name, &scale, &len) == 5 || + sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^,] , %d ) %n", + arg_sz, reg_name, idx_reg_name, &scale, &len) == 4 || + sscanf(arg_str, " %d @ %ld ( %%%15[^,] , %%%15[^)] ) %n", + arg_sz, &off, reg_name, idx_reg_name, &len) == 4 || + sscanf(arg_str, " %d @ ( %%%15[^,] , %%%15[^)] ) %n", + arg_sz, reg_name, idx_reg_name, &len) == 3 + ) { + /* + * Scale Index Base case: + * 1@-96(%rbp,%rax,8) + * 1@(%rbp,%rax,8) + * 1@-96(%rbp,%rax) + * 1@(%rbp,%rax) + */ + arg->arg_type = USDT_ARG_SIB; + arg->val_off = off; + + reg_off = calc_pt_regs_off(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; - if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", &arg_sz, &off, reg_name, &len) == 3) { + idx_reg_off = calc_pt_regs_off(idx_reg_name); + if (idx_reg_off < 0) + return idx_reg_off; + arg->idx_reg_off = idx_reg_off; + + /* validate scale factor and set fields directly */ + switch (scale) { + case 1: arg->scale_bitshift = 0; break; + case 2: arg->scale_bitshift = 1; break; + case 4: arg->scale_bitshift = 2; break; + case 8: arg->scale_bitshift = 3; break; + default: + pr_warn("usdt: invalid SIB scale %d, expected 1, 2, 4, 8\n", scale); + return -EINVAL; + } + } else if (sscanf(arg_str, " %d @ %ld ( %%%15[^)] ) %n", + arg_sz, &off, reg_name, &len) == 3) { /* Memory dereference case, e.g., -4@-20(%rbp) */ arg->arg_type = USDT_ARG_REG_DEREF; arg->val_off = off; @@ -1233,7 +1343,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec if (reg_off < 0) return reg_off; arg->reg_off = reg_off; - } else if (sscanf(arg_str, " %d @ ( %%%15[^)] ) %n", &arg_sz, reg_name, &len) == 2) { + } else if (sscanf(arg_str, " %d @ ( %%%15[^)] ) %n", arg_sz, reg_name, &len) == 2) { /* Memory dereference case without offset, e.g., 8@(%rsp) */ arg->arg_type = USDT_ARG_REG_DEREF; arg->val_off = 0; @@ -1241,16 +1351,17 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec if (reg_off < 0) return reg_off; arg->reg_off = reg_off; - } else if (sscanf(arg_str, " %d @ %%%15s %n", &arg_sz, reg_name, &len) == 2) { + } else if (sscanf(arg_str, " %d @ %%%15s %n", arg_sz, reg_name, &len) == 2) { /* Register read case, e.g., -4@%eax */ arg->arg_type = USDT_ARG_REG; + /* register read has no memory offset */ arg->val_off = 0; reg_off = calc_pt_regs_off(reg_name); if (reg_off < 0) return reg_off; arg->reg_off = reg_off; - } else if (sscanf(arg_str, " %d @ $%ld %n", &arg_sz, &off, &len) == 2) { + } else if (sscanf(arg_str, " %d @ $%ld %n", arg_sz, &off, &len) == 2) { /* Constant value case, e.g., 4@$71 */ arg->arg_type = USDT_ARG_CONST; arg->val_off = off; @@ -1260,34 +1371,18 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec return -EINVAL; } - arg->arg_signed = arg_sz < 0; - if (arg_sz < 0) - arg_sz = -arg_sz; - - switch (arg_sz) { - case 1: case 2: case 4: case 8: - arg->arg_bitshift = 64 - arg_sz * 8; - break; - default: - pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", - arg_num, arg_str, arg_sz); - return -EINVAL; - } - return len; } #elif defined(__s390x__) -/* Do not support __s390__ for now, since user_pt_regs is broken with -m31. */ - -static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz) { unsigned int reg; - int arg_sz, len; + int len; long off; - if (sscanf(arg_str, " %d @ %ld ( %%r%u ) %n", &arg_sz, &off, ®, &len) == 3) { + if (sscanf(arg_str, " %d @ %ld ( %%r%u ) %n", arg_sz, &off, ®, &len) == 3) { /* Memory dereference case, e.g., -2@-28(%r15) */ arg->arg_type = USDT_ARG_REG_DEREF; arg->val_off = off; @@ -1296,7 +1391,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec return -EINVAL; } arg->reg_off = offsetof(user_pt_regs, gprs[reg]); - } else if (sscanf(arg_str, " %d @ %%r%u %n", &arg_sz, ®, &len) == 2) { + } else if (sscanf(arg_str, " %d @ %%r%u %n", arg_sz, ®, &len) == 2) { /* Register read case, e.g., -8@%r0 */ arg->arg_type = USDT_ARG_REG; arg->val_off = 0; @@ -1305,7 +1400,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec return -EINVAL; } arg->reg_off = offsetof(user_pt_regs, gprs[reg]); - } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { + } else if (sscanf(arg_str, " %d @ %ld %n", arg_sz, &off, &len) == 2) { /* Constant value case, e.g., 4@71 */ arg->arg_type = USDT_ARG_CONST; arg->val_off = off; @@ -1315,20 +1410,6 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec return -EINVAL; } - arg->arg_signed = arg_sz < 0; - if (arg_sz < 0) - arg_sz = -arg_sz; - - switch (arg_sz) { - case 1: case 2: case 4: case 8: - arg->arg_bitshift = 64 - arg_sz * 8; - break; - default: - pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", - arg_num, arg_str, arg_sz); - return -EINVAL; - } - return len; } @@ -1348,13 +1429,13 @@ static int calc_pt_regs_off(const char *reg_name) return -ENOENT; } -static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz) { char reg_name[16]; - int arg_sz, len, reg_off; + int len, reg_off; long off; - if (sscanf(arg_str, " %d @ \[ %15[a-z0-9], %ld ] %n", &arg_sz, reg_name, &off, &len) == 3) { + if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] , %ld ] %n", arg_sz, reg_name, &off, &len) == 3) { /* Memory dereference case, e.g., -4@[sp, 96] */ arg->arg_type = USDT_ARG_REG_DEREF; arg->val_off = off; @@ -1362,7 +1443,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec if (reg_off < 0) return reg_off; arg->reg_off = reg_off; - } else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", &arg_sz, reg_name, &len) == 2) { + } else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", arg_sz, reg_name, &len) == 2) { /* Memory dereference case, e.g., -4@[sp] */ arg->arg_type = USDT_ARG_REG_DEREF; arg->val_off = 0; @@ -1370,12 +1451,12 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec if (reg_off < 0) return reg_off; arg->reg_off = reg_off; - } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { + } else if (sscanf(arg_str, " %d @ %ld %n", arg_sz, &off, &len) == 2) { /* Constant value case, e.g., 4@5 */ arg->arg_type = USDT_ARG_CONST; arg->val_off = off; arg->reg_off = 0; - } else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) { + } else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", arg_sz, reg_name, &len) == 2) { /* Register read case, e.g., -8@x4 */ arg->arg_type = USDT_ARG_REG; arg->val_off = 0; @@ -1388,20 +1469,6 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec return -EINVAL; } - arg->arg_signed = arg_sz < 0; - if (arg_sz < 0) - arg_sz = -arg_sz; - - switch (arg_sz) { - case 1: case 2: case 4: case 8: - arg->arg_bitshift = 64 - arg_sz * 8; - break; - default: - pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", - arg_num, arg_str, arg_sz); - return -EINVAL; - } - return len; } @@ -1456,13 +1523,13 @@ static int calc_pt_regs_off(const char *reg_name) return -ENOENT; } -static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz) { char reg_name[16]; - int arg_sz, len, reg_off; + int len, reg_off; long off; - if (sscanf(arg_str, " %d @ %ld ( %15[a-z0-9] ) %n", &arg_sz, &off, reg_name, &len) == 3) { + if (sscanf(arg_str, " %d @ %ld ( %15[a-z0-9] ) %n", arg_sz, &off, reg_name, &len) == 3) { /* Memory dereference case, e.g., -8@-88(s0) */ arg->arg_type = USDT_ARG_REG_DEREF; arg->val_off = off; @@ -1470,12 +1537,12 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec if (reg_off < 0) return reg_off; arg->reg_off = reg_off; - } else if (sscanf(arg_str, " %d @ %ld %n", &arg_sz, &off, &len) == 2) { + } else if (sscanf(arg_str, " %d @ %ld %n", arg_sz, &off, &len) == 2) { /* Constant value case, e.g., 4@5 */ arg->arg_type = USDT_ARG_CONST; arg->val_off = off; arg->reg_off = 0; - } else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", &arg_sz, reg_name, &len) == 2) { + } else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", arg_sz, reg_name, &len) == 2) { /* Register read case, e.g., -8@a1 */ arg->arg_type = USDT_ARG_REG; arg->val_off = 0; @@ -1488,17 +1555,83 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec return -EINVAL; } - arg->arg_signed = arg_sz < 0; - if (arg_sz < 0) - arg_sz = -arg_sz; + return len; +} - switch (arg_sz) { - case 1: case 2: case 4: case 8: - arg->arg_bitshift = 64 - arg_sz * 8; - break; - default: - pr_warn("usdt: unsupported arg #%d (spec '%s') size: %d\n", - arg_num, arg_str, arg_sz); +#elif defined(__arm__) + +static int calc_pt_regs_off(const char *reg_name) +{ + static struct { + const char *name; + size_t pt_regs_off; + } reg_map[] = { + { "r0", offsetof(struct pt_regs, uregs[0]) }, + { "r1", offsetof(struct pt_regs, uregs[1]) }, + { "r2", offsetof(struct pt_regs, uregs[2]) }, + { "r3", offsetof(struct pt_regs, uregs[3]) }, + { "r4", offsetof(struct pt_regs, uregs[4]) }, + { "r5", offsetof(struct pt_regs, uregs[5]) }, + { "r6", offsetof(struct pt_regs, uregs[6]) }, + { "r7", offsetof(struct pt_regs, uregs[7]) }, + { "r8", offsetof(struct pt_regs, uregs[8]) }, + { "r9", offsetof(struct pt_regs, uregs[9]) }, + { "r10", offsetof(struct pt_regs, uregs[10]) }, + { "fp", offsetof(struct pt_regs, uregs[11]) }, + { "ip", offsetof(struct pt_regs, uregs[12]) }, + { "sp", offsetof(struct pt_regs, uregs[13]) }, + { "lr", offsetof(struct pt_regs, uregs[14]) }, + { "pc", offsetof(struct pt_regs, uregs[15]) }, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(reg_map); i++) { + if (strcmp(reg_name, reg_map[i].name) == 0) + return reg_map[i].pt_regs_off; + } + + pr_warn("usdt: unrecognized register '%s'\n", reg_name); + return -ENOENT; +} + +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz) +{ + char reg_name[16]; + int len, reg_off; + long off; + + if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] , #%ld ] %n", + arg_sz, reg_name, &off, &len) == 3) { + /* Memory dereference case, e.g., -4@[fp, #96] */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = off; + reg_off = calc_pt_regs_off(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ \[ %15[a-z0-9] ] %n", arg_sz, reg_name, &len) == 2) { + /* Memory dereference case, e.g., -4@[sp] */ + arg->arg_type = USDT_ARG_REG_DEREF; + arg->val_off = 0; + reg_off = calc_pt_regs_off(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else if (sscanf(arg_str, " %d @ #%ld %n", arg_sz, &off, &len) == 2) { + /* Constant value case, e.g., 4@#5 */ + arg->arg_type = USDT_ARG_CONST; + arg->val_off = off; + arg->reg_off = 0; + } else if (sscanf(arg_str, " %d @ %15[a-z0-9] %n", arg_sz, reg_name, &len) == 2) { + /* Register read case, e.g., -8@r4 */ + arg->arg_type = USDT_ARG_REG; + arg->val_off = 0; + reg_off = calc_pt_regs_off(reg_name); + if (reg_off < 0) + return reg_off; + arg->reg_off = reg_off; + } else { + pr_warn("usdt: unrecognized arg #%d spec '%s'\n", arg_num, arg_str); return -EINVAL; } @@ -1507,7 +1640,7 @@ static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec #else -static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg) +static int parse_usdt_arg(const char *arg_str, int arg_num, struct usdt_arg_spec *arg, int *arg_sz) { pr_warn("usdt: libbpf doesn't support USDTs on current architecture\n"); return -ENOTSUP; diff --git a/tools/lib/bpf/zip.c b/tools/lib/bpf/zip.c new file mode 100644 index 000000000000..88c376a8348d --- /dev/null +++ b/tools/lib/bpf/zip.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* + * Routines for dealing with .zip archives. + * + * Copyright (c) Meta Platforms, Inc. and affiliates. + */ + +#include <errno.h> +#include <fcntl.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <unistd.h> + +#include "libbpf_internal.h" +#include "zip.h" + +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wpacked" +#pragma GCC diagnostic ignored "-Wattributes" + +/* Specification of ZIP file format can be found here: + * https://pkware.cachefly.net/webdocs/casestudies/APPNOTE.TXT + * For a high level overview of the structure of a ZIP file see + * sections 4.3.1 - 4.3.6. + * + * Data structures appearing in ZIP files do not contain any + * padding and they might be misaligned. To allow us to safely + * operate on pointers to such structures and their members, we + * declare the types as packed. + */ + +#define END_OF_CD_RECORD_MAGIC 0x06054b50 + +/* See section 4.3.16 of the spec. */ +struct end_of_cd_record { + /* Magic value equal to END_OF_CD_RECORD_MAGIC */ + __u32 magic; + + /* Number of the file containing this structure or 0xFFFF if ZIP64 archive. + * Zip archive might span multiple files (disks). + */ + __u16 this_disk; + + /* Number of the file containing the beginning of the central directory or + * 0xFFFF if ZIP64 archive. + */ + __u16 cd_disk; + + /* Number of central directory records on this disk or 0xFFFF if ZIP64 + * archive. + */ + __u16 cd_records; + + /* Number of central directory records on all disks or 0xFFFF if ZIP64 + * archive. + */ + __u16 cd_records_total; + + /* Size of the central directory record or 0xFFFFFFFF if ZIP64 archive. */ + __u32 cd_size; + + /* Offset of the central directory from the beginning of the archive or + * 0xFFFFFFFF if ZIP64 archive. + */ + __u32 cd_offset; + + /* Length of comment data following end of central directory record. */ + __u16 comment_length; + + /* Up to 64k of arbitrary bytes. */ + /* uint8_t comment[comment_length] */ +} __attribute__((packed)); + +#define CD_FILE_HEADER_MAGIC 0x02014b50 +#define FLAG_ENCRYPTED (1 << 0) +#define FLAG_HAS_DATA_DESCRIPTOR (1 << 3) + +/* See section 4.3.12 of the spec. */ +struct cd_file_header { + /* Magic value equal to CD_FILE_HEADER_MAGIC. */ + __u32 magic; + __u16 version; + /* Minimum zip version needed to extract the file. */ + __u16 min_version; + __u16 flags; + __u16 compression; + __u16 last_modified_time; + __u16 last_modified_date; + __u32 crc; + __u32 compressed_size; + __u32 uncompressed_size; + __u16 file_name_length; + __u16 extra_field_length; + __u16 file_comment_length; + /* Number of the disk where the file starts or 0xFFFF if ZIP64 archive. */ + __u16 disk; + __u16 internal_attributes; + __u32 external_attributes; + /* Offset from the start of the disk containing the local file header to the + * start of the local file header. + */ + __u32 offset; +} __attribute__((packed)); + +#define LOCAL_FILE_HEADER_MAGIC 0x04034b50 + +/* See section 4.3.7 of the spec. */ +struct local_file_header { + /* Magic value equal to LOCAL_FILE_HEADER_MAGIC. */ + __u32 magic; + /* Minimum zip version needed to extract the file. */ + __u16 min_version; + __u16 flags; + __u16 compression; + __u16 last_modified_time; + __u16 last_modified_date; + __u32 crc; + __u32 compressed_size; + __u32 uncompressed_size; + __u16 file_name_length; + __u16 extra_field_length; +} __attribute__((packed)); + +#pragma GCC diagnostic pop + +struct zip_archive { + void *data; + __u32 size; + __u32 cd_offset; + __u32 cd_records; +}; + +static void *check_access(struct zip_archive *archive, __u32 offset, __u32 size) +{ + if (offset + size > archive->size || offset > offset + size) + return NULL; + + return archive->data + offset; +} + +/* Returns 0 on success, -EINVAL on error and -ENOTSUP if the eocd indicates the + * archive uses features which are not supported. + */ +static int try_parse_end_of_cd(struct zip_archive *archive, __u32 offset) +{ + __u16 comment_length, cd_records; + struct end_of_cd_record *eocd; + __u32 cd_offset, cd_size; + + eocd = check_access(archive, offset, sizeof(*eocd)); + if (!eocd || eocd->magic != END_OF_CD_RECORD_MAGIC) + return -EINVAL; + + comment_length = eocd->comment_length; + if (offset + sizeof(*eocd) + comment_length != archive->size) + return -EINVAL; + + cd_records = eocd->cd_records; + if (eocd->this_disk != 0 || eocd->cd_disk != 0 || eocd->cd_records_total != cd_records) + /* This is a valid eocd, but we only support single-file non-ZIP64 archives. */ + return -ENOTSUP; + + cd_offset = eocd->cd_offset; + cd_size = eocd->cd_size; + if (!check_access(archive, cd_offset, cd_size)) + return -EINVAL; + + archive->cd_offset = cd_offset; + archive->cd_records = cd_records; + return 0; +} + +static int find_cd(struct zip_archive *archive) +{ + int64_t limit, offset; + int rc = -EINVAL; + + if (archive->size <= sizeof(struct end_of_cd_record)) + return -EINVAL; + + /* Because the end of central directory ends with a variable length array of + * up to 0xFFFF bytes we can't know exactly where it starts and need to + * search for it at the end of the file, scanning the (limit, offset] range. + */ + offset = archive->size - sizeof(struct end_of_cd_record); + limit = (int64_t)offset - (1 << 16); + + for (; offset >= 0 && offset > limit && rc != 0; offset--) { + rc = try_parse_end_of_cd(archive, offset); + if (rc == -ENOTSUP) + break; + } + return rc; +} + +struct zip_archive *zip_archive_open(const char *path) +{ + struct zip_archive *archive; + int err, fd; + off_t size; + void *data; + + fd = open(path, O_RDONLY | O_CLOEXEC); + if (fd < 0) + return ERR_PTR(-errno); + + size = lseek(fd, 0, SEEK_END); + if (size == (off_t)-1 || size > UINT32_MAX) { + close(fd); + return ERR_PTR(-EINVAL); + } + + data = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0); + err = -errno; + close(fd); + + if (data == MAP_FAILED) + return ERR_PTR(err); + + archive = malloc(sizeof(*archive)); + if (!archive) { + munmap(data, size); + return ERR_PTR(-ENOMEM); + } + + archive->data = data; + archive->size = size; + + err = find_cd(archive); + if (err) { + munmap(data, size); + free(archive); + return ERR_PTR(err); + } + + return archive; +} + +void zip_archive_close(struct zip_archive *archive) +{ + munmap(archive->data, archive->size); + free(archive); +} + +static struct local_file_header *local_file_header_at_offset(struct zip_archive *archive, + __u32 offset) +{ + struct local_file_header *lfh; + + lfh = check_access(archive, offset, sizeof(*lfh)); + if (!lfh || lfh->magic != LOCAL_FILE_HEADER_MAGIC) + return NULL; + + return lfh; +} + +static int get_entry_at_offset(struct zip_archive *archive, __u32 offset, struct zip_entry *out) +{ + struct local_file_header *lfh; + __u32 compressed_size; + const char *name; + void *data; + + lfh = local_file_header_at_offset(archive, offset); + if (!lfh) + return -EINVAL; + + offset += sizeof(*lfh); + if ((lfh->flags & FLAG_ENCRYPTED) || (lfh->flags & FLAG_HAS_DATA_DESCRIPTOR)) + return -EINVAL; + + name = check_access(archive, offset, lfh->file_name_length); + if (!name) + return -EINVAL; + + offset += lfh->file_name_length; + if (!check_access(archive, offset, lfh->extra_field_length)) + return -EINVAL; + + offset += lfh->extra_field_length; + compressed_size = lfh->compressed_size; + data = check_access(archive, offset, compressed_size); + if (!data) + return -EINVAL; + + out->compression = lfh->compression; + out->name_length = lfh->file_name_length; + out->name = name; + out->data = data; + out->data_length = compressed_size; + out->data_offset = offset; + + return 0; +} + +int zip_archive_find_entry(struct zip_archive *archive, const char *file_name, + struct zip_entry *out) +{ + size_t file_name_length = strlen(file_name); + __u32 i, offset = archive->cd_offset; + + for (i = 0; i < archive->cd_records; ++i) { + __u16 cdfh_name_length, cdfh_flags; + struct cd_file_header *cdfh; + const char *cdfh_name; + + cdfh = check_access(archive, offset, sizeof(*cdfh)); + if (!cdfh || cdfh->magic != CD_FILE_HEADER_MAGIC) + return -EINVAL; + + offset += sizeof(*cdfh); + cdfh_name_length = cdfh->file_name_length; + cdfh_name = check_access(archive, offset, cdfh_name_length); + if (!cdfh_name) + return -EINVAL; + + cdfh_flags = cdfh->flags; + if ((cdfh_flags & FLAG_ENCRYPTED) == 0 && + (cdfh_flags & FLAG_HAS_DATA_DESCRIPTOR) == 0 && + file_name_length == cdfh_name_length && + memcmp(file_name, archive->data + offset, file_name_length) == 0) { + return get_entry_at_offset(archive, cdfh->offset, out); + } + + offset += cdfh_name_length; + offset += cdfh->extra_field_length; + offset += cdfh->file_comment_length; + } + + return -ENOENT; +} diff --git a/tools/lib/bpf/zip.h b/tools/lib/bpf/zip.h new file mode 100644 index 000000000000..1c1bb21fba76 --- /dev/null +++ b/tools/lib/bpf/zip.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +#ifndef __LIBBPF_ZIP_H +#define __LIBBPF_ZIP_H + +#include <linux/types.h> + +/* Represents an open zip archive. + * Only basic ZIP files are supported, in particular the following are not + * supported: + * - encryption + * - streaming + * - multi-part ZIP files + * - ZIP64 + */ +struct zip_archive; + +/* Carries information on name, compression method, and data corresponding to a + * file in a zip archive. + */ +struct zip_entry { + /* Compression method as defined in pkzip spec. 0 means data is uncompressed. */ + __u16 compression; + + /* Non-null terminated name of the file. */ + const char *name; + /* Length of the file name. */ + __u16 name_length; + + /* Pointer to the file data. */ + const void *data; + /* Length of the file data. */ + __u32 data_length; + /* Offset of the file data within the archive. */ + __u32 data_offset; +}; + +/* Open a zip archive. Returns NULL in case of an error. */ +struct zip_archive *zip_archive_open(const char *path); + +/* Close a zip archive and release resources. */ +void zip_archive_close(struct zip_archive *archive); + +/* Look up an entry corresponding to a file in given zip archive. */ +int zip_archive_find_entry(struct zip_archive *archive, const char *name, struct zip_entry *out); + +#endif |