diff options
Diffstat (limited to 'tools/lib/bpf')
29 files changed, 8241 insertions, 1330 deletions
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 4db74758c674..35bf013e368c 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -1,3 +1,9 @@ libbpf_version.h +libbpf.pc FEATURE-DUMP.libbpf test_libbpf +libbpf.so.* +TAGS +tags +cscope.* +/bpf_helper_defs.h diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index ee9d5362f35b..e3962cfbc9a6 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1 +1,3 @@ -libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o +libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ + netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \ + btf_dump.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 8e7c56e9590f..99425d0be6ff 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -1,13 +1,18 @@ # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) # Most of this file is copied from tools/lib/traceevent/Makefile -BPF_VERSION = 0 -BPF_PATCHLEVEL = 0 -BPF_EXTRAVERSION = 2 +LIBBPF_VERSION := $(shell \ + grep -oE '^LIBBPF_([0-9.]+)' libbpf.map | \ + sort -rV | head -n1 | cut -d'_' -f2) +LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION))) MAKEFLAGS += --no-print-directory -ifeq ($(srctree),) +# This will work when bpf is built in tools env. where srctree +# isn't set and when invoked from selftests build, where srctree +# is a ".". building_out_of_srctree is undefined for in srctree +# builds +ifndef building_out_of_srctree srctree := $(patsubst %/,%,$(dir $(CURDIR))) srctree := $(patsubst %/,%,$(dir $(srctree))) srctree := $(patsubst %/,%,$(dir $(srctree))) @@ -51,7 +56,7 @@ ifndef VERBOSE endif FEATURE_USER = .libbpf -FEATURE_TESTS = libelf libelf-mmap bpf reallocarray cxx +FEATURE_TESTS = libelf libelf-mmap bpf reallocarray FEATURE_DISPLAY = libelf bpf INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi @@ -79,17 +84,12 @@ export prefix libdir src obj libdir_SQ = $(subst ','\'',$(libdir)) libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) -VERSION = $(BPF_VERSION) -PATCHLEVEL = $(BPF_PATCHLEVEL) -EXTRAVERSION = $(BPF_EXTRAVERSION) - OBJ = $@ N = -LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION) - LIB_TARGET = libbpf.a libbpf.so.$(LIBBPF_VERSION) LIB_FILE = libbpf.a libbpf.so* +PC_FILE = libbpf.pc # Set compile option CFLAGS ifdef EXTRA_CFLAGS @@ -112,6 +112,10 @@ override CFLAGS += -Werror -Wall override CFLAGS += -fPIC override CFLAGS += $(INCLUDES) override CFLAGS += -fvisibility=hidden +override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 + +# flags specific for shared library +SHLIB_FLAGS := -DSHARED ifeq ($(VERBOSE),1) Q = @@ -129,33 +133,33 @@ all: export srctree OUTPUT CC LD CFLAGS V include $(srctree)/tools/build/Makefile.include -BPF_IN := $(OUTPUT)libbpf-in.o +SHARED_OBJDIR := $(OUTPUT)sharedobjs/ +STATIC_OBJDIR := $(OUTPUT)staticobjs/ +BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o +BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o VERSION_SCRIPT := libbpf.map LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) +PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE)) + +TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags) -GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}') +GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ + cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}' | \ + sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) -CMD_TARGETS = $(LIB_TARGET) - -CXX_TEST_TARGET = $(OUTPUT)test_libbpf - -ifeq ($(feature-cxx), 1) - CMD_TARGETS += $(CXX_TEST_TARGET) -endif - -TARGETS = $(CMD_TARGETS) +CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) $(OUTPUT)test_libbpf all: fixdep $(Q)$(MAKE) all_cmd all_cmd: $(CMD_TARGETS) check -$(BPF_IN): force elfdep bpfdep +$(BPF_IN_SHARED): force elfdep bpfdep bpf_helper_defs.h @(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 @@ -171,31 +175,56 @@ $(BPF_IN): force elfdep bpfdep @(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 - $(Q)$(MAKE) $(build)=libbpf + $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" + +$(BPF_IN_STATIC): force elfdep bpfdep bpf_helper_defs.h + $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) + +bpf_helper_defs.h: $(srctree)/include/uapi/linux/bpf.h + $(Q)$(srctree)/scripts/bpf_helpers_doc.py --header \ + --file $(srctree)/include/uapi/linux/bpf.h > bpf_helper_defs.h $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION) -$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN) - $(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \ - -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@ +$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) + $(QUIET_LINK)$(CC) $(LDFLAGS) \ + --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@ @ln -sf $(@F) $(OUTPUT)libbpf.so - @ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION) + @ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION) -$(OUTPUT)libbpf.a: $(BPF_IN) +$(OUTPUT)libbpf.a: $(BPF_IN_STATIC) $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ -$(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a - $(QUIET_LINK)$(CXX) $(INCLUDES) $^ -lelf -o $@ +$(OUTPUT)test_libbpf: test_libbpf.c $(OUTPUT)libbpf.a + $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(INCLUDES) $^ -lelf -o $@ + +$(OUTPUT)libbpf.pc: + $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ + -e "s|@LIBDIR@|$(libdir_SQ)|" \ + -e "s|@VERSION@|$(LIBBPF_VERSION)|" \ + < libbpf.pc.template > $@ check: check_abi check_abi: $(OUTPUT)libbpf.so @if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then \ - echo "Warning: Num of global symbols in $(BPF_IN)" \ + echo "Warning: Num of global symbols in $(BPF_IN_SHARED)" \ "($(GLOBAL_SYM_COUNT)) does NOT match with num of" \ "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \ "Please make sure all LIBBPF_API symbols are" \ "versioned in $(VERSION_SCRIPT)." >&2; \ + readelf -s --wide $(OUTPUT)libbpf-in.o | \ + cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}'| \ + sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ + readelf -s --wide $(OUTPUT)libbpf.so | \ + grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ + sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ + diff -u $(OUTPUT)libbpf_global_syms.tmp \ + $(OUTPUT)libbpf_versioned_syms.tmp; \ + rm $(OUTPUT)libbpf_global_syms.tmp \ + $(OUTPUT)libbpf_versioned_syms.tmp; \ exit 1; \ fi @@ -217,14 +246,24 @@ install_lib: all_cmd $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) -install_headers: +install_headers: bpf_helper_defs.h $(call QUIET_INSTALL, headers) \ $(call do_install,bpf.h,$(prefix)/include/bpf,644); \ $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ $(call do_install,btf.h,$(prefix)/include/bpf,644); \ - $(call do_install,xsk.h,$(prefix)/include/bpf,644); + $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \ + $(call do_install,xsk.h,$(prefix)/include/bpf,644); \ + $(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \ + $(call do_install,bpf_helper_defs.h,$(prefix)/include/bpf,644); \ + $(call do_install,bpf_tracing.h,$(prefix)/include/bpf,644); \ + $(call do_install,bpf_endian.h,$(prefix)/include/bpf,644); \ + $(call do_install,bpf_core_read.h,$(prefix)/include/bpf,644); + +install_pkgconfig: $(PC_FILE) + $(call QUIET_INSTALL, $(PC_FILE)) \ + $(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644) -install: install_lib +install: install_lib install_pkgconfig ### Cleaning rules @@ -233,13 +272,15 @@ config-clean: $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null clean: - $(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \ - *.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd LIBBPF-CFLAGS + $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ + *.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \ + *.pc LIBBPF-CFLAGS bpf_helper_defs.h \ + $(SHARED_OBJDIR) $(STATIC_OBJDIR) $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf -PHONY += force elfdep bpfdep +PHONY += force elfdep bpfdep cscope tags force: elfdep: @@ -248,6 +289,17 @@ elfdep: bpfdep: @if [ "$(feature-bpf)" != "1" ]; then echo "BPF API too old"; exit 1 ; fi +cscope: + ls *.c *.h > cscope.files + cscope -b -q -I $(srctree)/include -f cscope.out + +tags: + rm -f TAGS tags + ls *.c *.h | xargs $(TAGS_PROG) -a + # Declare the contents of the .PHONY variable as phony. We keep that # information in a variable so we can use it in if_changed and friends. .PHONY: $(PHONY) + +# Delete partially updated (corrupted) files on error +.DELETE_ON_ERROR: diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst index cef7b77eab69..8928f7787f2d 100644 --- a/tools/lib/bpf/README.rst +++ b/tools/lib/bpf/README.rst @@ -9,7 +9,8 @@ described here. It's recommended to follow these conventions whenever a new function or type is added to keep libbpf API clean and consistent. All types and functions provided by libbpf API should have one of the -following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``. +following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``, +``perf_buffer_``. System call wrappers -------------------- diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9cd015574e83..98596e15390f 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -26,10 +26,11 @@ #include <memory.h> #include <unistd.h> #include <asm/unistd.h> +#include <errno.h> #include <linux/bpf.h> #include "bpf.h" #include "libbpf.h" -#include <errno.h> +#include "libbpf_internal.h" /* * When building perf, unistd.h is overridden. __NR_bpf is @@ -46,15 +47,13 @@ # define __NR_bpf 349 # elif defined(__s390__) # define __NR_bpf 351 +# elif defined(__arc__) +# define __NR_bpf 280 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif #endif -#ifndef min -#define min(x, y) ((x) < (y) ? (x) : (y)) -#endif - static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; @@ -79,7 +78,6 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size) int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) { - __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); @@ -89,8 +87,9 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) attr.value_size = create_attr->value_size; attr.max_entries = create_attr->max_entries; attr.map_flags = create_attr->map_flags; - memcpy(attr.map_name, create_attr->name, - min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (create_attr->name) + memcpy(attr.map_name, create_attr->name, + min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1)); attr.numa_node = create_attr->numa_node; attr.btf_fd = create_attr->btf_fd; attr.btf_key_type_id = create_attr->btf_key_type_id; @@ -155,7 +154,6 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node) { - __u32 name_len = name ? strlen(name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); @@ -166,7 +164,9 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, attr.inner_map_fd = inner_map_fd; attr.max_entries = max_entries; attr.map_flags = map_flags; - memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (name) + memcpy(attr.map_name, name, + min(strlen(name), BPF_OBJ_NAME_LEN - 1)); if (node >= 0) { attr.map_flags |= BPF_F_NUMA_NODE; @@ -189,7 +189,7 @@ static void * alloc_zero_tailing_info(const void *orecord, __u32 cnt, __u32 actual_rec_size, __u32 expected_rec_size) { - __u64 info_len = actual_rec_size * cnt; + __u64 info_len = (__u64)actual_rec_size * cnt; void *info, *nrecord; int i; @@ -216,21 +216,25 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, void *finfo = NULL, *linfo = NULL; union bpf_attr attr; __u32 log_level; - __u32 name_len; int fd; if (!load_attr || !log_buf != !log_buf_sz) return -EINVAL; log_level = load_attr->log_level; - if (log_level > 2 || (log_level && !log_buf)) + if (log_level > (4 | 2 | 1) || (log_level && !log_buf)) return -EINVAL; - name_len = load_attr->name ? strlen(load_attr->name) : 0; - memset(&attr, 0, sizeof(attr)); attr.prog_type = load_attr->prog_type; attr.expected_attach_type = load_attr->expected_attach_type; + if (attr.prog_type == BPF_PROG_TYPE_TRACING) { + attr.attach_btf_id = load_attr->attach_btf_id; + attr.attach_prog_fd = load_attr->attach_prog_fd; + } else { + attr.prog_ifindex = load_attr->prog_ifindex; + attr.kern_version = load_attr->kern_version; + } attr.insn_cnt = (__u32)load_attr->insns_cnt; attr.insns = ptr_to_u64(load_attr->insns); attr.license = ptr_to_u64(load_attr->license); @@ -244,8 +248,6 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, attr.log_size = 0; } - attr.kern_version = load_attr->kern_version; - attr.prog_ifindex = load_attr->prog_ifindex; attr.prog_btf_fd = load_attr->prog_btf_fd; attr.func_info_rec_size = load_attr->func_info_rec_size; attr.func_info_cnt = load_attr->func_info_cnt; @@ -253,8 +255,10 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, attr.line_info_rec_size = load_attr->line_info_rec_size; attr.line_info_cnt = load_attr->line_info_cnt; attr.line_info = ptr_to_u64(load_attr->line_info); - memcpy(attr.prog_name, load_attr->name, - min(name_len, BPF_OBJ_NAME_LEN - 1)); + if (load_attr->name) + memcpy(attr.prog_name, load_attr->name, + min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1)); + attr.prog_flags = load_attr->prog_flags; fd = sys_bpf_prog_load(&attr, sizeof(attr)); if (fd >= 0) @@ -429,6 +433,16 @@ int bpf_map_get_next_key(int fd, const void *key, void *next_key) return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); } +int bpf_map_freeze(int fd) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + + return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); +} + int bpf_obj_pin(int fd, const char *pathname) { union bpf_attr attr; @@ -545,16 +559,21 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) attr.test.data_out = ptr_to_u64(test_attr->data_out); attr.test.data_size_in = test_attr->data_size_in; attr.test.data_size_out = test_attr->data_size_out; + attr.test.ctx_in = ptr_to_u64(test_attr->ctx_in); + attr.test.ctx_out = ptr_to_u64(test_attr->ctx_out); + attr.test.ctx_size_in = test_attr->ctx_size_in; + attr.test.ctx_size_out = test_attr->ctx_size_out; attr.test.repeat = test_attr->repeat; ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); test_attr->data_size_out = attr.test.data_size_out; + test_attr->ctx_size_out = attr.test.ctx_size_out; test_attr->retval = attr.test.retval; test_attr->duration = attr.test.duration; return ret; } -int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) +static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd) { union bpf_attr attr; int err; @@ -562,26 +581,26 @@ int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) memset(&attr, 0, sizeof(attr)); attr.start_id = start_id; - err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr)); + err = sys_bpf(cmd, &attr, sizeof(attr)); if (!err) *next_id = attr.next_id; return err; } -int bpf_map_get_next_id(__u32 start_id, __u32 *next_id) +int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) { - union bpf_attr attr; - int err; - - memset(&attr, 0, sizeof(attr)); - attr.start_id = start_id; + return bpf_obj_get_next_id(start_id, next_id, BPF_PROG_GET_NEXT_ID); +} - err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr)); - if (!err) - *next_id = attr.next_id; +int bpf_map_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_MAP_GET_NEXT_ID); +} - return err; +int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id) +{ + return bpf_obj_get_next_id(start_id, next_id, BPF_BTF_GET_NEXT_ID); } int bpf_prog_get_fd_by_id(__u32 id) diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 6ffdd79bea89..3c791fa8e68e 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -26,6 +26,7 @@ #include <linux/bpf.h> #include <stdbool.h> #include <stddef.h> +#include <stdint.h> #ifdef __cplusplus extern "C" { @@ -76,8 +77,14 @@ struct bpf_load_program_attr { const struct bpf_insn *insns; size_t insns_cnt; const char *license; - __u32 kern_version; - __u32 prog_ifindex; + union { + __u32 kern_version; + __u32 attach_prog_fd; + }; + union { + __u32 prog_ifindex; + __u32 attach_btf_id; + }; __u32 prog_btf_fd; __u32 func_info_rec_size; const void *func_info; @@ -86,13 +93,14 @@ struct bpf_load_program_attr { const void *line_info; __u32 line_info_cnt; __u32 log_level; + __u32 prog_flags; }; /* Flags to direct loading requirements */ #define MAPS_RELAX_COMPAT 0x01 /* Recommend log buffer size */ -#define BPF_LOG_BUF_SIZE (256 * 1024) +#define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */ LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, char *log_buf, size_t log_buf_sz); @@ -117,6 +125,7 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value); LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); +LIBBPF_API int bpf_map_freeze(int 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_prog_attach(int prog_fd, int attachable_fd, @@ -135,6 +144,11 @@ struct bpf_prog_test_run_attr { * out: length of data_out */ __u32 retval; /* out: return code of the BPF program */ __u32 duration; /* out: average per repetition in ns */ + const void *ctx_in; /* optional */ + __u32 ctx_size_in; + void *ctx_out; /* optional */ + __u32 ctx_size_out; /* in: max length of ctx_out + * out: length of cxt_out */ }; LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr); @@ -148,6 +162,7 @@ LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 *retval, __u32 *duration); LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); +LIBBPF_API int bpf_btf_get_next_id(__u32 start_id, __u32 *next_id); LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id); LIBBPF_API int bpf_map_get_fd_by_id(__u32 id); LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id); diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h new file mode 100644 index 000000000000..7009dc90e012 --- /dev/null +++ b/tools/lib/bpf/bpf_core_read.h @@ -0,0 +1,263 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_CORE_READ_H__ +#define __BPF_CORE_READ_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 + * a field, captured as a first argument. __builtin_preserve_field_info(field, + * info_kind) returns __u32 integer and produces BTF field relocation, which + * is understood and processed by libbpf during BPF object loading. See + * selftests/bpf for examples. + */ +enum bpf_field_info_kind { + BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_FIELD_BYTE_SIZE = 1, + BPF_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_FIELD_SIGNED = 3, + BPF_FIELD_LSHIFT_U64 = 4, + BPF_FIELD_RSHIFT_U64 = 5, +}; + +#define __CORE_RELO(src, field, info) \ + __builtin_preserve_field_info((src)->field, BPF_FIELD_##info) + +#if __BYTE_ORDER == __LITTLE_ENDIAN +#define __CORE_BITFIELD_PROBE_READ(dst, src, fld) \ + bpf_probe_read((void *)dst, \ + __CORE_RELO(src, fld, BYTE_SIZE), \ + (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) +#else +/* semantics of LSHIFT_64 assumes loading values into low-ordered bytes, so + * for big-endian we need to adjust destination pointer accordingly, based on + * field byte size + */ +#define __CORE_BITFIELD_PROBE_READ(dst, src, fld) \ + bpf_probe_read((void *)dst + (8 - __CORE_RELO(src, fld, BYTE_SIZE)), \ + __CORE_RELO(src, fld, BYTE_SIZE), \ + (const void *)src + __CORE_RELO(src, fld, BYTE_OFFSET)) +#endif + +/* + * Extract bitfield, identified by s->field, and return its value as u64. + * All this is done in relocatable manner, so bitfield changes such as + * signedness, bit size, offset changes, this will be handled automatically. + * This version of macro is using bpf_probe_read() to read underlying integer + * storage. Macro functions as an expression and its return type is + * bpf_probe_read()'s return value: 0, on success, <0 on error. + */ +#define BPF_CORE_READ_BITFIELD_PROBED(s, field) ({ \ + unsigned long long val = 0; \ + \ + __CORE_BITFIELD_PROBE_READ(&val, s, field); \ + val <<= __CORE_RELO(s, field, LSHIFT_U64); \ + if (__CORE_RELO(s, field, SIGNED)) \ + val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64); \ + else \ + val = val >> __CORE_RELO(s, field, RSHIFT_U64); \ + val; \ +}) + +/* + * Extract bitfield, identified by s->field, and return its value as u64. + * This version of macro is using direct memory reads and should be used from + * BPF program types that support such functionality (e.g., typed raw + * tracepoints). + */ +#define BPF_CORE_READ_BITFIELD(s, field) ({ \ + const void *p = (const void *)s + __CORE_RELO(s, field, BYTE_OFFSET); \ + unsigned long long val; \ + \ + switch (__CORE_RELO(s, field, BYTE_SIZE)) { \ + case 1: val = *(const unsigned char *)p; \ + case 2: val = *(const unsigned short *)p; \ + case 4: val = *(const unsigned int *)p; \ + case 8: val = *(const unsigned long long *)p; \ + } \ + val <<= __CORE_RELO(s, field, LSHIFT_U64); \ + if (__CORE_RELO(s, field, SIGNED)) \ + val = ((long long)val) >> __CORE_RELO(s, field, RSHIFT_U64); \ + else \ + val = val >> __CORE_RELO(s, field, RSHIFT_U64); \ + val; \ +}) + +/* + * Convenience macro to check that field actually exists in target kernel's. + * Returns: + * 1, if matching field is present in target kernel; + * 0, if no matching field found. + */ +#define bpf_core_field_exists(field) \ + __builtin_preserve_field_info(field, BPF_FIELD_EXISTS) + +/* + * Convenience macro to get byte size of a field. Works for integers, + * struct/unions, pointers, arrays, and enums. + */ +#define bpf_core_field_size(field) \ + __builtin_preserve_field_info(field, BPF_FIELD_BYTE_SIZE) + +/* + * bpf_core_read() abstracts away bpf_probe_read() call and captures offset + * relocation for source address using __builtin_preserve_access_index() + * built-in, provided by Clang. + * + * __builtin_preserve_access_index() takes as an argument an expression of + * taking an address of a field within struct/union. It makes compiler emit + * 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. + * + * This relocation allows libbpf to adjust BPF instruction to use correct + * actual field offset, based on target kernel BTF type that matches original + * (local) BTF, used to record relocation. + */ +#define bpf_core_read(dst, sz, src) \ + bpf_probe_read(dst, sz, \ + (const void *)__builtin_preserve_access_index(src)) + +/* + * bpf_core_read_str() is a thin wrapper around bpf_probe_read_str() + * additionally emitting BPF CO-RE field relocation for specified source + * argument. + */ +#define bpf_core_read_str(dst, sz, src) \ + bpf_probe_read_str(dst, sz, \ + (const void *)__builtin_preserve_access_index(src)) + +#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 + +/* + * return number of provided arguments; used for switch-based variadic macro + * definitions (see ___last, ___arrow, etc below) + */ +#define ___narg(...) ___nth(_, ##__VA_ARGS__, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +/* + * return 0 if no arguments are passed, N - otherwise; used for + * recursively-defined macros to specify termination (0) case, and generic + * (N) case (e.g., ___read_ptrs, ___core_read) + */ +#define ___empty(...) ___nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0) + +#define ___last1(x) x +#define ___last2(a, x) x +#define ___last3(a, b, x) x +#define ___last4(a, b, c, x) x +#define ___last5(a, b, c, d, x) x +#define ___last6(a, b, c, d, e, x) x +#define ___last7(a, b, c, d, e, f, x) x +#define ___last8(a, b, c, d, e, f, g, x) x +#define ___last9(a, b, c, d, e, f, g, h, x) x +#define ___last10(a, b, c, d, e, f, g, h, i, x) x +#define ___last(...) ___apply(___last, ___narg(__VA_ARGS__))(__VA_ARGS__) + +#define ___nolast2(a, _) a +#define ___nolast3(a, b, _) a, b +#define ___nolast4(a, b, c, _) a, b, c +#define ___nolast5(a, b, c, d, _) a, b, c, d +#define ___nolast6(a, b, c, d, e, _) a, b, c, d, e +#define ___nolast7(a, b, c, d, e, f, _) a, b, c, d, e, f +#define ___nolast8(a, b, c, d, e, f, g, _) a, b, c, d, e, f, g +#define ___nolast9(a, b, c, d, e, f, g, h, _) a, b, c, d, e, f, g, h +#define ___nolast10(a, b, c, d, e, f, g, h, i, _) a, b, c, d, e, f, g, h, i +#define ___nolast(...) ___apply(___nolast, ___narg(__VA_ARGS__))(__VA_ARGS__) + +#define ___arrow1(a) a +#define ___arrow2(a, b) a->b +#define ___arrow3(a, b, c) a->b->c +#define ___arrow4(a, b, c, d) a->b->c->d +#define ___arrow5(a, b, c, d, e) a->b->c->d->e +#define ___arrow6(a, b, c, d, e, f) a->b->c->d->e->f +#define ___arrow7(a, b, c, d, e, f, g) a->b->c->d->e->f->g +#define ___arrow8(a, b, c, d, e, f, g, h) a->b->c->d->e->f->g->h +#define ___arrow9(a, b, c, d, e, f, g, h, i) a->b->c->d->e->f->g->h->i +#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__) + +#define ___type(...) typeof(___arrow(__VA_ARGS__)) + +#define ___read(read_fn, dst, src_type, src, accessor) \ + read_fn((void *)(dst), sizeof(*(dst)), &((src_type)(src))->accessor) + +/* "recursively" read a sequence of inner pointers using local __t var */ +#define ___rd_first(src, a) ___read(bpf_core_read, &__t, ___type(src), src, a); +#define ___rd_last(...) \ + ___read(bpf_core_read, &__t, \ + ___type(___nolast(__VA_ARGS__)), __t, ___last(__VA_ARGS__)); +#define ___rd_p1(...) const void *__t; ___rd_first(__VA_ARGS__) +#define ___rd_p2(...) ___rd_p1(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p3(...) ___rd_p2(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p4(...) ___rd_p3(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p5(...) ___rd_p4(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p6(...) ___rd_p5(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p7(...) ___rd_p6(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p8(...) ___rd_p7(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___rd_p9(...) ___rd_p8(___nolast(__VA_ARGS__)) ___rd_last(__VA_ARGS__) +#define ___read_ptrs(src, ...) \ + ___apply(___rd_p, ___narg(__VA_ARGS__))(src, __VA_ARGS__) + +#define ___core_read0(fn, dst, src, a) \ + ___read(fn, dst, ___type(src), src, a); +#define ___core_readN(fn, dst, src, ...) \ + ___read_ptrs(src, ___nolast(__VA_ARGS__)) \ + ___read(fn, dst, ___type(src, ___nolast(__VA_ARGS__)), __t, \ + ___last(__VA_ARGS__)); +#define ___core_read(fn, dst, src, a, ...) \ + ___apply(___core_read, ___empty(__VA_ARGS__))(fn, dst, \ + src, a, ##__VA_ARGS__) + +/* + * BPF_CORE_READ_INTO() is a more performance-conscious variant of + * BPF_CORE_READ(), in which final field is read into user-provided storage. + * See BPF_CORE_READ() below for more details on general usage. + */ +#define BPF_CORE_READ_INTO(dst, src, a, ...) \ + ({ \ + ___core_read(bpf_core_read, dst, src, a, ##__VA_ARGS__) \ + }) + +/* + * BPF_CORE_READ_STR_INTO() does same "pointer chasing" as + * BPF_CORE_READ() for intermediate pointers, but then executes (and returns + * corresponding error code) bpf_core_read_str() for final string read. + */ +#define BPF_CORE_READ_STR_INTO(dst, src, a, ...) \ + ({ \ + ___core_read(bpf_core_read_str, dst, src, a, ##__VA_ARGS__) \ + }) + +/* + * BPF_CORE_READ() is used to simplify BPF CO-RE relocatable read, especially + * when there are few pointer chasing steps. + * E.g., what in non-BPF world (or in BPF w/ BCC) would be something like: + * int x = s->a.b.c->d.e->f->g; + * can be succinctly achieved using BPF_CORE_READ as: + * int x = BPF_CORE_READ(s, a.b.c, d.e, f, g); + * + * BPF_CORE_READ will decompose above statement into 4 bpf_core_read (BPF + * CO-RE relocatable bpf_probe_read() wrapper) calls, logically equivalent to: + * 1. const void *__t = s->a.b.c; + * 2. __t = __t->d.e; + * 3. __t = __t->f; + * 4. return __t->g; + * + * Equivalence is logical, because there is a heavy type casting/preservation + * involved, as well as all the reads are happening through bpf_probe_read() + * calls using __builtin_preserve_access_index() to emit CO-RE relocations. + * + * N.B. Only up to 9 "field accessors" are supported, which should be more + * than enough for any practical purpose. + */ +#define BPF_CORE_READ(src, a, ...) \ + ({ \ + ___type(src, a, ##__VA_ARGS__) __r; \ + BPF_CORE_READ_INTO(&__r, src, a, ##__VA_ARGS__); \ + __r; \ + }) + +#endif + diff --git a/tools/lib/bpf/bpf_endian.h b/tools/lib/bpf/bpf_endian.h new file mode 100644 index 000000000000..fbe28008450f --- /dev/null +++ b/tools/lib/bpf/bpf_endian.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_ENDIAN__ +#define __BPF_ENDIAN__ + +#include <linux/stddef.h> +#include <linux/swab.h> + +/* LLVM's BPF target selects the endianness of the CPU + * it compiles on, or the user specifies (bpfel/bpfeb), + * respectively. The used __BYTE_ORDER__ is defined by + * the compiler, we cannot rely on __BYTE_ORDER from + * libc headers, since it doesn't reflect the actual + * requested byte order. + * + * Note, LLVM's BPF target has different __builtin_bswapX() + * semantics. It does map to BPF_ALU | BPF_END | BPF_TO_BE + * in bpfel and bpfeb case, which means below, that we map + * to cpu_to_be16(). We could use it unconditionally in BPF + * case, but better not rely on it, so that this header here + * can be used from application and BPF program side, which + * use different targets. + */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +# define __bpf_ntohs(x) __builtin_bswap16(x) +# define __bpf_htons(x) __builtin_bswap16(x) +# define __bpf_constant_ntohs(x) ___constant_swab16(x) +# define __bpf_constant_htons(x) ___constant_swab16(x) +# define __bpf_ntohl(x) __builtin_bswap32(x) +# define __bpf_htonl(x) __builtin_bswap32(x) +# define __bpf_constant_ntohl(x) ___constant_swab32(x) +# define __bpf_constant_htonl(x) ___constant_swab32(x) +# define __bpf_be64_to_cpu(x) __builtin_bswap64(x) +# define __bpf_cpu_to_be64(x) __builtin_bswap64(x) +# define __bpf_constant_be64_to_cpu(x) ___constant_swab64(x) +# define __bpf_constant_cpu_to_be64(x) ___constant_swab64(x) +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +# define __bpf_ntohs(x) (x) +# define __bpf_htons(x) (x) +# define __bpf_constant_ntohs(x) (x) +# define __bpf_constant_htons(x) (x) +# define __bpf_ntohl(x) (x) +# define __bpf_htonl(x) (x) +# define __bpf_constant_ntohl(x) (x) +# define __bpf_constant_htonl(x) (x) +# define __bpf_be64_to_cpu(x) (x) +# define __bpf_cpu_to_be64(x) (x) +# define __bpf_constant_be64_to_cpu(x) (x) +# define __bpf_constant_cpu_to_be64(x) (x) +#else +# error "Fix your compiler's __BYTE_ORDER__?!" +#endif + +#define bpf_htons(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_htons(x) : __bpf_htons(x)) +#define bpf_ntohs(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_ntohs(x) : __bpf_ntohs(x)) +#define bpf_htonl(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_htonl(x) : __bpf_htonl(x)) +#define bpf_ntohl(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_ntohl(x) : __bpf_ntohl(x)) +#define bpf_cpu_to_be64(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_cpu_to_be64(x) : __bpf_cpu_to_be64(x)) +#define bpf_be64_to_cpu(x) \ + (__builtin_constant_p(x) ? \ + __bpf_constant_be64_to_cpu(x) : __bpf_be64_to_cpu(x)) + +#endif /* __BPF_ENDIAN__ */ diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h new file mode 100644 index 000000000000..0c7d28292898 --- /dev/null +++ b/tools/lib/bpf/bpf_helpers.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_HELPERS__ +#define __BPF_HELPERS__ + +#include "bpf_helper_defs.h" + +#define __uint(name, val) int (*name)[val] +#define __type(name, val) typeof(val) *name + +/* Helper macro to print out debug messages */ +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +/* + * Helper macro to place programs, maps, license in + * different sections in elf_bpf file. Section names + * are interpreted by elf_bpf loader + */ +#define SEC(NAME) __attribute__((section(NAME), used)) + +#ifndef __always_inline +#define __always_inline __attribute__((always_inline)) +#endif + +/* + * Helper structure used by eBPF C program + * to describe BPF map attributes to libbpf loader + */ +struct bpf_map_def { + unsigned int type; + unsigned int key_size; + unsigned int value_size; + unsigned int max_entries; + unsigned int map_flags; +}; + +enum libbpf_pin_type { + LIBBPF_PIN_NONE, + /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ + LIBBPF_PIN_BY_NAME, +}; + +#endif diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c index 6978314ea7f6..3ed1a27b5f7c 100644 --- a/tools/lib/bpf/bpf_prog_linfo.c +++ b/tools/lib/bpf/bpf_prog_linfo.c @@ -6,10 +6,7 @@ #include <linux/err.h> #include <linux/bpf.h> #include "libbpf.h" - -#ifndef min -#define min(x, y) ((x) < (y) ? (x) : (y)) -#endif +#include "libbpf_internal.h" struct bpf_prog_linfo { void *raw_linfo; @@ -104,6 +101,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info) { struct bpf_prog_linfo *prog_linfo; __u32 nr_linfo, nr_jited_func; + __u64 data_sz; nr_linfo = info->nr_line_info; @@ -125,11 +123,11 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info) /* Copy xlated line_info */ prog_linfo->nr_linfo = nr_linfo; prog_linfo->rec_size = info->line_info_rec_size; - prog_linfo->raw_linfo = malloc(nr_linfo * prog_linfo->rec_size); + data_sz = (__u64)nr_linfo * prog_linfo->rec_size; + prog_linfo->raw_linfo = malloc(data_sz); if (!prog_linfo->raw_linfo) goto err_free; - memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info, - nr_linfo * prog_linfo->rec_size); + memcpy(prog_linfo->raw_linfo, (void *)(long)info->line_info, data_sz); nr_jited_func = info->nr_jited_ksyms; if (!nr_jited_func || @@ -145,13 +143,12 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info) /* Copy jited_line_info */ prog_linfo->nr_jited_func = nr_jited_func; prog_linfo->jited_rec_size = info->jited_line_info_rec_size; - prog_linfo->raw_jited_linfo = malloc(nr_linfo * - prog_linfo->jited_rec_size); + data_sz = (__u64)nr_linfo * prog_linfo->jited_rec_size; + prog_linfo->raw_jited_linfo = malloc(data_sz); if (!prog_linfo->raw_jited_linfo) goto err_free; memcpy(prog_linfo->raw_jited_linfo, - (void *)(long)info->jited_line_info, - nr_linfo * prog_linfo->jited_rec_size); + (void *)(long)info->jited_line_info, data_sz); /* Number of jited_line_info per jited func */ prog_linfo->nr_jited_linfo_per_func = malloc(nr_jited_func * diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h new file mode 100644 index 000000000000..b0dafe8b4ebc --- /dev/null +++ b/tools/lib/bpf/bpf_tracing.h @@ -0,0 +1,195 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +#ifndef __BPF_TRACING_H__ +#define __BPF_TRACING_H__ + +/* Scan the ARCH passed in from ARCH env variable (see Makefile) */ +#if defined(__TARGET_ARCH_x86) + #define bpf_target_x86 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_s390) + #define bpf_target_s390 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_arm) + #define bpf_target_arm + #define bpf_target_defined +#elif defined(__TARGET_ARCH_arm64) + #define bpf_target_arm64 + #define bpf_target_defined +#elif defined(__TARGET_ARCH_mips) + #define bpf_target_mips + #define bpf_target_defined +#elif defined(__TARGET_ARCH_powerpc) + #define bpf_target_powerpc + #define bpf_target_defined +#elif defined(__TARGET_ARCH_sparc) + #define bpf_target_sparc + #define bpf_target_defined +#else + #undef bpf_target_defined +#endif + +/* Fall back to what the compiler says */ +#ifndef bpf_target_defined +#if defined(__x86_64__) + #define bpf_target_x86 +#elif defined(__s390__) + #define bpf_target_s390 +#elif defined(__arm__) + #define bpf_target_arm +#elif defined(__aarch64__) + #define bpf_target_arm64 +#elif defined(__mips__) + #define bpf_target_mips +#elif defined(__powerpc__) + #define bpf_target_powerpc +#elif defined(__sparc__) + #define bpf_target_sparc +#endif +#endif + +#if defined(bpf_target_x86) + +#ifdef __KERNEL__ +#define PT_REGS_PARM1(x) ((x)->di) +#define PT_REGS_PARM2(x) ((x)->si) +#define PT_REGS_PARM3(x) ((x)->dx) +#define PT_REGS_PARM4(x) ((x)->cx) +#define PT_REGS_PARM5(x) ((x)->r8) +#define PT_REGS_RET(x) ((x)->sp) +#define PT_REGS_FP(x) ((x)->bp) +#define PT_REGS_RC(x) ((x)->ax) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->ip) +#else +#ifdef __i386__ +/* i386 kernel is built with -mregparm=3 */ +#define PT_REGS_PARM1(x) ((x)->eax) +#define PT_REGS_PARM2(x) ((x)->edx) +#define PT_REGS_PARM3(x) ((x)->ecx) +#define PT_REGS_PARM4(x) 0 +#define PT_REGS_PARM5(x) 0 +#define PT_REGS_RET(x) ((x)->esp) +#define PT_REGS_FP(x) ((x)->ebp) +#define PT_REGS_RC(x) ((x)->eax) +#define PT_REGS_SP(x) ((x)->esp) +#define PT_REGS_IP(x) ((x)->eip) +#else +#define PT_REGS_PARM1(x) ((x)->rdi) +#define PT_REGS_PARM2(x) ((x)->rsi) +#define PT_REGS_PARM3(x) ((x)->rdx) +#define PT_REGS_PARM4(x) ((x)->rcx) +#define PT_REGS_PARM5(x) ((x)->r8) +#define PT_REGS_RET(x) ((x)->rsp) +#define PT_REGS_FP(x) ((x)->rbp) +#define PT_REGS_RC(x) ((x)->rax) +#define PT_REGS_SP(x) ((x)->rsp) +#define PT_REGS_IP(x) ((x)->rip) +#endif +#endif + +#elif defined(bpf_target_s390) + +/* s390 provides user_pt_regs instead of struct pt_regs to userspace */ +struct pt_regs; +#define PT_REGS_S390 const volatile user_pt_regs +#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2]) +#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3]) +#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4]) +#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5]) +#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6]) +#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14]) +/* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11]) +#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2]) +#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15]) +#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr) + +#elif defined(bpf_target_arm) + +#define PT_REGS_PARM1(x) ((x)->uregs[0]) +#define PT_REGS_PARM2(x) ((x)->uregs[1]) +#define PT_REGS_PARM3(x) ((x)->uregs[2]) +#define PT_REGS_PARM4(x) ((x)->uregs[3]) +#define PT_REGS_PARM5(x) ((x)->uregs[4]) +#define PT_REGS_RET(x) ((x)->uregs[14]) +#define PT_REGS_FP(x) ((x)->uregs[11]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->uregs[0]) +#define PT_REGS_SP(x) ((x)->uregs[13]) +#define PT_REGS_IP(x) ((x)->uregs[12]) + +#elif defined(bpf_target_arm64) + +/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ +struct pt_regs; +#define PT_REGS_ARM64 const volatile struct user_pt_regs +#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0]) +#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1]) +#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2]) +#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3]) +#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4]) +#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30]) +/* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29]) +#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0]) +#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp) +#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc) + +#elif defined(bpf_target_mips) + +#define PT_REGS_PARM1(x) ((x)->regs[4]) +#define PT_REGS_PARM2(x) ((x)->regs[5]) +#define PT_REGS_PARM3(x) ((x)->regs[6]) +#define PT_REGS_PARM4(x) ((x)->regs[7]) +#define PT_REGS_PARM5(x) ((x)->regs[8]) +#define PT_REGS_RET(x) ((x)->regs[31]) +#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->regs[1]) +#define PT_REGS_SP(x) ((x)->regs[29]) +#define PT_REGS_IP(x) ((x)->cp0_epc) + +#elif defined(bpf_target_powerpc) + +#define PT_REGS_PARM1(x) ((x)->gpr[3]) +#define PT_REGS_PARM2(x) ((x)->gpr[4]) +#define PT_REGS_PARM3(x) ((x)->gpr[5]) +#define PT_REGS_PARM4(x) ((x)->gpr[6]) +#define PT_REGS_PARM5(x) ((x)->gpr[7]) +#define PT_REGS_RC(x) ((x)->gpr[3]) +#define PT_REGS_SP(x) ((x)->sp) +#define PT_REGS_IP(x) ((x)->nip) + +#elif defined(bpf_target_sparc) + +#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0]) +#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1]) +#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2]) +#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3]) +#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4]) +#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7]) +#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0]) +#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP]) + +/* Should this also be a bpf_target check for the sparc case? */ +#if defined(__arch64__) +#define PT_REGS_IP(x) ((x)->tpc) +#else +#define PT_REGS_IP(x) ((x)->pc) +#endif + +#endif + +#if defined(bpf_target_powerpc) +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP +#elif defined(bpf_target_sparc) +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) +#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP +#else +#define BPF_KPROBE_READ_RET_IP(ip, ctx) \ + ({ bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) +#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) \ + ({ bpf_probe_read(&(ip), sizeof(ip), \ + (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) +#endif + +#endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index cf119c9b6f27..88efa2bb7137 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1,29 +1,25 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2018 Facebook */ +#include <endian.h> #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <fcntl.h> #include <unistd.h> #include <errno.h> #include <linux/err.h> #include <linux/btf.h> +#include <gelf.h> #include "btf.h" #include "bpf.h" #include "libbpf.h" -#include "libbpf_util.h" - -#define max(a, b) ((a) > (b) ? (a) : (b)) -#define min(a, b) ((a) < (b) ? (a) : (b)) +#include "libbpf_internal.h" +#include "hashmap.h" #define BTF_MAX_NR_TYPES 0x7fffffff #define BTF_MAX_STR_OFFSET 0x7fffffff -#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \ - ((k) == BTF_KIND_VOLATILE) || \ - ((k) == BTF_KIND_CONST) || \ - ((k) == BTF_KIND_RESTRICT)) - static struct btf_type btf_void; struct btf { @@ -40,47 +36,6 @@ struct btf { int fd; }; -struct btf_ext_info { - /* - * info points to the individual info section (e.g. func_info and - * line_info) from the .BTF.ext. It does not include the __u32 rec_size. - */ - void *info; - __u32 rec_size; - __u32 len; -}; - -struct btf_ext { - union { - struct btf_ext_header *hdr; - void *data; - }; - struct btf_ext_info func_info; - struct btf_ext_info line_info; - __u32 data_size; -}; - -struct btf_ext_info_sec { - __u32 sec_name_off; - __u32 num_info; - /* Followed by num_info * record_size number of bytes */ - __u8 data[0]; -}; - -/* The minimum bpf_func_info checked by the loader */ -struct bpf_func_info_min { - __u32 insn_off; - __u32 type_id; -}; - -/* The minimum bpf_line_info checked by the loader */ -struct bpf_line_info_min { - __u32 insn_off; - __u32 file_name_off; - __u32 line_off; - __u32 line_col; -}; - static inline __u64 ptr_to_u64(const void *ptr) { return (__u64) (unsigned long) ptr; @@ -190,9 +145,9 @@ static int btf_parse_str_sec(struct btf *btf) static int btf_type_size(struct btf_type *t) { int base_size = sizeof(struct btf_type); - __u16 vlen = BTF_INFO_VLEN(t->info); + __u16 vlen = btf_vlen(t); - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_FWD: case BTF_KIND_CONST: case BTF_KIND_VOLATILE: @@ -212,8 +167,12 @@ static int btf_type_size(struct btf_type *t) return base_size + vlen * sizeof(struct btf_member); case BTF_KIND_FUNC_PROTO: return base_size + vlen * sizeof(struct btf_param); + case BTF_KIND_VAR: + return base_size + sizeof(struct btf_var); + case BTF_KIND_DATASEC: + return base_size + vlen * sizeof(struct btf_var_secinfo); default: - pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info)); + pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; } } @@ -257,7 +216,7 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) static bool btf_type_is_void(const struct btf_type *t) { - return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; + return t == &btf_void || btf_is_fwd(t); } static bool btf_type_is_void_or_null(const struct btf_type *t) @@ -278,11 +237,12 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) { - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: + case BTF_KIND_DATASEC: size = t->size; goto done; case BTF_KIND_PTR: @@ -292,10 +252,11 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: + case BTF_KIND_VAR: type_id = t->type; break; case BTF_KIND_ARRAY: - array = (const struct btf_array *)(t + 1); + array = btf_array(t); if (nelems && array->nelems > UINT32_MAX / nelems) return -E2BIG; nelems *= array->nelems; @@ -308,10 +269,9 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); } +done: if (size < 0) return -EINVAL; - -done: if (nelems && size > UINT32_MAX / nelems) return -E2BIG; @@ -326,7 +286,7 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); while (depth < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t) && - IS_MODIFIER(BTF_INFO_KIND(t->info))) { + (btf_is_mod(t) || btf_is_typedef(t) || btf_is_var(t))) { type_id = t->type; t = btf__type_by_id(btf, type_id); depth++; @@ -356,6 +316,28 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name) return -ENOENT; } +__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, + __u32 kind) +{ + __u32 i; + + if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void")) + return 0; + + for (i = 1; i <= btf->nr_types; i++) { + const struct btf_type *t = btf->types[i]; + const char *name; + + if (btf_kind(t) != kind) + continue; + name = btf__name_by_offset(btf, t->name_off); + if (name && !strcmp(type_name, name)) + return i; + } + + return -ENOENT; +} + void btf__free(struct btf *btf) { if (!btf) @@ -408,6 +390,218 @@ done: return btf; } +static bool btf_check_endianness(const GElf_Ehdr *ehdr) +{ +#if __BYTE_ORDER == __LITTLE_ENDIAN + return ehdr->e_ident[EI_DATA] == ELFDATA2LSB; +#elif __BYTE_ORDER == __BIG_ENDIAN + return ehdr->e_ident[EI_DATA] == ELFDATA2MSB; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif +} + +struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) +{ + 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; + GElf_Ehdr ehdr; + + 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); + 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; + } + if (!btf_check_endianness(&ehdr)) { + pr_warn("non-native ELF endianness is not supported\n"); + goto done; + } + if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) { + pr_warn("failed to get e_shstrndx from %s\n", path); + goto done; + } + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + GElf_Shdr sh; + char *name; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_warn("failed to get section(%d) header from %s\n", + idx, path); + goto done; + } + name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name); + if (!name) { + pr_warn("failed to get section(%d) name from %s\n", + idx, path); + goto done; + } + 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; + } + continue; + } + } + + err = 0; + + if (!btf_data) { + err = -ENOENT; + goto done; + } + btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(btf)) + goto done; + + if (btf_ext && btf_ext_data) { + *btf_ext = btf_ext__new(btf_ext_data->d_buf, + btf_ext_data->d_size); + if (IS_ERR(*btf_ext)) + goto done; + } else if (btf_ext) { + *btf_ext = NULL; + } +done: + if (elf) + elf_end(elf); + close(fd); + + if (err) + return ERR_PTR(err); + /* + * btf is always parsed before btf_ext, so no need to clean up + * btf_ext, if btf loading failed + */ + if (IS_ERR(btf)) + return btf; + if (btf_ext && IS_ERR(*btf_ext)) { + btf__free(btf); + err = PTR_ERR(*btf_ext); + return ERR_PTR(err); + } + return btf; +} + +static int compare_vsi_off(const void *_a, const void *_b) +{ + const struct btf_var_secinfo *a = _a; + const struct btf_var_secinfo *b = _b; + + return a->offset - b->offset; +} + +static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, + struct btf_type *t) +{ + __u32 size = 0, off = 0, i, vars = btf_vlen(t); + const char *name = btf__name_by_offset(btf, t->name_off); + const struct btf_type *t_var; + struct btf_var_secinfo *vsi; + const struct btf_var *var; + int ret; + + if (!name) { + pr_debug("No name found in string section for DATASEC kind.\n"); + return -ENOENT; + } + + ret = bpf_object__section_size(obj, name, &size); + if (ret || !size || (t->size && t->size != size)) { + pr_debug("Invalid size for section %s: %u bytes\n", name, size); + return -ENOENT; + } + + t->size = size; + + for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) { + t_var = btf__type_by_id(btf, vsi->type); + var = btf_var(t_var); + + if (!btf_is_var(t_var)) { + pr_debug("Non-VAR type seen in section %s\n", name); + return -EINVAL; + } + + if (var->linkage == BTF_VAR_STATIC) + continue; + + name = btf__name_by_offset(btf, t_var->name_off); + if (!name) { + pr_debug("No name found in string section for VAR kind\n"); + return -ENOENT; + } + + ret = bpf_object__variable_offset(obj, name, &off); + if (ret) { + pr_debug("No offset found in symbol table for VAR %s\n", + name); + return -ENOENT; + } + + vsi->offset = off; + } + + qsort(t + 1, vars, sizeof(*vsi), compare_vsi_off); + return 0; +} + +int btf__finalize_data(struct bpf_object *obj, struct btf *btf) +{ + int err = 0; + __u32 i; + + for (i = 1; i <= btf->nr_types; i++) { + struct btf_type *t = btf->types[i]; + + /* Loader needs to fix up some of the things compiler + * couldn't get its hands on while emitting BTF. This + * is section size and global variable offset. We use + * the info from the ELF itself for this purpose. + */ + if (btf_is_datasec(t)) { + err = btf_fixup_datasec(obj, btf, t); + if (err) + break; + } + } + + return err; +} + int btf__load(struct btf *btf) { __u32 log_buf_size = BPF_LOG_BUF_SIZE; @@ -427,9 +621,9 @@ int btf__load(struct btf *btf) log_buf, log_buf_size, false); if (btf->fd < 0) { err = -errno; - pr_warning("Error loading BTF: %s(%d)\n", strerror(errno), errno); + pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno); if (*log_buf) - pr_warning("%s\n", log_buf); + pr_warn("%s\n", log_buf); goto done; } @@ -534,8 +728,8 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, if (snprintf(container_name, max_name, "____btf_map_%s", map_name) == max_name) { - pr_warning("map:%s length of '____btf_map_%s' is too long\n", - map_name, map_name); + pr_warn("map:%s length of '____btf_map_%s' is too long\n", + map_name, map_name); return -EINVAL; } @@ -548,42 +742,41 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, container_type = btf__type_by_id(btf, container_id); if (!container_type) { - pr_warning("map:%s cannot find BTF type for container_id:%u\n", - map_name, container_id); + pr_warn("map:%s cannot find BTF type for container_id:%u\n", + map_name, container_id); return -EINVAL; } - if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT || - BTF_INFO_VLEN(container_type->info) < 2) { - pr_warning("map:%s container_name:%s is an invalid container struct\n", - map_name, container_name); + if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) { + pr_warn("map:%s container_name:%s is an invalid container struct\n", + map_name, container_name); return -EINVAL; } - key = (struct btf_member *)(container_type + 1); + key = btf_members(container_type); value = key + 1; key_size = btf__resolve_size(btf, key->type); if (key_size < 0) { - pr_warning("map:%s invalid BTF key_type_size\n", map_name); + pr_warn("map:%s invalid BTF key_type_size\n", map_name); return key_size; } if (expected_key_size != key_size) { - pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", - map_name, (__u32)key_size, expected_key_size); + pr_warn("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", + map_name, (__u32)key_size, expected_key_size); return -EINVAL; } value_size = btf__resolve_size(btf, value->type); if (value_size < 0) { - pr_warning("map:%s invalid BTF value_type_size\n", map_name); + pr_warn("map:%s invalid BTF value_type_size\n", map_name); return value_size; } if (expected_value_size != value_size) { - pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", - map_name, (__u32)value_size, expected_value_size); + pr_warn("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", + map_name, (__u32)value_size, expected_value_size); return -EINVAL; } @@ -610,6 +803,9 @@ static int btf_ext_setup_info(struct btf_ext *btf_ext, /* The start of the info sec (including the __u32 record_size). */ void *info; + if (ext_sec->len == 0) + return 0; + if (ext_sec->off & 0x03) { pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n", ext_sec->desc); @@ -713,11 +909,24 @@ static int btf_ext_setup_line_info(struct btf_ext *btf_ext) return btf_ext_setup_info(btf_ext, ¶m); } +static int btf_ext_setup_field_reloc(struct btf_ext *btf_ext) +{ + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->field_reloc_off, + .len = btf_ext->hdr->field_reloc_len, + .min_rec_size = sizeof(struct bpf_field_reloc), + .ext_info = &btf_ext->field_reloc_info, + .desc = "field_reloc", + }; + + return btf_ext_setup_info(btf_ext, ¶m); +} + static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) { const struct btf_ext_header *hdr = (struct btf_ext_header *)data; - if (data_size < offsetof(struct btf_ext_header, func_info_off) || + if (data_size < offsetofend(struct btf_ext_header, hdr_len) || data_size < hdr->hdr_len) { pr_debug("BTF.ext header not found"); return -EINVAL; @@ -775,6 +984,9 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) } memcpy(btf_ext->data, data, size); + if (btf_ext->hdr->hdr_len < + offsetofend(struct btf_ext_header, line_info_len)) + goto done; err = btf_ext_setup_func_info(btf_ext); if (err) goto done; @@ -783,6 +995,13 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) if (err) goto done; + if (btf_ext->hdr->hdr_len < + offsetofend(struct btf_ext_header, field_reloc_len)) + goto done; + err = btf_ext_setup_field_reloc(btf_ext); + if (err) + goto done; + done: if (err) { btf_ext__free(btf_ext); @@ -1070,16 +1289,9 @@ done: return err; } -#define BTF_DEDUP_TABLE_DEFAULT_SIZE (1 << 14) -#define BTF_DEDUP_TABLE_MAX_SIZE_LOG 31 #define BTF_UNPROCESSED_ID ((__u32)-1) #define BTF_IN_PROGRESS_ID ((__u32)-2) -struct btf_dedup_node { - struct btf_dedup_node *next; - __u32 type_id; -}; - struct btf_dedup { /* .BTF section to be deduped in-place */ struct btf *btf; @@ -1095,7 +1307,7 @@ struct btf_dedup { * candidates, which is fine because we rely on subsequent * btf_xxx_equal() checks to authoritatively verify type equality. */ - struct btf_dedup_node **dedup_table; + struct hashmap *dedup_table; /* Canonical types map */ __u32 *map; /* Hypothetical mapping, used during type graph equivalence checks */ @@ -1120,30 +1332,18 @@ struct btf_str_ptrs { __u32 cap; }; -static inline __u32 hash_combine(__u32 h, __u32 value) +static long hash_combine(long h, long value) { -/* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */ -#define GOLDEN_RATIO_PRIME 0x9e370001UL - return h * 37 + value * GOLDEN_RATIO_PRIME; -#undef GOLDEN_RATIO_PRIME + return h * 31 + value; } -#define for_each_dedup_cand(d, hash, node) \ - for (node = d->dedup_table[hash & (d->opts.dedup_table_size - 1)]; \ - node; \ - node = node->next) +#define for_each_dedup_cand(d, node, hash) \ + hashmap__for_each_key_entry(d->dedup_table, node, (void *)hash) -static int btf_dedup_table_add(struct btf_dedup *d, __u32 hash, __u32 type_id) +static int btf_dedup_table_add(struct btf_dedup *d, long hash, __u32 type_id) { - struct btf_dedup_node *node = malloc(sizeof(struct btf_dedup_node)); - int bucket = hash & (d->opts.dedup_table_size - 1); - - if (!node) - return -ENOMEM; - node->type_id = type_id; - node->next = d->dedup_table[bucket]; - d->dedup_table[bucket] = node; - return 0; + return hashmap__append(d->dedup_table, + (void *)hash, (void *)(long)type_id); } static int btf_dedup_hypot_map_add(struct btf_dedup *d, @@ -1172,36 +1372,10 @@ static void btf_dedup_clear_hypot_map(struct btf_dedup *d) d->hypot_cnt = 0; } -static void btf_dedup_table_free(struct btf_dedup *d) -{ - struct btf_dedup_node *head, *tmp; - int i; - - if (!d->dedup_table) - return; - - for (i = 0; i < d->opts.dedup_table_size; i++) { - while (d->dedup_table[i]) { - tmp = d->dedup_table[i]; - d->dedup_table[i] = tmp->next; - free(tmp); - } - - head = d->dedup_table[i]; - while (head) { - tmp = head; - head = head->next; - free(tmp); - } - } - - free(d->dedup_table); - d->dedup_table = NULL; -} - static void btf_dedup_free(struct btf_dedup *d) { - btf_dedup_table_free(d); + hashmap__free(d->dedup_table); + d->dedup_table = NULL; free(d->map); d->map = NULL; @@ -1215,40 +1389,43 @@ static void btf_dedup_free(struct btf_dedup *d) free(d); } -/* Find closest power of two >= to size, capped at 2^max_size_log */ -static __u32 roundup_pow2_max(__u32 size, int max_size_log) +static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx) { - int i; + return (size_t)key; +} - for (i = 0; i < max_size_log && (1U << i) < size; i++) - ; - return 1U << i; +static size_t btf_dedup_collision_hash_fn(const void *key, void *ctx) +{ + return 0; } +static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, const struct btf_dedup_opts *opts) { struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup)); + hashmap_hash_fn hash_fn = btf_dedup_identity_hash_fn; int i, err = 0; - __u32 sz; if (!d) return ERR_PTR(-ENOMEM); d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds; - sz = opts && opts->dedup_table_size ? opts->dedup_table_size - : BTF_DEDUP_TABLE_DEFAULT_SIZE; - sz = roundup_pow2_max(sz, BTF_DEDUP_TABLE_MAX_SIZE_LOG); - d->opts.dedup_table_size = sz; + /* dedup_table_size is now used only to force collisions in tests */ + if (opts && opts->dedup_table_size == 1) + hash_fn = btf_dedup_collision_hash_fn; d->btf = btf; d->btf_ext = btf_ext; - d->dedup_table = calloc(d->opts.dedup_table_size, - sizeof(struct btf_dedup_node *)); - if (!d->dedup_table) { - err = -ENOMEM; + d->dedup_table = hashmap__new(hash_fn, btf_dedup_equal_fn, NULL); + if (IS_ERR(d->dedup_table)) { + err = PTR_ERR(d->dedup_table); + d->dedup_table = NULL; goto done; } @@ -1259,8 +1436,15 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, } /* special BTF "void" type is made canonical immediately */ d->map[0] = 0; - for (i = 1; i <= btf->nr_types; i++) - d->map[i] = BTF_UNPROCESSED_ID; + for (i = 1; i <= btf->nr_types; i++) { + struct btf_type *t = d->btf->types[i]; + + /* VAR and DATASEC are never deduped and are self-canonical */ + if (btf_is_var(t) || btf_is_datasec(t)) + d->map[i] = i; + else + d->map[i] = BTF_UNPROCESSED_ID; + } d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types)); if (!d->hypot_map) { @@ -1297,11 +1481,11 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) if (r) return r; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *m = (struct btf_member *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1312,8 +1496,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) break; } case BTF_KIND_ENUM: { - struct btf_enum *m = (struct btf_enum *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_enum *m = btf_enum(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1324,8 +1508,8 @@ static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) break; } case BTF_KIND_FUNC_PROTO: { - struct btf_param *m = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_param *m = btf_params(t); + __u16 vlen = btf_vlen(t); for (j = 0; j < vlen; j++) { r = fn(&m->name_off, ctx); @@ -1559,9 +1743,9 @@ done: return err; } -static __u32 btf_hash_common(struct btf_type *t) +static long btf_hash_common(struct btf_type *t) { - __u32 h; + long h; h = hash_combine(0, t->name_off); h = hash_combine(h, t->info); @@ -1577,10 +1761,10 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) } /* Calculate type signature hash of INT. */ -static __u32 btf_hash_int(struct btf_type *t) +static long btf_hash_int(struct btf_type *t) { __u32 info = *(__u32 *)(t + 1); - __u32 h; + long h; h = btf_hash_common(t); h = hash_combine(h, info); @@ -1600,9 +1784,9 @@ static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2) } /* Calculate type signature hash of ENUM. */ -static __u32 btf_hash_enum(struct btf_type *t) +static long btf_hash_enum(struct btf_type *t) { - __u32 h; + long h; /* don't hash vlen and enum members to support enum fwd resolving */ h = hash_combine(0, t->name_off); @@ -1614,16 +1798,16 @@ static __u32 btf_hash_enum(struct btf_type *t) /* Check structural equality of two ENUMs. */ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) { - struct btf_enum *m1, *m2; + const struct btf_enum *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_enum *)(t1 + 1); - m2 = (struct btf_enum *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_enum(t1); + m2 = btf_enum(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->val != m2->val) return false; @@ -1635,8 +1819,7 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) static inline bool btf_is_enum_fwd(struct btf_type *t) { - return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM && - BTF_INFO_VLEN(t->info) == 0; + return btf_is_enum(t) && btf_vlen(t) == 0; } static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) @@ -1654,11 +1837,11 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) * as referenced type IDs equivalence is established separately during type * graph equivalence check algorithm. */ -static __u32 btf_hash_struct(struct btf_type *t) +static long btf_hash_struct(struct btf_type *t) { - struct btf_member *member = (struct btf_member *)(t + 1); - __u32 vlen = BTF_INFO_VLEN(t->info); - __u32 h = btf_hash_common(t); + const struct btf_member *member = btf_members(t); + __u32 vlen = btf_vlen(t); + long h = btf_hash_common(t); int i; for (i = 0; i < vlen; i++) { @@ -1677,16 +1860,16 @@ static __u32 btf_hash_struct(struct btf_type *t) */ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) { - struct btf_member *m1, *m2; + const struct btf_member *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_member *)(t1 + 1); - m2 = (struct btf_member *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_members(t1); + m2 = btf_members(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->offset != m2->offset) return false; @@ -1701,10 +1884,10 @@ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) * under assumption that they were already resolved to canonical type IDs and * are not going to change. */ -static __u32 btf_hash_array(struct btf_type *t) +static long btf_hash_array(struct btf_type *t) { - struct btf_array *info = (struct btf_array *)(t + 1); - __u32 h = btf_hash_common(t); + const struct btf_array *info = btf_array(t); + long h = btf_hash_common(t); h = hash_combine(h, info->type); h = hash_combine(h, info->index_type); @@ -1721,13 +1904,13 @@ static __u32 btf_hash_array(struct btf_type *t) */ static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) { - struct btf_array *info1, *info2; + const struct btf_array *info1, *info2; if (!btf_equal_common(t1, t2)) return false; - info1 = (struct btf_array *)(t1 + 1); - info2 = (struct btf_array *)(t2 + 1); + info1 = btf_array(t1); + info2 = btf_array(t2); return info1->type == info2->type && info1->index_type == info2->index_type && info1->nelems == info2->nelems; @@ -1740,14 +1923,10 @@ static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) */ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) { - struct btf_array *info1, *info2; - if (!btf_equal_common(t1, t2)) return false; - info1 = (struct btf_array *)(t1 + 1); - info2 = (struct btf_array *)(t2 + 1); - return info1->nelems == info2->nelems; + return btf_array(t1)->nelems == btf_array(t2)->nelems; } /* @@ -1755,11 +1934,11 @@ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) * under assumption that they were already resolved to canonical type IDs and * are not going to change. */ -static inline __u32 btf_hash_fnproto(struct btf_type *t) +static long btf_hash_fnproto(struct btf_type *t) { - struct btf_param *member = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); - __u32 h = btf_hash_common(t); + const struct btf_param *member = btf_params(t); + __u16 vlen = btf_vlen(t); + long h = btf_hash_common(t); int i; for (i = 0; i < vlen; i++) { @@ -1777,18 +1956,18 @@ static inline __u32 btf_hash_fnproto(struct btf_type *t) * This function is called during reference types deduplication to compare * FUNC_PROTO to potential canonical representative. */ -static inline bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) +static bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) { - struct btf_param *m1, *m2; + const struct btf_param *m1, *m2; __u16 vlen; int i; if (!btf_equal_common(t1, t2)) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_param *)(t1 + 1); - m2 = (struct btf_param *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off || m1->type != m2->type) return false; @@ -1803,9 +1982,9 @@ static inline bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) * IDs. This check is performed during type graph equivalence check and * referenced types equivalence is checked separately. */ -static inline bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) +static bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) { - struct btf_param *m1, *m2; + const struct btf_param *m1, *m2; __u16 vlen; int i; @@ -1813,9 +1992,9 @@ static inline bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) if (t1->name_off != t2->name_off || t1->info != t2->info) return false; - vlen = BTF_INFO_VLEN(t1->info); - m1 = (struct btf_param *)(t1 + 1); - m2 = (struct btf_param *)(t2 + 1); + vlen = btf_vlen(t1); + m1 = btf_params(t1); + m2 = btf_params(t2); for (i = 0; i < vlen; i++) { if (m1->name_off != m2->name_off) return false; @@ -1834,13 +2013,14 @@ static inline bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) { struct btf_type *t = d->btf->types[type_id]; + struct hashmap_entry *hash_entry; struct btf_type *cand; - struct btf_dedup_node *cand_node; /* if we don't find equivalent type, then we are canonical */ __u32 new_id = type_id; - __u32 h; + __u32 cand_id; + long h; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_CONST: case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: @@ -1851,14 +2031,17 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_UNION: case BTF_KIND_FUNC: case BTF_KIND_FUNC_PROTO: + case BTF_KIND_VAR: + case BTF_KIND_DATASEC: return 0; case BTF_KIND_INT: h = btf_hash_int(t); - for_each_dedup_cand(d, h, cand_node) { - cand = d->btf->types[cand_node->type_id]; + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; if (btf_equal_int(t, cand)) { - new_id = cand_node->type_id; + new_id = cand_id; break; } } @@ -1866,10 +2049,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_ENUM: h = btf_hash_enum(t); - for_each_dedup_cand(d, h, cand_node) { - cand = d->btf->types[cand_node->type_id]; + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; if (btf_equal_enum(t, cand)) { - new_id = cand_node->type_id; + new_id = cand_id; break; } if (d->opts.dont_resolve_fwds) @@ -1877,21 +2061,22 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) if (btf_compat_enum(t, cand)) { if (btf_is_enum_fwd(t)) { /* resolve fwd to full enum */ - new_id = cand_node->type_id; + new_id = cand_id; break; } /* resolve canonical enum fwd to full enum */ - d->map[cand_node->type_id] = type_id; + d->map[cand_id] = type_id; } } break; case BTF_KIND_FWD: h = btf_hash_common(t); - for_each_dedup_cand(d, h, cand_node) { - cand = d->btf->types[cand_node->type_id]; + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; if (btf_equal_common(t, cand)) { - new_id = cand_node->type_id; + new_id = cand_id; break; } } @@ -1948,13 +2133,13 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) { __u32 orig_type_id = type_id; - if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD) + if (!btf_is_fwd(d->btf->types[type_id])) return type_id; while (is_type_mapped(d, type_id) && d->map[type_id] != type_id) type_id = d->map[type_id]; - if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD) + if (!btf_is_fwd(d->btf->types[type_id])) return type_id; return orig_type_id; @@ -1963,7 +2148,7 @@ static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) static inline __u16 btf_fwd_kind(struct btf_type *t) { - return BTF_INFO_KFLAG(t->info) ? BTF_KIND_UNION : BTF_KIND_STRUCT; + return btf_kflag(t) ? BTF_KIND_UNION : BTF_KIND_STRUCT; } /* @@ -2084,8 +2269,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, cand_type = d->btf->types[cand_id]; canon_type = d->btf->types[canon_id]; - cand_kind = BTF_INFO_KIND(cand_type->info); - canon_kind = BTF_INFO_KIND(canon_type->info); + cand_kind = btf_kind(cand_type); + canon_kind = btf_kind(canon_type); if (cand_type->name_off != canon_type->name_off) return 0; @@ -2134,12 +2319,12 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); case BTF_KIND_ARRAY: { - struct btf_array *cand_arr, *canon_arr; + const struct btf_array *cand_arr, *canon_arr; if (!btf_compat_array(cand_type, canon_type)) return 0; - cand_arr = (struct btf_array *)(cand_type + 1); - canon_arr = (struct btf_array *)(canon_type + 1); + cand_arr = btf_array(cand_type); + canon_arr = btf_array(canon_type); eq = btf_dedup_is_equiv(d, cand_arr->index_type, canon_arr->index_type); if (eq <= 0) @@ -2149,14 +2334,14 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *cand_m, *canon_m; + const struct btf_member *cand_m, *canon_m; __u16 vlen; if (!btf_shallow_equal_struct(cand_type, canon_type)) return 0; - vlen = BTF_INFO_VLEN(cand_type->info); - cand_m = (struct btf_member *)(cand_type + 1); - canon_m = (struct btf_member *)(canon_type + 1); + vlen = btf_vlen(cand_type); + cand_m = btf_members(cand_type); + canon_m = btf_members(canon_type); for (i = 0; i < vlen; i++) { eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type); if (eq <= 0) @@ -2169,7 +2354,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, } case BTF_KIND_FUNC_PROTO: { - struct btf_param *cand_p, *canon_p; + const struct btf_param *cand_p, *canon_p; __u16 vlen; if (!btf_compat_fnproto(cand_type, canon_type)) @@ -2177,9 +2362,9 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type); if (eq <= 0) return eq; - vlen = BTF_INFO_VLEN(cand_type->info); - cand_p = (struct btf_param *)(cand_type + 1); - canon_p = (struct btf_param *)(canon_type + 1); + vlen = btf_vlen(cand_type); + cand_p = btf_params(cand_type); + canon_p = btf_params(canon_type); for (i = 0; i < vlen; i++) { eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type); if (eq <= 0) @@ -2234,8 +2419,8 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d) targ_type_id = d->hypot_map[cand_type_id]; t_id = resolve_type_id(d, targ_type_id); c_id = resolve_type_id(d, cand_type_id); - t_kind = BTF_INFO_KIND(d->btf->types[t_id]->info); - c_kind = BTF_INFO_KIND(d->btf->types[c_id]->info); + t_kind = btf_kind(d->btf->types[t_id]); + c_kind = btf_kind(d->btf->types[c_id]); /* * Resolve FWD into STRUCT/UNION. * It's ok to resolve FWD into STRUCT/UNION that's not yet @@ -2292,25 +2477,26 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d) */ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) { - struct btf_dedup_node *cand_node; struct btf_type *cand_type, *t; + struct hashmap_entry *hash_entry; /* if we don't find equivalent type, then we are canonical */ __u32 new_id = type_id; __u16 kind; - __u32 h; + long h; /* already deduped or is in process of deduping (loop detected) */ if (d->map[type_id] <= BTF_MAX_NR_TYPES) return 0; t = d->btf->types[type_id]; - kind = BTF_INFO_KIND(t->info); + kind = btf_kind(t); if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) return 0; h = btf_hash_struct(t); - for_each_dedup_cand(d, h, cand_node) { + for_each_dedup_cand(d, hash_entry, h) { + __u32 cand_id = (__u32)(long)hash_entry->value; int eq; /* @@ -2323,17 +2509,17 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) * creating a loop (FWD -> STRUCT and STRUCT -> FWD), because * FWD and compatible STRUCT/UNION are considered equivalent. */ - cand_type = d->btf->types[cand_node->type_id]; + cand_type = d->btf->types[cand_id]; if (!btf_shallow_equal_struct(t, cand_type)) continue; btf_dedup_clear_hypot_map(d); - eq = btf_dedup_is_equiv(d, type_id, cand_node->type_id); + eq = btf_dedup_is_equiv(d, type_id, cand_id); if (eq < 0) return eq; if (!eq) continue; - new_id = cand_node->type_id; + new_id = cand_id; btf_dedup_merge_hypot_map(d); break; } @@ -2383,12 +2569,12 @@ static int btf_dedup_struct_types(struct btf_dedup *d) */ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) { - struct btf_dedup_node *cand_node; + struct hashmap_entry *hash_entry; + __u32 new_id = type_id, cand_id; struct btf_type *t, *cand; /* if we don't find equivalent type, then we are representative type */ - __u32 new_id = type_id; int ref_type_id; - __u32 h; + long h; if (d->map[type_id] == BTF_IN_PROGRESS_ID) return -ELOOP; @@ -2398,7 +2584,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) t = d->btf->types[type_id]; d->map[type_id] = BTF_IN_PROGRESS_ID; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_CONST: case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: @@ -2411,17 +2597,18 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) t->type = ref_type_id; h = btf_hash_common(t); - for_each_dedup_cand(d, h, cand_node) { - cand = d->btf->types[cand_node->type_id]; + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; if (btf_equal_common(t, cand)) { - new_id = cand_node->type_id; + new_id = cand_id; break; } } break; case BTF_KIND_ARRAY: { - struct btf_array *info = (struct btf_array *)(t + 1); + struct btf_array *info = btf_array(t); ref_type_id = btf_dedup_ref_type(d, info->type); if (ref_type_id < 0) @@ -2434,10 +2621,11 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) info->index_type = ref_type_id; h = btf_hash_array(t); - for_each_dedup_cand(d, h, cand_node) { - cand = d->btf->types[cand_node->type_id]; + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; if (btf_equal_array(t, cand)) { - new_id = cand_node->type_id; + new_id = cand_id; break; } } @@ -2454,8 +2642,8 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) return ref_type_id; t->type = ref_type_id; - vlen = BTF_INFO_VLEN(t->info); - param = (struct btf_param *)(t + 1); + vlen = btf_vlen(t); + param = btf_params(t); for (i = 0; i < vlen; i++) { ref_type_id = btf_dedup_ref_type(d, param->type); if (ref_type_id < 0) @@ -2465,10 +2653,11 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) } h = btf_hash_fnproto(t); - for_each_dedup_cand(d, h, cand_node) { - cand = d->btf->types[cand_node->type_id]; + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = d->btf->types[cand_id]; if (btf_equal_fnproto(t, cand)) { - new_id = cand_node->type_id; + new_id = cand_id; break; } } @@ -2495,7 +2684,9 @@ static int btf_dedup_ref_types(struct btf_dedup *d) if (err < 0) return err; } - btf_dedup_table_free(d); + /* we won't need d->dedup_table anymore */ + hashmap__free(d->dedup_table); + d->dedup_table = NULL; return 0; } @@ -2592,7 +2783,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) struct btf_type *t = d->btf->types[type_id]; int i, r; - switch (BTF_INFO_KIND(t->info)) { + switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_ENUM: break; @@ -2604,6 +2795,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + case BTF_KIND_VAR: r = btf_dedup_remap_type_id(d, t->type); if (r < 0) return r; @@ -2611,7 +2803,7 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) break; case BTF_KIND_ARRAY: { - struct btf_array *arr_info = (struct btf_array *)(t + 1); + struct btf_array *arr_info = btf_array(t); r = btf_dedup_remap_type_id(d, arr_info->type); if (r < 0) @@ -2626,8 +2818,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - struct btf_member *member = (struct btf_member *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_member *member = btf_members(t); + __u16 vlen = btf_vlen(t); for (i = 0; i < vlen; i++) { r = btf_dedup_remap_type_id(d, member->type); @@ -2640,8 +2832,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) } case BTF_KIND_FUNC_PROTO: { - struct btf_param *param = (struct btf_param *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + struct btf_param *param = btf_params(t); + __u16 vlen = btf_vlen(t); r = btf_dedup_remap_type_id(d, t->type); if (r < 0) @@ -2658,6 +2850,20 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) break; } + case BTF_KIND_DATASEC: { + struct btf_var_secinfo *var = btf_var_secinfos(t); + __u16 vlen = btf_vlen(t); + + for (i = 0; i < vlen; i++) { + r = btf_dedup_remap_type_id(d, var->type); + if (r < 0) + return r; + var->type = r; + var++; + } + break; + } + default: return -EINVAL; } diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 28a1e1e59861..d9ac73a02cde 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -4,6 +4,8 @@ #ifndef __LIBBPF_BTF_H #define __LIBBPF_BTF_H +#include <stdarg.h> +#include <linux/btf.h> #include <linux/types.h> #ifdef __cplusplus @@ -16,11 +18,14 @@ extern "C" { #define BTF_ELF_SEC ".BTF" #define BTF_EXT_ELF_SEC ".BTF.ext" +#define MAPS_ELF_SEC ".maps" struct btf; struct btf_ext; struct btf_type; +struct bpf_object; + /* * The .BTF.ext ELF section layout defined as * struct btf_ext_header @@ -53,13 +58,22 @@ struct btf_ext_header { __u32 func_info_len; __u32 line_info_off; __u32 line_info_len; + + /* optional part of .BTF.ext header */ + __u32 field_reloc_off; + __u32 field_reloc_len; }; LIBBPF_API void btf__free(struct btf *btf); LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size); +LIBBPF_API struct btf *btf__parse_elf(const char *path, + struct btf_ext **btf_ext); +LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf); LIBBPF_API int btf__load(struct btf *btf); LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, const char *type_name); +LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf, + const char *type_name, __u32 kind); LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf); LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); @@ -97,6 +111,199 @@ struct btf_dedup_opts { LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, const struct btf_dedup_opts *opts); +struct btf_dump; + +struct btf_dump_opts { + void *ctx; +}; + +typedef void (*btf_dump_printf_fn_t)(void *ctx, const char *fmt, va_list args); + +LIBBPF_API struct btf_dump *btf_dump__new(const struct btf *btf, + const struct btf_ext *btf_ext, + const struct btf_dump_opts *opts, + btf_dump_printf_fn_t printf_fn); +LIBBPF_API void btf_dump__free(struct btf_dump *d); + +LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); + +/* + * A set of helpers for easier BTF types handling + */ +static inline __u16 btf_kind(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info); +} + +static inline __u16 btf_vlen(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static inline bool btf_kflag(const struct btf_type *t) +{ + return BTF_INFO_KFLAG(t->info); +} + +static inline bool btf_is_int(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_INT; +} + +static inline bool btf_is_ptr(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_PTR; +} + +static inline bool btf_is_array(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ARRAY; +} + +static inline bool btf_is_struct(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_STRUCT; +} + +static inline bool btf_is_union(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_UNION; +} + +static inline bool btf_is_composite(const struct btf_type *t) +{ + __u16 kind = btf_kind(t); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static inline bool btf_is_enum(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM; +} + +static inline bool btf_is_fwd(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FWD; +} + +static inline bool btf_is_typedef(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_TYPEDEF; +} + +static inline bool btf_is_volatile(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_VOLATILE; +} + +static inline bool btf_is_const(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_CONST; +} + +static inline bool btf_is_restrict(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_RESTRICT; +} + +static inline bool btf_is_mod(const struct btf_type *t) +{ + __u16 kind = btf_kind(t); + + return kind == BTF_KIND_VOLATILE || + kind == BTF_KIND_CONST || + kind == BTF_KIND_RESTRICT; +} + +static inline bool btf_is_func(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FUNC; +} + +static inline bool btf_is_func_proto(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_FUNC_PROTO; +} + +static inline bool btf_is_var(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_VAR; +} + +static inline bool btf_is_datasec(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_DATASEC; +} + +static inline __u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(__u32 *)(t + 1)); +} + +static inline __u8 btf_int_offset(const struct btf_type *t) +{ + return BTF_INT_OFFSET(*(__u32 *)(t + 1)); +} + +static inline __u8 btf_int_bits(const struct btf_type *t) +{ + return BTF_INT_BITS(*(__u32 *)(t + 1)); +} + +static inline struct btf_array *btf_array(const struct btf_type *t) +{ + return (struct btf_array *)(t + 1); +} + +static inline struct btf_enum *btf_enum(const struct btf_type *t) +{ + return (struct btf_enum *)(t + 1); +} + +static inline struct btf_member *btf_members(const struct btf_type *t) +{ + return (struct btf_member *)(t + 1); +} + +/* Get bit offset of a member with specified index. */ +static inline __u32 btf_member_bit_offset(const struct btf_type *t, + __u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + bool kflag = btf_kflag(t); + + return kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset; +} +/* + * Get bitfield size of a member, assuming t is BTF_KIND_STRUCT or + * BTF_KIND_UNION. If member is not a bitfield, zero is returned. + */ +static inline __u32 btf_member_bitfield_size(const struct btf_type *t, + __u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + bool kflag = btf_kflag(t); + + return kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; +} + +static inline struct btf_param *btf_params(const struct btf_type *t) +{ + return (struct btf_param *)(t + 1); +} + +static inline struct btf_var *btf_var(const struct btf_type *t) +{ + return (struct btf_var *)(t + 1); +} + +static inline struct btf_var_secinfo * +btf_var_secinfos(const struct btf_type *t) +{ + return (struct btf_var_secinfo *)(t + 1); +} + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c new file mode 100644 index 000000000000..cb126d8fcf75 --- /dev/null +++ b/tools/lib/bpf/btf_dump.c @@ -0,0 +1,1386 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * BTF-to-C type converter. + * + * Copyright (c) 2019 Facebook + */ + +#include <stdbool.h> +#include <stddef.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <linux/err.h> +#include <linux/btf.h> +#include "btf.h" +#include "hashmap.h" +#include "libbpf.h" +#include "libbpf_internal.h" + +static const char PREFIXES[] = "\t\t\t\t\t\t\t\t\t\t\t\t\t"; +static const size_t PREFIX_CNT = sizeof(PREFIXES) - 1; + +static const char *pfx(int lvl) +{ + return lvl >= PREFIX_CNT ? PREFIXES : &PREFIXES[PREFIX_CNT - lvl]; +} + +enum btf_dump_type_order_state { + NOT_ORDERED, + ORDERING, + ORDERED, +}; + +enum btf_dump_type_emit_state { + NOT_EMITTED, + EMITTING, + EMITTED, +}; + +/* per-type auxiliary state */ +struct btf_dump_type_aux_state { + /* topological sorting state */ + enum btf_dump_type_order_state order_state: 2; + /* emitting state used to determine the need for forward declaration */ + enum btf_dump_type_emit_state emit_state: 2; + /* whether forward declaration was already emitted */ + __u8 fwd_emitted: 1; + /* whether unique non-duplicate name was already assigned */ + __u8 name_resolved: 1; + /* whether type is referenced from any other type */ + __u8 referenced: 1; +}; + +struct btf_dump { + const struct btf *btf; + const struct btf_ext *btf_ext; + btf_dump_printf_fn_t printf_fn; + struct btf_dump_opts opts; + + /* per-type auxiliary state */ + struct btf_dump_type_aux_state *type_states; + /* per-type optional cached unique name, must be freed, if present */ + const char **cached_names; + + /* topo-sorted list of dependent type definitions */ + __u32 *emit_queue; + int emit_queue_cap; + int emit_queue_cnt; + + /* + * stack of type declarations (e.g., chain of modifiers, arrays, + * funcs, etc) + */ + __u32 *decl_stack; + int decl_stack_cap; + int decl_stack_cnt; + + /* maps struct/union/enum name to a number of name occurrences */ + struct hashmap *type_names; + /* + * maps typedef identifiers and enum value names to a number of such + * name occurrences + */ + struct hashmap *ident_names; +}; + +static size_t str_hash_fn(const void *key, void *ctx) +{ + const char *s = key; + size_t h = 0; + + while (*s) { + h = h * 31 + *s; + s++; + } + return h; +} + +static bool str_equal_fn(const void *a, const void *b, void *ctx) +{ + return strcmp(a, b) == 0; +} + +static const char *btf_name_of(const struct btf_dump *d, __u32 name_off) +{ + return btf__name_by_offset(d->btf, name_off); +} + +static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + d->printf_fn(d->opts.ctx, fmt, args); + va_end(args); +} + +struct btf_dump *btf_dump__new(const struct btf *btf, + const struct btf_ext *btf_ext, + const struct btf_dump_opts *opts, + btf_dump_printf_fn_t printf_fn) +{ + struct btf_dump *d; + int err; + + d = calloc(1, sizeof(struct btf_dump)); + if (!d) + return ERR_PTR(-ENOMEM); + + d->btf = btf; + d->btf_ext = btf_ext; + d->printf_fn = printf_fn; + d->opts.ctx = opts ? opts->ctx : NULL; + + d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); + if (IS_ERR(d->type_names)) { + err = PTR_ERR(d->type_names); + d->type_names = NULL; + btf_dump__free(d); + return ERR_PTR(err); + } + d->ident_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); + if (IS_ERR(d->ident_names)) { + err = PTR_ERR(d->ident_names); + d->ident_names = NULL; + btf_dump__free(d); + return ERR_PTR(err); + } + + return d; +} + +void btf_dump__free(struct btf_dump *d) +{ + int i, cnt; + + if (!d) + return; + + free(d->type_states); + if (d->cached_names) { + /* any set cached name is owned by us and should be freed */ + for (i = 0, cnt = btf__get_nr_types(d->btf); i <= cnt; i++) { + if (d->cached_names[i]) + free((void *)d->cached_names[i]); + } + } + free(d->cached_names); + free(d->emit_queue); + free(d->decl_stack); + hashmap__free(d->type_names); + hashmap__free(d->ident_names); + + free(d); +} + +static int btf_dump_mark_referenced(struct btf_dump *d); +static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr); +static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id); + +/* + * Dump BTF type in a compilable C syntax, including all the necessary + * dependent types, necessary for compilation. If some of the dependent types + * were already emitted as part of previous btf_dump__dump_type() invocation + * for another type, they won't be emitted again. This API allows callers to + * filter out BTF types according to user-defined criterias and emitted only + * minimal subset of types, necessary to compile everything. Full struct/union + * definitions will still be emitted, even if the only usage is through + * pointer and could be satisfied with just a forward declaration. + * + * Dumping is done in two high-level passes: + * 1. Topologically sort type definitions to satisfy C rules of compilation. + * 2. Emit type definitions in C syntax. + * + * Returns 0 on success; <0, otherwise. + */ +int btf_dump__dump_type(struct btf_dump *d, __u32 id) +{ + int err, i; + + if (id > btf__get_nr_types(d->btf)) + return -EINVAL; + + /* type states are lazily allocated, as they might not be needed */ + if (!d->type_states) { + d->type_states = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->type_states[0])); + if (!d->type_states) + return -ENOMEM; + d->cached_names = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->cached_names[0])); + if (!d->cached_names) + return -ENOMEM; + + /* VOID is special */ + d->type_states[0].order_state = ORDERED; + d->type_states[0].emit_state = EMITTED; + + /* eagerly determine referenced types for anon enums */ + err = btf_dump_mark_referenced(d); + if (err) + return err; + } + + d->emit_queue_cnt = 0; + err = btf_dump_order_type(d, id, false); + if (err < 0) + return err; + + for (i = 0; i < d->emit_queue_cnt; i++) + btf_dump_emit_type(d, d->emit_queue[i], 0 /*top-level*/); + + return 0; +} + +/* + * Mark all types that are referenced from any other type. This is used to + * determine top-level anonymous enums that need to be emitted as an + * independent type declarations. + * Anonymous enums come in two flavors: either embedded in a struct's field + * 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: + * top-level anonymous enum won't be referenced by anything, while embedded + * one will. + */ +static int btf_dump_mark_referenced(struct btf_dump *d) +{ + int i, j, n = btf__get_nr_types(d->btf); + const struct btf_type *t; + __u16 vlen; + + for (i = 1; i <= n; i++) { + t = btf__type_by_id(d->btf, i); + vlen = btf_vlen(t); + + switch (btf_kind(t)) { + case BTF_KIND_INT: + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + break; + + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + d->type_states[t->type].referenced = 1; + break; + + case BTF_KIND_ARRAY: { + const struct btf_array *a = btf_array(t); + + d->type_states[a->index_type].referenced = 1; + d->type_states[a->type].referenced = 1; + break; + } + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + + for (j = 0; j < vlen; j++, m++) + d->type_states[m->type].referenced = 1; + break; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + + for (j = 0; j < vlen; j++, p++) + d->type_states[p->type].referenced = 1; + break; + } + case BTF_KIND_DATASEC: { + const struct btf_var_secinfo *v = btf_var_secinfos(t); + + for (j = 0; j < vlen; j++, v++) + d->type_states[v->type].referenced = 1; + break; + } + default: + return -EINVAL; + } + } + return 0; +} +static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id) +{ + __u32 *new_queue; + size_t new_cap; + + if (d->emit_queue_cnt >= d->emit_queue_cap) { + new_cap = max(16, d->emit_queue_cap * 3 / 2); + new_queue = realloc(d->emit_queue, + new_cap * sizeof(new_queue[0])); + if (!new_queue) + return -ENOMEM; + d->emit_queue = new_queue; + d->emit_queue_cap = new_cap; + } + + d->emit_queue[d->emit_queue_cnt++] = id; + return 0; +} + +/* + * Determine order of emitting dependent types and specified type to satisfy + * C compilation rules. This is done through topological sorting with an + * additional complication which comes from C rules. The main idea for C is + * that if some type is "embedded" into a struct/union, it's size needs to be + * known at the time of definition of containing type. E.g., for: + * + * struct A {}; + * struct B { struct A x; } + * + * struct A *HAS* to be defined before struct B, because it's "embedded", + * i.e., it is part of struct B layout. But in the following case: + * + * struct A; + * struct B { struct A *x; } + * struct A {}; + * + * it's enough to just have a forward declaration of struct A at the time of + * struct B definition, as struct B has a pointer to struct A, so the size of + * field x is known without knowing struct A size: it's sizeof(void *). + * + * Unfortunately, there are some trickier cases we need to handle, e.g.: + * + * struct A {}; // if this was forward-declaration: compilation error + * struct B { + * struct { // anonymous struct + * struct A y; + * } *x; + * }; + * + * In this case, struct B's field x is a pointer, so it's size is known + * regardless of the size of (anonymous) struct it points to. But because this + * struct is anonymous and thus defined inline inside struct B, *and* it + * embeds struct A, compiler requires full definition of struct A to be known + * before struct B can be defined. This creates a transitive dependency + * between struct A and struct B. If struct A was forward-declared before + * struct B definition and fully defined after struct B definition, that would + * trigger compilation error. + * + * All this means that while we are doing topological sorting on BTF type + * graph, we need to determine relationships between different types (graph + * nodes): + * - weak link (relationship) between X and Y, if Y *CAN* be + * forward-declared at the point of X definition; + * - strong link, if Y *HAS* to be fully-defined before X can be defined. + * + * The rule is as follows. Given a chain of BTF types from X to Y, if there is + * BTF_KIND_PTR type in the chain and at least one non-anonymous type + * Z (excluding X, including Y), then link is weak. Otherwise, it's strong. + * Weak/strong relationship is determined recursively during DFS traversal and + * is returned as a result from btf_dump_order_type(). + * + * btf_dump_order_type() is trying to avoid unnecessary forward declarations, + * but it is not guaranteeing that no extraneous forward declarations will be + * emitted. + * + * To avoid extra work, algorithm marks some of BTF types as ORDERED, when + * it's done with them, but not for all (e.g., VOLATILE, CONST, RESTRICT, + * ARRAY, FUNC_PROTO), as weak/strong semantics for those depends on the + * entire graph path, so depending where from one came to that BTF type, it + * might cause weak or strong ordering. For types like STRUCT/UNION/INT/ENUM, + * once they are processed, there is no need to do it again, so they are + * marked as ORDERED. We can mark PTR as ORDERED as well, as it semi-forces + * weak link, unless subsequent referenced STRUCT/UNION/ENUM is anonymous. But + * in any case, once those are processed, no need to do it again, as the + * result won't change. + * + * Returns: + * - 1, if type is part of strong link (so there is strong topological + * ordering requirements); + * - 0, if type is part of weak link (so can be satisfied through forward + * declaration); + * - <0, on error (e.g., unsatisfiable type loop detected). + */ +static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) +{ + /* + * Order state is used to detect strong link cycles, but only for BTF + * kinds that are or could be an independent definition (i.e., + * stand-alone fwd decl, enum, typedef, struct, union). Ptrs, arrays, + * func_protos, modifiers are just means to get to these definitions. + * Int/void don't need definitions, they are assumed to be always + * properly defined. We also ignore datasec, var, and funcs for now. + * So for all non-defining kinds, we never even set ordering state, + * for defining kinds we set ORDERING and subsequently ORDERED if it + * forms a strong link. + */ + struct btf_dump_type_aux_state *tstate = &d->type_states[id]; + const struct btf_type *t; + __u16 vlen; + int err, i; + + /* return true, letting typedefs know that it's ok to be emitted */ + if (tstate->order_state == ORDERED) + return 1; + + t = btf__type_by_id(d->btf, id); + + if (tstate->order_state == ORDERING) { + /* type loop, but resolvable through fwd declaration */ + if (btf_is_composite(t) && through_ptr && t->name_off != 0) + return 0; + pr_warn("unsatisfiable type cycle, id:[%u]\n", id); + return -ELOOP; + } + + switch (btf_kind(t)) { + case BTF_KIND_INT: + tstate->order_state = ORDERED; + return 0; + + case BTF_KIND_PTR: + err = btf_dump_order_type(d, t->type, true); + tstate->order_state = ORDERED; + return err; + + case BTF_KIND_ARRAY: + return btf_dump_order_type(d, btf_array(t)->type, through_ptr); + + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + /* + * struct/union is part of strong link, only if it's embedded + * (so no ptr in a path) or it's anonymous (so has to be + * defined inline, even if declared through ptr) + */ + if (through_ptr && t->name_off != 0) + return 0; + + tstate->order_state = ORDERING; + + vlen = btf_vlen(t); + for (i = 0; i < vlen; i++, m++) { + err = btf_dump_order_type(d, m->type, false); + if (err < 0) + return err; + } + + if (t->name_off != 0) { + err = btf_dump_add_emit_queue_id(d, id); + if (err < 0) + return err; + } + + tstate->order_state = ORDERED; + return 1; + } + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + /* + * non-anonymous or non-referenced enums are top-level + * declarations and should be emitted. Same logic can be + * applied to FWDs, it won't hurt anyways. + */ + if (t->name_off != 0 || !tstate->referenced) { + err = btf_dump_add_emit_queue_id(d, id); + if (err) + return err; + } + tstate->order_state = ORDERED; + return 1; + + case BTF_KIND_TYPEDEF: { + int is_strong; + + is_strong = btf_dump_order_type(d, t->type, through_ptr); + if (is_strong < 0) + return is_strong; + + /* typedef is similar to struct/union w.r.t. fwd-decls */ + if (through_ptr && !is_strong) + return 0; + + /* typedef is always a named definition */ + err = btf_dump_add_emit_queue_id(d, id); + if (err) + return err; + + d->type_states[id].order_state = ORDERED; + return 1; + } + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return btf_dump_order_type(d, t->type, through_ptr); + + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + bool is_strong; + + err = btf_dump_order_type(d, t->type, through_ptr); + if (err < 0) + return err; + is_strong = err > 0; + + vlen = btf_vlen(t); + for (i = 0; i < vlen; i++, p++) { + err = btf_dump_order_type(d, p->type, through_ptr); + if (err < 0) + return err; + if (err > 0) + is_strong = true; + } + return is_strong; + } + case BTF_KIND_FUNC: + case BTF_KIND_VAR: + case BTF_KIND_DATASEC: + d->type_states[id].order_state = ORDERED; + return 0; + + default: + return -EINVAL; + } +} + +static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t); +static void btf_dump_emit_struct_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl); + +static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t); +static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl); + +static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, + const struct btf_type *t); + +static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl); + +/* a local view into a shared stack */ +struct id_stack { + const __u32 *ids; + int cnt; +}; + +static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, + const char *fname, int lvl); +static void btf_dump_emit_type_chain(struct btf_dump *d, + struct id_stack *decl_stack, + const char *fname, int lvl); + +static const char *btf_dump_type_name(struct btf_dump *d, __u32 id); +static const char *btf_dump_ident_name(struct btf_dump *d, __u32 id); +static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map, + const char *orig_name); + +static bool btf_dump_is_blacklisted(struct btf_dump *d, __u32 id) +{ + const struct btf_type *t = btf__type_by_id(d->btf, id); + + /* __builtin_va_list is a compiler built-in, which causes compilation + * errors, when compiling w/ different compiler, then used to compile + * original code (e.g., GCC to compile kernel, Clang to use generated + * C header from BTF). As it is built-in, it should be already defined + * properly internally in compiler. + */ + if (t->name_off == 0) + return false; + return strcmp(btf_name_of(d, t->name_off), "__builtin_va_list") == 0; +} + +/* + * Emit C-syntax definitions of types from chains of BTF types. + * + * High-level handling of determining necessary forward declarations are handled + * by btf_dump_emit_type() itself, but all nitty-gritty details of emitting type + * declarations/definitions in C syntax are handled by a combo of + * btf_dump_emit_type_decl()/btf_dump_emit_type_chain() w/ delegation to + * corresponding btf_dump_emit_*_{def,fwd}() functions. + * + * We also keep track of "containing struct/union type ID" to determine when + * we reference it from inside and thus can avoid emitting unnecessary forward + * declaration. + * + * This algorithm is designed in such a way, that even if some error occurs + * (either technical, e.g., out of memory, or logical, i.e., malformed BTF + * that doesn't comply to C rules completely), algorithm will try to proceed + * and produce as much meaningful output as possible. + */ +static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) +{ + struct btf_dump_type_aux_state *tstate = &d->type_states[id]; + bool top_level_def = cont_id == 0; + const struct btf_type *t; + __u16 kind; + + if (tstate->emit_state == EMITTED) + return; + + t = btf__type_by_id(d->btf, id); + kind = btf_kind(t); + + if (tstate->emit_state == EMITTING) { + if (tstate->fwd_emitted) + return; + + switch (kind) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + /* + * if we are referencing a struct/union that we are + * part of - then no need for fwd declaration + */ + if (id == cont_id) + return; + if (t->name_off == 0) { + pr_warn("anonymous struct/union loop, id:[%u]\n", + id); + return; + } + btf_dump_emit_struct_fwd(d, id, t); + btf_dump_printf(d, ";\n\n"); + tstate->fwd_emitted = 1; + break; + case BTF_KIND_TYPEDEF: + /* + * for typedef fwd_emitted means typedef definition + * was emitted, but it can be used only for "weak" + * references through pointer only, not for embedding + */ + if (!btf_dump_is_blacklisted(d, id)) { + btf_dump_emit_typedef_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + }; + tstate->fwd_emitted = 1; + break; + default: + break; + } + + return; + } + + switch (kind) { + case BTF_KIND_INT: + tstate->emit_state = EMITTED; + break; + case BTF_KIND_ENUM: + if (top_level_def) { + btf_dump_emit_enum_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + } + tstate->emit_state = EMITTED; + break; + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + btf_dump_emit_type(d, t->type, cont_id); + break; + case BTF_KIND_ARRAY: + btf_dump_emit_type(d, btf_array(t)->type, cont_id); + break; + case BTF_KIND_FWD: + btf_dump_emit_fwd_def(d, id, t); + btf_dump_printf(d, ";\n\n"); + tstate->emit_state = EMITTED; + break; + case BTF_KIND_TYPEDEF: + tstate->emit_state = EMITTING; + btf_dump_emit_type(d, t->type, id); + /* + * typedef can server as both definition and forward + * declaration; at this stage someone depends on + * typedef as a forward declaration (refers to it + * through pointer), so unless we already did it, + * emit typedef as a forward declaration + */ + if (!tstate->fwd_emitted && !btf_dump_is_blacklisted(d, id)) { + btf_dump_emit_typedef_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + } + tstate->emit_state = EMITTED; + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + tstate->emit_state = EMITTING; + /* if it's a top-level struct/union definition or struct/union + * is anonymous, then in C we'll be emitting all fields and + * their types (as opposed to just `struct X`), so we need to + * make sure that all types, referenced from struct/union + * members have necessary forward-declarations, where + * applicable + */ + if (top_level_def || t->name_off == 0) { + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); + int i, new_cont_id; + + new_cont_id = t->name_off == 0 ? cont_id : id; + for (i = 0; i < vlen; i++, m++) + btf_dump_emit_type(d, m->type, new_cont_id); + } else if (!tstate->fwd_emitted && id != cont_id) { + btf_dump_emit_struct_fwd(d, id, t); + btf_dump_printf(d, ";\n\n"); + tstate->fwd_emitted = 1; + } + + if (top_level_def) { + btf_dump_emit_struct_def(d, id, t, 0); + btf_dump_printf(d, ";\n\n"); + tstate->emit_state = EMITTED; + } else { + tstate->emit_state = NOT_EMITTED; + } + break; + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); + int i; + + btf_dump_emit_type(d, t->type, cont_id); + for (i = 0; i < vlen; i++, p++) + btf_dump_emit_type(d, p->type, cont_id); + + break; + } + default: + break; + } +} + +static int btf_align_of(const struct btf *btf, __u32 id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + __u16 kind = btf_kind(t); + + switch (kind) { + case BTF_KIND_INT: + case BTF_KIND_ENUM: + return min(sizeof(void *), t->size); + case BTF_KIND_PTR: + return sizeof(void *); + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return btf_align_of(btf, t->type); + case BTF_KIND_ARRAY: + return btf_align_of(btf, btf_array(t)->type); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + const struct btf_member *m = btf_members(t); + __u16 vlen = btf_vlen(t); + int i, align = 1; + + for (i = 0; i < vlen; i++, m++) + align = max(align, btf_align_of(btf, m->type)); + + return align; + } + default: + pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); + return 1; + } +} + +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; + __u16 vlen; + + align = btf_align_of(btf, id); + /* size of a non-packed struct has to be a multiple of its alignment*/ + if (t->size % align) + return true; + + m = btf_members(t); + vlen = btf_vlen(t); + /* all non-bitfield fields have to be naturally aligned */ + for (i = 0; i < vlen; i++, m++) { + align = btf_align_of(btf, m->type); + bit_sz = btf_member_bitfield_size(t, i); + if (bit_sz == 0 && m->offset % (8 * 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 + */ + 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 off_diff = m_off - cur_off; + int ptr_bits = sizeof(void *) * 8; + + 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; + + 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); + } + btf_dump_printf(d, "\n%s%s: %d;", pfx(lvl), pad_type, pad_bits); + off_diff -= pad_bits; + } +} + +static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + btf_dump_printf(d, "%s %s", + btf_is_struct(t) ? "struct" : "union", + btf_dump_type_name(d, id)); +} + +static void btf_dump_emit_struct_def(struct btf_dump *d, + __u32 id, + const struct btf_type *t, + int lvl) +{ + const struct btf_member *m = btf_members(t); + bool is_struct = btf_is_struct(t); + int align, i, packed, off = 0; + __u16 vlen = btf_vlen(t); + + packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; + + btf_dump_printf(d, "%s%s%s {", + is_struct ? "struct" : "union", + t->name_off ? " " : "", + btf_dump_type_name(d, id)); + + for (i = 0; i < vlen; i++, m++) { + const char *fname; + int m_off, m_sz; + + 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); + + btf_dump_emit_bit_padding(d, off, m_off, m_sz, align, 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; + } else { + m_sz = max(0, btf__resolve_size(d->btf, m->type)); + off = m_off + m_sz * 8; + } + 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 (vlen) + btf_dump_printf(d, "\n"); + btf_dump_printf(d, "%s}", pfx(lvl)); + if (packed) + btf_dump_printf(d, " __attribute__((packed))"); +} + +static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + btf_dump_printf(d, "enum %s", btf_dump_type_name(d, id)); +} + +static void btf_dump_emit_enum_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, + int lvl) +{ + const struct btf_enum *v = btf_enum(t); + __u16 vlen = btf_vlen(t); + const char *name; + size_t dup_cnt; + int i; + + btf_dump_printf(d, "enum%s%s", + t->name_off ? " " : "", + btf_dump_type_name(d, id)); + + if (vlen) { + btf_dump_printf(d, " {"); + for (i = 0; i < vlen; i++, v++) { + name = btf_name_of(d, v->name_off); + /* enumerators share namespace with typedef idents */ + dup_cnt = btf_dump_name_dups(d, d->ident_names, name); + if (dup_cnt > 1) { + btf_dump_printf(d, "\n%s%s___%zu = %d,", + pfx(lvl + 1), name, dup_cnt, + (__s32)v->val); + } else { + btf_dump_printf(d, "\n%s%s = %d,", + pfx(lvl + 1), name, + (__s32)v->val); + } + } + btf_dump_printf(d, "\n%s}", pfx(lvl)); + } +} + +static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + const char *name = btf_dump_type_name(d, id); + + if (btf_kflag(t)) + btf_dump_printf(d, "union %s", name); + else + btf_dump_printf(d, "struct %s", name); +} + +static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id, + const struct btf_type *t, int lvl) +{ + const char *name = btf_dump_ident_name(d, id); + + /* + * Old GCC versions are emitting invalid typedef for __gnuc_va_list + * pointing to VOID. This generates warnings from btf_dump() and + * results in uncompilable header file, so we are fixing it up here + * with valid typedef into __builtin_va_list. + */ + if (t->type == 0 && strcmp(name, "__gnuc_va_list") == 0) { + btf_dump_printf(d, "typedef __builtin_va_list __gnuc_va_list"); + return; + } + + btf_dump_printf(d, "typedef "); + btf_dump_emit_type_decl(d, t->type, name, lvl); +} + +static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id) +{ + __u32 *new_stack; + size_t new_cap; + + if (d->decl_stack_cnt >= d->decl_stack_cap) { + new_cap = max(16, d->decl_stack_cap * 3 / 2); + new_stack = realloc(d->decl_stack, + new_cap * sizeof(new_stack[0])); + if (!new_stack) + return -ENOMEM; + d->decl_stack = new_stack; + d->decl_stack_cap = new_cap; + } + + d->decl_stack[d->decl_stack_cnt++] = id; + + return 0; +} + +/* + * Emit type declaration (e.g., field type declaration in a struct or argument + * declaration in function prototype) in correct C syntax. + * + * For most types it's trivial, but there are few quirky type declaration + * cases worth mentioning: + * - function prototypes (especially nesting of function prototypes); + * - arrays; + * - const/volatile/restrict for pointers vs other types. + * + * For a good discussion of *PARSING* C syntax (as a human), see + * Peter van der Linden's "Expert C Programming: Deep C Secrets", + * Ch.3 "Unscrambling Declarations in C". + * + * It won't help with BTF to C conversion much, though, as it's an opposite + * problem. So we came up with this algorithm in reverse to van der Linden's + * parsing algorithm. It goes from structured BTF representation of type + * declaration to a valid compilable C syntax. + * + * For instance, consider this C typedef: + * typedef const int * const * arr[10] arr_t; + * It will be represented in BTF with this chain of BTF types: + * [typedef] -> [array] -> [ptr] -> [const] -> [ptr] -> [const] -> [int] + * + * Notice how [const] modifier always goes before type it modifies in BTF type + * graph, but in C syntax, const/volatile/restrict modifiers are written to + * the right of pointers, but to the left of other types. There are also other + * quirks, like function pointers, arrays of them, functions returning other + * functions, etc. + * + * We handle that by pushing all the types to a stack, until we hit "terminal" + * type (int/enum/struct/union/fwd). Then depending on the kind of a type on + * top of a stack, modifiers are handled differently. Array/function pointers + * have also wildly different syntax and how nesting of them are done. See + * code for authoritative definition. + * + * To avoid allocating new stack for each independent chain of BTF types, we + * share one bigger stack, with each chain working only on its own local view + * of a stack frame. Some care is required to "pop" stack frames after + * processing type declaration chain. + */ +static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, + const char *fname, int lvl) +{ + struct id_stack decl_stack; + const struct btf_type *t; + int err, stack_start; + + stack_start = d->decl_stack_cnt; + for (;;) { + err = btf_dump_push_decl_stack_id(d, id); + if (err < 0) { + /* + * if we don't have enough memory for entire type decl + * chain, restore stack, emit warning, and try to + * proceed nevertheless + */ + pr_warn("not enough memory for decl stack:%d", err); + d->decl_stack_cnt = stack_start; + return; + } + + /* VOID */ + if (id == 0) + break; + + t = btf__type_by_id(d->btf, id); + switch (btf_kind(t)) { + case BTF_KIND_PTR: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_FUNC_PROTO: + id = t->type; + break; + case BTF_KIND_ARRAY: + id = btf_array(t)->type; + break; + case BTF_KIND_INT: + case BTF_KIND_ENUM: + case BTF_KIND_FWD: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_TYPEDEF: + goto done; + default: + pr_warn("unexpected type in decl chain, kind:%u, id:[%u]\n", + btf_kind(t), id); + goto done; + } + } +done: + /* + * We might be inside a chain of declarations (e.g., array of function + * pointers returning anonymous (so inlined) structs, having another + * array field). Each of those needs its own "stack frame" to handle + * emitting of declarations. Those stack frames are non-overlapping + * portions of shared btf_dump->decl_stack. To make it a bit nicer to + * handle this set of nested stacks, we create a view corresponding to + * our own "stack frame" and work with it as an independent stack. + * We'll need to clean up after emit_type_chain() returns, though. + */ + decl_stack.ids = d->decl_stack + stack_start; + decl_stack.cnt = d->decl_stack_cnt - stack_start; + btf_dump_emit_type_chain(d, &decl_stack, fname, lvl); + /* + * emit_type_chain() guarantees that it will pop its entire decl_stack + * frame before returning. But it works with a read-only view into + * decl_stack, so it doesn't actually pop anything from the + * perspective of shared btf_dump->decl_stack, per se. We need to + * reset decl_stack state to how it was before us to avoid it growing + * all the time. + */ + d->decl_stack_cnt = stack_start; +} + +static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) +{ + const struct btf_type *t; + __u32 id; + + while (decl_stack->cnt) { + id = decl_stack->ids[decl_stack->cnt - 1]; + t = btf__type_by_id(d->btf, id); + + switch (btf_kind(t)) { + case BTF_KIND_VOLATILE: + btf_dump_printf(d, "volatile "); + break; + case BTF_KIND_CONST: + btf_dump_printf(d, "const "); + break; + case BTF_KIND_RESTRICT: + btf_dump_printf(d, "restrict "); + break; + default: + return; + } + decl_stack->cnt--; + } +} + +static void btf_dump_emit_name(const struct btf_dump *d, + const char *name, bool last_was_ptr) +{ + bool separate = name[0] && !last_was_ptr; + + btf_dump_printf(d, "%s%s", separate ? " " : "", name); +} + +static void btf_dump_emit_type_chain(struct btf_dump *d, + struct id_stack *decls, + const char *fname, int lvl) +{ + /* + * last_was_ptr is used to determine if we need to separate pointer + * asterisk (*) from previous part of type signature with space, so + * that we get `int ***`, instead of `int * * *`. We default to true + * for cases where we have single pointer in a chain. E.g., in ptr -> + * func_proto case. func_proto will start a new emit_type_chain call + * with just ptr, which should be emitted as (*) or (*<fname>), so we + * don't want to prepend space for that last pointer. + */ + bool last_was_ptr = true; + const struct btf_type *t; + const char *name; + __u16 kind; + __u32 id; + + while (decls->cnt) { + id = decls->ids[--decls->cnt]; + if (id == 0) { + /* VOID is a special snowflake */ + btf_dump_emit_mods(d, decls); + btf_dump_printf(d, "void"); + last_was_ptr = false; + continue; + } + + t = btf__type_by_id(d->btf, id); + kind = btf_kind(t); + + switch (kind) { + case BTF_KIND_INT: + btf_dump_emit_mods(d, decls); + name = btf_name_of(d, t->name_off); + btf_dump_printf(d, "%s", name); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + btf_dump_emit_mods(d, decls); + /* inline anonymous struct/union */ + if (t->name_off == 0) + btf_dump_emit_struct_def(d, id, t, lvl); + else + btf_dump_emit_struct_fwd(d, id, t); + break; + case BTF_KIND_ENUM: + btf_dump_emit_mods(d, decls); + /* inline anonymous enum */ + if (t->name_off == 0) + btf_dump_emit_enum_def(d, id, t, lvl); + else + btf_dump_emit_enum_fwd(d, id, t); + break; + case BTF_KIND_FWD: + btf_dump_emit_mods(d, decls); + btf_dump_emit_fwd_def(d, id, t); + break; + case BTF_KIND_TYPEDEF: + btf_dump_emit_mods(d, decls); + btf_dump_printf(d, "%s", btf_dump_ident_name(d, id)); + break; + case BTF_KIND_PTR: + btf_dump_printf(d, "%s", last_was_ptr ? "*" : " *"); + break; + case BTF_KIND_VOLATILE: + btf_dump_printf(d, " volatile"); + break; + case BTF_KIND_CONST: + btf_dump_printf(d, " const"); + break; + case BTF_KIND_RESTRICT: + btf_dump_printf(d, " restrict"); + break; + case BTF_KIND_ARRAY: { + const struct btf_array *a = btf_array(t); + const struct btf_type *next_t; + __u32 next_id; + bool multidim; + /* + * GCC has a bug + * (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=8354) + * which causes it to emit extra const/volatile + * modifiers for an array, if array's element type has + * const/volatile modifiers. Clang doesn't do that. + * In general, it doesn't seem very meaningful to have + * a const/volatile modifier for array, so we are + * going to silently skip them here. + */ + while (decls->cnt) { + next_id = decls->ids[decls->cnt - 1]; + next_t = btf__type_by_id(d->btf, next_id); + if (btf_is_mod(next_t)) + decls->cnt--; + else + break; + } + + if (decls->cnt == 0) { + btf_dump_emit_name(d, fname, last_was_ptr); + btf_dump_printf(d, "[%u]", a->nelems); + return; + } + + next_id = decls->ids[decls->cnt - 1]; + next_t = btf__type_by_id(d->btf, next_id); + multidim = btf_is_array(next_t); + /* we need space if we have named non-pointer */ + if (fname[0] && !last_was_ptr) + btf_dump_printf(d, " "); + /* no parentheses for multi-dimensional array */ + if (!multidim) + btf_dump_printf(d, "("); + btf_dump_emit_type_chain(d, decls, fname, lvl); + if (!multidim) + btf_dump_printf(d, ")"); + btf_dump_printf(d, "[%u]", a->nelems); + return; + } + case BTF_KIND_FUNC_PROTO: { + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); + int i; + + btf_dump_emit_mods(d, decls); + if (decls->cnt) { + btf_dump_printf(d, " ("); + btf_dump_emit_type_chain(d, decls, fname, lvl); + btf_dump_printf(d, ")"); + } else { + btf_dump_emit_name(d, fname, last_was_ptr); + } + btf_dump_printf(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. + */ + if (vlen == 1 && p->type == 0) { + btf_dump_printf(d, ")"); + return; + } + + for (i = 0; i < vlen; i++, p++) { + if (i > 0) + btf_dump_printf(d, ", "); + + /* last arg of type void is vararg */ + if (i == vlen - 1 && p->type == 0) { + btf_dump_printf(d, "..."); + break; + } + + name = btf_name_of(d, p->name_off); + btf_dump_emit_type_decl(d, p->type, name, lvl); + } + + btf_dump_printf(d, ")"); + return; + } + default: + pr_warn("unexpected type in decl chain, kind:%u, id:[%u]\n", + kind, id); + return; + } + + last_was_ptr = kind == BTF_KIND_PTR; + } + + btf_dump_emit_name(d, fname, last_was_ptr); +} + +/* return number of duplicates (occurrences) of a given name */ +static size_t btf_dump_name_dups(struct btf_dump *d, struct hashmap *name_map, + const char *orig_name) +{ + size_t dup_cnt = 0; + + hashmap__find(name_map, orig_name, (void **)&dup_cnt); + dup_cnt++; + hashmap__set(name_map, orig_name, (void *)dup_cnt, NULL, NULL); + + return dup_cnt; +} + +static const char *btf_dump_resolve_name(struct btf_dump *d, __u32 id, + struct hashmap *name_map) +{ + struct btf_dump_type_aux_state *s = &d->type_states[id]; + const struct btf_type *t = btf__type_by_id(d->btf, id); + const char *orig_name = btf_name_of(d, t->name_off); + const char **cached_name = &d->cached_names[id]; + size_t dup_cnt; + + if (t->name_off == 0) + return ""; + + if (s->name_resolved) + return *cached_name ? *cached_name : orig_name; + + dup_cnt = btf_dump_name_dups(d, name_map, orig_name); + if (dup_cnt > 1) { + const size_t max_len = 256; + char new_name[max_len]; + + snprintf(new_name, max_len, "%s___%zu", orig_name, dup_cnt); + *cached_name = strdup(new_name); + } + + s->name_resolved = 1; + return *cached_name ? *cached_name : orig_name; +} + +static const char *btf_dump_type_name(struct btf_dump *d, __u32 id) +{ + return btf_dump_resolve_name(d, id, d->type_names); +} + +static const char *btf_dump_ident_name(struct btf_dump *d, __u32 id) +{ + return btf_dump_resolve_name(d, id, d->ident_names); +} diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c new file mode 100644 index 000000000000..6122272943e6 --- /dev/null +++ b/tools/lib/bpf/hashmap.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +/* + * Generic non-thread safe hash map implementation. + * + * Copyright (c) 2019 Facebook + */ +#include <stdint.h> +#include <stdlib.h> +#include <stdio.h> +#include <errno.h> +#include <linux/err.h> +#include "hashmap.h" + +/* start with 4 buckets */ +#define HASHMAP_MIN_CAP_BITS 2 + +static void hashmap_add_entry(struct hashmap_entry **pprev, + struct hashmap_entry *entry) +{ + entry->next = *pprev; + *pprev = entry; +} + +static void hashmap_del_entry(struct hashmap_entry **pprev, + struct hashmap_entry *entry) +{ + *pprev = entry->next; + entry->next = NULL; +} + +void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn, + hashmap_equal_fn equal_fn, void *ctx) +{ + map->hash_fn = hash_fn; + map->equal_fn = equal_fn; + map->ctx = ctx; + + map->buckets = NULL; + map->cap = 0; + map->cap_bits = 0; + map->sz = 0; +} + +struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, + hashmap_equal_fn equal_fn, + void *ctx) +{ + struct hashmap *map = malloc(sizeof(struct hashmap)); + + if (!map) + return ERR_PTR(-ENOMEM); + hashmap__init(map, hash_fn, equal_fn, ctx); + return map; +} + +void hashmap__clear(struct hashmap *map) +{ + free(map->buckets); + map->cap = map->cap_bits = map->sz = 0; +} + +void hashmap__free(struct hashmap *map) +{ + if (!map) + return; + + hashmap__clear(map); + free(map); +} + +size_t hashmap__size(const struct hashmap *map) +{ + return map->sz; +} + +size_t hashmap__capacity(const struct hashmap *map) +{ + return map->cap; +} + +static bool hashmap_needs_to_grow(struct hashmap *map) +{ + /* grow if empty or more than 75% filled */ + return (map->cap == 0) || ((map->sz + 1) * 4 / 3 > map->cap); +} + +static int hashmap_grow(struct hashmap *map) +{ + struct hashmap_entry **new_buckets; + struct hashmap_entry *cur, *tmp; + size_t new_cap_bits, new_cap; + size_t h; + int bkt; + + new_cap_bits = map->cap_bits + 1; + if (new_cap_bits < HASHMAP_MIN_CAP_BITS) + new_cap_bits = HASHMAP_MIN_CAP_BITS; + + new_cap = 1UL << new_cap_bits; + new_buckets = calloc(new_cap, sizeof(new_buckets[0])); + if (!new_buckets) + return -ENOMEM; + + hashmap__for_each_entry_safe(map, cur, tmp, bkt) { + h = hash_bits(map->hash_fn(cur->key, map->ctx), new_cap_bits); + hashmap_add_entry(&new_buckets[h], cur); + } + + map->cap = new_cap; + map->cap_bits = new_cap_bits; + free(map->buckets); + map->buckets = new_buckets; + + return 0; +} + +static bool hashmap_find_entry(const struct hashmap *map, + const void *key, size_t hash, + struct hashmap_entry ***pprev, + struct hashmap_entry **entry) +{ + struct hashmap_entry *cur, **prev_ptr; + + if (!map->buckets) + return false; + + for (prev_ptr = &map->buckets[hash], cur = *prev_ptr; + cur; + prev_ptr = &cur->next, cur = cur->next) { + if (map->equal_fn(cur->key, key, map->ctx)) { + if (pprev) + *pprev = prev_ptr; + *entry = cur; + return true; + } + } + + return false; +} + +int hashmap__insert(struct hashmap *map, const void *key, void *value, + enum hashmap_insert_strategy strategy, + const void **old_key, void **old_value) +{ + struct hashmap_entry *entry; + size_t h; + int err; + + if (old_key) + *old_key = NULL; + if (old_value) + *old_value = NULL; + + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + if (strategy != HASHMAP_APPEND && + hashmap_find_entry(map, key, h, NULL, &entry)) { + if (old_key) + *old_key = entry->key; + if (old_value) + *old_value = entry->value; + + if (strategy == HASHMAP_SET || strategy == HASHMAP_UPDATE) { + entry->key = key; + entry->value = value; + return 0; + } else if (strategy == HASHMAP_ADD) { + return -EEXIST; + } + } + + if (strategy == HASHMAP_UPDATE) + return -ENOENT; + + if (hashmap_needs_to_grow(map)) { + err = hashmap_grow(map); + if (err) + return err; + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + } + + entry = malloc(sizeof(struct hashmap_entry)); + if (!entry) + return -ENOMEM; + + entry->key = key; + entry->value = value; + hashmap_add_entry(&map->buckets[h], entry); + map->sz++; + + return 0; +} + +bool hashmap__find(const struct hashmap *map, const void *key, void **value) +{ + struct hashmap_entry *entry; + size_t h; + + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + if (!hashmap_find_entry(map, key, h, NULL, &entry)) + return false; + + if (value) + *value = entry->value; + return true; +} + +bool hashmap__delete(struct hashmap *map, const void *key, + const void **old_key, void **old_value) +{ + struct hashmap_entry **pprev, *entry; + size_t h; + + h = hash_bits(map->hash_fn(key, map->ctx), map->cap_bits); + if (!hashmap_find_entry(map, key, h, &pprev, &entry)) + return false; + + if (old_key) + *old_key = entry->key; + if (old_value) + *old_value = entry->value; + + hashmap_del_entry(pprev, entry); + free(entry); + map->sz--; + + return true; +} + diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h new file mode 100644 index 000000000000..bae8879cdf58 --- /dev/null +++ b/tools/lib/bpf/hashmap.h @@ -0,0 +1,178 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Generic non-thread safe hash map implementation. + * + * Copyright (c) 2019 Facebook + */ +#ifndef __LIBBPF_HASHMAP_H +#define __LIBBPF_HASHMAP_H + +#include <stdbool.h> +#include <stddef.h> +#ifdef __GLIBC__ +#include <bits/wordsize.h> +#else +#include <bits/reg.h> +#endif +#include "libbpf_internal.h" + +static inline size_t hash_bits(size_t h, int bits) +{ + /* shuffle bits and return requested number of upper bits */ + return (h * 11400714819323198485llu) >> (__WORDSIZE - bits); +} + +typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx); +typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx); + +struct hashmap_entry { + const void *key; + void *value; + struct hashmap_entry *next; +}; + +struct hashmap { + hashmap_hash_fn hash_fn; + hashmap_equal_fn equal_fn; + void *ctx; + + struct hashmap_entry **buckets; + size_t cap; + size_t cap_bits; + 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, + hashmap_equal_fn equal_fn, + void *ctx); +void hashmap__clear(struct hashmap *map); +void hashmap__free(struct hashmap *map); + +size_t hashmap__size(const struct hashmap *map); +size_t hashmap__capacity(const struct hashmap *map); + +/* + * Hashmap insertion strategy: + * - HASHMAP_ADD - only add key/value if key doesn't exist yet; + * - HASHMAP_SET - add key/value pair if key doesn't exist yet; otherwise, + * update value; + * - HASHMAP_UPDATE - update value, if key already exists; otherwise, do + * nothing and return -ENOENT; + * - HASHMAP_APPEND - always add key/value pair, even if key already exists. + * This turns hashmap into a multimap by allowing multiple values to be + * associated with the same key. Most useful read API for such hashmap is + * hashmap__for_each_key_entry() iteration. If hashmap__find() is still + * used, it will return last inserted key/value entry (first in a bucket + * chain). + */ +enum hashmap_insert_strategy { + HASHMAP_ADD, + HASHMAP_SET, + HASHMAP_UPDATE, + HASHMAP_APPEND, +}; + +/* + * hashmap__insert() adds key/value entry w/ various semantics, depending on + * provided strategy value. If a given key/value pair replaced already + * existing key/value pair, both old key and old value will be returned + * through old_key and old_value to allow calling code do proper memory + * management. + */ +int hashmap__insert(struct hashmap *map, const void *key, void *value, + enum hashmap_insert_strategy strategy, + const void **old_key, void **old_value); + +static inline int hashmap__add(struct hashmap *map, + const void *key, void *value) +{ + return hashmap__insert(map, key, value, HASHMAP_ADD, NULL, NULL); +} + +static inline int hashmap__set(struct hashmap *map, + const void *key, void *value, + const void **old_key, void **old_value) +{ + return hashmap__insert(map, key, value, HASHMAP_SET, + old_key, old_value); +} + +static inline int hashmap__update(struct hashmap *map, + const void *key, void *value, + const void **old_key, void **old_value) +{ + return hashmap__insert(map, key, value, HASHMAP_UPDATE, + old_key, old_value); +} + +static inline int hashmap__append(struct hashmap *map, + const void *key, void *value) +{ + return hashmap__insert(map, key, value, HASHMAP_APPEND, NULL, NULL); +} + +bool hashmap__delete(struct hashmap *map, const void *key, + const void **old_key, void **old_value); + +bool hashmap__find(const struct hashmap *map, const void *key, void **value); + +/* + * hashmap__for_each_entry - iterate over all entries in hashmap + * @map: hashmap to iterate + * @cur: struct hashmap_entry * used as a loop cursor + * @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) + +/* + * hashmap__for_each_entry_safe - iterate over all entries in hashmap, safe + * against removals + * @map: hashmap to iterate + * @cur: struct hashmap_entry * used as a loop cursor + * @tmp: struct hashmap_entry * used as a temporary next cursor storage + * @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]; \ + cur && ({tmp = cur->next; true; }); \ + cur = tmp) + +/* + * hashmap__for_each_key_entry - iterate over entries associated with given key + * @map: hashmap to iterate + * @cur: struct hashmap_entry * used as a loop cursor + * @key: key to iterate entries for + */ +#define hashmap__for_each_key_entry(map, cur, _key) \ + for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ + map->cap_bits); \ + map->buckets ? map->buckets[bkt] : NULL; }); \ + cur; \ + cur = cur->next) \ + if (map->equal_fn(cur->key, (_key), map->ctx)) + +#define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ + for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ + map->cap_bits); \ + cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + cur && ({ tmp = cur->next; true; }); \ + cur = tmp) \ + 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 11c25d9ea431..b20f82e58989 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7,6 +7,7 @@ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> * Copyright (C) 2015 Huawei Inc. * Copyright (C) 2017 Nicira, Inc. + * Copyright (C) 2019 Isovalent, Inc. */ #ifndef _GNU_SOURCE @@ -19,6 +20,7 @@ #include <inttypes.h> #include <string.h> #include <unistd.h> +#include <endian.h> #include <fcntl.h> #include <errno.h> #include <asm/unistd.h> @@ -31,9 +33,14 @@ #include <linux/limits.h> #include <linux/perf_event.h> #include <linux/ring_buffer.h> +#include <linux/version.h> +#include <sys/epoll.h> +#include <sys/ioctl.h> +#include <sys/mman.h> #include <sys/stat.h> #include <sys/types.h> #include <sys/vfs.h> +#include <sys/utsname.h> #include <tools/libc_compat.h> #include <libelf.h> #include <gelf.h> @@ -42,7 +49,8 @@ #include "bpf.h" #include "btf.h" #include "str_error.h" -#include "libbpf_util.h" +#include "libbpf_internal.h" +#include "hashmap.h" #ifndef EM_BPF #define EM_BPF 247 @@ -52,6 +60,11 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif +/* vsprintf() in __base_pr() uses nonliteral format string. It may break + * compilation if user enables corresponding warning. Disable it explicitly. + */ +#pragma GCC diagnostic ignored "-Wformat-nonliteral" + #define __printf(a, b) __attribute__((format(printf, a, b))) static int __base_pr(enum libbpf_print_level level, const char *format, @@ -65,9 +78,12 @@ static int __base_pr(enum libbpf_print_level level, const char *format, static libbpf_print_fn_t __libbpf_pr = __base_pr; -void libbpf_set_print(libbpf_print_fn_t fn) +libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn) { + libbpf_print_fn_t old_print_fn = __libbpf_pr; + __libbpf_pr = fn; + return old_print_fn; } __printf(2, 3) @@ -89,7 +105,7 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...) err = action; \ if (err) \ goto out; \ -} while(0) +} while (0) /* Copied from tools/perf/util/util.h */ @@ -120,6 +136,14 @@ static inline __u64 ptr_to_u64(const void *ptr) struct bpf_capabilities { /* v4.14: kernel support for program & map names. */ __u32 name:1; + /* v5.2: kernel support for global data sections. */ + __u32 global_data:1; + /* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */ + __u32 btf_func:1; + /* BTF_KIND_VAR and BTF_KIND_DATASEC support */ + __u32 btf_datasec:1; + /* BPF_F_MMAPABLE is supported for arrays */ + __u32 array_mmap:1; }; /* @@ -144,6 +168,7 @@ struct bpf_program { enum { RELO_LD64, RELO_CALL, + RELO_DATA, } type; int insn_idx; union { @@ -152,6 +177,7 @@ struct bpf_program { }; } *reloc_desc; int nr_reloc; + int log_level; struct { int nr; @@ -164,7 +190,8 @@ struct bpf_program { bpf_program_clear_priv_t clear_priv; enum bpf_attach_type expected_attach_type; - int btf_fd; + __u32 attach_btf_id; + __u32 attach_prog_fd; void *func_info; __u32 func_info_rec_size; __u32 func_info_cnt; @@ -174,12 +201,27 @@ struct bpf_program { void *line_info; __u32 line_info_rec_size; __u32 line_info_cnt; + __u32 prog_flags; +}; + +enum libbpf_map_type { + LIBBPF_MAP_UNSPEC, + LIBBPF_MAP_DATA, + LIBBPF_MAP_BSS, + LIBBPF_MAP_RODATA, +}; + +static const char * const libbpf_type_to_btf_name[] = { + [LIBBPF_MAP_DATA] = ".data", + [LIBBPF_MAP_BSS] = ".bss", + [LIBBPF_MAP_RODATA] = ".rodata", }; struct bpf_map { int fd; char *name; - size_t offset; + int sec_idx; + size_t sec_offset; int map_ifindex; int inner_map_fd; struct bpf_map_def def; @@ -187,11 +229,21 @@ struct bpf_map { __u32 btf_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; + enum libbpf_map_type libbpf_type; + char *pin_path; + bool pinned; + bool reused; +}; + +struct bpf_secdata { + void *rodata; + void *data; }; static LIST_HEAD(bpf_objects_list); struct bpf_object { + char name[BPF_OBJ_NAME_LEN]; char license[64]; __u32 kern_version; @@ -199,9 +251,12 @@ struct bpf_object { size_t nr_programs; struct bpf_map *maps; size_t nr_maps; + size_t maps_cap; + struct bpf_secdata sections; bool loaded; bool has_pseudo_calls; + bool relaxed_core_relocs; /* * Information when doing elf related work. Only valid if fd @@ -209,19 +264,26 @@ struct bpf_object { */ struct { int fd; - void *obj_buf; + const void *obj_buf; size_t obj_buf_sz; Elf *elf; GElf_Ehdr ehdr; Elf_Data *symbols; + Elf_Data *data; + Elf_Data *rodata; + Elf_Data *bss; size_t strtabidx; struct { GElf_Shdr shdr; Elf_Data *data; - } *reloc; - int nr_reloc; + } *reloc_sects; + int nr_reloc_sects; int maps_shndx; + int btf_maps_shndx; int text_shndx; + int data_shndx; + int rodata_shndx; + int bss_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -257,14 +319,13 @@ void bpf_program__unload(struct bpf_program *prog) for (i = 0; i < prog->instances.nr; i++) zclose(prog->instances.fds[i]); } else if (prog->instances.nr != -1) { - pr_warning("Internal error: instances.nr is %d\n", - prog->instances.nr); + pr_warn("Internal error: instances.nr is %d\n", + prog->instances.nr); } prog->instances.nr = -1; zfree(&prog->instances.fds); - zclose(prog->btf_fd); zfree(&prog->func_info); zfree(&prog->line_info); } @@ -307,8 +368,11 @@ static int bpf_program__init(void *data, size_t size, char *section_name, int idx, struct bpf_program *prog) { - if (size < sizeof(struct bpf_insn)) { - pr_warning("corrupted section '%s'\n", section_name); + const size_t bpf_insn_sz = sizeof(struct bpf_insn); + + if (size == 0 || size % bpf_insn_sz) { + pr_warn("corrupted section '%s', size: %zu\n", + section_name, size); return -EINVAL; } @@ -316,32 +380,30 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, prog->section_name = strdup(section_name); if (!prog->section_name) { - pr_warning("failed to alloc name for prog under section(%d) %s\n", - idx, section_name); + pr_warn("failed to alloc name for prog under section(%d) %s\n", + idx, section_name); goto errout; } prog->pin_name = __bpf_program__pin_name(prog); if (!prog->pin_name) { - pr_warning("failed to alloc pin name for prog under section(%d) %s\n", - idx, section_name); + pr_warn("failed to alloc pin name for prog under section(%d) %s\n", + idx, section_name); goto errout; } prog->insns = malloc(size); if (!prog->insns) { - pr_warning("failed to alloc insns for prog under section %s\n", - section_name); + pr_warn("failed to alloc insns for prog under section %s\n", + section_name); goto errout; } - prog->insns_cnt = size / sizeof(struct bpf_insn); - memcpy(prog->insns, data, - prog->insns_cnt * sizeof(struct bpf_insn)); + prog->insns_cnt = size / bpf_insn_sz; + memcpy(prog->insns, data, size); prog->idx = idx; prog->instances.fds = NULL; prog->instances.nr = -1; prog->type = BPF_PROG_TYPE_UNSPEC; - prog->btf_fd = -1; return 0; errout: @@ -371,8 +433,8 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size, * is still valid, so don't need special treat for * bpf_close_object(). */ - pr_warning("failed to alloc a new program under section '%s'\n", - section_name); + pr_warn("failed to alloc a new program under section '%s'\n", + section_name); bpf_program__exit(&prog); return -ENOMEM; } @@ -412,8 +474,8 @@ bpf_object__init_prog_names(struct bpf_object *obj) obj->efile.strtabidx, sym.st_name); if (!name) { - pr_warning("failed to get sym name string for prog %s\n", - prog->section_name); + pr_warn("failed to get sym name string for prog %s\n", + prog->section_name); return -LIBBPF_ERRNO__LIBELF; } } @@ -422,15 +484,15 @@ bpf_object__init_prog_names(struct bpf_object *obj) name = ".text"; if (!name) { - pr_warning("failed to find sym for prog %s\n", - prog->section_name); + pr_warn("failed to find sym for prog %s\n", + prog->section_name); return -EINVAL; } prog->name = strdup(name); if (!prog->name) { - pr_warning("failed to allocate memory for prog sym %s\n", - name); + pr_warn("failed to allocate memory for prog sym %s\n", + name); return -ENOMEM; } } @@ -438,23 +500,47 @@ bpf_object__init_prog_names(struct bpf_object *obj) return 0; } +static __u32 get_kernel_version(void) +{ + __u32 major, minor, patch; + struct utsname info; + + uname(&info); + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + return KERNEL_VERSION(major, minor, patch); +} + static struct bpf_object *bpf_object__new(const char *path, - void *obj_buf, - size_t obj_buf_sz) + const void *obj_buf, + size_t obj_buf_sz, + const char *obj_name) { struct bpf_object *obj; + char *end; obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1); if (!obj) { - pr_warning("alloc memory failed for %s\n", path); + pr_warn("alloc memory failed for %s\n", path); return ERR_PTR(-ENOMEM); } strcpy(obj->path, path); - obj->efile.fd = -1; + if (obj_name) { + strncpy(obj->name, obj_name, sizeof(obj->name) - 1); + obj->name[sizeof(obj->name) - 1] = 0; + } else { + /* Using basename() GNU version which doesn't modify arg. */ + strncpy(obj->name, basename((void *)path), + sizeof(obj->name) - 1); + end = strchr(obj->name, '.'); + if (end) + *end = 0; + } + obj->efile.fd = -1; /* - * Caller of this function should also calls + * Caller of this function should also call * bpf_object__elf_finish() after data collection to return * obj_buf to user. If not, we should duplicate the buffer to * avoid user freeing them before elf finish. @@ -462,7 +548,12 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf = obj_buf; obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.maps_shndx = -1; + obj->efile.btf_maps_shndx = -1; + obj->efile.data_shndx = -1; + obj->efile.rodata_shndx = -1; + obj->efile.bss_shndx = -1; + obj->kern_version = get_kernel_version(); obj->loaded = false; INIT_LIST_HEAD(&obj->list); @@ -480,9 +571,12 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.elf = NULL; } obj->efile.symbols = NULL; + obj->efile.data = NULL; + obj->efile.rodata = NULL; + obj->efile.bss = NULL; - zfree(&obj->efile.reloc); - obj->efile.nr_reloc = 0; + zfree(&obj->efile.reloc_sects); + obj->efile.nr_reloc_sects = 0; zclose(obj->efile.fd); obj->efile.obj_buf = NULL; obj->efile.obj_buf_sz = 0; @@ -494,7 +588,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) GElf_Ehdr *ep; if (obj_elf_valid(obj)) { - pr_warning("elf init: internal error\n"); + pr_warn("elf init: internal error\n"); return -LIBBPF_ERRNO__LIBELF; } @@ -503,43 +597,40 @@ static int bpf_object__elf_init(struct bpf_object *obj) * obj_buf should have been validated by * bpf_object__open_buffer(). */ - obj->efile.elf = elf_memory(obj->efile.obj_buf, + obj->efile.elf = elf_memory((char *)obj->efile.obj_buf, obj->efile.obj_buf_sz); } else { obj->efile.fd = open(obj->path, O_RDONLY); if (obj->efile.fd < 0) { - char errmsg[STRERR_BUFSIZE]; - char *cp = libbpf_strerror_r(errno, errmsg, - sizeof(errmsg)); + char errmsg[STRERR_BUFSIZE], *cp; - pr_warning("failed to open %s: %s\n", obj->path, cp); - return -errno; + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("failed to open %s: %s\n", obj->path, cp); + return err; } obj->efile.elf = elf_begin(obj->efile.fd, - LIBBPF_ELF_C_READ_MMAP, - NULL); + LIBBPF_ELF_C_READ_MMAP, NULL); } if (!obj->efile.elf) { - pr_warning("failed to open %s as ELF file\n", - obj->path); + pr_warn("failed to open %s as ELF file\n", obj->path); err = -LIBBPF_ERRNO__LIBELF; goto errout; } if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) { - pr_warning("failed to get EHDR from %s\n", - obj->path); + pr_warn("failed to get EHDR from %s\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; goto errout; } ep = &obj->efile.ehdr; /* Old LLVM set e_machine to EM_NONE */ - if ((ep->e_type != ET_REL) || (ep->e_machine && (ep->e_machine != EM_BPF))) { - pr_warning("%s is not an eBPF object file\n", - obj->path); + if (ep->e_type != ET_REL || + (ep->e_machine && ep->e_machine != EM_BPF)) { + pr_warn("%s is not an eBPF object file\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; goto errout; } @@ -550,58 +641,41 @@ errout: return err; } -static int -bpf_object__check_endianness(struct bpf_object *obj) +static int bpf_object__check_endianness(struct bpf_object *obj) { - static unsigned int const endian = 1; - - switch (obj->efile.ehdr.e_ident[EI_DATA]) { - case ELFDATA2LSB: - /* We are big endian, BPF obj is little endian. */ - if (*(unsigned char const *)&endian != 1) - goto mismatch; - break; - - case ELFDATA2MSB: - /* We are little endian, BPF obj is big endian. */ - if (*(unsigned char const *)&endian != 0) - goto mismatch; - break; - default: - return -LIBBPF_ERRNO__ENDIAN; - } - - return 0; - -mismatch: - pr_warning("Error: endianness mismatch.\n"); +#if __BYTE_ORDER == __LITTLE_ENDIAN + if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB) + return 0; +#elif __BYTE_ORDER == __BIG_ENDIAN + if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB) + return 0; +#else +# error "Unrecognized __BYTE_ORDER__" +#endif + pr_warn("endianness mismatch.\n"); return -LIBBPF_ERRNO__ENDIAN; } static int -bpf_object__init_license(struct bpf_object *obj, - void *data, size_t size) +bpf_object__init_license(struct bpf_object *obj, void *data, size_t size) { - memcpy(obj->license, data, - min(size, sizeof(obj->license) - 1)); + memcpy(obj->license, data, min(size, sizeof(obj->license) - 1)); pr_debug("license of %s is %s\n", obj->path, obj->license); return 0; } static int -bpf_object__init_kversion(struct bpf_object *obj, - void *data, size_t size) +bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size) { __u32 kver; if (size != sizeof(kver)) { - pr_warning("invalid kver section in %s\n", obj->path); + pr_warn("invalid kver section in %s\n", obj->path); return -LIBBPF_ERRNO__FORMAT; } memcpy(&kver, data, sizeof(kver)); obj->kern_version = kver; - pr_debug("kernel version of %s is %x\n", obj->path, - obj->kern_version); + pr_debug("kernel version of %s is %x\n", obj->path, obj->kern_version); return 0; } @@ -610,7 +684,9 @@ static int compare_bpf_map(const void *_a, const void *_b) const struct bpf_map *a = _a; const struct bpf_map *b = _b; - return a->offset - b->offset; + if (a->sec_idx != b->sec_idx) + return a->sec_idx - b->sec_idx; + return a->sec_offset - b->sec_offset; } static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) @@ -621,17 +697,240 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type) return false; } +static int bpf_object_search_section_size(const struct bpf_object *obj, + const char *name, size_t *d_size) +{ + const GElf_Ehdr *ep = &obj->efile.ehdr; + Elf *elf = obj->efile.elf; + Elf_Scn *scn = NULL; + int idx = 0; + + while ((scn = elf_nextscn(elf, scn)) != NULL) { + const char *sec_name; + Elf_Data *data; + GElf_Shdr sh; + + idx++; + if (gelf_getshdr(scn, &sh) != &sh) { + pr_warn("failed to get section(%d) header from %s\n", + idx, obj->path); + return -EIO; + } + + sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); + if (!sec_name) { + pr_warn("failed to get section(%d) name from %s\n", + idx, obj->path); + return -EIO; + } + + if (strcmp(name, sec_name)) + continue; + + data = elf_getdata(scn, 0); + if (!data) { + pr_warn("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); + return -EIO; + } + + *d_size = data->d_size; + return 0; + } + + return -ENOENT; +} + +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size) +{ + int ret = -ENOENT; + size_t d_size; + + *size = 0; + if (!name) { + return -EINVAL; + } else if (!strcmp(name, ".data")) { + if (obj->efile.data) + *size = obj->efile.data->d_size; + } else if (!strcmp(name, ".bss")) { + if (obj->efile.bss) + *size = obj->efile.bss->d_size; + } else if (!strcmp(name, ".rodata")) { + if (obj->efile.rodata) + *size = obj->efile.rodata->d_size; + } else { + ret = bpf_object_search_section_size(obj, name, &d_size); + if (!ret) + *size = d_size; + } + + return *size ? 0 : ret; +} + +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off) +{ + Elf_Data *symbols = obj->efile.symbols; + const char *sname; + size_t si; + + if (!name || !off) + return -EINVAL; + + for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) { + GElf_Sym sym; + + if (!gelf_getsym(symbols, si, &sym)) + continue; + if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL || + GELF_ST_TYPE(sym.st_info) != STT_OBJECT) + continue; + + sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + if (!sname) { + pr_warn("failed to get sym name string for var %s\n", + name); + return -EIO; + } + if (strcmp(name, sname) == 0) { + *off = sym.st_value; + return 0; + } + } + + return -ENOENT; +} + +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) +{ + struct bpf_map *new_maps; + size_t new_cap; + int i; + + if (obj->nr_maps < obj->maps_cap) + return &obj->maps[obj->nr_maps++]; + + new_cap = max((size_t)4, obj->maps_cap * 3 / 2); + new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps)); + if (!new_maps) { + pr_warn("alloc maps for object failed\n"); + return ERR_PTR(-ENOMEM); + } + + obj->maps_cap = new_cap; + obj->maps = new_maps; + + /* zero out new maps */ + memset(obj->maps + obj->nr_maps, 0, + (obj->maps_cap - obj->nr_maps) * sizeof(*obj->maps)); + /* + * fill all fd with -1 so won't close incorrect fd (fd=0 is stdin) + * when failure (zclose won't close negative fd)). + */ + for (i = obj->nr_maps; i < obj->maps_cap; i++) { + obj->maps[i].fd = -1; + obj->maps[i].inner_map_fd = -1; + } + + return &obj->maps[obj->nr_maps++]; +} + static int -bpf_object__init_maps(struct bpf_object *obj, int flags) +bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, + int sec_idx, Elf_Data *data, void **data_buff) +{ + char map_name[BPF_OBJ_NAME_LEN]; + struct bpf_map_def *def; + struct bpf_map *map; + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map->libbpf_type = type; + map->sec_idx = sec_idx; + map->sec_offset = 0; + snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name, + libbpf_type_to_btf_name[type]); + map->name = strdup(map_name); + if (!map->name) { + pr_warn("failed to alloc map name\n"); + return -ENOMEM; + } + + def = &map->def; + def->type = BPF_MAP_TYPE_ARRAY; + def->key_size = sizeof(int); + def->value_size = data->d_size; + def->max_entries = 1; + def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0; + if (obj->caps.array_mmap) + def->map_flags |= BPF_F_MMAPABLE; + + 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); + + if (data_buff) { + *data_buff = malloc(data->d_size); + if (!*data_buff) { + zfree(&map->name); + pr_warn("failed to alloc map content buffer\n"); + return -ENOMEM; + } + memcpy(*data_buff, data->d_buf, data->d_size); + } + + pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name); + return 0; +} + +static int bpf_object__init_global_data_maps(struct bpf_object *obj) +{ + int err; + + if (!obj->caps.global_data) + return 0; + /* + * Populate obj->maps with libbpf internal maps. + */ + if (obj->efile.data_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA, + obj->efile.data_shndx, + obj->efile.data, + &obj->sections.data); + if (err) + return err; + } + if (obj->efile.rodata_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA, + obj->efile.rodata_shndx, + obj->efile.rodata, + &obj->sections.rodata); + if (err) + return err; + } + if (obj->efile.bss_shndx >= 0) { + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS, + obj->efile.bss_shndx, + obj->efile.bss, NULL); + if (err) + return err; + } + return 0; +} + +static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) { - bool strict = !(flags & MAPS_RELAX_COMPAT); - int i, map_idx, map_def_sz, nr_maps = 0; - Elf_Scn *scn; - Elf_Data *data = NULL; Elf_Data *symbols = obj->efile.symbols; + int i, map_def_sz = 0, nr_maps = 0, nr_syms; + Elf_Data *data = NULL; + Elf_Scn *scn; if (obj->efile.maps_shndx < 0) - return -EINVAL; + return 0; + if (!symbols) return -EINVAL; @@ -639,8 +938,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) if (scn) data = elf_getdata(scn, NULL); if (!scn || !data) { - pr_warning("failed to get Elf_Data from map section %d\n", - obj->efile.maps_shndx); + pr_warn("failed to get Elf_Data from map section %d\n", + obj->efile.maps_shndx); return -EINVAL; } @@ -651,7 +950,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * * TODO: Detect array of map and report error. */ - for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + nr_syms = symbols->d_size / sizeof(GElf_Sym); + for (i = 0; i < nr_syms; i++) { GElf_Sym sym; if (!gelf_getsym(symbols, i, &sym)) @@ -660,70 +960,58 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) continue; nr_maps++; } - - /* Alloc obj->maps and fill nr_maps. */ - pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, - nr_maps, data->d_size); - - if (!nr_maps) - return 0; - /* Assume equally sized map definitions */ - map_def_sz = data->d_size / nr_maps; - if (!data->d_size || (data->d_size % nr_maps) != 0) { - pr_warning("unable to determine map definition size " - "section %s, %d maps in %zd bytes\n", - obj->path, nr_maps, data->d_size); - return -EINVAL; - } - - obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); - if (!obj->maps) { - pr_warning("alloc maps for object failed\n"); - return -ENOMEM; - } - obj->nr_maps = nr_maps; + pr_debug("maps in %s: %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); - for (i = 0; i < nr_maps; i++) { - /* - * fill all fd with -1 so won't close incorrect - * fd (fd=0 is stdin) when failure (zclose won't close - * negative fd)). - */ - obj->maps[i].fd = -1; - obj->maps[i].inner_map_fd = -1; + if (!data->d_size || nr_maps == 0 || (data->d_size % nr_maps) != 0) { + pr_warn("unable to determine map definition size section %s, %d maps in %zd bytes\n", + obj->path, nr_maps, data->d_size); + return -EINVAL; } + map_def_sz = data->d_size / nr_maps; - /* - * Fill obj->maps using data in "maps" section. - */ - for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + /* Fill obj->maps using data in "maps" section. */ + for (i = 0; i < nr_syms; i++) { GElf_Sym sym; const char *map_name; struct bpf_map_def *def; + struct bpf_map *map; if (!gelf_getsym(symbols, i, &sym)) continue; if (sym.st_shndx != obj->efile.maps_shndx) continue; - map_name = elf_strptr(obj->efile.elf, - obj->efile.strtabidx, + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name); - obj->maps[map_idx].offset = sym.st_value; + if (!map_name) { + pr_warn("failed to get map #%d name sym string for obj %s\n", + i, obj->path); + return -LIBBPF_ERRNO__FORMAT; + } + + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->sec_idx = sym.st_shndx; + map->sec_offset = sym.st_value; + pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); if (sym.st_value + map_def_sz > data->d_size) { - pr_warning("corrupted maps section in %s: last map \"%s\" too small\n", - obj->path, map_name); + pr_warn("corrupted maps section in %s: last map \"%s\" too small\n", + obj->path, map_name); return -EINVAL; } - obj->maps[map_idx].name = strdup(map_name); - if (!obj->maps[map_idx].name) { - pr_warning("failed to alloc map name\n"); + map->name = strdup(map_name); + if (!map->name) { + pr_warn("failed to alloc map name\n"); return -ENOMEM; } - pr_debug("map %d is \"%s\"\n", map_idx, - obj->maps[map_idx].name); + pr_debug("map %d is \"%s\"\n", i, map->name); def = (struct bpf_map_def *)(data->d_buf + sym.st_value); /* * If the definition of the map in the object file fits in @@ -732,7 +1020,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * calloc above. */ if (map_def_sz <= sizeof(struct bpf_map_def)) { - memcpy(&obj->maps[map_idx].def, def, map_def_sz); + memcpy(&map->def, def, map_def_sz); } else { /* * Here the map structure being read is bigger than what @@ -741,24 +1029,394 @@ bpf_object__init_maps(struct bpf_object *obj, int flags) * incompatible. */ char *b; + for (b = ((char *)def) + sizeof(struct bpf_map_def); b < ((char *)def) + map_def_sz; b++) { if (*b != 0) { - pr_warning("maps section in %s: \"%s\" " - "has unrecognized, non-zero " - "options\n", - obj->path, map_name); + pr_warn("maps section in %s: \"%s\" has unrecognized, non-zero options\n", + obj->path, map_name); if (strict) return -EINVAL; } } - memcpy(&obj->maps[map_idx].def, def, - sizeof(struct bpf_map_def)); + memcpy(&map->def, def, sizeof(struct bpf_map_def)); + } + } + return 0; +} + +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id) +{ + const struct btf_type *t = btf__type_by_id(btf, id); + + if (res_id) + *res_id = id; + + while (btf_is_mod(t) || btf_is_typedef(t)) { + if (res_id) + *res_id = t->type; + t = btf__type_by_id(btf, t->type); + } + + return t; +} + +/* + * Fetch integer attribute of BTF map definition. Such attributes are + * represented using a pointer to an array, in which dimensionality of array + * encodes specified integer value. E.g., int (*type)[BPF_MAP_TYPE_ARRAY]; + * encodes `type => BPF_MAP_TYPE_ARRAY` key/value pair completely using BTF + * type definition, while using only sizeof(void *) space in ELF data section. + */ +static bool get_map_field_int(const char *map_name, const struct btf *btf, + const struct btf_type *def, + const struct btf_member *m, __u32 *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); + const struct btf_array *arr_info; + const struct btf_type *arr_t; + + if (!btf_is_ptr(t)) { + pr_warn("map '%s': attr '%s': expected PTR, got %u.\n", + map_name, name, btf_kind(t)); + return false; + } + + arr_t = btf__type_by_id(btf, t->type); + if (!arr_t) { + pr_warn("map '%s': attr '%s': type [%u] not found.\n", + map_name, name, t->type); + return false; + } + if (!btf_is_array(arr_t)) { + pr_warn("map '%s': attr '%s': expected ARRAY, got %u.\n", + map_name, name, btf_kind(arr_t)); + return false; + } + arr_info = btf_array(arr_t); + *res = arr_info->nelems; + return true; +} + +static int build_map_pin_path(struct bpf_map *map, const char *path) +{ + char buf[PATH_MAX]; + int err, len; + + if (!path) + path = "/sys/fs/bpf"; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, bpf_map__name(map)); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + err = bpf_map__set_pin_path(map, buf); + if (err) + return err; + + return 0; +} + +static int bpf_object__init_user_btf_map(struct bpf_object *obj, + const struct btf_type *sec, + int var_idx, int sec_idx, + const Elf_Data *data, bool strict, + const char *pin_root_path) +{ + const struct btf_type *var, *def, *t; + const struct btf_var_secinfo *vi; + const struct btf_var *var_extra; + const struct btf_member *m; + const char *map_name; + struct bpf_map *map; + int vlen, i; + + vi = btf_var_secinfos(sec) + var_idx; + var = btf__type_by_id(obj->btf, vi->type); + var_extra = btf_var(var); + map_name = btf__name_by_offset(obj->btf, var->name_off); + vlen = btf_vlen(var); + + if (map_name == NULL || map_name[0] == '\0') { + pr_warn("map #%d: empty name.\n", var_idx); + return -EINVAL; + } + if ((__u64)vi->offset + vi->size > data->d_size) { + pr_warn("map '%s' BTF data is corrupted.\n", map_name); + return -EINVAL; + } + if (!btf_is_var(var)) { + pr_warn("map '%s': unexpected var kind %u.\n", + map_name, btf_kind(var)); + return -EINVAL; + } + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && + var_extra->linkage != BTF_VAR_STATIC) { + pr_warn("map '%s': unsupported var linkage %u.\n", + map_name, var_extra->linkage); + return -EOPNOTSUPP; + } + + def = skip_mods_and_typedefs(obj->btf, var->type, NULL); + if (!btf_is_struct(def)) { + pr_warn("map '%s': unexpected def kind %u.\n", + map_name, btf_kind(var)); + return -EINVAL; + } + if (def->size > vi->size) { + pr_warn("map '%s': invalid def size.\n", map_name); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + map->name = strdup(map_name); + if (!map->name) { + pr_warn("map '%s': failed to alloc map name.\n", map_name); + return -ENOMEM; + } + map->libbpf_type = LIBBPF_MAP_UNSPEC; + map->def.type = BPF_MAP_TYPE_UNSPEC; + map->sec_idx = sec_idx; + map->sec_offset = vi->offset; + pr_debug("map '%s': at sec_idx %d, offset %zu.\n", + map_name, map->sec_idx, map->sec_offset); + + vlen = btf_vlen(def); + m = btf_members(def); + for (i = 0; i < vlen; i++, m++) { + const char *name = btf__name_by_offset(obj->btf, m->name_off); + + if (!name) { + pr_warn("map '%s': invalid field #%d.\n", map_name, i); + return -EINVAL; + } + if (strcmp(name, "type") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + &map->def.type)) + return -EINVAL; + pr_debug("map '%s': found type = %u.\n", + map_name, map->def.type); + } else if (strcmp(name, "max_entries") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + &map->def.max_entries)) + return -EINVAL; + pr_debug("map '%s': found max_entries = %u.\n", + map_name, map->def.max_entries); + } else if (strcmp(name, "map_flags") == 0) { + if (!get_map_field_int(map_name, obj->btf, def, m, + &map->def.map_flags)) + return -EINVAL; + pr_debug("map '%s': found map_flags = %u.\n", + map_name, map->def.map_flags); + } else if (strcmp(name, "key_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, obj->btf, def, m, + &sz)) + return -EINVAL; + pr_debug("map '%s': found key_size = %u.\n", + map_name, sz); + if (map->def.key_size && map->def.key_size != sz) { + pr_warn("map '%s': conflicting key size %u != %u.\n", + map_name, map->def.key_size, sz); + return -EINVAL; + } + map->def.key_size = sz; + } else if (strcmp(name, "key") == 0) { + __s64 sz; + + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warn("map '%s': key type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (!btf_is_ptr(t)) { + pr_warn("map '%s': key spec is not PTR: %u.\n", + map_name, btf_kind(t)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warn("map '%s': can't determine key size for type [%u]: %lld.\n", + map_name, t->type, sz); + return sz; + } + pr_debug("map '%s': found key [%u], sz = %lld.\n", + map_name, t->type, sz); + if (map->def.key_size && map->def.key_size != sz) { + pr_warn("map '%s': conflicting key size %u != %lld.\n", + map_name, map->def.key_size, sz); + return -EINVAL; + } + map->def.key_size = sz; + map->btf_key_type_id = t->type; + } else if (strcmp(name, "value_size") == 0) { + __u32 sz; + + if (!get_map_field_int(map_name, obj->btf, def, m, + &sz)) + return -EINVAL; + pr_debug("map '%s': found value_size = %u.\n", + map_name, sz); + if (map->def.value_size && map->def.value_size != sz) { + pr_warn("map '%s': conflicting value size %u != %u.\n", + map_name, map->def.value_size, sz); + return -EINVAL; + } + map->def.value_size = sz; + } else if (strcmp(name, "value") == 0) { + __s64 sz; + + t = btf__type_by_id(obj->btf, m->type); + if (!t) { + pr_warn("map '%s': value type [%d] not found.\n", + map_name, m->type); + return -EINVAL; + } + if (!btf_is_ptr(t)) { + pr_warn("map '%s': value spec is not PTR: %u.\n", + map_name, btf_kind(t)); + return -EINVAL; + } + sz = btf__resolve_size(obj->btf, t->type); + if (sz < 0) { + pr_warn("map '%s': can't determine value size for type [%u]: %lld.\n", + map_name, t->type, sz); + return sz; + } + pr_debug("map '%s': found value [%u], sz = %lld.\n", + map_name, t->type, sz); + if (map->def.value_size && map->def.value_size != sz) { + pr_warn("map '%s': conflicting value size %u != %lld.\n", + map_name, map->def.value_size, sz); + return -EINVAL; + } + map->def.value_size = sz; + map->btf_value_type_id = t->type; + } else if (strcmp(name, "pinning") == 0) { + __u32 val; + int err; + + if (!get_map_field_int(map_name, obj->btf, def, m, + &val)) + return -EINVAL; + pr_debug("map '%s': found pinning = %u.\n", + map_name, val); + + if (val != LIBBPF_PIN_NONE && + val != LIBBPF_PIN_BY_NAME) { + pr_warn("map '%s': invalid pinning value %u.\n", + map_name, val); + return -EINVAL; + } + if (val == LIBBPF_PIN_BY_NAME) { + err = build_map_pin_path(map, pin_root_path); + if (err) { + pr_warn("map '%s': couldn't build pin path.\n", + map_name); + return err; + } + } + } else { + if (strict) { + pr_warn("map '%s': unknown field '%s'.\n", + map_name, name); + return -ENOTSUP; + } + pr_debug("map '%s': ignoring unknown field '%s'.\n", + map_name, name); + } + } + + if (map->def.type == BPF_MAP_TYPE_UNSPEC) { + pr_warn("map '%s': map type isn't specified.\n", map_name); + return -EINVAL; + } + + return 0; +} + +static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, + const char *pin_root_path) +{ + const struct btf_type *sec = NULL; + int nr_types, i, vlen, err; + const struct btf_type *t; + const char *name; + Elf_Data *data; + Elf_Scn *scn; + + if (obj->efile.btf_maps_shndx < 0) + return 0; + + scn = elf_getscn(obj->efile.elf, obj->efile.btf_maps_shndx); + if (scn) + data = elf_getdata(scn, NULL); + if (!scn || !data) { + pr_warn("failed to get Elf_Data from map section %d (%s)\n", + obj->efile.maps_shndx, MAPS_ELF_SEC); + return -EINVAL; + } + + nr_types = btf__get_nr_types(obj->btf); + for (i = 1; i <= nr_types; i++) { + t = btf__type_by_id(obj->btf, i); + if (!btf_is_datasec(t)) + continue; + name = btf__name_by_offset(obj->btf, t->name_off); + if (strcmp(name, MAPS_ELF_SEC) == 0) { + sec = t; + break; } - map_idx++; } - qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map); + if (!sec) { + pr_warn("DATASEC '%s' not found.\n", MAPS_ELF_SEC); + return -ENOENT; + } + + vlen = btf_vlen(sec); + for (i = 0; i < vlen; i++) { + err = bpf_object__init_user_btf_map(obj, sec, i, + obj->efile.btf_maps_shndx, + data, strict, + pin_root_path); + if (err) + return err; + } + + return 0; +} + +static int bpf_object__init_maps(struct bpf_object *obj, bool relaxed_maps, + const char *pin_root_path) +{ + bool strict = !relaxed_maps; + int err; + + err = bpf_object__init_user_maps(obj, strict); + if (err) + return err; + + err = bpf_object__init_user_btf_maps(obj, strict, pin_root_path); + if (err) + return err; + + err = bpf_object__init_global_data_maps(obj); + if (err) + return err; + + if (obj->nr_maps) { + qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), + compare_bpf_map); + } return 0; } @@ -780,18 +1438,175 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) return false; } -static int bpf_object__elf_collect(struct bpf_object *obj, int flags) +static void bpf_object__sanitize_btf(struct bpf_object *obj) +{ + bool has_datasec = obj->caps.btf_datasec; + bool has_func = obj->caps.btf_func; + struct btf *btf = obj->btf; + struct btf_type *t; + int i, j, vlen; + + if (!obj->btf || (has_func && has_datasec)) + return; + + for (i = 1; i <= btf__get_nr_types(btf); i++) { + t = (struct btf_type *)btf__type_by_id(btf, i); + + if (!has_datasec && btf_is_var(t)) { + /* replace VAR with INT */ + t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); + /* + * using size = 1 is the safest choice, 4 will be too + * big and cause kernel BTF validation failure if + * original variable took less than 4 bytes + */ + t->size = 1; + *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8); + } else if (!has_datasec && btf_is_datasec(t)) { + /* replace DATASEC with STRUCT */ + const struct btf_var_secinfo *v = btf_var_secinfos(t); + struct btf_member *m = btf_members(t); + struct btf_type *vt; + char *name; + + name = (char *)btf__name_by_offset(btf, t->name_off); + while (*name) { + if (*name == '.') + *name = '_'; + name++; + } + + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_STRUCT, 0, vlen); + for (j = 0; j < vlen; j++, v++, m++) { + /* order of field assignments is important */ + m->offset = v->offset * 8; + m->type = v->type; + /* preserve variable name as member name */ + vt = (void *)btf__type_by_id(btf, v->type); + m->name_off = vt->name_off; + } + } else if (!has_func && btf_is_func_proto(t)) { + /* replace FUNC_PROTO with ENUM */ + vlen = btf_vlen(t); + t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen); + t->size = sizeof(__u32); /* kernel enforced */ + } else if (!has_func && btf_is_func(t)) { + /* replace FUNC with TYPEDEF */ + t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); + } + } +} + +static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) +{ + if (!obj->btf_ext) + return; + + if (!obj->caps.btf_func) { + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + } +} + +static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) +{ + return obj->efile.btf_maps_shndx >= 0; +} + +static int bpf_object__init_btf(struct bpf_object *obj, + Elf_Data *btf_data, + Elf_Data *btf_ext_data) +{ + bool btf_required = bpf_object__is_btf_mandatory(obj); + int err = 0; + + if (btf_data) { + obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); + if (IS_ERR(obj->btf)) { + pr_warn("Error loading ELF section %s: %d.\n", + BTF_ELF_SEC, err); + goto out; + } + err = btf__finalize_data(obj, obj->btf); + if (err) { + pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); + goto out; + } + } + if (btf_ext_data) { + if (!obj->btf) { + pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", + BTF_EXT_ELF_SEC, BTF_ELF_SEC); + goto out; + } + obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, + btf_ext_data->d_size); + if (IS_ERR(obj->btf_ext)) { + pr_warn("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext)); + obj->btf_ext = NULL; + goto out; + } + } +out: + if (err || IS_ERR(obj->btf)) { + if (btf_required) + err = err ? : PTR_ERR(obj->btf); + else + err = 0; + if (!IS_ERR_OR_NULL(obj->btf)) + btf__free(obj->btf); + obj->btf = NULL; + } + if (btf_required && !obj->btf) { + pr_warn("BTF is required, but is missing or corrupted.\n"); + return err == 0 ? -ENOENT : err; + } + return 0; +} + +static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) +{ + int err = 0; + + if (!obj->btf) + return 0; + + bpf_object__sanitize_btf(obj); + bpf_object__sanitize_btf_ext(obj); + + err = btf__load(obj->btf); + if (err) { + pr_warn("Error loading %s into kernel: %d.\n", + BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + /* btf_ext can't exist without btf, so free it as well */ + if (obj->btf_ext) { + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + } + + if (bpf_object__is_btf_mandatory(obj)) + return err; + } + return 0; +} + +static int bpf_object__elf_collect(struct bpf_object *obj, bool relaxed_maps, + const char *pin_root_path) { Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; Elf_Data *btf_ext_data = NULL; + Elf_Data *btf_data = NULL; Elf_Scn *scn = NULL; int idx = 0, err = 0; /* Elf is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { - pr_warning("failed to get e_shstrndx from %s\n", - obj->path); + pr_warn("failed to get e_shstrndx from %s\n", obj->path); return -LIBBPF_ERRNO__FORMAT; } @@ -802,87 +1617,86 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) idx++; if (gelf_getshdr(scn, &sh) != &sh) { - pr_warning("failed to get section(%d) header from %s\n", - idx, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + pr_warn("failed to get section(%d) header from %s\n", + idx, obj->path); + return -LIBBPF_ERRNO__FORMAT; } name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name); if (!name) { - pr_warning("failed to get section(%d) name from %s\n", - idx, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + pr_warn("failed to get section(%d) name from %s\n", + idx, obj->path); + return -LIBBPF_ERRNO__FORMAT; } data = elf_getdata(scn, 0); if (!data) { - pr_warning("failed to get section(%d) data from %s(%s)\n", - idx, name, obj->path); - err = -LIBBPF_ERRNO__FORMAT; - goto out; + pr_warn("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); + return -LIBBPF_ERRNO__FORMAT; } pr_debug("section(%d) %s, size %ld, link %d, flags %lx, type=%d\n", idx, name, (unsigned long)data->d_size, (int)sh.sh_link, (unsigned long)sh.sh_flags, (int)sh.sh_type); - if (strcmp(name, "license") == 0) + if (strcmp(name, "license") == 0) { err = bpf_object__init_license(obj, data->d_buf, data->d_size); - else if (strcmp(name, "version") == 0) + if (err) + return err; + } else if (strcmp(name, "version") == 0) { err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); - else if (strcmp(name, "maps") == 0) + if (err) + return err; + } else if (strcmp(name, "maps") == 0) { obj->efile.maps_shndx = idx; - else if (strcmp(name, BTF_ELF_SEC) == 0) { - obj->btf = btf__new(data->d_buf, data->d_size); - if (IS_ERR(obj->btf)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_ELF_SEC, PTR_ERR(obj->btf)); - obj->btf = NULL; - continue; - } - err = btf__load(obj->btf); - if (err) { - pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n", - BTF_ELF_SEC, err); - btf__free(obj->btf); - obj->btf = NULL; - err = 0; - } + } else if (strcmp(name, MAPS_ELF_SEC) == 0) { + obj->efile.btf_maps_shndx = idx; + } else if (strcmp(name, BTF_ELF_SEC) == 0) { + btf_data = data; } else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) { btf_ext_data = data; } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { - pr_warning("bpf: multiple SYMTAB in %s\n", - obj->path); - err = -LIBBPF_ERRNO__FORMAT; - } else { - obj->efile.symbols = data; - obj->efile.strtabidx = sh.sh_link; + pr_warn("bpf: multiple SYMTAB in %s\n", + obj->path); + return -LIBBPF_ERRNO__FORMAT; } - } else if ((sh.sh_type == SHT_PROGBITS) && - (sh.sh_flags & SHF_EXECINSTR) && - (data->d_size > 0)) { - if (strcmp(name, ".text") == 0) - obj->efile.text_shndx = idx; - err = bpf_object__add_program(obj, data->d_buf, - data->d_size, name, idx); - if (err) { - char errmsg[STRERR_BUFSIZE]; - char *cp = libbpf_strerror_r(-err, errmsg, - sizeof(errmsg)); - - pr_warning("failed to alloc program %s (%s): %s", - name, obj->path, cp); + obj->efile.symbols = data; + obj->efile.strtabidx = sh.sh_link; + } else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) { + if (sh.sh_flags & SHF_EXECINSTR) { + if (strcmp(name, ".text") == 0) + obj->efile.text_shndx = idx; + err = bpf_object__add_program(obj, data->d_buf, + data->d_size, + name, idx); + if (err) { + char errmsg[STRERR_BUFSIZE]; + char *cp; + + cp = libbpf_strerror_r(-err, errmsg, + sizeof(errmsg)); + pr_warn("failed to alloc program %s (%s): %s", + name, obj->path, cp); + return err; + } + } else if (strcmp(name, ".data") == 0) { + obj->efile.data = data; + obj->efile.data_shndx = idx; + } else if (strcmp(name, ".rodata") == 0) { + obj->efile.rodata = data; + obj->efile.rodata_shndx = idx; + } else { + pr_debug("skip section(%d) %s\n", idx, name); } } else if (sh.sh_type == SHT_REL) { - void *reloc = obj->efile.reloc; - int nr_reloc = obj->efile.nr_reloc + 1; + int nr_sects = obj->efile.nr_reloc_sects; + void *sects = obj->efile.reloc_sects; int sec = sh.sh_info; /* points to other section */ /* Only do relo for section with exec instructions */ @@ -892,53 +1706,37 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) continue; } - reloc = reallocarray(reloc, nr_reloc, - sizeof(*obj->efile.reloc)); - if (!reloc) { - pr_warning("realloc failed\n"); - err = -ENOMEM; - } else { - int n = nr_reloc - 1; + sects = reallocarray(sects, nr_sects + 1, + sizeof(*obj->efile.reloc_sects)); + if (!sects) { + pr_warn("reloc_sects realloc failed\n"); + return -ENOMEM; + } - obj->efile.reloc = reloc; - obj->efile.nr_reloc = nr_reloc; + obj->efile.reloc_sects = sects; + obj->efile.nr_reloc_sects++; - obj->efile.reloc[n].shdr = sh; - obj->efile.reloc[n].data = data; - } + obj->efile.reloc_sects[nr_sects].shdr = sh; + obj->efile.reloc_sects[nr_sects].data = data; + } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { + obj->efile.bss = data; + obj->efile.bss_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } - if (err) - goto out; } - if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) { - pr_warning("Corrupted ELF file: index of strtab invalid\n"); - return LIBBPF_ERRNO__FORMAT; - } - if (btf_ext_data) { - if (!obj->btf) { - pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n", - BTF_EXT_ELF_SEC, BTF_ELF_SEC); - } else { - obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, - btf_ext_data->d_size); - if (IS_ERR(obj->btf_ext)) { - pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_EXT_ELF_SEC, - PTR_ERR(obj->btf_ext)); - obj->btf_ext = NULL; - } - } - } - if (obj->efile.maps_shndx >= 0) { - err = bpf_object__init_maps(obj, flags); - if (err) - goto out; + if (!obj->efile.strtabidx || obj->efile.strtabidx > idx) { + pr_warn("Corrupted ELF file: index of strtab invalid\n"); + return -LIBBPF_ERRNO__FORMAT; } - err = bpf_object__init_prog_names(obj); -out: + err = bpf_object__init_btf(obj, btf_data, btf_ext_data); + if (!err) + err = bpf_object__init_maps(obj, relaxed_maps, pin_root_path); + if (!err) + err = bpf_object__sanitize_and_load_btf(obj); + if (!err) + err = bpf_object__init_prog_names(obj); return err; } @@ -957,7 +1755,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx) } struct bpf_program * -bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) +bpf_object__find_program_by_title(const struct bpf_object *obj, + const char *title) { struct bpf_program *pos; @@ -968,115 +1767,222 @@ bpf_object__find_program_by_title(struct bpf_object *obj, const char *title) return NULL; } +static bool bpf_object__shndx_is_data(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.data_shndx || + shndx == obj->efile.bss_shndx || + shndx == obj->efile.rodata_shndx; +} + +static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, + int shndx) +{ + return shndx == obj->efile.maps_shndx || + shndx == obj->efile.btf_maps_shndx; +} + +static enum libbpf_map_type +bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) +{ + if (shndx == obj->efile.data_shndx) + return LIBBPF_MAP_DATA; + else if (shndx == obj->efile.bss_shndx) + return LIBBPF_MAP_BSS; + else if (shndx == obj->efile.rodata_shndx) + return LIBBPF_MAP_RODATA; + else + return LIBBPF_MAP_UNSPEC; +} + +static int bpf_program__record_reloc(struct bpf_program *prog, + struct reloc_desc *reloc_desc, + __u32 insn_idx, const char *name, + const GElf_Sym *sym, const GElf_Rel *rel) +{ + struct bpf_insn *insn = &prog->insns[insn_idx]; + size_t map_idx, nr_maps = prog->obj->nr_maps; + struct bpf_object *obj = prog->obj; + __u32 shdr_idx = sym->st_shndx; + enum libbpf_map_type type; + struct bpf_map *map; + + /* sub-program call relocation */ + if (insn->code == (BPF_JMP | BPF_CALL)) { + if (insn->src_reg != BPF_PSEUDO_CALL) { + pr_warn("incorrect bpf_call opcode\n"); + return -LIBBPF_ERRNO__RELOC; + } + /* text_shndx can be 0, if no default "main" program exists */ + if (!shdr_idx || shdr_idx != obj->efile.text_shndx) { + pr_warn("bad call relo against section %u\n", shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + if (sym->st_value % 8) { + pr_warn("bad call relo offset: %lu\n", sym->st_value); + return -LIBBPF_ERRNO__RELOC; + } + reloc_desc->type = RELO_CALL; + reloc_desc->insn_idx = insn_idx; + reloc_desc->text_off = sym->st_value / 8; + obj->has_pseudo_calls = true; + return 0; + } + + if (insn->code != (BPF_LD | BPF_IMM | BPF_DW)) { + pr_warn("invalid relo for insns[%d].code 0x%x\n", + insn_idx, insn->code); + return -LIBBPF_ERRNO__RELOC; + } + if (!shdr_idx || shdr_idx >= SHN_LORESERVE) { + pr_warn("invalid relo for \'%s\' in special section 0x%x; forgot to initialize global var?..\n", + name, shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + + type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); + + /* generic map reference relocation */ + if (type == LIBBPF_MAP_UNSPEC) { + if (!bpf_object__shndx_is_maps(obj, shdr_idx)) { + pr_warn("bad map relo against section %u\n", + shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + map = &obj->maps[map_idx]; + if (map->libbpf_type != type || + map->sec_idx != sym->st_shndx || + map->sec_offset != sym->st_value) + continue; + pr_debug("found map %zd (%s, sec %d, off %zu) for insn %u\n", + map_idx, map->name, map->sec_idx, + map->sec_offset, insn_idx); + break; + } + if (map_idx >= nr_maps) { + pr_warn("map relo failed to find map for sec %u, off %llu\n", + shdr_idx, (__u64)sym->st_value); + return -LIBBPF_ERRNO__RELOC; + } + reloc_desc->type = RELO_LD64; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = map_idx; + return 0; + } + + /* global data map relocation */ + if (!bpf_object__shndx_is_data(obj, shdr_idx)) { + pr_warn("bad data relo against section %u\n", shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + if (!obj->caps.global_data) { + pr_warn("relocation: kernel does not support global \'%s\' variable access in insns[%d]\n", + name, insn_idx); + return -LIBBPF_ERRNO__RELOC; + } + for (map_idx = 0; map_idx < nr_maps; map_idx++) { + map = &obj->maps[map_idx]; + if (map->libbpf_type != type) + continue; + pr_debug("found data map %zd (%s, sec %d, off %zu) for insn %u\n", + map_idx, map->name, map->sec_idx, map->sec_offset, + insn_idx); + break; + } + if (map_idx >= nr_maps) { + pr_warn("data relo failed to find map for sec %u\n", + shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + + reloc_desc->type = RELO_DATA; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = map_idx; + return 0; +} + static int bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, Elf_Data *data, struct bpf_object *obj) { Elf_Data *symbols = obj->efile.symbols; - int text_shndx = obj->efile.text_shndx; - int maps_shndx = obj->efile.maps_shndx; - struct bpf_map *maps = obj->maps; - size_t nr_maps = obj->nr_maps; - int i, nrels; - - pr_debug("collecting relocating info for: '%s'\n", - prog->section_name); + int err, i, nrels; + + pr_debug("collecting relocating info for: '%s'\n", prog->section_name); nrels = shdr->sh_size / shdr->sh_entsize; prog->reloc_desc = malloc(sizeof(*prog->reloc_desc) * nrels); if (!prog->reloc_desc) { - pr_warning("failed to alloc memory in relocation\n"); + pr_warn("failed to alloc memory in relocation\n"); return -ENOMEM; } prog->nr_reloc = nrels; for (i = 0; i < nrels; i++) { + const char *name; + __u32 insn_idx; GElf_Sym sym; GElf_Rel rel; - unsigned int insn_idx; - struct bpf_insn *insns = prog->insns; - size_t map_idx; if (!gelf_getrel(data, i, &rel)) { - pr_warning("relocation: failed to get %d reloc\n", i); + pr_warn("relocation: failed to get %d reloc\n", i); return -LIBBPF_ERRNO__FORMAT; } - - if (!gelf_getsym(symbols, - GELF_R_SYM(rel.r_info), - &sym)) { - pr_warning("relocation: symbol %"PRIx64" not found\n", - GELF_R_SYM(rel.r_info)); + if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { + pr_warn("relocation: symbol %"PRIx64" not found\n", + GELF_R_SYM(rel.r_info)); return -LIBBPF_ERRNO__FORMAT; } - pr_debug("relo for %lld value %lld name %d\n", - (long long) (rel.r_info >> 32), - (long long) sym.st_value, sym.st_name); - - if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) { - pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n", - prog->section_name, sym.st_shndx); - return -LIBBPF_ERRNO__RELOC; - } + if (rel.r_offset % sizeof(struct bpf_insn)) + return -LIBBPF_ERRNO__FORMAT; insn_idx = rel.r_offset / sizeof(struct bpf_insn); - pr_debug("relocation: insn_idx=%u\n", insn_idx); - - if (insns[insn_idx].code == (BPF_JMP | BPF_CALL)) { - if (insns[insn_idx].src_reg != BPF_PSEUDO_CALL) { - pr_warning("incorrect bpf_call opcode\n"); - return -LIBBPF_ERRNO__RELOC; - } - prog->reloc_desc[i].type = RELO_CALL; - prog->reloc_desc[i].insn_idx = insn_idx; - prog->reloc_desc[i].text_off = sym.st_value; - obj->has_pseudo_calls = true; - continue; - } - - if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) { - pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n", - insn_idx, insns[insn_idx].code); - return -LIBBPF_ERRNO__RELOC; - } - - /* TODO: 'maps' is sorted. We can use bsearch to make it faster. */ - for (map_idx = 0; map_idx < nr_maps; map_idx++) { - if (maps[map_idx].offset == sym.st_value) { - pr_debug("relocation: find map %zd (%s) for insn %u\n", - map_idx, maps[map_idx].name, insn_idx); - break; - } - } + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; - if (map_idx >= nr_maps) { - pr_warning("bpf relocation: map_idx %d large than %d\n", - (int)map_idx, (int)nr_maps - 1); - return -LIBBPF_ERRNO__RELOC; - } + pr_debug("relo for shdr %u, symb %llu, value %llu, type %d, bind %d, name %d (\'%s\'), insn %u\n", + (__u32)sym.st_shndx, (__u64)GELF_R_SYM(rel.r_info), + (__u64)sym.st_value, GELF_ST_TYPE(sym.st_info), + GELF_ST_BIND(sym.st_info), sym.st_name, name, + insn_idx); - prog->reloc_desc[i].type = RELO_LD64; - prog->reloc_desc[i].insn_idx = insn_idx; - prog->reloc_desc[i].map_idx = map_idx; + err = bpf_program__record_reloc(prog, &prog->reloc_desc[i], + insn_idx, name, &sym, &rel); + if (err) + return err; } return 0; } -static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) +static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) { struct bpf_map_def *def = &map->def; - __u32 key_type_id, value_type_id; + __u32 key_type_id = 0, value_type_id = 0; int ret; - ret = btf__get_map_kv_tids(btf, map->name, def->key_size, - def->value_size, &key_type_id, - &value_type_id); - if (ret) + /* if it's BTF-defined map, we don't need to search for type IDs */ + if (map->sec_idx == obj->efile.btf_maps_shndx) + return 0; + + if (!bpf_map__is_internal(map)) { + ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size, + def->value_size, &key_type_id, + &value_type_id); + } else { + /* + * LLVM annotates global data differently in BTF, that is, + * only as '.data', '.bss' or '.rodata'. + */ + ret = btf__find_by_name(obj->btf, + libbpf_type_to_btf_name[map->libbpf_type]); + } + if (ret < 0) return ret; map->btf_key_type_id = key_type_id; - map->btf_value_type_id = value_type_id; - + map->btf_value_type_id = bpf_map__is_internal(map) ? + ret : value_type_id; return 0; } @@ -1096,16 +2002,22 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) return -errno; new_fd = open("/", O_RDONLY | O_CLOEXEC); - if (new_fd < 0) + if (new_fd < 0) { + err = -errno; goto err_free_new_name; + } new_fd = dup3(fd, new_fd, O_CLOEXEC); - if (new_fd < 0) + if (new_fd < 0) { + err = -errno; goto err_close_new_fd; + } err = zclose(map->fd); - if (err) + if (err) { + err = -errno; goto err_close_new_fd; + } free(map->name); map->fd = new_fd; @@ -1117,6 +2029,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) map->def.map_flags = info.map_flags; map->btf_key_type_id = info.btf_key_type_id; map->btf_value_type_id = info.btf_value_type_id; + map->reused = true; return 0; @@ -1124,7 +2037,7 @@ err_close_new_fd: close(new_fd); err_free_new_name: free(new_name); - return -errno; + return err; } int bpf_map__resize(struct bpf_map *map, __u32 max_entries) @@ -1163,8 +2076,8 @@ bpf_object__probe_name(struct bpf_object *obj) ret = bpf_load_program_xattr(&attr, NULL, 0); if (ret < 0) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n", - __func__, cp, errno); + pr_warn("Error in %s():%s(%d). Couldn't load basic 'r0 = 0' BPF program.\n", + __func__, cp, errno); return -errno; } close(ret); @@ -1182,15 +2095,239 @@ bpf_object__probe_name(struct bpf_object *obj) } static int +bpf_object__probe_global_data(struct bpf_object *obj) +{ + struct bpf_load_program_attr prg_attr; + struct bpf_create_map_attr map_attr; + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int ret, map; + + memset(&map_attr, 0, sizeof(map_attr)); + map_attr.map_type = BPF_MAP_TYPE_ARRAY; + map_attr.key_size = sizeof(int); + map_attr.value_size = 32; + map_attr.max_entries = 1; + + map = bpf_create_map_xattr(&map_attr); + if (map < 0) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, errno); + return -errno; + } + + insns[0].imm = map; + + memset(&prg_attr, 0, sizeof(prg_attr)); + prg_attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + prg_attr.insns = insns; + prg_attr.insns_cnt = ARRAY_SIZE(insns); + prg_attr.license = "GPL"; + + ret = bpf_load_program_xattr(&prg_attr, NULL, 0); + if (ret >= 0) { + obj->caps.global_data = 1; + close(ret); + } + + close(map); + return 0; +} + +static int bpf_object__probe_btf_func(struct bpf_object *obj) +{ + 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), + }; + int btf_fd; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (btf_fd >= 0) { + obj->caps.btf_func = 1; + close(btf_fd); + return 1; + } + + return 0; +} + +static int bpf_object__probe_btf_datasec(struct bpf_object *obj) +{ + 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), + }; + int btf_fd; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (btf_fd >= 0) { + obj->caps.btf_datasec = 1; + close(btf_fd); + return 1; + } + + return 0; +} + +static int bpf_object__probe_array_mmap(struct bpf_object *obj) +{ + struct bpf_create_map_attr attr = { + .map_type = BPF_MAP_TYPE_ARRAY, + .map_flags = BPF_F_MMAPABLE, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1, + }; + int fd; + + fd = bpf_create_map_xattr(&attr); + if (fd >= 0) { + obj->caps.array_mmap = 1; + close(fd); + return 1; + } + + return 0; +} + +static int bpf_object__probe_caps(struct bpf_object *obj) { - return bpf_object__probe_name(obj); + int (*probe_fn[])(struct bpf_object *obj) = { + bpf_object__probe_name, + bpf_object__probe_global_data, + bpf_object__probe_btf_func, + bpf_object__probe_btf_datasec, + bpf_object__probe_array_mmap, + }; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(probe_fn); i++) { + ret = probe_fn[i](obj); + if (ret < 0) + pr_debug("Probe #%d failed with %d.\n", i, ret); + } + + return 0; +} + +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; + + map_info_len = sizeof(map_info); + + if (bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len)) { + pr_warn("failed to get map info for map FD %d: %s\n", + map_fd, libbpf_strerror_r(errno, msg, sizeof(msg))); + return false; + } + + return (map_info.type == map->def.type && + map_info.key_size == map->def.key_size && + map_info.value_size == map->def.value_size && + map_info.max_entries == map->def.max_entries && + map_info.map_flags == map->def.map_flags); +} + +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); + if (pin_fd < 0) { + err = -errno; + if (err == -ENOENT) { + pr_debug("found no pinned map to reuse at '%s'\n", + map->pin_path); + return 0; + } + + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warn("couldn't retrieve pinned map '%s': %s\n", + map->pin_path, cp); + return err; + } + + if (!map_is_reuse_compat(map, pin_fd)) { + pr_warn("couldn't reuse pinned map at '%s': parameter mismatch\n", + map->pin_path); + close(pin_fd); + return -EINVAL; + } + + err = bpf_map__reuse_fd(map, pin_fd); + if (err) { + close(pin_fd); + return err; + } + map->pinned = true; + pr_debug("reused pinned map at '%s'\n", map->pin_path); + + return 0; +} + +static int +bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + int err, zero = 0; + __u8 *data; + + /* Nothing to do here since kernel already zero-initializes .bss map. */ + if (map->libbpf_type == LIBBPF_MAP_BSS) + return 0; + + data = map->libbpf_type == LIBBPF_MAP_DATA ? + obj->sections.data : obj->sections.rodata; + + err = bpf_map_update_elem(map->fd, &zero, data, 0); + /* Freeze .rodata map as read-only from syscall side. */ + if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) { + err = bpf_map_freeze(map->fd); + if (err) { + cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + pr_warn("Error freezing map(%s) as read-only: %s\n", + map->name, cp); + err = 0; + } + } + return err; } static int bpf_object__create_maps(struct bpf_object *obj) { struct bpf_create_map_attr create_attr = {}; + int nr_cpus = 0; unsigned int i; int err; @@ -1200,6 +2337,15 @@ bpf_object__create_maps(struct bpf_object *obj) char *cp, errmsg[STRERR_BUFSIZE]; int *pfd = &map->fd; + if (map->pin_path) { + err = bpf_object__reuse_map(map); + if (err) { + pr_warn("error reusing pinned map %s\n", + map->name); + return err; + } + } + if (map->fd >= 0) { pr_debug("skip map create (preset) %s: fd=%d\n", map->name, map->fd); @@ -1213,7 +2359,22 @@ bpf_object__create_maps(struct bpf_object *obj) create_attr.map_flags = def->map_flags; create_attr.key_size = def->key_size; create_attr.value_size = def->value_size; - create_attr.max_entries = def->max_entries; + if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && + !def->max_entries) { + if (!nr_cpus) + nr_cpus = libbpf_num_possible_cpus(); + if (nr_cpus < 0) { + pr_warn("failed to determine number of system CPUs: %d\n", + nr_cpus); + err = nr_cpus; + goto err_out; + } + pr_debug("map '%s': setting size to %d\n", + map->name, nr_cpus); + create_attr.max_entries = nr_cpus; + } else { + create_attr.max_entries = def->max_entries; + } create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; @@ -1221,17 +2382,19 @@ bpf_object__create_maps(struct bpf_object *obj) map->inner_map_fd >= 0) create_attr.inner_map_fd = map->inner_map_fd; - if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) { + if (obj->btf && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; create_attr.btf_value_type_id = map->btf_value_type_id; } *pfd = bpf_create_map_xattr(&create_attr); - if (*pfd < 0 && create_attr.btf_key_type_id) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", - map->name, cp, errno); + if (*pfd < 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); create_attr.btf_fd = 0; create_attr.btf_key_type_id = 0; create_attr.btf_value_type_id = 0; @@ -1243,15 +2406,34 @@ bpf_object__create_maps(struct bpf_object *obj) if (*pfd < 0) { size_t j; - err = *pfd; - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("failed to create map (name: '%s'): %s\n", - map->name, cp); + err = -errno; +err_out: + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("failed to create map (name: '%s'): %s(%d)\n", + map->name, cp, err); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; } - pr_debug("create map %s: fd=%d\n", map->name, *pfd); + + if (bpf_map__is_internal(map)) { + err = bpf_object__populate_internal_map(obj, map); + if (err < 0) { + zclose(*pfd); + goto err_out; + } + } + + if (map->pin_path && !map->pinned) { + err = bpf_map__pin(map, NULL); + if (err) { + pr_warn("failed to auto-pin map name '%s' at '%s'\n", + map->name, map->pin_path); + return err; + } + } + + pr_debug("created map %s: fd=%d\n", map->name, *pfd); } return 0; @@ -1262,8 +2444,8 @@ check_btf_ext_reloc_err(struct bpf_program *prog, int err, void *btf_prog_info, const char *info_name) { if (err != -ENOENT) { - pr_warning("Error in loading %s for sec %s.\n", - info_name, prog->section_name); + pr_warn("Error in loading %s for sec %s.\n", + info_name, prog->section_name); return err; } @@ -1272,20 +2454,16 @@ check_btf_ext_reloc_err(struct bpf_program *prog, int err, if (btf_prog_info) { /* * Some info has already been found but has problem - * in the last btf_ext reloc. Must have to error - * out. + * in the last btf_ext reloc. Must have to error out. */ - pr_warning("Error in relocating %s for sec %s.\n", - info_name, prog->section_name); + pr_warn("Error in relocating %s for sec %s.\n", + info_name, prog->section_name); return err; } - /* - * Have problem loading the very first info. Ignore - * the rest. - */ - pr_warning("Cannot find %s for main program sec %s. Ignore all %s.\n", - info_name, prog->section_name, info_name); + /* Have problem loading the very first info. Ignore the rest. */ + pr_warn("Cannot find %s for main program sec %s. Ignore all %s.\n", + info_name, prog->section_name, info_name); return 0; } @@ -1327,12 +2505,1051 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj, prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext); } - if (!insn_offset) - prog->btf_fd = btf__fd(obj->btf); + return 0; +} + +#define BPF_CORE_SPEC_MAX_LEN 64 + +/* represents BPF CO-RE field or array element accessor */ +struct bpf_core_accessor { + __u32 type_id; /* struct/union type or array element type */ + __u32 idx; /* field index or array index */ + const char *name; /* field name or NULL for array accessor */ +}; + +struct bpf_core_spec { + const struct btf *btf; + /* high-level spec: named fields and array indices only */ + struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* high-level spec length */ + int len; + /* raw, low-level spec: 1-to-1 with accessor spec string */ + int raw_spec[BPF_CORE_SPEC_MAX_LEN]; + /* raw spec length */ + int raw_len; + /* field bit offset represented by spec */ + __u32 bit_offset; +}; + +static bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +/* + * Turn bpf_field_reloc into a low- and high-level spec representation, + * validating correctness along the way, as well as calculating resulting + * field bit offset, specified by accessor string. Low-level spec captures + * every single level of nestedness, including traversing anonymous + * struct/union members. High-level one only captures semantically meaningful + * "turning points": named fields and array indicies. + * E.g., for this case: + * + * struct sample { + * int __unimportant; + * struct { + * int __1; + * int __2; + * int a[7]; + * }; + * }; + * + * struct sample *s = ...; + * + * int x = &s->a[3]; // access string = '0:1:2:3' + * + * Low-level spec has 1:1 mapping with each element of access string (it's + * just a parsed access string representation): [0, 1, 2, 3]. + * + * High-level spec will capture only 3 points: + * - intial zero-index access by pointer (&s->... is the same as &s[0]...); + * - field 'a' access (corresponds to '2' in low-level spec); + * - array element #3 access (corresponds to '3' in low-level spec). + * + */ +static int bpf_core_spec_parse(const struct btf *btf, + __u32 type_id, + const char *spec_str, + struct bpf_core_spec *spec) +{ + int access_idx, parsed_len, i; + const struct btf_type *t; + const char *name; + __u32 id; + __s64 sz; + + if (str_is_empty(spec_str) || *spec_str == ':') + return -EINVAL; + + memset(spec, 0, sizeof(*spec)); + spec->btf = btf; + + /* parse spec_str="0:1:2:3:4" into array raw_spec=[0, 1, 2, 3, 4] */ + while (*spec_str) { + if (*spec_str == ':') + ++spec_str; + if (sscanf(spec_str, "%d%n", &access_idx, &parsed_len) != 1) + return -EINVAL; + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + spec_str += parsed_len; + spec->raw_spec[spec->raw_len++] = access_idx; + } + + if (spec->raw_len == 0) + return -EINVAL; + + /* first spec value is always reloc type array index */ + t = skip_mods_and_typedefs(btf, type_id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[0]; + spec->spec[0].type_id = id; + spec->spec[0].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->bit_offset = access_idx * sz * 8; + + for (i = 1; i < spec->raw_len; i++) { + t = skip_mods_and_typedefs(btf, id, &id); + if (!t) + return -EINVAL; + + access_idx = spec->raw_spec[i]; + + if (btf_is_composite(t)) { + const struct btf_member *m; + __u32 bit_offset; + + if (access_idx >= btf_vlen(t)) + return -EINVAL; + + bit_offset = btf_member_bit_offset(t, access_idx); + spec->bit_offset += bit_offset; + + m = btf_members(t) + access_idx; + if (m->name_off) { + name = btf__name_by_offset(btf, m->name_off); + if (str_is_empty(name)) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->spec[spec->len].name = name; + spec->len++; + } + + id = m->type; + } else if (btf_is_array(t)) { + const struct btf_array *a = btf_array(t); + + t = skip_mods_and_typedefs(btf, a->type, &id); + if (!t || access_idx >= a->nelems) + return -EINVAL; + + spec->spec[spec->len].type_id = id; + spec->spec[spec->len].idx = access_idx; + spec->len++; + + sz = btf__resolve_size(btf, id); + if (sz < 0) + return sz; + spec->bit_offset += access_idx * sz * 8; + } else { + pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %d\n", + type_id, spec_str, i, id, btf_kind(t)); + return -EINVAL; + } + } + + return 0; +} + +static bool bpf_core_is_flavor_sep(const char *s) +{ + /* check X___Y name pattern, where X and Y are not underscores */ + return s[0] != '_' && /* X */ + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ + s[4] != '_'; /* Y */ +} + +/* Given 'some_struct_name___with_flavor' return the length of a name prefix + * before last triple underscore. Struct name part after last triple + * underscore is ignored by BPF CO-RE relocation during relocation matching. + */ +static size_t bpf_core_essential_name_len(const char *name) +{ + size_t n = strlen(name); + int i; + + for (i = n - 5; i >= 0; i--) { + if (bpf_core_is_flavor_sep(name + i)) + return i + 1; + } + return n; +} + +/* dynamically sized list of type IDs */ +struct ids_vec { + __u32 *data; + int len; +}; + +static void bpf_core_free_cands(struct ids_vec *cand_ids) +{ + free(cand_ids->data); + free(cand_ids); +} + +static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, + __u32 local_type_id, + const struct btf *targ_btf) +{ + size_t local_essent_len, targ_essent_len; + const char *local_name, *targ_name; + const struct btf_type *t; + struct ids_vec *cand_ids; + __u32 *new_ids; + int i, err, n; + + t = btf__type_by_id(local_btf, local_type_id); + if (!t) + return ERR_PTR(-EINVAL); + + local_name = btf__name_by_offset(local_btf, t->name_off); + if (str_is_empty(local_name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(local_name); + + cand_ids = calloc(1, sizeof(*cand_ids)); + if (!cand_ids) + return ERR_PTR(-ENOMEM); + + n = btf__get_nr_types(targ_btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(targ_btf, i); + targ_name = btf__name_by_offset(targ_btf, t->name_off); + if (str_is_empty(targ_name)) + continue; + + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != local_essent_len) + continue; + + if (strncmp(local_name, targ_name, local_essent_len) == 0) { + pr_debug("[%d] %s: found candidate [%d] %s\n", + local_type_id, local_name, i, targ_name); + new_ids = realloc(cand_ids->data, cand_ids->len + 1); + if (!new_ids) { + err = -ENOMEM; + goto err_out; + } + cand_ids->data = new_ids; + cand_ids->data[cand_ids->len++] = i; + } + } + return cand_ids; +err_out: + bpf_core_free_cands(cand_ids); + return ERR_PTR(err); +} + +/* Check two types for compatibility, skipping const/volatile/restrict and + * typedefs, to ensure we are relocating compatible entities: + * - any two STRUCTs/UNIONs are compatible and can be mixed; + * - any two FWDs are compatible, if their names match (modulo flavor suffix); + * - any two PTRs are always compatible; + * - for ENUMs, names should be the same (ignoring flavor suffix) or at + * least one of enums should be anonymous; + * - for ENUMs, check sizes, names are ignored; + * - for INT, size and signedness are ignored; + * - for ARRAY, dimensionality is ignored, element types are checked for + * compatibility recursively; + * - everything else shouldn't be ever a target of relocation. + * These rules are not set in stone and probably will be adjusted as we get + * more experience with using BPF CO-RE relocations. + */ +static int bpf_core_fields_are_compat(const struct btf *local_btf, + __u32 local_id, + const struct btf *targ_btf, + __u32 targ_id) +{ + const struct btf_type *local_type, *targ_type; + +recur: + local_type = skip_mods_and_typedefs(local_btf, local_id, &local_id); + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!local_type || !targ_type) + return -EINVAL; + + if (btf_is_composite(local_type) && btf_is_composite(targ_type)) + return 1; + if (btf_kind(local_type) != btf_kind(targ_type)) + return 0; + + switch (btf_kind(local_type)) { + case BTF_KIND_PTR: + return 1; + case BTF_KIND_FWD: + case BTF_KIND_ENUM: { + const char *local_name, *targ_name; + size_t local_len, targ_len; + + local_name = btf__name_by_offset(local_btf, + local_type->name_off); + targ_name = btf__name_by_offset(targ_btf, targ_type->name_off); + local_len = bpf_core_essential_name_len(local_name); + targ_len = bpf_core_essential_name_len(targ_name); + /* one of them is anonymous or both w/ same flavor-less names */ + return local_len == 0 || targ_len == 0 || + (local_len == targ_len && + strncmp(local_name, targ_name, local_len) == 0); + } + case BTF_KIND_INT: + /* just reject deprecated bitfield-like integers; all other + * integers are by default compatible between each other + */ + return btf_int_offset(local_type) == 0 && + btf_int_offset(targ_type) == 0; + case BTF_KIND_ARRAY: + local_id = btf_array(local_type)->type; + targ_id = btf_array(targ_type)->type; + goto recur; + default: + pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n", + btf_kind(local_type), local_id, targ_id); + return 0; + } +} + +/* + * Given single high-level named field accessor in local type, find + * corresponding high-level accessor for a target type. Along the way, + * maintain low-level spec for target as well. Also keep updating target + * bit offset. + * + * Searching is performed through recursive exhaustive enumeration of all + * fields of a struct/union. If there are any anonymous (embedded) + * structs/unions, they are recursively searched as well. If field with + * desired name is found, check compatibility between local and target types, + * before returning result. + * + * 1 is returned, if field is found. + * 0 is returned if no compatible field is found. + * <0 is returned on error. + */ +static int bpf_core_match_member(const struct btf *local_btf, + const struct bpf_core_accessor *local_acc, + const struct btf *targ_btf, + __u32 targ_id, + struct bpf_core_spec *spec, + __u32 *next_targ_id) +{ + const struct btf_type *local_type, *targ_type; + const struct btf_member *local_member, *m; + const char *local_name, *targ_name; + __u32 local_id; + int i, n, found; + + targ_type = skip_mods_and_typedefs(targ_btf, targ_id, &targ_id); + if (!targ_type) + return -EINVAL; + if (!btf_is_composite(targ_type)) + return 0; + + local_id = local_acc->type_id; + local_type = btf__type_by_id(local_btf, local_id); + local_member = btf_members(local_type) + local_acc->idx; + local_name = btf__name_by_offset(local_btf, local_member->name_off); + + n = btf_vlen(targ_type); + m = btf_members(targ_type); + for (i = 0; i < n; i++, m++) { + __u32 bit_offset; + + bit_offset = btf_member_bit_offset(targ_type, i); + + /* too deep struct/union/array nesting */ + if (spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + /* speculate this member will be the good one */ + spec->bit_offset += bit_offset; + spec->raw_spec[spec->raw_len++] = i; + + targ_name = btf__name_by_offset(targ_btf, m->name_off); + if (str_is_empty(targ_name)) { + /* embedded struct/union, we need to go deeper */ + found = bpf_core_match_member(local_btf, local_acc, + targ_btf, m->type, + spec, next_targ_id); + if (found) /* either found or error */ + return found; + } else if (strcmp(local_name, targ_name) == 0) { + /* matching named field */ + struct bpf_core_accessor *targ_acc; + + targ_acc = &spec->spec[spec->len++]; + targ_acc->type_id = targ_id; + targ_acc->idx = i; + targ_acc->name = targ_name; + + *next_targ_id = m->type; + found = bpf_core_fields_are_compat(local_btf, + local_member->type, + targ_btf, m->type); + if (!found) + spec->len--; /* pop accessor */ + return found; + } + /* member turned out not to be what we looked for */ + spec->bit_offset -= bit_offset; + spec->raw_len--; + } return 0; } +/* + * Try to match local spec to a target type and, if successful, produce full + * target spec (high-level, low-level + bit offset). + */ +static int bpf_core_spec_match(struct bpf_core_spec *local_spec, + const struct btf *targ_btf, __u32 targ_id, + struct bpf_core_spec *targ_spec) +{ + const struct btf_type *targ_type; + const struct bpf_core_accessor *local_acc; + struct bpf_core_accessor *targ_acc; + int i, sz, matched; + + memset(targ_spec, 0, sizeof(*targ_spec)); + targ_spec->btf = targ_btf; + + local_acc = &local_spec->spec[0]; + targ_acc = &targ_spec->spec[0]; + + for (i = 0; i < local_spec->len; i++, local_acc++, targ_acc++) { + targ_type = skip_mods_and_typedefs(targ_spec->btf, targ_id, + &targ_id); + if (!targ_type) + return -EINVAL; + + if (local_acc->name) { + matched = bpf_core_match_member(local_spec->btf, + local_acc, + targ_btf, targ_id, + targ_spec, &targ_id); + if (matched <= 0) + return matched; + } else { + /* for i=0, targ_id is already treated as array element + * type (because it's the original struct), for others + * we should find array element type first + */ + if (i > 0) { + const struct btf_array *a; + + if (!btf_is_array(targ_type)) + return 0; + + a = btf_array(targ_type); + if (local_acc->idx >= a->nelems) + return 0; + if (!skip_mods_and_typedefs(targ_btf, a->type, + &targ_id)) + return -EINVAL; + } + + /* too deep struct/union/array nesting */ + if (targ_spec->raw_len == BPF_CORE_SPEC_MAX_LEN) + return -E2BIG; + + targ_acc->type_id = targ_id; + targ_acc->idx = local_acc->idx; + targ_acc->name = NULL; + targ_spec->len++; + targ_spec->raw_spec[targ_spec->raw_len] = targ_acc->idx; + targ_spec->raw_len++; + + sz = btf__resolve_size(targ_btf, targ_id); + if (sz < 0) + return sz; + targ_spec->bit_offset += local_acc->idx * sz * 8; + } + } + + return 1; +} + +static int bpf_core_calc_field_relo(const struct bpf_program *prog, + const struct bpf_field_reloc *relo, + const struct bpf_core_spec *spec, + __u32 *val, bool *validate) +{ + const struct bpf_core_accessor *acc = &spec->spec[spec->len - 1]; + const struct btf_type *t = btf__type_by_id(spec->btf, acc->type_id); + __u32 byte_off, byte_sz, bit_off, bit_sz; + const struct btf_member *m; + const struct btf_type *mt; + bool bitfield; + __s64 sz; + + /* a[n] accessor needs special handling */ + if (!acc->name) { + if (relo->kind == BPF_FIELD_BYTE_OFFSET) { + *val = spec->bit_offset / 8; + } else if (relo->kind == BPF_FIELD_BYTE_SIZE) { + sz = btf__resolve_size(spec->btf, acc->type_id); + if (sz < 0) + return -EINVAL; + *val = sz; + } else { + pr_warn("prog '%s': relo %d at insn #%d can't be applied to array access\n", + bpf_program__title(prog, false), + relo->kind, relo->insn_off / 8); + return -EINVAL; + } + if (validate) + *validate = true; + return 0; + } + + m = btf_members(t) + acc->idx; + mt = skip_mods_and_typedefs(spec->btf, m->type, NULL); + bit_off = spec->bit_offset; + bit_sz = btf_member_bitfield_size(t, acc->idx); + + bitfield = bit_sz > 0; + if (bitfield) { + byte_sz = mt->size; + byte_off = bit_off / 8 / byte_sz * byte_sz; + /* figure out smallest int size necessary for bitfield load */ + while (bit_off + bit_sz - byte_off * 8 > byte_sz * 8) { + if (byte_sz >= 8) { + /* bitfield can't be read with 64-bit read */ + pr_warn("prog '%s': relo %d at insn #%d can't be satisfied for bitfield\n", + bpf_program__title(prog, false), + relo->kind, relo->insn_off / 8); + return -E2BIG; + } + byte_sz *= 2; + byte_off = bit_off / 8 / byte_sz * byte_sz; + } + } else { + sz = btf__resolve_size(spec->btf, m->type); + if (sz < 0) + return -EINVAL; + byte_sz = sz; + byte_off = spec->bit_offset / 8; + bit_sz = byte_sz * 8; + } + + /* for bitfields, all the relocatable aspects are ambiguous and we + * might disagree with compiler, so turn off validation of expected + * value, except for signedness + */ + if (validate) + *validate = !bitfield; + + switch (relo->kind) { + case BPF_FIELD_BYTE_OFFSET: + *val = byte_off; + break; + case BPF_FIELD_BYTE_SIZE: + *val = byte_sz; + break; + case BPF_FIELD_SIGNED: + /* enums will be assumed unsigned */ + *val = btf_is_enum(mt) || + (btf_int_encoding(mt) & BTF_INT_SIGNED); + if (validate) + *validate = true; /* signedness is never ambiguous */ + break; + case BPF_FIELD_LSHIFT_U64: +#if __BYTE_ORDER == __LITTLE_ENDIAN + *val = 64 - (bit_off + bit_sz - byte_off * 8); +#else + *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8); +#endif + break; + case BPF_FIELD_RSHIFT_U64: + *val = 64 - bit_sz; + if (validate) + *validate = true; /* right shift is never ambiguous */ + break; + case BPF_FIELD_EXISTS: + default: + pr_warn("prog '%s': unknown relo %d at insn #%d\n", + bpf_program__title(prog, false), + relo->kind, relo->insn_off / 8); + return -EINVAL; + } + + return 0; +} + +/* + * Patch relocatable BPF instruction. + * + * Patched value is determined by relocation kind and target specification. + * For field existence relocation target spec will be NULL if field is not + * found. + * Expected insn->imm value is determined using relocation kind and local + * spec, and is checked before patching instruction. If actual insn->imm value + * is wrong, bail out with error. + * + * Currently three kinds of BPF instructions are supported: + * 1. rX = <imm> (assignment with immediate operand); + * 2. rX += <imm> (arithmetic operations with immediate operand); + */ +static int bpf_core_reloc_insn(struct bpf_program *prog, + const struct bpf_field_reloc *relo, + const struct bpf_core_spec *local_spec, + const struct bpf_core_spec *targ_spec) +{ + bool failed = false, validate = true; + __u32 orig_val, new_val; + struct bpf_insn *insn; + int insn_idx, err; + __u8 class; + + if (relo->insn_off % sizeof(struct bpf_insn)) + return -EINVAL; + insn_idx = relo->insn_off / sizeof(struct bpf_insn); + + if (relo->kind == BPF_FIELD_EXISTS) { + orig_val = 1; /* can't generate EXISTS relo w/o local field */ + new_val = targ_spec ? 1 : 0; + } else if (!targ_spec) { + failed = true; + new_val = (__u32)-1; + } else { + err = bpf_core_calc_field_relo(prog, relo, local_spec, + &orig_val, &validate); + if (err) + return err; + err = bpf_core_calc_field_relo(prog, relo, targ_spec, + &new_val, NULL); + if (err) + return err; + } + + insn = &prog->insns[insn_idx]; + class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_SRC(insn->code) != BPF_K) + return -EINVAL; + if (!failed && validate && insn->imm != orig_val) { + pr_warn("prog '%s': unexpected insn #%d value: got %u, exp %u -> %u\n", + bpf_program__title(prog, false), insn_idx, + insn->imm, orig_val, new_val); + return -EINVAL; + } + orig_val = insn->imm; + insn->imm = new_val; + pr_debug("prog '%s': patched insn #%d (ALU/ALU64)%s imm %u -> %u\n", + bpf_program__title(prog, false), insn_idx, + failed ? " w/ failed reloc" : "", orig_val, new_val); + } else { + pr_warn("prog '%s': trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", + bpf_program__title(prog, false), + insn_idx, insn->code, insn->src_reg, insn->dst_reg, + insn->off, insn->imm); + return -EINVAL; + } + + return 0; +} + +static struct btf *btf_load_raw(const char *path) +{ + struct btf *btf; + size_t read_cnt; + struct stat st; + void *data; + FILE *f; + + if (stat(path, &st)) + return ERR_PTR(-errno); + + data = malloc(st.st_size); + if (!data) + return ERR_PTR(-ENOMEM); + + f = fopen(path, "rb"); + if (!f) { + btf = ERR_PTR(-errno); + goto cleanup; + } + + read_cnt = fread(data, 1, st.st_size, f); + fclose(f); + if (read_cnt < st.st_size) { + btf = ERR_PTR(-EBADF); + goto cleanup; + } + + btf = btf__new(data, read_cnt); + +cleanup: + free(data); + return btf; +} + +/* + * Probe few well-known locations for vmlinux kernel image and try to load BTF + * data out of it to use for target BTF. + */ +static struct btf *bpf_core_find_kernel_btf(void) +{ + struct { + const char *path_fmt; + bool raw_btf; + } locations[] = { + /* try canonical vmlinux BTF through sysfs first */ + { "/sys/kernel/btf/vmlinux", true /* raw BTF */ }, + /* fall back to trying to find vmlinux ELF on disk otherwise */ + { "/boot/vmlinux-%1$s" }, + { "/lib/modules/%1$s/vmlinux-%1$s" }, + { "/lib/modules/%1$s/build/vmlinux" }, + { "/usr/lib/modules/%1$s/kernel/vmlinux" }, + { "/usr/lib/debug/boot/vmlinux-%1$s" }, + { "/usr/lib/debug/boot/vmlinux-%1$s.debug" }, + { "/usr/lib/debug/lib/modules/%1$s/vmlinux" }, + }; + char path[PATH_MAX + 1]; + struct utsname buf; + struct btf *btf; + int i; + + uname(&buf); + + for (i = 0; i < ARRAY_SIZE(locations); i++) { + snprintf(path, PATH_MAX, locations[i].path_fmt, buf.release); + + if (access(path, R_OK)) + continue; + + if (locations[i].raw_btf) + btf = btf_load_raw(path); + else + btf = btf__parse_elf(path, NULL); + + pr_debug("loading kernel BTF '%s': %ld\n", + path, IS_ERR(btf) ? PTR_ERR(btf) : 0); + if (IS_ERR(btf)) + continue; + + return btf; + } + + pr_warn("failed to find valid kernel BTF\n"); + return ERR_PTR(-ESRCH); +} + +/* Output spec definition in the format: + * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>, + * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b + */ +static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) +{ + const struct btf_type *t; + const char *s; + __u32 type_id; + int i; + + type_id = spec->spec[0].type_id; + t = btf__type_by_id(spec->btf, type_id); + s = btf__name_by_offset(spec->btf, t->name_off); + libbpf_print(level, "[%u] %s + ", type_id, s); + + for (i = 0; i < spec->raw_len; i++) + libbpf_print(level, "%d%s", spec->raw_spec[i], + i == spec->raw_len - 1 ? " => " : ":"); + + libbpf_print(level, "%u.%u @ &x", + spec->bit_offset / 8, spec->bit_offset % 8); + + for (i = 0; i < spec->len; i++) { + if (spec->spec[i].name) + libbpf_print(level, ".%s", spec->spec[i].name); + else + libbpf_print(level, "[%u]", spec->spec[i].idx); + } + +} + +static size_t bpf_core_hash_fn(const void *key, void *ctx) +{ + return (size_t)key; +} + +static bool bpf_core_equal_fn(const void *k1, const void *k2, void *ctx) +{ + return k1 == k2; +} + +static void *u32_as_hash_key(__u32 x) +{ + return (void *)(uintptr_t)x; +} + +/* + * CO-RE relocate single instruction. + * + * The outline and important points of the algorithm: + * 1. For given local type, find corresponding candidate target types. + * Candidate type is a type with the same "essential" name, ignoring + * everything after last triple underscore (___). E.g., `sample`, + * `sample___flavor_one`, `sample___flavor_another_one`, are all candidates + * for each other. Names with triple underscore are referred to as + * "flavors" and are useful, among other things, to allow to + * specify/support incompatible variations of the same kernel struct, which + * might differ between different kernel versions and/or build + * configurations. + * + * N.B. Struct "flavors" could be generated by bpftool's BTF-to-C + * converter, when deduplicated BTF of a kernel still contains more than + * one different types with the same name. In that case, ___2, ___3, etc + * are appended starting from second name conflict. But start flavors are + * also useful to be defined "locally", in BPF program, to extract same + * data from incompatible changes between different kernel + * versions/configurations. For instance, to handle field renames between + * kernel versions, one can use two flavors of the struct name with the + * same common name and use conditional relocations to extract that field, + * depending on target kernel version. + * 2. For each candidate type, try to match local specification to this + * candidate target type. Matching involves finding corresponding + * high-level spec accessors, meaning that all named fields should match, + * as well as all array accesses should be within the actual bounds. Also, + * types should be compatible (see bpf_core_fields_are_compat for details). + * 3. It is supported and expected that there might be multiple flavors + * matching the spec. As long as all the specs resolve to the same set of + * offsets across all candidates, there is no error. If there is any + * ambiguity, CO-RE relocation will fail. This is necessary to accomodate + * imprefection of BTF deduplication, which can cause slight duplication of + * the same BTF type, if some directly or indirectly referenced (by + * pointer) type gets resolved to different actual types in different + * object files. If such situation occurs, deduplicated BTF will end up + * with two (or more) structurally identical types, which differ only in + * types they refer to through pointer. This should be OK in most cases and + * is not an error. + * 4. Candidate types search is performed by linearly scanning through all + * types in target BTF. It is anticipated that this is overall more + * efficient memory-wise and not significantly worse (if not better) + * CPU-wise compared to prebuilding a map from all local type names to + * a list of candidate type names. It's also sped up by caching resolved + * list of matching candidates per each local "root" type ID, that has at + * least one bpf_field_reloc associated with it. This list is shared + * between multiple relocations for the same type ID and is updated as some + * of the candidates are pruned due to structural incompatibility. + */ +static int bpf_core_reloc_field(struct bpf_program *prog, + const struct bpf_field_reloc *relo, + int relo_idx, + const struct btf *local_btf, + const struct btf *targ_btf, + struct hashmap *cand_cache) +{ + const char *prog_name = bpf_program__title(prog, false); + struct bpf_core_spec local_spec, cand_spec, targ_spec; + const void *type_key = u32_as_hash_key(relo->type_id); + const struct btf_type *local_type, *cand_type; + const char *local_name, *cand_name; + struct ids_vec *cand_ids; + __u32 local_id, cand_id; + const char *spec_str; + int i, j, err; + + local_id = relo->type_id; + local_type = btf__type_by_id(local_btf, local_id); + if (!local_type) + return -EINVAL; + + local_name = btf__name_by_offset(local_btf, local_type->name_off); + if (str_is_empty(local_name)) + return -EINVAL; + + spec_str = btf__name_by_offset(local_btf, relo->access_str_off); + if (str_is_empty(spec_str)) + return -EINVAL; + + err = bpf_core_spec_parse(local_btf, local_id, spec_str, &local_spec); + if (err) { + pr_warn("prog '%s': relo #%d: parsing [%d] %s + %s failed: %d\n", + prog_name, relo_idx, local_id, local_name, spec_str, + err); + return -EINVAL; + } + + pr_debug("prog '%s': relo #%d: kind %d, spec is ", prog_name, relo_idx, + relo->kind); + bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); + libbpf_print(LIBBPF_DEBUG, "\n"); + + if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) { + cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf); + if (IS_ERR(cand_ids)) { + pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s: %ld", + prog_name, relo_idx, local_id, local_name, + PTR_ERR(cand_ids)); + return PTR_ERR(cand_ids); + } + err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL); + if (err) { + bpf_core_free_cands(cand_ids); + return err; + } + } + + for (i = 0, j = 0; i < cand_ids->len; i++) { + cand_id = cand_ids->data[i]; + cand_type = btf__type_by_id(targ_btf, cand_id); + cand_name = btf__name_by_offset(targ_btf, cand_type->name_off); + + err = bpf_core_spec_match(&local_spec, targ_btf, + cand_id, &cand_spec); + pr_debug("prog '%s': relo #%d: matching candidate #%d %s against spec ", + prog_name, relo_idx, i, cand_name); + bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); + libbpf_print(LIBBPF_DEBUG, ": %d\n", err); + if (err < 0) { + pr_warn("prog '%s': relo #%d: matching error: %d\n", + prog_name, relo_idx, err); + return err; + } + if (err == 0) + continue; + + if (j == 0) { + targ_spec = cand_spec; + } else if (cand_spec.bit_offset != targ_spec.bit_offset) { + /* if there are many candidates, they should all + * resolve to the same bit offset + */ + pr_warn("prog '%s': relo #%d: offset ambiguity: %u != %u\n", + prog_name, relo_idx, cand_spec.bit_offset, + targ_spec.bit_offset); + return -EINVAL; + } + + cand_ids->data[j++] = cand_spec.spec[0].type_id; + } + + /* + * For BPF_FIELD_EXISTS relo or when relaxed CO-RE reloc mode is + * requested, it's expected that we might not find any candidates. + * In this case, if field wasn't found in any candidate, the list of + * candidates shouldn't change at all, we'll just handle relocating + * appropriately, depending on relo's kind. + */ + if (j > 0) + cand_ids->len = j; + + if (j == 0 && !prog->obj->relaxed_core_relocs && + relo->kind != BPF_FIELD_EXISTS) { + pr_warn("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", + prog_name, relo_idx, local_id, local_name, spec_str); + return -ESRCH; + } + + /* bpf_core_reloc_insn should know how to handle missing targ_spec */ + err = bpf_core_reloc_insn(prog, relo, &local_spec, + j ? &targ_spec : NULL); + if (err) { + pr_warn("prog '%s': relo #%d: failed to patch insn at offset %d: %d\n", + prog_name, relo_idx, relo->insn_off, err); + return -EINVAL; + } + + return 0; +} + +static int +bpf_core_reloc_fields(struct bpf_object *obj, const char *targ_btf_path) +{ + const struct btf_ext_info_sec *sec; + const struct bpf_field_reloc *rec; + const struct btf_ext_info *seg; + struct hashmap_entry *entry; + struct hashmap *cand_cache = NULL; + struct bpf_program *prog; + struct btf *targ_btf; + const char *sec_name; + int i, err = 0; + + if (targ_btf_path) + targ_btf = btf__parse_elf(targ_btf_path, NULL); + else + targ_btf = bpf_core_find_kernel_btf(); + if (IS_ERR(targ_btf)) { + pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf)); + return PTR_ERR(targ_btf); + } + + cand_cache = hashmap__new(bpf_core_hash_fn, bpf_core_equal_fn, NULL); + if (IS_ERR(cand_cache)) { + err = PTR_ERR(cand_cache); + goto out; + } + + seg = &obj->btf_ext->field_reloc_info; + for_each_btf_ext_sec(seg, sec) { + sec_name = btf__name_by_offset(obj->btf, sec->sec_name_off); + if (str_is_empty(sec_name)) { + err = -EINVAL; + goto out; + } + prog = bpf_object__find_program_by_title(obj, sec_name); + if (!prog) { + pr_warn("failed to find program '%s' for CO-RE offset relocation\n", + sec_name); + err = -EINVAL; + goto out; + } + + pr_debug("prog '%s': performing %d CO-RE offset relocs\n", + sec_name, sec->num_info); + + for_each_btf_ext_rec(seg, sec, i, rec) { + err = bpf_core_reloc_field(prog, rec, i, obj->btf, + targ_btf, cand_cache); + if (err) { + pr_warn("prog '%s': relo #%d: failed to relocate: %d\n", + sec_name, i, err); + goto out; + } + } + } + +out: + btf__free(targ_btf); + if (!IS_ERR_OR_NULL(cand_cache)) { + hashmap__for_each_entry(cand_cache, entry, i) { + bpf_core_free_cands(entry->value); + } + hashmap__free(cand_cache); + } + return err; +} + +static int +bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) +{ + int err = 0; + + if (obj->btf_ext->field_reloc_info.len) + err = bpf_core_reloc_fields(obj, targ_btf_path); + + return err; +} + static int bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, struct reloc_desc *relo) @@ -1346,23 +3563,24 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, return -LIBBPF_ERRNO__RELOC; if (prog->idx == obj->efile.text_shndx) { - pr_warning("relo in .text insn %d into off %d\n", - relo->insn_idx, relo->text_off); + pr_warn("relo in .text insn %d into off %d\n", + relo->insn_idx, relo->text_off); return -LIBBPF_ERRNO__RELOC; } if (prog->main_prog_cnt == 0) { text = bpf_object__find_prog_by_idx(obj, obj->efile.text_shndx); if (!text) { - pr_warning("no .text section found yet relo into text exist\n"); + pr_warn("no .text section found yet relo into text exist\n"); return -LIBBPF_ERRNO__RELOC; } new_cnt = prog->insns_cnt + text->insns_cnt; new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn)); if (!new_insn) { - pr_warning("oom in prog realloc\n"); + pr_warn("oom in prog realloc\n"); return -ENOMEM; } + prog->insns = new_insn; if (obj->btf_ext) { err = bpf_program_reloc_btf_ext(prog, obj, @@ -1374,7 +3592,6 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, memcpy(new_insn + prog->insns_cnt, text->insns, text->insns_cnt * sizeof(*insn)); - prog->insns = new_insn; prog->main_prog_cnt = prog->insns_cnt; prog->insns_cnt = new_cnt; pr_debug("added %zd insn from %s to prog %s\n", @@ -1382,7 +3599,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, prog->section_name); } insn = &prog->insns[relo->insn_idx]; - insn->imm += prog->main_prog_cnt - relo->insn_idx; + insn->imm += relo->text_off + prog->main_prog_cnt - relo->insn_idx; return 0; } @@ -1405,21 +3622,29 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; for (i = 0; i < prog->nr_reloc; i++) { - if (prog->reloc_desc[i].type == RELO_LD64) { + if (prog->reloc_desc[i].type == RELO_LD64 || + prog->reloc_desc[i].type == RELO_DATA) { + bool relo_data = prog->reloc_desc[i].type == RELO_DATA; struct bpf_insn *insns = prog->insns; int insn_idx, map_idx; insn_idx = prog->reloc_desc[i].insn_idx; map_idx = prog->reloc_desc[i].map_idx; - if (insn_idx >= (int)prog->insns_cnt) { - pr_warning("relocation out of range: '%s'\n", - prog->section_name); + if (insn_idx + 1 >= (int)prog->insns_cnt) { + pr_warn("relocation out of range: '%s'\n", + prog->section_name); return -LIBBPF_ERRNO__RELOC; } - insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + + if (!relo_data) { + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; + } else { + insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE; + insns[insn_idx + 1].imm = insns[insn_idx].imm; + } insns[insn_idx].imm = obj->maps[map_idx].fd; - } else { + } else if (prog->reloc_desc[i].type == RELO_CALL) { err = bpf_program__reloc_text(prog, obj, &prog->reloc_desc[i]); if (err) @@ -1432,21 +3657,27 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) return 0; } - static int -bpf_object__relocate(struct bpf_object *obj) +bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { struct bpf_program *prog; size_t i; int err; + 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); + return err; + } + } for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; err = bpf_program__relocate(prog, obj); if (err) { - pr_warning("failed to relocate '%s'\n", - prog->section_name); + pr_warn("failed to relocate '%s'\n", prog->section_name); return err; } } @@ -1458,30 +3689,28 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) int i, err; if (!obj_elf_valid(obj)) { - pr_warning("Internal error: elf object is closed\n"); + pr_warn("Internal error: elf object is closed\n"); return -LIBBPF_ERRNO__INTERNAL; } - for (i = 0; i < obj->efile.nr_reloc; i++) { - GElf_Shdr *shdr = &obj->efile.reloc[i].shdr; - Elf_Data *data = obj->efile.reloc[i].data; + for (i = 0; i < obj->efile.nr_reloc_sects; i++) { + GElf_Shdr *shdr = &obj->efile.reloc_sects[i].shdr; + Elf_Data *data = obj->efile.reloc_sects[i].data; int idx = shdr->sh_info; struct bpf_program *prog; if (shdr->sh_type != SHT_REL) { - pr_warning("internal error at %d\n", __LINE__); + pr_warn("internal error at %d\n", __LINE__); return -LIBBPF_ERRNO__INTERNAL; } prog = bpf_object__find_prog_by_idx(obj, idx); if (!prog) { - pr_warning("relocation failed: no section(%d)\n", idx); + pr_warn("relocation failed: no section(%d)\n", idx); return -LIBBPF_ERRNO__RELOC; } - err = bpf_program__collect_reloc(prog, - shdr, data, - obj); + err = bpf_program__collect_reloc(prog, shdr, data, obj); if (err) return err; } @@ -1494,8 +3723,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, { struct bpf_load_program_attr load_attr; char *cp, errmsg[STRERR_BUFSIZE]; + int log_buf_size = BPF_LOG_BUF_SIZE; char *log_buf; - int ret; + int btf_fd, ret; + + if (!insns || !insns_cnt) + return -EINVAL; memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); load_attr.prog_type = prog->type; @@ -1505,60 +3738,73 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.insns = insns; load_attr.insns_cnt = insns_cnt; load_attr.license = license; - load_attr.kern_version = kern_version; - load_attr.prog_ifindex = prog->prog_ifindex; - load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0; + if (prog->type == BPF_PROG_TYPE_TRACING) { + load_attr.attach_prog_fd = prog->attach_prog_fd; + load_attr.attach_btf_id = prog->attach_btf_id; + } else { + load_attr.kern_version = kern_version; + load_attr.prog_ifindex = prog->prog_ifindex; + } + /* if .BTF.ext was loaded, kernel supports associated BTF for prog */ + if (prog->obj->btf_ext) + btf_fd = bpf_object__btf_fd(prog->obj); + else + btf_fd = -1; + load_attr.prog_btf_fd = btf_fd >= 0 ? btf_fd : 0; 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; load_attr.line_info = prog->line_info; load_attr.line_info_rec_size = prog->line_info_rec_size; load_attr.line_info_cnt = prog->line_info_cnt; - if (!load_attr.insns || !load_attr.insns_cnt) - return -EINVAL; + load_attr.log_level = prog->log_level; + load_attr.prog_flags = prog->prog_flags; - log_buf = malloc(BPF_LOG_BUF_SIZE); +retry_load: + log_buf = malloc(log_buf_size); if (!log_buf) - pr_warning("Alloc log buffer for bpf loader error, continue without log\n"); + pr_warn("Alloc log buffer for bpf loader error, continue without log\n"); - ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE); + ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size); if (ret >= 0) { + if (load_attr.log_level) + pr_debug("verifier log:\n%s", log_buf); *pfd = ret; ret = 0; goto out; } - ret = -LIBBPF_ERRNO__LOAD; + if (errno == ENOSPC) { + log_buf_size <<= 1; + free(log_buf); + goto retry_load; + } + ret = -errno; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("load bpf program failed: %s\n", cp); + pr_warn("load bpf program failed: %s\n", cp); if (log_buf && log_buf[0] != '\0') { ret = -LIBBPF_ERRNO__VERIFY; - pr_warning("-- BEGIN DUMP LOG ---\n"); - pr_warning("\n%s\n", log_buf); - pr_warning("-- END LOG --\n"); + pr_warn("-- BEGIN DUMP LOG ---\n"); + pr_warn("\n%s\n", log_buf); + pr_warn("-- END LOG --\n"); } else if (load_attr.insns_cnt >= BPF_MAXINSNS) { - pr_warning("Program too large (%zu insns), at most %d insns\n", - load_attr.insns_cnt, BPF_MAXINSNS); + pr_warn("Program too large (%zu insns), at most %d insns\n", + load_attr.insns_cnt, BPF_MAXINSNS); ret = -LIBBPF_ERRNO__PROG2BIG; - } else { + } else if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) { /* Wrong program type? */ - if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) { - int fd; - - load_attr.prog_type = BPF_PROG_TYPE_KPROBE; - load_attr.expected_attach_type = 0; - fd = bpf_load_program_xattr(&load_attr, NULL, 0); - if (fd >= 0) { - close(fd); - ret = -LIBBPF_ERRNO__PROGTYPE; - goto out; - } - } + int fd; - if (log_buf) - ret = -LIBBPF_ERRNO__KVER; + load_attr.prog_type = BPF_PROG_TYPE_KPROBE; + load_attr.expected_attach_type = 0; + fd = bpf_load_program_xattr(&load_attr, NULL, 0); + if (fd >= 0) { + close(fd); + ret = -LIBBPF_ERRNO__PROGTYPE; + goto out; + } } out: @@ -1574,14 +3820,14 @@ bpf_program__load(struct bpf_program *prog, if (prog->instances.nr < 0 || !prog->instances.fds) { if (prog->preprocessor) { - pr_warning("Internal error: can't load program '%s'\n", - prog->section_name); + pr_warn("Internal error: can't load program '%s'\n", + prog->section_name); return -LIBBPF_ERRNO__INTERNAL; } prog->instances.fds = malloc(sizeof(int)); if (!prog->instances.fds) { - pr_warning("Not enough memory for BPF fds\n"); + pr_warn("Not enough memory for BPF fds\n"); return -ENOMEM; } prog->instances.nr = 1; @@ -1590,8 +3836,8 @@ bpf_program__load(struct bpf_program *prog, if (!prog->preprocessor) { if (prog->instances.nr != 1) { - pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n", - prog->section_name, prog->instances.nr); + pr_warn("Program '%s' is inconsistent: nr(%d) != 1\n", + prog->section_name, prog->instances.nr); } err = load_program(prog, prog->insns, prog->insns_cnt, license, kern_version, &fd); @@ -1608,8 +3854,8 @@ bpf_program__load(struct bpf_program *prog, err = preprocessor(prog, i, prog->insns, prog->insns_cnt, &result); if (err) { - pr_warning("Preprocessing the %dth instance of program '%s' failed\n", - i, prog->section_name); + pr_warn("Preprocessing the %dth instance of program '%s' failed\n", + i, prog->section_name); goto out; } @@ -1627,8 +3873,8 @@ bpf_program__load(struct bpf_program *prog, license, kern_version, &fd); if (err) { - pr_warning("Loading the %dth instance of program '%s' failed\n", - i, prog->section_name); + pr_warn("Loading the %dth instance of program '%s' failed\n", + i, prog->section_name); goto out; } @@ -1638,21 +3884,20 @@ bpf_program__load(struct bpf_program *prog, } out: if (err) - pr_warning("failed to load program '%s'\n", - prog->section_name); + pr_warn("failed to load program '%s'\n", prog->section_name); zfree(&prog->insns); prog->insns_cnt = 0; return err; } -static bool bpf_program__is_function_storage(struct bpf_program *prog, - struct bpf_object *obj) +static bool bpf_program__is_function_storage(const struct bpf_program *prog, + const struct bpf_object *obj) { return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls; } static int -bpf_object__load_progs(struct bpf_object *obj) +bpf_object__load_progs(struct bpf_object *obj, int log_level) { size_t i; int err; @@ -1660,6 +3905,7 @@ bpf_object__load_progs(struct bpf_object *obj) for (i = 0; i < obj->nr_programs; i++) { if (bpf_program__is_function_storage(&obj->programs[i], obj)) continue; + obj->programs[i].log_level |= log_level; err = bpf_program__load(&obj->programs[i], obj->license, obj->kern_version); @@ -1669,89 +3915,104 @@ bpf_object__load_progs(struct bpf_object *obj) return 0; } -static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) -{ - switch (type) { - case BPF_PROG_TYPE_SOCKET_FILTER: - case BPF_PROG_TYPE_SCHED_CLS: - case BPF_PROG_TYPE_SCHED_ACT: - case BPF_PROG_TYPE_XDP: - case BPF_PROG_TYPE_CGROUP_SKB: - case BPF_PROG_TYPE_CGROUP_SOCK: - case BPF_PROG_TYPE_LWT_IN: - case BPF_PROG_TYPE_LWT_OUT: - case BPF_PROG_TYPE_LWT_XMIT: - case BPF_PROG_TYPE_LWT_SEG6LOCAL: - case BPF_PROG_TYPE_SOCK_OPS: - case BPF_PROG_TYPE_SK_SKB: - case BPF_PROG_TYPE_CGROUP_DEVICE: - case BPF_PROG_TYPE_SK_MSG: - case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: - case BPF_PROG_TYPE_LIRC_MODE2: - case BPF_PROG_TYPE_SK_REUSEPORT: - case BPF_PROG_TYPE_FLOW_DISSECTOR: - case BPF_PROG_TYPE_UNSPEC: - case BPF_PROG_TYPE_TRACEPOINT: - case BPF_PROG_TYPE_RAW_TRACEPOINT: - case BPF_PROG_TYPE_PERF_EVENT: - return false; - case BPF_PROG_TYPE_KPROBE: - default: - return true; - } -} - -static int bpf_object__validate(struct bpf_object *obj, bool needs_kver) -{ - if (needs_kver && obj->kern_version == 0) { - pr_warning("%s doesn't provide kernel version\n", - obj->path); - return -LIBBPF_ERRNO__KVERSION; - } - return 0; -} - +static int libbpf_find_attach_btf_id(const char *name, + enum bpf_attach_type attach_type, + __u32 attach_prog_fd); static struct bpf_object * -__bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, - bool needs_kver, int flags) +__bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, + struct bpf_object_open_opts *opts) { + const char *pin_root_path; + struct bpf_program *prog; struct bpf_object *obj; + const char *obj_name; + char tmp_name[64]; + bool relaxed_maps; + __u32 attach_prog_fd; int err; if (elf_version(EV_CURRENT) == EV_NONE) { - pr_warning("failed to init libelf for %s\n", path); + pr_warn("failed to init libelf for %s\n", + path ? : "(mem buf)"); return ERR_PTR(-LIBBPF_ERRNO__LIBELF); } - obj = bpf_object__new(path, obj_buf, obj_buf_sz); + if (!OPTS_VALID(opts, bpf_object_open_opts)) + return ERR_PTR(-EINVAL); + + obj_name = OPTS_GET(opts, object_name, NULL); + 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); + } + + obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); if (IS_ERR(obj)) return obj; + obj->relaxed_core_relocs = OPTS_GET(opts, relaxed_core_relocs, false); + relaxed_maps = OPTS_GET(opts, relaxed_maps, false); + pin_root_path = OPTS_GET(opts, pin_root_path, NULL); + attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); + CHECK_ERR(bpf_object__elf_init(obj), err, out); CHECK_ERR(bpf_object__check_endianness(obj), err, out); - CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out); + CHECK_ERR(bpf_object__probe_caps(obj), err, out); + CHECK_ERR(bpf_object__elf_collect(obj, relaxed_maps, pin_root_path), + err, out); CHECK_ERR(bpf_object__collect_reloc(obj), err, out); - CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out); - bpf_object__elf_finish(obj); + + bpf_object__for_each_program(prog, obj) { + enum bpf_prog_type prog_type; + enum bpf_attach_type attach_type; + + err = libbpf_prog_type_by_name(prog->section_name, &prog_type, + &attach_type); + if (err == -ESRCH) + /* couldn't guess, but user might manually specify */ + continue; + if (err) + goto out; + + bpf_program__set_type(prog, prog_type); + bpf_program__set_expected_attach_type(prog, attach_type); + if (prog_type == BPF_PROG_TYPE_TRACING) { + err = libbpf_find_attach_btf_id(prog->section_name, + attach_type, + attach_prog_fd); + if (err <= 0) + goto out; + prog->attach_btf_id = err; + prog->attach_prog_fd = attach_prog_fd; + } + } + return obj; out: bpf_object__close(obj); return ERR_PTR(err); } -struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr, - int flags) +static struct bpf_object * +__bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags) { + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, + .relaxed_maps = flags & MAPS_RELAX_COMPAT, + ); + /* param validation */ if (!attr->file) return NULL; pr_debug("loading %s\n", attr->file); - - return __bpf_object__open(attr->file, NULL, 0, - bpf_prog_type__needs_kver(attr->prog_type), - flags); + return __bpf_object__open(attr->file, NULL, 0, &opts); } struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) @@ -1769,27 +4030,42 @@ struct bpf_object *bpf_object__open(const char *path) return bpf_object__open_xattr(&attr); } -struct bpf_object *bpf_object__open_buffer(void *obj_buf, - size_t obj_buf_sz, - const char *name) +struct bpf_object * +bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts) { - char tmp_name[64]; + if (!path) + return ERR_PTR(-EINVAL); - /* param validation */ - if (!obj_buf || obj_buf_sz <= 0) - return NULL; + pr_debug("loading %s\n", path); - if (!name) { - snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx", - (unsigned long)obj_buf, - (unsigned long)obj_buf_sz); - tmp_name[sizeof(tmp_name) - 1] = '\0'; - name = tmp_name; - } - pr_debug("loading object '%s' from buffer\n", - name); + return __bpf_object__open(path, NULL, 0, opts); +} - return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true); +struct bpf_object * +bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, + struct bpf_object_open_opts *opts) +{ + if (!obj_buf || obj_buf_sz == 0) + return ERR_PTR(-EINVAL); + + return __bpf_object__open(NULL, obj_buf, obj_buf_sz, opts); +} + +struct bpf_object * +bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, + const char *name) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, + .object_name = name, + /* wrong default, but backwards-compatible */ + .relaxed_maps = true, + ); + + /* returning NULL is wrong, but backwards-compatible */ + if (!obj_buf || obj_buf_sz == 0) + return NULL; + + return bpf_object__open_mem(obj_buf, obj_buf_sz, &opts); } int bpf_object__unload(struct bpf_object *obj) @@ -1808,29 +4084,68 @@ int bpf_object__unload(struct bpf_object *obj) return 0; } -int bpf_object__load(struct bpf_object *obj) +int bpf_object__load_xattr(struct bpf_object_load_attr *attr) { - int err; + struct bpf_object *obj; + int err, i; + if (!attr) + return -EINVAL; + obj = attr->obj; if (!obj) return -EINVAL; if (obj->loaded) { - pr_warning("object should not be loaded twice\n"); + pr_warn("object should not be loaded twice\n"); return -EINVAL; } obj->loaded = true; - CHECK_ERR(bpf_object__probe_caps(obj), err, out); CHECK_ERR(bpf_object__create_maps(obj), err, out); - CHECK_ERR(bpf_object__relocate(obj), err, out); - CHECK_ERR(bpf_object__load_progs(obj), err, out); + CHECK_ERR(bpf_object__relocate(obj, attr->target_btf_path), err, out); + CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); return 0; out: + /* unpin any maps that were auto-pinned during load */ + for (i = 0; i < obj->nr_maps; i++) + if (obj->maps[i].pinned && !obj->maps[i].reused) + bpf_map__unpin(&obj->maps[i], NULL); + bpf_object__unload(obj); - pr_warning("failed to load object '%s'\n", obj->path); + pr_warn("failed to load object '%s'\n", obj->path); + return err; +} + +int bpf_object__load(struct bpf_object *obj) +{ + struct bpf_object_load_attr attr = { + .obj = obj, + }; + + return bpf_object__load_xattr(&attr); +} + +static int make_parent_dir(const char *path) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + char *dname, *dir; + int err = 0; + + dname = strdup(path); + if (dname == NULL) + return -ENOMEM; + + dir = dirname(dname); + if (mkdir(dir, 0700) && errno != EEXIST) + err = -errno; + + free(dname); + if (err) { + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warn("failed to mkdir %s: %s\n", path, cp); + } return err; } @@ -1851,13 +4166,13 @@ static int check_path(const char *path) dir = dirname(dname); if (statfs(dir, &st_fs)) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("failed to statfs %s: %s\n", dir, cp); + pr_warn("failed to statfs %s: %s\n", dir, cp); err = -errno; } free(dname); if (!err && st_fs.f_type != BPF_FS_MAGIC) { - pr_warning("specified path %s is not on BPF FS\n", path); + pr_warn("specified path %s is not on BPF FS\n", path); err = -EINVAL; } @@ -1870,24 +4185,28 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, char *cp, errmsg[STRERR_BUFSIZE]; int err; + err = make_parent_dir(path); + if (err) + return err; + err = check_path(path); if (err) return err; if (prog == NULL) { - pr_warning("invalid program pointer\n"); + pr_warn("invalid program pointer\n"); return -EINVAL; } if (instance < 0 || instance >= prog->instances.nr) { - pr_warning("invalid prog instance %d of prog %s (max %d)\n", - instance, prog->section_name, prog->instances.nr); + pr_warn("invalid prog instance %d of prog %s (max %d)\n", + instance, prog->section_name, prog->instances.nr); return -EINVAL; } if (bpf_obj_pin(prog->instances.fds[instance], path)) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("failed to pin program: %s\n", cp); + pr_warn("failed to pin program: %s\n", cp); return -errno; } pr_debug("pinned program '%s'\n", path); @@ -1905,13 +4224,13 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, return err; if (prog == NULL) { - pr_warning("invalid program pointer\n"); + pr_warn("invalid program pointer\n"); return -EINVAL; } if (instance < 0 || instance >= prog->instances.nr) { - pr_warning("invalid prog instance %d of prog %s (max %d)\n", - instance, prog->section_name, prog->instances.nr); + pr_warn("invalid prog instance %d of prog %s (max %d)\n", + instance, prog->section_name, prog->instances.nr); return -EINVAL; } @@ -1923,36 +4242,25 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, return 0; } -static int make_dir(const char *path) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - int err = 0; - - if (mkdir(path, 0700) && errno != EEXIST) - err = -errno; - - if (err) { - cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); - pr_warning("failed to mkdir %s: %s\n", path, cp); - } - return err; -} - int bpf_program__pin(struct bpf_program *prog, const char *path) { int i, err; + err = make_parent_dir(path); + if (err) + return err; + err = check_path(path); if (err) return err; if (prog == NULL) { - pr_warning("invalid program pointer\n"); + pr_warn("invalid program pointer\n"); return -EINVAL; } if (prog->instances.nr <= 0) { - pr_warning("no instances of prog %s to pin\n", + pr_warn("no instances of prog %s to pin\n", prog->section_name); return -EINVAL; } @@ -1962,10 +4270,6 @@ int bpf_program__pin(struct bpf_program *prog, const char *path) return bpf_program__pin_instance(prog, path, 0); } - err = make_dir(path); - if (err) - return err; - for (i = 0; i < prog->instances.nr; i++) { char buf[PATH_MAX]; int len; @@ -2014,12 +4318,12 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path) return err; if (prog == NULL) { - pr_warning("invalid program pointer\n"); + pr_warn("invalid program pointer\n"); return -EINVAL; } if (prog->instances.nr <= 0) { - pr_warning("no instances of prog %s to pin\n", + pr_warn("no instances of prog %s to pin\n", prog->section_name); return -EINVAL; } @@ -2056,47 +4360,123 @@ int bpf_map__pin(struct bpf_map *map, const char *path) char *cp, errmsg[STRERR_BUFSIZE]; int err; - err = check_path(path); - if (err) - return err; - if (map == NULL) { - pr_warning("invalid map pointer\n"); + pr_warn("invalid map pointer\n"); return -EINVAL; } - if (bpf_obj_pin(map->fd, path)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("failed to pin map: %s\n", cp); - return -errno; + if (map->pin_path) { + if (path && strcmp(path, map->pin_path)) { + pr_warn("map '%s' already has pin path '%s' different from '%s'\n", + bpf_map__name(map), map->pin_path, path); + return -EINVAL; + } else if (map->pinned) { + pr_debug("map '%s' already pinned at '%s'; not re-pinning\n", + bpf_map__name(map), map->pin_path); + return 0; + } + } else { + if (!path) { + pr_warn("missing a path to pin map '%s' at\n", + bpf_map__name(map)); + return -EINVAL; + } else if (map->pinned) { + pr_warn("map '%s' already pinned\n", bpf_map__name(map)); + return -EEXIST; + } + + map->pin_path = strdup(path); + if (!map->pin_path) { + err = -errno; + goto out_err; + } } - pr_debug("pinned map '%s'\n", path); + err = make_parent_dir(map->pin_path); + if (err) + return err; + + err = check_path(map->pin_path); + if (err) + return err; + + if (bpf_obj_pin(map->fd, map->pin_path)) { + err = -errno; + goto out_err; + } + + map->pinned = true; + pr_debug("pinned map '%s'\n", map->pin_path); return 0; + +out_err: + cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); + pr_warn("failed to pin map: %s\n", cp); + return err; } int bpf_map__unpin(struct bpf_map *map, const char *path) { int err; - err = check_path(path); - if (err) - return err; - if (map == NULL) { - pr_warning("invalid map pointer\n"); + pr_warn("invalid map pointer\n"); + return -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", + bpf_map__name(map), map->pin_path, path); + return -EINVAL; + } + path = map->pin_path; + } else if (!path) { + pr_warn("no path to unpin map '%s' from\n", + bpf_map__name(map)); return -EINVAL; } + err = check_path(path); + if (err) + return err; + err = unlink(path); if (err != 0) return -errno; - pr_debug("unpinned map '%s'\n", path); + + map->pinned = false; + pr_debug("unpinned map '%s' from '%s'\n", bpf_map__name(map), path); return 0; } +int bpf_map__set_pin_path(struct bpf_map *map, const char *path) +{ + char *new = NULL; + + if (path) { + new = strdup(path); + if (!new) + return -errno; + } + + free(map->pin_path); + map->pin_path = new; + return 0; +} + +const char *bpf_map__get_pin_path(const struct bpf_map *map) +{ + return map->pin_path; +} + +bool bpf_map__is_pinned(const struct bpf_map *map) +{ + return map->pinned; +} + int bpf_object__pin_maps(struct bpf_object *obj, const char *path) { struct bpf_map *map; @@ -2106,29 +4486,32 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) return -ENOENT; if (!obj->loaded) { - pr_warning("object not yet loaded; load it first\n"); + pr_warn("object not yet loaded; load it first\n"); return -ENOENT; } - err = make_dir(path); - if (err) - return err; - bpf_object__for_each_map(map, obj) { + char *pin_path = NULL; char buf[PATH_MAX]; - int len; - len = snprintf(buf, PATH_MAX, "%s/%s", path, - bpf_map__name(map)); - if (len < 0) { - err = -EINVAL; - goto err_unpin_maps; - } else if (len >= PATH_MAX) { - err = -ENAMETOOLONG; - goto err_unpin_maps; + if (path) { + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + bpf_map__name(map)); + if (len < 0) { + err = -EINVAL; + goto err_unpin_maps; + } else if (len >= PATH_MAX) { + err = -ENAMETOOLONG; + goto err_unpin_maps; + } + pin_path = buf; + } else if (!map->pin_path) { + continue; } - err = bpf_map__pin(map, buf); + err = bpf_map__pin(map, pin_path); if (err) goto err_unpin_maps; } @@ -2137,17 +4520,10 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) err_unpin_maps: while ((map = bpf_map__prev(map, obj))) { - char buf[PATH_MAX]; - int len; - - len = snprintf(buf, PATH_MAX, "%s/%s", path, - bpf_map__name(map)); - if (len < 0) - continue; - else if (len >= PATH_MAX) + if (!map->pin_path) continue; - bpf_map__unpin(map, buf); + bpf_map__unpin(map, NULL); } return err; @@ -2162,17 +4538,24 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) return -ENOENT; bpf_object__for_each_map(map, obj) { + char *pin_path = NULL; char buf[PATH_MAX]; - int len; - len = snprintf(buf, PATH_MAX, "%s/%s", path, - bpf_map__name(map)); - if (len < 0) - return -EINVAL; - else if (len >= PATH_MAX) - return -ENAMETOOLONG; + if (path) { + int len; + + len = snprintf(buf, PATH_MAX, "%s/%s", path, + bpf_map__name(map)); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + pin_path = buf; + } else if (!map->pin_path) { + continue; + } - err = bpf_map__unpin(map, buf); + err = bpf_map__unpin(map, pin_path); if (err) return err; } @@ -2189,14 +4572,10 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) return -ENOENT; if (!obj->loaded) { - pr_warning("object not yet loaded; load it first\n"); + pr_warn("object not yet loaded; load it first\n"); return -ENOENT; } - err = make_dir(path); - if (err) - return err; - bpf_object__for_each_program(prog, obj) { char buf[PATH_MAX]; int len; @@ -2297,12 +4676,16 @@ void bpf_object__close(struct bpf_object *obj) for (i = 0; i < obj->nr_maps; i++) { zfree(&obj->maps[i].name); + zfree(&obj->maps[i].pin_path); if (obj->maps[i].clear_priv) obj->maps[i].clear_priv(&obj->maps[i], obj->maps[i].priv); obj->maps[i].priv = NULL; obj->maps[i].clear_priv = NULL; } + + zfree(&obj->sections.rodata); + zfree(&obj->sections.data); zfree(&obj->maps); obj->nr_maps = 0; @@ -2335,17 +4718,17 @@ bpf_object__next(struct bpf_object *prev) return next; } -const char *bpf_object__name(struct bpf_object *obj) +const char *bpf_object__name(const struct bpf_object *obj) { - return obj ? obj->path : ERR_PTR(-EINVAL); + return obj ? obj->name : ERR_PTR(-EINVAL); } -unsigned int bpf_object__kversion(struct bpf_object *obj) +unsigned int bpf_object__kversion(const struct bpf_object *obj) { return obj ? obj->kern_version : 0; } -struct btf *bpf_object__btf(struct bpf_object *obj) +struct btf *bpf_object__btf(const struct bpf_object *obj) { return obj ? obj->btf : NULL; } @@ -2366,13 +4749,14 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv, return 0; } -void *bpf_object__priv(struct bpf_object *obj) +void *bpf_object__priv(const struct bpf_object *obj) { return obj ? obj->priv : ERR_PTR(-EINVAL); } static struct bpf_program * -__bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) +__bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, + bool forward) { size_t nr_programs = obj->nr_programs; ssize_t idx; @@ -2386,7 +4770,7 @@ __bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) &obj->programs[nr_programs - 1]; if (p->obj != obj) { - pr_warning("error: program handler doesn't match object\n"); + pr_warn("error: program handler doesn't match object\n"); return NULL; } @@ -2397,7 +4781,7 @@ __bpf_program__iter(struct bpf_program *p, struct bpf_object *obj, bool forward) } struct bpf_program * -bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) +bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj) { struct bpf_program *prog = prev; @@ -2409,7 +4793,7 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj) } struct bpf_program * -bpf_program__prev(struct bpf_program *next, struct bpf_object *obj) +bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj) { struct bpf_program *prog = next; @@ -2431,7 +4815,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv, return 0; } -void *bpf_program__priv(struct bpf_program *prog) +void *bpf_program__priv(const struct bpf_program *prog) { return prog ? prog->priv : ERR_PTR(-EINVAL); } @@ -2441,7 +4825,7 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) prog->prog_ifindex = ifindex; } -const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) +const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) { const char *title; @@ -2449,7 +4833,7 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) if (needs_copy) { title = strdup(title); if (!title) { - pr_warning("failed to strdup program title\n"); + pr_warn("failed to strdup program title\n"); return ERR_PTR(-ENOMEM); } } @@ -2457,11 +4841,16 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) return title; } -int bpf_program__fd(struct bpf_program *prog) +int bpf_program__fd(const struct bpf_program *prog) { return bpf_program__nth_fd(prog, 0); } +size_t bpf_program__size(const struct bpf_program *prog) +{ + return prog->insns_cnt * sizeof(struct bpf_insn); +} + int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, bpf_program_prep_t prep) { @@ -2471,13 +4860,13 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, return -EINVAL; if (prog->instances.nr > 0 || prog->instances.fds) { - pr_warning("Can't set pre-processor after loading\n"); + pr_warn("Can't set pre-processor after loading\n"); return -EINVAL; } instances_fds = malloc(sizeof(int) * nr_instances); if (!instances_fds) { - pr_warning("alloc memory failed for fds\n"); + pr_warn("alloc memory failed for fds\n"); return -ENOMEM; } @@ -2490,7 +4879,7 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, return 0; } -int bpf_program__nth_fd(struct bpf_program *prog, int n) +int bpf_program__nth_fd(const struct bpf_program *prog, int n) { int fd; @@ -2498,45 +4887,50 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n) return -EINVAL; if (n >= prog->instances.nr || n < 0) { - pr_warning("Can't get the %dth fd from program %s: only %d instances\n", - n, prog->section_name, prog->instances.nr); + pr_warn("Can't get the %dth fd from program %s: only %d instances\n", + n, prog->section_name, prog->instances.nr); return -EINVAL; } fd = prog->instances.fds[n]; if (fd < 0) { - pr_warning("%dth instance of program '%s' is invalid\n", - n, prog->section_name); + pr_warn("%dth instance of program '%s' is invalid\n", + n, prog->section_name); return -ENOENT; } return fd; } +enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog) +{ + return prog->type; +} + void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type) { prog->type = type; } -static bool bpf_program__is_type(struct bpf_program *prog, +static bool bpf_program__is_type(const struct bpf_program *prog, enum bpf_prog_type type) { return prog ? (prog->type == type) : false; } -#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ -int bpf_program__set_##NAME(struct bpf_program *prog) \ -{ \ - if (!prog) \ - return -EINVAL; \ - bpf_program__set_type(prog, TYPE); \ - return 0; \ -} \ - \ -bool bpf_program__is_##NAME(struct bpf_program *prog) \ -{ \ - return bpf_program__is_type(prog, TYPE); \ -} \ +#define BPF_PROG_TYPE_FNS(NAME, TYPE) \ +int bpf_program__set_##NAME(struct bpf_program *prog) \ +{ \ + if (!prog) \ + return -EINVAL; \ + bpf_program__set_type(prog, TYPE); \ + return 0; \ +} \ + \ +bool bpf_program__is_##NAME(const struct bpf_program *prog) \ +{ \ + return bpf_program__is_type(prog, TYPE); \ +} \ BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER); BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); @@ -2546,6 +4940,13 @@ BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); +BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING); + +enum bpf_attach_type +bpf_program__get_expected_attach_type(struct bpf_program *prog) +{ + return prog->expected_attach_type; +} void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type) @@ -2553,19 +4954,23 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, prog->expected_attach_type = type; } -#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \ - { string, sizeof(string) - 1, ptype, eatype, is_attachable, atype } +#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, btf, atype) \ + { string, sizeof(string) - 1, ptype, eatype, is_attachable, btf, atype } /* Programs that can NOT be attached. */ -#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0) +#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0) /* Programs that can be attached. */ #define BPF_APROG_SEC(string, ptype, atype) \ - BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype) + BPF_PROG_SEC_IMPL(string, ptype, 0, 1, 0, atype) /* Programs that must specify expected attach type at load time. */ #define BPF_EAPROG_SEC(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype) + BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, 0, eatype) + +/* Programs that use BTF to identify attach point */ +#define BPF_PROG_BTF(string, ptype, eatype) \ + BPF_PROG_SEC_IMPL(string, ptype, eatype, 0, 1, 0) /* Programs that can be attached but attach type can't be identified by section * name. Kept for backward compatibility. @@ -2577,16 +4982,27 @@ static const struct { size_t len; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; - int is_attachable; + bool is_attachable; + bool is_attach_btf; enum bpf_attach_type attach_type; } section_names[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("uretprobe/", BPF_PROG_TYPE_KPROBE), BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), + BPF_PROG_SEC("tp/", BPF_PROG_TYPE_TRACEPOINT), BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), + BPF_PROG_SEC("raw_tp/", BPF_PROG_TYPE_RAW_TRACEPOINT), + BPF_PROG_BTF("tp_btf/", BPF_PROG_TYPE_TRACING, + BPF_TRACE_RAW_TP), + BPF_PROG_BTF("fentry/", BPF_PROG_TYPE_TRACING, + BPF_TRACE_FENTRY), + BPF_PROG_BTF("fexit/", BPF_PROG_TYPE_TRACING, + BPF_TRACE_FEXIT), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), @@ -2631,6 +5047,16 @@ static const struct { BPF_CGROUP_UDP4_SENDMSG), BPF_EAPROG_SEC("cgroup/sendmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG), + BPF_EAPROG_SEC("cgroup/recvmsg4", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_UDP4_RECVMSG), + BPF_EAPROG_SEC("cgroup/recvmsg6", BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_CGROUP_UDP6_RECVMSG), + BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_CGROUP_SYSCTL), + BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_CGROUP_GETSOCKOPT), + BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_CGROUP_SETSOCKOPT), }; #undef BPF_PROG_SEC_IMPL @@ -2683,14 +5109,105 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, *expected_attach_type = section_names[i].expected_attach_type; return 0; } - pr_warning("failed to guess program type based on ELF section name '%s'\n", name); + pr_warn("failed to guess program type from ELF section '%s'\n", name); type_names = libbpf_get_type_names(false); if (type_names != NULL) { pr_info("supported section(type) names are:%s\n", type_names); free(type_names); } - return -EINVAL; + return -ESRCH; +} + +#define BTF_PREFIX "btf_trace_" +int libbpf_find_vmlinux_btf_id(const char *name, + enum bpf_attach_type attach_type) +{ + struct btf *btf = bpf_core_find_kernel_btf(); + char raw_tp_btf[128] = BTF_PREFIX; + char *dst = raw_tp_btf + sizeof(BTF_PREFIX) - 1; + const char *btf_name; + int err = -EINVAL; + __u32 kind; + + if (IS_ERR(btf)) { + pr_warn("vmlinux BTF is not found\n"); + return -EINVAL; + } + + if (attach_type == BPF_TRACE_RAW_TP) { + /* prepend "btf_trace_" prefix per kernel convention */ + strncat(dst, name, sizeof(raw_tp_btf) - sizeof(BTF_PREFIX)); + btf_name = raw_tp_btf; + kind = BTF_KIND_TYPEDEF; + } else { + btf_name = name; + kind = BTF_KIND_FUNC; + } + err = btf__find_by_name_kind(btf, btf_name, kind); + btf__free(btf); + return err; +} + +static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) +{ + struct bpf_prog_info_linear *info_linear; + struct bpf_prog_info *info; + struct btf *btf = NULL; + int err = -EINVAL; + + info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0); + if (IS_ERR_OR_NULL(info_linear)) { + pr_warn("failed get_prog_info_linear for FD %d\n", + attach_prog_fd); + return -EINVAL; + } + info = &info_linear->info; + if (!info->btf_id) { + pr_warn("The target program doesn't have BTF\n"); + goto out; + } + if (btf__get_from_id(info->btf_id, &btf)) { + pr_warn("Failed to get BTF of the program\n"); + goto out; + } + err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); + btf__free(btf); + if (err <= 0) { + pr_warn("%s is not found in prog's BTF\n", name); + goto out; + } +out: + free(info_linear); + return err; +} + +static int libbpf_find_attach_btf_id(const char *name, + enum bpf_attach_type attach_type, + __u32 attach_prog_fd) +{ + int i, err; + + if (!name) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(section_names); i++) { + if (!section_names[i].is_attach_btf) + continue; + if (strncmp(name, section_names[i].sec, section_names[i].len)) + continue; + if (attach_prog_fd) + err = libbpf_find_prog_btf_id(name + section_names[i].len, + attach_prog_fd); + else + err = libbpf_find_vmlinux_btf_id(name + section_names[i].len, + attach_type); + if (err <= 0) + pr_warn("%s is not found in vmlinux BTF\n", name); + return err; + } + pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name); + return -ESRCH; } int libbpf_attach_type_by_name(const char *name, @@ -2710,7 +5227,7 @@ int libbpf_attach_type_by_name(const char *name, *attach_type = section_names[i].attach_type; return 0; } - pr_warning("failed to guess attach type based on ELF section name '%s'\n", name); + pr_warn("failed to guess attach type based on ELF section name '%s'\n", name); type_names = libbpf_get_type_names(true); if (type_names != NULL) { pr_info("attachable section(type) names are:%s\n", type_names); @@ -2720,26 +5237,17 @@ int libbpf_attach_type_by_name(const char *name, return -EINVAL; } -static int -bpf_program__identify_section(struct bpf_program *prog, - enum bpf_prog_type *prog_type, - enum bpf_attach_type *expected_attach_type) -{ - return libbpf_prog_type_by_name(prog->section_name, prog_type, - expected_attach_type); -} - -int bpf_map__fd(struct bpf_map *map) +int bpf_map__fd(const struct bpf_map *map) { return map ? map->fd : -EINVAL; } -const struct bpf_map_def *bpf_map__def(struct bpf_map *map) +const struct bpf_map_def *bpf_map__def(const struct bpf_map *map) { return map ? &map->def : ERR_PTR(-EINVAL); } -const char *bpf_map__name(struct bpf_map *map) +const char *bpf_map__name(const struct bpf_map *map) { return map ? map->name : NULL; } @@ -2770,16 +5278,21 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv, return 0; } -void *bpf_map__priv(struct bpf_map *map) +void *bpf_map__priv(const struct bpf_map *map) { return map ? map->priv : ERR_PTR(-EINVAL); } -bool bpf_map__is_offload_neutral(struct bpf_map *map) +bool bpf_map__is_offload_neutral(const struct bpf_map *map) { return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } +bool bpf_map__is_internal(const struct bpf_map *map) +{ + return map->libbpf_type != LIBBPF_MAP_UNSPEC; +} + void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) { map->map_ifindex = ifindex; @@ -2788,11 +5301,11 @@ void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) { if (!bpf_map_type__is_map_in_map(map->def.type)) { - pr_warning("error: unsupported map type\n"); + pr_warn("error: unsupported map type\n"); return -EINVAL; } if (map->inner_map_fd != -1) { - pr_warning("error: inner_map_fd already specified\n"); + pr_warn("error: inner_map_fd already specified\n"); return -EINVAL; } map->inner_map_fd = fd; @@ -2800,7 +5313,7 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) } static struct bpf_map * -__bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) +__bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) { ssize_t idx; struct bpf_map *s, *e; @@ -2812,8 +5325,8 @@ __bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) e = obj->maps + obj->nr_maps; if ((m < s) || (m >= e)) { - pr_warning("error in %s: map handler doesn't belong to object\n", - __func__); + pr_warn("error in %s: map handler doesn't belong to object\n", + __func__); return NULL; } @@ -2824,7 +5337,7 @@ __bpf_map__iter(struct bpf_map *m, struct bpf_object *obj, int i) } struct bpf_map * -bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) +bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj) { if (prev == NULL) return obj->maps; @@ -2833,7 +5346,7 @@ bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) } struct bpf_map * -bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) +bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj) { if (next == NULL) { if (!obj->nr_maps) @@ -2845,7 +5358,7 @@ bpf_map__prev(struct bpf_map *next, struct bpf_object *obj) } struct bpf_map * -bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name) { struct bpf_map *pos; @@ -2857,7 +5370,7 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) } int -bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name) { return bpf_map__fd(bpf_object__find_map_by_name(obj, name)); } @@ -2865,20 +5378,12 @@ bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) { - int i; - - for (i = 0; i < obj->nr_maps; i++) { - if (obj->maps[i].offset == offset) - return &obj->maps[i]; - } - return ERR_PTR(-ENOENT); + return ERR_PTR(-ENOTSUP); } long libbpf_get_error(const void *ptr) { - if (IS_ERR(ptr)) - return PTR_ERR(ptr); - return 0; + return PTR_ERR_OR_ZERO(ptr); } int bpf_prog_load(const char *file, enum bpf_prog_type type, @@ -2897,13 +5402,8 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type, int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, struct bpf_object **pobj, int *prog_fd) { - struct bpf_object_open_attr open_attr = { - .file = attr->file, - .prog_type = attr->prog_type, - }; + struct bpf_object_open_attr open_attr = {}; struct bpf_program *prog, *first_prog = NULL; - enum bpf_attach_type expected_attach_type; - enum bpf_prog_type prog_type; struct bpf_object *obj; struct bpf_map *map; int err; @@ -2913,31 +5413,37 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, if (!attr->file) return -EINVAL; + open_attr.file = attr->file; + open_attr.prog_type = attr->prog_type; + obj = bpf_object__open_xattr(&open_attr); if (IS_ERR_OR_NULL(obj)) return -ENOENT; bpf_object__for_each_program(prog, obj) { + enum bpf_attach_type attach_type = attr->expected_attach_type; /* - * If type is not specified, try to guess it based on - * section name. + * to preserve backwards compatibility, bpf_prog_load treats + * attr->prog_type, if specified, as an override to whatever + * bpf_object__open guessed */ - prog_type = attr->prog_type; - prog->prog_ifindex = attr->ifindex; - expected_attach_type = attr->expected_attach_type; - if (prog_type == BPF_PROG_TYPE_UNSPEC) { - err = bpf_program__identify_section(prog, &prog_type, - &expected_attach_type); - if (err < 0) { - bpf_object__close(obj); - return -EINVAL; - } + if (attr->prog_type != BPF_PROG_TYPE_UNSPEC) { + bpf_program__set_type(prog, attr->prog_type); + bpf_program__set_expected_attach_type(prog, + attach_type); + } + if (bpf_program__get_type(prog) == BPF_PROG_TYPE_UNSPEC) { + /* + * we haven't guessed from section name and user + * didn't provide a fallback type, too bad... + */ + bpf_object__close(obj); + return -EINVAL; } - bpf_program__set_type(prog, prog_type); - bpf_program__set_expected_attach_type(prog, - expected_attach_type); - + prog->prog_ifindex = attr->ifindex; + prog->log_level = attr->log_level; + prog->prog_flags = attr->prog_flags; if (!first_prog) first_prog = prog; } @@ -2948,7 +5454,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, } if (!first_prog) { - pr_warning("object file doesn't contain bpf program\n"); + pr_warn("object file doesn't contain bpf program\n"); bpf_object__close(obj); return -ENOENT; } @@ -2964,6 +5470,402 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, return 0; } +struct bpf_link { + int (*destroy)(struct bpf_link *link); +}; + +int bpf_link__destroy(struct bpf_link *link) +{ + int err; + + if (!link) + return 0; + + err = link->destroy(link); + free(link); + + return err; +} + +struct bpf_link_fd { + struct bpf_link link; /* has to be at the top of struct */ + int fd; /* hook FD */ +}; + +static int bpf_link__destroy_perf_event(struct bpf_link *link) +{ + struct bpf_link_fd *l = (void *)link; + int err; + + err = ioctl(l->fd, PERF_EVENT_IOC_DISABLE, 0); + if (err) + err = -errno; + + close(l->fd); + return err; +} + +struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, + int pfd) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link_fd *link; + int prog_fd, err; + + if (pfd < 0) { + pr_warn("program '%s': invalid perf event FD %d\n", + bpf_program__title(prog, false), pfd); + return ERR_PTR(-EINVAL); + } + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("program '%s': can't attach BPF program w/o FD (did you load it?)\n", + bpf_program__title(prog, false)); + return ERR_PTR(-EINVAL); + } + + link = malloc(sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->link.destroy = &bpf_link__destroy_perf_event; + link->fd = pfd; + + if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { + err = -errno; + free(link); + pr_warn("program '%s': failed to attach to pfd %d: %s\n", + bpf_program__title(prog, false), pfd, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return ERR_PTR(err); + } + if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) { + err = -errno; + free(link); + pr_warn("program '%s': failed to enable pfd %d: %s\n", + bpf_program__title(prog, false), pfd, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return ERR_PTR(err); + } + return (struct bpf_link *)link; +} + +/* + * this function is expected to parse integer in the range of [0, 2^31-1] from + * given file using scanf format string fmt. If actual parsed value is + * negative, the result might be indistinguishable from error + */ +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"); + if (!f) { + err = -errno; + pr_debug("failed to open '%s': %s\n", file, + libbpf_strerror_r(err, buf, sizeof(buf))); + 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))); + fclose(f); + return err; + } + fclose(f); + return ret; +} + +static int determine_kprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/kprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_uprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_kprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/kprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +static int determine_uprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, + uint64_t offset, int pid) +{ + struct perf_event_attr attr = {}; + char errmsg[STRERR_BUFSIZE]; + int type, pfd, err; + + type = uprobe ? determine_uprobe_perf_type() + : determine_kprobe_perf_type(); + if (type < 0) { + pr_warn("failed to determine %s perf type: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(type, errmsg, sizeof(errmsg))); + return type; + } + if (retprobe) { + int bit = uprobe ? determine_uprobe_retprobe_bit() + : determine_kprobe_retprobe_bit(); + + if (bit < 0) { + pr_warn("failed to determine %s retprobe bit: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(bit, errmsg, sizeof(errmsg))); + return bit; + } + attr.config |= 1 << bit; + } + attr.size = sizeof(attr); + attr.type = type; + attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */ + attr.config2 = offset; /* kprobe_addr or probe_offset */ + + /* pid filter is meaningful only for uprobes */ + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid /* pid */, + pid == -1 ? 0 : -1 /* cpu */, + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("%s perf_event_open() failed: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + return pfd; +} + +struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, + bool retprobe, + const char *func_name) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int pfd, err; + + pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name, + 0 /* offset */, -1 /* pid */); + if (pfd < 0) { + pr_warn("program '%s': failed to create %s '%s' perf event: %s\n", + bpf_program__title(prog, false), + retprobe ? "kretprobe" : "kprobe", func_name, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link = bpf_program__attach_perf_event(prog, pfd); + if (IS_ERR(link)) { + close(pfd); + err = PTR_ERR(link); + pr_warn("program '%s': failed to attach to %s '%s': %s\n", + bpf_program__title(prog, false), + retprobe ? "kretprobe" : "kprobe", func_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return link; + } + return link; +} + +struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, + bool retprobe, pid_t pid, + const char *binary_path, + size_t func_offset) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int pfd, err; + + pfd = perf_event_open_probe(true /* uprobe */, retprobe, + binary_path, func_offset, pid); + if (pfd < 0) { + pr_warn("program '%s': failed to create %s '%s:0x%zx' perf event: %s\n", + bpf_program__title(prog, false), + retprobe ? "uretprobe" : "uprobe", + binary_path, func_offset, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link = bpf_program__attach_perf_event(prog, pfd); + if (IS_ERR(link)) { + close(pfd); + err = PTR_ERR(link); + pr_warn("program '%s': failed to attach to %s '%s:0x%zx': %s\n", + bpf_program__title(prog, false), + retprobe ? "uretprobe" : "uprobe", + binary_path, func_offset, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return link; + } + return link; +} + +static int determine_tracepoint_id(const char *tp_category, + const char *tp_name) +{ + char file[PATH_MAX]; + int ret; + + ret = snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s/id", + tp_category, tp_name); + if (ret < 0) + return -errno; + if (ret >= sizeof(file)) { + pr_debug("tracepoint %s/%s path is too long\n", + tp_category, tp_name); + return -E2BIG; + } + return parse_uint_from_file(file, "%d\n"); +} + +static int perf_event_open_tracepoint(const char *tp_category, + const char *tp_name) +{ + 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))); + return tp_id; + } + + attr.type = PERF_TYPE_TRACEPOINT; + attr.size = sizeof(attr); + attr.config = tp_id; + + pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu */, + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("tracepoint '%s/%s' perf_event_open() failed: %s\n", + tp_category, tp_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + return pfd; +} + +struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, + const char *tp_category, + const char *tp_name) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link *link; + int pfd, err; + + pfd = perf_event_open_tracepoint(tp_category, tp_name); + if (pfd < 0) { + pr_warn("program '%s': failed to create tracepoint '%s/%s' perf event: %s\n", + bpf_program__title(prog, false), + tp_category, tp_name, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link = bpf_program__attach_perf_event(prog, pfd); + if (IS_ERR(link)) { + close(pfd); + err = PTR_ERR(link); + pr_warn("program '%s': failed to attach to tracepoint '%s/%s': %s\n", + bpf_program__title(prog, false), + tp_category, tp_name, + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return link; + } + return link; +} + +static int bpf_link__destroy_fd(struct bpf_link *link) +{ + struct bpf_link_fd *l = (void *)link; + + return close(l->fd); +} + +struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, + const char *tp_name) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link_fd *link; + int prog_fd, pfd; + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("program '%s': can't attach before loaded\n", + bpf_program__title(prog, false)); + return ERR_PTR(-EINVAL); + } + + link = malloc(sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->link.destroy = &bpf_link__destroy_fd; + + pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); + if (pfd < 0) { + pfd = -errno; + free(link); + pr_warn("program '%s': failed to attach to raw tracepoint '%s': %s\n", + bpf_program__title(prog, false), tp_name, + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link->fd = pfd; + return (struct bpf_link *)link; +} + +struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) +{ + char errmsg[STRERR_BUFSIZE]; + struct bpf_link_fd *link; + int prog_fd, pfd; + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + pr_warn("program '%s': can't attach before loaded\n", + bpf_program__title(prog, false)); + return ERR_PTR(-EINVAL); + } + + link = malloc(sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->link.destroy = &bpf_link__destroy_fd; + + pfd = bpf_raw_tracepoint_open(NULL, prog_fd); + if (pfd < 0) { + pfd = -errno; + free(link); + pr_warn("program '%s': failed to attach to trace: %s\n", + bpf_program__title(prog, false), + libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); + return ERR_PTR(pfd); + } + link->fd = pfd; + return (struct bpf_link *)link; +} + enum bpf_perf_event_ret bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, @@ -3012,6 +5914,370 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, return ret; } +struct perf_buffer; + +struct perf_buffer_params { + struct perf_event_attr *attr; + /* if event_cb is specified, it takes precendence */ + perf_buffer_event_fn event_cb; + /* sample_cb and lost_cb are higher-level common-case callbacks */ + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; + int cpu_cnt; + int *cpus; + int *map_keys; +}; + +struct perf_cpu_buf { + struct perf_buffer *pb; + void *base; /* mmap()'ed memory */ + void *buf; /* for reconstructing segmented data */ + size_t buf_size; + int fd; + int cpu; + int map_key; +}; + +struct perf_buffer { + perf_buffer_event_fn event_cb; + perf_buffer_sample_fn sample_cb; + perf_buffer_lost_fn lost_cb; + void *ctx; /* passed into callbacks */ + + size_t page_size; + size_t mmap_size; + struct perf_cpu_buf **cpu_bufs; + struct epoll_event *events; + int cpu_cnt; + int epoll_fd; /* perf event FD */ + int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */ +}; + +static void perf_buffer__free_cpu_buf(struct perf_buffer *pb, + struct perf_cpu_buf *cpu_buf) +{ + if (!cpu_buf) + return; + if (cpu_buf->base && + munmap(cpu_buf->base, pb->mmap_size + pb->page_size)) + pr_warn("failed to munmap cpu_buf #%d\n", cpu_buf->cpu); + if (cpu_buf->fd >= 0) { + ioctl(cpu_buf->fd, PERF_EVENT_IOC_DISABLE, 0); + close(cpu_buf->fd); + } + free(cpu_buf->buf); + free(cpu_buf); +} + +void perf_buffer__free(struct perf_buffer *pb) +{ + int i; + + if (!pb) + return; + if (pb->cpu_bufs) { + for (i = 0; i < pb->cpu_cnt && pb->cpu_bufs[i]; i++) { + struct perf_cpu_buf *cpu_buf = pb->cpu_bufs[i]; + + bpf_map_delete_elem(pb->map_fd, &cpu_buf->map_key); + perf_buffer__free_cpu_buf(pb, cpu_buf); + } + free(pb->cpu_bufs); + } + if (pb->epoll_fd >= 0) + close(pb->epoll_fd); + free(pb->events); + free(pb); +} + +static struct perf_cpu_buf * +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)); + if (!cpu_buf) + return ERR_PTR(-ENOMEM); + + cpu_buf->pb = pb; + cpu_buf->cpu = cpu; + cpu_buf->map_key = map_key; + + cpu_buf->fd = syscall(__NR_perf_event_open, attr, -1 /* pid */, cpu, + -1, PERF_FLAG_FD_CLOEXEC); + 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))); + goto error; + } + + cpu_buf->base = mmap(NULL, pb->mmap_size + pb->page_size, + PROT_READ | PROT_WRITE, MAP_SHARED, + cpu_buf->fd, 0); + if (cpu_buf->base == MAP_FAILED) { + 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))); + 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))); + goto error; + } + + return cpu_buf; + +error: + perf_buffer__free_cpu_buf(pb, cpu_buf); + return (struct perf_cpu_buf *)ERR_PTR(err); +} + +static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, + struct perf_buffer_params *p); + +struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts) +{ + struct perf_buffer_params p = {}; + struct perf_event_attr attr = { 0, }; + + 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; + + p.attr = &attr; + p.sample_cb = opts ? opts->sample_cb : NULL; + p.lost_cb = opts ? opts->lost_cb : NULL; + p.ctx = opts ? opts->ctx : NULL; + + return __perf_buffer__new(map_fd, page_cnt, &p); +} + +struct perf_buffer * +perf_buffer__new_raw(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts) +{ + struct perf_buffer_params p = {}; + + p.attr = opts->attr; + p.event_cb = opts->event_cb; + p.ctx = opts->ctx; + p.cpu_cnt = opts->cpu_cnt; + p.cpus = opts->cpus; + p.map_keys = opts->map_keys; + + return __perf_buffer__new(map_fd, page_cnt, &p); +} + +static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, + struct perf_buffer_params *p) +{ + struct bpf_map_info map = {}; + char msg[STRERR_BUFSIZE]; + struct perf_buffer *pb; + __u32 map_info_len; + int err, i; + + if (page_cnt & (page_cnt - 1)) { + pr_warn("page count should be power of two, but is %zu\n", + page_cnt); + return ERR_PTR(-EINVAL); + } + + map_info_len = sizeof(map); + err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len); + if (err) { + err = -errno; + pr_warn("failed to get map info for map FD %d: %s\n", + map_fd, libbpf_strerror_r(err, msg, sizeof(msg))); + return ERR_PTR(err); + } + + if (map.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + pr_warn("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", + map.name); + return ERR_PTR(-EINVAL); + } + + pb = calloc(1, sizeof(*pb)); + if (!pb) + return ERR_PTR(-ENOMEM); + + pb->event_cb = p->event_cb; + pb->sample_cb = p->sample_cb; + pb->lost_cb = p->lost_cb; + pb->ctx = p->ctx; + + pb->page_size = getpagesize(); + pb->mmap_size = pb->page_size * page_cnt; + pb->map_fd = map_fd; + + pb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); + if (pb->epoll_fd < 0) { + err = -errno; + pr_warn("failed to create epoll instance: %s\n", + libbpf_strerror_r(err, msg, sizeof(msg))); + goto error; + } + + if (p->cpu_cnt > 0) { + pb->cpu_cnt = p->cpu_cnt; + } else { + pb->cpu_cnt = libbpf_num_possible_cpus(); + if (pb->cpu_cnt < 0) { + err = pb->cpu_cnt; + goto error; + } + if (map.max_entries < pb->cpu_cnt) + pb->cpu_cnt = map.max_entries; + } + + pb->events = calloc(pb->cpu_cnt, sizeof(*pb->events)); + if (!pb->events) { + err = -ENOMEM; + pr_warn("failed to allocate events: out of memory\n"); + goto error; + } + pb->cpu_bufs = calloc(pb->cpu_cnt, sizeof(*pb->cpu_bufs)); + if (!pb->cpu_bufs) { + err = -ENOMEM; + pr_warn("failed to allocate buffers: out of memory\n"); + goto error; + } + + for (i = 0; i < pb->cpu_cnt; i++) { + struct perf_cpu_buf *cpu_buf; + int cpu, map_key; + + cpu = p->cpu_cnt > 0 ? p->cpus[i] : i; + map_key = p->cpu_cnt > 0 ? p->map_keys[i] : i; + + cpu_buf = perf_buffer__open_cpu_buf(pb, p->attr, cpu, map_key); + if (IS_ERR(cpu_buf)) { + err = PTR_ERR(cpu_buf); + goto error; + } + + pb->cpu_bufs[i] = cpu_buf; + + err = bpf_map_update_elem(pb->map_fd, &map_key, + &cpu_buf->fd, 0); + if (err) { + 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))); + goto error; + } + + pb->events[i].events = EPOLLIN; + pb->events[i].data.ptr = cpu_buf; + if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd, + &pb->events[i]) < 0) { + 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))); + goto error; + } + } + + return pb; + +error: + if (pb) + perf_buffer__free(pb); + return ERR_PTR(err); +} + +struct perf_sample_raw { + struct perf_event_header header; + uint32_t size; + char data[0]; +}; + +struct perf_sample_lost { + struct perf_event_header header; + uint64_t id; + uint64_t lost; + uint64_t sample_id; +}; + +static enum bpf_perf_event_ret +perf_buffer__process_record(struct perf_event_header *e, void *ctx) +{ + struct perf_cpu_buf *cpu_buf = ctx; + struct perf_buffer *pb = cpu_buf->pb; + void *data = e; + + /* user wants full control over parsing perf event */ + if (pb->event_cb) + return pb->event_cb(pb->ctx, cpu_buf->cpu, e); + + switch (e->type) { + case PERF_RECORD_SAMPLE: { + struct perf_sample_raw *s = data; + + if (pb->sample_cb) + pb->sample_cb(pb->ctx, cpu_buf->cpu, s->data, s->size); + break; + } + case PERF_RECORD_LOST: { + struct perf_sample_lost *s = data; + + if (pb->lost_cb) + pb->lost_cb(pb->ctx, cpu_buf->cpu, s->lost); + break; + } + default: + pr_warn("unknown perf sample type %d\n", e->type); + return LIBBPF_PERF_EVENT_ERROR; + } + return LIBBPF_PERF_EVENT_CONT; +} + +static int perf_buffer__process_records(struct perf_buffer *pb, + struct perf_cpu_buf *cpu_buf) +{ + enum bpf_perf_event_ret ret; + + ret = bpf_perf_event_read_simple(cpu_buf->base, pb->mmap_size, + pb->page_size, &cpu_buf->buf, + &cpu_buf->buf_size, + perf_buffer__process_record, cpu_buf); + if (ret != LIBBPF_PERF_EVENT_CONT) + return ret; + return 0; +} + +int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) +{ + int i, cnt, err; + + cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms); + for (i = 0; i < cnt; i++) { + struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr; + + err = perf_buffer__process_records(pb, cpu_buf); + if (err) { + pr_warn("error while processing records: %d\n", err); + return err; + } + } + return cnt < 0 ? -errno : cnt; +} + struct bpf_prog_info_array_desc { int array_offset; /* e.g. offset of jited_prog_insns */ int count_offset; /* e.g. offset of jited_prog_len */ @@ -3069,7 +6335,8 @@ static struct bpf_prog_info_array_desc bpf_prog_info_array_desc[] = { }; -static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, int offset) +static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, + int offset) { __u32 *array = (__u32 *)info; @@ -3078,7 +6345,8 @@ static __u32 bpf_prog_info_read_offset_u32(struct bpf_prog_info *info, int offse return -(int)offset; } -static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, int offset) +static __u64 bpf_prog_info_read_offset_u64(struct bpf_prog_info *info, + int offset) { __u64 *array = (__u64 *)info; @@ -3202,13 +6470,13 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays) v2 = bpf_prog_info_read_offset_u32(&info_linear->info, desc->count_offset); if (v1 != v2) - pr_warning("%s: mismatch in element count\n", __func__); + pr_warn("%s: mismatch in element count\n", __func__); v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset); v2 = bpf_prog_info_read_offset_u32(&info_linear->info, desc->size_offset); if (v1 != v2) - pr_warning("%s: mismatch in rec size\n", __func__); + pr_warn("%s: mismatch in rec size\n", __func__); } /* step 7: update info_len and data_len */ @@ -3257,3 +6525,63 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) desc->array_offset, addr); } } + +int libbpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + int len = 0, n = 0, il = 0, ir = 0; + unsigned int start = 0, end = 0; + int tmp_cpus = 0; + static int cpus; + char buf[128]; + int error = 0; + int fd = -1; + + tmp_cpus = READ_ONCE(cpus); + if (tmp_cpus > 0) + return tmp_cpus; + + fd = open(fcpu, O_RDONLY); + if (fd < 0) { + error = errno; + pr_warn("Failed to open file %s: %s\n", fcpu, strerror(error)); + return -error; + } + len = read(fd, buf, sizeof(buf)); + close(fd); + if (len <= 0) { + error = len ? errno : EINVAL; + pr_warn("Failed to read # of possible cpus from %s: %s\n", + fcpu, strerror(error)); + return -error; + } + if (len == sizeof(buf)) { + pr_warn("File %s size overflow\n", fcpu); + return -EOVERFLOW; + } + buf[len] = '\0'; + + for (ir = 0, tmp_cpus = 0; ir <= len; ir++) { + /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ + if (buf[ir] == ',' || buf[ir] == '\0') { + buf[ir] = '\0'; + n = sscanf(&buf[il], "%u-%u", &start, &end); + if (n <= 0) { + pr_warn("Failed to get # CPUs from %s\n", + &buf[il]); + return -EINVAL; + } else if (n == 1) { + end = start; + } + tmp_cpus += end - start + 1; + il = ir + 1; + } + } + if (tmp_cpus <= 0) { + pr_warn("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu); + return -EINVAL; + } + + WRITE_ONCE(cpus, tmp_cpus); + return tmp_cpus; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index c70785cc8ef5..0dbf4bfba0c4 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -57,7 +57,7 @@ enum libbpf_print_level { typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, const char *, va_list ap); -LIBBPF_API void libbpf_set_print(libbpf_print_fn_t fn); +LIBBPF_API libbpf_print_fn_t libbpf_set_print(libbpf_print_fn_t fn); /* Hide internal to user */ struct bpf_object; @@ -67,14 +67,80 @@ struct bpf_object_open_attr { enum bpf_prog_type prog_type; }; +/* Helper macro to declare and initialize libbpf options struct + * + * This dance with uninitialized declaration, followed by memset to zero, + * followed by assignment using compound literal syntax is done to preserve + * ability to use a nice struct field initialization syntax and **hopefully** + * have all the padding bytes initialized to zero. It's not guaranteed though, + * when copying literal, that compiler won't copy garbage in literal's padding + * bytes, but that's the best way I've found and it seems to work in practice. + * + * Macro declares opts struct of given type and name, zero-initializes, + * including any extra padding, it with memset() and then assigns initial + * values provided by users in struct initializer-syntax as varargs. + */ +#define DECLARE_LIBBPF_OPTS(TYPE, NAME, ...) \ + struct TYPE NAME = ({ \ + memset(&NAME, 0, sizeof(struct TYPE)); \ + (struct TYPE) { \ + .sz = sizeof(struct TYPE), \ + __VA_ARGS__ \ + }; \ + }) + +struct bpf_object_open_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* object name override, if provided: + * - for object open from file, this will override setting object + * name from file path's base name; + * - for object open from memory buffer, this will specify an object + * name and will override default "<addr>-<buf-size>" name; + */ + const char *object_name; + /* parse map definitions non-strictly, allowing extra attributes/data */ + bool relaxed_maps; + /* process CO-RE relocations non-strictly, allowing them to fail */ + bool relaxed_core_relocs; + /* maps that set the 'pinning' attribute in their definition will have + * their pin_path attribute set to a file in this directory, and be + * auto-pinned to that path on load; defaults to "/sys/fs/bpf". + */ + const char *pin_root_path; + __u32 attach_prog_fd; +}; +#define bpf_object_open_opts__last_field attach_prog_fd + LIBBPF_API struct bpf_object *bpf_object__open(const char *path); LIBBPF_API struct bpf_object * +bpf_object__open_file(const char *path, struct bpf_object_open_opts *opts); +LIBBPF_API struct bpf_object * +bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, + struct bpf_object_open_opts *opts); + +/* deprecated bpf_object__open variants */ +LIBBPF_API struct bpf_object * +bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, + const char *name); +LIBBPF_API struct bpf_object * bpf_object__open_xattr(struct bpf_object_open_attr *attr); -struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr, - int flags); -LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf, - size_t obj_buf_sz, - const char *name); + +int bpf_object__section_size(const struct bpf_object *obj, const char *name, + __u32 *size); +int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, + __u32 *off); + +enum libbpf_pin_type { + LIBBPF_PIN_NONE, + /* PIN_BY_NAME: pin maps by name (in /sys/fs/bpf by default) */ + LIBBPF_PIN_BY_NAME, +}; + +/* 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). + */ LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path); LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj, const char *path); @@ -85,18 +151,26 @@ LIBBPF_API int bpf_object__unpin_programs(struct bpf_object *obj, LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path); LIBBPF_API void bpf_object__close(struct bpf_object *object); +struct bpf_object_load_attr { + struct bpf_object *obj; + int log_level; + const char *target_btf_path; +}; + /* Load/unload object into/from kernel */ LIBBPF_API int bpf_object__load(struct bpf_object *obj); +LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); LIBBPF_API int bpf_object__unload(struct bpf_object *obj); -LIBBPF_API const char *bpf_object__name(struct bpf_object *obj); -LIBBPF_API unsigned int bpf_object__kversion(struct bpf_object *obj); +LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj); +LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); struct btf; -LIBBPF_API struct btf *bpf_object__btf(struct bpf_object *obj); +LIBBPF_API struct btf *bpf_object__btf(const struct bpf_object *obj); LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); LIBBPF_API struct bpf_program * -bpf_object__find_program_by_title(struct bpf_object *obj, const char *title); +bpf_object__find_program_by_title(const struct bpf_object *obj, + const char *title); LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ @@ -108,18 +182,20 @@ LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *); LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv); -LIBBPF_API void *bpf_object__priv(struct bpf_object *prog); +LIBBPF_API void *bpf_object__priv(const struct bpf_object *prog); LIBBPF_API int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, enum bpf_attach_type *expected_attach_type); LIBBPF_API int libbpf_attach_type_by_name(const char *name, enum bpf_attach_type *attach_type); +LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name, + enum bpf_attach_type attach_type); /* Accessors of bpf_program */ struct bpf_program; LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog, - struct bpf_object *obj); + const struct bpf_object *obj); #define bpf_object__for_each_program(pos, obj) \ for ((pos) = bpf_program__next(NULL, (obj)); \ @@ -127,24 +203,26 @@ LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog, (pos) = bpf_program__next((pos), (obj))) LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog, - struct bpf_object *obj); + const struct bpf_object *obj); -typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, - void *); +typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv, bpf_program_clear_priv_t clear_priv); -LIBBPF_API void *bpf_program__priv(struct bpf_program *prog); +LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); -LIBBPF_API const char *bpf_program__title(struct bpf_program *prog, +LIBBPF_API const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy); +/* returns program size in bytes */ +LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog); + LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_version); -LIBBPF_API int bpf_program__fd(struct bpf_program *prog); +LIBBPF_API int bpf_program__fd(const struct bpf_program *prog); LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog, const char *path, int instance); @@ -155,6 +233,29 @@ LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); LIBBPF_API int bpf_program__unpin(struct bpf_program *prog, const char *path); LIBBPF_API void bpf_program__unload(struct bpf_program *prog); +struct bpf_link; + +LIBBPF_API int bpf_link__destroy(struct bpf_link *link); + +LIBBPF_API struct bpf_link * +bpf_program__attach_perf_event(struct bpf_program *prog, int pfd); +LIBBPF_API struct bpf_link * +bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe, + const char *func_name); +LIBBPF_API struct bpf_link * +bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe, + pid_t pid, const char *binary_path, + size_t func_offset); +LIBBPF_API struct bpf_link * +bpf_program__attach_tracepoint(struct bpf_program *prog, + const char *tp_category, + const char *tp_name); +LIBBPF_API struct bpf_link * +bpf_program__attach_raw_tracepoint(struct bpf_program *prog, + const char *tp_name); + +LIBBPF_API struct bpf_link * +bpf_program__attach_trace(struct bpf_program *prog); struct bpf_insn; /* @@ -217,7 +318,7 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, bpf_program_prep_t prep); -LIBBPF_API int bpf_program__nth_fd(struct bpf_program *prog, int n); +LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n); /* * Adjust type of BPF program. Default is kprobe. @@ -230,20 +331,27 @@ LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog); LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog); + +LIBBPF_API enum bpf_prog_type bpf_program__get_type(struct bpf_program *prog); LIBBPF_API void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); + +LIBBPF_API enum bpf_attach_type +bpf_program__get_expected_attach_type(struct bpf_program *prog); LIBBPF_API void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type); -LIBBPF_API bool bpf_program__is_socket_filter(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_tracepoint(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_raw_tracepoint(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_kprobe(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_sched_cls(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_sched_act(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_xdp(struct bpf_program *prog); -LIBBPF_API bool bpf_program__is_perf_event(struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_kprobe(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog); /* * No need for __attribute__((packed)), all members of 'bpf_map_def' @@ -265,10 +373,10 @@ struct bpf_map_def { */ struct bpf_map; LIBBPF_API struct bpf_map * -bpf_object__find_map_by_name(struct bpf_object *obj, const char *name); +bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); LIBBPF_API int -bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name); +bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name); /* * Get bpf_map through the offset of corresponding struct bpf_map_def @@ -278,7 +386,7 @@ LIBBPF_API struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); LIBBPF_API struct bpf_map * -bpf_map__next(struct bpf_map *map, struct bpf_object *obj); +bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj); #define bpf_object__for_each_map(pos, obj) \ for ((pos) = bpf_map__next(NULL, (obj)); \ (pos) != NULL; \ @@ -286,22 +394,26 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); #define bpf_map__for_each bpf_object__for_each_map LIBBPF_API struct bpf_map * -bpf_map__prev(struct bpf_map *map, struct bpf_object *obj); +bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj); -LIBBPF_API int bpf_map__fd(struct bpf_map *map); -LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map); -LIBBPF_API const char *bpf_map__name(struct bpf_map *map); +LIBBPF_API int bpf_map__fd(const struct bpf_map *map); +LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); +LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv); -LIBBPF_API void *bpf_map__priv(struct bpf_map *map); +LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); -LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map); +LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); +LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); +LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); +LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map); +LIBBPF_API bool bpf_map__is_pinned(const struct bpf_map *map); LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path); @@ -314,6 +426,8 @@ struct bpf_prog_load_attr { enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; int ifindex; + int log_level; + int prog_flags; }; LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, @@ -321,8 +435,38 @@ LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd); +struct xdp_link_info { + __u32 prog_id; + __u32 drv_prog_id; + __u32 hw_prog_id; + __u32 skb_prog_id; + __u8 attach_mode; +}; + LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); +LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, + size_t info_size, __u32 flags); + +struct perf_buffer; + +typedef void (*perf_buffer_sample_fn)(void *ctx, int cpu, + void *data, __u32 size); +typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); + +/* common use perf buffer options */ +struct perf_buffer_opts { + /* if specified, sample_cb is called for each sample */ + perf_buffer_sample_fn sample_cb; + /* if specified, lost_cb is called for each batch of lost samples */ + perf_buffer_lost_fn lost_cb; + /* ctx is provided to sample_cb and lost_cb */ + void *ctx; +}; + +LIBBPF_API struct perf_buffer * +perf_buffer__new(int map_fd, size_t page_cnt, + const struct perf_buffer_opts *opts); enum bpf_perf_event_ret { LIBBPF_PERF_EVENT_DONE = 0, @@ -331,6 +475,35 @@ enum bpf_perf_event_ret { }; struct perf_event_header; + +typedef enum bpf_perf_event_ret +(*perf_buffer_event_fn)(void *ctx, int cpu, struct perf_event_header *event); + +/* raw perf buffer options, giving most power and control */ +struct perf_buffer_raw_opts { + /* perf event attrs passed directly into perf_event_open() */ + struct perf_event_attr *attr; + /* raw event callback */ + perf_buffer_event_fn event_cb; + /* ctx is provided to event_cb */ + void *ctx; + /* if cpu_cnt == 0, open all on all possible CPUs (up to the number of + * max_entries of given PERF_EVENT_ARRAY map) + */ + int cpu_cnt; + /* if cpu_cnt > 0, cpus is an array of CPUs to open ring buffers on */ + int *cpus; + /* if cpu_cnt > 0, map_keys specify map keys to set per-CPU FDs for */ + int *map_keys; +}; + +LIBBPF_API struct perf_buffer * +perf_buffer__new_raw(int map_fd, size_t page_cnt, + const struct perf_buffer_raw_opts *opts); + +LIBBPF_API void perf_buffer__free(struct perf_buffer *pb); +LIBBPF_API int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms); + typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(struct perf_event_header *hdr, void *private_data); @@ -441,6 +614,22 @@ bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear); LIBBPF_API void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); +/* + * A helper function to get the number of possible CPUs before looking up + * per-CPU maps. Negative errno is returned on failure. + * + * Example usage: + * + * int ncpus = libbpf_num_possible_cpus(); + * if (ncpus < 0) { + * // error handling + * } + * long values[ncpus]; + * bpf_map_lookup_elem(per_cpu_map_fd, key, values); + * + */ +LIBBPF_API int libbpf_num_possible_cpus(void); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f3ce50500cf2..8ddc2c40e482 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -157,3 +157,54 @@ LIBBPF_0.0.2 { bpf_program__bpil_addr_to_offs; bpf_program__bpil_offs_to_addr; } LIBBPF_0.0.1; + +LIBBPF_0.0.3 { + global: + bpf_map__is_internal; + bpf_map_freeze; + btf__finalize_data; +} LIBBPF_0.0.2; + +LIBBPF_0.0.4 { + global: + bpf_link__destroy; + bpf_object__load_xattr; + bpf_program__attach_kprobe; + bpf_program__attach_perf_event; + bpf_program__attach_raw_tracepoint; + bpf_program__attach_tracepoint; + bpf_program__attach_uprobe; + btf_dump__dump_type; + btf_dump__free; + btf_dump__new; + btf__parse_elf; + libbpf_num_possible_cpus; + perf_buffer__free; + perf_buffer__new; + perf_buffer__new_raw; + perf_buffer__poll; + xsk_umem__create; +} LIBBPF_0.0.3; + +LIBBPF_0.0.5 { + global: + bpf_btf_get_next_id; +} LIBBPF_0.0.4; + +LIBBPF_0.0.6 { + global: + bpf_get_link_xdp_info; + bpf_map__get_pin_path; + bpf_map__is_pinned; + bpf_map__set_pin_path; + bpf_object__open_file; + bpf_object__open_mem; + bpf_program__attach_trace; + bpf_program__get_expected_attach_type; + bpf_program__get_type; + bpf_program__is_tracing; + bpf_program__set_tracing; + bpf_program__size; + btf__find_by_name_kind; + libbpf_find_vmlinux_btf_id; +} LIBBPF_0.0.5; diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template new file mode 100644 index 000000000000..ac17fcef2108 --- /dev/null +++ b/tools/lib/bpf/libbpf.pc.template @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +prefix=@PREFIX@ +libdir=@LIBDIR@ +includedir=${prefix}/include + +Name: libbpf +Description: BPF library +Version: @VERSION@ +Libs: -L${libdir} -lbpf +Requires.private: libelf +Cflags: -I${includedir} diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h new file mode 100644 index 000000000000..97ac17a64a58 --- /dev/null +++ b/tools/lib/bpf/libbpf_internal.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Internal libbpf helpers. + * + * Copyright (c) 2019 Facebook + */ + +#ifndef __LIBBPF_LIBBPF_INTERNAL_H +#define __LIBBPF_LIBBPF_INTERNAL_H + +#include "libbpf.h" + +#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) +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) +#define BTF_MEMBER_ENC(name, type, bits_offset) (name), (type), (bits_offset) +#define BTF_PARAM_ENC(name, type) (name), (type) +#define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) + +#ifndef min +# define min(x, y) ((x) < (y) ? (x) : (y)) +#endif +#ifndef max +# define max(x, y) ((x) < (y) ? (y) : (x)) +#endif +#ifndef offsetofend +# define offsetofend(TYPE, FIELD) \ + (offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD)) +#endif + +/* Symbol versioning is different between static and shared library. + * Properly versioned symbols are needed for shared library, but + * only the symbol of the new version is needed for static library. + */ +#ifdef SHARED +# define COMPAT_VERSION(internal_name, api_name, version) \ + asm(".symver " #internal_name "," #api_name "@" #version); +# define DEFAULT_VERSION(internal_name, api_name, version) \ + asm(".symver " #internal_name "," #api_name "@@" #version); +#else +# define COMPAT_VERSION(internal_name, api_name, version) +# define DEFAULT_VERSION(internal_name, api_name, version) \ + extern typeof(internal_name) api_name \ + __attribute__((alias(#internal_name))); +#endif + +extern void libbpf_print(enum libbpf_print_level level, + const char *format, ...) + __attribute__((format(printf, 2, 3))); + +#define __pr(level, fmt, ...) \ +do { \ + libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \ +} while (0) + +#define pr_warn(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__) +#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) +#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) + +static inline bool libbpf_validate_opts(const char *opts, + size_t opts_sz, size_t user_sz, + const char *type_name) +{ + if (user_sz < sizeof(size_t)) { + pr_warn("%s size (%zu) is too small\n", type_name, user_sz); + return false; + } + if (user_sz > opts_sz) { + size_t i; + + for (i = opts_sz; i < user_sz; i++) { + if (opts[i]) { + pr_warn("%s has non-zero extra bytes", + type_name); + return false; + } + } + } + return true; +} + +#define OPTS_VALID(opts, type) \ + (!(opts) || libbpf_validate_opts((const char *)opts, \ + offsetofend(struct type, \ + type##__last_field), \ + (opts)->sz, #type)) +#define OPTS_HAS(opts, field) \ + ((opts) && opts->sz >= offsetofend(typeof(*(opts)), field)) +#define OPTS_GET(opts, field, fallback_value) \ + (OPTS_HAS(opts, field) ? (opts)->field : fallback_value) + +int libbpf__load_raw_btf(const char *raw_types, size_t types_len, + const char *str_sec, size_t str_len); + +struct btf_ext_info { + /* + * info points to the individual info section (e.g. func_info and + * line_info) from the .BTF.ext. It does not include the __u32 rec_size. + */ + void *info; + __u32 rec_size; + __u32 len; +}; + +#define for_each_btf_ext_sec(seg, sec) \ + for (sec = (seg)->info; \ + (void *)sec < (seg)->info + (seg)->len; \ + sec = (void *)sec + sizeof(struct btf_ext_info_sec) + \ + (seg)->rec_size * sec->num_info) + +#define for_each_btf_ext_rec(seg, sec, i, rec) \ + for (i = 0, rec = (void *)&(sec)->data; \ + i < (sec)->num_info; \ + i++, rec = (void *)rec + (seg)->rec_size) + +struct btf_ext { + union { + struct btf_ext_header *hdr; + void *data; + }; + struct btf_ext_info func_info; + struct btf_ext_info line_info; + struct btf_ext_info field_reloc_info; + __u32 data_size; +}; + +struct btf_ext_info_sec { + __u32 sec_name_off; + __u32 num_info; + /* Followed by num_info * record_size number of bytes */ + __u8 data[0]; +}; + +/* The minimum bpf_func_info checked by the loader */ +struct bpf_func_info_min { + __u32 insn_off; + __u32 type_id; +}; + +/* The minimum bpf_line_info checked by the loader */ +struct bpf_line_info_min { + __u32 insn_off; + __u32 file_name_off; + __u32 line_off; + __u32 line_col; +}; + +/* bpf_field_info_kind encodes which aspect of captured field has to be + * adjusted by relocations. Currently supported values are: + * - BPF_FIELD_BYTE_OFFSET: field offset (in bytes); + * - BPF_FIELD_EXISTS: field existence (1, if field exists; 0, otherwise); + */ +enum bpf_field_info_kind { + BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_FIELD_BYTE_SIZE = 1, + BPF_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_FIELD_SIGNED = 3, + BPF_FIELD_LSHIFT_U64 = 4, + BPF_FIELD_RSHIFT_U64 = 5, +}; + +/* The minimum bpf_field_reloc checked by the loader + * + * Field relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * field; + * - access_str_off - offset into corresponding .BTF string section. String + * itself encodes an accessed field using a sequence of field and array + * indicies, separated by colon (:). It's conceptually very close to LLVM's + * getelementptr ([0]) instruction's arguments for identifying offset to + * a field. + * + * Example to provide a better feel. + * + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int x = &s->a; // encoded as "0:0" (a is field #0) + * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_field_reloc { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_field_info_kind kind; +}; + +#endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 8c3a1c04dcb2..a9eb8b322671 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -9,11 +9,13 @@ #include <net/if.h> #include <sys/utsname.h> +#include <linux/btf.h> #include <linux/filter.h> #include <linux/kernel.h> #include "bpf.h" #include "libbpf.h" +#include "libbpf_internal.h" static bool grep(const char *buffer, const char *pattern) { @@ -93,10 +95,14 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_LIRC_MODE2: case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_TRACING: default: break; } @@ -129,11 +135,68 @@ bool bpf_probe_prog_type(enum bpf_prog_type prog_type, __u32 ifindex) return errno != EINVAL && errno != EOPNOTSUPP; } +int libbpf__load_raw_btf(const char *raw_types, size_t types_len, + const char *str_sec, size_t str_len) +{ + struct btf_header hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = types_len, + .str_off = types_len, + .str_len = str_len, + }; + int btf_fd, btf_len; + __u8 *raw_btf; + + btf_len = hdr.hdr_len + hdr.type_len + hdr.str_len; + raw_btf = malloc(btf_len); + if (!raw_btf) + return -ENOMEM; + + memcpy(raw_btf, &hdr, sizeof(hdr)); + memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len); + memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len); + + btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false); + + free(raw_btf); + return btf_fd; +} + +static int load_sk_storage_btf(void) +{ + const char strs[] = "\0bpf_spin_lock\0val\0cnt\0l"; + /* struct bpf_spin_lock { + * int val; + * }; + * struct val { + * int cnt; + * struct bpf_spin_lock l; + * }; + */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct bpf_spin_lock */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4), + BTF_MEMBER_ENC(15, 1, 0), /* int val; */ + /* struct val */ /* [3] */ + BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ + BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + }; + + return libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); +} + bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) { int key_size, value_size, max_entries, map_flags; + __u32 btf_key_type_id = 0, btf_value_type_id = 0; struct bpf_create_map_attr attr = {}; - int fd = -1, fd_inner; + int fd = -1, btf_fd = -1, fd_inner; key_size = sizeof(__u32); value_size = sizeof(__u32); @@ -159,6 +222,16 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_STACK: key_size = 0; break; + case BPF_MAP_TYPE_SK_STORAGE: + btf_key_type_id = 1; + btf_value_type_id = 3; + value_size = 8; + max_entries = 0; + map_flags = BPF_F_NO_PREALLOC; + btf_fd = load_sk_storage_btf(); + if (btf_fd < 0) + return false; + break; case BPF_MAP_TYPE_UNSPEC: case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_ARRAY: @@ -172,6 +245,7 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_CPUMAP: case BPF_MAP_TYPE_XSKMAP: @@ -204,11 +278,18 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) attr.max_entries = max_entries; attr.map_flags = map_flags; attr.map_ifindex = ifindex; + if (btf_fd >= 0) { + attr.btf_fd = btf_fd; + attr.btf_key_type_id = btf_key_type_id; + attr.btf_value_type_id = btf_value_type_id; + } fd = bpf_create_map_xattr(&attr); } if (fd >= 0) close(fd); + if (btf_fd >= 0) + close(btf_fd); return fd >= 0; } diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h index 81ecda0cb9c9..59c779c5790c 100644 --- a/tools/lib/bpf/libbpf_util.h +++ b/tools/lib/bpf/libbpf_util.h @@ -10,18 +10,35 @@ extern "C" { #endif -extern void libbpf_print(enum libbpf_print_level level, - const char *format, ...) - __attribute__((format(printf, 2, 3))); - -#define __pr(level, fmt, ...) \ -do { \ - libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \ -} while (0) - -#define pr_warning(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__) -#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) -#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) +/* Use these barrier functions instead of smp_[rw]mb() when they are + * used in a libbpf header file. That way they can be built into the + * application that uses libbpf. + */ +#if defined(__i386__) || defined(__x86_64__) +# define libbpf_smp_rmb() asm volatile("" : : : "memory") +# define libbpf_smp_wmb() asm volatile("" : : : "memory") +# define libbpf_smp_mb() \ + asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc") +/* Hinders stores to be observed before older loads. */ +# define libbpf_smp_rwmb() asm volatile("" : : : "memory") +#elif defined(__aarch64__) +# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory") +# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory") +# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_rwmb() libbpf_smp_mb() +#elif defined(__arm__) +/* These are only valid for armv7 and above */ +# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory") +# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory") +# define libbpf_smp_rwmb() libbpf_smp_mb() +#else +/* Architecture missing native barrier functions. */ +# define libbpf_smp_rmb() __sync_synchronize() +# define libbpf_smp_wmb() __sync_synchronize() +# define libbpf_smp_mb() __sync_synchronize() +# define libbpf_smp_rwmb() __sync_synchronize() +#endif #ifdef __cplusplus } /* extern "C" */ diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index ce3ec81b71c0..5065c1aa1061 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -12,6 +12,7 @@ #include "bpf.h" #include "libbpf.h" +#include "libbpf_internal.h" #include "nlattr.h" #ifndef SOL_NETLINK @@ -24,7 +25,7 @@ typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t, struct xdp_id_md { int ifindex; __u32 flags; - __u32 id; + struct xdp_link_info info; }; int libbpf_netlink_open(__u32 *nl_pid) @@ -43,7 +44,7 @@ int libbpf_netlink_open(__u32 *nl_pid) if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, &one, sizeof(one)) < 0) { - fprintf(stderr, "Netlink error reporting not supported\n"); + pr_warn("Netlink error reporting not supported\n"); } if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { @@ -202,26 +203,11 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh, return dump_link_nlmsg(cookie, ifi, tb); } -static unsigned char get_xdp_id_attr(unsigned char mode, __u32 flags) -{ - if (mode != XDP_ATTACHED_MULTI) - return IFLA_XDP_PROG_ID; - if (flags & XDP_FLAGS_DRV_MODE) - return IFLA_XDP_DRV_PROG_ID; - if (flags & XDP_FLAGS_HW_MODE) - return IFLA_XDP_HW_PROG_ID; - if (flags & XDP_FLAGS_SKB_MODE) - return IFLA_XDP_SKB_PROG_ID; - - return IFLA_XDP_UNSPEC; -} - -static int get_xdp_id(void *cookie, void *msg, struct nlattr **tb) +static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) { struct nlattr *xdp_tb[IFLA_XDP_MAX + 1]; struct xdp_id_md *xdp_id = cookie; struct ifinfomsg *ifinfo = msg; - unsigned char mode, xdp_attr; int ret; if (xdp_id->ifindex && xdp_id->ifindex != ifinfo->ifi_index) @@ -237,27 +223,40 @@ static int get_xdp_id(void *cookie, void *msg, struct nlattr **tb) if (!xdp_tb[IFLA_XDP_ATTACHED]) return 0; - mode = libbpf_nla_getattr_u8(xdp_tb[IFLA_XDP_ATTACHED]); - if (mode == XDP_ATTACHED_NONE) - return 0; + xdp_id->info.attach_mode = libbpf_nla_getattr_u8( + xdp_tb[IFLA_XDP_ATTACHED]); - xdp_attr = get_xdp_id_attr(mode, xdp_id->flags); - if (!xdp_attr || !xdp_tb[xdp_attr]) + if (xdp_id->info.attach_mode == XDP_ATTACHED_NONE) return 0; - xdp_id->id = libbpf_nla_getattr_u32(xdp_tb[xdp_attr]); + if (xdp_tb[IFLA_XDP_PROG_ID]) + xdp_id->info.prog_id = libbpf_nla_getattr_u32( + xdp_tb[IFLA_XDP_PROG_ID]); + + if (xdp_tb[IFLA_XDP_SKB_PROG_ID]) + xdp_id->info.skb_prog_id = libbpf_nla_getattr_u32( + xdp_tb[IFLA_XDP_SKB_PROG_ID]); + + if (xdp_tb[IFLA_XDP_DRV_PROG_ID]) + xdp_id->info.drv_prog_id = libbpf_nla_getattr_u32( + xdp_tb[IFLA_XDP_DRV_PROG_ID]); + + if (xdp_tb[IFLA_XDP_HW_PROG_ID]) + xdp_id->info.hw_prog_id = libbpf_nla_getattr_u32( + xdp_tb[IFLA_XDP_HW_PROG_ID]); return 0; } -int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, + size_t info_size, __u32 flags) { struct xdp_id_md xdp_id = {}; int sock, ret; __u32 nl_pid; __u32 mask; - if (flags & ~XDP_FLAGS_MASK) + if (flags & ~XDP_FLAGS_MASK || !info_size) return -EINVAL; /* Check whether the single {HW,DRV,SKB} mode is set */ @@ -273,14 +272,44 @@ int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) xdp_id.ifindex = ifindex; xdp_id.flags = flags; - ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_id, &xdp_id); - if (!ret) - *prog_id = xdp_id.id; + ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_info, &xdp_id); + if (!ret) { + size_t sz = min(info_size, sizeof(xdp_id.info)); + + memcpy(info, &xdp_id.info, sz); + memset((void *) info + sz, 0, info_size - sz); + } close(sock); return ret; } +static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags) +{ + if (info->attach_mode != XDP_ATTACHED_MULTI) + return info->prog_id; + if (flags & XDP_FLAGS_DRV_MODE) + return info->drv_prog_id; + if (flags & XDP_FLAGS_HW_MODE) + return info->hw_prog_id; + if (flags & XDP_FLAGS_SKB_MODE) + return info->skb_prog_id; + + return 0; +} + +int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +{ + struct xdp_link_info info; + int ret; + + ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags); + if (!ret) + *prog_id = get_xdp_id(&info, flags); + + return ret; +} + int libbpf_nl_get_link(int sock, unsigned int nl_pid, libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie) { diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index 1e69c0c8d413..8db44bbfc66d 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -8,6 +8,7 @@ #include <errno.h> #include "nlattr.h" +#include "libbpf_internal.h" #include <linux/rtnetlink.h> #include <string.h> #include <stdio.h> @@ -121,8 +122,8 @@ int libbpf_nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, } if (tb[type]) - fprintf(stderr, "Attribute of type %#x found multiple times in message, " - "previous attribute is being ignored.\n", type); + pr_warn("Attribute of type %#x found multiple times in message, " + "previous attribute is being ignored.\n", type); tb[type] = nla; } @@ -181,15 +182,14 @@ int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh) if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) { - fprintf(stderr, - "Failed to parse extended error attributes\n"); + pr_warn("Failed to parse extended error attributes\n"); return 0; } if (tb[NLMSGERR_ATTR_MSG]) errmsg = (char *) libbpf_nla_data(tb[NLMSGERR_ATTR_MSG]); - fprintf(stderr, "Kernel error message: %s\n", errmsg); + pr_warn("Kernel error message: %s\n", errmsg); return 0; } diff --git a/tools/lib/bpf/str_error.c b/tools/lib/bpf/str_error.c index 00e48ac5b806..b8064eedc177 100644 --- a/tools/lib/bpf/str_error.c +++ b/tools/lib/bpf/str_error.c @@ -11,7 +11,7 @@ */ char *libbpf_strerror_r(int err, char *dst, int len) { - int ret = strerror_r(err, dst, 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/test_libbpf.cpp b/tools/lib/bpf/test_libbpf.c index fc134873bb6d..f0eb2727b766 100644 --- a/tools/lib/bpf/test_libbpf.cpp +++ b/tools/lib/bpf/test_libbpf.c @@ -7,12 +7,14 @@ int main(int argc, char *argv[]) { - /* libbpf.h */ - libbpf_set_print(NULL); + /* libbpf.h */ + libbpf_set_print(NULL); - /* bpf.h */ - bpf_prog_get_fd_by_id(0); + /* bpf.h */ + bpf_prog_get_fd_by_id(0); - /* btf.h */ - btf__new(NULL, 0); + /* btf.h */ + btf__new(NULL, 0); + + return 0; } diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 8d0078b65486..8e0ffa800a71 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -29,7 +29,7 @@ #include "bpf.h" #include "libbpf.h" -#include "libbpf_util.h" +#include "libbpf_internal.h" #include "xsk.h" #ifndef SOL_XDP @@ -60,10 +60,8 @@ struct xsk_socket { struct xsk_umem *umem; struct xsk_socket_config config; int fd; - int xsks_map; int ifindex; int prog_fd; - int qidconf_map_fd; int xsks_map_fd; __u32 queue_id; char ifname[IFNAMSIZ]; @@ -75,22 +73,20 @@ struct xsk_nl_info { int fd; }; -/* For 32-bit systems, we need to use mmap2 as the offsets are 64-bit. - * Unfortunately, it is not part of glibc. - */ -static inline void *xsk_mmap(void *addr, size_t length, int prot, int flags, - int fd, __u64 offset) -{ -#ifdef __NR_mmap2 - unsigned int page_shift = __builtin_ffs(getpagesize()) - 1; - long ret = syscall(__NR_mmap2, addr, length, prot, flags, fd, - (off_t)(offset >> page_shift)); - - return (void *)ret; -#else - return mmap(addr, length, prot, flags, fd, offset); -#endif -} +/* Up until and including Linux 5.3 */ +struct xdp_ring_offset_v1 { + __u64 producer; + __u64 consumer; + __u64 desc; +}; + +/* Up until and including Linux 5.3 */ +struct xdp_mmap_offsets_v1 { + struct xdp_ring_offset_v1 rx; + struct xdp_ring_offset_v1 tx; + struct xdp_ring_offset_v1 fr; + struct xdp_ring_offset_v1 cr; +}; int xsk_umem__fd(const struct xsk_umem *umem) { @@ -117,6 +113,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg, cfg->comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; + cfg->flags = XSK_UMEM__DEFAULT_FLAGS; return; } @@ -124,6 +121,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg, cfg->comp_size = usr_cfg->comp_size; cfg->frame_size = usr_cfg->frame_size; cfg->frame_headroom = usr_cfg->frame_headroom; + cfg->flags = usr_cfg->flags; } static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, @@ -150,14 +148,66 @@ static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, return 0; } -int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, - struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, - const struct xsk_umem_config *usr_config) +static void xsk_mmap_offsets_v1(struct xdp_mmap_offsets *off) +{ + struct xdp_mmap_offsets_v1 off_v1; + + /* getsockopt on a kernel <= 5.3 has no flags fields. + * Copy over the offsets to the correct places in the >=5.4 format + * and put the flags where they would have been on that kernel. + */ + memcpy(&off_v1, off, sizeof(off_v1)); + + off->rx.producer = off_v1.rx.producer; + off->rx.consumer = off_v1.rx.consumer; + off->rx.desc = off_v1.rx.desc; + off->rx.flags = off_v1.rx.consumer + sizeof(__u32); + + off->tx.producer = off_v1.tx.producer; + off->tx.consumer = off_v1.tx.consumer; + off->tx.desc = off_v1.tx.desc; + off->tx.flags = off_v1.tx.consumer + sizeof(__u32); + + off->fr.producer = off_v1.fr.producer; + off->fr.consumer = off_v1.fr.consumer; + off->fr.desc = off_v1.fr.desc; + off->fr.flags = off_v1.fr.consumer + sizeof(__u32); + + off->cr.producer = off_v1.cr.producer; + off->cr.consumer = off_v1.cr.consumer; + off->cr.desc = off_v1.cr.desc; + off->cr.flags = off_v1.cr.consumer + sizeof(__u32); +} + +static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off) +{ + socklen_t optlen; + int err; + + optlen = sizeof(*off); + err = getsockopt(fd, SOL_XDP, XDP_MMAP_OFFSETS, off, &optlen); + if (err) + return err; + + if (optlen == sizeof(*off)) + return 0; + + if (optlen == sizeof(struct xdp_mmap_offsets_v1)) { + xsk_mmap_offsets_v1(off); + return 0; + } + + return -EINVAL; +} + +int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, + __u64 size, struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *usr_config) { struct xdp_mmap_offsets off; struct xdp_umem_reg mr; struct xsk_umem *umem; - socklen_t optlen; void *map; int err; @@ -179,10 +229,12 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, umem->umem_area = umem_area; xsk_set_umem_config(&umem->config, usr_config); + memset(&mr, 0, sizeof(mr)); mr.addr = (uintptr_t)umem_area; mr.len = size; mr.chunk_size = umem->config.frame_size; mr.headroom = umem->config.frame_headroom; + mr.flags = umem->config.flags; err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr)); if (err) { @@ -204,17 +256,15 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, goto out_socket; } - optlen = sizeof(off); - err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen); + err = xsk_get_mmap_offsets(umem->fd, &off); if (err) { err = -errno; goto out_socket; } - map = xsk_mmap(NULL, off.fr.desc + - umem->config.fill_size * sizeof(__u64), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, - umem->fd, XDP_UMEM_PGOFF_FILL_RING); + map = mmap(NULL, off.fr.desc + umem->config.fill_size * sizeof(__u64), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd, + XDP_UMEM_PGOFF_FILL_RING); if (map == MAP_FAILED) { err = -errno; goto out_socket; @@ -225,13 +275,13 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, fill->size = umem->config.fill_size; fill->producer = map + off.fr.producer; fill->consumer = map + off.fr.consumer; + fill->flags = map + off.fr.flags; fill->ring = map + off.fr.desc; fill->cached_cons = umem->config.fill_size; - map = xsk_mmap(NULL, - off.cr.desc + umem->config.comp_size * sizeof(__u64), - PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, - umem->fd, XDP_UMEM_PGOFF_COMPLETION_RING); + map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, umem->fd, + XDP_UMEM_PGOFF_COMPLETION_RING); if (map == MAP_FAILED) { err = -errno; goto out_mmap; @@ -242,14 +292,14 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, comp->size = umem->config.comp_size; comp->producer = map + off.cr.producer; comp->consumer = map + off.cr.consumer; + comp->flags = map + off.cr.flags; comp->ring = map + off.cr.desc; *umem_ptr = umem; return 0; out_mmap: - munmap(umem->fill, - off.fr.desc + umem->config.fill_size * sizeof(__u64)); + munmap(map, off.fr.desc + umem->config.fill_size * sizeof(__u64)); out_socket: close(umem->fd); out_umem_alloc: @@ -257,50 +307,87 @@ out_umem_alloc: return err; } +struct xsk_umem_config_v1 { + __u32 fill_size; + __u32 comp_size; + __u32 frame_size; + __u32 frame_headroom; +}; + +int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, + __u64 size, struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *usr_config) +{ + struct xsk_umem_config config; + + memcpy(&config, usr_config, sizeof(struct xsk_umem_config_v1)); + config.flags = 0; + + return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp, + &config); +} +COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) +DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) + static int xsk_load_xdp_prog(struct xsk_socket *xsk) { - char bpf_log_buf[BPF_LOG_BUF_SIZE]; + static const int log_buf_size = 16 * 1024; + char log_buf[log_buf_size]; int err, prog_fd; /* This is the C-program: * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) * { - * int *qidconf, index = ctx->rx_queue_index; + * int ret, index = ctx->rx_queue_index; * * // A set entry here means that the correspnding queue_id * // has an active AF_XDP socket bound to it. - * qidconf = bpf_map_lookup_elem(&qidconf_map, &index); - * if (!qidconf) - * return XDP_ABORTED; + * ret = bpf_redirect_map(&xsks_map, index, XDP_PASS); + * if (ret > 0) + * return ret; * - * if (*qidconf) + * // Fallback for pre-5.3 kernels, not supporting default + * // action in the flags parameter. + * if (bpf_map_lookup_elem(&xsks_map, &index)) * return bpf_redirect_map(&xsks_map, index, 0); - * * return XDP_PASS; * } */ struct bpf_insn prog[] = { - /* r1 = *(u32 *)(r1 + 16) */ - BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 16), - /* *(u32 *)(r10 - 4) = r1 */ - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_1, -4), + /* r2 = *(u32 *)(r1 + 16) */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16), + /* *(u32 *)(r10 - 4) = r2 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -4), + /* r1 = xskmap[] */ + BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), + /* r3 = XDP_PASS */ + BPF_MOV64_IMM(BPF_REG_3, 2), + /* call bpf_redirect_map */ + BPF_EMIT_CALL(BPF_FUNC_redirect_map), + /* if w0 != 0 goto pc+13 */ + BPF_JMP32_IMM(BPF_JSGT, BPF_REG_0, 0, 13), + /* r2 = r10 */ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + /* r2 += -4 */ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), - BPF_LD_MAP_FD(BPF_REG_1, xsk->qidconf_map_fd), + /* r1 = xskmap[] */ + BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), + /* call bpf_map_lookup_elem */ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + /* r1 = r0 */ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), - BPF_MOV32_IMM(BPF_REG_0, 0), - /* if r1 == 0 goto +8 */ - BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 8), - BPF_MOV32_IMM(BPF_REG_0, 2), - /* r1 = *(u32 *)(r1 + 0) */ - BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 0), - /* if r1 == 0 goto +5 */ + /* r0 = XDP_PASS */ + BPF_MOV64_IMM(BPF_REG_0, 2), + /* if r1 == 0 goto pc+5 */ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5), /* r2 = *(u32 *)(r10 - 4) */ - BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_10, -4), - BPF_MOV32_IMM(BPF_REG_3, 0), + /* r1 = xskmap[] */ + BPF_LD_MAP_FD(BPF_REG_1, xsk->xsks_map_fd), + /* r3 = 0 */ + BPF_MOV64_IMM(BPF_REG_3, 0), + /* call bpf_redirect_map */ BPF_EMIT_CALL(BPF_FUNC_redirect_map), /* The jumps are to this instruction */ BPF_EXIT_INSN(), @@ -308,10 +395,10 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, prog, insns_cnt, - "LGPL-2.1 or BSD-2-Clause", 0, bpf_log_buf, - BPF_LOG_BUF_SIZE); + "LGPL-2.1 or BSD-2-Clause", 0, log_buf, + log_buf_size); if (prog_fd < 0) { - pr_warning("BPF log buffer:\n%s", bpf_log_buf); + pr_warn("BPF log buffer:\n%s", log_buf); return prog_fd; } @@ -327,30 +414,35 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) static int xsk_get_max_queues(struct xsk_socket *xsk) { - struct ethtool_channels channels; - struct ifreq ifr; + struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; + struct ifreq ifr = {}; int fd, err, ret; fd = socket(AF_INET, SOCK_DGRAM, 0); if (fd < 0) return -errno; - channels.cmd = ETHTOOL_GCHANNELS; ifr.ifr_data = (void *)&channels; - strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ); + memcpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); + ifr.ifr_name[IFNAMSIZ - 1] = '\0'; err = ioctl(fd, SIOCETHTOOL, &ifr); if (err && errno != EOPNOTSUPP) { ret = -errno; goto out; } - if (channels.max_combined == 0 || errno == EOPNOTSUPP) + if (err) { /* If the device says it has no channels, then all traffic * is sent to a single stream, so max queues = 1. */ ret = 1; - else - ret = channels.max_combined; + } else { + /* Take the max of rx, tx, combined. Drivers return + * the number of channels in different ways. + */ + ret = max(channels.max_rx, channels.max_tx); + ret = max(ret, (int)channels.max_combined); + } out: close(fd); @@ -366,18 +458,11 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk) if (max_queues < 0) return max_queues; - fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "qidconf_map", + fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map", sizeof(int), sizeof(int), max_queues, 0); if (fd < 0) return fd; - xsk->qidconf_map_fd = fd; - fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map", - sizeof(int), sizeof(int), max_queues, 0); - if (fd < 0) { - close(xsk->qidconf_map_fd); - return fd; - } xsk->xsks_map_fd = fd; return 0; @@ -385,23 +470,17 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk) static void xsk_delete_bpf_maps(struct xsk_socket *xsk) { - close(xsk->qidconf_map_fd); + bpf_map_delete_elem(xsk->xsks_map_fd, &xsk->queue_id); close(xsk->xsks_map_fd); } -static int xsk_update_bpf_maps(struct xsk_socket *xsk, int qidconf_value, - int xsks_value) +static int xsk_lookup_bpf_maps(struct xsk_socket *xsk) { - bool qidconf_map_updated = false, xsks_map_updated = false; + __u32 i, *map_ids, num_maps, prog_len = sizeof(struct bpf_prog_info); + __u32 map_len = sizeof(struct bpf_map_info); struct bpf_prog_info prog_info = {}; - __u32 prog_len = sizeof(prog_info); struct bpf_map_info map_info; - __u32 map_len = sizeof(map_info); - __u32 *map_ids; - int reset_value = 0; - __u32 num_maps; - unsigned int i; - int err; + int fd, err; err = bpf_obj_get_info_by_fd(xsk->prog_fd, &prog_info, &prog_len); if (err) @@ -421,67 +500,44 @@ static int xsk_update_bpf_maps(struct xsk_socket *xsk, int qidconf_value, if (err) goto out_map_ids; - for (i = 0; i < prog_info.nr_map_ids; i++) { - int fd; + xsk->xsks_map_fd = -1; + for (i = 0; i < prog_info.nr_map_ids; i++) { fd = bpf_map_get_fd_by_id(map_ids[i]); - if (fd < 0) { - err = -errno; - goto out_maps; - } + if (fd < 0) + continue; err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len); - if (err) - goto out_maps; - - if (!strcmp(map_info.name, "qidconf_map")) { - err = bpf_map_update_elem(fd, &xsk->queue_id, - &qidconf_value, 0); - if (err) - goto out_maps; - qidconf_map_updated = true; - xsk->qidconf_map_fd = fd; - } else if (!strcmp(map_info.name, "xsks_map")) { - err = bpf_map_update_elem(fd, &xsk->queue_id, - &xsks_value, 0); - if (err) - goto out_maps; - xsks_map_updated = true; + if (err) { + close(fd); + continue; + } + + if (!strcmp(map_info.name, "xsks_map")) { xsk->xsks_map_fd = fd; + continue; } - if (qidconf_map_updated && xsks_map_updated) - break; + close(fd); } - if (!(qidconf_map_updated && xsks_map_updated)) { + err = 0; + if (xsk->xsks_map_fd == -1) err = -ENOENT; - goto out_maps; - } - err = 0; - goto out_success; - -out_maps: - if (qidconf_map_updated) - (void)bpf_map_update_elem(xsk->qidconf_map_fd, &xsk->queue_id, - &reset_value, 0); - if (xsks_map_updated) - (void)bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, - &reset_value, 0); -out_success: - if (qidconf_map_updated) - close(xsk->qidconf_map_fd); - if (xsks_map_updated) - close(xsk->xsks_map_fd); out_map_ids: free(map_ids); return err; } +static int xsk_set_bpf_maps(struct xsk_socket *xsk) +{ + return bpf_map_update_elem(xsk->xsks_map_fd, &xsk->queue_id, + &xsk->fd, 0); +} + static int xsk_setup_xdp_prog(struct xsk_socket *xsk) { - bool prog_attached = false; __u32 prog_id = 0; int err; @@ -491,31 +547,35 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) return err; if (!prog_id) { - prog_attached = true; err = xsk_create_bpf_maps(xsk); if (err) return err; err = xsk_load_xdp_prog(xsk); - if (err) - goto out_maps; + if (err) { + xsk_delete_bpf_maps(xsk); + return err; + } } else { xsk->prog_fd = bpf_prog_get_fd_by_id(prog_id); + if (xsk->prog_fd < 0) + return -errno; + err = xsk_lookup_bpf_maps(xsk); + if (err) { + close(xsk->prog_fd); + return err; + } } - err = xsk_update_bpf_maps(xsk, true, xsk->fd); - if (err) - goto out_load; + if (xsk->rx) + err = xsk_set_bpf_maps(xsk); + if (err) { + xsk_delete_bpf_maps(xsk); + close(xsk->prog_fd); + return err; + } return 0; - -out_load: - if (prog_attached) - close(xsk->prog_fd); -out_maps: - if (prog_attached) - xsk_delete_bpf_maps(xsk); - return err; } int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, @@ -523,25 +583,30 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, const struct xsk_socket_config *usr_config) { + void *rx_map = NULL, *tx_map = NULL; struct sockaddr_xdp sxdp = {}; struct xdp_mmap_offsets off; struct xsk_socket *xsk; - socklen_t optlen; - void *map; int err; - if (!umem || !xsk_ptr || !rx || !tx) + if (!umem || !xsk_ptr || !(rx || tx)) return -EFAULT; - if (umem->refcount) { - pr_warning("Error: shared umems not supported by libbpf.\n"); - return -EBUSY; - } - xsk = calloc(1, sizeof(*xsk)); if (!xsk) return -ENOMEM; + err = xsk_set_xdp_socket_config(&xsk->config, usr_config); + if (err) + goto out_xsk_alloc; + + if (umem->refcount && + !(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { + pr_warn("Error: shared umems not supported by libbpf supplied XDP program.\n"); + err = -EBUSY; + goto out_xsk_alloc; + } + if (umem->refcount++ > 0) { xsk->fd = socket(AF_XDP, SOCK_RAW, 0); if (xsk->fd < 0) { @@ -560,11 +625,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, err = -errno; goto out_socket; } - strncpy(xsk->ifname, ifname, IFNAMSIZ); - - err = xsk_set_xdp_socket_config(&xsk->config, usr_config); - if (err) - goto out_socket; + memcpy(xsk->ifname, ifname, IFNAMSIZ - 1); + xsk->ifname[IFNAMSIZ - 1] = '\0'; if (rx) { err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING, @@ -585,48 +647,47 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, } } - optlen = sizeof(off); - err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen); + err = xsk_get_mmap_offsets(xsk->fd, &off); if (err) { err = -errno; goto out_socket; } if (rx) { - map = xsk_mmap(NULL, off.rx.desc + - xsk->config.rx_size * sizeof(struct xdp_desc), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, - xsk->fd, XDP_PGOFF_RX_RING); - if (map == MAP_FAILED) { + rx_map = mmap(NULL, off.rx.desc + + xsk->config.rx_size * sizeof(struct xdp_desc), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, + xsk->fd, XDP_PGOFF_RX_RING); + if (rx_map == MAP_FAILED) { err = -errno; goto out_socket; } rx->mask = xsk->config.rx_size - 1; rx->size = xsk->config.rx_size; - rx->producer = map + off.rx.producer; - rx->consumer = map + off.rx.consumer; - rx->ring = map + off.rx.desc; + rx->producer = rx_map + off.rx.producer; + rx->consumer = rx_map + off.rx.consumer; + rx->flags = rx_map + off.rx.flags; + rx->ring = rx_map + off.rx.desc; } xsk->rx = rx; if (tx) { - map = xsk_mmap(NULL, off.tx.desc + - xsk->config.tx_size * sizeof(struct xdp_desc), - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, - xsk->fd, XDP_PGOFF_TX_RING); - if (map == MAP_FAILED) { + tx_map = mmap(NULL, off.tx.desc + + xsk->config.tx_size * sizeof(struct xdp_desc), + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, + xsk->fd, XDP_PGOFF_TX_RING); + if (tx_map == MAP_FAILED) { err = -errno; goto out_mmap_rx; } tx->mask = xsk->config.tx_size - 1; tx->size = xsk->config.tx_size; - tx->producer = map + off.tx.producer; - tx->consumer = map + off.tx.consumer; - tx->ring = map + off.tx.desc; + tx->producer = tx_map + off.tx.producer; + tx->consumer = tx_map + off.tx.consumer; + tx->flags = tx_map + off.tx.flags; + tx->ring = tx_map + off.tx.desc; tx->cached_cons = xsk->config.tx_size; } xsk->tx = tx; @@ -634,7 +695,12 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, sxdp.sxdp_family = PF_XDP; sxdp.sxdp_ifindex = xsk->ifindex; sxdp.sxdp_queue_id = xsk->queue_id; - sxdp.sxdp_flags = xsk->config.bind_flags; + if (umem->refcount > 1) { + sxdp.sxdp_flags = XDP_SHARED_UMEM; + sxdp.sxdp_shared_umem_fd = umem->fd; + } else { + sxdp.sxdp_flags = xsk->config.bind_flags; + } err = bind(xsk->fd, (struct sockaddr *)&sxdp, sizeof(sxdp)); if (err) { @@ -642,6 +708,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, goto out_mmap_tx; } + xsk->prog_fd = -1; + if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { err = xsk_setup_xdp_prog(xsk); if (err) @@ -653,13 +721,11 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, out_mmap_tx: if (tx) - munmap(xsk->tx, - off.tx.desc + + munmap(tx_map, off.tx.desc + xsk->config.tx_size * sizeof(struct xdp_desc)); out_mmap_rx: if (rx) - munmap(xsk->rx, - off.rx.desc + + munmap(rx_map, off.rx.desc + xsk->config.rx_size * sizeof(struct xdp_desc)); out_socket: if (--umem->refcount) @@ -672,7 +738,6 @@ out_xsk_alloc: int xsk_umem__delete(struct xsk_umem *umem) { struct xdp_mmap_offsets off; - socklen_t optlen; int err; if (!umem) @@ -681,12 +746,11 @@ int xsk_umem__delete(struct xsk_umem *umem) if (umem->refcount) return -EBUSY; - optlen = sizeof(off); - err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen); + err = xsk_get_mmap_offsets(umem->fd, &off); if (!err) { - munmap(umem->fill->ring, + munmap(umem->fill->ring - off.fr.desc, off.fr.desc + umem->config.fill_size * sizeof(__u64)); - munmap(umem->comp->ring, + munmap(umem->comp->ring - off.cr.desc, off.cr.desc + umem->config.comp_size * sizeof(__u64)); } @@ -698,26 +762,29 @@ int xsk_umem__delete(struct xsk_umem *umem) void xsk_socket__delete(struct xsk_socket *xsk) { + size_t desc_sz = sizeof(struct xdp_desc); struct xdp_mmap_offsets off; - socklen_t optlen; int err; if (!xsk) return; - (void)xsk_update_bpf_maps(xsk, 0, 0); + if (xsk->prog_fd != -1) { + xsk_delete_bpf_maps(xsk); + close(xsk->prog_fd); + } - optlen = sizeof(off); - err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen); + err = xsk_get_mmap_offsets(xsk->fd, &off); if (!err) { - if (xsk->rx) - munmap(xsk->rx->ring, - off.rx.desc + - xsk->config.rx_size * sizeof(struct xdp_desc)); - if (xsk->tx) - munmap(xsk->tx->ring, - off.tx.desc + - xsk->config.tx_size * sizeof(struct xdp_desc)); + if (xsk->rx) { + munmap(xsk->rx->ring - off.rx.desc, + off.rx.desc + xsk->config.rx_size * desc_sz); + } + if (xsk->tx) { + munmap(xsk->tx->ring - off.tx.desc, + off.tx.desc + xsk->config.tx_size * desc_sz); + } + } xsk->umem->refcount--; diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h index a497f00e2962..584f6820a639 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/lib/bpf/xsk.h @@ -16,6 +16,7 @@ #include <linux/if_xdp.h> #include "libbpf.h" +#include "libbpf_util.h" #ifdef __cplusplus extern "C" { @@ -31,11 +32,16 @@ struct name { \ __u32 *producer; \ __u32 *consumer; \ void *ring; \ + __u32 *flags; \ } DEFINE_XSK_RING(xsk_ring_prod); DEFINE_XSK_RING(xsk_ring_cons); +/* For a detailed explanation on the memory barriers associated with the + * ring, please take a look at net/xdp/xsk_queue.h. + */ + struct xsk_umem; struct xsk_socket; @@ -71,6 +77,11 @@ xsk_ring_cons__rx_desc(const struct xsk_ring_cons *rx, __u32 idx) return &descs[idx & rx->mask]; } +static inline int xsk_ring_prod__needs_wakeup(const struct xsk_ring_prod *r) +{ + return *r->flags & XDP_RING_NEED_WAKEUP; +} + static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb) { __u32 free_entries = r->cached_cons - r->cached_prod; @@ -105,7 +116,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb) static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod, size_t nb, __u32 *idx) { - if (unlikely(xsk_prod_nb_free(prod, nb) < nb)) + if (xsk_prod_nb_free(prod, nb) < nb) return 0; *idx = prod->cached_prod; @@ -116,10 +127,10 @@ static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod, static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb) { - /* Make sure everything has been written to the ring before signalling - * this to the kernel. + /* Make sure everything has been written to the ring before indicating + * this to the kernel by writing the producer pointer. */ - smp_wmb(); + libbpf_smp_wmb(); *prod->producer += nb; } @@ -129,11 +140,11 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons, { size_t entries = xsk_cons_nb_avail(cons, nb); - if (likely(entries > 0)) { + if (entries > 0) { /* Make sure we do not speculatively read the data before * we have received the packet buffers from the ring. */ - smp_rmb(); + libbpf_smp_rmb(); *idx = cons->cached_cons; cons->cached_cons += entries; @@ -144,6 +155,11 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons, static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb) { + /* Make sure data has been read before indicating we are done + * with the entries by updating the consumer pointer. + */ + libbpf_smp_rwmb(); + *cons->consumer += nb; } @@ -152,20 +168,37 @@ static inline void *xsk_umem__get_data(void *umem_area, __u64 addr) return &((char *)umem_area)[addr]; } +static inline __u64 xsk_umem__extract_addr(__u64 addr) +{ + return addr & XSK_UNALIGNED_BUF_ADDR_MASK; +} + +static inline __u64 xsk_umem__extract_offset(__u64 addr) +{ + return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT; +} + +static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr) +{ + return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr); +} + LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem); LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk); #define XSK_RING_CONS__DEFAULT_NUM_DESCS 2048 #define XSK_RING_PROD__DEFAULT_NUM_DESCS 2048 -#define XSK_UMEM__DEFAULT_FRAME_SHIFT 11 /* 2048 bytes */ +#define XSK_UMEM__DEFAULT_FRAME_SHIFT 12 /* 4096 bytes */ #define XSK_UMEM__DEFAULT_FRAME_SIZE (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT) #define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0 +#define XSK_UMEM__DEFAULT_FLAGS 0 struct xsk_umem_config { __u32 fill_size; __u32 comp_size; __u32 frame_size; __u32 frame_headroom; + __u32 flags; }; /* Flags for the libbpf_flags field. */ @@ -185,6 +218,16 @@ LIBBPF_API int xsk_umem__create(struct xsk_umem **umem, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, const struct xsk_umem_config *config); +LIBBPF_API int xsk_umem__create_v0_0_2(struct xsk_umem **umem, + void *umem_area, __u64 size, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *config); +LIBBPF_API int xsk_umem__create_v0_0_4(struct xsk_umem **umem, + void *umem_area, __u64 size, + struct xsk_ring_prod *fill, + struct xsk_ring_cons *comp, + const struct xsk_umem_config *config); LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk, const char *ifname, __u32 queue_id, struct xsk_umem *umem, |
