diff options
Diffstat (limited to 'tools/lib')
107 files changed, 12222 insertions, 1896 deletions
diff --git a/tools/lib/api/debug-internal.h b/tools/lib/api/debug-internal.h index 80c783497d25..5a5820c11db8 100644 --- a/tools/lib/api/debug-internal.h +++ b/tools/lib/api/debug-internal.h @@ -10,11 +10,11 @@ do { \ (func)("libapi: " fmt, ##__VA_ARGS__); \ } while (0) -extern libapi_print_fn_t __pr_warning; +extern libapi_print_fn_t __pr_warn; extern libapi_print_fn_t __pr_info; extern libapi_print_fn_t __pr_debug; -#define pr_warning(fmt, ...) __pr(__pr_warning, fmt, ##__VA_ARGS__) +#define pr_warn(fmt, ...) __pr(__pr_warn, fmt, ##__VA_ARGS__) #define pr_info(fmt, ...) __pr(__pr_info, fmt, ##__VA_ARGS__) #define pr_debug(fmt, ...) __pr(__pr_debug, fmt, ##__VA_ARGS__) diff --git a/tools/lib/api/debug.c b/tools/lib/api/debug.c index 69b1ba3d1ee3..7708f0558e8c 100644 --- a/tools/lib/api/debug.c +++ b/tools/lib/api/debug.c @@ -15,7 +15,7 @@ static int __base_pr(const char *format, ...) return err; } -libapi_print_fn_t __pr_warning = __base_pr; +libapi_print_fn_t __pr_warn = __base_pr; libapi_print_fn_t __pr_info = __base_pr; libapi_print_fn_t __pr_debug; @@ -23,7 +23,7 @@ void libapi_set_print(libapi_print_fn_t warn, libapi_print_fn_t info, libapi_print_fn_t debug) { - __pr_warning = warn; + __pr_warn = warn; __pr_info = info; __pr_debug = debug; } diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 7aba8243a0e7..027b18f7ed8c 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -210,6 +210,7 @@ static bool fs__env_override(struct fs *fs) size_t name_len = strlen(fs->name); /* name + "_PATH" + '\0' */ char upper_name[name_len + 5 + 1]; + memcpy(upper_name, fs->name, name_len); mem_toupper(upper_name, name_len); strcpy(&upper_name[name_len], "_PATH"); @@ -219,7 +220,8 @@ static bool fs__env_override(struct fs *fs) return false; fs->found = true; - strncpy(fs->path, override_path, sizeof(fs->path)); + strncpy(fs->path, override_path, sizeof(fs->path) - 1); + fs->path[sizeof(fs->path) - 1] = '\0'; return true; } @@ -381,8 +383,8 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep) n = read(fd, bf + size, alloc_size - size); if (n < 0) { if (size) { - pr_warning("read failed %d: %s\n", errno, - strerror_r(errno, sbuf, sizeof(sbuf))); + pr_warn("read failed %d: %s\n", errno, + strerror_r(errno, sbuf, sizeof(sbuf))); err = 0; } else err = -errno; diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index 38494782be06..5043747ef6c5 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -71,3 +71,18 @@ int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, BITMAP_LAST_WORD_MASK(bits)); return result != 0; } + +int __bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + unsigned int k, lim = bits/BITS_PER_LONG; + for (k = 0; k < lim; ++k) + if (bitmap1[k] != bitmap2[k]) + return 0; + + if (bits % BITS_PER_LONG) + if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) + return 0; + + return 1; +} diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index d9e9dec04605..e97c2ebcf447 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -1,5 +1,8 @@ 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/Makefile b/tools/lib/bpf/Makefile index 9312066a1ae3..aee7f1a83c77 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 = 4 +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 $(srctree))) @@ -51,8 +56,8 @@ ifndef VERBOSE endif FEATURE_USER = .libbpf -FEATURE_TESTS = libelf libelf-mmap bpf reallocarray cxx -FEATURE_DISPLAY = libelf bpf +FEATURE_TESTS = libelf libelf-mmap zlib bpf reallocarray +FEATURE_DISPLAY = libelf zlib bpf INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES) @@ -79,15 +84,9 @@ 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 @@ -113,6 +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 = @@ -130,34 +133,35 @@ 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 +BPF_HELPER_DEFS := $(OUTPUT)bpf_helper_defs.h LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) PC_FILE := $(addprefix $(OUTPUT),$(PC_FILE)) -GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}') +TAGS_PROG := $(if $(shell which etags 2>/dev/null),etags,ctags) + +GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ + cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + sed 's/\[.*\]//' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ + 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) $(PC_FILE) -CXX_TEST_TARGET = $(OUTPUT)test_libbpf - -ifeq ($(feature-cxx), 1) - CMD_TARGETS += $(CXX_TEST_TARGET) -endif - -TARGETS = $(CMD_TARGETS) - all: fixdep $(Q)$(MAKE) all_cmd all_cmd: $(CMD_TARGETS) check -$(BPF_IN): force elfdep bpfdep +$(BPF_IN_SHARED): force elfdep zdep bpfdep $(BPF_HELPER_DEFS) @(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 @@ -173,22 +177,27 @@ $(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 zdep bpfdep $(BPF_HELPER_DEFS) + $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) + +$(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h + $(QUIET_GEN)$(srctree)/scripts/bpf_helpers_doc.py --header \ + --file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS) $(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 -lz -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)libbpf.pc: $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ -e "s|@LIBDIR@|$(libdir_SQ)|" \ @@ -199,13 +208,15 @@ 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 | \ - awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}'| \ + readelf -s --wide $(BPF_IN_SHARED) | \ + cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \ + sed 's/\[.*\]//' | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf -s --wide $(OUTPUT)libbpf.so | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ @@ -235,13 +246,19 @@ install_lib: all_cmd $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) -install_headers: +install_headers: $(BPF_HELPER_DEFS) $(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); \ $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \ - $(call do_install,xsk.h,$(prefix)/include/bpf,644); + $(call do_install,libbpf_common.h,$(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),$(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)) \ @@ -256,21 +273,38 @@ 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 *.pc LIBBPF-CFLAGS + $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ + *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ + $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ + $(addprefix $(OUTPUT), \ + *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc) $(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf -PHONY += force elfdep bpfdep +PHONY += force elfdep zdep bpfdep cscope tags force: elfdep: @if [ "$(feature-libelf)" != "1" ]; then echo "No libelf found"; exit 1 ; fi +zdep: + @if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi + bpfdep: @if [ "$(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/bpf.c b/tools/lib/bpf/bpf.c index c7d7993c44bb..c6dafe563176 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -32,6 +32,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + /* * When building perf, unistd.h is overridden. __NR_bpf is * required to be defined explicitly. @@ -95,7 +98,11 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) attr.btf_key_type_id = create_attr->btf_key_type_id; attr.btf_value_type_id = create_attr->btf_value_type_id; attr.map_ifindex = create_attr->map_ifindex; - attr.inner_map_fd = create_attr->inner_map_fd; + if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS) + attr.btf_vmlinux_value_type_id = + create_attr->btf_vmlinux_value_type_id; + else + attr.inner_map_fd = create_attr->inner_map_fd; return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } @@ -189,7 +196,7 @@ 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; @@ -228,6 +235,16 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, 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_STRUCT_OPS) { + attr.attach_btf_id = load_attr->attach_btf_id; + } else if (attr.prog_type == BPF_PROG_TYPE_TRACING || + attr.prog_type == BPF_PROG_TYPE_EXT) { + 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); @@ -241,8 +258,6 @@ 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; @@ -438,6 +453,64 @@ int bpf_map_freeze(int fd) return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); } +static int bpf_map_batch_common(int cmd, int fd, void *in_batch, + void *out_batch, void *keys, void *values, + __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + union bpf_attr attr; + int ret; + + if (!OPTS_VALID(opts, bpf_map_batch_opts)) + return -EINVAL; + + memset(&attr, 0, sizeof(attr)); + attr.batch.map_fd = fd; + attr.batch.in_batch = ptr_to_u64(in_batch); + attr.batch.out_batch = ptr_to_u64(out_batch); + attr.batch.keys = ptr_to_u64(keys); + attr.batch.values = ptr_to_u64(values); + attr.batch.count = *count; + attr.batch.elem_flags = OPTS_GET(opts, elem_flags, 0); + attr.batch.flags = OPTS_GET(opts, flags, 0); + + ret = sys_bpf(cmd, &attr, sizeof(attr)); + *count = attr.batch.count; + + return ret; +} + +int bpf_map_delete_batch(int fd, void *keys, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_DELETE_BATCH, fd, NULL, + NULL, keys, NULL, count, opts); +} + +int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, void *keys, + void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_LOOKUP_BATCH, fd, in_batch, + out_batch, keys, values, count, opts); +} + +int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, void *out_batch, + void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_LOOKUP_AND_DELETE_BATCH, + fd, in_batch, out_batch, keys, values, + count, opts); +} + +int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts) +{ + return bpf_map_batch_common(BPF_MAP_UPDATE_BATCH, fd, NULL, NULL, + keys, values, count, opts); +} + int bpf_obj_pin(int fd, const char *pathname) { union bpf_attr attr; @@ -462,13 +535,28 @@ int bpf_obj_get(const char *pathname) int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, unsigned int flags) { + DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, opts, + .flags = flags, + ); + + return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts); +} + +int bpf_prog_attach_xattr(int prog_fd, int target_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts) +{ union bpf_attr attr; + if (!OPTS_VALID(opts, bpf_prog_attach_opts)) + return -EINVAL; + memset(&attr, 0, sizeof(attr)); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; - attr.attach_flags = flags; + attr.attach_flags = OPTS_GET(opts, flags, 0); + attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0); return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); } @@ -568,7 +656,7 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) 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; @@ -576,26 +664,26 @@ 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 ff42ca043dc8..b976e77316cc 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -28,14 +28,12 @@ #include <stddef.h> #include <stdint.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - struct bpf_create_map_attr { const char *name; enum bpf_map_type map_type; @@ -48,7 +46,10 @@ struct bpf_create_map_attr { __u32 btf_key_type_id; __u32 btf_value_type_id; __u32 map_ifindex; - __u32 inner_map_fd; + union { + __u32 inner_map_fd; + __u32 btf_vmlinux_value_type_id; + }; }; LIBBPF_API int @@ -77,8 +78,14 @@ 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; @@ -120,10 +127,43 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, 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); + +struct bpf_map_batch_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u64 elem_flags; + __u64 flags; +}; +#define bpf_map_batch_opts__last_field flags + +LIBBPF_API int bpf_map_delete_batch(int fd, void *keys, + __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_lookup_batch(int fd, void *in_batch, void *out_batch, + void *keys, void *values, __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_lookup_and_delete_batch(int fd, void *in_batch, + void *out_batch, void *keys, + void *values, __u32 *count, + const struct bpf_map_batch_opts *opts); +LIBBPF_API int bpf_map_update_batch(int fd, void *keys, void *values, + __u32 *count, + const struct bpf_map_batch_opts *opts); + LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); LIBBPF_API int bpf_obj_get(const char *pathname); + +struct bpf_prog_attach_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + unsigned int flags; + int replace_prog_fd; +}; +#define bpf_prog_attach_opts__last_field replace_prog_fd + LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); +LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); @@ -156,6 +196,7 @@ 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..f69cc208778a --- /dev/null +++ b/tools/lib/bpf/bpf_helpers.h @@ -0,0 +1,58 @@ +/* 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 +#ifndef __weak +#define __weak __attribute__((weak)) +#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, +}; + +enum libbpf_tristate { + TRI_NO = 0, + TRI_YES = 1, + TRI_MODULE = 2, +}; + +#define __kconfig __attribute__((section(".kconfig"))) + +#endif diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c index 8c67561c93b0..bafca49cb1e6 100644 --- a/tools/lib/bpf/bpf_prog_linfo.c +++ b/tools/lib/bpf/bpf_prog_linfo.c @@ -8,6 +8,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + struct bpf_prog_linfo { void *raw_linfo; void *raw_jited_linfo; @@ -101,6 +104,7 @@ 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; @@ -122,11 +126,11 @@ 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 || @@ -142,13 +146,12 @@ 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 d821107f55f9..3d1c25fc97ae 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -8,6 +8,10 @@ #include <fcntl.h> #include <unistd.h> #include <errno.h> +#include <sys/utsname.h> +#include <sys/param.h> +#include <sys/stat.h> +#include <linux/kernel.h> #include <linux/err.h> #include <linux/btf.h> #include <gelf.h> @@ -17,15 +21,11 @@ #include "libbpf_internal.h" #include "hashmap.h" -#define BTF_MAX_NR_TYPES 0x7fffffff -#define BTF_MAX_STR_OFFSET 0x7fffffff +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 -#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \ - ((k) == BTF_KIND_VOLATILE) || \ - ((k) == BTF_KIND_CONST) || \ - ((k) == BTF_KIND_RESTRICT)) - -#define IS_VAR(k) ((k) == BTF_KIND_VAR) +#define BTF_MAX_NR_TYPES 0x7fffffffU +#define BTF_MAX_STR_OFFSET 0x7fffffffU static struct btf_type btf_void; @@ -43,47 +43,6 @@ 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; @@ -98,7 +57,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) if (btf->types_size == BTF_MAX_NR_TYPES) return -E2BIG; - expand_by = max(btf->types_size >> 2, 16); + expand_by = max(btf->types_size >> 2, 16U); new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by); new_types = realloc(btf->types, sizeof(*new_types) * new_size); @@ -193,9 +152,9 @@ 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: @@ -220,7 +179,7 @@ static int btf_type_size(struct btf_type *t) 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; } } @@ -264,7 +223,7 @@ 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) @@ -285,7 +244,7 @@ __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: @@ -304,7 +263,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) 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; @@ -317,16 +276,54 @@ __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; return nelems * size; } +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 *), (size_t)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, max_align = 1, align; + + for (i = 0; i < vlen; i++, m++) { + align = btf__align_of(btf, m->type); + if (align <= 0) + return align; + max_align = max(max_align, align); + } + + return max_align; + } + default: + pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); + return 0; + } +} + int btf__resolve_type(const struct btf *btf, __u32 type_id) { const struct btf_type *t; @@ -335,8 +332,7 @@ 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)) || - IS_VAR(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++; @@ -366,6 +362,28 @@ __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) @@ -439,14 +457,14 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) GElf_Ehdr ehdr; 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); return ERR_PTR(-LIBBPF_ERRNO__LIBELF); } fd = open(path, O_RDONLY); if (fd < 0) { err = -errno; - pr_warning("failed to open %s: %s\n", path, strerror(errno)); + pr_warn("failed to open %s: %s\n", path, strerror(errno)); return ERR_PTR(err); } @@ -454,19 +472,19 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) elf = elf_begin(fd, ELF_C_READ, NULL); if (!elf) { - pr_warning("failed to open %s as ELF file\n", path); + pr_warn("failed to open %s as ELF file\n", path); goto done; } if (!gelf_getehdr(elf, &ehdr)) { - pr_warning("failed to get EHDR from %s\n", path); + pr_warn("failed to get EHDR from %s\n", path); goto done; } if (!btf_check_endianness(&ehdr)) { - pr_warning("non-native ELF endianness is not supported\n"); + pr_warn("non-native ELF endianness is not supported\n"); goto done; } if (!elf_rawdata(elf_getscn(elf, ehdr.e_shstrndx), NULL)) { - pr_warning("failed to get e_shstrndx from %s\n", path); + pr_warn("failed to get e_shstrndx from %s\n", path); goto done; } @@ -476,29 +494,29 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) idx++; if (gelf_getshdr(scn, &sh) != &sh) { - pr_warning("failed to get section(%d) header from %s\n", - idx, path); + 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_warning("failed to get section(%d) name from %s\n", - idx, path); + 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_warning("failed to get section(%d, %s) data from %s\n", - idx, name, path); + 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_warning("failed to get section(%d, %s) data from %s\n", - idx, name, path); + pr_warn("failed to get section(%d, %s) data from %s\n", + idx, name, path); goto done; } continue; @@ -555,11 +573,11 @@ static int compare_vsi_off(const void *_a, const void *_b) static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, struct btf_type *t) { - __u32 size = 0, off = 0, i, vars = BTF_INFO_VLEN(t->info); + __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; - struct btf_var *var; + const struct btf_var *var; int ret; if (!name) { @@ -567,6 +585,12 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, return -ENOENT; } + /* .extern datasec size and var offsets were set correctly during + * extern collection step, so just skip straight to sorting variables + */ + if (t->size) + goto sort_vars; + 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); @@ -575,12 +599,11 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, t->size = size; - for (i = 0, vsi = (struct btf_var_secinfo *)(t + 1); - i < vars; i++, vsi++) { + for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) { t_var = btf__type_by_id(btf, vsi->type); - var = (struct btf_var *)(t_var + 1); + var = btf_var(t_var); - if (BTF_INFO_KIND(t_var->info) != BTF_KIND_VAR) { + if (!btf_is_var(t_var)) { pr_debug("Non-VAR type seen in section %s\n", name); return -EINVAL; } @@ -596,14 +619,16 @@ static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf, ret = bpf_object__variable_offset(obj, name, &off); if (ret) { - pr_debug("No offset found in symbol table for VAR %s\n", name); + 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); +sort_vars: + qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off); return 0; } @@ -620,7 +645,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf) * is section size and global variable offset. We use * the info from the ELF itself for this purpose. */ - if (BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC) { + if (btf_is_datasec(t)) { err = btf_fixup_datasec(obj, btf, t); if (err) break; @@ -649,9 +674,9 @@ 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; } @@ -756,8 +781,8 @@ 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; } @@ -770,42 +795,41 @@ 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; } @@ -832,6 +856,9 @@ 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); @@ -935,11 +962,24 @@ 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; @@ -997,6 +1037,9 @@ 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; @@ -1005,6 +1048,13 @@ 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); @@ -1355,7 +1405,7 @@ static int btf_dedup_hypot_map_add(struct btf_dedup *d, if (d->hypot_cnt == d->hypot_cap) { __u32 *new_list; - d->hypot_cap += max(16, d->hypot_cap / 2); + d->hypot_cap += max((size_t)16, d->hypot_cap / 2); new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap); if (!new_list) return -ENOMEM; @@ -1441,10 +1491,9 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, d->map[0] = 0; for (i = 1; i <= btf->nr_types; i++) { struct btf_type *t = d->btf->types[i]; - __u16 kind = BTF_INFO_KIND(t->info); /* VAR and DATASEC are never deduped and are self-canonical */ - if (kind == BTF_KIND_VAR || kind == BTF_KIND_DATASEC) + if (btf_is_var(t) || btf_is_datasec(t)) d->map[i] = i; else d->map[i] = BTF_UNPROCESSED_ID; @@ -1485,11 +1534,11 @@ 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); @@ -1500,8 +1549,8 @@ 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); @@ -1512,8 +1561,8 @@ 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); @@ -1652,7 +1701,7 @@ static int btf_dedup_strings(struct btf_dedup *d) if (strs.cnt + 1 > strs.cap) { struct btf_str_ptr *new_ptrs; - strs.cap += max(strs.cnt / 2, 16); + strs.cap += max(strs.cnt / 2, 16U); new_ptrs = realloc(strs.ptrs, sizeof(strs.ptrs[0]) * strs.cap); if (!new_ptrs) { @@ -1802,16 +1851,16 @@ static long 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; @@ -1823,8 +1872,7 @@ 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) @@ -1844,8 +1892,8 @@ static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2) */ 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); + const struct btf_member *member = btf_members(t); + __u32 vlen = btf_vlen(t); long h = btf_hash_common(t); int i; @@ -1865,16 +1913,16 @@ static long 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; @@ -1891,7 +1939,7 @@ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) */ static long btf_hash_array(struct btf_type *t) { - struct btf_array *info = (struct btf_array *)(t + 1); + const struct btf_array *info = btf_array(t); long h = btf_hash_common(t); h = hash_combine(h, info->type); @@ -1909,13 +1957,13 @@ static long 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; @@ -1928,14 +1976,10 @@ 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; } /* @@ -1945,8 +1989,8 @@ static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) */ 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); + const struct btf_param *member = btf_params(t); + __u16 vlen = btf_vlen(t); long h = btf_hash_common(t); int i; @@ -1967,16 +2011,16 @@ static long btf_hash_fnproto(struct btf_type *t) */ 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; @@ -1993,7 +2037,7 @@ static bool btf_equal_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; @@ -2001,9 +2045,9 @@ static 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; @@ -2029,7 +2073,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) __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: @@ -2142,13 +2186,13 @@ 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; @@ -2157,7 +2201,7 @@ 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; } /* @@ -2278,8 +2322,8 @@ 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; @@ -2328,12 +2372,12 @@ 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) @@ -2343,14 +2387,14 @@ 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) @@ -2363,7 +2407,7 @@ 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)) @@ -2371,9 +2415,9 @@ 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) @@ -2428,8 +2472,8 @@ 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 @@ -2498,7 +2542,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) 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; @@ -2593,7 +2637,7 @@ 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: @@ -2617,7 +2661,7 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) 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) @@ -2651,8 +2695,8 @@ 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) @@ -2792,7 +2836,7 @@ 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; @@ -2812,7 +2856,7 @@ 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) @@ -2827,8 +2871,8 @@ 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); @@ -2841,8 +2885,8 @@ 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) @@ -2860,8 +2904,8 @@ static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) } case BTF_KIND_DATASEC: { - struct btf_var_secinfo *var = (struct btf_var_secinfo *)(t + 1); - __u16 vlen = BTF_INFO_VLEN(t->info); + 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); @@ -2891,3 +2935,89 @@ static int btf_dedup_remap_types(struct btf_dedup *d) } 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. + */ +struct btf *libbpf_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); +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 88a52ae56fc6..70c1b7ec2bd0 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -5,16 +5,15 @@ #define __LIBBPF_BTF_H #include <stdarg.h> +#include <linux/btf.h> #include <linux/types.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - #define BTF_ELF_SEC ".BTF" #define BTF_EXT_ELF_SEC ".BTF.ext" #define MAPS_ELF_SEC ".maps" @@ -57,6 +56,10 @@ 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); @@ -67,11 +70,14 @@ 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); LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); +LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); LIBBPF_API int btf__fd(const struct btf *btf); LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); @@ -96,6 +102,8 @@ LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf, LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API struct btf *libbpf_find_kernel_btf(void); + struct btf_dedup_opts { unsigned int dedup_table_size; bool dont_resolve_fwds; @@ -120,6 +128,205 @@ LIBBPF_API void btf_dump__free(struct btf_dump *d); LIBBPF_API int btf_dump__dump_type(struct btf_dump *d, __u32 id); +struct btf_dump_emit_type_decl_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; + /* optional field name for type declaration, e.g.: + * - struct my_struct <FNAME> + * - void (*<FNAME>)(int) + * - char (*<FNAME>)[123] + */ + const char *field_name; + /* extra indentation level (in number of tabs) to emit for multi-line + * type declarations (e.g., anonymous struct); applies for lines + * starting from the second one (first line is assumed to have + * necessary indentation already + */ + int indent_level; +}; +#define btf_dump_emit_type_decl_opts__last_field indent_level + +LIBBPF_API int +btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, + const struct btf_dump_emit_type_decl_opts *opts); + +/* + * 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 index 7065bb5b2752..bd09ed1710f1 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -18,6 +18,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + 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; @@ -48,6 +51,8 @@ struct btf_dump_type_aux_state { __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 { @@ -100,21 +105,6 @@ static bool str_equal_fn(const void *a, const void *b, void *ctx) return strcmp(a, b) == 0; } -static __u16 btf_kind_of(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info); -} - -static __u16 btf_vlen_of(const struct btf_type *t) -{ - return BTF_INFO_VLEN(t->info); -} - -static bool btf_kflag_of(const struct btf_type *t) -{ - return BTF_INFO_KFLAG(t->info); -} - static const char *btf_name_of(const struct btf_dump *d, __u32 name_off) { return btf__name_by_offset(d->btf, name_off); @@ -129,6 +119,8 @@ static void btf_dump_printf(const struct btf_dump *d, const char *fmt, ...) va_end(args); } +static int btf_dump_mark_referenced(struct btf_dump *d); + struct btf_dump *btf_dump__new(const struct btf *btf, const struct btf_ext *btf_ext, const struct btf_dump_opts *opts, @@ -150,18 +142,40 @@ struct btf_dump *btf_dump__new(const struct btf *btf, if (IS_ERR(d->type_names)) { err = PTR_ERR(d->type_names); d->type_names = NULL; - btf_dump__free(d); - return ERR_PTR(err); + goto 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); + goto err; + } + d->type_states = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->type_states[0])); + if (!d->type_states) { + err = -ENOMEM; + goto err; + } + d->cached_names = calloc(1 + btf__get_nr_types(d->btf), + sizeof(d->cached_names[0])); + if (!d->cached_names) { + err = -ENOMEM; + goto err; } + /* 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) + goto err; + return d; +err: + btf_dump__free(d); + return ERR_PTR(err); } void btf_dump__free(struct btf_dump *d) @@ -214,22 +228,6 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id) 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; - } - d->emit_queue_cnt = 0; err = btf_dump_order_type(d, id, false); if (err < 0) @@ -241,6 +239,79 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id) 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; @@ -349,7 +420,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) */ struct btf_dump_type_aux_state *tstate = &d->type_states[id]; const struct btf_type *t; - __u16 kind, vlen; + __u16 vlen; int err, i; /* return true, letting typedefs know that it's ok to be emitted */ @@ -357,18 +428,16 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return 1; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); if (tstate->order_state == ORDERING) { /* type loop, but resolvable through fwd declaration */ - if ((kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION) && - through_ptr && t->name_off != 0) + if (btf_is_composite(t) && through_ptr && t->name_off != 0) return 0; - pr_warning("unsatisfiable type cycle, id:[%u]\n", id); + pr_warn("unsatisfiable type cycle, id:[%u]\n", id); return -ELOOP; } - switch (kind) { + switch (btf_kind(t)) { case BTF_KIND_INT: tstate->order_state = ORDERED; return 0; @@ -378,14 +447,12 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) tstate->order_state = ORDERED; return err; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); + case BTF_KIND_ARRAY: + return btf_dump_order_type(d, btf_array(t)->type, through_ptr); - return btf_dump_order_type(d, a->type, through_ptr); - } case BTF_KIND_STRUCT: case BTF_KIND_UNION: { - const struct btf_member *m = (void *)(t + 1); + 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 @@ -396,7 +463,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) tstate->order_state = ORDERING; - vlen = btf_vlen_of(t); + vlen = btf_vlen(t); for (i = 0; i < vlen; i++, m++) { err = btf_dump_order_type(d, m->type, false); if (err < 0) @@ -414,7 +481,12 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) } case BTF_KIND_ENUM: case BTF_KIND_FWD: - if (t->name_off != 0) { + /* + * 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; @@ -447,7 +519,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return btf_dump_order_type(d, t->type, through_ptr); case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); + const struct btf_param *p = btf_params(t); bool is_strong; err = btf_dump_order_type(d, t->type, through_ptr); @@ -455,7 +527,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return err; is_strong = err > 0; - vlen = btf_vlen_of(t); + vlen = btf_vlen(t); for (i = 0; i < vlen; i++, p++) { err = btf_dump_order_type(d, p->type, through_ptr); if (err < 0) @@ -553,12 +625,7 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) return; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); - - if (top_level_def && t->name_off == 0) { - pr_warning("unexpected nameless definition, id:[%u]\n", id); - return; - } + kind = btf_kind(t); if (tstate->emit_state == EMITTING) { if (tstate->fwd_emitted) @@ -574,8 +641,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) if (id == cont_id) return; if (t->name_off == 0) { - pr_warning("anonymous struct/union loop, id:[%u]\n", - id); + pr_warn("anonymous struct/union loop, id:[%u]\n", + id); return; } btf_dump_emit_struct_fwd(d, id, t); @@ -618,12 +685,9 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) case BTF_KIND_RESTRICT: btf_dump_emit_type(d, t->type, cont_id); break; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - btf_dump_emit_type(d, a->type, cont_id); + 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"); @@ -656,8 +720,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) * applicable */ if (top_level_def || t->name_off == 0) { - const struct btf_member *m = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + 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; @@ -678,8 +742,8 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) } break; case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); int i; btf_dump_emit_type(d, t->type, cont_id); @@ -693,65 +757,25 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) } } -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_of(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: { - const struct btf_array *a = (void *)(t + 1); - - return btf_align_of(btf, a->type); - } - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: { - const struct btf_member *m = (void *)(t + 1); - __u16 vlen = btf_vlen_of(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_warning("unsupported BTF_KIND:%u\n", btf_kind_of(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; - bool kflag; - align = btf_align_of(btf, id); + align = btf__align_of(btf, id); /* size of a non-packed struct has to be a multiple of its alignment*/ - if (t->size % align) + if (align && t->size % align) return true; - m = (void *)(t + 1); - kflag = btf_kflag_of(t); - vlen = btf_vlen_of(t); + 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 = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; - if (bit_sz == 0 && m->offset % (8 * align) != 0) + align = btf__align_of(btf, m->type); + bit_sz = btf_member_bitfield_size(t, i); + if (align && bit_sz == 0 && m->offset % (8 * align) != 0) return true; } @@ -807,7 +831,7 @@ 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_kind_of(t) == BTF_KIND_STRUCT ? "struct" : "union", + btf_is_struct(t) ? "struct" : "union", btf_dump_type_name(d, id)); } @@ -816,14 +840,12 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, const struct btf_type *t, int lvl) { - const struct btf_member *m = (void *)(t + 1); - bool kflag = btf_kflag_of(t), is_struct; + 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_of(t); + __u16 vlen = btf_vlen(t); - is_struct = btf_kind_of(t) == BTF_KIND_STRUCT; packed = is_struct ? btf_is_struct_packed(d->btf, id, t) : 0; - align = packed ? 1 : btf_align_of(d->btf, id); btf_dump_printf(d, "%s%s%s {", is_struct ? "struct" : "union", @@ -835,9 +857,9 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, int m_off, m_sz; fname = btf_name_of(d, m->name_off); - m_sz = kflag ? BTF_MEMBER_BITFIELD_SIZE(m->offset) : 0; - m_off = kflag ? BTF_MEMBER_BIT_OFFSET(m->offset) : m->offset; - align = packed ? 1 : btf_align_of(d->btf, m->type); + 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)); @@ -853,6 +875,13 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, 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)); @@ -870,8 +899,8 @@ 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 = (void *)(t+1); - __u16 vlen = btf_vlen_of(t); + const struct btf_enum *v = btf_enum(t); + __u16 vlen = btf_vlen(t); const char *name; size_t dup_cnt; int i; @@ -905,7 +934,7 @@ static void btf_dump_emit_fwd_def(struct btf_dump *d, __u32 id, { const char *name = btf_dump_type_name(d, id); - if (btf_kflag_of(t)) + if (btf_kflag(t)) btf_dump_printf(d, "union %s", name); else btf_dump_printf(d, "struct %s", name); @@ -916,6 +945,17 @@ static void btf_dump_emit_typedef_def(struct btf_dump *d, __u32 id, { 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); } @@ -981,13 +1021,27 @@ static int btf_dump_push_decl_stack_id(struct btf_dump *d, __u32 id) * of a stack frame. Some care is required to "pop" stack frames after * processing type declaration chain. */ +int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, + const struct btf_dump_emit_type_decl_opts *opts) +{ + const char *fname; + int lvl; + + if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts)) + return -EINVAL; + + fname = OPTS_GET(opts, field_name, NULL); + lvl = OPTS_GET(opts, indent_level, 0); + btf_dump_emit_type_decl(d, id, fname, lvl); + return 0; +} + 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; - __u16 kind; stack_start = d->decl_stack_cnt; for (;;) { @@ -998,7 +1052,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, * chain, restore stack, emit warning, and try to * proceed nevertheless */ - pr_warning("not enough memory for decl stack:%d", err); + pr_warn("not enough memory for decl stack:%d", err); d->decl_stack_cnt = stack_start; return; } @@ -1008,8 +1062,7 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, break; t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); - switch (kind) { + switch (btf_kind(t)) { case BTF_KIND_PTR: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: @@ -1017,12 +1070,9 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, case BTF_KIND_FUNC_PROTO: id = t->type; break; - case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); - - id = a->type; + case BTF_KIND_ARRAY: + id = btf_array(t)->type; break; - } case BTF_KIND_INT: case BTF_KIND_ENUM: case BTF_KIND_FWD: @@ -1031,8 +1081,8 @@ static void btf_dump_emit_type_decl(struct btf_dump *d, __u32 id, case BTF_KIND_TYPEDEF: goto done; default: - pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n", - kind, id); + pr_warn("unexpected type in decl chain, kind:%u, id:[%u]\n", + btf_kind(t), id); goto done; } } @@ -1070,7 +1120,7 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) id = decl_stack->ids[decl_stack->cnt - 1]; t = btf__type_by_id(d->btf, id); - switch (btf_kind_of(t)) { + switch (btf_kind(t)) { case BTF_KIND_VOLATILE: btf_dump_printf(d, "volatile "); break; @@ -1087,20 +1137,6 @@ static void btf_dump_emit_mods(struct btf_dump *d, struct id_stack *decl_stack) } } -static bool btf_is_mod_kind(const struct btf *btf, __u32 id) -{ - const struct btf_type *t = btf__type_by_id(btf, id); - - switch (btf_kind_of(t)) { - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - return true; - default: - return false; - } -} - static void btf_dump_emit_name(const struct btf_dump *d, const char *name, bool last_was_ptr) { @@ -1139,7 +1175,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, } t = btf__type_by_id(d->btf, id); - kind = btf_kind_of(t); + kind = btf_kind(t); switch (kind) { case BTF_KIND_INT: @@ -1185,7 +1221,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, btf_dump_printf(d, " restrict"); break; case BTF_KIND_ARRAY: { - const struct btf_array *a = (void *)(t + 1); + const struct btf_array *a = btf_array(t); const struct btf_type *next_t; __u32 next_id; bool multidim; @@ -1201,7 +1237,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, */ while (decls->cnt) { next_id = decls->ids[decls->cnt - 1]; - if (btf_is_mod_kind(d->btf, next_id)) + next_t = btf__type_by_id(d->btf, next_id); + if (btf_is_mod(next_t)) decls->cnt--; else break; @@ -1213,8 +1250,9 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, return; } + next_id = decls->ids[decls->cnt - 1]; next_t = btf__type_by_id(d->btf, next_id); - multidim = btf_kind_of(next_t) == BTF_KIND_ARRAY; + 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, " "); @@ -1228,8 +1266,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, return; } case BTF_KIND_FUNC_PROTO: { - const struct btf_param *p = (void *)(t + 1); - __u16 vlen = btf_vlen_of(t); + const struct btf_param *p = btf_params(t); + __u16 vlen = btf_vlen(t); int i; btf_dump_emit_mods(d, decls); @@ -1270,8 +1308,8 @@ static void btf_dump_emit_type_chain(struct btf_dump *d, return; } default: - pr_warning("unexpected type in decl chain, kind:%u, id:[%u]\n", - kind, id); + pr_warn("unexpected type in decl chain, kind:%u, id:[%u]\n", + kind, id); return; } diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c index 6122272943e6..54c30c802070 100644 --- a/tools/lib/bpf/hashmap.c +++ b/tools/lib/bpf/hashmap.c @@ -12,6 +12,9 @@ #include <linux/err.h> #include "hashmap.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + /* start with 4 buckets */ #define HASHMAP_MIN_CAP_BITS 2 diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 2b57d7ea7836..514b1a524abb 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -18,6 +18,7 @@ #include <stdarg.h> #include <libgen.h> #include <inttypes.h> +#include <limits.h> #include <string.h> #include <unistd.h> #include <endian.h> @@ -33,21 +34,29 @@ #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 <sys/resource.h> #include <tools/libc_compat.h> #include <libelf.h> #include <gelf.h> +#include <zlib.h> #include "libbpf.h" #include "bpf.h" #include "btf.h" #include "str_error.h" #include "libbpf_internal.h" +#include "hashmap.h" + +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 #ifndef EM_BPF #define EM_BPF 247 @@ -64,6 +73,12 @@ #define __printf(a, b) __attribute__((format(printf, a, b))) +static struct bpf_map *bpf_object__add_map(struct bpf_object *obj); +static struct bpf_program *bpf_object__find_prog_by_idx(struct bpf_object *obj, + int idx); +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); + static int __base_pr(enum libbpf_print_level level, const char *format, va_list args) { @@ -75,9 +90,12 @@ 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) @@ -93,14 +111,33 @@ void libbpf_print(enum libbpf_print_level level, const char *format, ...) va_end(args); } -#define STRERR_BUFSIZE 128 +static void pr_perm_msg(int err) +{ + struct rlimit limit; + char buf[100]; + + if (err != -EPERM || geteuid() != 0) + return; + + err = getrlimit(RLIMIT_MEMLOCK, &limit); + if (err) + return; + + if (limit.rlim_cur == RLIM_INFINITY) + return; + + if (limit.rlim_cur < 1024) + snprintf(buf, sizeof(buf), "%zu bytes", (size_t)limit.rlim_cur); + else if (limit.rlim_cur < 1024*1024) + snprintf(buf, sizeof(buf), "%.1f KiB", (double)limit.rlim_cur / 1024); + else + snprintf(buf, sizeof(buf), "%.1f MiB", (double)limit.rlim_cur / (1024*1024)); -#define CHECK_ERR(action, err, out) do { \ - err = action; \ - if (err) \ - goto out; \ -} while(0) + pr_warn("permission error while running as root; try raising 'ulimit -l'? current value: %s\n", + buf); +} +#define STRERR_BUFSIZE 128 /* Copied from tools/perf/util/util.h */ #ifndef zfree @@ -136,6 +173,24 @@ struct bpf_capabilities { __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; + /* BTF_FUNC_GLOBAL is supported */ + __u32 btf_func_global:1; +}; + +enum reloc_type { + RELO_LD64, + RELO_CALL, + RELO_DATA, + RELO_EXTERN, +}; + +struct reloc_desc { + enum reloc_type type; + int insn_idx; + int map_idx; + int sym_off; }; /* @@ -156,18 +211,7 @@ struct bpf_program { size_t insns_cnt, main_prog_cnt; enum bpf_prog_type type; - struct reloc_desc { - enum { - RELO_LD64, - RELO_CALL, - RELO_DATA, - } type; - int insn_idx; - union { - int map_idx; - int text_off; - }; - } *reloc_desc; + struct reloc_desc *reloc_desc; int nr_reloc; int log_level; @@ -182,6 +226,8 @@ struct bpf_program { bpf_program_clear_priv_t clear_priv; enum bpf_attach_type expected_attach_type; + __u32 attach_btf_id; + __u32 attach_prog_fd; void *func_info; __u32 func_info_rec_size; __u32 func_info_cnt; @@ -194,22 +240,51 @@ struct bpf_program { __u32 prog_flags; }; +struct bpf_struct_ops { + const char *tname; + const struct btf_type *type; + struct bpf_program **progs; + __u32 *kern_func_off; + /* e.g. struct tcp_congestion_ops in bpf_prog's btf format */ + void *data; + /* e.g. struct bpf_struct_ops_tcp_congestion_ops in + * btf_vmlinux's format. + * struct bpf_struct_ops_tcp_congestion_ops { + * [... some other kernel fields ...] + * struct tcp_congestion_ops data; + * } + * kern_vdata-size == sizeof(struct bpf_struct_ops_tcp_congestion_ops) + * bpf_map__init_kern_struct_ops() will populate the "kern_vdata" + * from "data". + */ + void *kern_vdata; + __u32 type_id; +}; + +#define DATA_SEC ".data" +#define BSS_SEC ".bss" +#define RODATA_SEC ".rodata" +#define KCONFIG_SEC ".kconfig" +#define STRUCT_OPS_SEC ".struct_ops" + enum libbpf_map_type { LIBBPF_MAP_UNSPEC, LIBBPF_MAP_DATA, LIBBPF_MAP_BSS, LIBBPF_MAP_RODATA, + LIBBPF_MAP_KCONFIG, }; static const char * const libbpf_type_to_btf_name[] = { - [LIBBPF_MAP_DATA] = ".data", - [LIBBPF_MAP_BSS] = ".bss", - [LIBBPF_MAP_RODATA] = ".rodata", + [LIBBPF_MAP_DATA] = DATA_SEC, + [LIBBPF_MAP_BSS] = BSS_SEC, + [LIBBPF_MAP_RODATA] = RODATA_SEC, + [LIBBPF_MAP_KCONFIG] = KCONFIG_SEC, }; struct bpf_map { - int fd; char *name; + int fd; int sec_idx; size_t sec_offset; int map_ifindex; @@ -217,14 +292,37 @@ struct bpf_map { struct bpf_map_def def; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 btf_vmlinux_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; enum libbpf_map_type libbpf_type; + void *mmaped; + struct bpf_struct_ops *st_ops; + char *pin_path; + bool pinned; + bool reused; }; -struct bpf_secdata { - void *rodata; - void *data; +enum extern_type { + EXT_UNKNOWN, + EXT_CHAR, + EXT_BOOL, + EXT_INT, + EXT_TRISTATE, + EXT_CHAR_ARR, +}; + +struct extern_desc { + const char *name; + int sym_idx; + int btf_id; + enum extern_type type; + int sz; + int align; + int data_off; + bool is_signed; + bool is_weak; + bool is_set; }; static LIST_HEAD(bpf_objects_list); @@ -239,7 +337,11 @@ struct bpf_object { struct bpf_map *maps; size_t nr_maps; size_t maps_cap; - struct bpf_secdata sections; + + char *kconfig; + struct extern_desc *externs; + int nr_extern; + int kconfig_map_idx; bool loaded; bool has_pseudo_calls; @@ -250,7 +352,7 @@ struct bpf_object { */ struct { int fd; - void *obj_buf; + const void *obj_buf; size_t obj_buf_sz; Elf *elf; GElf_Ehdr ehdr; @@ -258,18 +360,21 @@ struct bpf_object { Elf_Data *data; Elf_Data *rodata; Elf_Data *bss; + Elf_Data *st_ops_data; 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 symbols_shndx; int data_shndx; int rodata_shndx; int bss_shndx; + int st_ops_shndx; } efile; /* * All loaded bpf_object is linked in a list, which is @@ -279,6 +384,10 @@ struct bpf_object { struct list_head list; struct btf *btf; + /* Parse and load BTF vmlinux if any of the programs in the object need + * it at load time. + */ + struct btf *btf_vmlinux; struct btf_ext *btf_ext; void *priv; @@ -305,8 +414,8 @@ 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; @@ -357,8 +466,8 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, const size_t bpf_insn_sz = sizeof(struct bpf_insn); if (size == 0 || size % bpf_insn_sz) { - pr_warning("corrupted section '%s', size: %zu\n", - section_name, size); + pr_warn("corrupted section '%s', size: %zu\n", + section_name, size); return -EINVAL; } @@ -366,22 +475,22 @@ 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 / bpf_insn_sz; @@ -419,8 +528,8 @@ 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; } @@ -460,8 +569,8 @@ 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; } } @@ -470,41 +579,401 @@ 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; + } + } + + 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 const struct btf_member * +find_member_by_offset(const struct btf_type *t, __u32 bit_offset) +{ + struct btf_member *m; + int i; + + for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { + if (btf_member_bit_offset(t, i) == bit_offset) + return m; + } + + return NULL; +} + +static const struct btf_member * +find_member_by_name(const struct btf *btf, const struct btf_type *t, + const char *name) +{ + struct btf_member *m; + int i; + + for (i = 0, m = btf_members(t); i < btf_vlen(t); i++, m++) { + if (!strcmp(btf__name_by_offset(btf, m->name_off), name)) + return m; + } + + return NULL; +} + +#define STRUCT_OPS_VALUE_PREFIX "bpf_struct_ops_" +static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, + const char *name, __u32 kind); + +static int +find_struct_ops_kern_types(const struct btf *btf, const char *tname, + const struct btf_type **type, __u32 *type_id, + const struct btf_type **vtype, __u32 *vtype_id, + const struct btf_member **data_member) +{ + const struct btf_type *kern_type, *kern_vtype; + const struct btf_member *kern_data_member; + __s32 kern_vtype_id, kern_type_id; + __u32 i; + + kern_type_id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT); + if (kern_type_id < 0) { + pr_warn("struct_ops init_kern: struct %s is not found in kernel BTF\n", + tname); + return kern_type_id; + } + kern_type = btf__type_by_id(btf, kern_type_id); + + /* Find the corresponding "map_value" type that will be used + * in map_update(BPF_MAP_TYPE_STRUCT_OPS). For example, + * find "struct bpf_struct_ops_tcp_congestion_ops" from the + * btf_vmlinux. + */ + kern_vtype_id = find_btf_by_prefix_kind(btf, STRUCT_OPS_VALUE_PREFIX, + tname, BTF_KIND_STRUCT); + if (kern_vtype_id < 0) { + pr_warn("struct_ops init_kern: struct %s%s is not found in kernel BTF\n", + STRUCT_OPS_VALUE_PREFIX, tname); + return kern_vtype_id; + } + kern_vtype = btf__type_by_id(btf, kern_vtype_id); + + /* Find "struct tcp_congestion_ops" from + * struct bpf_struct_ops_tcp_congestion_ops { + * [ ... ] + * struct tcp_congestion_ops data; + * } + */ + kern_data_member = btf_members(kern_vtype); + for (i = 0; i < btf_vlen(kern_vtype); i++, kern_data_member++) { + if (kern_data_member->type == kern_type_id) + break; + } + if (i == btf_vlen(kern_vtype)) { + pr_warn("struct_ops init_kern: struct %s data is not found in struct %s%s\n", + tname, STRUCT_OPS_VALUE_PREFIX, tname); + return -EINVAL; + } + + *type = kern_type; + *type_id = kern_type_id; + *vtype = kern_vtype; + *vtype_id = kern_vtype_id; + *data_member = kern_data_member; + + return 0; +} + +static bool bpf_map__is_struct_ops(const struct bpf_map *map) +{ + return map->def.type == BPF_MAP_TYPE_STRUCT_OPS; +} + +/* Init the map's fields that depend on kern_btf */ +static int bpf_map__init_kern_struct_ops(struct bpf_map *map, + const struct btf *btf, + const struct btf *kern_btf) +{ + const struct btf_member *member, *kern_member, *kern_data_member; + const struct btf_type *type, *kern_type, *kern_vtype; + __u32 i, kern_type_id, kern_vtype_id, kern_data_off; + struct bpf_struct_ops *st_ops; + void *data, *kern_data; + const char *tname; + int err; + + st_ops = map->st_ops; + type = st_ops->type; + tname = st_ops->tname; + err = find_struct_ops_kern_types(kern_btf, tname, + &kern_type, &kern_type_id, + &kern_vtype, &kern_vtype_id, + &kern_data_member); + if (err) + return err; + + pr_debug("struct_ops init_kern %s: type_id:%u kern_type_id:%u kern_vtype_id:%u\n", + map->name, st_ops->type_id, kern_type_id, kern_vtype_id); + + map->def.value_size = kern_vtype->size; + map->btf_vmlinux_value_type_id = kern_vtype_id; + + st_ops->kern_vdata = calloc(1, kern_vtype->size); + if (!st_ops->kern_vdata) + return -ENOMEM; + + data = st_ops->data; + kern_data_off = kern_data_member->offset / 8; + kern_data = st_ops->kern_vdata + kern_data_off; + + member = btf_members(type); + for (i = 0; i < btf_vlen(type); i++, member++) { + const struct btf_type *mtype, *kern_mtype; + __u32 mtype_id, kern_mtype_id; + void *mdata, *kern_mdata; + __s64 msize, kern_msize; + __u32 moff, kern_moff; + __u32 kern_member_idx; + const char *mname; + + mname = btf__name_by_offset(btf, member->name_off); + kern_member = find_member_by_name(kern_btf, kern_type, mname); + if (!kern_member) { + pr_warn("struct_ops init_kern %s: Cannot find member %s in kernel BTF\n", + map->name, mname); + return -ENOTSUP; + } + + kern_member_idx = kern_member - btf_members(kern_type); + if (btf_member_bitfield_size(type, i) || + btf_member_bitfield_size(kern_type, kern_member_idx)) { + pr_warn("struct_ops init_kern %s: bitfield %s is not supported\n", + map->name, mname); + return -ENOTSUP; + } + + moff = member->offset / 8; + kern_moff = kern_member->offset / 8; + + mdata = data + moff; + kern_mdata = kern_data + kern_moff; + + mtype = skip_mods_and_typedefs(btf, member->type, &mtype_id); + kern_mtype = skip_mods_and_typedefs(kern_btf, kern_member->type, + &kern_mtype_id); + if (BTF_INFO_KIND(mtype->info) != + BTF_INFO_KIND(kern_mtype->info)) { + pr_warn("struct_ops init_kern %s: Unmatched member type %s %u != %u(kernel)\n", + map->name, mname, BTF_INFO_KIND(mtype->info), + BTF_INFO_KIND(kern_mtype->info)); + return -ENOTSUP; + } + + if (btf_is_ptr(mtype)) { + struct bpf_program *prog; + + mtype = skip_mods_and_typedefs(btf, mtype->type, &mtype_id); + kern_mtype = skip_mods_and_typedefs(kern_btf, + kern_mtype->type, + &kern_mtype_id); + if (!btf_is_func_proto(mtype) || + !btf_is_func_proto(kern_mtype)) { + pr_warn("struct_ops init_kern %s: non func ptr %s is not supported\n", + map->name, mname); + return -ENOTSUP; + } + + prog = st_ops->progs[i]; + if (!prog) { + pr_debug("struct_ops init_kern %s: func ptr %s is not set\n", + map->name, mname); + continue; + } + + prog->attach_btf_id = kern_type_id; + prog->expected_attach_type = kern_member_idx; + + st_ops->kern_func_off[i] = kern_data_off + kern_moff; + + pr_debug("struct_ops init_kern %s: func ptr %s is set to prog %s from data(+%u) to kern_data(+%u)\n", + map->name, mname, prog->name, moff, + kern_moff); + + continue; + } + + msize = btf__resolve_size(btf, mtype_id); + kern_msize = btf__resolve_size(kern_btf, kern_mtype_id); + if (msize < 0 || kern_msize < 0 || msize != kern_msize) { + pr_warn("struct_ops init_kern %s: Error in size of member %s: %zd != %zd(kernel)\n", + map->name, mname, (ssize_t)msize, + (ssize_t)kern_msize); + return -ENOTSUP; + } + + pr_debug("struct_ops init_kern %s: copy %s %u bytes from data(+%u) to kern_data(+%u)\n", + map->name, mname, (unsigned int)msize, + moff, kern_moff); + memcpy(kern_mdata, mdata, msize); + } + + return 0; +} + +static int bpf_object__init_kern_struct_ops_maps(struct bpf_object *obj) +{ + struct bpf_map *map; + size_t i; + int err; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + + if (!bpf_map__is_struct_ops(map)) + continue; + + err = bpf_map__init_kern_struct_ops(map, obj->btf, + obj->btf_vmlinux); + if (err) + return err; + } + + return 0; +} + +static int bpf_object__init_struct_ops_maps(struct bpf_object *obj) +{ + const struct btf_type *type, *datasec; + const struct btf_var_secinfo *vsi; + struct bpf_struct_ops *st_ops; + const char *tname, *var_name; + __s32 type_id, datasec_id; + const struct btf *btf; + struct bpf_map *map; + __u32 i; + + if (obj->efile.st_ops_shndx == -1) + return 0; + + btf = obj->btf; + datasec_id = btf__find_by_name_kind(btf, STRUCT_OPS_SEC, + BTF_KIND_DATASEC); + if (datasec_id < 0) { + pr_warn("struct_ops init: DATASEC %s not found\n", + STRUCT_OPS_SEC); + return -EINVAL; + } + + datasec = btf__type_by_id(btf, datasec_id); + vsi = btf_var_secinfos(datasec); + for (i = 0; i < btf_vlen(datasec); i++, vsi++) { + type = btf__type_by_id(obj->btf, vsi->type); + var_name = btf__name_by_offset(obj->btf, type->name_off); + + type_id = btf__resolve_type(obj->btf, vsi->type); + if (type_id < 0) { + pr_warn("struct_ops init: Cannot resolve var type_id %u in DATASEC %s\n", + vsi->type, STRUCT_OPS_SEC); + return -EINVAL; + } + + type = btf__type_by_id(obj->btf, type_id); + tname = btf__name_by_offset(obj->btf, type->name_off); + if (!tname[0]) { + pr_warn("struct_ops init: anonymous type is not supported\n"); + return -ENOTSUP; + } + if (!btf_is_struct(type)) { + pr_warn("struct_ops init: %s is not a struct\n", tname); + return -EINVAL; + } + + map = bpf_object__add_map(obj); + if (IS_ERR(map)) + return PTR_ERR(map); + + map->sec_idx = obj->efile.st_ops_shndx; + map->sec_offset = vsi->offset; + map->name = strdup(var_name); + if (!map->name) return -ENOMEM; + + map->def.type = BPF_MAP_TYPE_STRUCT_OPS; + map->def.key_size = sizeof(int); + map->def.value_size = type->size; + map->def.max_entries = 1; + + map->st_ops = calloc(1, sizeof(*map->st_ops)); + if (!map->st_ops) + return -ENOMEM; + st_ops = map->st_ops; + st_ops->data = malloc(type->size); + st_ops->progs = calloc(btf_vlen(type), sizeof(*st_ops->progs)); + st_ops->kern_func_off = malloc(btf_vlen(type) * + sizeof(*st_ops->kern_func_off)); + if (!st_ops->data || !st_ops->progs || !st_ops->kern_func_off) + return -ENOMEM; + + if (vsi->offset + type->size > obj->efile.st_ops_data->d_size) { + pr_warn("struct_ops init: var %s is beyond the end of DATASEC %s\n", + var_name, STRUCT_OPS_SEC); + return -EINVAL; } + + memcpy(st_ops->data, + obj->efile.st_ops_data->d_buf + vsi->offset, + type->size); + st_ops->tname = tname; + st_ops->type = type; + st_ops->type_id = type_id; + + pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n", + tname, type_id, var_name, vsi->offset); } return 0; } 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); - /* 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; + 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; /* @@ -520,7 +989,10 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.data_shndx = -1; obj->efile.rodata_shndx = -1; obj->efile.bss_shndx = -1; + obj->efile.st_ops_shndx = -1; + obj->kconfig_map_idx = -1; + obj->kern_version = get_kernel_version(); obj->loaded = false; INIT_LIST_HEAD(&obj->list); @@ -541,9 +1013,10 @@ static void bpf_object__elf_finish(struct bpf_object *obj) obj->efile.data = NULL; obj->efile.rodata = NULL; obj->efile.bss = NULL; + obj->efile.st_ops_data = 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; @@ -555,7 +1028,7 @@ 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; } @@ -564,7 +1037,7 @@ 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); @@ -573,7 +1046,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) err = -errno; cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warning("failed to open %s: %s\n", obj->path, cp); + pr_warn("failed to open %s: %s\n", obj->path, cp); return err; } @@ -582,13 +1055,13 @@ static int bpf_object__elf_init(struct bpf_object *obj) } 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; } @@ -597,7 +1070,7 @@ static int bpf_object__elf_init(struct bpf_object *obj) /* 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); + pr_warn("%s is not an eBPF object file\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; goto errout; } @@ -619,7 +1092,7 @@ static int bpf_object__check_endianness(struct bpf_object *obj) #else # error "Unrecognized __BYTE_ORDER__" #endif - pr_warning("endianness mismatch.\n"); + pr_warn("endianness mismatch.\n"); return -LIBBPF_ERRNO__ENDIAN; } @@ -637,7 +1110,7 @@ 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)); @@ -646,16 +1119,6 @@ bpf_object__init_kversion(struct bpf_object *obj, void *data, size_t size) return 0; } -static int compare_bpf_map(const void *_a, const void *_b) -{ - const struct bpf_map *a = _a; - const struct bpf_map *b = _b; - - 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) { if (type == BPF_MAP_TYPE_ARRAY_OF_MAPS || @@ -679,15 +1142,15 @@ static int bpf_object_search_section_size(const struct bpf_object *obj, idx++; if (gelf_getshdr(scn, &sh) != &sh) { - pr_warning("failed to get section(%d) header from %s\n", - idx, obj->path); + 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_warning("failed to get section(%d) name from %s\n", - idx, obj->path); + pr_warn("failed to get section(%d) name from %s\n", + idx, obj->path); return -EIO; } @@ -696,8 +1159,8 @@ static int bpf_object_search_section_size(const struct bpf_object *obj, data = elf_getdata(scn, 0); if (!data) { - pr_warning("failed to get section(%d) data from %s(%s)\n", - idx, name, obj->path); + pr_warn("failed to get section(%d) data from %s(%s)\n", + idx, name, obj->path); return -EIO; } @@ -717,15 +1180,18 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name, *size = 0; if (!name) { return -EINVAL; - } else if (!strcmp(name, ".data")) { + } else if (!strcmp(name, DATA_SEC)) { if (obj->efile.data) *size = obj->efile.data->d_size; - } else if (!strcmp(name, ".bss")) { + } else if (!strcmp(name, BSS_SEC)) { if (obj->efile.bss) *size = obj->efile.bss->d_size; - } else if (!strcmp(name, ".rodata")) { + } else if (!strcmp(name, RODATA_SEC)) { if (obj->efile.rodata) *size = obj->efile.rodata->d_size; + } else if (!strcmp(name, STRUCT_OPS_SEC)) { + if (obj->efile.st_ops_data) + *size = obj->efile.st_ops_data->d_size; } else { ret = bpf_object_search_section_size(obj, name, &d_size); if (!ret) @@ -757,8 +1223,8 @@ int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name); if (!sname) { - pr_warning("failed to get sym name string for var %s\n", - name); + pr_warn("failed to get sym name string for var %s\n", + name); return -EIO; } if (strcmp(name, sname) == 0) { @@ -782,7 +1248,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) 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_warning("alloc maps for object failed\n"); + pr_warn("alloc maps for object failed\n"); return ERR_PTR(-ENOMEM); } @@ -804,13 +1270,38 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) return &obj->maps[obj->nr_maps++]; } +static size_t bpf_map_mmap_sz(const struct bpf_map *map) +{ + long page_sz = sysconf(_SC_PAGE_SIZE); + size_t map_sz; + + map_sz = (size_t)roundup(map->def.value_size, 8) * map->def.max_entries; + map_sz = roundup(map_sz, page_sz); + return map_sz; +} + +static char *internal_map_name(struct bpf_object *obj, + enum libbpf_map_type type) +{ + char map_name[BPF_OBJ_NAME_LEN]; + const char *sfx = libbpf_type_to_btf_name[type]; + int sfx_len = max((size_t)7, strlen(sfx)); + int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, + strlen(obj->name)); + + snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name, + sfx_len, libbpf_type_to_btf_name[type]); + + return strdup(map_name); +} + static int bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, - int sec_idx, Elf_Data *data, void **data_buff) + int sec_idx, void *data, size_t data_sz) { - char map_name[BPF_OBJ_NAME_LEN]; struct bpf_map_def *def; struct bpf_map *map; + int err; map = bpf_object__add_map(obj); if (IS_ERR(map)) @@ -819,32 +1310,38 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type, 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); + map->name = internal_map_name(obj, type); if (!map->name) { - pr_warning("failed to alloc map name\n"); + pr_warn("failed to alloc map name\n"); return -ENOMEM; } - pr_debug("map '%s' (global data): at sec_idx %d, offset %zu.\n", - map_name, map->sec_idx, map->sec_offset); def = &map->def; def->type = BPF_MAP_TYPE_ARRAY; def->key_size = sizeof(int); - def->value_size = data->d_size; + def->value_size = data_sz; def->max_entries = 1; - def->map_flags = type == LIBBPF_MAP_RODATA ? BPF_F_RDONLY_PROG : 0; - if (data_buff) { - *data_buff = malloc(data->d_size); - if (!*data_buff) { - zfree(&map->name); - pr_warning("failed to alloc map content buffer\n"); - return -ENOMEM; - } - memcpy(*data_buff, data->d_buf, data->d_size); + def->map_flags = type == LIBBPF_MAP_RODATA || type == LIBBPF_MAP_KCONFIG + ? BPF_F_RDONLY_PROG : 0; + 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); + + map->mmaped = mmap(NULL, bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + if (map->mmaped == MAP_FAILED) { + err = -errno; + map->mmaped = NULL; + pr_warn("failed to alloc map '%s' content buffer: %d\n", + map->name, err); + zfree(&map->name); + return err; } + if (data) + memcpy(map->mmaped, data, data_sz); + pr_debug("map %td is \"%s\"\n", map - obj->maps, map->name); return 0; } @@ -853,37 +1350,332 @@ 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); + obj->efile.data->d_buf, + obj->efile.data->d_size); 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); + obj->efile.rodata->d_buf, + obj->efile.rodata->d_size); 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); + NULL, + obj->efile.bss->d_size); if (err) return err; } return 0; } + +static struct extern_desc *find_extern_by_name(const struct bpf_object *obj, + const void *name) +{ + int i; + + for (i = 0; i < obj->nr_extern; i++) { + if (strcmp(obj->externs[i].name, name) == 0) + return &obj->externs[i]; + } + return NULL; +} + +static int set_ext_value_tri(struct extern_desc *ext, void *ext_val, + char value) +{ + switch (ext->type) { + case EXT_BOOL: + if (value == 'm') { + pr_warn("extern %s=%c should be tristate or char\n", + ext->name, value); + return -EINVAL; + } + *(bool *)ext_val = value == 'y' ? true : false; + break; + case EXT_TRISTATE: + if (value == 'y') + *(enum libbpf_tristate *)ext_val = TRI_YES; + else if (value == 'm') + *(enum libbpf_tristate *)ext_val = TRI_MODULE; + else /* value == 'n' */ + *(enum libbpf_tristate *)ext_val = TRI_NO; + break; + case EXT_CHAR: + *(char *)ext_val = value; + break; + case EXT_UNKNOWN: + case EXT_INT: + case EXT_CHAR_ARR: + default: + pr_warn("extern %s=%c should be bool, tristate, or char\n", + ext->name, value); + return -EINVAL; + } + ext->is_set = true; + return 0; +} + +static int set_ext_value_str(struct extern_desc *ext, char *ext_val, + const char *value) +{ + size_t len; + + if (ext->type != EXT_CHAR_ARR) { + pr_warn("extern %s=%s should char array\n", ext->name, value); + return -EINVAL; + } + + len = strlen(value); + if (value[len - 1] != '"') { + pr_warn("extern '%s': invalid string config '%s'\n", + ext->name, value); + return -EINVAL; + } + + /* strip quotes */ + len -= 2; + if (len >= ext->sz) { + pr_warn("extern '%s': long string config %s of (%zu bytes) truncated to %d bytes\n", + ext->name, value, len, ext->sz - 1); + len = ext->sz - 1; + } + memcpy(ext_val, value + 1, len); + ext_val[len] = '\0'; + ext->is_set = true; + return 0; +} + +static int parse_u64(const char *value, __u64 *res) +{ + char *value_end; + int err; + + errno = 0; + *res = strtoull(value, &value_end, 0); + if (errno) { + err = -errno; + pr_warn("failed to parse '%s' as integer: %d\n", value, err); + return err; + } + if (*value_end) { + pr_warn("failed to parse '%s' as integer completely\n", value); + return -EINVAL; + } + return 0; +} + +static bool is_ext_value_in_range(const struct extern_desc *ext, __u64 v) +{ + int bit_sz = ext->sz * 8; + + if (ext->sz == 8) + return true; + + /* Validate that value stored in u64 fits in integer of `ext->sz` + * bytes size without any loss of information. If the target integer + * is signed, we rely on the following limits of integer type of + * Y bits and subsequent transformation: + * + * -2^(Y-1) <= X <= 2^(Y-1) - 1 + * 0 <= X + 2^(Y-1) <= 2^Y - 1 + * 0 <= X + 2^(Y-1) < 2^Y + * + * For unsigned target integer, check that all the (64 - Y) bits are + * zero. + */ + if (ext->is_signed) + return v + (1ULL << (bit_sz - 1)) < (1ULL << bit_sz); + else + return (v >> bit_sz) == 0; +} + +static int set_ext_value_num(struct extern_desc *ext, void *ext_val, + __u64 value) +{ + if (ext->type != EXT_INT && ext->type != EXT_CHAR) { + pr_warn("extern %s=%llu should be integer\n", + ext->name, (unsigned long long)value); + return -EINVAL; + } + if (!is_ext_value_in_range(ext, value)) { + pr_warn("extern %s=%llu value doesn't fit in %d bytes\n", + ext->name, (unsigned long long)value, ext->sz); + return -ERANGE; + } + switch (ext->sz) { + case 1: *(__u8 *)ext_val = value; break; + case 2: *(__u16 *)ext_val = value; break; + case 4: *(__u32 *)ext_val = value; break; + case 8: *(__u64 *)ext_val = value; break; + default: + return -EINVAL; + } + ext->is_set = true; + return 0; +} + +static int bpf_object__process_kconfig_line(struct bpf_object *obj, + char *buf, void *data) +{ + struct extern_desc *ext; + char *sep, *value; + int len, err = 0; + void *ext_val; + __u64 num; + + if (strncmp(buf, "CONFIG_", 7)) + return 0; + + sep = strchr(buf, '='); + if (!sep) { + pr_warn("failed to parse '%s': no separator\n", buf); + return -EINVAL; + } + + /* Trim ending '\n' */ + len = strlen(buf); + if (buf[len - 1] == '\n') + buf[len - 1] = '\0'; + /* Split on '=' and ensure that a value is present. */ + *sep = '\0'; + if (!sep[1]) { + *sep = '='; + pr_warn("failed to parse '%s': no value\n", buf); + return -EINVAL; + } + + ext = find_extern_by_name(obj, buf); + if (!ext || ext->is_set) + return 0; + + ext_val = data + ext->data_off; + value = sep + 1; + + switch (*value) { + case 'y': case 'n': case 'm': + err = set_ext_value_tri(ext, ext_val, *value); + break; + case '"': + err = set_ext_value_str(ext, ext_val, value); + break; + default: + /* assume integer */ + err = parse_u64(value, &num); + if (err) { + pr_warn("extern %s=%s should be integer\n", + ext->name, value); + return err; + } + err = set_ext_value_num(ext, ext_val, num); + break; + } + if (err) + return err; + pr_debug("extern %s=%s\n", ext->name, value); + return 0; +} + +static int bpf_object__read_kconfig_file(struct bpf_object *obj, void *data) +{ + char buf[PATH_MAX]; + struct utsname uts; + int len, err = 0; + gzFile file; + + uname(&uts); + len = snprintf(buf, PATH_MAX, "/boot/config-%s", uts.release); + if (len < 0) + return -EINVAL; + else if (len >= PATH_MAX) + return -ENAMETOOLONG; + + /* gzopen also accepts uncompressed files. */ + file = gzopen(buf, "r"); + if (!file) + file = gzopen("/proc/config.gz", "r"); + + if (!file) { + pr_warn("failed to open system Kconfig\n"); + return -ENOENT; + } + + while (gzgets(file, buf, sizeof(buf))) { + err = bpf_object__process_kconfig_line(obj, buf, data); + if (err) { + pr_warn("error parsing system Kconfig line '%s': %d\n", + buf, err); + goto out; + } + } + +out: + gzclose(file); + return err; +} + +static int bpf_object__read_kconfig_mem(struct bpf_object *obj, + const char *config, void *data) +{ + char buf[PATH_MAX]; + int err = 0; + FILE *file; + + file = fmemopen((void *)config, strlen(config), "r"); + if (!file) { + err = -errno; + pr_warn("failed to open in-memory Kconfig: %d\n", err); + return err; + } + + while (fgets(buf, sizeof(buf), file)) { + err = bpf_object__process_kconfig_line(obj, buf, data); + if (err) { + pr_warn("error parsing in-memory Kconfig line '%s': %d\n", + buf, err); + break; + } + } + + fclose(file); + return err; +} + +static int bpf_object__init_kconfig_map(struct bpf_object *obj) +{ + struct extern_desc *last_ext; + size_t map_sz; + int err; + + if (obj->nr_extern == 0) + return 0; + + last_ext = &obj->externs[obj->nr_extern - 1]; + map_sz = last_ext->data_off + last_ext->sz; + + err = bpf_object__init_internal_map(obj, LIBBPF_MAP_KCONFIG, + obj->efile.symbols_shndx, + NULL, map_sz); + if (err) + return err; + + obj->kconfig_map_idx = obj->nr_maps - 1; + + return 0; +} + static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) { Elf_Data *symbols = obj->efile.symbols; @@ -901,8 +1693,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) 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; } @@ -927,13 +1719,12 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path, nr_maps, data->d_size); - 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); + 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; i < nr_syms; i++) { @@ -954,8 +1745,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) map_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name); if (!map_name) { - pr_warning("failed to get map #%d name sym string for obj %s\n", - i, obj->path); + pr_warn("failed to get map #%d name sym string for obj %s\n", + i, obj->path); return -LIBBPF_ERRNO__FORMAT; } @@ -965,14 +1756,14 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) 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; } map->name = strdup(map_name); if (!map->name) { - pr_warning("failed to alloc map name\n"); + pr_warn("failed to alloc map name\n"); return -ENOMEM; } pr_debug("map %d is \"%s\"\n", i, map->name); @@ -993,13 +1784,12 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) * 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; } @@ -1010,23 +1800,35 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return 0; } -static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, - __u32 id) +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); - while (true) { - switch (BTF_INFO_KIND(t->info)) { - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - case BTF_KIND_TYPEDEF: - t = btf__type_by_id(btf, t->type); - break; - default: - return t; - } + 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; +} + +static const struct btf_type * +resolve_func_ptr(const struct btf *btf, __u32 id, __u32 *res_id) +{ + const struct btf_type *t; + + t = skip_mods_and_typedefs(btf, id, NULL); + if (!btf_is_ptr(t)) + return NULL; + + t = skip_mods_and_typedefs(btf, t->type, res_id); + + return btf_is_func_proto(t) ? t : NULL; } /* @@ -1038,38 +1840,61 @@ static const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, */ 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); + 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_INFO_KIND(t->info) != BTF_KIND_PTR) { - pr_warning("map '%s': attr '%s': expected PTR, got %u.\n", - map_name, name, BTF_INFO_KIND(t->info)); + 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_warning("map '%s': attr '%s': type [%u] not found.\n", - map_name, name, t->type); + pr_warn("map '%s': attr '%s': type [%u] not found.\n", + map_name, name, t->type); return false; } - if (BTF_INFO_KIND(arr_t->info) != BTF_KIND_ARRAY) { - pr_warning("map '%s': attr '%s': expected ARRAY, got %u.\n", - map_name, name, BTF_INFO_KIND(arr_t->info)); + 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 = (const void *)(arr_t + 1); + 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 Elf_Data *data, bool strict, + const char *pin_root_path) { const struct btf_type *var, *def, *t; const struct btf_var_secinfo *vi; @@ -1079,40 +1904,40 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, struct bpf_map *map; int vlen, i; - vi = (const struct btf_var_secinfo *)(const void *)(sec + 1) + var_idx; + vi = btf_var_secinfos(sec) + var_idx; var = btf__type_by_id(obj->btf, vi->type); - var_extra = (const void *)(var + 1); + var_extra = btf_var(var); map_name = btf__name_by_offset(obj->btf, var->name_off); - vlen = BTF_INFO_VLEN(var->info); + vlen = btf_vlen(var); if (map_name == NULL || map_name[0] == '\0') { - pr_warning("map #%d: empty name.\n", var_idx); + pr_warn("map #%d: empty name.\n", var_idx); return -EINVAL; } if ((__u64)vi->offset + vi->size > data->d_size) { - pr_warning("map '%s' BTF data is corrupted.\n", map_name); + pr_warn("map '%s' BTF data is corrupted.\n", map_name); return -EINVAL; } - if (BTF_INFO_KIND(var->info) != BTF_KIND_VAR) { - pr_warning("map '%s': unexpected var kind %u.\n", - map_name, BTF_INFO_KIND(var->info)); + 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_warning("map '%s': unsupported var linkage %u.\n", - map_name, var_extra->linkage); + 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); - if (BTF_INFO_KIND(def->info) != BTF_KIND_STRUCT) { - pr_warning("map '%s': unexpected def kind %u.\n", - map_name, BTF_INFO_KIND(var->info)); + 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_warning("map '%s': invalid def size.\n", map_name); + pr_warn("map '%s': invalid def size.\n", map_name); return -EINVAL; } @@ -1121,7 +1946,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, return PTR_ERR(map); map->name = strdup(map_name); if (!map->name) { - pr_warning("map '%s': failed to alloc map name.\n", map_name); + pr_warn("map '%s': failed to alloc map name.\n", map_name); return -ENOMEM; } map->libbpf_type = LIBBPF_MAP_UNSPEC; @@ -1131,14 +1956,13 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': at sec_idx %d, offset %zu.\n", map_name, map->sec_idx, map->sec_offset); - vlen = BTF_INFO_VLEN(def->info); - m = (const void *)(def + 1); + 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_warning("map '%s': invalid field #%d.\n", - map_name, i); + pr_warn("map '%s': invalid field #%d.\n", map_name, i); return -EINVAL; } if (strcmp(name, "type") == 0) { @@ -1168,8 +1992,8 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': found key_size = %u.\n", map_name, sz); if (map->def.key_size && map->def.key_size != sz) { - pr_warning("map '%s': conflicting key size %u != %u.\n", - map_name, 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; @@ -1178,26 +2002,26 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, t = btf__type_by_id(obj->btf, m->type); if (!t) { - pr_warning("map '%s': key type [%d] not found.\n", - map_name, m->type); + pr_warn("map '%s': key type [%d] not found.\n", + map_name, m->type); return -EINVAL; } - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { - pr_warning("map '%s': key spec is not PTR: %u.\n", - map_name, BTF_INFO_KIND(t->info)); + 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_warning("map '%s': can't determine key size for type [%u]: %lld.\n", - map_name, t->type, sz); + pr_warn("map '%s': can't determine key size for type [%u]: %zd.\n", + map_name, t->type, (ssize_t)sz); return sz; } - pr_debug("map '%s': found key [%u], sz = %lld.\n", - map_name, t->type, sz); + pr_debug("map '%s': found key [%u], sz = %zd.\n", + map_name, t->type, (ssize_t)sz); if (map->def.key_size && map->def.key_size != sz) { - pr_warning("map '%s': conflicting key size %u != %lld.\n", - map_name, map->def.key_size, sz); + pr_warn("map '%s': conflicting key size %u != %zd.\n", + map_name, map->def.key_size, (ssize_t)sz); return -EINVAL; } map->def.key_size = sz; @@ -1211,8 +2035,8 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': found value_size = %u.\n", map_name, sz); if (map->def.value_size && map->def.value_size != sz) { - pr_warning("map '%s': conflicting value size %u != %u.\n", - map_name, 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; @@ -1221,34 +2045,58 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, t = btf__type_by_id(obj->btf, m->type); if (!t) { - pr_warning("map '%s': value type [%d] not found.\n", - map_name, m->type); + pr_warn("map '%s': value type [%d] not found.\n", + map_name, m->type); return -EINVAL; } - if (BTF_INFO_KIND(t->info) != BTF_KIND_PTR) { - pr_warning("map '%s': value spec is not PTR: %u.\n", - map_name, BTF_INFO_KIND(t->info)); + 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_warning("map '%s': can't determine value size for type [%u]: %lld.\n", - map_name, t->type, sz); + pr_warn("map '%s': can't determine value size for type [%u]: %zd.\n", + map_name, t->type, (ssize_t)sz); return sz; } - pr_debug("map '%s': found value [%u], sz = %lld.\n", - map_name, t->type, sz); + pr_debug("map '%s': found value [%u], sz = %zd.\n", + map_name, t->type, (ssize_t)sz); if (map->def.value_size && map->def.value_size != sz) { - pr_warning("map '%s': conflicting value size %u != %lld.\n", - map_name, map->def.value_size, sz); + pr_warn("map '%s': conflicting value size %u != %zd.\n", + map_name, map->def.value_size, (ssize_t)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_warning("map '%s': unknown field '%s'.\n", - map_name, name); + pr_warn("map '%s': unknown field '%s'.\n", + map_name, name); return -ENOTSUP; } pr_debug("map '%s': ignoring unknown field '%s'.\n", @@ -1257,14 +2105,15 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, } if (map->def.type == BPF_MAP_TYPE_UNSPEC) { - pr_warning("map '%s': map type isn't specified.\n", map_name); + 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) +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; @@ -1280,15 +2129,15 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) if (scn) data = elf_getdata(scn, NULL); if (!scn || !data) { - pr_warning("failed to get Elf_Data from map section %d (%s)\n", - obj->efile.maps_shndx, MAPS_ELF_SEC); + 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_INFO_KIND(t->info) != BTF_KIND_DATASEC) + if (!btf_is_datasec(t)) continue; name = btf__name_by_offset(obj->btf, t->name_off); if (strcmp(name, MAPS_ELF_SEC) == 0) { @@ -1298,15 +2147,16 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) } if (!sec) { - pr_warning("DATASEC '%s' not found.\n", MAPS_ELF_SEC); + pr_warn("DATASEC '%s' not found.\n", MAPS_ELF_SEC); return -ENOENT; } - vlen = BTF_INFO_VLEN(sec->info); + 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); + data, strict, + pin_root_path); if (err) return err; } @@ -1314,27 +2164,24 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict) return 0; } -static int bpf_object__init_maps(struct bpf_object *obj, int flags) +static int bpf_object__init_maps(struct bpf_object *obj, + const struct bpf_object_open_opts *opts) { - bool strict = !(flags & MAPS_RELAX_COMPAT); + const char *pin_root_path; + bool strict; int err; - err = bpf_object__init_user_maps(obj, strict); - if (err) - return err; + strict = !OPTS_GET(opts, relaxed_maps, false); + pin_root_path = OPTS_GET(opts, pin_root_path, NULL); - err = bpf_object__init_user_btf_maps(obj, strict); - if (err) - return err; - - err = bpf_object__init_global_data_maps(obj); + err = bpf_object__init_user_maps(obj, strict); + err = err ?: bpf_object__init_user_btf_maps(obj, strict, pin_root_path); + err = err ?: bpf_object__init_global_data_maps(obj); + err = err ?: bpf_object__init_kconfig_map(obj); + err = err ?: bpf_object__init_struct_ops_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; } @@ -1358,21 +2205,20 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) static void bpf_object__sanitize_btf(struct bpf_object *obj) { + bool has_func_global = obj->caps.btf_func_global; 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; - __u16 kind; - if (!obj->btf || (has_func && has_datasec)) + if (!obj->btf || (has_func && has_datasec && has_func_global)) return; for (i = 1; i <= btf__get_nr_types(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); - kind = BTF_INFO_KIND(t->info); - if (!has_datasec && kind == BTF_KIND_VAR) { + if (!has_datasec && btf_is_var(t)) { /* replace VAR with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); /* @@ -1381,11 +2227,11 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) * original variable took less than 4 bytes */ t->size = 1; - *(int *)(t+1) = BTF_INT_ENC(0, 0, 8); - } else if (!has_datasec && kind == BTF_KIND_DATASEC) { + *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8); + } else if (!has_datasec && btf_is_datasec(t)) { /* replace DATASEC with STRUCT */ - struct btf_var_secinfo *v = (void *)(t + 1); - struct btf_member *m = (void *)(t + 1); + const struct btf_var_secinfo *v = btf_var_secinfos(t); + struct btf_member *m = btf_members(t); struct btf_type *vt; char *name; @@ -1396,7 +2242,7 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) name++; } - vlen = BTF_INFO_VLEN(t->info); + 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 */ @@ -1406,14 +2252,17 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj) vt = (void *)btf__type_by_id(btf, v->type); m->name_off = vt->name_off; } - } else if (!has_func && kind == BTF_KIND_FUNC_PROTO) { + } else if (!has_func && btf_is_func_proto(t)) { /* replace FUNC_PROTO with ENUM */ - vlen = BTF_INFO_VLEN(t->info); + vlen = btf_vlen(t); t->info = BTF_INFO_ENC(BTF_KIND_ENUM, 0, vlen); t->size = sizeof(__u32); /* kernel enforced */ - } else if (!has_func && kind == BTF_KIND_FUNC) { + } else if (!has_func && btf_is_func(t)) { /* replace FUNC with TYPEDEF */ t->info = BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0); + } else if (!has_func_global && btf_is_func(t)) { + /* replace BTF_FUNC_GLOBAL with BTF_FUNC_STATIC */ + t->info = BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0); } } } @@ -1431,29 +2280,27 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) { - return obj->efile.btf_maps_shndx >= 0; + return obj->efile.btf_maps_shndx >= 0 || + obj->efile.st_ops_shndx >= 0 || + obj->nr_extern > 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; + int err = -ENOENT; if (btf_data) { obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); if (IS_ERR(obj->btf)) { - pr_warning("Error loading ELF section %s: %d.\n", - BTF_ELF_SEC, err); - goto out; - } - err = btf__finalize_data(obj, obj->btf); - if (err) { - pr_warning("Error finalizing %s: %d.\n", - BTF_ELF_SEC, err); + err = PTR_ERR(obj->btf); + obj->btf = NULL; + pr_warn("Error loading ELF section %s: %d.\n", + BTF_ELF_SEC, err); goto out; } + err = 0; } if (btf_ext_data) { if (!obj->btf) { @@ -1464,29 +2311,79 @@ static int bpf_object__init_btf(struct bpf_object *obj, obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); 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)); + 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 (err && bpf_object__is_btf_mandatory(obj)) { + pr_warn("BTF is required, but is missing or corrupted.\n"); + return err; } - if (btf_required && !obj->btf) { - pr_warning("BTF is required, but is missing or corrupted.\n"); - return err == 0 ? -ENOENT : err; + return 0; +} + +static int bpf_object__finalize_btf(struct bpf_object *obj) +{ + int err; + + if (!obj->btf) + return 0; + + err = btf__finalize_data(obj, obj->btf); + if (!err) + return 0; + + pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err); + btf__free(obj->btf); + obj->btf = NULL; + btf_ext__free(obj->btf_ext); + obj->btf_ext = NULL; + + if (bpf_object__is_btf_mandatory(obj)) { + pr_warn("BTF is required, but is missing or corrupted.\n"); + return -ENOENT; } return 0; } +static inline bool libbpf_prog_needs_vmlinux_btf(struct bpf_program *prog) +{ + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) + return true; + + /* BPF_PROG_TYPE_TRACING programs which do not attach to other programs + * also need vmlinux BTF + */ + if (prog->type == BPF_PROG_TYPE_TRACING && !prog->attach_prog_fd) + return true; + + return false; +} + +static int bpf_object__load_vmlinux_btf(struct bpf_object *obj) +{ + struct bpf_program *prog; + int err; + + bpf_object__for_each_program(prog, obj) { + if (libbpf_prog_needs_vmlinux_btf(prog)) { + obj->btf_vmlinux = libbpf_find_kernel_btf(); + if (IS_ERR(obj->btf_vmlinux)) { + err = PTR_ERR(obj->btf_vmlinux); + pr_warn("Error loading vmlinux BTF: %d\n", err); + obj->btf_vmlinux = NULL; + return err; + } + return 0; + } + } + + return 0; +} + static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) { int err = 0; @@ -1499,8 +2396,8 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) err = btf__load(obj->btf); if (err) { - pr_warning("Error loading %s into kernel: %d.\n", - BTF_ELF_SEC, 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 */ @@ -1515,7 +2412,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) return 0; } -static int bpf_object__elf_collect(struct bpf_object *obj, int flags) +static int bpf_object__elf_collect(struct bpf_object *obj) { Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; @@ -1526,7 +2423,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) /* 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; } @@ -1537,22 +2434,22 @@ 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); + 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); + 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); + 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", @@ -1582,61 +2479,69 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) 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); + pr_warn("bpf: multiple SYMTAB in %s\n", + obj->path); return -LIBBPF_ERRNO__FORMAT; } obj->efile.symbols = data; + obj->efile.symbols_shndx = idx; 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); + data->d_size, + name, idx); if (err) { char errmsg[STRERR_BUFSIZE]; - char *cp = libbpf_strerror_r(-err, errmsg, - sizeof(errmsg)); + char *cp; - pr_warning("failed to alloc program %s (%s): %s", - name, obj->path, 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) { + } else if (strcmp(name, DATA_SEC) == 0) { obj->efile.data = data; obj->efile.data_shndx = idx; - } else if (strcmp(name, ".rodata") == 0) { + } else if (strcmp(name, RODATA_SEC) == 0) { obj->efile.rodata = data; obj->efile.rodata_shndx = idx; + } else if (strcmp(name, STRUCT_OPS_SEC) == 0) { + obj->efile.st_ops_data = data; + obj->efile.st_ops_shndx = idx; } else { pr_debug("skip section(%d) %s\n", idx, name); } } else if (sh.sh_type == SHT_REL) { - int nr_reloc = obj->efile.nr_reloc; - void *reloc = obj->efile.reloc; + 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 */ - if (!section_have_execinstr(obj, sec)) { + if (!section_have_execinstr(obj, sec) && + strcmp(name, ".rel" STRUCT_OPS_SEC)) { pr_debug("skip relo %s(%d) for section(%d)\n", name, idx, sec); continue; } - reloc = reallocarray(reloc, nr_reloc + 1, - sizeof(*obj->efile.reloc)); - if (!reloc) { - pr_warning("realloc failed\n"); + 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++; + obj->efile.reloc_sects = sects; + obj->efile.nr_reloc_sects++; - obj->efile.reloc[nr_reloc].shdr = sh; - obj->efile.reloc[nr_reloc].data = data; - } else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) { + 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_SEC) == 0) { obj->efile.bss = data; obj->efile.bss_shndx = idx; } else { @@ -1644,18 +2549,221 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) } } - if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) { - pr_warning("Corrupted ELF file: index of strtab invalid\n"); + 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_btf(obj, btf_data, btf_ext_data); - if (!err) - err = bpf_object__init_maps(obj, flags); - if (!err) - err = bpf_object__sanitize_and_load_btf(obj); - if (!err) - err = bpf_object__init_prog_names(obj); - return err; + return bpf_object__init_btf(obj, btf_data, btf_ext_data); +} + +static bool sym_is_extern(const GElf_Sym *sym) +{ + int bind = GELF_ST_BIND(sym->st_info); + /* externs are symbols w/ type=NOTYPE, bind=GLOBAL|WEAK, section=UND */ + return sym->st_shndx == SHN_UNDEF && + (bind == STB_GLOBAL || bind == STB_WEAK) && + GELF_ST_TYPE(sym->st_info) == STT_NOTYPE; +} + +static int find_extern_btf_id(const struct btf *btf, const char *ext_name) +{ + const struct btf_type *t; + const char *var_name; + int i, n; + + if (!btf) + return -ESRCH; + + n = btf__get_nr_types(btf); + for (i = 1; i <= n; i++) { + t = btf__type_by_id(btf, i); + + if (!btf_is_var(t)) + continue; + + var_name = btf__name_by_offset(btf, t->name_off); + if (strcmp(var_name, ext_name)) + continue; + + if (btf_var(t)->linkage != BTF_VAR_GLOBAL_EXTERN) + return -EINVAL; + + return i; + } + + return -ENOENT; +} + +static enum extern_type find_extern_type(const struct btf *btf, int id, + bool *is_signed) +{ + const struct btf_type *t; + const char *name; + + t = skip_mods_and_typedefs(btf, id, NULL); + name = btf__name_by_offset(btf, t->name_off); + + if (is_signed) + *is_signed = false; + switch (btf_kind(t)) { + case BTF_KIND_INT: { + int enc = btf_int_encoding(t); + + if (enc & BTF_INT_BOOL) + return t->size == 1 ? EXT_BOOL : EXT_UNKNOWN; + if (is_signed) + *is_signed = enc & BTF_INT_SIGNED; + if (t->size == 1) + return EXT_CHAR; + if (t->size < 1 || t->size > 8 || (t->size & (t->size - 1))) + return EXT_UNKNOWN; + return EXT_INT; + } + case BTF_KIND_ENUM: + if (t->size != 4) + return EXT_UNKNOWN; + if (strcmp(name, "libbpf_tristate")) + return EXT_UNKNOWN; + return EXT_TRISTATE; + case BTF_KIND_ARRAY: + if (btf_array(t)->nelems == 0) + return EXT_UNKNOWN; + if (find_extern_type(btf, btf_array(t)->type, NULL) != EXT_CHAR) + return EXT_UNKNOWN; + return EXT_CHAR_ARR; + default: + return EXT_UNKNOWN; + } +} + +static int cmp_externs(const void *_a, const void *_b) +{ + const struct extern_desc *a = _a; + const struct extern_desc *b = _b; + + /* descending order by alignment requirements */ + if (a->align != b->align) + return a->align > b->align ? -1 : 1; + /* ascending order by size, within same alignment class */ + if (a->sz != b->sz) + return a->sz < b->sz ? -1 : 1; + /* resolve ties by name */ + return strcmp(a->name, b->name); +} + +static int bpf_object__collect_externs(struct bpf_object *obj) +{ + const struct btf_type *t; + struct extern_desc *ext; + int i, n, off, btf_id; + struct btf_type *sec; + const char *ext_name; + Elf_Scn *scn; + GElf_Shdr sh; + + if (!obj->efile.symbols) + return 0; + + scn = elf_getscn(obj->efile.elf, obj->efile.symbols_shndx); + if (!scn) + return -LIBBPF_ERRNO__FORMAT; + if (gelf_getshdr(scn, &sh) != &sh) + return -LIBBPF_ERRNO__FORMAT; + n = sh.sh_size / sh.sh_entsize; + + pr_debug("looking for externs among %d symbols...\n", n); + for (i = 0; i < n; i++) { + GElf_Sym sym; + + if (!gelf_getsym(obj->efile.symbols, i, &sym)) + return -LIBBPF_ERRNO__FORMAT; + if (!sym_is_extern(&sym)) + continue; + ext_name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name); + if (!ext_name || !ext_name[0]) + continue; + + ext = obj->externs; + ext = reallocarray(ext, obj->nr_extern + 1, sizeof(*ext)); + if (!ext) + return -ENOMEM; + obj->externs = ext; + ext = &ext[obj->nr_extern]; + memset(ext, 0, sizeof(*ext)); + obj->nr_extern++; + + ext->btf_id = find_extern_btf_id(obj->btf, ext_name); + if (ext->btf_id <= 0) { + pr_warn("failed to find BTF for extern '%s': %d\n", + ext_name, ext->btf_id); + return ext->btf_id; + } + t = btf__type_by_id(obj->btf, ext->btf_id); + ext->name = btf__name_by_offset(obj->btf, t->name_off); + ext->sym_idx = i; + ext->is_weak = GELF_ST_BIND(sym.st_info) == STB_WEAK; + ext->sz = btf__resolve_size(obj->btf, t->type); + if (ext->sz <= 0) { + pr_warn("failed to resolve size of extern '%s': %d\n", + ext_name, ext->sz); + return ext->sz; + } + ext->align = btf__align_of(obj->btf, t->type); + if (ext->align <= 0) { + pr_warn("failed to determine alignment of extern '%s': %d\n", + ext_name, ext->align); + return -EINVAL; + } + ext->type = find_extern_type(obj->btf, t->type, + &ext->is_signed); + if (ext->type == EXT_UNKNOWN) { + pr_warn("extern '%s' type is unsupported\n", ext_name); + return -ENOTSUP; + } + } + pr_debug("collected %d externs total\n", obj->nr_extern); + + if (!obj->nr_extern) + return 0; + + /* sort externs by (alignment, size, name) and calculate their offsets + * within a map */ + qsort(obj->externs, obj->nr_extern, sizeof(*ext), cmp_externs); + off = 0; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + ext->data_off = roundup(off, ext->align); + off = ext->data_off + ext->sz; + pr_debug("extern #%d: symbol %d, off %u, name %s\n", + i, ext->sym_idx, ext->data_off, ext->name); + } + + btf_id = btf__find_by_name(obj->btf, KCONFIG_SEC); + if (btf_id <= 0) { + pr_warn("no BTF info found for '%s' datasec\n", KCONFIG_SEC); + return -ESRCH; + } + + sec = (struct btf_type *)btf__type_by_id(obj->btf, btf_id); + sec->size = off; + n = btf_vlen(sec); + for (i = 0; i < n; i++) { + struct btf_var_secinfo *vs = btf_var_secinfos(sec) + i; + + t = btf__type_by_id(obj->btf, vs->type); + ext_name = btf__name_by_offset(obj->btf, t->name_off); + ext = find_extern_by_name(obj, ext_name); + if (!ext) { + pr_warn("failed to find extern definition for BTF var '%s'\n", + ext_name); + return -ESRCH; + } + vs->offset = ext->data_off; + btf_var(t)->linkage = BTF_VAR_GLOBAL_ALLOCATED; + } + + return 0; } static struct bpf_program * @@ -1685,6 +2793,19 @@ bpf_object__find_program_by_title(const struct bpf_object *obj, return NULL; } +struct bpf_program * +bpf_object__find_program_by_name(const struct bpf_object *obj, + const char *name) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + if (!strcmp(prog->name, name)) + return prog; + } + return NULL; +} + static bool bpf_object__shndx_is_data(const struct bpf_object *obj, int shndx) { @@ -1700,14 +2821,6 @@ static bool bpf_object__shndx_is_maps(const struct bpf_object *obj, shndx == obj->efile.btf_maps_shndx; } -static bool bpf_object__relo_in_known_section(const struct bpf_object *obj, - int shndx) -{ - return shndx == obj->efile.text_shndx || - bpf_object__shndx_is_maps(obj, shndx) || - bpf_object__shndx_is_data(obj, shndx); -} - static enum libbpf_map_type bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) { @@ -1717,127 +2830,190 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx) return LIBBPF_MAP_BSS; else if (shndx == obj->efile.rodata_shndx) return LIBBPF_MAP_RODATA; + else if (shndx == obj->efile.symbols_shndx) + return LIBBPF_MAP_KCONFIG; 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: %zu\n", + (size_t)sym->st_value); + return -LIBBPF_ERRNO__RELOC; + } + reloc_desc->type = RELO_CALL; + reloc_desc->insn_idx = insn_idx; + reloc_desc->sym_off = sym->st_value; + 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 (sym_is_extern(sym)) { + int sym_idx = GELF_R_SYM(rel->r_info); + int i, n = obj->nr_extern; + struct extern_desc *ext; + + for (i = 0; i < n; i++) { + ext = &obj->externs[i]; + if (ext->sym_idx == sym_idx) + break; + } + if (i >= n) { + pr_warn("extern relo failed to find extern for sym %d\n", + sym_idx); + return -LIBBPF_ERRNO__RELOC; + } + pr_debug("found extern #%d '%s' (sym %d, off %u) for insn %u\n", + i, ext->name, ext->sym_idx, ext->data_off, insn_idx); + reloc_desc->type = RELO_EXTERN; + reloc_desc->insn_idx = insn_idx; + reloc_desc->sym_off = ext->data_off; + return 0; + } + + 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 %zu\n", + shdr_idx, (size_t)sym->st_value); + return -LIBBPF_ERRNO__RELOC; + } + reloc_desc->type = RELO_LD64; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = map_idx; + reloc_desc->sym_off = 0; /* sym->st_value determines 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; + } + 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; + reloc_desc->sym_off = sym->st_value; + 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; - struct bpf_map *maps = obj->maps; - size_t nr_maps = obj->nr_maps; - int i, nrels; + 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++) { - struct bpf_insn *insns = prog->insns; - enum libbpf_map_type type; - unsigned int insn_idx; - unsigned int shdr_idx; const char *name; - size_t map_idx; + __u32 insn_idx; GElf_Sym sym; GElf_Rel rel; 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)); + pr_warn("relocation: symbol %"PRIx64" not found\n", + GELF_R_SYM(rel.r_info)); return -LIBBPF_ERRNO__FORMAT; } + if (rel.r_offset % sizeof(struct bpf_insn)) + return -LIBBPF_ERRNO__FORMAT; + insn_idx = rel.r_offset / sizeof(struct bpf_insn); name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, sym.st_name) ? : "<?>"; - pr_debug("relo for %lld value %lld name %d (\'%s\')\n", - (long long) (rel.r_info >> 32), - (long long) sym.st_value, sym.st_name, name); - - shdr_idx = sym.st_shndx; - if (!bpf_object__relo_in_known_section(obj, shdr_idx)) { - pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n", - prog->section_name, shdr_idx); - return -LIBBPF_ERRNO__RELOC; - } - - 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; - } + pr_debug("relo for shdr %u, symb %zu, value %zu, type %d, bind %d, name %d (\'%s\'), insn %u\n", + (__u32)sym.st_shndx, (size_t)GELF_R_SYM(rel.r_info), + (size_t)sym.st_value, GELF_ST_TYPE(sym.st_info), + GELF_ST_BIND(sym.st_info), sym.st_name, name, + insn_idx); - if (bpf_object__shndx_is_maps(obj, shdr_idx) || - bpf_object__shndx_is_data(obj, shdr_idx)) { - type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx); - if (type != LIBBPF_MAP_UNSPEC) { - if (GELF_ST_BIND(sym.st_info) == STB_GLOBAL) { - pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n", - name, insn_idx, insns[insn_idx].code); - return -LIBBPF_ERRNO__RELOC; - } - if (!obj->caps.global_data) { - pr_warning("bpf: 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++) { - if (maps[map_idx].libbpf_type != type) - continue; - if (type != LIBBPF_MAP_UNSPEC || - (maps[map_idx].sec_idx == sym.st_shndx && - maps[map_idx].sec_offset == sym.st_value)) { - pr_debug("relocation: found map %zd (%s, sec_idx %d, offset %zu) for insn %u\n", - map_idx, maps[map_idx].name, - maps[map_idx].sec_idx, - maps[map_idx].sec_offset, - insn_idx); - break; - } - } - - if (map_idx >= nr_maps) { - pr_warning("bpf relocation: map_idx %d larger than %d\n", - (int)map_idx, (int)nr_maps - 1); - return -LIBBPF_ERRNO__RELOC; - } - - prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ? - RELO_DATA : 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; } @@ -1848,8 +3024,12 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) __u32 key_type_id = 0, value_type_id = 0; int ret; - /* if it's BTF-defined map, we don't need to search for type IDs */ - if (map->sec_idx == obj->efile.btf_maps_shndx) + /* if it's BTF-defined map, we don't need to search for type IDs. + * For struct_ops map, it does not need btf_key_type_id and + * btf_value_type_id. + */ + if (map->sec_idx == obj->efile.btf_maps_shndx || + bpf_map__is_struct_ops(map)) return 0; if (!bpf_map__is_internal(map)) { @@ -1889,16 +3069,22 @@ 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; @@ -1910,6 +3096,7 @@ 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; @@ -1917,7 +3104,7 @@ 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) @@ -1956,8 +3143,8 @@ 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); @@ -1997,8 +3184,8 @@ bpf_object__probe_global_data(struct bpf_object *obj) map = bpf_create_map_xattr(&map_attr); if (map < 0) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, errno); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, errno); return -errno; } @@ -2022,7 +3209,7 @@ bpf_object__probe_global_data(struct bpf_object *obj) static int bpf_object__probe_btf_func(struct bpf_object *obj) { - const char strs[] = "\0int\0x\0a"; + static const char strs[] = "\0int\0x\0a"; /* void x(int a) {} */ __u32 types[] = { /* int */ @@ -2046,9 +3233,35 @@ static int bpf_object__probe_btf_func(struct bpf_object *obj) return 0; } +static int bpf_object__probe_btf_func_global(struct bpf_object *obj) +{ + static const char strs[] = "\0int\0x\0a"; + /* static void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), + }; + int btf_fd; + + btf_fd = libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs)); + if (btf_fd >= 0) { + obj->caps.btf_func_global = 1; + close(btf_fd); + return 1; + } + + return 0; +} + static int bpf_object__probe_btf_datasec(struct bpf_object *obj) { - const char strs[] = "\0x\0.data"; + static const char strs[] = "\0x\0.data"; /* static int a; */ __u32 types[] = { /* int */ @@ -2073,6 +3286,27 @@ static int bpf_object__probe_btf_datasec(struct bpf_object *obj) 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) { @@ -2080,7 +3314,9 @@ bpf_object__probe_caps(struct bpf_object *obj) bpf_object__probe_name, bpf_object__probe_global_data, bpf_object__probe_btf_func, + bpf_object__probe_btf_func_global, bpf_object__probe_btf_datasec, + bpf_object__probe_array_mmap, }; int i, ret; @@ -2093,32 +3329,98 @@ bpf_object__probe_caps(struct bpf_object *obj) 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) { + enum libbpf_map_type map_type = map->libbpf_type; 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) + /* kernel already zero-initializes .bss map. */ + if (map_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, map->mmaped, 0); + if (err) { + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error setting initial map(%s) contents: %s\n", + map->name, cp); + return err; + } - 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) { + /* Freeze .rodata and .kconfig map as read-only from syscall side. */ + if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG) { err = bpf_map_freeze(map->fd); if (err) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warning("Error freezing map(%s) as read-only: %s\n", - map->name, cp); - err = 0; + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); + pr_warn("Error freezing map(%s) as read-only: %s\n", + map->name, cp); + return err; } } - return err; + return 0; } static int @@ -2135,6 +3437,15 @@ 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); @@ -2153,8 +3464,8 @@ bpf_object__create_maps(struct bpf_object *obj) if (!nr_cpus) nr_cpus = libbpf_num_possible_cpus(); if (nr_cpus < 0) { - pr_warning("failed to determine number of system CPUs: %d\n", - nr_cpus); + pr_warn("failed to determine number of system CPUs: %d\n", + nr_cpus); err = nr_cpus; goto err_out; } @@ -2170,6 +3481,9 @@ bpf_object__create_maps(struct bpf_object *obj) if (bpf_map_type__is_map_in_map(def->type) && map->inner_map_fd >= 0) create_attr.inner_map_fd = map->inner_map_fd; + if (bpf_map__is_struct_ops(map)) + create_attr.btf_vmlinux_value_type_id = + map->btf_vmlinux_value_type_id; if (obj->btf && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); @@ -2182,8 +3496,8 @@ bpf_object__create_maps(struct bpf_object *obj) create_attr.btf_value_type_id)) { err = -errno; cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", - map->name, cp, err); + pr_warn("Error in bpf_create_map_xattr(%s):%s(%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; @@ -2198,8 +3512,9 @@ bpf_object__create_maps(struct bpf_object *obj) err = -errno; err_out: cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); - pr_warning("failed to create map (name: '%s'): %s(%d)\n", - map->name, cp, err); + pr_warn("failed to create map (name: '%s'): %s(%d)\n", + map->name, cp, err); + pr_perm_msg(err); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; @@ -2213,6 +3528,15 @@ 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); } @@ -2224,8 +3548,8 @@ 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; } @@ -2236,14 +3560,14 @@ check_btf_ext_reloc_err(struct bpf_program *prog, int err, * Some info has already been found but has problem * 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); + pr_warn("Cannot find %s for main program sec %s. Ignore all %s.\n", + info_name, prog->section_name, info_name); return 0; } @@ -2288,6 +3612,1031 @@ bpf_program_reloc_btf_ext(struct bpf_program *prog, struct bpf_object *obj, 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]; +} + +static bool is_flex_arr(const struct btf *btf, + const struct bpf_core_accessor *acc, + const struct btf_array *arr) +{ + const struct btf_type *t; + + /* not a flexible array, if not inside a struct or has non-zero size */ + if (!acc->name || arr->nelems > 0) + return false; + + /* has to be the last member of enclosing struct */ + t = btf__type_by_id(btf, acc->type_id); + return acc->idx == btf_vlen(t) - 1; +} + +/* + * 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; + struct bpf_core_accessor *acc; + 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]; + acc = &spec->spec[spec->len]; + + 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; + + acc->type_id = id; + acc->idx = access_idx; + acc->name = name; + spec->len++; + } + + id = m->type; + } else if (btf_is_array(t)) { + const struct btf_array *a = btf_array(t); + bool flex; + + t = skip_mods_and_typedefs(btf, a->type, &id); + if (!t) + return -EINVAL; + + flex = is_flex_arr(btf, acc - 1, a); + if (!flex && 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 = reallocarray(cand_ids->data, + cand_ids->len + 1, + sizeof(*cand_ids->data)); + 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; + bool flex; + + if (!btf_is_array(targ_type)) + return 0; + + a = btf_array(targ_type); + flex = is_flex_arr(targ_btf, targ_acc - 1, a); + if (!flex && 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, + int relo_idx, + const struct bpf_core_spec *local_spec, + const struct bpf_core_spec *targ_spec) +{ + __u32 orig_val, new_val; + struct bpf_insn *insn; + bool validate = true; + 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); + insn = &prog->insns[insn_idx]; + class = BPF_CLASS(insn->code); + + 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) { + pr_debug("prog '%s': relo #%d: substituting insn #%d w/ invalid insn\n", + bpf_program__title(prog, false), relo_idx, insn_idx); + insn->code = BPF_JMP | BPF_CALL; + insn->dst_reg = 0; + insn->src_reg = 0; + insn->off = 0; + /* if this instruction is reachable (not a dead code), + * verifier will complain with the following message: + * invalid func unknown#195896080 + */ + insn->imm = 195896080; /* => 0xbad2310 => "bad relo" */ + return 0; + } 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; + } + + switch (class) { + case BPF_ALU: + case BPF_ALU64: + if (BPF_SRC(insn->code) != BPF_K) + return -EINVAL; + if (validate && insn->imm != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (ALU/ALU64) value: got %u, exp %u -> %u\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, insn->imm, orig_val, new_val); + return -EINVAL; + } + orig_val = insn->imm; + insn->imm = new_val; + pr_debug("prog '%s': relo #%d: patched insn #%d (ALU/ALU64) imm %u -> %u\n", + bpf_program__title(prog, false), relo_idx, insn_idx, + orig_val, new_val); + break; + case BPF_LDX: + case BPF_ST: + case BPF_STX: + if (validate && insn->off != orig_val) { + pr_warn("prog '%s': relo #%d: unexpected insn #%d (LD/LDX/ST/STX) value: got %u, exp %u -> %u\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, insn->off, orig_val, new_val); + return -EINVAL; + } + if (new_val > SHRT_MAX) { + pr_warn("prog '%s': relo #%d: insn #%d (LDX/ST/STX) value too big: %u\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, new_val); + return -ERANGE; + } + orig_val = insn->off; + insn->off = new_val; + pr_debug("prog '%s': relo #%d: patched insn #%d (LDX/ST/STX) off %u -> %u\n", + bpf_program__title(prog, false), relo_idx, insn_idx, + orig_val, new_val); + break; + default: + pr_warn("prog '%s': relo #%d: trying to relocate unrecognized insn #%d, code:%x, src:%x, dst:%x, off:%x, imm:%x\n", + bpf_program__title(prog, false), relo_idx, + insn_idx, insn->code, insn->src_reg, insn->dst_reg, + insn->off, insn->imm); + return -EINVAL; + } + + return 0; +} + +/* 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 used BPF program has field + * existence checks or kernel version/config checks, it's expected + * that we might not find any candidates. In this case, if field + * wasn't found in any candidate, the list of candidates shouldn't + * change at all, we'll just handle relocating appropriately, + * depending on relo's kind. + */ + if (j > 0) + cand_ids->len = j; + + /* + * If no candidates were found, it might be both a programmer error, + * as well as expected case, depending whether instruction w/ + * relocation is guarded in some way that makes it unreachable (dead + * code) if relocation can't be resolved. This is handled in + * bpf_core_reloc_insn() uniformly by replacing that instruction with + * BPF helper call insn (using invalid helper ID). If that instruction + * is indeed unreachable, then it will be ignored and eliminated by + * verifier. If it was an error, then verifier will complain and point + * to a specific instruction number in its log. + */ + if (j == 0) + pr_debug("prog '%s': relo #%d: no matching targets found for [%d] %s + %s\n", + prog_name, relo_idx, local_id, local_name, spec_str); + + /* bpf_core_reloc_insn should know how to handle missing targ_spec */ + err = bpf_core_reloc_insn(prog, relo, relo_idx, &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 = libbpf_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) @@ -2297,27 +4646,19 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj, size_t new_cnt; int err; - if (relo->type != RELO_CALL) - 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); - return -LIBBPF_ERRNO__RELOC; - } - - if (prog->main_prog_cnt == 0) { + if (prog->idx != obj->efile.text_shndx && 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, @@ -2329,15 +4670,15 @@ 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", text->insns_cnt, text->section_name, prog->section_name); } + insn = &prog->insns[relo->insn_idx]; - insn->imm += prog->main_prog_cnt - relo->insn_idx; + insn->imm += relo->sym_off / 8 + prog->main_prog_cnt - relo->insn_idx; return 0; } @@ -2360,33 +4701,38 @@ 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 || - 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 + 1 >= (int)prog->insns_cnt) { - pr_warning("relocation out of range: '%s'\n", - prog->section_name); - return -LIBBPF_ERRNO__RELOC; - } + struct reloc_desc *relo = &prog->reloc_desc[i]; + struct bpf_insn *insn = &prog->insns[relo->insn_idx]; - 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 if (prog->reloc_desc[i].type == RELO_CALL) { - err = bpf_program__reloc_text(prog, obj, - &prog->reloc_desc[i]); + if (relo->insn_idx + 1 >= (int)prog->insns_cnt) { + pr_warn("relocation out of range: '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__RELOC; + } + + switch (relo->type) { + case RELO_LD64: + insn[0].src_reg = BPF_PSEUDO_MAP_FD; + insn[0].imm = obj->maps[relo->map_idx].fd; + break; + case RELO_DATA: + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[1].imm = insn[0].imm + relo->sym_off; + insn[0].imm = obj->maps[relo->map_idx].fd; + break; + case RELO_EXTERN: + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[0].imm = obj->maps[obj->kconfig_map_idx].fd; + insn[1].imm = relo->sym_off; + break; + case RELO_CALL: + err = bpf_program__reloc_text(prog, obj, relo); if (err) return err; + break; + default: + pr_warn("relo #%d: bad relo type %d\n", i, relo->type); + return -EINVAL; } } @@ -2395,50 +4741,89 @@ 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; + } + } + /* ensure .text is relocated first, as it's going to be copied as-is + * later for sub-program calls + */ for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; + if (prog->idx != obj->efile.text_shndx) + continue; 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; + } + break; + } + /* now relocate everything but .text, which by now is relocated + * properly, so we can copy raw sub-program instructions as is safely + */ + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + if (prog->idx == obj->efile.text_shndx) + continue; + + err = bpf_program__relocate(prog, obj); + if (err) { + pr_warn("failed to relocate '%s'\n", prog->section_name); return err; } } return 0; } +static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj, + GElf_Shdr *shdr, + Elf_Data *data); + 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; } + if (idx == obj->efile.st_ops_shndx) { + err = bpf_object__collect_struct_ops_map_reloc(obj, + shdr, + data); + if (err) + return err; + continue; + } + 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; } @@ -2470,8 +4855,16 @@ 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; + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) { + load_attr.attach_btf_id = prog->attach_btf_id; + } else if (prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_EXT) { + 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); @@ -2490,7 +4883,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, 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, log_buf_size); @@ -2507,36 +4900,32 @@ retry_load: free(log_buf); goto retry_load; } - ret = -LIBBPF_ERRNO__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); + pr_perm_msg(ret); 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: @@ -2544,22 +4933,30 @@ out: return ret; } -int -bpf_program__load(struct bpf_program *prog, - char *license, __u32 kern_version) +static int libbpf_find_attach_btf_id(struct bpf_program *prog); + +int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) { - int err = 0, fd, i; + int err = 0, fd, i, btf_id; + + if (prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_EXT) { + btf_id = libbpf_find_attach_btf_id(prog); + if (btf_id <= 0) + return btf_id; + prog->attach_btf_id = btf_id; + } 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; @@ -2568,11 +4965,11 @@ 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); + license, kern_ver, &fd); if (!err) prog->instances.fds[0] = fd; goto out; @@ -2586,8 +4983,8 @@ 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; } @@ -2601,12 +4998,10 @@ bpf_program__load(struct bpf_program *prog, } err = load_program(prog, result.new_insn_ptr, - result.new_insn_cnt, - license, kern_version, &fd); - + result.new_insn_cnt, license, kern_ver, &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; } @@ -2616,8 +5011,7 @@ 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; @@ -2648,93 +5042,101 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) 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_RAW_TRACEPOINT_WRITABLE: - case BPF_PROG_TYPE_PERF_EVENT: - case BPF_PROG_TYPE_CGROUP_SYSCTL: - case BPF_PROG_TYPE_CGROUP_SOCKOPT: - 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 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, + const struct bpf_object_open_opts *opts) { + const char *obj_name, *kconfig; + struct bpf_program *prog; struct bpf_object *obj; + char tmp_name[64]; 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; - CHECK_ERR(bpf_object__elf_init(obj), err, out); - CHECK_ERR(bpf_object__check_endianness(obj), err, out); - CHECK_ERR(bpf_object__probe_caps(obj), err, out); - CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out); - CHECK_ERR(bpf_object__collect_reloc(obj), err, out); - CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out); + kconfig = OPTS_GET(opts, kconfig, NULL); + if (kconfig) { + obj->kconfig = strdup(kconfig); + if (!obj->kconfig) + return ERR_PTR(-ENOMEM); + } + err = bpf_object__elf_init(obj); + err = err ? : bpf_object__check_endianness(obj); + err = err ? : bpf_object__elf_collect(obj); + err = err ? : bpf_object__collect_externs(obj); + err = err ? : bpf_object__finalize_btf(obj); + err = err ? : bpf_object__init_maps(obj, opts); + err = err ? : bpf_object__init_prog_names(obj); + err = err ? : bpf_object__collect_reloc(obj); + if (err) + goto 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; + + if (prog->type != BPF_PROG_TYPE_UNSPEC) + continue; + + 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 || + prog_type == BPF_PROG_TYPE_EXT) + prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); + } + 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) @@ -2752,25 +5154,42 @@ 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, const 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); - 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, + const 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) @@ -2780,8 +5199,11 @@ int bpf_object__unload(struct bpf_object *obj) if (!obj) return -EINVAL; - for (i = 0; i < obj->nr_maps; i++) + for (i = 0; i < obj->nr_maps; i++) { zclose(obj->maps[i].fd); + if (obj->maps[i].st_ops) + zfree(&obj->maps[i].st_ops->kern_vdata); + } for (i = 0; i < obj->nr_programs; i++) bpf_program__unload(&obj->programs[i]); @@ -2789,10 +5211,96 @@ int bpf_object__unload(struct bpf_object *obj) return 0; } +static int bpf_object__sanitize_maps(struct bpf_object *obj) +{ + struct bpf_map *m; + + bpf_object__for_each_map(m, obj) { + if (!bpf_map__is_internal(m)) + continue; + if (!obj->caps.global_data) { + pr_warn("kernel doesn't support global data\n"); + return -ENOTSUP; + } + if (!obj->caps.array_mmap) + m->def.map_flags ^= BPF_F_MMAPABLE; + } + + return 0; +} + +static int bpf_object__resolve_externs(struct bpf_object *obj, + const char *extra_kconfig) +{ + bool need_config = false; + struct extern_desc *ext; + int err, i; + void *data; + + if (obj->nr_extern == 0) + return 0; + + data = obj->maps[obj->kconfig_map_idx].mmaped; + + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + + if (strcmp(ext->name, "LINUX_KERNEL_VERSION") == 0) { + void *ext_val = data + ext->data_off; + __u32 kver = get_kernel_version(); + + if (!kver) { + pr_warn("failed to get kernel version\n"); + return -EINVAL; + } + err = set_ext_value_num(ext, ext_val, kver); + if (err) + return err; + pr_debug("extern %s=0x%x\n", ext->name, kver); + } else if (strncmp(ext->name, "CONFIG_", 7) == 0) { + need_config = true; + } else { + pr_warn("unrecognized extern '%s'\n", ext->name); + return -EINVAL; + } + } + if (need_config && extra_kconfig) { + err = bpf_object__read_kconfig_mem(obj, extra_kconfig, data); + if (err) + return -EINVAL; + need_config = false; + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + if (!ext->is_set) { + need_config = true; + break; + } + } + } + if (need_config) { + err = bpf_object__read_kconfig_file(obj, data); + if (err) + return -EINVAL; + } + for (i = 0; i < obj->nr_extern; i++) { + ext = &obj->externs[i]; + + if (!ext->is_set && !ext->is_weak) { + pr_warn("extern %s (strong) not resolved\n", ext->name); + return -ESRCH; + } else if (!ext->is_set) { + pr_debug("extern %s (weak) not resolved, defaulting to zero\n", + ext->name); + } + } + + return 0; +} + int bpf_object__load_xattr(struct bpf_object_load_attr *attr) { struct bpf_object *obj; - int err; + int err, i; if (!attr) return -EINVAL; @@ -2801,20 +5309,37 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) 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__create_maps(obj), err, out); - CHECK_ERR(bpf_object__relocate(obj), err, out); - CHECK_ERR(bpf_object__load_progs(obj, attr->log_level), err, out); + err = bpf_object__probe_caps(obj); + err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); + err = err ? : bpf_object__sanitize_and_load_btf(obj); + err = err ? : bpf_object__sanitize_maps(obj); + err = err ? : bpf_object__load_vmlinux_btf(obj); + err = err ? : bpf_object__init_kern_struct_ops_maps(obj); + err = err ? : bpf_object__create_maps(obj); + err = err ? : bpf_object__relocate(obj, attr->target_btf_path); + err = err ? : bpf_object__load_progs(obj, attr->log_level); + + btf__free(obj->btf_vmlinux); + obj->btf_vmlinux = NULL; + + if (err) + goto 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; } @@ -2827,6 +5352,28 @@ int bpf_object__load(struct bpf_object *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; +} + static int check_path(const char *path) { char *cp, errmsg[STRERR_BUFSIZE]; @@ -2844,13 +5391,13 @@ 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; } @@ -2863,24 +5410,28 @@ 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); @@ -2898,13 +5449,13 @@ 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; } @@ -2916,36 +5467,25 @@ 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; } @@ -2955,10 +5495,6 @@ 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; @@ -3007,12 +5543,12 @@ 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; } @@ -3049,47 +5585,123 @@ 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; + } + } + + 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; } - pr_debug("pinned map '%s'\n", path); + 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; @@ -3099,29 +5711,32 @@ 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; } @@ -3130,17 +5745,10 @@ 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; @@ -3155,17 +5763,24 @@ 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; } @@ -3182,14 +5797,10 @@ 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; @@ -3289,16 +5900,33 @@ void bpf_object__close(struct bpf_object *obj) btf_ext__free(obj->btf_ext); for (i = 0; i < obj->nr_maps; i++) { - zfree(&obj->maps[i].name); - 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; + struct bpf_map *map = &obj->maps[i]; + + if (map->clear_priv) + map->clear_priv(map, map->priv); + map->priv = NULL; + map->clear_priv = NULL; + + if (map->mmaped) { + munmap(map->mmaped, bpf_map_mmap_sz(map)); + map->mmaped = NULL; + } + + if (map->st_ops) { + zfree(&map->st_ops->data); + zfree(&map->st_ops->progs); + zfree(&map->st_ops->kern_func_off); + zfree(&map->st_ops); + } + + zfree(&map->name); + zfree(&map->pin_path); } - zfree(&obj->sections.rodata); - zfree(&obj->sections.data); + zfree(&obj->kconfig); + zfree(&obj->externs); + obj->nr_extern = 0; + zfree(&obj->maps); obj->nr_maps = 0; @@ -3333,7 +5961,7 @@ bpf_object__next(struct bpf_object *prev) 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(const struct bpf_object *obj) @@ -3383,7 +6011,7 @@ __bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, &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; } @@ -3438,6 +6066,11 @@ void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) prog->prog_ifindex = ifindex; } +const char *bpf_program__name(const struct bpf_program *prog) +{ + return prog->name; +} + const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) { const char *title; @@ -3446,7 +6079,7 @@ const char *bpf_program__title(const 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); } } @@ -3459,6 +6092,11 @@ 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) { @@ -3468,13 +6106,13 @@ 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; } @@ -3495,21 +6133,26 @@ int bpf_program__nth_fd(const 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; @@ -3543,6 +6186,15 @@ BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); +BPF_PROG_TYPE_FNS(tracing, BPF_PROG_TYPE_TRACING); +BPF_PROG_TYPE_FNS(struct_ops, BPF_PROG_TYPE_STRUCT_OPS); +BPF_PROG_TYPE_FNS(extension, BPF_PROG_TYPE_EXT); + +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) @@ -3550,40 +6202,95 @@ 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. */ #define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype) -static const struct { +#define SEC_DEF(sec_pfx, ptype, ...) { \ + .sec = sec_pfx, \ + .len = sizeof(sec_pfx) - 1, \ + .prog_type = BPF_PROG_TYPE_##ptype, \ + __VA_ARGS__ \ +} + +struct bpf_sec_def; + +typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec, + struct bpf_program *prog); + +static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, + struct bpf_program *prog); +static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog); +static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog); +static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, + struct bpf_program *prog); + +struct bpf_sec_def { const char *sec; 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[] = { + attach_fn_t attach_fn; +}; + +static const struct bpf_sec_def section_defs[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), - BPF_PROG_SEC("kprobe/", BPF_PROG_TYPE_KPROBE), - BPF_PROG_SEC("kretprobe/", BPF_PROG_TYPE_KPROBE), + BPF_PROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT), + SEC_DEF("kprobe/", KPROBE, + .attach_fn = attach_kprobe), + BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), + SEC_DEF("kretprobe/", KPROBE, + .attach_fn = attach_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("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), + SEC_DEF("tracepoint/", TRACEPOINT, + .attach_fn = attach_tp), + SEC_DEF("tp/", TRACEPOINT, + .attach_fn = attach_tp), + SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT, + .attach_fn = attach_raw_tp), + SEC_DEF("raw_tp/", RAW_TRACEPOINT, + .attach_fn = attach_raw_tp), + SEC_DEF("tp_btf/", TRACING, + .expected_attach_type = BPF_TRACE_RAW_TP, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("fentry/", TRACING, + .expected_attach_type = BPF_TRACE_FENTRY, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("fexit/", TRACING, + .expected_attach_type = BPF_TRACE_FEXIT, + .is_attach_btf = true, + .attach_fn = attach_trace), + SEC_DEF("freplace/", EXT, + .is_attach_btf = true, + .attach_fn = attach_trace), 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), @@ -3638,6 +6345,7 @@ static const struct { BPF_CGROUP_GETSOCKOPT), BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT), + BPF_PROG_SEC("struct_ops", BPF_PROG_TYPE_STRUCT_OPS), }; #undef BPF_PROG_SEC_IMPL @@ -3645,12 +6353,26 @@ static const struct { #undef BPF_APROG_SEC #undef BPF_EAPROG_SEC #undef BPF_APROG_COMPAT +#undef SEC_DEF #define MAX_TYPE_NAME_SIZE 32 +static const struct bpf_sec_def *find_sec_def(const char *sec_name) +{ + int i, n = ARRAY_SIZE(section_defs); + + for (i = 0; i < n; i++) { + if (strncmp(sec_name, + section_defs[i].sec, section_defs[i].len)) + continue; + return §ion_defs[i]; + } + return NULL; +} + static char *libbpf_get_type_names(bool attach_type) { - int i, len = ARRAY_SIZE(section_names) * MAX_TYPE_NAME_SIZE; + int i, len = ARRAY_SIZE(section_defs) * MAX_TYPE_NAME_SIZE; char *buf; buf = malloc(len); @@ -3659,16 +6381,16 @@ static char *libbpf_get_type_names(bool attach_type) buf[0] = '\0'; /* Forge string buf with all available names */ - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (attach_type && !section_names[i].is_attachable) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (attach_type && !section_defs[i].is_attachable) continue; - if (strlen(buf) + strlen(section_names[i].sec) + 2 > len) { + if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) { free(buf); return NULL; } strcat(buf, " "); - strcat(buf, section_names[i].sec); + strcat(buf, section_defs[i].sec); } return buf; @@ -3677,29 +6399,270 @@ static char *libbpf_get_type_names(bool attach_type) int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, enum bpf_attach_type *expected_attach_type) { + const struct bpf_sec_def *sec_def; char *type_names; - int i; if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (strncmp(name, section_names[i].sec, section_names[i].len)) - continue; - *prog_type = section_names[i].prog_type; - *expected_attach_type = section_names[i].expected_attach_type; + sec_def = find_sec_def(name); + if (sec_def) { + *prog_type = sec_def->prog_type; + *expected_attach_type = sec_def->expected_attach_type; return 0; } - pr_warning("failed to guess program type based on ELF section name '%s'\n", name); + + pr_debug("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); + pr_debug("supported section(type) names are:%s\n", type_names); free(type_names); } + return -ESRCH; +} + +static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, + size_t offset) +{ + struct bpf_map *map; + size_t i; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + if (!bpf_map__is_struct_ops(map)) + continue; + if (map->sec_offset <= offset && + offset - map->sec_offset < map->def.value_size) + return map; + } + + return NULL; +} + +/* Collect the reloc from ELF and populate the st_ops->progs[] */ +static int bpf_object__collect_struct_ops_map_reloc(struct bpf_object *obj, + GElf_Shdr *shdr, + Elf_Data *data) +{ + const struct btf_member *member; + struct bpf_struct_ops *st_ops; + struct bpf_program *prog; + unsigned int shdr_idx; + const struct btf *btf; + struct bpf_map *map; + Elf_Data *symbols; + unsigned int moff; + const char *name; + __u32 member_idx; + GElf_Sym sym; + GElf_Rel rel; + int i, nrels; + + symbols = obj->efile.symbols; + btf = obj->btf; + nrels = shdr->sh_size / shdr->sh_entsize; + for (i = 0; i < nrels; i++) { + if (!gelf_getrel(data, i, &rel)) { + pr_warn("struct_ops reloc: failed to get %d reloc\n", i); + return -LIBBPF_ERRNO__FORMAT; + } + + if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) { + pr_warn("struct_ops reloc: symbol %zx not found\n", + (size_t)GELF_R_SYM(rel.r_info)); + return -LIBBPF_ERRNO__FORMAT; + } + + name = elf_strptr(obj->efile.elf, obj->efile.strtabidx, + sym.st_name) ? : "<?>"; + map = find_struct_ops_map_by_offset(obj, rel.r_offset); + if (!map) { + pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n", + (size_t)rel.r_offset); + return -EINVAL; + } + + moff = rel.r_offset - map->sec_offset; + shdr_idx = sym.st_shndx; + st_ops = map->st_ops; + pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel.r_offset %zu map->sec_offset %zu name %d (\'%s\')\n", + map->name, + (long long)(rel.r_info >> 32), + (long long)sym.st_value, + shdr_idx, (size_t)rel.r_offset, + map->sec_offset, sym.st_name, name); + + if (shdr_idx >= SHN_LORESERVE) { + pr_warn("struct_ops reloc %s: rel.r_offset %zu shdr_idx %u unsupported non-static function\n", + map->name, (size_t)rel.r_offset, shdr_idx); + return -LIBBPF_ERRNO__RELOC; + } + + member = find_member_by_offset(st_ops->type, moff * 8); + if (!member) { + pr_warn("struct_ops reloc %s: cannot find member at moff %u\n", + map->name, moff); + return -EINVAL; + } + member_idx = member - btf_members(st_ops->type); + name = btf__name_by_offset(btf, member->name_off); + + if (!resolve_func_ptr(btf, member->type, NULL)) { + pr_warn("struct_ops reloc %s: cannot relocate non func ptr %s\n", + map->name, name); + return -EINVAL; + } + + prog = bpf_object__find_prog_by_idx(obj, shdr_idx); + if (!prog) { + pr_warn("struct_ops reloc %s: cannot find prog at shdr_idx %u to relocate func ptr %s\n", + map->name, shdr_idx, name); + return -EINVAL; + } + + if (prog->type == BPF_PROG_TYPE_UNSPEC) { + const struct bpf_sec_def *sec_def; + + sec_def = find_sec_def(prog->section_name); + if (sec_def && + sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) { + /* for pr_warn */ + prog->type = sec_def->prog_type; + goto invalid_prog; + } + + prog->type = BPF_PROG_TYPE_STRUCT_OPS; + prog->attach_btf_id = st_ops->type_id; + prog->expected_attach_type = member_idx; + } else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || + prog->attach_btf_id != st_ops->type_id || + prog->expected_attach_type != member_idx) { + goto invalid_prog; + } + st_ops->progs[member_idx] = prog; + } + + return 0; + +invalid_prog: + pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", + map->name, prog->name, prog->section_name, prog->type, + prog->attach_btf_id, prog->expected_attach_type, name); return -EINVAL; } +#define BTF_TRACE_PREFIX "btf_trace_" +#define BTF_MAX_NAME_SIZE 128 + +static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, + const char *name, __u32 kind) +{ + char btf_type_name[BTF_MAX_NAME_SIZE]; + int ret; + + ret = snprintf(btf_type_name, sizeof(btf_type_name), + "%s%s", prefix, name); + /* snprintf returns the number of characters written excluding the + * the terminating null. So, if >= BTF_MAX_NAME_SIZE are written, it + * indicates truncation. + */ + if (ret < 0 || ret >= sizeof(btf_type_name)) + return -ENAMETOOLONG; + return btf__find_by_name_kind(btf, btf_type_name, kind); +} + +static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name, + enum bpf_attach_type attach_type) +{ + int err; + + if (attach_type == BPF_TRACE_RAW_TP) + err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name, + BTF_KIND_TYPEDEF); + else + err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); + + return err; +} + +int libbpf_find_vmlinux_btf_id(const char *name, + enum bpf_attach_type attach_type) +{ + struct btf *btf; + + btf = libbpf_find_kernel_btf(); + if (IS_ERR(btf)) { + pr_warn("vmlinux BTF is not found\n"); + return -EINVAL; + } + + return __find_vmlinux_btf_id(btf, name, attach_type); +} + +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(struct bpf_program *prog) +{ + enum bpf_attach_type attach_type = prog->expected_attach_type; + __u32 attach_prog_fd = prog->attach_prog_fd; + const char *name = prog->section_name; + int i, err; + + if (!name) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (!section_defs[i].is_attach_btf) + continue; + if (strncmp(name, section_defs[i].sec, section_defs[i].len)) + continue; + if (attach_prog_fd) + err = libbpf_find_prog_btf_id(name + section_defs[i].len, + attach_prog_fd); + else + err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux, + name + section_defs[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, enum bpf_attach_type *attach_type) { @@ -3709,33 +6672,24 @@ int libbpf_attach_type_by_name(const char *name, if (!name) return -EINVAL; - for (i = 0; i < ARRAY_SIZE(section_names); i++) { - if (strncmp(name, section_names[i].sec, section_names[i].len)) + for (i = 0; i < ARRAY_SIZE(section_defs); i++) { + if (strncmp(name, section_defs[i].sec, section_defs[i].len)) continue; - if (!section_names[i].is_attachable) + if (!section_defs[i].is_attachable) return -EINVAL; - *attach_type = section_names[i].attach_type; + *attach_type = section_defs[i].attach_type; return 0; } - pr_warning("failed to guess attach type based on ELF section name '%s'\n", name); + pr_debug("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); + pr_debug("attachable section(type) names are:%s\n", type_names); free(type_names); } 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(const struct bpf_map *map) { return map ? map->fd : -EINVAL; @@ -3800,11 +6754,11 @@ 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; @@ -3824,8 +6778,8 @@ __bpf_map__iter(const struct bpf_map *m, const 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; } @@ -3903,8 +6857,6 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, { 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; @@ -3922,26 +6874,27 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, 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) @@ -3954,7 +6907,7 @@ 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; } @@ -3971,17 +6924,37 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, } struct bpf_link { + int (*detach)(struct bpf_link *link); int (*destroy)(struct bpf_link *link); + bool disconnected; }; +/* Release "ownership" of underlying BPF resource (typically, BPF program + * attached to some BPF hook, e.g., tracepoint, kprobe, etc). Disconnected + * link, when destructed through bpf_link__destroy() call won't attempt to + * detach/unregisted that BPF resource. This is useful in situations where, + * say, attached BPF program has to outlive userspace program that attached it + * in the system. Depending on type of BPF program, though, there might be + * additional steps (like pinning BPF program in BPF FS) necessary to ensure + * exit of userspace program doesn't trigger automatic detachment and clean up + * inside the kernel. + */ +void bpf_link__disconnect(struct bpf_link *link) +{ + link->disconnected = true; +} + int bpf_link__destroy(struct bpf_link *link) { - int err; + int err = 0; if (!link) return 0; - err = link->destroy(link); + if (!link->disconnected && link->detach) + err = link->detach(link); + if (link->destroy) + link->destroy(link); free(link); return err; @@ -3992,7 +6965,7 @@ struct bpf_link_fd { int fd; /* hook FD */ }; -static int bpf_link__destroy_perf_event(struct bpf_link *link) +static int bpf_link__detach_perf_event(struct bpf_link *link) { struct bpf_link_fd *l = (void *)link; int err; @@ -4013,36 +6986,36 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int prog_fd, err; if (pfd < 0) { - pr_warning("program '%s': invalid perf event FD %d\n", - bpf_program__title(prog, false), pfd); + 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_warning("program '%s': can't attach BPF program w/o FD (did you load it?)\n", - bpf_program__title(prog, false)); + 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)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_perf_event; + link->link.detach = &bpf_link__detach_perf_event; link->fd = pfd; if (ioctl(pfd, PERF_EVENT_IOC_SET_BPF, prog_fd) < 0) { err = -errno; free(link); - pr_warning("program '%s': failed to attach to pfd %d: %s\n", - bpf_program__title(prog, false), pfd, + 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_warning("program '%s': failed to enable pfd %d: %s\n", - bpf_program__title(prog, false), pfd, + 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); } @@ -4117,9 +7090,9 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, type = uprobe ? determine_uprobe_perf_type() : determine_kprobe_perf_type(); if (type < 0) { - pr_warning("failed to determine %s perf type: %s\n", - uprobe ? "uprobe" : "kprobe", - libbpf_strerror_r(type, errmsg, sizeof(errmsg))); + pr_warn("failed to determine %s perf type: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(type, errmsg, sizeof(errmsg))); return type; } if (retprobe) { @@ -4127,10 +7100,9 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, : determine_kprobe_retprobe_bit(); if (bit < 0) { - pr_warning("failed to determine %s retprobe bit: %s\n", - uprobe ? "uprobe" : "kprobe", - libbpf_strerror_r(bit, errmsg, - sizeof(errmsg))); + 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; @@ -4147,9 +7119,9 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); if (pfd < 0) { err = -errno; - pr_warning("%s perf_event_open() failed: %s\n", - uprobe ? "uprobe" : "kprobe", - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + pr_warn("%s perf_event_open() failed: %s\n", + uprobe ? "uprobe" : "kprobe", + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); return err; } return pfd; @@ -4166,25 +7138,37 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name, 0 /* offset */, -1 /* pid */); if (pfd < 0) { - pr_warning("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))); + 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_warning("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))); + 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; } +static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + const char *func_name; + bool retprobe; + + func_name = bpf_program__title(prog, false) + sec->len; + retprobe = strcmp(sec->sec, "kretprobe/") == 0; + + return bpf_program__attach_kprobe(prog, retprobe, func_name); +} + struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, @@ -4197,22 +7181,22 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path, func_offset, pid); if (pfd < 0) { - pr_warning("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))); + 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_warning("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))); + 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; @@ -4246,9 +7230,9 @@ static int perf_event_open_tracepoint(const char *tp_category, tp_id = determine_tracepoint_id(tp_category, tp_name); if (tp_id < 0) { - pr_warning("failed to determine tracepoint '%s/%s' perf event ID: %s\n", - tp_category, tp_name, - libbpf_strerror_r(tp_id, errmsg, sizeof(errmsg))); + 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; } @@ -4260,9 +7244,9 @@ static int perf_event_open_tracepoint(const char *tp_category, -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); if (pfd < 0) { err = -errno; - pr_warning("tracepoint '%s/%s' perf_event_open() failed: %s\n", - tp_category, tp_name, - libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + 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; @@ -4278,26 +7262,52 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, pfd = perf_event_open_tracepoint(tp_category, tp_name); if (pfd < 0) { - pr_warning("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))); + 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_warning("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))); + 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) +static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + char *sec_name, *tp_cat, *tp_name; + struct bpf_link *link; + + sec_name = strdup(bpf_program__title(prog, false)); + if (!sec_name) + return ERR_PTR(-ENOMEM); + + /* extract "tp/<category>/<name>" */ + tp_cat = sec_name + sec->len; + tp_name = strchr(tp_cat, '/'); + if (!tp_name) { + link = ERR_PTR(-EINVAL); + goto out; + } + *tp_name = '\0'; + tp_name++; + + link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); +out: + free(sec_name); + return link; +} + +static int bpf_link__detach_fd(struct bpf_link *link) { struct bpf_link_fd *l = (void *)link; @@ -4313,29 +7323,137 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { - pr_warning("program '%s': can't attach before loaded\n", - bpf_program__title(prog, false)); + pr_warn("program '%s': can't attach before loaded\n", + bpf_program__title(prog, false)); return ERR_PTR(-EINVAL); } - link = malloc(sizeof(*link)); + link = calloc(1, sizeof(*link)); if (!link) return ERR_PTR(-ENOMEM); - link->link.destroy = &bpf_link__destroy_fd; + link->link.detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); if (pfd < 0) { pfd = -errno; free(link); - pr_warning("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))); + 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; +} + +static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + const char *tp_name = bpf_program__title(prog, false) + sec->len; + + return bpf_program__attach_raw_tracepoint(prog, tp_name); +} + +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 = calloc(1, sizeof(*link)); + if (!link) + return ERR_PTR(-ENOMEM); + link->link.detach = &bpf_link__detach_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; } +static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + return bpf_program__attach_trace(prog); +} + +struct bpf_link *bpf_program__attach(struct bpf_program *prog) +{ + const struct bpf_sec_def *sec_def; + + sec_def = find_sec_def(bpf_program__title(prog, false)); + if (!sec_def || !sec_def->attach_fn) + return ERR_PTR(-ESRCH); + + return sec_def->attach_fn(sec_def, prog); +} + +static int bpf_link__detach_struct_ops(struct bpf_link *link) +{ + struct bpf_link_fd *l = (void *)link; + __u32 zero = 0; + + if (bpf_map_delete_elem(l->fd, &zero)) + return -errno; + + return 0; +} + +struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) +{ + struct bpf_struct_ops *st_ops; + struct bpf_link_fd *link; + __u32 i, zero = 0; + int err; + + if (!bpf_map__is_struct_ops(map) || map->fd == -1) + return ERR_PTR(-EINVAL); + + link = calloc(1, sizeof(*link)); + if (!link) + return ERR_PTR(-EINVAL); + + st_ops = map->st_ops; + for (i = 0; i < btf_vlen(st_ops->type); i++) { + struct bpf_program *prog = st_ops->progs[i]; + void *kern_data; + int prog_fd; + + if (!prog) + continue; + + prog_fd = bpf_program__fd(prog); + kern_data = st_ops->kern_vdata + st_ops->kern_func_off[i]; + *(unsigned long *)kern_data = prog_fd; + } + + err = bpf_map_update_elem(map->fd, &zero, st_ops->kern_vdata, 0); + if (err) { + err = -errno; + free(link); + return ERR_PTR(err); + } + + link->link.detach = bpf_link__detach_struct_ops; + link->fd = map->fd; + + 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, @@ -4419,7 +7537,7 @@ struct perf_buffer { size_t mmap_size; struct perf_cpu_buf **cpu_bufs; struct epoll_event *events; - int cpu_cnt; + int cpu_cnt; /* number of allocated CPU buffers */ int epoll_fd; /* perf event FD */ int map_fd; /* BPF_MAP_TYPE_PERF_EVENT_ARRAY BPF map FD */ }; @@ -4431,7 +7549,7 @@ static void perf_buffer__free_cpu_buf(struct perf_buffer *pb, return; if (cpu_buf->base && munmap(cpu_buf->base, pb->mmap_size + pb->page_size)) - pr_warning("failed to munmap cpu_buf #%d\n", cpu_buf->cpu); + 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); @@ -4481,8 +7599,8 @@ perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, -1, PERF_FLAG_FD_CLOEXEC); if (cpu_buf->fd < 0) { err = -errno; - pr_warning("failed to open perf buffer event on cpu #%d: %s\n", - cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + pr_warn("failed to open perf buffer event on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); goto error; } @@ -4492,15 +7610,15 @@ perf_buffer__open_cpu_buf(struct perf_buffer *pb, struct perf_event_attr *attr, if (cpu_buf->base == MAP_FAILED) { cpu_buf->base = NULL; err = -errno; - pr_warning("failed to mmap perf buffer on cpu #%d: %s\n", - cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + 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_warning("failed to enable perf buffer event on cpu #%d: %s\n", - cpu, libbpf_strerror_r(err, msg, sizeof(msg))); + pr_warn("failed to enable perf buffer event on cpu #%d: %s\n", + cpu, libbpf_strerror_r(err, msg, sizeof(msg))); goto error; } @@ -4553,15 +7671,17 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt, static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, struct perf_buffer_params *p) { + const char *online_cpus_file = "/sys/devices/system/cpu/online"; struct bpf_map_info map = {}; char msg[STRERR_BUFSIZE]; struct perf_buffer *pb; + bool *online = NULL; __u32 map_info_len; - int err, i; + int err, i, j, n; if (page_cnt & (page_cnt - 1)) { - pr_warning("page count should be power of two, but is %zu\n", - page_cnt); + pr_warn("page count should be power of two, but is %zu\n", + page_cnt); return ERR_PTR(-EINVAL); } @@ -4569,14 +7689,14 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, err = bpf_obj_get_info_by_fd(map_fd, &map, &map_info_len); if (err) { err = -errno; - pr_warning("failed to get map info for map FD %d: %s\n", - map_fd, libbpf_strerror_r(err, msg, sizeof(msg))); + 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_warning("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", - map.name); + pr_warn("map '%s' should be BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", + map.name); return ERR_PTR(-EINVAL); } @@ -4596,8 +7716,8 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, pb->epoll_fd = epoll_create1(EPOLL_CLOEXEC); if (pb->epoll_fd < 0) { err = -errno; - pr_warning("failed to create epoll instance: %s\n", - libbpf_strerror_r(err, msg, sizeof(msg))); + pr_warn("failed to create epoll instance: %s\n", + libbpf_strerror_r(err, msg, sizeof(msg))); goto error; } @@ -4616,56 +7736,72 @@ static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, pb->events = calloc(pb->cpu_cnt, sizeof(*pb->events)); if (!pb->events) { err = -ENOMEM; - pr_warning("failed to allocate events: out of memory\n"); + 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_warning("failed to allocate buffers: out of memory\n"); + pr_warn("failed to allocate buffers: out of memory\n"); goto error; } - for (i = 0; i < pb->cpu_cnt; i++) { + err = parse_cpu_mask_file(online_cpus_file, &online, &n); + if (err) { + pr_warn("failed to get online CPU mask: %d\n", err); + goto error; + } + + for (i = 0, j = 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; + /* in case user didn't explicitly requested particular CPUs to + * be attached to, skip offline/not present CPUs + */ + if (p->cpu_cnt <= 0 && (cpu >= n || !online[cpu])) + continue; + 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; + pb->cpu_bufs[j] = cpu_buf; err = bpf_map_update_elem(pb->map_fd, &map_key, &cpu_buf->fd, 0); if (err) { err = -errno; - pr_warning("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))); + 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; + pb->events[j].events = EPOLLIN; + pb->events[j].data.ptr = cpu_buf; if (epoll_ctl(pb->epoll_fd, EPOLL_CTL_ADD, cpu_buf->fd, - &pb->events[i]) < 0) { + &pb->events[j]) < 0) { err = -errno; - pr_warning("failed to epoll_ctl cpu #%d perf FD %d: %s\n", - cpu, cpu_buf->fd, - libbpf_strerror_r(err, msg, sizeof(msg))); + 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; } + j++; } + pb->cpu_cnt = j; + free(online); return pb; error: + free(online); if (pb) perf_buffer__free(pb); return ERR_PTR(err); @@ -4711,7 +7847,7 @@ perf_buffer__process_record(struct perf_event_header *e, void *ctx) break; } default: - pr_warning("unknown perf sample type %d\n", e->type); + pr_warn("unknown perf sample type %d\n", e->type); return LIBBPF_PERF_EVENT_ERROR; } return LIBBPF_PERF_EVENT_CONT; @@ -4741,7 +7877,7 @@ int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) err = perf_buffer__process_records(pb, cpu_buf); if (err) { - pr_warning("error while processing records: %d\n", err); + pr_warn("error while processing records: %d\n", err); return err; } } @@ -4805,7 +7941,8 @@ 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; @@ -4814,7 +7951,8 @@ 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; @@ -4938,13 +8076,13 @@ 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 */ @@ -4994,63 +8132,267 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) } } -int libbpf_num_possible_cpus(void) +int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz) { - 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; + int err = 0, n, len, start, end = -1; + bool *tmp; - tmp_cpus = READ_ONCE(cpus); - if (tmp_cpus > 0) - return tmp_cpus; + *mask = NULL; + *mask_sz = 0; + + /* Each sub string separated by ',' has format \d+-\d+ or \d+ */ + while (*s) { + if (*s == ',' || *s == '\n') { + s++; + continue; + } + n = sscanf(s, "%d%n-%d%n", &start, &len, &end, &len); + if (n <= 0 || n > 2) { + pr_warn("Failed to get CPU range %s: %d\n", s, n); + err = -EINVAL; + goto cleanup; + } else if (n == 1) { + end = start; + } + if (start < 0 || start > end) { + pr_warn("Invalid CPU range [%d,%d] in %s\n", + start, end, s); + err = -EINVAL; + goto cleanup; + } + tmp = realloc(*mask, end + 1); + if (!tmp) { + err = -ENOMEM; + goto cleanup; + } + *mask = tmp; + memset(tmp + *mask_sz, 0, start - *mask_sz); + memset(tmp + start, 1, end - start + 1); + *mask_sz = end + 1; + s += len; + } + if (!*mask_sz) { + pr_warn("Empty CPU range\n"); + return -EINVAL; + } + return 0; +cleanup: + free(*mask); + *mask = NULL; + return err; +} + +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz) +{ + int fd, err = 0, len; + char buf[128]; fd = open(fcpu, O_RDONLY); if (fd < 0) { - error = errno; - pr_warning("Failed to open file %s: %s\n", - fcpu, strerror(error)); - return -error; + err = -errno; + pr_warn("Failed to open cpu mask file %s: %d\n", fcpu, err); + return err; } len = read(fd, buf, sizeof(buf)); close(fd); if (len <= 0) { - error = len ? errno : EINVAL; - pr_warning("Failed to read # of possible cpus from %s: %s\n", - fcpu, strerror(error)); - return -error; + err = len ? -errno : -EINVAL; + pr_warn("Failed to read cpu mask from %s: %d\n", fcpu, err); + return err; } - if (len == sizeof(buf)) { - pr_warning("File %s size overflow\n", fcpu); - return -EOVERFLOW; + if (len >= sizeof(buf)) { + pr_warn("CPU mask is too big in file %s\n", fcpu); + return -E2BIG; } 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_warning("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_warning("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu); - return -EINVAL; + return parse_cpu_mask_str(buf, mask, mask_sz); +} + +int libbpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + static int cpus; + int err, n, i, tmp_cpus; + bool *mask; + + tmp_cpus = READ_ONCE(cpus); + if (tmp_cpus > 0) + return tmp_cpus; + + err = parse_cpu_mask_file(fcpu, &mask, &n); + if (err) + return err; + + tmp_cpus = 0; + for (i = 0; i < n; i++) { + if (mask[i]) + tmp_cpus++; } + free(mask); WRITE_ONCE(cpus, tmp_cpus); return tmp_cpus; } + +int bpf_object__open_skeleton(struct bpf_object_skeleton *s, + const struct bpf_object_open_opts *opts) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts, + .object_name = s->name, + ); + struct bpf_object *obj; + int i; + + /* Attempt to preserve opts->object_name, unless overriden by user + * explicitly. Overwriting object name for skeletons is discouraged, + * as it breaks global data maps, because they contain object name + * prefix as their own map name prefix. When skeleton is generated, + * bpftool is making an assumption that this name will stay the same. + */ + if (opts) { + memcpy(&skel_opts, opts, sizeof(*opts)); + if (!opts->object_name) + skel_opts.object_name = s->name; + } + + obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts); + if (IS_ERR(obj)) { + pr_warn("failed to initialize skeleton BPF object '%s': %ld\n", + s->name, PTR_ERR(obj)); + return PTR_ERR(obj); + } + + *s->obj = obj; + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map **map = s->maps[i].map; + const char *name = s->maps[i].name; + void **mmaped = s->maps[i].mmaped; + + *map = bpf_object__find_map_by_name(obj, name); + if (!*map) { + pr_warn("failed to find skeleton map '%s'\n", name); + return -ESRCH; + } + + /* externs shouldn't be pre-setup from user code */ + if (mmaped && (*map)->libbpf_type != LIBBPF_MAP_KCONFIG) + *mmaped = (*map)->mmaped; + } + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_program **prog = s->progs[i].prog; + const char *name = s->progs[i].name; + + *prog = bpf_object__find_program_by_name(obj, name); + if (!*prog) { + pr_warn("failed to find skeleton program '%s'\n", name); + return -ESRCH; + } + } + + return 0; +} + +int bpf_object__load_skeleton(struct bpf_object_skeleton *s) +{ + int i, err; + + err = bpf_object__load(*s->obj); + if (err) { + pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err); + return err; + } + + for (i = 0; i < s->map_cnt; i++) { + struct bpf_map *map = *s->maps[i].map; + size_t mmap_sz = bpf_map_mmap_sz(map); + int prot, map_fd = bpf_map__fd(map); + void **mmaped = s->maps[i].mmaped; + + if (!mmaped) + continue; + + if (!(map->def.map_flags & BPF_F_MMAPABLE)) { + *mmaped = NULL; + continue; + } + + if (map->def.map_flags & BPF_F_RDONLY_PROG) + prot = PROT_READ; + else + prot = PROT_READ | PROT_WRITE; + + /* Remap anonymous mmap()-ed "map initialization image" as + * a BPF map-backed mmap()-ed memory, but preserving the same + * memory address. This will cause kernel to change process' + * page table to point to a different piece of kernel memory, + * but from userspace point of view memory address (and its + * contents, being identical at this point) will stay the + * same. This mapping will be released by bpf_object__close() + * as per normal clean up procedure, so we don't need to worry + * about it from skeleton's clean up perspective. + */ + *mmaped = mmap(map->mmaped, mmap_sz, prot, + MAP_SHARED | MAP_FIXED, map_fd, 0); + if (*mmaped == MAP_FAILED) { + err = -errno; + *mmaped = NULL; + pr_warn("failed to re-mmap() map '%s': %d\n", + bpf_map__name(map), err); + return err; + } + } + + return 0; +} + +int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) +{ + int i; + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_program *prog = *s->progs[i].prog; + struct bpf_link **link = s->progs[i].link; + const struct bpf_sec_def *sec_def; + const char *sec_name = bpf_program__title(prog, false); + + sec_def = find_sec_def(sec_name); + if (!sec_def || !sec_def->attach_fn) + continue; + + *link = sec_def->attach_fn(sec_def, prog); + if (IS_ERR(*link)) { + pr_warn("failed to auto-attach program '%s': %ld\n", + bpf_program__name(prog), PTR_ERR(*link)); + return PTR_ERR(*link); + } + } + + return 0; +} + +void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) +{ + int i; + + for (i = 0; i < s->prog_cnt; i++) { + struct bpf_link **link = s->progs[i].link; + + if (!IS_ERR_OR_NULL(*link)) + bpf_link__destroy(*link); + *link = NULL; + } +} + +void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) +{ + if (s->progs) + bpf_object__detach_skeleton(s); + if (s->obj) + bpf_object__close(*s->obj); + free(s->maps); + free(s->progs); + free(s); +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 5cbf459ece0b..3fe12c9d1f92 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -17,14 +17,12 @@ #include <sys/types.h> // for size_t #include <linux/bpf.h> +#include "libbpf_common.h" + #ifdef __cplusplus extern "C" { #endif -#ifndef LIBBPF_API -#define LIBBPF_API __attribute__((visibility("default"))) -#endif - enum libbpf_errno { __LIBBPF_ERRNO__START = 4000, @@ -57,7 +55,7 @@ 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; @@ -67,18 +65,61 @@ struct bpf_object_open_attr { enum bpf_prog_type prog_type; }; +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; + /* DEPRECATED: handle CO-RE relocations non-strictly, allowing failures. + * Value is ignored. Relocations always are processed non-strictly. + * Non-relocatable instructions are replaced with invalid ones to + * prevent accidental errors. + * */ + 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; + /* Additional kernel config content that augments and overrides + * system Kconfig for CONFIG_xxx externs. + */ + const char *kconfig; +}; +#define bpf_object_open_opts__last_field kconfig + LIBBPF_API struct bpf_object *bpf_object__open(const char *path); LIBBPF_API struct bpf_object * +bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts); +LIBBPF_API struct bpf_object * +bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, + const struct bpf_object_open_opts *opts); + +/* deprecated bpf_object__open variants */ +LIBBPF_API struct bpf_object * +bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, + const char *name); +LIBBPF_API struct bpf_object * bpf_object__open_xattr(struct bpf_object_open_attr *attr); -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); @@ -92,12 +133,14 @@ 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(const struct bpf_object *obj); LIBBPF_API unsigned int bpf_object__kversion(const struct bpf_object *obj); @@ -108,6 +151,9 @@ LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); LIBBPF_API struct bpf_program * bpf_object__find_program_by_title(const struct bpf_object *obj, const char *title); +LIBBPF_API struct bpf_program * +bpf_object__find_program_by_name(const struct bpf_object *obj, + const char *name); LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ @@ -126,6 +172,8 @@ 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; @@ -149,9 +197,13 @@ LIBBPF_API void *bpf_program__priv(const struct bpf_program *prog); LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); +LIBBPF_API const char *bpf_program__name(const struct bpf_program *prog); LIBBPF_API const char *bpf_program__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(const struct bpf_program *prog); @@ -167,9 +219,12 @@ LIBBPF_API void bpf_program__unload(struct bpf_program *prog); struct bpf_link; +LIBBPF_API void bpf_link__disconnect(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); LIBBPF_API struct bpf_link * +bpf_program__attach(struct bpf_program *prog); +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, @@ -186,6 +241,10 @@ 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_map; +LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map); struct bpf_insn; /* @@ -261,8 +320,16 @@ LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog); LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_tracing(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_struct_ops(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_extension(struct bpf_program *prog); + +LIBBPF_API 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); @@ -275,6 +342,9 @@ LIBBPF_API bool bpf_program__is_sched_cls(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_sched_act(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_xdp(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_perf_event(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_tracing(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_struct_ops(const struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_extension(const struct bpf_program *prog); /* * No need for __attribute__((packed)), all members of 'bpf_map_def' @@ -294,7 +364,6 @@ struct bpf_map_def { * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel, * so no need to worry about a name clash. */ -struct bpf_map; LIBBPF_API struct bpf_map * bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name); @@ -334,6 +403,9 @@ LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); 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); @@ -355,8 +427,18 @@ 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; @@ -422,18 +504,6 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, void **copy_mem, size_t *copy_size, bpf_perf_event_print_t fn, void *private_data); -struct nlattr; -typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); -int libbpf_netlink_open(unsigned int *nl_pid); -int libbpf_nl_get_link(int sock, unsigned int nl_pid, - libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); -int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); -int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, - libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); -int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, - libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); - struct bpf_prog_linfo; struct bpf_prog_info; @@ -460,6 +530,7 @@ LIBBPF_API bool bpf_probe_prog_type(enum bpf_prog_type prog_type, LIBBPF_API bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex); LIBBPF_API bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, __u32 ifindex); +LIBBPF_API bool bpf_probe_large_insn_limit(__u32 ifindex); /* * Get bpf_prog_info in continuous memory @@ -540,6 +611,50 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear); */ LIBBPF_API int libbpf_num_possible_cpus(void); +struct bpf_map_skeleton { + const char *name; + struct bpf_map **map; + void **mmaped; +}; + +struct bpf_prog_skeleton { + const char *name; + struct bpf_program **prog; + struct bpf_link **link; +}; + +struct bpf_object_skeleton { + size_t sz; /* size of this struct, for forward/backward compatibility */ + + const char *name; + void *data; + size_t data_sz; + + struct bpf_object **obj; + + int map_cnt; + int map_skel_sz; /* sizeof(struct bpf_skeleton_map) */ + struct bpf_map_skeleton *maps; + + int prog_cnt; + int prog_skel_sz; /* sizeof(struct bpf_skeleton_prog) */ + struct bpf_prog_skeleton *progs; +}; + +LIBBPF_API int +bpf_object__open_skeleton(struct bpf_object_skeleton *s, + const struct bpf_object_open_opts *opts); +LIBBPF_API int bpf_object__load_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s); +LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s); + +enum libbpf_tristate { + TRI_NO = 0, + TRI_YES = 1, + TRI_MODULE = 2, +}; + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f9d316e873d8..b035122142bb 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -183,4 +183,55 @@ LIBBPF_0.0.4 { 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; + +LIBBPF_0.0.7 { + global: + btf_dump__emit_type_decl; + bpf_link__disconnect; + bpf_map__attach_struct_ops; + bpf_map_delete_batch; + bpf_map_lookup_and_delete_batch; + bpf_map_lookup_batch; + bpf_map_update_batch; + bpf_object__find_program_by_name; + bpf_object__attach_skeleton; + bpf_object__destroy_skeleton; + bpf_object__detach_skeleton; + bpf_object__load_skeleton; + bpf_object__open_skeleton; + bpf_probe_large_insn_limit; + bpf_prog_attach_xattr; + bpf_program__attach; + bpf_program__name; + bpf_program__is_extension; + bpf_program__is_struct_ops; + bpf_program__set_extension; + bpf_program__set_struct_ops; + btf__align_of; + libbpf_find_kernel_btf; +} LIBBPF_0.0.6; diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template index ac17fcef2108..b45ed534bdfb 100644 --- a/tools/lib/bpf/libbpf.pc.template +++ b/tools/lib/bpf/libbpf.pc.template @@ -8,5 +8,5 @@ Name: libbpf Description: BPF library Version: @VERSION@ Libs: -L${libdir} -lbpf -Requires.private: libelf +Requires.private: libelf zlib Cflags: -I${includedir} diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h new file mode 100644 index 000000000000..a23ae1ac27eb --- /dev/null +++ b/tools/lib/bpf/libbpf_common.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Common user-facing libbpf helpers. + * + * Copyright (c) 2019 Facebook + */ + +#ifndef __LIBBPF_LIBBPF_COMMON_H +#define __LIBBPF_LIBBPF_COMMON_H + +#include <string.h> + +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + +/* 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__ \ + }; \ + }) + +#endif /* __LIBBPF_LIBBPF_COMMON_H */ diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c index 4343e40588c6..0afb51f7a919 100644 --- a/tools/lib/bpf/libbpf_errno.c +++ b/tools/lib/bpf/libbpf_errno.c @@ -13,6 +13,9 @@ #include "libbpf.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #define ERRNO_OFFSET(e) ((e) - __LIBBPF_ERRNO__START) #define ERRCODE_OFFSET(c) ERRNO_OFFSET(LIBBPF_ERRNO__##c) #define NR_ERRNO (__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START) diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 2ac29bd36226..8c3afbd97747 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -29,6 +29,26 @@ #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, ...) @@ -39,11 +59,178 @@ do { \ libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \ } while (0) -#define pr_warning(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__) +#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\n", + 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 parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); +int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); +int 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); + +struct nlattr; +typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); +int libbpf_netlink_open(unsigned int *nl_pid); +int libbpf_nl_get_link(int sock, unsigned int nl_pid, + libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); +int libbpf_nl_get_class(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_class_nlmsg, void *cookie); +int libbpf_nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + libbpf_dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); +int libbpf_nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + libbpf_dump_nlmsg_t dump_filter_nlmsg, void *cookie); + +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 ace1a0708d99..b782ebef6ac9 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -17,6 +17,9 @@ #include "libbpf.h" #include "libbpf_internal.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + static bool grep(const char *buffer, const char *pattern) { return !!strstr(buffer, pattern); @@ -102,6 +105,9 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_STRUCT_OPS: + case BPF_PROG_TYPE_EXT: default: break; } @@ -244,11 +250,13 @@ 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: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: + case BPF_MAP_TYPE_STRUCT_OPS: default: break; } @@ -319,3 +327,24 @@ bool bpf_probe_helper(enum bpf_func_id id, enum bpf_prog_type prog_type, return res; } + +/* + * Probe for availability of kernel commit (5.3): + * + * c04c0d2b968a ("bpf: increase complexity limit and maximum program size") + */ +bool bpf_probe_large_insn_limit(__u32 ifindex) +{ + struct bpf_insn insns[BPF_MAXINSNS + 1]; + int i; + + for (i = 0; i < BPF_MAXINSNS; i++) + insns[i] = BPF_MOV64_IMM(BPF_REG_0, 1); + insns[BPF_MAXINSNS] = BPF_EXIT_INSN(); + + errno = 0; + probe_load(BPF_PROG_TYPE_SCHED_CLS, insns, ARRAY_SIZE(insns), NULL, 0, + ifindex); + + return errno != E2BIG && errno != EINVAL; +} diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index ce3ec81b71c0..431bd25c6cdb 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -12,8 +12,12 @@ #include "bpf.h" #include "libbpf.h" +#include "libbpf_internal.h" #include "nlattr.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #ifndef SOL_NETLINK #define SOL_NETLINK 270 #endif @@ -24,7 +28,7 @@ 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 +47,7 @@ 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 +206,11 @@ 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 +226,40 @@ 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 +275,44 @@ 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..0ad41dfea8eb 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -8,10 +8,14 @@ #include <errno.h> #include "nlattr.h" +#include "libbpf_internal.h" #include <linux/rtnetlink.h> #include <string.h> #include <stdio.h> +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + static uint16_t nla_attr_minlen[LIBBPF_NLA_TYPE_MAX+1] = { [LIBBPF_NLA_U8] = sizeof(uint8_t), [LIBBPF_NLA_U16] = sizeof(uint16_t), @@ -121,8 +125,8 @@ 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 +185,14 @@ 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 b8064eedc177..146da01979c7 100644 --- a/tools/lib/bpf/str_error.c +++ b/tools/lib/bpf/str_error.c @@ -4,6 +4,9 @@ #include <stdio.h> #include "str_error.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + /* * Wrapper to allow for building in non-GNU systems such as Alpine Linux's musl * libc, while checking strerror_r() return to avoid having to check this in diff --git a/tools/lib/bpf/test_libbpf.cpp b/tools/lib/bpf/test_libbpf.cpp deleted file mode 100644 index fc134873bb6d..000000000000 --- a/tools/lib/bpf/test_libbpf.cpp +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#include "libbpf.h" -#include "bpf.h" -#include "btf.h" - -/* do nothing, just make sure we can link successfully */ - -int main(int argc, char *argv[]) -{ - /* libbpf.h */ - libbpf_set_print(NULL); - - /* bpf.h */ - bpf_prog_get_fd_by_id(0); - - /* btf.h */ - btf__new(NULL, 0); -} diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 680e63066cf3..9807903f121e 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -32,6 +32,9 @@ #include "libbpf_internal.h" #include "xsk.h" +/* make sure libbpf doesn't use kernel-only integer typedefs */ +#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 + #ifndef SOL_XDP #define SOL_XDP 283 #endif @@ -65,7 +68,6 @@ struct xsk_socket { int xsks_map_fd; __u32 queue_id; char ifname[IFNAMSIZ]; - bool zc; }; struct xsk_nl_info { @@ -74,22 +76,20 @@ 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) { @@ -116,6 +116,7 @@ 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; } @@ -123,6 +124,7 @@ 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, @@ -149,14 +151,66 @@ 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; @@ -178,10 +232,12 @@ 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) { @@ -203,17 +259,15 @@ 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; @@ -224,13 +278,13 @@ 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; @@ -241,6 +295,7 @@ 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; @@ -255,6 +310,29 @@ 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) { static const int log_buf_size = 16 * 1024; @@ -264,33 +342,55 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) /* This is the C-program: * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) * { - * int 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. + * ret = bpf_redirect_map(&xsks_map, index, XDP_PASS); + * if (ret > 0) + * return ret; + * + * // Fallback for pre-5.3 kernels, not supporting default + * // action in the flags parameter. * if (bpf_map_lookup_elem(&xsks_map, &index)) * return bpf_redirect_map(&xsks_map, index, 0); - * * return XDP_PASS; * } */ struct bpf_insn prog[] = { - /* 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), + /* 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, 2), - /* 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(), @@ -301,7 +401,7 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk) "LGPL-2.1 or BSD-2-Clause", 0, log_buf, log_buf_size); if (prog_fd < 0) { - pr_warning("BPF log buffer:\n%s", log_buf); + pr_warn("BPF log buffer:\n%s", log_buf); return prog_fd; } @@ -334,13 +434,18 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) goto out; } - if (err || channels.max_combined == 0) + 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); @@ -456,6 +561,8 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) } } 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); @@ -463,7 +570,8 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) } } - err = xsk_set_bpf_maps(xsk); + if (xsk->rx) + err = xsk_set_bpf_maps(xsk); if (err) { xsk_delete_bpf_maps(xsk); close(xsk->prog_fd); @@ -481,23 +589,27 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, void *rx_map = NULL, *tx_map = NULL; struct sockaddr_xdp sxdp = {}; struct xdp_mmap_offsets off; - struct xdp_options opts; struct xsk_socket *xsk; - socklen_t optlen; 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) { @@ -519,10 +631,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, memcpy(xsk->ifname, ifname, IFNAMSIZ - 1); xsk->ifname[IFNAMSIZ - 1] = '\0'; - err = xsk_set_xdp_socket_config(&xsk->config, usr_config); - if (err) - goto out_socket; - if (rx) { err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING, &xsk->config.rx_size, @@ -542,19 +650,17 @@ 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) { - 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); + 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; @@ -564,16 +670,16 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, rx->size = xsk->config.rx_size; rx->producer = rx_map + off.rx.producer; rx->consumer = rx_map + off.rx.consumer; + rx->flags = rx_map + off.rx.flags; rx->ring = rx_map + off.rx.desc; } xsk->rx = rx; if (tx) { - 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); + 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; @@ -583,6 +689,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, tx->size = xsk->config.tx_size; tx->producer = tx_map + off.tx.producer; tx->consumer = tx_map + off.tx.consumer; + tx->flags = tx_map + off.tx.flags; tx->ring = tx_map + off.tx.desc; tx->cached_cons = xsk->config.tx_size; } @@ -591,7 +698,12 @@ 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) { @@ -601,15 +713,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, xsk->prog_fd = -1; - optlen = sizeof(opts); - err = getsockopt(xsk->fd, SOL_XDP, XDP_OPTIONS, &opts, &optlen); - if (err) { - err = -errno; - goto out_mmap_tx; - } - - xsk->zc = opts.flags & XDP_OPTIONS_ZEROCOPY; - if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { err = xsk_setup_xdp_prog(xsk); if (err) @@ -638,7 +741,6 @@ out_xsk_alloc: int xsk_umem__delete(struct xsk_umem *umem) { struct xdp_mmap_offsets off; - socklen_t optlen; int err; if (!umem) @@ -647,8 +749,7 @@ 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 - off.fr.desc, off.fr.desc + umem->config.fill_size * sizeof(__u64)); @@ -666,7 +767,6 @@ 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) @@ -677,8 +777,7 @@ void xsk_socket__delete(struct xsk_socket *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, diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h index 833a6e60d065..584f6820a639 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/lib/bpf/xsk.h @@ -32,6 +32,7 @@ struct name { \ __u32 *producer; \ __u32 *consumer; \ void *ring; \ + __u32 *flags; \ } DEFINE_XSK_RING(xsk_ring_prod); @@ -76,6 +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; @@ -162,6 +168,21 @@ 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); @@ -170,12 +191,14 @@ LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk); #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. */ @@ -195,6 +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, diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h index a81d91d4fc78..a6d7ee5f18ba 100644 --- a/tools/lib/lockdep/include/liblockdep/common.h +++ b/tools/lib/lockdep/include/liblockdep/common.h @@ -42,8 +42,7 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, void lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, struct lockdep_map *nest_lock, unsigned long ip); -void lock_release(struct lockdep_map *lock, int nested, - unsigned long ip); +void lock_release(struct lockdep_map *lock, unsigned long ip); void lockdep_reset_lock(struct lockdep_map *lock); void lockdep_register_key(struct lock_class_key *key); void lockdep_unregister_key(struct lock_class_key *key); diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h index 783dd0df06f9..bd106b82759b 100644 --- a/tools/lib/lockdep/include/liblockdep/mutex.h +++ b/tools/lib/lockdep/include/liblockdep/mutex.h @@ -42,7 +42,7 @@ static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock static inline int liblockdep_pthread_mutex_unlock(liblockdep_pthread_mutex_t *lock) { - lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&lock->dep_map, (unsigned long)_RET_IP_); return pthread_mutex_unlock(&lock->mutex); } diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h index 365762e3a1ea..6d5d2932bf4d 100644 --- a/tools/lib/lockdep/include/liblockdep/rwlock.h +++ b/tools/lib/lockdep/include/liblockdep/rwlock.h @@ -44,7 +44,7 @@ static inline int liblockdep_pthread_rwlock_rdlock(liblockdep_pthread_rwlock_t * static inline int liblockdep_pthread_rwlock_unlock(liblockdep_pthread_rwlock_t *lock) { - lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&lock->dep_map, (unsigned long)_RET_IP_); return pthread_rwlock_unlock(&lock->rwlock); } diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c index 76245d16196d..8f1adbe887b2 100644 --- a/tools/lib/lockdep/preload.c +++ b/tools/lib/lockdep/preload.c @@ -270,7 +270,7 @@ int pthread_mutex_lock(pthread_mutex_t *mutex) */ r = ll_pthread_mutex_lock(mutex); if (r) - lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -284,7 +284,7 @@ int pthread_mutex_trylock(pthread_mutex_t *mutex) lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_mutex_trylock(mutex); if (r) - lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -295,7 +295,7 @@ int pthread_mutex_unlock(pthread_mutex_t *mutex) try_init_preload(); - lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(mutex)->dep_map, (unsigned long)_RET_IP_); /* * Just like taking a lock, only in reverse! * @@ -355,7 +355,7 @@ int pthread_rwlock_rdlock(pthread_rwlock_t *rwlock) lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_rdlock(rwlock); if (r) - lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -369,7 +369,7 @@ int pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock) lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_tryrdlock(rwlock); if (r) - lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -383,7 +383,7 @@ int pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock) lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_trywrlock(rwlock); if (r) - lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -397,7 +397,7 @@ int pthread_rwlock_wrlock(pthread_rwlock_t *rwlock) lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_wrlock(rwlock); if (r) - lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); return r; } @@ -408,7 +408,7 @@ int pthread_rwlock_unlock(pthread_rwlock_t *rwlock) init_preload(); - lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_); + lock_release(&__get_lock(rwlock)->dep_map, (unsigned long)_RET_IP_); r = ll_pthread_rwlock_unlock(rwlock); if (r) lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_); diff --git a/tools/lib/perf/Build b/tools/lib/perf/Build new file mode 100644 index 000000000000..2ef9a4ec6d99 --- /dev/null +++ b/tools/lib/perf/Build @@ -0,0 +1,13 @@ +libperf-y += core.o +libperf-y += cpumap.o +libperf-y += threadmap.o +libperf-y += evsel.o +libperf-y += evlist.o +libperf-y += mmap.o +libperf-y += zalloc.o +libperf-y += xyarray.o +libperf-y += lib.o + +$(OUTPUT)zalloc.o: ../../lib/zalloc.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/lib/perf/Documentation/Makefile b/tools/lib/perf/Documentation/Makefile new file mode 100644 index 000000000000..972754082a85 --- /dev/null +++ b/tools/lib/perf/Documentation/Makefile @@ -0,0 +1,156 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +# Most of this file is copied from tools/perf/Documentation/Makefile + +include ../../../scripts/Makefile.include +include ../../../scripts/utilities.mak + +MAN3_TXT = libperf.txt +MAN7_TXT = libperf-counting.txt libperf-sampling.txt +MAN_EX = examples/*.c + +MAN_TXT = $(MAN3_TXT) $(MAN7_TXT) + +_MAN_XML = $(patsubst %.txt,%.xml,$(MAN_TXT)) +_MAN_HTML = $(patsubst %.txt,%.html,$(MAN_TXT)) +_MAN_3 = $(patsubst %.txt,%.3,$(MAN3_TXT)) +_MAN_7 = $(patsubst %.txt,%.7,$(MAN7_TXT)) + +MAN_XML = $(addprefix $(OUTPUT),$(_MAN_XML)) +MAN_HTML = $(addprefix $(OUTPUT),$(_MAN_HTML)) +MAN_3 = $(addprefix $(OUTPUT),$(_MAN_3)) +MAN_7 = $(addprefix $(OUTPUT),$(_MAN_7)) +MAN_X = $(MAN_3) $(MAN_7) + +# Make the path relative to DESTDIR, not prefix +ifndef DESTDIR + prefix ?=$(HOME) +endif + +mandir ?= $(prefix)/share/man +man3dir = $(mandir)/man3 +man7dir = $(mandir)/man7 + +docdir ?= $(prefix)/share/doc/libperf +htmldir = $(docdir)/html +exdir = $(docdir)/examples + +ASCIIDOC = asciidoc +ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf +ASCIIDOC_HTML = xhtml11 +MANPAGE_XSL = manpage-normal.xsl +XMLTO_EXTRA = +XMLTO =xmlto + +INSTALL ?= install +RM ?= rm -f + +# For asciidoc ... +# -7.1.2, no extra settings are needed. +# 8.0-, set ASCIIDOC8. +# + +# For docbook-xsl ... +# -1.68.1, set ASCIIDOC_NO_ROFF? (based on changelog from 1.73.0) +# 1.69.0, no extra settings are needed? +# 1.69.1-1.71.0, set DOCBOOK_SUPPRESS_SP? +# 1.71.1, no extra settings are needed? +# 1.72.0, set DOCBOOK_XSL_172. +# 1.73.0-, set ASCIIDOC_NO_ROFF + +# If you had been using DOCBOOK_XSL_172 in an attempt to get rid +# of 'the ".ft C" problem' in your generated manpages, and you +# instead ended up with weird characters around callouts, try +# using ASCIIDOC_NO_ROFF instead (it works fine with ASCIIDOC8). + +ifdef ASCIIDOC8 + ASCIIDOC_EXTRA += -a asciidoc7compatible +endif +ifdef DOCBOOK_XSL_172 + ASCIIDOC_EXTRA += -a libperf-asciidoc-no-roff + MANPAGE_XSL = manpage-1.72.xsl +else + ifdef ASCIIDOC_NO_ROFF + # docbook-xsl after 1.72 needs the regular XSL, but will not + # pass-thru raw roff codes from asciidoc.conf, so turn them off. + ASCIIDOC_EXTRA += -a libperf-asciidoc-no-roff + endif +endif +ifdef MAN_BOLD_LITERAL + XMLTO_EXTRA += -m manpage-bold-literal.xsl +endif +ifdef DOCBOOK_SUPPRESS_SP + XMLTO_EXTRA += -m manpage-suppress-sp.xsl +endif + +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +export DESTDIR DESTDIR_SQ + +# Please note that there is a minor bug in asciidoc. +# The version after 6.0.3 _will_ include the patch found here: +# http://marc.theaimsgroup.com/?l=libtraceevent&m=111558757202243&w=2 +# +# Until that version is released you may have to apply the patch +# yourself - yes, all 6 characters of it! + +QUIET_SUBDIR0 = +$(MAKE) -C # space to separate -C and subdir +QUIET_SUBDIR1 = + +ifneq ($(findstring $(MAKEFLAGS),w),w) + PRINT_DIR = --no-print-directory +else # "make -w" + NO_SUBDIR = : +endif + +ifneq ($(findstring $(MAKEFLAGS),s),s) + ifneq ($(V),1) + QUIET_ASCIIDOC = @echo ' ASCIIDOC '$@; + QUIET_XMLTO = @echo ' XMLTO '$@; + endif +endif + +all: $(MAN_X) $(MAN_HTML) + +$(MAN_HTML) $(MAN_X): asciidoc.conf + +install-man: all + $(call QUIET_INSTALL, man) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(man3dir); \ + $(INSTALL) -m 644 $(MAN_3) $(DESTDIR)$(man3dir); \ + $(INSTALL) -d -m 755 $(DESTDIR)$(man7dir); \ + $(INSTALL) -m 644 $(MAN_7) $(DESTDIR)$(man7dir); + +install-html: + $(call QUIET_INSTALL, html) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(htmldir); \ + $(INSTALL) -m 644 $(MAN_HTML) $(DESTDIR)$(htmldir); \ + +install-examples: + $(call QUIET_INSTALL, examples) \ + $(INSTALL) -d -m 755 $(DESTDIR)$(exdir); \ + $(INSTALL) -m 644 $(MAN_EX) $(DESTDIR)$(exdir); \ + +CLEAN_FILES = \ + $(MAN_XML) $(addsuffix +,$(MAN_XML)) \ + $(MAN_HTML) $(addsuffix +,$(MAN_HTML)) \ + $(MAN_X) + +clean: + $(call QUIET_CLEAN, Documentation) $(RM) $(CLEAN_FILES) + +$(MAN_3): $(OUTPUT)%.3: %.xml + $(QUIET_XMLTO)$(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< + +$(MAN_7): $(OUTPUT)%.7: %.xml + $(QUIET_XMLTO)$(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $< + +$(MAN_XML): $(OUTPUT)%.xml: %.txt + $(QUIET_ASCIIDOC)$(ASCIIDOC) -b docbook -d manpage \ + $(ASCIIDOC_EXTRA) -alibperf_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ + +$(MAN_HTML): $(OUTPUT)%.html: %.txt + $(QUIET_ASCIIDOC)$(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \ + $(ASCIIDOC_EXTRA) -aperf_version=$(EVENT_PARSE_VERSION) -o $@+ $< && \ + mv $@+ $@ diff --git a/tools/lib/perf/Documentation/asciidoc.conf b/tools/lib/perf/Documentation/asciidoc.conf new file mode 100644 index 000000000000..9d5a5a5ee091 --- /dev/null +++ b/tools/lib/perf/Documentation/asciidoc.conf @@ -0,0 +1,120 @@ +## linktep: macro +# +# Usage: linktep:command[manpage-section] +# +# Note, {0} is the manpage section, while {target} is the command. +# +# Show TEP link as: <command>(<section>); if section is defined, else just show +# the command. + +[macros] +(?su)[\\]?(?P<name>linktep):(?P<target>\S*?)\[(?P<attrlist>.*?)\]= + +[attributes] +asterisk=* +plus=+ +caret=^ +startsb=[ +endsb=] +tilde=~ + +ifdef::backend-docbook[] +[linktep-inlinemacro] +{0%{target}} +{0#<citerefentry>} +{0#<refentrytitle>{target}</refentrytitle><manvolnum>{0}</manvolnum>} +{0#</citerefentry>} +endif::backend-docbook[] + +ifdef::backend-docbook[] +ifndef::tep-asciidoc-no-roff[] +# "unbreak" docbook-xsl v1.68 for manpages. v1.69 works with or without this. +# v1.72 breaks with this because it replaces dots not in roff requests. +[listingblock] +<example><title>{title}</title> +<literallayout> +ifdef::doctype-manpage[] + .ft C +endif::doctype-manpage[] +| +ifdef::doctype-manpage[] + .ft +endif::doctype-manpage[] +</literallayout> +{title#}</example> +endif::tep-asciidoc-no-roff[] + +ifdef::tep-asciidoc-no-roff[] +ifdef::doctype-manpage[] +# The following two small workarounds insert a simple paragraph after screen +[listingblock] +<example><title>{title}</title> +<literallayout> +| +</literallayout><simpara></simpara> +{title#}</example> + +[verseblock] +<formalpara{id? id="{id}"}><title>{title}</title><para> +{title%}<literallayout{id? id="{id}"}> +{title#}<literallayout> +| +</literallayout> +{title#}</para></formalpara> +{title%}<simpara></simpara> +endif::doctype-manpage[] +endif::tep-asciidoc-no-roff[] +endif::backend-docbook[] + +ifdef::doctype-manpage[] +ifdef::backend-docbook[] +[header] +template::[header-declarations] +<refentry> +<refmeta> +<refentrytitle>{mantitle}</refentrytitle> +<manvolnum>{manvolnum}</manvolnum> +<refmiscinfo class="source">libperf</refmiscinfo> +<refmiscinfo class="version">{libperf_version}</refmiscinfo> +<refmiscinfo class="manual">libperf Manual</refmiscinfo> +</refmeta> +<refnamediv> + <refname>{manname1}</refname> + <refname>{manname2}</refname> + <refname>{manname3}</refname> + <refname>{manname4}</refname> + <refname>{manname5}</refname> + <refname>{manname6}</refname> + <refname>{manname7}</refname> + <refname>{manname8}</refname> + <refname>{manname9}</refname> + <refname>{manname10}</refname> + <refname>{manname11}</refname> + <refname>{manname12}</refname> + <refname>{manname13}</refname> + <refname>{manname14}</refname> + <refname>{manname15}</refname> + <refname>{manname16}</refname> + <refname>{manname17}</refname> + <refname>{manname18}</refname> + <refname>{manname19}</refname> + <refname>{manname20}</refname> + <refname>{manname21}</refname> + <refname>{manname22}</refname> + <refname>{manname23}</refname> + <refname>{manname24}</refname> + <refname>{manname25}</refname> + <refname>{manname26}</refname> + <refname>{manname27}</refname> + <refname>{manname28}</refname> + <refname>{manname29}</refname> + <refname>{manname30}</refname> + <refpurpose>{manpurpose}</refpurpose> +</refnamediv> +endif::backend-docbook[] +endif::doctype-manpage[] + +ifdef::backend-xhtml11[] +[linktep-inlinemacro] +<a href="{target}.html">{target}{0?({0})}</a> +endif::backend-xhtml11[] diff --git a/tools/lib/perf/Documentation/examples/sampling.c b/tools/lib/perf/Documentation/examples/sampling.c new file mode 100644 index 000000000000..8e1a926a9cfe --- /dev/null +++ b/tools/lib/perf/Documentation/examples/sampling.c @@ -0,0 +1,119 @@ +#include <linux/perf_event.h> +#include <perf/evlist.h> +#include <perf/evsel.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <perf/mmap.h> +#include <perf/core.h> +#include <perf/event.h> +#include <stdio.h> +#include <unistd.h> + +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + +union u64_swap { + __u64 val64; + __u32 val32[2]; +}; + +int main(int argc, char **argv) +{ + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_mmap *map; + struct perf_cpu_map *cpus; + struct perf_event_attr attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .disabled = 1, + .freq = 1, + .sample_freq = 10, + .sample_type = PERF_SAMPLE_IP|PERF_SAMPLE_TID|PERF_SAMPLE_CPU|PERF_SAMPLE_PERIOD, + }; + int err = -1; + union perf_event *event; + + libperf_init(libperf_print); + + cpus = perf_cpu_map__new(NULL); + if (!cpus) { + fprintf(stderr, "failed to create cpus\n"); + return -1; + } + + evlist = perf_evlist__new(); + if (!evlist) { + fprintf(stderr, "failed to create evlist\n"); + goto out_cpus; + } + + evsel = perf_evsel__new(&attr); + if (!evsel) { + fprintf(stderr, "failed to create cycles\n"); + goto out_cpus; + } + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, cpus, NULL); + + err = perf_evlist__open(evlist); + if (err) { + fprintf(stderr, "failed to open evlist\n"); + goto out_evlist; + } + + err = perf_evlist__mmap(evlist, 4); + if (err) { + fprintf(stderr, "failed to mmap evlist\n"); + goto out_evlist; + } + + perf_evlist__enable(evlist); + sleep(3); + perf_evlist__disable(evlist); + + perf_evlist__for_each_mmap(evlist, map, false) { + if (perf_mmap__read_init(map) < 0) + continue; + + while ((event = perf_mmap__read_event(map)) != NULL) { + int cpu, pid, tid; + __u64 ip, period, *array; + union u64_swap u; + + array = event->sample.array; + + ip = *array; + array++; + + u.val64 = *array; + pid = u.val32[0]; + tid = u.val32[1]; + array++; + + u.val64 = *array; + cpu = u.val32[0]; + array++; + + period = *array; + + fprintf(stdout, "cpu %3d, pid %6d, tid %6d, ip %20llx, period %20llu\n", + cpu, pid, tid, ip, period); + + perf_mmap__consume(map); + } + + perf_mmap__read_done(map); + } + +out_evlist: + perf_evlist__delete(evlist); +out_cpus: + perf_cpu_map__put(cpus); + return err; +} diff --git a/tools/lib/perf/Documentation/libperf-counting.txt b/tools/lib/perf/Documentation/libperf-counting.txt new file mode 100644 index 000000000000..cae9757f49c1 --- /dev/null +++ b/tools/lib/perf/Documentation/libperf-counting.txt @@ -0,0 +1,211 @@ +libperf-counting(7) +=================== + +NAME +---- +libperf-counting - counting interface + +DESCRIPTION +----------- +The counting interface provides API to meassure and get count for specific perf events. + +The following test tries to explain count on `counting.c` example. + +It is by no means complete guide to counting, but shows libperf basic API for counting. + +The `counting.c` comes with libbperf package and can be compiled and run like: + +[source,bash] +-- +$ gcc -o counting counting.c -lperf +$ sudo ./counting +count 176792, enabled 176944, run 176944 +count 176242, enabled 176242, run 176242 +-- + +It requires root access, because of the `PERF_COUNT_SW_CPU_CLOCK` event, +which is available only for root. + +The `counting.c` example monitors two events on the current process and displays their count, in a nutshel it: + +* creates events +* adds them to the event list +* opens and enables events through the event list +* does some workload +* disables events +* reads and displays event counts +* destroys the event list + +The first thing you need to do before using libperf is to call init function: + +[source,c] +-- + 8 static int libperf_print(enum libperf_print_level level, + 9 const char *fmt, va_list ap) + 10 { + 11 return vfprintf(stderr, fmt, ap); + 12 } + + 14 int main(int argc, char **argv) + 15 { + ... + 35 libperf_init(libperf_print); +-- + +It will setup the library and sets function for debug output from library. + +The `libperf_print` callback will receive any message with its debug level, +defined as: + +[source,c] +-- +enum libperf_print_level { + LIBPERF_ERR, + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, + LIBPERF_DEBUG2, + LIBPERF_DEBUG3, +}; +-- + +Once the setup is complete we start by defining specific events using the `struct perf_event_attr`. + +We create software events for cpu and task: + +[source,c] +-- + 20 struct perf_event_attr attr1 = { + 21 .type = PERF_TYPE_SOFTWARE, + 22 .config = PERF_COUNT_SW_CPU_CLOCK, + 23 .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING, + 24 .disabled = 1, + 25 }; + 26 struct perf_event_attr attr2 = { + 27 .type = PERF_TYPE_SOFTWARE, + 28 .config = PERF_COUNT_SW_TASK_CLOCK, + 29 .read_format = PERF_FORMAT_TOTAL_TIME_ENABLED|PERF_FORMAT_TOTAL_TIME_RUNNING, + 30 .disabled = 1, + 31 }; +-- + +The `read_format` setup tells perf to include timing details together with each count. + +Next step is to prepare threads map. + +In this case we will monitor current process, so we create threads map with single pid (0): + +[source,c] +-- + 37 threads = perf_thread_map__new_dummy(); + 38 if (!threads) { + 39 fprintf(stderr, "failed to create threads\n"); + 40 return -1; + 41 } + 42 + 43 perf_thread_map__set_pid(threads, 0, 0); +-- + +Now we create libperf's event list, which will serve as holder for the events we want: + +[source,c] +-- + 45 evlist = perf_evlist__new(); + 46 if (!evlist) { + 47 fprintf(stderr, "failed to create evlist\n"); + 48 goto out_threads; + 49 } +-- + +We create libperf's events for the attributes we defined earlier and add them to the list: + +[source,c] +-- + 51 evsel = perf_evsel__new(&attr1); + 52 if (!evsel) { + 53 fprintf(stderr, "failed to create evsel1\n"); + 54 goto out_evlist; + 55 } + 56 + 57 perf_evlist__add(evlist, evsel); + 58 + 59 evsel = perf_evsel__new(&attr2); + 60 if (!evsel) { + 61 fprintf(stderr, "failed to create evsel2\n"); + 62 goto out_evlist; + 63 } + 64 + 65 perf_evlist__add(evlist, evsel); +-- + +Configure event list with the thread map and open events: + +[source,c] +-- + 67 perf_evlist__set_maps(evlist, NULL, threads); + 68 + 69 err = perf_evlist__open(evlist); + 70 if (err) { + 71 fprintf(stderr, "failed to open evsel\n"); + 72 goto out_evlist; + 73 } +-- + +Both events are created as disabled (note the `disabled = 1` assignment above), +so we need to enable the whole list explicitely (both events). + +From this moment events are counting and we can do our workload. + +When we are done we disable the events list. + +[source,c] +-- + 75 perf_evlist__enable(evlist); + 76 + 77 while (count--); + 78 + 79 perf_evlist__disable(evlist); +-- + +Now we need to get the counts from events, following code iterates throught the events list and read counts: + +[source,c] +-- + 81 perf_evlist__for_each_evsel(evlist, evsel) { + 82 perf_evsel__read(evsel, 0, 0, &counts); + 83 fprintf(stdout, "count %llu, enabled %llu, run %llu\n", + 84 counts.val, counts.ena, counts.run); + 85 } +-- + +And finaly cleanup. + +We close the whole events list (both events) and remove it together with the threads map: + +[source,c] +-- + 87 perf_evlist__close(evlist); + 88 + 89 out_evlist: + 90 perf_evlist__delete(evlist); + 91 out_threads: + 92 perf_thread_map__put(threads); + 93 return err; + 94 } +-- + +REPORTING BUGS +-------------- +Report bugs to <linux-perf-users@vger.kernel.org>. + +LICENSE +------- +libperf is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + +SEE ALSO +-------- +libperf(3), libperf-sampling(7) diff --git a/tools/lib/perf/Documentation/libperf-sampling.txt b/tools/lib/perf/Documentation/libperf-sampling.txt new file mode 100644 index 000000000000..d71a7b4fcf5f --- /dev/null +++ b/tools/lib/perf/Documentation/libperf-sampling.txt @@ -0,0 +1,243 @@ +libperf-sampling(7) +=================== + +NAME +---- +libperf-sampling - sampling interface + + +DESCRIPTION +----------- +The sampling interface provides API to meassure and get count for specific perf events. + +The following test tries to explain count on `sampling.c` example. + +It is by no means complete guide to sampling, but shows libperf basic API for sampling. + +The `sampling.c` comes with libbperf package and can be compiled and run like: + +[source,bash] +-- +$ gcc -o sampling sampling.c -lperf +$ sudo ./sampling +cpu 0, pid 0, tid 0, ip ffffffffad06c4e6, period 1 +cpu 0, pid 4465, tid 4469, ip ffffffffad118748, period 18322959 +cpu 0, pid 0, tid 0, ip ffffffffad115722, period 33544846 +cpu 0, pid 4465, tid 4470, ip 7f84fe0cdad6, period 23687474 +cpu 0, pid 0, tid 0, ip ffffffffad9e0349, period 34255790 +cpu 0, pid 4465, tid 4469, ip ffffffffad136581, period 38664069 +cpu 0, pid 0, tid 0, ip ffffffffad9e55e2, period 21922384 +cpu 0, pid 4465, tid 4470, ip 7f84fe0ebebf, period 17655175 +... +-- + +It requires root access, because it uses hardware cycles event. + +The `sampling.c` example profiles/samples all CPUs with hardware cycles, in a nutshel it: + +- creates events +- adds them to the event list +- opens and enables events through the event list +- sleeps for 3 seconds +- disables events +- reads and displays recorded samples +- destroys the event list + +The first thing you need to do before using libperf is to call init function: + +[source,c] +-- + 12 static int libperf_print(enum libperf_print_level level, + 13 const char *fmt, va_list ap) + 14 { + 15 return vfprintf(stderr, fmt, ap); + 16 } + + 23 int main(int argc, char **argv) + 24 { + ... + 40 libperf_init(libperf_print); +-- + +It will setup the library and sets function for debug output from library. + +The `libperf_print` callback will receive any message with its debug level, +defined as: + +[source,c] +-- +enum libperf_print_level { + LIBPERF_ERR, + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, + LIBPERF_DEBUG2, + LIBPERF_DEBUG3, +}; +-- + +Once the setup is complete we start by defining cycles event using the `struct perf_event_attr`: + +[source,c] +-- + 29 struct perf_event_attr attr = { + 30 .type = PERF_TYPE_HARDWARE, + 31 .config = PERF_COUNT_HW_CPU_CYCLES, + 32 .disabled = 1, + 33 .freq = 1, + 34 .sample_freq = 10, + 35 .sample_type = PERF_SAMPLE_IP|PERF_SAMPLE_TID|PERF_SAMPLE_CPU|PERF_SAMPLE_PERIOD, + 36 }; +-- + +Next step is to prepare cpus map. + +In this case we will monitor all the available CPUs: + +[source,c] +-- + 42 cpus = perf_cpu_map__new(NULL); + 43 if (!cpus) { + 44 fprintf(stderr, "failed to create cpus\n"); + 45 return -1; + 46 } +-- + +Now we create libperf's event list, which will serve as holder for the cycles event: + +[source,c] +-- + 48 evlist = perf_evlist__new(); + 49 if (!evlist) { + 50 fprintf(stderr, "failed to create evlist\n"); + 51 goto out_cpus; + 52 } +-- + +We create libperf's event for the cycles attribute we defined earlier and add it to the list: + +[source,c] +-- + 54 evsel = perf_evsel__new(&attr); + 55 if (!evsel) { + 56 fprintf(stderr, "failed to create cycles\n"); + 57 goto out_cpus; + 58 } + 59 + 60 perf_evlist__add(evlist, evsel); +-- + +Configure event list with the cpus map and open event: + +[source,c] +-- + 62 perf_evlist__set_maps(evlist, cpus, NULL); + 63 + 64 err = perf_evlist__open(evlist); + 65 if (err) { + 66 fprintf(stderr, "failed to open evlist\n"); + 67 goto out_evlist; + 68 } +-- + +Once the events list is open, we can create memory maps AKA perf ring buffers: + +[source,c] +-- + 70 err = perf_evlist__mmap(evlist, 4); + 71 if (err) { + 72 fprintf(stderr, "failed to mmap evlist\n"); + 73 goto out_evlist; + 74 } +-- + +The event is created as disabled (note the `disabled = 1` assignment above), +so we need to enable the events list explicitely. + +From this moment the cycles event is sampling. + +We will sleep for 3 seconds while the ring buffers get data from all CPUs, then we disable the events list. + +[source,c] +-- + 76 perf_evlist__enable(evlist); + 77 sleep(3); + 78 perf_evlist__disable(evlist); +-- + +Following code walks through the ring buffers and reads stored events/samples: + +[source,c] +-- + 80 perf_evlist__for_each_mmap(evlist, map, false) { + 81 if (perf_mmap__read_init(map) < 0) + 82 continue; + 83 + 84 while ((event = perf_mmap__read_event(map)) != NULL) { + + /* process event */ + +108 perf_mmap__consume(map); +109 } +110 perf_mmap__read_done(map); +111 } + +-- + +Each sample needs to get parsed: + +[source,c] +-- + 85 int cpu, pid, tid; + 86 __u64 ip, period, *array; + 87 union u64_swap u; + 88 + 89 array = event->sample.array; + 90 + 91 ip = *array; + 92 array++; + 93 + 94 u.val64 = *array; + 95 pid = u.val32[0]; + 96 tid = u.val32[1]; + 97 array++; + 98 + 99 u.val64 = *array; +100 cpu = u.val32[0]; +101 array++; +102 +103 period = *array; +104 +105 fprintf(stdout, "cpu %3d, pid %6d, tid %6d, ip %20llx, period %20llu\n", +106 cpu, pid, tid, ip, period); +-- + +And finaly cleanup. + +We close the whole events list (both events) and remove it together with the threads map: + +[source,c] +-- +113 out_evlist: +114 perf_evlist__delete(evlist); +115 out_cpus: +116 perf_cpu_map__put(cpus); +117 return err; +118 } +-- + +REPORTING BUGS +-------------- +Report bugs to <linux-perf-users@vger.kernel.org>. + +LICENSE +------- +libperf is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + +SEE ALSO +-------- +libperf(3), libperf-counting(7) diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt new file mode 100644 index 000000000000..5a6bb512789d --- /dev/null +++ b/tools/lib/perf/Documentation/libperf.txt @@ -0,0 +1,246 @@ +libperf(3) +========== + +NAME +---- +libperf - Linux kernel perf event library + + +SYNOPSIS +-------- +*Generic API:* + +[source,c] +-- + #include <perf/core.h> + + enum libperf_print_level { + LIBPERF_ERR, + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, + LIBPERF_DEBUG2, + LIBPERF_DEBUG3, + }; + + typedef int (*libperf_print_fn_t)(enum libperf_print_level level, + const char *, va_list ap); + + void libperf_init(libperf_print_fn_t fn); +-- + +*API to handle cpu maps:* + +[source,c] +-- + #include <perf/cpumap.h> + + struct perf_cpu_map; + + struct perf_cpu_map *perf_cpu_map__dummy_new(void); + struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); + struct perf_cpu_map *perf_cpu_map__read(FILE *file); + struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); + struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, + struct perf_cpu_map *other); + void perf_cpu_map__put(struct perf_cpu_map *map); + int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); + int perf_cpu_map__nr(const struct perf_cpu_map *cpus); + bool perf_cpu_map__empty(const struct perf_cpu_map *map); + int perf_cpu_map__max(struct perf_cpu_map *map); + + #define perf_cpu_map__for_each_cpu(cpu, idx, cpus) +-- + +*API to handle thread maps:* + +[source,c] +-- + #include <perf/threadmap.h> + + struct perf_thread_map; + + struct perf_thread_map *perf_thread_map__new_dummy(void); + + void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid); + char *perf_thread_map__comm(struct perf_thread_map *map, int thread); + int perf_thread_map__nr(struct perf_thread_map *threads); + pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread); + + struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map); + void perf_thread_map__put(struct perf_thread_map *map); +-- + +*API to handle event lists:* + +[source,c] +-- + #include <perf/evlist.h> + + struct perf_evlist; + + void perf_evlist__add(struct perf_evlist *evlist, + struct perf_evsel *evsel); + void perf_evlist__remove(struct perf_evlist *evlist, + struct perf_evsel *evsel); + struct perf_evlist *perf_evlist__new(void); + void perf_evlist__delete(struct perf_evlist *evlist); + struct perf_evsel* perf_evlist__next(struct perf_evlist *evlist, + struct perf_evsel *evsel); + int perf_evlist__open(struct perf_evlist *evlist); + void perf_evlist__close(struct perf_evlist *evlist); + void perf_evlist__enable(struct perf_evlist *evlist); + void perf_evlist__disable(struct perf_evlist *evlist); + + #define perf_evlist__for_each_evsel(evlist, pos) + + void perf_evlist__set_maps(struct perf_evlist *evlist, + struct perf_cpu_map *cpus, + struct perf_thread_map *threads); + int perf_evlist__poll(struct perf_evlist *evlist, int timeout); + int perf_evlist__filter_pollfd(struct perf_evlist *evlist, + short revents_and_mask); + + int perf_evlist__mmap(struct perf_evlist *evlist, int pages); + void perf_evlist__munmap(struct perf_evlist *evlist); + + struct perf_mmap *perf_evlist__next_mmap(struct perf_evlist *evlist, + struct perf_mmap *map, + bool overwrite); + + #define perf_evlist__for_each_mmap(evlist, pos, overwrite) +-- + +*API to handle events:* + +[source,c] +-- + #include <perf/evsel.h>* + + struct perf_evsel; + + struct perf_counts_values { + union { + struct { + uint64_t val; + uint64_t ena; + uint64_t run; + }; + uint64_t values[3]; + }; + }; + + struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr); + void perf_evsel__delete(struct perf_evsel *evsel); + int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads); + void perf_evsel__close(struct perf_evsel *evsel); + void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); + int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count); + int perf_evsel__enable(struct perf_evsel *evsel); + int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); + int perf_evsel__disable(struct perf_evsel *evsel); + int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); + struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); + struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); + struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); +-- + +*API to handle maps (perf ring buffers):* + +[source,c] +-- + #include <perf/mmap.h> + + struct perf_mmap; + + void perf_mmap__consume(struct perf_mmap *map); + int perf_mmap__read_init(struct perf_mmap *map); + void perf_mmap__read_done(struct perf_mmap *map); + union perf_event *perf_mmap__read_event(struct perf_mmap *map); +-- + +*Structures to access perf API events:* + +[source,c] +-- + #include <perf/event.h> + + struct perf_record_mmap; + struct perf_record_mmap2; + struct perf_record_comm; + struct perf_record_namespaces; + struct perf_record_fork; + struct perf_record_lost; + struct perf_record_lost_samples; + struct perf_record_read; + struct perf_record_throttle; + struct perf_record_ksymbol; + struct perf_record_bpf_event; + struct perf_record_sample; + struct perf_record_switch; + struct perf_record_header_attr; + struct perf_record_record_cpu_map; + struct perf_record_cpu_map_data; + struct perf_record_cpu_map; + struct perf_record_event_update_cpus; + struct perf_record_event_update_scale; + struct perf_record_event_update; + struct perf_trace_event_type; + struct perf_record_header_event_type; + struct perf_record_header_tracing_data; + struct perf_record_header_build_id; + struct perf_record_id_index; + struct perf_record_auxtrace_info; + struct perf_record_auxtrace; + struct perf_record_auxtrace_error; + struct perf_record_aux; + struct perf_record_itrace_start; + struct perf_record_thread_map_entry; + struct perf_record_thread_map; + struct perf_record_stat_config_entry; + struct perf_record_stat_config; + struct perf_record_stat; + struct perf_record_stat_round; + struct perf_record_time_conv; + struct perf_record_header_feature; + struct perf_record_compressed; +-- + +DESCRIPTION +----------- +The libperf library provides an API to access the linux kernel perf +events subsystem. + +Following objects are key to the libperf interface: + +[horizontal] + +struct perf_cpu_map:: Provides a cpu list abstraction. + +struct perf_thread_map:: Provides a thread list abstraction. + +struct perf_evsel:: Provides an abstraction for single a perf event. + +struct perf_evlist:: Gathers several struct perf_evsel object and performs functions on all of them. + +struct perf_mmap:: Provides an abstraction for accessing perf ring buffer. + +The exported API functions bind these objects together. + +REPORTING BUGS +-------------- +Report bugs to <linux-perf-users@vger.kernel.org>. + +LICENSE +------- +libperf is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git + +SEE ALSO +-------- +libperf-sampling(7), libperf-counting(7) diff --git a/tools/lib/perf/Documentation/manpage-1.72.xsl b/tools/lib/perf/Documentation/manpage-1.72.xsl new file mode 100644 index 000000000000..b4d315cb8c47 --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-1.72.xsl @@ -0,0 +1,14 @@ +<!-- manpage-1.72.xsl: + special settings for manpages rendered from asciidoc+docbook + handles peculiarities in docbook-xsl 1.72.0 --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<xsl:import href="manpage-base.xsl"/> + +<!-- these are the special values for the roff control characters + needed for docbook-xsl 1.72.0 --> +<xsl:param name="git.docbook.backslash">▓</xsl:param> +<xsl:param name="git.docbook.dot" >⌂</xsl:param> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-base.xsl b/tools/lib/perf/Documentation/manpage-base.xsl new file mode 100644 index 000000000000..a264fa616093 --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-base.xsl @@ -0,0 +1,35 @@ +<!-- manpage-base.xsl: + special formatting for manpages rendered from asciidoc+docbook --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- these params silence some output from xmlto --> +<xsl:param name="man.output.quietly" select="1"/> +<xsl:param name="refentry.meta.get.quietly" select="1"/> + +<!-- convert asciidoc callouts to man page format; + git.docbook.backslash and git.docbook.dot params + must be supplied by another XSL file or other means --> +<xsl:template match="co"> + <xsl:value-of select="concat( + $git.docbook.backslash,'fB(', + substring-after(@id,'-'),')', + $git.docbook.backslash,'fR')"/> +</xsl:template> +<xsl:template match="calloutlist"> + <xsl:value-of select="$git.docbook.dot"/> + <xsl:text>sp </xsl:text> + <xsl:apply-templates/> + <xsl:text> </xsl:text> +</xsl:template> +<xsl:template match="callout"> + <xsl:value-of select="concat( + $git.docbook.backslash,'fB', + substring-after(@arearefs,'-'), + '. ',$git.docbook.backslash,'fR')"/> + <xsl:apply-templates/> + <xsl:value-of select="$git.docbook.dot"/> + <xsl:text>br </xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-bold-literal.xsl b/tools/lib/perf/Documentation/manpage-bold-literal.xsl new file mode 100644 index 000000000000..608eb5df6281 --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-bold-literal.xsl @@ -0,0 +1,17 @@ +<!-- manpage-bold-literal.xsl: + special formatting for manpages rendered from asciidoc+docbook --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- render literal text as bold (instead of plain or monospace); + this makes literal text easier to distinguish in manpages + viewed on a tty --> +<xsl:template match="literal"> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fB</xsl:text> + <xsl:apply-templates/> + <xsl:value-of select="$git.docbook.backslash"/> + <xsl:text>fR</xsl:text> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-normal.xsl b/tools/lib/perf/Documentation/manpage-normal.xsl new file mode 100644 index 000000000000..a48f5b11f3dc --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-normal.xsl @@ -0,0 +1,13 @@ +<!-- manpage-normal.xsl: + special settings for manpages rendered from asciidoc+docbook + handles anything we want to keep away from docbook-xsl 1.72.0 --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<xsl:import href="manpage-base.xsl"/> + +<!-- these are the normal values for the roff control characters --> +<xsl:param name="git.docbook.backslash">\</xsl:param> +<xsl:param name="git.docbook.dot" >.</xsl:param> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Documentation/manpage-suppress-sp.xsl b/tools/lib/perf/Documentation/manpage-suppress-sp.xsl new file mode 100644 index 000000000000..a63c7632a87d --- /dev/null +++ b/tools/lib/perf/Documentation/manpage-suppress-sp.xsl @@ -0,0 +1,21 @@ +<!-- manpage-suppress-sp.xsl: + special settings for manpages rendered from asciidoc+docbook + handles erroneous, inline .sp in manpage output of some + versions of docbook-xsl --> +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + version="1.0"> + +<!-- attempt to work around spurious .sp at the tail of the line + that some versions of docbook stylesheets seem to add --> +<xsl:template match="simpara"> + <xsl:variable name="content"> + <xsl:apply-templates/> + </xsl:variable> + <xsl:value-of select="normalize-space($content)"/> + <xsl:if test="not(ancestor::authorblurb) and + not(ancestor::personblurb)"> + <xsl:text> </xsl:text> + </xsl:if> +</xsl:template> + +</xsl:stylesheet> diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile new file mode 100644 index 000000000000..3718d65cffac --- /dev/null +++ b/tools/lib/perf/Makefile @@ -0,0 +1,191 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +# Most of this file is copied from tools/lib/bpf/Makefile + +LIBPERF_VERSION = 0 +LIBPERF_PATCHLEVEL = 0 +LIBPERF_EXTRAVERSION = 1 + +MAKEFLAGS += --no-print-directory + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +INSTALL = install + +# Use DESTDIR for installing into a different root directory. +# This is useful for building a package. The program will be +# installed in this directory as if it was the root directory. +# Then the build tool can move it later. +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +include $(srctree)/tools/scripts/Makefile.include +include $(srctree)/tools/scripts/Makefile.arch + +ifeq ($(LP64), 1) + libdir_relative = lib64 +else + libdir_relative = lib +endif + +prefix ?= +libdir = $(prefix)/$(libdir_relative) + +# Shell quotes +libdir_SQ = $(subst ','\'',$(libdir)) +libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) + +ifeq ("$(origin V)", "command line") + VERBOSE = $(V) +endif +ifndef VERBOSE + VERBOSE = 0 +endif + +ifeq ($(VERBOSE),1) + Q = +else + Q = @ +endif + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -Wall +endif + +INCLUDES = \ +-I$(srctree)/tools/lib/perf/include \ +-I$(srctree)/tools/lib/ \ +-I$(srctree)/tools/include \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/ \ +-I$(srctree)/tools/arch/$(SRCARCH)/include/uapi \ +-I$(srctree)/tools/include/uapi + +# Append required CFLAGS +override CFLAGS += $(EXTRA_WARNINGS) +override CFLAGS += -Werror -Wall +override CFLAGS += -fPIC +override CFLAGS += $(INCLUDES) +override CFLAGS += -fvisibility=hidden + +all: + +export srctree OUTPUT CC LD CFLAGS V +export DESTDIR DESTDIR_SQ + +include $(srctree)/tools/build/Makefile.include + +VERSION_SCRIPT := libperf.map + +PATCHLEVEL = $(LIBPERF_PATCHLEVEL) +EXTRAVERSION = $(LIBPERF_EXTRAVERSION) +VERSION = $(LIBPERF_VERSION).$(LIBPERF_PATCHLEVEL).$(LIBPERF_EXTRAVERSION) + +LIBPERF_SO := $(OUTPUT)libperf.so.$(VERSION) +LIBPERF_A := $(OUTPUT)libperf.a +LIBPERF_IN := $(OUTPUT)libperf-in.o +LIBPERF_PC := $(OUTPUT)libperf.pc + +LIBPERF_ALL := $(LIBPERF_A) $(OUTPUT)libperf.so* + +LIB_DIR := $(srctree)/tools/lib/api/ + +ifneq ($(OUTPUT),) +ifneq ($(subdir),) + API_PATH=$(OUTPUT)/../lib/api/ +else + API_PATH=$(OUTPUT) +endif +else + API_PATH=$(LIB_DIR) +endif + +LIBAPI = $(API_PATH)libapi.a +export LIBAPI + +$(LIBAPI): FORCE + $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) $(OUTPUT)libapi.a + +$(LIBAPI)-clean: + $(call QUIET_CLEAN, libapi) + $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null + +$(LIBPERF_IN): FORCE + $(Q)$(MAKE) $(build)=libperf + +$(LIBPERF_A): $(LIBPERF_IN) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN) + +$(LIBPERF_SO): $(LIBPERF_IN) $(LIBAPI) + $(QUIET_LINK)$(CC) --shared -Wl,-soname,libperf.so \ + -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@ + @ln -sf $(@F) $(OUTPUT)libperf.so + @ln -sf $(@F) $(OUTPUT)libperf.so.$(LIBPERF_VERSION) + + +libs: $(LIBPERF_A) $(LIBPERF_SO) $(LIBPERF_PC) + +all: fixdep + $(Q)$(MAKE) libs + +clean: $(LIBAPI)-clean + $(call QUIET_CLEAN, libperf) $(RM) $(LIBPERF_A) \ + *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBPERF_VERSION) .*.d .*.cmd LIBPERF-CFLAGS $(LIBPERF_PC) + $(Q)$(MAKE) -C tests clean + +tests: libs + $(Q)$(MAKE) -C tests + $(Q)$(MAKE) -C tests run + +$(LIBPERF_PC): + $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \ + -e "s|@LIBDIR@|$(libdir_SQ)|" \ + -e "s|@VERSION@|$(VERSION)|" \ + < libperf.pc.template > $@ + +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + +define do_install + if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ + fi; \ + $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2' +endef + +install_lib: libs + $(call QUIET_INSTALL, $(LIBPERF_ALL)) \ + $(call do_install_mkdir,$(libdir_SQ)); \ + cp -fpR $(LIBPERF_ALL) $(DESTDIR)$(libdir_SQ) + +install_headers: + $(call QUIET_INSTALL, headers) \ + $(call do_install,include/perf/core.h,$(prefix)/include/perf,644); \ + $(call do_install,include/perf/cpumap.h,$(prefix)/include/perf,644); \ + $(call do_install,include/perf/threadmap.h,$(prefix)/include/perf,644); \ + $(call do_install,include/perf/evlist.h,$(prefix)/include/perf,644); \ + $(call do_install,include/perf/evsel.h,$(prefix)/include/perf,644); \ + $(call do_install,include/perf/event.h,$(prefix)/include/perf,644); \ + $(call do_install,include/perf/mmap.h,$(prefix)/include/perf,644); + +install_pkgconfig: $(LIBPERF_PC) + $(call QUIET_INSTALL, $(LIBPERF_PC)) \ + $(call do_install,$(LIBPERF_PC),$(libdir_SQ)/pkgconfig,644) + +install_doc: + $(Q)$(MAKE) -C Documentation install-man install-html install-examples + +install: install_lib install_headers install_pkgconfig install_doc + +FORCE: + +.PHONY: all install clean tests FORCE diff --git a/tools/lib/perf/core.c b/tools/lib/perf/core.c new file mode 100644 index 000000000000..58fc894b76c5 --- /dev/null +++ b/tools/lib/perf/core.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define __printf(a, b) __attribute__((format(printf, a, b))) + +#include <stdio.h> +#include <stdarg.h> +#include <unistd.h> +#include <linux/compiler.h> +#include <perf/core.h> +#include <internal/lib.h> +#include "internal.h" + +static int __base_pr(enum libperf_print_level level __maybe_unused, const char *format, + va_list args) +{ + return vfprintf(stderr, format, args); +} + +static libperf_print_fn_t __libperf_pr = __base_pr; + +__printf(2, 3) +void libperf_print(enum libperf_print_level level, const char *format, ...) +{ + va_list args; + + if (!__libperf_pr) + return; + + va_start(args, format); + __libperf_pr(level, format, args); + va_end(args); +} + +void libperf_init(libperf_print_fn_t fn) +{ + page_size = sysconf(_SC_PAGE_SIZE); + __libperf_pr = fn; +} diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c new file mode 100644 index 000000000000..f93f4e703e4c --- /dev/null +++ b/tools/lib/perf/cpumap.c @@ -0,0 +1,345 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <perf/cpumap.h> +#include <stdlib.h> +#include <linux/refcount.h> +#include <internal/cpumap.h> +#include <asm/bug.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <ctype.h> +#include <limits.h> + +struct perf_cpu_map *perf_cpu_map__dummy_new(void) +{ + struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int)); + + if (cpus != NULL) { + cpus->nr = 1; + cpus->map[0] = -1; + refcount_set(&cpus->refcnt, 1); + } + + return cpus; +} + +static void cpu_map__delete(struct perf_cpu_map *map) +{ + if (map) { + WARN_ONCE(refcount_read(&map->refcnt) != 0, + "cpu_map refcnt unbalanced\n"); + free(map); + } +} + +struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map) +{ + if (map) + refcount_inc(&map->refcnt); + return map; +} + +void perf_cpu_map__put(struct perf_cpu_map *map) +{ + if (map && refcount_dec_and_test(&map->refcnt)) + cpu_map__delete(map); +} + +static struct perf_cpu_map *cpu_map__default_new(void) +{ + struct perf_cpu_map *cpus; + int nr_cpus; + + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + if (nr_cpus < 0) + return NULL; + + cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int)); + if (cpus != NULL) { + int i; + + for (i = 0; i < nr_cpus; ++i) + cpus->map[i] = i; + + cpus->nr = nr_cpus; + refcount_set(&cpus->refcnt, 1); + } + + return cpus; +} + +static int cmp_int(const void *a, const void *b) +{ + return *(const int *)a - *(const int*)b; +} + +static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus) +{ + size_t payload_size = nr_cpus * sizeof(int); + struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size); + int i, j; + + if (cpus != NULL) { + memcpy(cpus->map, tmp_cpus, payload_size); + qsort(cpus->map, nr_cpus, sizeof(int), cmp_int); + /* Remove dups */ + j = 0; + for (i = 0; i < nr_cpus; i++) { + if (i == 0 || cpus->map[i] != cpus->map[i - 1]) + cpus->map[j++] = cpus->map[i]; + } + cpus->nr = j; + assert(j <= nr_cpus); + refcount_set(&cpus->refcnt, 1); + } + + return cpus; +} + +struct perf_cpu_map *perf_cpu_map__read(FILE *file) +{ + struct perf_cpu_map *cpus = NULL; + int nr_cpus = 0; + int *tmp_cpus = NULL, *tmp; + int max_entries = 0; + int n, cpu, prev; + char sep; + + sep = 0; + prev = -1; + for (;;) { + n = fscanf(file, "%u%c", &cpu, &sep); + if (n <= 0) + break; + if (prev >= 0) { + int new_max = nr_cpus + cpu - prev - 1; + + WARN_ONCE(new_max >= MAX_NR_CPUS, "Perf can support %d CPUs. " + "Consider raising MAX_NR_CPUS\n", MAX_NR_CPUS); + + if (new_max >= max_entries) { + max_entries = new_max + MAX_NR_CPUS / 2; + tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + if (tmp == NULL) + goto out_free_tmp; + tmp_cpus = tmp; + } + + while (++prev < cpu) + tmp_cpus[nr_cpus++] = prev; + } + if (nr_cpus == max_entries) { + max_entries += MAX_NR_CPUS; + tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + if (tmp == NULL) + goto out_free_tmp; + tmp_cpus = tmp; + } + + tmp_cpus[nr_cpus++] = cpu; + if (n == 2 && sep == '-') + prev = cpu; + else + prev = -1; + if (n == 1 || sep == '\n') + break; + } + + if (nr_cpus > 0) + cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); + else + cpus = cpu_map__default_new(); +out_free_tmp: + free(tmp_cpus); + return cpus; +} + +static struct perf_cpu_map *cpu_map__read_all_cpu_map(void) +{ + struct perf_cpu_map *cpus = NULL; + FILE *onlnf; + + onlnf = fopen("/sys/devices/system/cpu/online", "r"); + if (!onlnf) + return cpu_map__default_new(); + + cpus = perf_cpu_map__read(onlnf); + fclose(onlnf); + return cpus; +} + +struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list) +{ + struct perf_cpu_map *cpus = NULL; + unsigned long start_cpu, end_cpu = 0; + char *p = NULL; + int i, nr_cpus = 0; + int *tmp_cpus = NULL, *tmp; + int max_entries = 0; + + if (!cpu_list) + return cpu_map__read_all_cpu_map(); + + /* + * must handle the case of empty cpumap to cover + * TOPOLOGY header for NUMA nodes with no CPU + * ( e.g., because of CPU hotplug) + */ + if (!isdigit(*cpu_list) && *cpu_list != '\0') + goto out; + + while (isdigit(*cpu_list)) { + p = NULL; + start_cpu = strtoul(cpu_list, &p, 0); + if (start_cpu >= INT_MAX + || (*p != '\0' && *p != ',' && *p != '-')) + goto invalid; + + if (*p == '-') { + cpu_list = ++p; + p = NULL; + end_cpu = strtoul(cpu_list, &p, 0); + + if (end_cpu >= INT_MAX || (*p != '\0' && *p != ',')) + goto invalid; + + if (end_cpu < start_cpu) + goto invalid; + } else { + end_cpu = start_cpu; + } + + WARN_ONCE(end_cpu >= MAX_NR_CPUS, "Perf can support %d CPUs. " + "Consider raising MAX_NR_CPUS\n", MAX_NR_CPUS); + + for (; start_cpu <= end_cpu; start_cpu++) { + /* check for duplicates */ + for (i = 0; i < nr_cpus; i++) + if (tmp_cpus[i] == (int)start_cpu) + goto invalid; + + if (nr_cpus == max_entries) { + max_entries += MAX_NR_CPUS; + tmp = realloc(tmp_cpus, max_entries * sizeof(int)); + if (tmp == NULL) + goto invalid; + tmp_cpus = tmp; + } + tmp_cpus[nr_cpus++] = (int)start_cpu; + } + if (*p) + ++p; + + cpu_list = p; + } + + if (nr_cpus > 0) + cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); + else if (*cpu_list != '\0') + cpus = cpu_map__default_new(); + else + cpus = perf_cpu_map__dummy_new(); +invalid: + free(tmp_cpus); +out: + return cpus; +} + +int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx) +{ + if (idx < cpus->nr) + return cpus->map[idx]; + + return -1; +} + +int perf_cpu_map__nr(const struct perf_cpu_map *cpus) +{ + return cpus ? cpus->nr : 1; +} + +bool perf_cpu_map__empty(const struct perf_cpu_map *map) +{ + return map ? map->map[0] == -1 : true; +} + +int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu) +{ + int i; + + for (i = 0; i < cpus->nr; ++i) { + if (cpus->map[i] == cpu) + return i; + } + + return -1; +} + +int perf_cpu_map__max(struct perf_cpu_map *map) +{ + int i, max = -1; + + for (i = 0; i < map->nr; i++) { + if (map->map[i] > max) + max = map->map[i]; + } + + return max; +} + +/* + * Merge two cpumaps + * + * orig either gets freed and replaced with a new map, or reused + * with no reference count change (similar to "realloc") + * other has its reference count increased. + */ + +struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, + struct perf_cpu_map *other) +{ + int *tmp_cpus; + int tmp_len; + int i, j, k; + struct perf_cpu_map *merged; + + if (!orig && !other) + return NULL; + if (!orig) { + perf_cpu_map__get(other); + return other; + } + if (!other) + return orig; + if (orig->nr == other->nr && + !memcmp(orig->map, other->map, orig->nr * sizeof(int))) + return orig; + + tmp_len = orig->nr + other->nr; + tmp_cpus = malloc(tmp_len * sizeof(int)); + if (!tmp_cpus) + return NULL; + + /* Standard merge algorithm from wikipedia */ + i = j = k = 0; + while (i < orig->nr && j < other->nr) { + if (orig->map[i] <= other->map[j]) { + if (orig->map[i] == other->map[j]) + j++; + tmp_cpus[k++] = orig->map[i++]; + } else + tmp_cpus[k++] = other->map[j++]; + } + + while (i < orig->nr) + tmp_cpus[k++] = orig->map[i++]; + + while (j < other->nr) + tmp_cpus[k++] = other->map[j++]; + assert(k <= tmp_len); + + merged = cpu_map__trim_new(k, tmp_cpus); + free(tmp_cpus); + perf_cpu_map__put(orig); + return merged; +} diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c new file mode 100644 index 000000000000..5b9f2ca50591 --- /dev/null +++ b/tools/lib/perf/evlist.c @@ -0,0 +1,644 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <perf/evlist.h> +#include <perf/evsel.h> +#include <linux/bitops.h> +#include <linux/list.h> +#include <linux/hash.h> +#include <sys/ioctl.h> +#include <internal/evlist.h> +#include <internal/evsel.h> +#include <internal/xyarray.h> +#include <internal/mmap.h> +#include <internal/cpumap.h> +#include <internal/threadmap.h> +#include <internal/xyarray.h> +#include <internal/lib.h> +#include <linux/zalloc.h> +#include <sys/ioctl.h> +#include <stdlib.h> +#include <errno.h> +#include <unistd.h> +#include <fcntl.h> +#include <signal.h> +#include <poll.h> +#include <sys/mman.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <api/fd/array.h> + +void perf_evlist__init(struct perf_evlist *evlist) +{ + int i; + + for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i) + INIT_HLIST_HEAD(&evlist->heads[i]); + INIT_LIST_HEAD(&evlist->entries); + evlist->nr_entries = 0; + fdarray__init(&evlist->pollfd, 64); +} + +static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + /* + * We already have cpus for evsel (via PMU sysfs) so + * keep it, if there's no target cpu list defined. + */ + if (!evsel->own_cpus || evlist->has_user_cpus) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evlist->cpus); + } else if (evsel->cpus != evsel->own_cpus) { + perf_cpu_map__put(evsel->cpus); + evsel->cpus = perf_cpu_map__get(evsel->own_cpus); + } + + perf_thread_map__put(evsel->threads); + evsel->threads = perf_thread_map__get(evlist->threads); + evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus); +} + +static void perf_evlist__propagate_maps(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + perf_evlist__for_each_evsel(evlist, evsel) + __perf_evlist__propagate_maps(evlist, evsel); +} + +void perf_evlist__add(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + list_add_tail(&evsel->node, &evlist->entries); + evlist->nr_entries += 1; + __perf_evlist__propagate_maps(evlist, evsel); +} + +void perf_evlist__remove(struct perf_evlist *evlist, + struct perf_evsel *evsel) +{ + list_del_init(&evsel->node); + evlist->nr_entries -= 1; +} + +struct perf_evlist *perf_evlist__new(void) +{ + struct perf_evlist *evlist = zalloc(sizeof(*evlist)); + + if (evlist != NULL) + perf_evlist__init(evlist); + + return evlist; +} + +struct perf_evsel * +perf_evlist__next(struct perf_evlist *evlist, struct perf_evsel *prev) +{ + struct perf_evsel *next; + + if (!prev) { + next = list_first_entry(&evlist->entries, + struct perf_evsel, + node); + } else { + next = list_next_entry(prev, node); + } + + /* Empty list is noticed here so don't need checking on entry. */ + if (&next->node == &evlist->entries) + return NULL; + + return next; +} + +static void perf_evlist__purge(struct perf_evlist *evlist) +{ + struct perf_evsel *pos, *n; + + perf_evlist__for_each_entry_safe(evlist, n, pos) { + list_del_init(&pos->node); + perf_evsel__delete(pos); + } + + evlist->nr_entries = 0; +} + +void perf_evlist__exit(struct perf_evlist *evlist) +{ + perf_cpu_map__put(evlist->cpus); + perf_thread_map__put(evlist->threads); + evlist->cpus = NULL; + evlist->threads = NULL; + fdarray__exit(&evlist->pollfd); +} + +void perf_evlist__delete(struct perf_evlist *evlist) +{ + if (evlist == NULL) + return; + + perf_evlist__munmap(evlist); + perf_evlist__close(evlist); + perf_evlist__purge(evlist); + perf_evlist__exit(evlist); + free(evlist); +} + +void perf_evlist__set_maps(struct perf_evlist *evlist, + struct perf_cpu_map *cpus, + struct perf_thread_map *threads) +{ + /* + * Allow for the possibility that one or another of the maps isn't being + * changed i.e. don't put it. Note we are assuming the maps that are + * being applied are brand new and evlist is taking ownership of the + * original reference count of 1. If that is not the case it is up to + * the caller to increase the reference count. + */ + if (cpus != evlist->cpus) { + perf_cpu_map__put(evlist->cpus); + evlist->cpus = perf_cpu_map__get(cpus); + } + + if (threads != evlist->threads) { + perf_thread_map__put(evlist->threads); + evlist->threads = perf_thread_map__get(threads); + } + + if (!evlist->all_cpus && cpus) + evlist->all_cpus = perf_cpu_map__get(cpus); + + perf_evlist__propagate_maps(evlist); +} + +int perf_evlist__open(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + int err; + + perf_evlist__for_each_entry(evlist, evsel) { + err = perf_evsel__open(evsel, evsel->cpus, evsel->threads); + if (err < 0) + goto out_err; + } + + return 0; + +out_err: + perf_evlist__close(evlist); + return err; +} + +void perf_evlist__close(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + perf_evlist__for_each_entry_reverse(evlist, evsel) + perf_evsel__close(evsel); +} + +void perf_evlist__enable(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + perf_evlist__for_each_entry(evlist, evsel) + perf_evsel__enable(evsel); +} + +void perf_evlist__disable(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + perf_evlist__for_each_entry(evlist, evsel) + perf_evsel__disable(evsel); +} + +u64 perf_evlist__read_format(struct perf_evlist *evlist) +{ + struct perf_evsel *first = perf_evlist__first(evlist); + + return first->attr.read_format; +} + +#define SID(e, x, y) xyarray__entry(e->sample_id, x, y) + +static void perf_evlist__id_hash(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, u64 id) +{ + int hash; + struct perf_sample_id *sid = SID(evsel, cpu, thread); + + sid->id = id; + sid->evsel = evsel; + hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS); + hlist_add_head(&sid->node, &evlist->heads[hash]); +} + +void perf_evlist__id_add(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, u64 id) +{ + perf_evlist__id_hash(evlist, evsel, cpu, thread, id); + evsel->id[evsel->ids++] = id; +} + +int perf_evlist__id_add_fd(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, int fd) +{ + u64 read_data[4] = { 0, }; + int id_idx = 1; /* The first entry is the counter value */ + u64 id; + int ret; + + ret = ioctl(fd, PERF_EVENT_IOC_ID, &id); + if (!ret) + goto add; + + if (errno != ENOTTY) + return -1; + + /* Legacy way to get event id.. All hail to old kernels! */ + + /* + * This way does not work with group format read, so bail + * out in that case. + */ + if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP) + return -1; + + if (!(evsel->attr.read_format & PERF_FORMAT_ID) || + read(fd, &read_data, sizeof(read_data)) == -1) + return -1; + + if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + ++id_idx; + if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + ++id_idx; + + id = read_data[id_idx]; + +add: + perf_evlist__id_add(evlist, evsel, cpu, thread, id); + return 0; +} + +int perf_evlist__alloc_pollfd(struct perf_evlist *evlist) +{ + int nr_cpus = perf_cpu_map__nr(evlist->cpus); + int nr_threads = perf_thread_map__nr(evlist->threads); + int nfds = 0; + struct perf_evsel *evsel; + + perf_evlist__for_each_entry(evlist, evsel) { + if (evsel->system_wide) + nfds += nr_cpus; + else + nfds += nr_cpus * nr_threads; + } + + if (fdarray__available_entries(&evlist->pollfd) < nfds && + fdarray__grow(&evlist->pollfd, nfds) < 0) + return -ENOMEM; + + return 0; +} + +int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, + void *ptr, short revent) +{ + int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP); + + if (pos >= 0) { + evlist->pollfd.priv[pos].ptr = ptr; + fcntl(fd, F_SETFL, O_NONBLOCK); + } + + return pos; +} + +static void perf_evlist__munmap_filtered(struct fdarray *fda, int fd, + void *arg __maybe_unused) +{ + struct perf_mmap *map = fda->priv[fd].ptr; + + if (map) + perf_mmap__put(map); +} + +int perf_evlist__filter_pollfd(struct perf_evlist *evlist, short revents_and_mask) +{ + return fdarray__filter(&evlist->pollfd, revents_and_mask, + perf_evlist__munmap_filtered, NULL); +} + +int perf_evlist__poll(struct perf_evlist *evlist, int timeout) +{ + return fdarray__poll(&evlist->pollfd, timeout); +} + +static struct perf_mmap* perf_evlist__alloc_mmap(struct perf_evlist *evlist, bool overwrite) +{ + int i; + struct perf_mmap *map; + + map = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap)); + if (!map) + return NULL; + + for (i = 0; i < evlist->nr_mmaps; i++) { + struct perf_mmap *prev = i ? &map[i - 1] : NULL; + + /* + * When the perf_mmap() call is made we grab one refcount, plus + * one extra to let perf_mmap__consume() get the last + * events after all real references (perf_mmap__get()) are + * dropped. + * + * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and + * thus does perf_mmap__get() on it. + */ + perf_mmap__init(&map[i], prev, overwrite, NULL); + } + + return map; +} + +static void perf_evlist__set_sid_idx(struct perf_evlist *evlist, + struct perf_evsel *evsel, int idx, int cpu, + int thread) +{ + struct perf_sample_id *sid = SID(evsel, cpu, thread); + + sid->idx = idx; + if (evlist->cpus && cpu >= 0) + sid->cpu = evlist->cpus->map[cpu]; + else + sid->cpu = -1; + if (!evsel->system_wide && evlist->threads && thread >= 0) + sid->tid = perf_thread_map__pid(evlist->threads, thread); + else + sid->tid = -1; +} + +static struct perf_mmap* +perf_evlist__mmap_cb_get(struct perf_evlist *evlist, bool overwrite, int idx) +{ + struct perf_mmap *maps; + + maps = overwrite ? evlist->mmap_ovw : evlist->mmap; + + if (!maps) { + maps = perf_evlist__alloc_mmap(evlist, overwrite); + if (!maps) + return NULL; + + if (overwrite) + evlist->mmap_ovw = maps; + else + evlist->mmap = maps; + } + + return &maps[idx]; +} + +#define FD(e, x, y) (*(int *) xyarray__entry(e->fd, x, y)) + +static int +perf_evlist__mmap_cb_mmap(struct perf_mmap *map, struct perf_mmap_param *mp, + int output, int cpu) +{ + return perf_mmap__mmap(map, mp, output, cpu); +} + +static void perf_evlist__set_mmap_first(struct perf_evlist *evlist, struct perf_mmap *map, + bool overwrite) +{ + if (overwrite) + evlist->mmap_ovw_first = map; + else + evlist->mmap_first = map; +} + +static int +mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, + int idx, struct perf_mmap_param *mp, int cpu_idx, + int thread, int *_output, int *_output_overwrite) +{ + int evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx); + struct perf_evsel *evsel; + int revent; + + perf_evlist__for_each_entry(evlist, evsel) { + bool overwrite = evsel->attr.write_backward; + struct perf_mmap *map; + int *output, fd, cpu; + + if (evsel->system_wide && thread) + continue; + + cpu = perf_cpu_map__idx(evsel->cpus, evlist_cpu); + if (cpu == -1) + continue; + + map = ops->get(evlist, overwrite, idx); + if (map == NULL) + return -ENOMEM; + + if (overwrite) { + mp->prot = PROT_READ; + output = _output_overwrite; + } else { + mp->prot = PROT_READ | PROT_WRITE; + output = _output; + } + + fd = FD(evsel, cpu, thread); + + if (*output == -1) { + *output = fd; + + /* + * The last one will be done at perf_mmap__consume(), so that we + * make sure we don't prevent tools from consuming every last event in + * the ring buffer. + * + * I.e. we can get the POLLHUP meaning that the fd doesn't exist + * anymore, but the last events for it are still in the ring buffer, + * waiting to be consumed. + * + * Tools can chose to ignore this at their own discretion, but the + * evlist layer can't just drop it when filtering events in + * perf_evlist__filter_pollfd(). + */ + refcount_set(&map->refcnt, 2); + + if (ops->mmap(map, mp, *output, evlist_cpu) < 0) + return -1; + + if (!idx) + perf_evlist__set_mmap_first(evlist, map, overwrite); + } else { + if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0) + return -1; + + perf_mmap__get(map); + } + + revent = !overwrite ? POLLIN : 0; + + if (!evsel->system_wide && + perf_evlist__add_pollfd(evlist, fd, map, revent) < 0) { + perf_mmap__put(map); + return -1; + } + + if (evsel->attr.read_format & PERF_FORMAT_ID) { + if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread, + fd) < 0) + return -1; + perf_evlist__set_sid_idx(evlist, evsel, idx, cpu, + thread); + } + } + + return 0; +} + +static int +mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, + struct perf_mmap_param *mp) +{ + int thread; + int nr_threads = perf_thread_map__nr(evlist->threads); + + for (thread = 0; thread < nr_threads; thread++) { + int output = -1; + int output_overwrite = -1; + + if (ops->idx) + ops->idx(evlist, mp, thread, false); + + if (mmap_per_evsel(evlist, ops, thread, mp, 0, thread, + &output, &output_overwrite)) + goto out_unmap; + } + + return 0; + +out_unmap: + perf_evlist__munmap(evlist); + return -1; +} + +static int +mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops, + struct perf_mmap_param *mp) +{ + int nr_threads = perf_thread_map__nr(evlist->threads); + int nr_cpus = perf_cpu_map__nr(evlist->cpus); + int cpu, thread; + + for (cpu = 0; cpu < nr_cpus; cpu++) { + int output = -1; + int output_overwrite = -1; + + if (ops->idx) + ops->idx(evlist, mp, cpu, true); + + for (thread = 0; thread < nr_threads; thread++) { + if (mmap_per_evsel(evlist, ops, cpu, mp, cpu, + thread, &output, &output_overwrite)) + goto out_unmap; + } + } + + return 0; + +out_unmap: + perf_evlist__munmap(evlist); + return -1; +} + +static int perf_evlist__nr_mmaps(struct perf_evlist *evlist) +{ + int nr_mmaps; + + nr_mmaps = perf_cpu_map__nr(evlist->cpus); + if (perf_cpu_map__empty(evlist->cpus)) + nr_mmaps = perf_thread_map__nr(evlist->threads); + + return nr_mmaps; +} + +int perf_evlist__mmap_ops(struct perf_evlist *evlist, + struct perf_evlist_mmap_ops *ops, + struct perf_mmap_param *mp) +{ + struct perf_evsel *evsel; + const struct perf_cpu_map *cpus = evlist->cpus; + const struct perf_thread_map *threads = evlist->threads; + + if (!ops || !ops->get || !ops->mmap) + return -EINVAL; + + mp->mask = evlist->mmap_len - page_size - 1; + + evlist->nr_mmaps = perf_evlist__nr_mmaps(evlist); + + perf_evlist__for_each_entry(evlist, evsel) { + if ((evsel->attr.read_format & PERF_FORMAT_ID) && + evsel->sample_id == NULL && + perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0) + return -ENOMEM; + } + + if (evlist->pollfd.entries == NULL && perf_evlist__alloc_pollfd(evlist) < 0) + return -ENOMEM; + + if (perf_cpu_map__empty(cpus)) + return mmap_per_thread(evlist, ops, mp); + + return mmap_per_cpu(evlist, ops, mp); +} + +int perf_evlist__mmap(struct perf_evlist *evlist, int pages) +{ + struct perf_mmap_param mp; + struct perf_evlist_mmap_ops ops = { + .get = perf_evlist__mmap_cb_get, + .mmap = perf_evlist__mmap_cb_mmap, + }; + + evlist->mmap_len = (pages + 1) * page_size; + + return perf_evlist__mmap_ops(evlist, &ops, &mp); +} + +void perf_evlist__munmap(struct perf_evlist *evlist) +{ + int i; + + if (evlist->mmap) { + for (i = 0; i < evlist->nr_mmaps; i++) + perf_mmap__munmap(&evlist->mmap[i]); + } + + if (evlist->mmap_ovw) { + for (i = 0; i < evlist->nr_mmaps; i++) + perf_mmap__munmap(&evlist->mmap_ovw[i]); + } + + zfree(&evlist->mmap); + zfree(&evlist->mmap_ovw); +} + +struct perf_mmap* +perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map, + bool overwrite) +{ + if (map) + return map->next; + + return overwrite ? evlist->mmap_ovw_first : evlist->mmap_first; +} diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c new file mode 100644 index 000000000000..4dc06289f4c7 --- /dev/null +++ b/tools/lib/perf/evsel.c @@ -0,0 +1,301 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <unistd.h> +#include <sys/syscall.h> +#include <perf/evsel.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <linux/list.h> +#include <internal/evsel.h> +#include <linux/zalloc.h> +#include <stdlib.h> +#include <internal/xyarray.h> +#include <internal/cpumap.h> +#include <internal/threadmap.h> +#include <internal/lib.h> +#include <linux/string.h> +#include <sys/ioctl.h> + +void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr) +{ + INIT_LIST_HEAD(&evsel->node); + evsel->attr = *attr; +} + +struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr) +{ + struct perf_evsel *evsel = zalloc(sizeof(*evsel)); + + if (evsel != NULL) + perf_evsel__init(evsel, attr); + + return evsel; +} + +void perf_evsel__delete(struct perf_evsel *evsel) +{ + free(evsel); +} + +#define FD(e, x, y) (*(int *) xyarray__entry(e->fd, x, y)) + +int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int)); + + if (evsel->fd) { + int cpu, thread; + for (cpu = 0; cpu < ncpus; cpu++) { + for (thread = 0; thread < nthreads; thread++) { + FD(evsel, cpu, thread) = -1; + } + } + } + + return evsel->fd != NULL ? 0 : -ENOMEM; +} + +static int +sys_perf_event_open(struct perf_event_attr *attr, + pid_t pid, int cpu, int group_fd, + unsigned long flags) +{ + return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags); +} + +int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads) +{ + int cpu, thread, err = 0; + + if (cpus == NULL) { + static struct perf_cpu_map *empty_cpu_map; + + if (empty_cpu_map == NULL) { + empty_cpu_map = perf_cpu_map__dummy_new(); + if (empty_cpu_map == NULL) + return -ENOMEM; + } + + cpus = empty_cpu_map; + } + + if (threads == NULL) { + static struct perf_thread_map *empty_thread_map; + + if (empty_thread_map == NULL) { + empty_thread_map = perf_thread_map__new_dummy(); + if (empty_thread_map == NULL) + return -ENOMEM; + } + + threads = empty_thread_map; + } + + if (evsel->fd == NULL && + perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0) + return -ENOMEM; + + for (cpu = 0; cpu < cpus->nr; cpu++) { + for (thread = 0; thread < threads->nr; thread++) { + int fd; + + fd = sys_perf_event_open(&evsel->attr, + threads->map[thread].pid, + cpus->map[cpu], -1, 0); + + if (fd < 0) + return -errno; + + FD(evsel, cpu, thread) = fd; + } + } + + return err; +} + +static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu) +{ + int thread; + + for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) { + if (FD(evsel, cpu, thread) >= 0) + close(FD(evsel, cpu, thread)); + FD(evsel, cpu, thread) = -1; + } +} + +void perf_evsel__close_fd(struct perf_evsel *evsel) +{ + int cpu; + + for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) + perf_evsel__close_fd_cpu(evsel, cpu); +} + +void perf_evsel__free_fd(struct perf_evsel *evsel) +{ + xyarray__delete(evsel->fd); + evsel->fd = NULL; +} + +void perf_evsel__close(struct perf_evsel *evsel) +{ + if (evsel->fd == NULL) + return; + + perf_evsel__close_fd(evsel); + perf_evsel__free_fd(evsel); +} + +void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu) +{ + if (evsel->fd == NULL) + return; + + perf_evsel__close_fd_cpu(evsel, cpu); +} + +int perf_evsel__read_size(struct perf_evsel *evsel) +{ + u64 read_format = evsel->attr.read_format; + int entry = sizeof(u64); /* value */ + int size = 0; + int nr = 1; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + size += sizeof(u64); + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + size += sizeof(u64); + + if (read_format & PERF_FORMAT_ID) + entry += sizeof(u64); + + if (read_format & PERF_FORMAT_GROUP) { + nr = evsel->nr_members; + size += sizeof(u64); + } + + size += entry * nr; + return size; +} + +int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count) +{ + size_t size = perf_evsel__read_size(evsel); + + memset(count, 0, sizeof(*count)); + + if (FD(evsel, cpu, thread) < 0) + return -EINVAL; + + if (readn(FD(evsel, cpu, thread), count->values, size) <= 0) + return -errno; + + return 0; +} + +static int perf_evsel__run_ioctl(struct perf_evsel *evsel, + int ioc, void *arg, + int cpu) +{ + int thread; + + for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) { + int fd = FD(evsel, cpu, thread), + err = ioctl(fd, ioc, arg); + + if (err) + return err; + } + + return 0; +} + +int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu) +{ + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu); +} + +int perf_evsel__enable(struct perf_evsel *evsel) +{ + int i; + int err = 0; + + for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++) + err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, i); + return err; +} + +int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu) +{ + return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu); +} + +int perf_evsel__disable(struct perf_evsel *evsel) +{ + int i; + int err = 0; + + for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++) + err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, i); + return err; +} + +int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter) +{ + int err = 0, i; + + for (i = 0; i < evsel->cpus->nr && !err; i++) + err = perf_evsel__run_ioctl(evsel, + PERF_EVENT_IOC_SET_FILTER, + (void *)filter, i); + return err; +} + +struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) +{ + return evsel->cpus; +} + +struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel) +{ + return evsel->threads; +} + +struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel) +{ + return &evsel->attr; +} + +int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + if (ncpus == 0 || nthreads == 0) + return 0; + + if (evsel->system_wide) + nthreads = 1; + + evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id)); + if (evsel->sample_id == NULL) + return -ENOMEM; + + evsel->id = zalloc(ncpus * nthreads * sizeof(u64)); + if (evsel->id == NULL) { + xyarray__delete(evsel->sample_id); + evsel->sample_id = NULL; + return -ENOMEM; + } + + return 0; +} + +void perf_evsel__free_id(struct perf_evsel *evsel) +{ + xyarray__delete(evsel->sample_id); + evsel->sample_id = NULL; + zfree(&evsel->id); + evsel->ids = 0; +} diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h new file mode 100644 index 000000000000..840d4032587b --- /dev/null +++ b/tools/lib/perf/include/internal/cpumap.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_CPUMAP_H +#define __LIBPERF_INTERNAL_CPUMAP_H + +#include <linux/refcount.h> + +struct perf_cpu_map { + refcount_t refcnt; + int nr; + int map[]; +}; + +#ifndef MAX_NR_CPUS +#define MAX_NR_CPUS 2048 +#endif + +int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu); + +#endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h new file mode 100644 index 000000000000..74dc8c3f0b66 --- /dev/null +++ b/tools/lib/perf/include/internal/evlist.h @@ -0,0 +1,127 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_EVLIST_H +#define __LIBPERF_INTERNAL_EVLIST_H + +#include <linux/list.h> +#include <api/fd/array.h> +#include <internal/evsel.h> + +#define PERF_EVLIST__HLIST_BITS 8 +#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS) + +struct perf_cpu_map; +struct perf_thread_map; +struct perf_mmap_param; + +struct perf_evlist { + struct list_head entries; + int nr_entries; + bool has_user_cpus; + struct perf_cpu_map *cpus; + struct perf_cpu_map *all_cpus; + struct perf_thread_map *threads; + int nr_mmaps; + size_t mmap_len; + struct fdarray pollfd; + struct hlist_head heads[PERF_EVLIST__HLIST_SIZE]; + struct perf_mmap *mmap; + struct perf_mmap *mmap_ovw; + struct perf_mmap *mmap_first; + struct perf_mmap *mmap_ovw_first; +}; + +typedef void +(*perf_evlist_mmap__cb_idx_t)(struct perf_evlist*, struct perf_mmap_param*, int, bool); +typedef struct perf_mmap* +(*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int); +typedef int +(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, int); + +struct perf_evlist_mmap_ops { + perf_evlist_mmap__cb_idx_t idx; + perf_evlist_mmap__cb_get_t get; + perf_evlist_mmap__cb_mmap_t mmap; +}; + +int perf_evlist__alloc_pollfd(struct perf_evlist *evlist); +int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd, + void *ptr, short revent); + +int perf_evlist__mmap_ops(struct perf_evlist *evlist, + struct perf_evlist_mmap_ops *ops, + struct perf_mmap_param *mp); + +void perf_evlist__init(struct perf_evlist *evlist); +void perf_evlist__exit(struct perf_evlist *evlist); + +/** + * __perf_evlist__for_each_entry - iterate thru all the evsels + * @list: list_head instance to iterate + * @evsel: struct perf_evsel iterator + */ +#define __perf_evlist__for_each_entry(list, evsel) \ + list_for_each_entry(evsel, list, node) + +/** + * evlist__for_each_entry - iterate thru all the evsels + * @evlist: perf_evlist instance to iterate + * @evsel: struct perf_evsel iterator + */ +#define perf_evlist__for_each_entry(evlist, evsel) \ + __perf_evlist__for_each_entry(&(evlist)->entries, evsel) + +/** + * __perf_evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order + * @list: list_head instance to iterate + * @evsel: struct evsel iterator + */ +#define __perf_evlist__for_each_entry_reverse(list, evsel) \ + list_for_each_entry_reverse(evsel, list, node) + +/** + * perf_evlist__for_each_entry_reverse - iterate thru all the evsels in reverse order + * @evlist: evlist instance to iterate + * @evsel: struct evsel iterator + */ +#define perf_evlist__for_each_entry_reverse(evlist, evsel) \ + __perf_evlist__for_each_entry_reverse(&(evlist)->entries, evsel) + +/** + * __perf_evlist__for_each_entry_safe - safely iterate thru all the evsels + * @list: list_head instance to iterate + * @tmp: struct evsel temp iterator + * @evsel: struct evsel iterator + */ +#define __perf_evlist__for_each_entry_safe(list, tmp, evsel) \ + list_for_each_entry_safe(evsel, tmp, list, node) + +/** + * perf_evlist__for_each_entry_safe - safely iterate thru all the evsels + * @evlist: evlist instance to iterate + * @evsel: struct evsel iterator + * @tmp: struct evsel temp iterator + */ +#define perf_evlist__for_each_entry_safe(evlist, tmp, evsel) \ + __perf_evlist__for_each_entry_safe(&(evlist)->entries, tmp, evsel) + +static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist) +{ + return list_entry(evlist->entries.next, struct perf_evsel, node); +} + +static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist) +{ + return list_entry(evlist->entries.prev, struct perf_evsel, node); +} + +u64 perf_evlist__read_format(struct perf_evlist *evlist); + +void perf_evlist__id_add(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, u64 id); + +int perf_evlist__id_add_fd(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, int fd); + +#endif /* __LIBPERF_INTERNAL_EVLIST_H */ diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h new file mode 100644 index 000000000000..1ffd083b235e --- /dev/null +++ b/tools/lib/perf/include/internal/evsel.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_EVSEL_H +#define __LIBPERF_INTERNAL_EVSEL_H + +#include <linux/types.h> +#include <linux/perf_event.h> +#include <stdbool.h> +#include <sys/types.h> + +struct perf_cpu_map; +struct perf_thread_map; +struct xyarray; + +/* + * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are + * more than one entry in the evlist. + */ +struct perf_sample_id { + struct hlist_node node; + u64 id; + struct perf_evsel *evsel; + /* + * 'idx' will be used for AUX area sampling. A sample will have AUX area + * data that will be queued for decoding, where there are separate + * queues for each CPU (per-cpu tracing) or task (per-thread tracing). + * The sample ID can be used to lookup 'idx' which is effectively the + * queue number. + */ + int idx; + int cpu; + pid_t tid; + + /* Holds total ID period value for PERF_SAMPLE_READ processing. */ + u64 period; +}; + +struct perf_evsel { + struct list_head node; + struct perf_event_attr attr; + struct perf_cpu_map *cpus; + struct perf_cpu_map *own_cpus; + struct perf_thread_map *threads; + struct xyarray *fd; + struct xyarray *sample_id; + u64 *id; + u32 ids; + + /* parse modifier helper */ + int nr_members; + bool system_wide; +}; + +void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr); +int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads); +void perf_evsel__close_fd(struct perf_evsel *evsel); +void perf_evsel__free_fd(struct perf_evsel *evsel); +int perf_evsel__read_size(struct perf_evsel *evsel); +int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter); + +int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads); +void perf_evsel__free_id(struct perf_evsel *evsel); + +#endif /* __LIBPERF_INTERNAL_EVSEL_H */ diff --git a/tools/lib/perf/include/internal/lib.h b/tools/lib/perf/include/internal/lib.h new file mode 100644 index 000000000000..5175d491b2d4 --- /dev/null +++ b/tools/lib/perf/include/internal/lib.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_LIB_H +#define __LIBPERF_INTERNAL_LIB_H + +#include <sys/types.h> + +extern unsigned int page_size; + +ssize_t readn(int fd, void *buf, size_t n); +ssize_t writen(int fd, const void *buf, size_t n); + +#endif /* __LIBPERF_INTERNAL_CPUMAP_H */ diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h new file mode 100644 index 000000000000..be7556e0a2b2 --- /dev/null +++ b/tools/lib/perf/include/internal/mmap.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_MMAP_H +#define __LIBPERF_INTERNAL_MMAP_H + +#include <linux/compiler.h> +#include <linux/refcount.h> +#include <linux/types.h> +#include <stdbool.h> + +/* perf sample has 16 bits size limit */ +#define PERF_SAMPLE_MAX_SIZE (1 << 16) + +struct perf_mmap; + +typedef void (*libperf_unmap_cb_t)(struct perf_mmap *map); + +/** + * struct perf_mmap - perf's ring buffer mmap details + * + * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this + */ +struct perf_mmap { + void *base; + int mask; + int fd; + int cpu; + refcount_t refcnt; + u64 prev; + u64 start; + u64 end; + bool overwrite; + u64 flush; + libperf_unmap_cb_t unmap_cb; + char event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8); + struct perf_mmap *next; +}; + +struct perf_mmap_param { + int prot; + int mask; +}; + +size_t perf_mmap__mmap_len(struct perf_mmap *map); + +void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev, + bool overwrite, libperf_unmap_cb_t unmap_cb); +int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp, + int fd, int cpu); +void perf_mmap__munmap(struct perf_mmap *map); +void perf_mmap__get(struct perf_mmap *map); +void perf_mmap__put(struct perf_mmap *map); + +u64 perf_mmap__read_head(struct perf_mmap *map); + +#endif /* __LIBPERF_INTERNAL_MMAP_H */ diff --git a/tools/lib/perf/include/internal/tests.h b/tools/lib/perf/include/internal/tests.h new file mode 100644 index 000000000000..2093e8868a67 --- /dev/null +++ b/tools/lib/perf/include/internal/tests.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_TESTS_H +#define __LIBPERF_INTERNAL_TESTS_H + +#include <stdio.h> + +int tests_failed; + +#define __T_START \ +do { \ + fprintf(stdout, "- running %s...", __FILE__); \ + fflush(NULL); \ + tests_failed = 0; \ +} while (0) + +#define __T_END \ +do { \ + if (tests_failed) \ + fprintf(stdout, " FAILED (%d)\n", tests_failed); \ + else \ + fprintf(stdout, "OK\n"); \ +} while (0) + +#define __T(text, cond) \ +do { \ + if (!(cond)) { \ + fprintf(stderr, "FAILED %s:%d %s\n", __FILE__, __LINE__, text); \ + tests_failed++; \ + return -1; \ + } \ +} while (0) + +#endif /* __LIBPERF_INTERNAL_TESTS_H */ diff --git a/tools/lib/perf/include/internal/threadmap.h b/tools/lib/perf/include/internal/threadmap.h new file mode 100644 index 000000000000..df748baf9eda --- /dev/null +++ b/tools/lib/perf/include/internal/threadmap.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_THREADMAP_H +#define __LIBPERF_INTERNAL_THREADMAP_H + +#include <linux/refcount.h> +#include <sys/types.h> +#include <unistd.h> + +struct thread_map_data { + pid_t pid; + char *comm; +}; + +struct perf_thread_map { + refcount_t refcnt; + int nr; + int err_thread; + struct thread_map_data map[]; +}; + +struct perf_thread_map *perf_thread_map__realloc(struct perf_thread_map *map, int nr); + +#endif /* __LIBPERF_INTERNAL_THREADMAP_H */ diff --git a/tools/lib/perf/include/internal/xyarray.h b/tools/lib/perf/include/internal/xyarray.h new file mode 100644 index 000000000000..51e35d6c8ec4 --- /dev/null +++ b/tools/lib/perf/include/internal/xyarray.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_XYARRAY_H +#define __LIBPERF_INTERNAL_XYARRAY_H + +#include <linux/compiler.h> +#include <sys/types.h> + +struct xyarray { + size_t row_size; + size_t entry_size; + size_t entries; + size_t max_x; + size_t max_y; + char contents[] __aligned(8); +}; + +struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size); +void xyarray__delete(struct xyarray *xy); +void xyarray__reset(struct xyarray *xy); + +static inline void *xyarray__entry(struct xyarray *xy, int x, int y) +{ + return &xy->contents[x * xy->row_size + y * xy->entry_size]; +} + +static inline int xyarray__max_y(struct xyarray *xy) +{ + return xy->max_y; +} + +static inline int xyarray__max_x(struct xyarray *xy) +{ + return xy->max_x; +} + +#endif /* __LIBPERF_INTERNAL_XYARRAY_H */ diff --git a/tools/lib/perf/include/perf/core.h b/tools/lib/perf/include/perf/core.h new file mode 100644 index 000000000000..a3f6d68edad7 --- /dev/null +++ b/tools/lib/perf/include/perf/core.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_CORE_H +#define __LIBPERF_CORE_H + +#include <stdarg.h> + +#ifndef LIBPERF_API +#define LIBPERF_API __attribute__((visibility("default"))) +#endif + +enum libperf_print_level { + LIBPERF_ERR, + LIBPERF_WARN, + LIBPERF_INFO, + LIBPERF_DEBUG, + LIBPERF_DEBUG2, + LIBPERF_DEBUG3, +}; + +typedef int (*libperf_print_fn_t)(enum libperf_print_level level, + const char *, va_list ap); + +LIBPERF_API void libperf_init(libperf_print_fn_t fn); + +#endif /* __LIBPERF_CORE_H */ diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h new file mode 100644 index 000000000000..6a17ad730cbc --- /dev/null +++ b/tools/lib/perf/include/perf/cpumap.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_CPUMAP_H +#define __LIBPERF_CPUMAP_H + +#include <perf/core.h> +#include <stdio.h> +#include <stdbool.h> + +struct perf_cpu_map; + +LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map); +LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig, + struct perf_cpu_map *other); +LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map); +LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx); +LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus); +LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map); +LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map); + +#define perf_cpu_map__for_each_cpu(cpu, idx, cpus) \ + for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx); \ + (idx) < perf_cpu_map__nr(cpus); \ + (idx)++, (cpu) = perf_cpu_map__cpu(cpus, idx)) + +#endif /* __LIBPERF_CPUMAP_H */ diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h new file mode 100644 index 000000000000..18106899cb4e --- /dev/null +++ b/tools/lib/perf/include/perf/event.h @@ -0,0 +1,385 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_EVENT_H +#define __LIBPERF_EVENT_H + +#include <linux/perf_event.h> +#include <linux/types.h> +#include <linux/limits.h> +#include <linux/bpf.h> +#include <sys/types.h> /* pid_t */ + +struct perf_record_mmap { + struct perf_event_header header; + __u32 pid, tid; + __u64 start; + __u64 len; + __u64 pgoff; + char filename[PATH_MAX]; +}; + +struct perf_record_mmap2 { + struct perf_event_header header; + __u32 pid, tid; + __u64 start; + __u64 len; + __u64 pgoff; + __u32 maj; + __u32 min; + __u64 ino; + __u64 ino_generation; + __u32 prot; + __u32 flags; + char filename[PATH_MAX]; +}; + +struct perf_record_comm { + struct perf_event_header header; + __u32 pid, tid; + char comm[16]; +}; + +struct perf_record_namespaces { + struct perf_event_header header; + __u32 pid, tid; + __u64 nr_namespaces; + struct perf_ns_link_info link_info[]; +}; + +struct perf_record_fork { + struct perf_event_header header; + __u32 pid, ppid; + __u32 tid, ptid; + __u64 time; +}; + +struct perf_record_lost { + struct perf_event_header header; + __u64 id; + __u64 lost; +}; + +struct perf_record_lost_samples { + struct perf_event_header header; + __u64 lost; +}; + +/* + * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID + */ +struct perf_record_read { + struct perf_event_header header; + __u32 pid, tid; + __u64 value; + __u64 time_enabled; + __u64 time_running; + __u64 id; +}; + +struct perf_record_throttle { + struct perf_event_header header; + __u64 time; + __u64 id; + __u64 stream_id; +}; + +#ifndef KSYM_NAME_LEN +#define KSYM_NAME_LEN 256 +#endif + +struct perf_record_ksymbol { + struct perf_event_header header; + __u64 addr; + __u32 len; + __u16 ksym_type; + __u16 flags; + char name[KSYM_NAME_LEN]; +}; + +struct perf_record_bpf_event { + struct perf_event_header header; + __u16 type; + __u16 flags; + __u32 id; + + /* for bpf_prog types */ + __u8 tag[BPF_TAG_SIZE]; // prog tag +}; + +struct perf_record_sample { + struct perf_event_header header; + __u64 array[]; +}; + +struct perf_record_switch { + struct perf_event_header header; + __u32 next_prev_pid; + __u32 next_prev_tid; +}; + +struct perf_record_header_attr { + struct perf_event_header header; + struct perf_event_attr attr; + __u64 id[]; +}; + +enum { + PERF_CPU_MAP__CPUS = 0, + PERF_CPU_MAP__MASK = 1, +}; + +struct cpu_map_entries { + __u16 nr; + __u16 cpu[]; +}; + +struct perf_record_record_cpu_map { + __u16 nr; + __u16 long_size; + unsigned long mask[]; +}; + +struct perf_record_cpu_map_data { + __u16 type; + char data[]; +}; + +struct perf_record_cpu_map { + struct perf_event_header header; + struct perf_record_cpu_map_data data; +}; + +enum { + PERF_EVENT_UPDATE__UNIT = 0, + PERF_EVENT_UPDATE__SCALE = 1, + PERF_EVENT_UPDATE__NAME = 2, + PERF_EVENT_UPDATE__CPUS = 3, +}; + +struct perf_record_event_update_cpus { + struct perf_record_cpu_map_data cpus; +}; + +struct perf_record_event_update_scale { + double scale; +}; + +struct perf_record_event_update { + struct perf_event_header header; + __u64 type; + __u64 id; + char data[]; +}; + +#define MAX_EVENT_NAME 64 + +struct perf_trace_event_type { + __u64 event_id; + char name[MAX_EVENT_NAME]; +}; + +struct perf_record_header_event_type { + struct perf_event_header header; + struct perf_trace_event_type event_type; +}; + +struct perf_record_header_tracing_data { + struct perf_event_header header; + __u32 size; +}; + +struct perf_record_header_build_id { + struct perf_event_header header; + pid_t pid; + __u8 build_id[24]; + char filename[]; +}; + +struct id_index_entry { + __u64 id; + __u64 idx; + __u64 cpu; + __u64 tid; +}; + +struct perf_record_id_index { + struct perf_event_header header; + __u64 nr; + struct id_index_entry entries[0]; +}; + +struct perf_record_auxtrace_info { + struct perf_event_header header; + __u32 type; + __u32 reserved__; /* For alignment */ + __u64 priv[]; +}; + +struct perf_record_auxtrace { + struct perf_event_header header; + __u64 size; + __u64 offset; + __u64 reference; + __u32 idx; + __u32 tid; + __u32 cpu; + __u32 reserved__; /* For alignment */ +}; + +#define MAX_AUXTRACE_ERROR_MSG 64 + +struct perf_record_auxtrace_error { + struct perf_event_header header; + __u32 type; + __u32 code; + __u32 cpu; + __u32 pid; + __u32 tid; + __u32 fmt; + __u64 ip; + __u64 time; + char msg[MAX_AUXTRACE_ERROR_MSG]; +}; + +struct perf_record_aux { + struct perf_event_header header; + __u64 aux_offset; + __u64 aux_size; + __u64 flags; +}; + +struct perf_record_itrace_start { + struct perf_event_header header; + __u32 pid; + __u32 tid; +}; + +struct perf_record_thread_map_entry { + __u64 pid; + char comm[16]; +}; + +struct perf_record_thread_map { + struct perf_event_header header; + __u64 nr; + struct perf_record_thread_map_entry entries[]; +}; + +enum { + PERF_STAT_CONFIG_TERM__AGGR_MODE = 0, + PERF_STAT_CONFIG_TERM__INTERVAL = 1, + PERF_STAT_CONFIG_TERM__SCALE = 2, + PERF_STAT_CONFIG_TERM__MAX = 3, +}; + +struct perf_record_stat_config_entry { + __u64 tag; + __u64 val; +}; + +struct perf_record_stat_config { + struct perf_event_header header; + __u64 nr; + struct perf_record_stat_config_entry data[]; +}; + +struct perf_record_stat { + struct perf_event_header header; + + __u64 id; + __u32 cpu; + __u32 thread; + + union { + struct { + __u64 val; + __u64 ena; + __u64 run; + }; + __u64 values[3]; + }; +}; + +struct perf_record_stat_round { + struct perf_event_header header; + __u64 type; + __u64 time; +}; + +struct perf_record_time_conv { + struct perf_event_header header; + __u64 time_shift; + __u64 time_mult; + __u64 time_zero; +}; + +struct perf_record_header_feature { + struct perf_event_header header; + __u64 feat_id; + char data[]; +}; + +struct perf_record_compressed { + struct perf_event_header header; + char data[]; +}; + +enum perf_user_event_type { /* above any possible kernel type */ + PERF_RECORD_USER_TYPE_START = 64, + PERF_RECORD_HEADER_ATTR = 64, + PERF_RECORD_HEADER_EVENT_TYPE = 65, /* deprecated */ + PERF_RECORD_HEADER_TRACING_DATA = 66, + PERF_RECORD_HEADER_BUILD_ID = 67, + PERF_RECORD_FINISHED_ROUND = 68, + PERF_RECORD_ID_INDEX = 69, + PERF_RECORD_AUXTRACE_INFO = 70, + PERF_RECORD_AUXTRACE = 71, + PERF_RECORD_AUXTRACE_ERROR = 72, + PERF_RECORD_THREAD_MAP = 73, + PERF_RECORD_CPU_MAP = 74, + PERF_RECORD_STAT_CONFIG = 75, + PERF_RECORD_STAT = 76, + PERF_RECORD_STAT_ROUND = 77, + PERF_RECORD_EVENT_UPDATE = 78, + PERF_RECORD_TIME_CONV = 79, + PERF_RECORD_HEADER_FEATURE = 80, + PERF_RECORD_COMPRESSED = 81, + PERF_RECORD_HEADER_MAX +}; + +union perf_event { + struct perf_event_header header; + struct perf_record_mmap mmap; + struct perf_record_mmap2 mmap2; + struct perf_record_comm comm; + struct perf_record_namespaces namespaces; + struct perf_record_fork fork; + struct perf_record_lost lost; + struct perf_record_lost_samples lost_samples; + struct perf_record_read read; + struct perf_record_throttle throttle; + struct perf_record_sample sample; + struct perf_record_bpf_event bpf; + struct perf_record_ksymbol ksymbol; + struct perf_record_header_attr attr; + struct perf_record_event_update event_update; + struct perf_record_header_event_type event_type; + struct perf_record_header_tracing_data tracing_data; + struct perf_record_header_build_id build_id; + struct perf_record_id_index id_index; + struct perf_record_auxtrace_info auxtrace_info; + struct perf_record_auxtrace auxtrace; + struct perf_record_auxtrace_error auxtrace_error; + struct perf_record_aux aux; + struct perf_record_itrace_start itrace_start; + struct perf_record_switch context_switch; + struct perf_record_thread_map thread_map; + struct perf_record_cpu_map cpu_map; + struct perf_record_stat_config stat_config; + struct perf_record_stat stat; + struct perf_record_stat_round stat_round; + struct perf_record_time_conv time_conv; + struct perf_record_header_feature feat; + struct perf_record_compressed pack; +}; + +#endif /* __LIBPERF_EVENT_H */ diff --git a/tools/lib/perf/include/perf/evlist.h b/tools/lib/perf/include/perf/evlist.h new file mode 100644 index 000000000000..0a7479dc13bf --- /dev/null +++ b/tools/lib/perf/include/perf/evlist.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_EVLIST_H +#define __LIBPERF_EVLIST_H + +#include <perf/core.h> +#include <stdbool.h> + +struct perf_evlist; +struct perf_evsel; +struct perf_cpu_map; +struct perf_thread_map; + +LIBPERF_API void perf_evlist__add(struct perf_evlist *evlist, + struct perf_evsel *evsel); +LIBPERF_API void perf_evlist__remove(struct perf_evlist *evlist, + struct perf_evsel *evsel); +LIBPERF_API struct perf_evlist *perf_evlist__new(void); +LIBPERF_API void perf_evlist__delete(struct perf_evlist *evlist); +LIBPERF_API struct perf_evsel* perf_evlist__next(struct perf_evlist *evlist, + struct perf_evsel *evsel); +LIBPERF_API int perf_evlist__open(struct perf_evlist *evlist); +LIBPERF_API void perf_evlist__close(struct perf_evlist *evlist); +LIBPERF_API void perf_evlist__enable(struct perf_evlist *evlist); +LIBPERF_API void perf_evlist__disable(struct perf_evlist *evlist); + +#define perf_evlist__for_each_evsel(evlist, pos) \ + for ((pos) = perf_evlist__next((evlist), NULL); \ + (pos) != NULL; \ + (pos) = perf_evlist__next((evlist), (pos))) + +LIBPERF_API void perf_evlist__set_maps(struct perf_evlist *evlist, + struct perf_cpu_map *cpus, + struct perf_thread_map *threads); +LIBPERF_API int perf_evlist__poll(struct perf_evlist *evlist, int timeout); +LIBPERF_API int perf_evlist__filter_pollfd(struct perf_evlist *evlist, + short revents_and_mask); + +LIBPERF_API int perf_evlist__mmap(struct perf_evlist *evlist, int pages); +LIBPERF_API void perf_evlist__munmap(struct perf_evlist *evlist); + +LIBPERF_API struct perf_mmap *perf_evlist__next_mmap(struct perf_evlist *evlist, + struct perf_mmap *map, + bool overwrite); +#define perf_evlist__for_each_mmap(evlist, pos, overwrite) \ + for ((pos) = perf_evlist__next_mmap((evlist), NULL, overwrite); \ + (pos) != NULL; \ + (pos) = perf_evlist__next_mmap((evlist), (pos), overwrite)) + +#endif /* __LIBPERF_EVLIST_H */ diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h new file mode 100644 index 000000000000..c82ec39a4ad0 --- /dev/null +++ b/tools/lib/perf/include/perf/evsel.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_EVSEL_H +#define __LIBPERF_EVSEL_H + +#include <stdint.h> +#include <perf/core.h> + +struct perf_evsel; +struct perf_event_attr; +struct perf_cpu_map; +struct perf_thread_map; + +struct perf_counts_values { + union { + struct { + uint64_t val; + uint64_t ena; + uint64_t run; + }; + uint64_t values[3]; + }; +}; + +LIBPERF_API struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr); +LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus, + struct perf_thread_map *threads); +LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel); +LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu); +LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count); +LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu); +LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel); +LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu); +LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel); +LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel); +LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel); + +#endif /* __LIBPERF_EVSEL_H */ diff --git a/tools/lib/perf/include/perf/mmap.h b/tools/lib/perf/include/perf/mmap.h new file mode 100644 index 000000000000..9508ad90d8b9 --- /dev/null +++ b/tools/lib/perf/include/perf/mmap.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_MMAP_H +#define __LIBPERF_MMAP_H + +#include <perf/core.h> + +struct perf_mmap; +union perf_event; + +LIBPERF_API void perf_mmap__consume(struct perf_mmap *map); +LIBPERF_API int perf_mmap__read_init(struct perf_mmap *map); +LIBPERF_API void perf_mmap__read_done(struct perf_mmap *map); +LIBPERF_API union perf_event *perf_mmap__read_event(struct perf_mmap *map); + +#endif /* __LIBPERF_MMAP_H */ diff --git a/tools/lib/perf/include/perf/threadmap.h b/tools/lib/perf/include/perf/threadmap.h new file mode 100644 index 000000000000..a7c50de8d010 --- /dev/null +++ b/tools/lib/perf/include/perf/threadmap.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_THREADMAP_H +#define __LIBPERF_THREADMAP_H + +#include <perf/core.h> +#include <sys/types.h> + +struct perf_thread_map; + +LIBPERF_API struct perf_thread_map *perf_thread_map__new_dummy(void); + +LIBPERF_API void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid); +LIBPERF_API char *perf_thread_map__comm(struct perf_thread_map *map, int thread); +LIBPERF_API int perf_thread_map__nr(struct perf_thread_map *threads); +LIBPERF_API pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread); + +LIBPERF_API struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map); +LIBPERF_API void perf_thread_map__put(struct perf_thread_map *map); + +#endif /* __LIBPERF_THREADMAP_H */ diff --git a/tools/lib/perf/internal.h b/tools/lib/perf/internal.h new file mode 100644 index 000000000000..2c27e158de6b --- /dev/null +++ b/tools/lib/perf/internal.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LIBPERF_INTERNAL_H +#define __LIBPERF_INTERNAL_H + +#include <perf/core.h> + +void libperf_print(enum libperf_print_level level, + const char *format, ...) + __attribute__((format(printf, 2, 3))); + +#define __pr(level, fmt, ...) \ +do { \ + libperf_print(level, "libperf: " fmt, ##__VA_ARGS__); \ +} while (0) + +#define pr_err(fmt, ...) __pr(LIBPERF_ERR, fmt, ##__VA_ARGS__) +#define pr_warning(fmt, ...) __pr(LIBPERF_WARN, fmt, ##__VA_ARGS__) +#define pr_info(fmt, ...) __pr(LIBPERF_INFO, fmt, ##__VA_ARGS__) +#define pr_debug(fmt, ...) __pr(LIBPERF_DEBUG, fmt, ##__VA_ARGS__) +#define pr_debug2(fmt, ...) __pr(LIBPERF_DEBUG2, fmt, ##__VA_ARGS__) +#define pr_debug3(fmt, ...) __pr(LIBPERF_DEBUG3, fmt, ##__VA_ARGS__) + +#endif /* __LIBPERF_INTERNAL_H */ diff --git a/tools/lib/perf/lib.c b/tools/lib/perf/lib.c new file mode 100644 index 000000000000..18658931fc71 --- /dev/null +++ b/tools/lib/perf/lib.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <unistd.h> +#include <stdbool.h> +#include <errno.h> +#include <linux/kernel.h> +#include <internal/lib.h> + +unsigned int page_size; + +static ssize_t ion(bool is_read, int fd, void *buf, size_t n) +{ + void *buf_start = buf; + size_t left = n; + + while (left) { + /* buf must be treated as const if !is_read. */ + ssize_t ret = is_read ? read(fd, buf, left) : + write(fd, buf, left); + + if (ret < 0 && errno == EINTR) + continue; + if (ret <= 0) + return ret; + + left -= ret; + buf += ret; + } + + BUG_ON((size_t)(buf - buf_start) != n); + return n; +} + +/* + * Read exactly 'n' bytes or return an error. + */ +ssize_t readn(int fd, void *buf, size_t n) +{ + return ion(true, fd, buf, n); +} + +/* + * Write exactly 'n' bytes or return an error. + */ +ssize_t writen(int fd, const void *buf, size_t n) +{ + /* ion does not modify buf. */ + return ion(false, fd, (void *)buf, n); +} diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map new file mode 100644 index 000000000000..7be1af8a546c --- /dev/null +++ b/tools/lib/perf/libperf.map @@ -0,0 +1,51 @@ +LIBPERF_0.0.1 { + global: + libperf_init; + perf_cpu_map__dummy_new; + perf_cpu_map__get; + perf_cpu_map__put; + perf_cpu_map__new; + perf_cpu_map__read; + perf_cpu_map__nr; + perf_cpu_map__cpu; + perf_cpu_map__empty; + perf_cpu_map__max; + perf_thread_map__new_dummy; + perf_thread_map__set_pid; + perf_thread_map__comm; + perf_thread_map__nr; + perf_thread_map__pid; + perf_thread_map__get; + perf_thread_map__put; + perf_evsel__new; + perf_evsel__delete; + perf_evsel__enable; + perf_evsel__disable; + perf_evsel__open; + perf_evsel__close; + perf_evsel__read; + perf_evsel__cpus; + perf_evsel__threads; + perf_evsel__attr; + perf_evlist__new; + perf_evlist__delete; + perf_evlist__open; + perf_evlist__close; + perf_evlist__enable; + perf_evlist__disable; + perf_evlist__add; + perf_evlist__remove; + perf_evlist__next; + perf_evlist__set_maps; + perf_evlist__poll; + perf_evlist__mmap; + perf_evlist__munmap; + perf_evlist__filter_pollfd; + perf_evlist__next_mmap; + perf_mmap__consume; + perf_mmap__read_init; + perf_mmap__read_done; + perf_mmap__read_event; + local: + *; +}; diff --git a/tools/lib/perf/libperf.pc.template b/tools/lib/perf/libperf.pc.template new file mode 100644 index 000000000000..117e4a237b55 --- /dev/null +++ b/tools/lib/perf/libperf.pc.template @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +prefix=@PREFIX@ +libdir=@LIBDIR@ +includedir=${prefix}/include + +Name: libperf +Description: perf library +Version: @VERSION@ +Libs: -L${libdir} -lperf +Cflags: -I${includedir} diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c new file mode 100644 index 000000000000..79d5ed6c38cc --- /dev/null +++ b/tools/lib/perf/mmap.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <sys/mman.h> +#include <inttypes.h> +#include <asm/bug.h> +#include <errno.h> +#include <string.h> +#include <linux/ring_buffer.h> +#include <linux/perf_event.h> +#include <perf/mmap.h> +#include <perf/event.h> +#include <internal/mmap.h> +#include <internal/lib.h> +#include <linux/kernel.h> +#include "internal.h" + +void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev, + bool overwrite, libperf_unmap_cb_t unmap_cb) +{ + map->fd = -1; + map->overwrite = overwrite; + map->unmap_cb = unmap_cb; + refcount_set(&map->refcnt, 0); + if (prev) + prev->next = map; +} + +size_t perf_mmap__mmap_len(struct perf_mmap *map) +{ + return map->mask + 1 + page_size; +} + +int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp, + int fd, int cpu) +{ + map->prev = 0; + map->mask = mp->mask; + map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot, + MAP_SHARED, fd, 0); + if (map->base == MAP_FAILED) { + map->base = NULL; + return -1; + } + + map->fd = fd; + map->cpu = cpu; + return 0; +} + +void perf_mmap__munmap(struct perf_mmap *map) +{ + if (map && map->base != NULL) { + munmap(map->base, perf_mmap__mmap_len(map)); + map->base = NULL; + map->fd = -1; + refcount_set(&map->refcnt, 0); + } + if (map && map->unmap_cb) + map->unmap_cb(map); +} + +void perf_mmap__get(struct perf_mmap *map) +{ + refcount_inc(&map->refcnt); +} + +void perf_mmap__put(struct perf_mmap *map) +{ + BUG_ON(map->base && refcount_read(&map->refcnt) == 0); + + if (refcount_dec_and_test(&map->refcnt)) + perf_mmap__munmap(map); +} + +static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail) +{ + ring_buffer_write_tail(md->base, tail); +} + +u64 perf_mmap__read_head(struct perf_mmap *map) +{ + return ring_buffer_read_head(map->base); +} + +static bool perf_mmap__empty(struct perf_mmap *map) +{ + struct perf_event_mmap_page *pc = map->base; + + return perf_mmap__read_head(map) == map->prev && !pc->aux_size; +} + +void perf_mmap__consume(struct perf_mmap *map) +{ + if (!map->overwrite) { + u64 old = map->prev; + + perf_mmap__write_tail(map, old); + } + + if (refcount_read(&map->refcnt) == 1 && perf_mmap__empty(map)) + perf_mmap__put(map); +} + +static int overwrite_rb_find_range(void *buf, int mask, u64 *start, u64 *end) +{ + struct perf_event_header *pheader; + u64 evt_head = *start; + int size = mask + 1; + + pr_debug2("%s: buf=%p, start=%"PRIx64"\n", __func__, buf, *start); + pheader = (struct perf_event_header *)(buf + (*start & mask)); + while (true) { + if (evt_head - *start >= (unsigned int)size) { + pr_debug("Finished reading overwrite ring buffer: rewind\n"); + if (evt_head - *start > (unsigned int)size) + evt_head -= pheader->size; + *end = evt_head; + return 0; + } + + pheader = (struct perf_event_header *)(buf + (evt_head & mask)); + + if (pheader->size == 0) { + pr_debug("Finished reading overwrite ring buffer: get start\n"); + *end = evt_head; + return 0; + } + + evt_head += pheader->size; + pr_debug3("move evt_head: %"PRIx64"\n", evt_head); + } + WARN_ONCE(1, "Shouldn't get here\n"); + return -1; +} + +/* + * Report the start and end of the available data in ringbuffer + */ +static int __perf_mmap__read_init(struct perf_mmap *md) +{ + u64 head = perf_mmap__read_head(md); + u64 old = md->prev; + unsigned char *data = md->base + page_size; + unsigned long size; + + md->start = md->overwrite ? head : old; + md->end = md->overwrite ? old : head; + + if ((md->end - md->start) < md->flush) + return -EAGAIN; + + size = md->end - md->start; + if (size > (unsigned long)(md->mask) + 1) { + if (!md->overwrite) { + WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n"); + + md->prev = head; + perf_mmap__consume(md); + return -EAGAIN; + } + + /* + * Backward ring buffer is full. We still have a chance to read + * most of data from it. + */ + if (overwrite_rb_find_range(data, md->mask, &md->start, &md->end)) + return -EINVAL; + } + + return 0; +} + +int perf_mmap__read_init(struct perf_mmap *map) +{ + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!refcount_read(&map->refcnt)) + return -ENOENT; + + return __perf_mmap__read_init(map); +} + +/* + * Mandatory for overwrite mode + * The direction of overwrite mode is backward. + * The last perf_mmap__read() will set tail to map->core.prev. + * Need to correct the map->core.prev to head which is the end of next read. + */ +void perf_mmap__read_done(struct perf_mmap *map) +{ + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!refcount_read(&map->refcnt)) + return; + + map->prev = perf_mmap__read_head(map); +} + +/* When check_messup is true, 'end' must points to a good entry */ +static union perf_event *perf_mmap__read(struct perf_mmap *map, + u64 *startp, u64 end) +{ + unsigned char *data = map->base + page_size; + union perf_event *event = NULL; + int diff = end - *startp; + + if (diff >= (int)sizeof(event->header)) { + size_t size; + + event = (union perf_event *)&data[*startp & map->mask]; + size = event->header.size; + + if (size < sizeof(event->header) || diff < (int)size) + return NULL; + + /* + * Event straddles the mmap boundary -- header should always + * be inside due to u64 alignment of output. + */ + if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) { + unsigned int offset = *startp; + unsigned int len = min(sizeof(*event), size), cpy; + void *dst = map->event_copy; + + do { + cpy = min(map->mask + 1 - (offset & map->mask), len); + memcpy(dst, &data[offset & map->mask], cpy); + offset += cpy; + dst += cpy; + len -= cpy; + } while (len); + + event = (union perf_event *)map->event_copy; + } + + *startp += size; + } + + return event; +} + +/* + * Read event from ring buffer one by one. + * Return one event for each call. + * + * Usage: + * perf_mmap__read_init() + * while(event = perf_mmap__read_event()) { + * //process the event + * perf_mmap__consume() + * } + * perf_mmap__read_done() + */ +union perf_event *perf_mmap__read_event(struct perf_mmap *map) +{ + union perf_event *event; + + /* + * Check if event was unmapped due to a POLLHUP/POLLERR. + */ + if (!refcount_read(&map->refcnt)) + return NULL; + + /* non-overwirte doesn't pause the ringbuffer */ + if (!map->overwrite) + map->end = perf_mmap__read_head(map); + + event = perf_mmap__read(map, &map->start, map->end); + + if (!map->overwrite) + map->prev = map->start; + + return event; +} diff --git a/tools/lib/perf/tests/Makefile b/tools/lib/perf/tests/Makefile new file mode 100644 index 000000000000..96841775feaf --- /dev/null +++ b/tools/lib/perf/tests/Makefile @@ -0,0 +1,38 @@ +# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +TESTS = test-cpumap test-threadmap test-evlist test-evsel + +TESTS_SO := $(addsuffix -so,$(TESTS)) +TESTS_A := $(addsuffix -a,$(TESTS)) + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -Wall +endif + +all: + +include $(srctree)/tools/scripts/Makefile.include + +INCLUDE = -I$(srctree)/tools/lib/perf/include -I$(srctree)/tools/include -I$(srctree)/tools/lib + +$(TESTS_A): FORCE + $(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -o $@ $(subst -a,.c,$@) ../libperf.a $(LIBAPI) + +$(TESTS_SO): FORCE + $(QUIET_LINK)$(CC) $(INCLUDE) $(CFLAGS) -L.. -o $@ $(subst -so,.c,$@) $(LIBAPI) -lperf + +all: $(TESTS_A) $(TESTS_SO) + +run: + @echo "running static:" + @for i in $(TESTS_A); do ./$$i; done + @echo "running dynamic:" + @for i in $(TESTS_SO); do LD_LIBRARY_PATH=../ ./$$i; done + +clean: + $(call QUIET_CLEAN, tests)$(RM) $(TESTS_A) $(TESTS_SO) + +.PHONY: all clean FORCE diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c new file mode 100644 index 000000000000..c8d45091e7c2 --- /dev/null +++ b/tools/lib/perf/tests/test-cpumap.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdarg.h> +#include <stdio.h> +#include <perf/cpumap.h> +#include <internal/tests.h> + +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + +int main(int argc, char **argv) +{ + struct perf_cpu_map *cpus; + + __T_START; + + libperf_init(libperf_print); + + cpus = perf_cpu_map__dummy_new(); + if (!cpus) + return -1; + + perf_cpu_map__get(cpus); + perf_cpu_map__put(cpus); + perf_cpu_map__put(cpus); + + __T_END; + return 0; +} diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c new file mode 100644 index 000000000000..6d8ebe0c2504 --- /dev/null +++ b/tools/lib/perf/tests/test-evlist.c @@ -0,0 +1,413 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE // needed for sched.h to get sched_[gs]etaffinity and CPU_(ZERO,SET) +#include <sched.h> +#include <stdio.h> +#include <stdarg.h> +#include <unistd.h> +#include <stdlib.h> +#include <linux/perf_event.h> +#include <linux/limits.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/prctl.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <perf/evlist.h> +#include <perf/evsel.h> +#include <perf/mmap.h> +#include <perf/event.h> +#include <internal/tests.h> +#include <api/fs/fs.h> + +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + +static int test_stat_cpu(void) +{ + struct perf_cpu_map *cpus; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_event_attr attr1 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + struct perf_event_attr attr2 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + }; + int err, cpu, tmp; + + cpus = perf_cpu_map__new(NULL); + __T("failed to create cpus", cpus); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + evsel = perf_evsel__new(&attr1); + __T("failed to create evsel1", evsel); + + perf_evlist__add(evlist, evsel); + + evsel = perf_evsel__new(&attr2); + __T("failed to create evsel2", evsel); + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, cpus, NULL); + + err = perf_evlist__open(evlist); + __T("failed to open evsel", err == 0); + + perf_evlist__for_each_evsel(evlist, evsel) { + cpus = perf_evsel__cpus(evsel); + + perf_cpu_map__for_each_cpu(cpu, tmp, cpus) { + struct perf_counts_values counts = { .val = 0 }; + + perf_evsel__read(evsel, cpu, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + } + } + + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + + perf_cpu_map__put(cpus); + return 0; +} + +static int test_stat_thread(void) +{ + struct perf_counts_values counts = { .val = 0 }; + struct perf_thread_map *threads; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_event_attr attr1 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + struct perf_event_attr attr2 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + }; + int err; + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + evsel = perf_evsel__new(&attr1); + __T("failed to create evsel1", evsel); + + perf_evlist__add(evlist, evsel); + + evsel = perf_evsel__new(&attr2); + __T("failed to create evsel2", evsel); + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, NULL, threads); + + err = perf_evlist__open(evlist); + __T("failed to open evsel", err == 0); + + perf_evlist__for_each_evsel(evlist, evsel) { + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + } + + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + + perf_thread_map__put(threads); + return 0; +} + +static int test_stat_thread_enable(void) +{ + struct perf_counts_values counts = { .val = 0 }; + struct perf_thread_map *threads; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_event_attr attr1 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + .disabled = 1, + }; + struct perf_event_attr attr2 = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + .disabled = 1, + }; + int err; + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + evsel = perf_evsel__new(&attr1); + __T("failed to create evsel1", evsel); + + perf_evlist__add(evlist, evsel); + + evsel = perf_evsel__new(&attr2); + __T("failed to create evsel2", evsel); + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, NULL, threads); + + err = perf_evlist__open(evlist); + __T("failed to open evsel", err == 0); + + perf_evlist__for_each_evsel(evlist, evsel) { + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val == 0); + } + + perf_evlist__enable(evlist); + + perf_evlist__for_each_evsel(evlist, evsel) { + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + } + + perf_evlist__disable(evlist); + + perf_evlist__close(evlist); + perf_evlist__delete(evlist); + + perf_thread_map__put(threads); + return 0; +} + +static int test_mmap_thread(void) +{ + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_mmap *map; + struct perf_cpu_map *cpus; + struct perf_thread_map *threads; + struct perf_event_attr attr = { + .type = PERF_TYPE_TRACEPOINT, + .sample_period = 1, + .wakeup_watermark = 1, + .disabled = 1, + }; + char path[PATH_MAX]; + int id, err, pid, go_pipe[2]; + union perf_event *event; + char bf; + int count = 0; + + snprintf(path, PATH_MAX, "%s/kernel/debug/tracing/events/syscalls/sys_enter_prctl/id", + sysfs__mountpoint()); + + if (filename__read_int(path, &id)) { + fprintf(stderr, "error: failed to get tracepoint id: %s\n", path); + return -1; + } + + attr.config = id; + + err = pipe(go_pipe); + __T("failed to create pipe", err == 0); + + fflush(NULL); + + pid = fork(); + if (!pid) { + int i; + + read(go_pipe[0], &bf, 1); + + /* Generate 100 prctl calls. */ + for (i = 0; i < 100; i++) + prctl(0, 0, 0, 0, 0); + + exit(0); + } + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + cpus = perf_cpu_map__dummy_new(); + __T("failed to create cpus", cpus); + + perf_thread_map__set_pid(threads, 0, pid); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel1", evsel); + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, cpus, threads); + + err = perf_evlist__open(evlist); + __T("failed to open evlist", err == 0); + + err = perf_evlist__mmap(evlist, 4); + __T("failed to mmap evlist", err == 0); + + perf_evlist__enable(evlist); + + /* kick the child and wait for it to finish */ + write(go_pipe[1], &bf, 1); + waitpid(pid, NULL, 0); + + /* + * There's no need to call perf_evlist__disable, + * monitored process is dead now. + */ + + perf_evlist__for_each_mmap(evlist, map, false) { + if (perf_mmap__read_init(map) < 0) + continue; + + while ((event = perf_mmap__read_event(map)) != NULL) { + count++; + perf_mmap__consume(map); + } + + perf_mmap__read_done(map); + } + + /* calls perf_evlist__munmap/perf_evlist__close */ + perf_evlist__delete(evlist); + + perf_thread_map__put(threads); + perf_cpu_map__put(cpus); + + /* + * The generated prctl calls should match the + * number of events in the buffer. + */ + __T("failed count", count == 100); + + return 0; +} + +static int test_mmap_cpus(void) +{ + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct perf_mmap *map; + struct perf_cpu_map *cpus; + struct perf_event_attr attr = { + .type = PERF_TYPE_TRACEPOINT, + .sample_period = 1, + .wakeup_watermark = 1, + .disabled = 1, + }; + cpu_set_t saved_mask; + char path[PATH_MAX]; + int id, err, cpu, tmp; + union perf_event *event; + int count = 0; + + snprintf(path, PATH_MAX, "%s/kernel/debug/tracing/events/syscalls/sys_enter_prctl/id", + sysfs__mountpoint()); + + if (filename__read_int(path, &id)) { + fprintf(stderr, "error: failed to get tracepoint id: %s\n", path); + return -1; + } + + attr.config = id; + + cpus = perf_cpu_map__new(NULL); + __T("failed to create cpus", cpus); + + evlist = perf_evlist__new(); + __T("failed to create evlist", evlist); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel1", evsel); + + perf_evlist__add(evlist, evsel); + + perf_evlist__set_maps(evlist, cpus, NULL); + + err = perf_evlist__open(evlist); + __T("failed to open evlist", err == 0); + + err = perf_evlist__mmap(evlist, 4); + __T("failed to mmap evlist", err == 0); + + perf_evlist__enable(evlist); + + err = sched_getaffinity(0, sizeof(saved_mask), &saved_mask); + __T("sched_getaffinity failed", err == 0); + + perf_cpu_map__for_each_cpu(cpu, tmp, cpus) { + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + + err = sched_setaffinity(0, sizeof(mask), &mask); + __T("sched_setaffinity failed", err == 0); + + prctl(0, 0, 0, 0, 0); + } + + err = sched_setaffinity(0, sizeof(saved_mask), &saved_mask); + __T("sched_setaffinity failed", err == 0); + + perf_evlist__disable(evlist); + + perf_evlist__for_each_mmap(evlist, map, false) { + if (perf_mmap__read_init(map) < 0) + continue; + + while ((event = perf_mmap__read_event(map)) != NULL) { + count++; + perf_mmap__consume(map); + } + + perf_mmap__read_done(map); + } + + /* calls perf_evlist__munmap/perf_evlist__close */ + perf_evlist__delete(evlist); + + /* + * The generated prctl events should match the + * number of cpus or be bigger (we are system-wide). + */ + __T("failed count", count >= perf_cpu_map__nr(cpus)); + + perf_cpu_map__put(cpus); + + return 0; +} + +int main(int argc, char **argv) +{ + __T_START; + + libperf_init(libperf_print); + + test_stat_cpu(); + test_stat_thread(); + test_stat_thread_enable(); + test_mmap_thread(); + test_mmap_cpus(); + + __T_END; + return 0; +} diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c new file mode 100644 index 000000000000..135722ac965b --- /dev/null +++ b/tools/lib/perf/tests/test-evsel.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdarg.h> +#include <stdio.h> +#include <linux/perf_event.h> +#include <perf/cpumap.h> +#include <perf/threadmap.h> +#include <perf/evsel.h> +#include <internal/tests.h> + +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + +static int test_stat_cpu(void) +{ + struct perf_cpu_map *cpus; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + int err, cpu, tmp; + + cpus = perf_cpu_map__new(NULL); + __T("failed to create cpus", cpus); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, cpus, NULL); + __T("failed to open evsel", err == 0); + + perf_cpu_map__for_each_cpu(cpu, tmp, cpus) { + struct perf_counts_values counts = { .val = 0 }; + + perf_evsel__read(evsel, cpu, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + } + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_cpu_map__put(cpus); + return 0; +} + +static int test_stat_thread(void) +{ + struct perf_counts_values counts = { .val = 0 }; + struct perf_thread_map *threads; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + }; + int err; + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, NULL, threads); + __T("failed to open evsel", err == 0); + + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_thread_map__put(threads); + return 0; +} + +static int test_stat_thread_enable(void) +{ + struct perf_counts_values counts = { .val = 0 }; + struct perf_thread_map *threads; + struct perf_evsel *evsel; + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_TASK_CLOCK, + .disabled = 1, + }; + int err; + + threads = perf_thread_map__new_dummy(); + __T("failed to create threads", threads); + + perf_thread_map__set_pid(threads, 0, 0); + + evsel = perf_evsel__new(&attr); + __T("failed to create evsel", evsel); + + err = perf_evsel__open(evsel, NULL, threads); + __T("failed to open evsel", err == 0); + + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val == 0); + + err = perf_evsel__enable(evsel); + __T("failed to enable evsel", err == 0); + + perf_evsel__read(evsel, 0, 0, &counts); + __T("failed to read value for evsel", counts.val != 0); + + err = perf_evsel__disable(evsel); + __T("failed to enable evsel", err == 0); + + perf_evsel__close(evsel); + perf_evsel__delete(evsel); + + perf_thread_map__put(threads); + return 0; +} + +int main(int argc, char **argv) +{ + __T_START; + + libperf_init(libperf_print); + + test_stat_cpu(); + test_stat_thread(); + test_stat_thread_enable(); + + __T_END; + return 0; +} diff --git a/tools/lib/perf/tests/test-threadmap.c b/tools/lib/perf/tests/test-threadmap.c new file mode 100644 index 000000000000..7dc4d6fbedde --- /dev/null +++ b/tools/lib/perf/tests/test-threadmap.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdarg.h> +#include <stdio.h> +#include <perf/threadmap.h> +#include <internal/tests.h> + +static int libperf_print(enum libperf_print_level level, + const char *fmt, va_list ap) +{ + return vfprintf(stderr, fmt, ap); +} + +int main(int argc, char **argv) +{ + struct perf_thread_map *threads; + + __T_START; + + libperf_init(libperf_print); + + threads = perf_thread_map__new_dummy(); + if (!threads) + return -1; + + perf_thread_map__get(threads); + perf_thread_map__put(threads); + perf_thread_map__put(threads); + + __T_END; + return 0; +} diff --git a/tools/lib/perf/threadmap.c b/tools/lib/perf/threadmap.c new file mode 100644 index 000000000000..e92c368b0a6c --- /dev/null +++ b/tools/lib/perf/threadmap.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <perf/threadmap.h> +#include <stdlib.h> +#include <linux/refcount.h> +#include <internal/threadmap.h> +#include <string.h> +#include <asm/bug.h> +#include <stdio.h> + +static void perf_thread_map__reset(struct perf_thread_map *map, int start, int nr) +{ + size_t size = (nr - start) * sizeof(map->map[0]); + + memset(&map->map[start], 0, size); + map->err_thread = -1; +} + +struct perf_thread_map *perf_thread_map__realloc(struct perf_thread_map *map, int nr) +{ + size_t size = sizeof(*map) + sizeof(map->map[0]) * nr; + int start = map ? map->nr : 0; + + map = realloc(map, size); + /* + * We only realloc to add more items, let's reset new items. + */ + if (map) + perf_thread_map__reset(map, start, nr); + + return map; +} + +#define thread_map__alloc(__nr) perf_thread_map__realloc(NULL, __nr) + +void perf_thread_map__set_pid(struct perf_thread_map *map, int thread, pid_t pid) +{ + map->map[thread].pid = pid; +} + +char *perf_thread_map__comm(struct perf_thread_map *map, int thread) +{ + return map->map[thread].comm; +} + +struct perf_thread_map *perf_thread_map__new_dummy(void) +{ + struct perf_thread_map *threads = thread_map__alloc(1); + + if (threads != NULL) { + perf_thread_map__set_pid(threads, 0, -1); + threads->nr = 1; + refcount_set(&threads->refcnt, 1); + } + return threads; +} + +static void perf_thread_map__delete(struct perf_thread_map *threads) +{ + if (threads) { + int i; + + WARN_ONCE(refcount_read(&threads->refcnt) != 0, + "thread map refcnt unbalanced\n"); + for (i = 0; i < threads->nr; i++) + free(perf_thread_map__comm(threads, i)); + free(threads); + } +} + +struct perf_thread_map *perf_thread_map__get(struct perf_thread_map *map) +{ + if (map) + refcount_inc(&map->refcnt); + return map; +} + +void perf_thread_map__put(struct perf_thread_map *map) +{ + if (map && refcount_dec_and_test(&map->refcnt)) + perf_thread_map__delete(map); +} + +int perf_thread_map__nr(struct perf_thread_map *threads) +{ + return threads ? threads->nr : 1; +} + +pid_t perf_thread_map__pid(struct perf_thread_map *map, int thread) +{ + return map->map[thread].pid; +} diff --git a/tools/lib/perf/xyarray.c b/tools/lib/perf/xyarray.c new file mode 100644 index 000000000000..dcd901d154bb --- /dev/null +++ b/tools/lib/perf/xyarray.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <internal/xyarray.h> +#include <linux/zalloc.h> +#include <stdlib.h> +#include <string.h> + +struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size) +{ + size_t row_size = ylen * entry_size; + struct xyarray *xy = zalloc(sizeof(*xy) + xlen * row_size); + + if (xy != NULL) { + xy->entry_size = entry_size; + xy->row_size = row_size; + xy->entries = xlen * ylen; + xy->max_x = xlen; + xy->max_y = ylen; + } + + return xy; +} + +void xyarray__reset(struct xyarray *xy) +{ + size_t n = xy->entries * xy->entry_size; + + memset(xy->contents, 0, n); +} + +void xyarray__delete(struct xyarray *xy) +{ + free(xy); +} diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c index 804f145e3113..2548ff8c4d9c 100644 --- a/tools/lib/rbtree.c +++ b/tools/lib/rbtree.c @@ -83,14 +83,10 @@ __rb_rotate_set_parents(struct rb_node *old, struct rb_node *new, static __always_inline void __rb_insert(struct rb_node *node, struct rb_root *root, - bool newleft, struct rb_node **leftmost, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)) { struct rb_node *parent = rb_red_parent(node), *gparent, *tmp; - if (newleft) - *leftmost = node; - while (true) { /* * Loop invariant: node is red. @@ -436,34 +432,17 @@ static const struct rb_augment_callbacks dummy_callbacks = { void rb_insert_color(struct rb_node *node, struct rb_root *root) { - __rb_insert(node, root, false, NULL, dummy_rotate); + __rb_insert(node, root, dummy_rotate); } void rb_erase(struct rb_node *node, struct rb_root *root) { struct rb_node *rebalance; - rebalance = __rb_erase_augmented(node, root, - NULL, &dummy_callbacks); + rebalance = __rb_erase_augmented(node, root, &dummy_callbacks); if (rebalance) ____rb_erase_color(rebalance, root, dummy_rotate); } -void rb_insert_color_cached(struct rb_node *node, - struct rb_root_cached *root, bool leftmost) -{ - __rb_insert(node, &root->rb_root, leftmost, - &root->rb_leftmost, dummy_rotate); -} - -void rb_erase_cached(struct rb_node *node, struct rb_root_cached *root) -{ - struct rb_node *rebalance; - rebalance = __rb_erase_augmented(node, &root->rb_root, - &root->rb_leftmost, &dummy_callbacks); - if (rebalance) - ____rb_erase_color(rebalance, &root->rb_root, dummy_rotate); -} - /* * Augmented rbtree manipulation functions. * @@ -472,10 +451,9 @@ void rb_erase_cached(struct rb_node *node, struct rb_root_cached *root) */ void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, - bool newleft, struct rb_node **leftmost, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)) { - __rb_insert(node, root, newleft, leftmost, augment_rotate); + __rb_insert(node, root, augment_rotate); } /* @@ -580,15 +558,6 @@ void rb_replace_node(struct rb_node *victim, struct rb_node *new, __rb_change_child(victim, new, parent, root); } -void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, - struct rb_root_cached *root) -{ - rb_replace_node(victim, new, &root->rb_root); - - if (root->rb_leftmost == victim) - root->rb_leftmost = new; -} - static struct rb_node *rb_left_deepest_node(const struct rb_node *node) { for (;;) { diff --git a/tools/lib/string.c b/tools/lib/string.c index f2ae1b87c719..f645343815de 100644 --- a/tools/lib/string.c +++ b/tools/lib/string.c @@ -96,6 +96,10 @@ int strtobool(const char *s, bool *res) * If libc has strlcpy() then that version will override this * implementation: */ +#ifdef __clang__ +#pragma clang diagnostic push +#pragma clang diagnostic ignored "-Wignored-attributes" +#endif size_t __weak strlcpy(char *dest, const char *src, size_t size) { size_t ret = strlen(src); @@ -107,6 +111,9 @@ size_t __weak strlcpy(char *dest, const char *src, size_t size) } return ret; } +#ifdef __clang__ +#pragma clang diagnostic pop +#endif /** * skip_spaces - Removes leading whitespace from @str. diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile index ed61fb3a46c0..1c777a72bb39 100644 --- a/tools/lib/subcmd/Makefile +++ b/tools/lib/subcmd/Makefile @@ -19,10 +19,17 @@ MAKEFLAGS += --no-print-directory LIBFILE = $(OUTPUT)libsubcmd.a -CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS := -ggdb3 -Wall -Wextra -std=gnu99 -fPIC -ifeq ($(CC_NO_CLANG), 0) +ifeq ($(DEBUG),0) + ifeq ($(feature-fortify-source), 1) + CFLAGS += -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 + endif +endif + +ifeq ($(DEBUG),1) + CFLAGS += -O0 +else ifeq ($(CC_NO_CLANG), 0) CFLAGS += -O3 else CFLAGS += -O6 @@ -37,6 +44,8 @@ CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE CFLAGS += -I$(srctree)/tools/include/ +CFLAGS += $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) + SUBCMD_IN := $(OUTPUT)libsubcmd-in.o all: diff --git a/tools/lib/traceevent/Build b/tools/lib/traceevent/Build index ba54bfce0b0b..f9a5d79578f5 100644 --- a/tools/lib/traceevent/Build +++ b/tools/lib/traceevent/Build @@ -6,14 +6,3 @@ libtraceevent-y += parse-utils.o libtraceevent-y += kbuffer-parse.o libtraceevent-y += tep_strerror.o libtraceevent-y += event-parse-api.o - -plugin_jbd2-y += plugin_jbd2.o -plugin_hrtimer-y += plugin_hrtimer.o -plugin_kmem-y += plugin_kmem.o -plugin_kvm-y += plugin_kvm.o -plugin_mac80211-y += plugin_mac80211.o -plugin_sched_switch-y += plugin_sched_switch.o -plugin_function-y += plugin_function.o -plugin_xen-y += plugin_xen.o -plugin_scsi-y += plugin_scsi.o -plugin_cfg80211-y += plugin_cfg80211.o diff --git a/tools/lib/traceevent/Documentation/libtraceevent-event_print.txt b/tools/lib/traceevent/Documentation/libtraceevent-event_print.txt new file mode 100644 index 000000000000..2c6a61811118 --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-event_print.txt @@ -0,0 +1,130 @@ +libtraceevent(3) +================ + +NAME +---- +tep_print_event - Writes event information into a trace sequence. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* +*#include <trace-seq.h>* + +void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seqpass:[*]_s_, struct tep_record pass:[*]_record_, const char pass:[*]_fmt_, _..._) +-- + +DESCRIPTION +----------- + +The _tep_print_event()_ function parses the event information of the given +_record_ and writes it into the trace sequence _s_, according to the format +string _fmt_. The desired information is specified after the format string. +The _fmt_ is printf-like format string, following arguments are supported: +[verse] +-- + TEP_PRINT_PID, "%d" - PID of the event. + TEP_PRINT_CPU, "%d" - Event CPU. + TEP_PRINT_COMM, "%s" - Event command string. + TEP_PRINT_NAME, "%s" - Event name. + TEP_PRINT_LATENCY, "%s" - Latency of the event. It prints 4 or more + fields - interrupt state, scheduling state, + current context, and preemption count. + Field 1 is the interrupt enabled state: + d : Interrupts are disabled + . : Interrupts are enabled + X : The architecture does not support this + information + Field 2 is the "need resched" state. + N : The task is set to call the scheduler when + possible, as another higher priority task + may need to be scheduled in. + . : The task is not set to call the scheduler. + Field 3 is the context state. + . : Normal context + s : Soft interrupt context + h : Hard interrupt context + H : Hard interrupt context which triggered + during soft interrupt context. + z : NMI context + Z : NMI context which triggered during hard + interrupt context + Field 4 is the preemption count. + . : The preempt count is zero. + On preemptible kernels (where the task can be scheduled + out in arbitrary locations while in kernel context), the + preempt count, when non zero, will prevent the kernel + from scheduling out the current task. The preempt count + number is displayed when it is not zero. + Depending on the kernel, it may show other fields + (lock depth, or migration disabled, which are unique to + specialized kernels). + TEP_PRINT_TIME, %d - event time stamp. A divisor and precision can be + specified as part of this format string: + "%precision.divisord". Example: + "%3.1000d" - divide the time by 1000 and print the first + 3 digits before the dot. Thus, the time stamp + "123456000" will be printed as "123.456" + TEP_PRINT_INFO, "%s" - event information. + TEP_PRINT_INFO_RAW, "%s" - event information, in raw format. + +-- +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +#include <trace-seq.h> +... +struct trace_seq seq; +trace_seq_init(&seq); +struct tep_handle *tep = tep_alloc(); +... +void print_my_event(struct tep_record *record) +{ + trace_seq_reset(&seq); + tep_print_event(tep, s, record, "%16s-%-5d [%03d] %s %6.1000d %s %s", + TEP_PRINT_COMM, TEP_PRINT_PID, TEP_PRINT_CPU, + TEP_PRINT_LATENCY, TEP_PRINT_TIME, TEP_PRINT_NAME, + TEP_PRINT_INFO); +} +... +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*trace-seq.h* + Header file to include in order to have access to trace sequences related APIs. + Trace sequences are used to allow a function to call several other functions + to create a string of data to use. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt index 38bfea30a5f6..f6aca0df2151 100644 --- a/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt +++ b/tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt @@ -59,12 +59,12 @@ parser context. The _tep_register_function()_ function registers a function name mapped to an address and (optional) module. This mapping is used in case the function tracer -or events have "%pF" or "%pS" parameter in its format string. It is common to -pass in the kallsyms function names with their corresponding addresses with this +or events have "%pS" parameter in its format string. It is common to pass in +the kallsyms function names with their corresponding addresses with this function. The _tep_ argument is the trace event parser context. The _name_ is -the name of the function, the string is copied internally. The _addr_ is -the start address of the function. The _mod_ is the kernel module -the function may be in (NULL for none). +the name of the function, the string is copied internally. The _addr_ is the +start address of the function. The _mod_ is the kernel module the function may +be in (NULL for none). The _tep_register_print_string()_ function registers a string by the address it was stored in the kernel. Some strings internal to the kernel with static diff --git a/tools/lib/traceevent/Documentation/libtraceevent-handle.txt b/tools/lib/traceevent/Documentation/libtraceevent-handle.txt index 8d568316847d..45b20172e262 100644 --- a/tools/lib/traceevent/Documentation/libtraceevent-handle.txt +++ b/tools/lib/traceevent/Documentation/libtraceevent-handle.txt @@ -3,7 +3,7 @@ libtraceevent(3) NAME ---- -tep_alloc, tep_free,tep_ref, tep_unref,tep_ref_get - Create, destroy, manage +tep_alloc, tep_free,tep_ref, tep_unref,tep_get_ref - Create, destroy, manage references of trace event parser context. SYNOPSIS @@ -16,7 +16,7 @@ struct tep_handle pass:[*]*tep_alloc*(void); void *tep_free*(struct tep_handle pass:[*]_tep_); void *tep_ref*(struct tep_handle pass:[*]_tep_); void *tep_unref*(struct tep_handle pass:[*]_tep_); -int *tep_ref_get*(struct tep_handle pass:[*]_tep_); +int *tep_get_ref*(struct tep_handle pass:[*]_tep_); -- DESCRIPTION @@ -57,9 +57,9 @@ EXAMPLE ... struct tep_handle *tep = tep_alloc(); ... -int ref = tep_ref_get(tep); +int ref = tep_get_ref(tep); tep_ref(tep); -if ( (ref+1) != tep_ref_get(tep)) { +if ( (ref+1) != tep_get_ref(tep)) { /* Something wrong happened, the counter is not incremented by 1 */ } tep_unref(tep); diff --git a/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt b/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt new file mode 100644 index 000000000000..596032ade31f --- /dev/null +++ b/tools/lib/traceevent/Documentation/libtraceevent-plugins.txt @@ -0,0 +1,99 @@ +libtraceevent(3) +================ + +NAME +---- +tep_load_plugins, tep_unload_plugins - Load / unload traceevent plugins. + +SYNOPSIS +-------- +[verse] +-- +*#include <event-parse.h>* + +struct tep_plugin_list pass:[*]*tep_load_plugins*(struct tep_handle pass:[*]_tep_); +void *tep_unload_plugins*(struct tep_plugin_list pass:[*]_plugin_list_, struct tep_handle pass:[*]_tep_); +-- + +DESCRIPTION +----------- +The _tep_load_plugins()_ function loads all plugins, located in the plugin +directories. The _tep_ argument is trace event parser context. +The plugin directories are : +[verse] +-- + - System's plugin directory, defined at the library compile time. It + depends on the library installation prefix and usually is + _(install_preffix)/lib/traceevent/plugins_ + - Directory, defined by the environment variable _TRACEEVENT_PLUGIN_DIR_ + - User's plugin directory, located at _~/.local/lib/traceevent/plugins_ +-- +Loading of plugins can be controlled by the _tep_flags_, using the +_tep_set_flag()_ API: +[verse] +-- + _TEP_DISABLE_SYS_PLUGINS_ - do not load plugins, located in + the system's plugin directory. + _TEP_DISABLE_PLUGINS_ - do not load any plugins. +-- +The _tep_set_flag()_ API needs to be called before _tep_load_plugins()_, if +loading of all plugins is not the desired case. + +The _tep_unload_plugins()_ function unloads the plugins, previously loaded by +_tep_load_plugins()_. The _tep_ argument is trace event parser context. The +_plugin_list_ is the list of loaded plugins, returned by +the _tep_load_plugins()_ function. + +RETURN VALUE +------------ +The _tep_load_plugins()_ function returns a list of successfully loaded plugins, +or NULL in case no plugins are loaded. + +EXAMPLE +------- +[source,c] +-- +#include <event-parse.h> +... +struct tep_handle *tep = tep_alloc(); +... +struct tep_plugin_list *plugins = tep_load_plugins(tep); +if (plugins == NULL) { + /* no plugins are loaded */ +} +... +tep_unload_plugins(plugins, tep); +-- + +FILES +----- +[verse] +-- +*event-parse.h* + Header file to include in order to have access to the library APIs. +*-ltraceevent* + Linker switch to add when building a program that uses the library. +-- + +SEE ALSO +-------- +_libtraceevent(3)_, _trace-cmd(1)_, _tep_set_flag(3)_ + +AUTHOR +------ +[verse] +-- +*Steven Rostedt* <rostedt@goodmis.org>, author of *libtraceevent*. +*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page. +-- +REPORTING BUGS +-------------- +Report bugs to <linux-trace-devel@vger.kernel.org> + +LICENSE +------- +libtraceevent is Free Software licensed under the GNU LGPL 2.1 + +RESOURCES +--------- +https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git diff --git a/tools/lib/traceevent/Documentation/libtraceevent.txt b/tools/lib/traceevent/Documentation/libtraceevent.txt index fbd977b47de1..d530a7ce8fb2 100644 --- a/tools/lib/traceevent/Documentation/libtraceevent.txt +++ b/tools/lib/traceevent/Documentation/libtraceevent.txt @@ -16,7 +16,7 @@ Management of tep handler data structure and access of its members: void *tep_free*(struct tep_handle pass:[*]_tep_); void *tep_ref*(struct tep_handle pass:[*]_tep_); void *tep_unref*(struct tep_handle pass:[*]_tep_); - int *tep_ref_get*(struct tep_handle pass:[*]_tep_); + int *tep_get_ref*(struct tep_handle pass:[*]_tep_); void *tep_set_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_); void *tep_clear_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_); bool *tep_test_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flags_); @@ -26,15 +26,12 @@ Management of tep handler data structure and access of its members: void *tep_set_long_size*(struct tep_handle pass:[*]_tep_, int _long_size_); int *tep_get_page_size*(struct tep_handle pass:[*]_tep_); void *tep_set_page_size*(struct tep_handle pass:[*]_tep_, int _page_size_); - bool *tep_is_latency_format*(struct tep_handle pass:[*]_tep_); - void *tep_set_latency_format*(struct tep_handle pass:[*]_tep_, int _lat_); int *tep_get_header_page_size*(struct tep_handle pass:[*]_tep_); int *tep_get_header_timestamp_size*(struct tep_handle pass:[*]_tep_); bool *tep_is_old_format*(struct tep_handle pass:[*]_tep_); int *tep_strerror*(struct tep_handle pass:[*]_tep_, enum tep_errno _errnum_, char pass:[*]_buf_, size_t _buflen_); Register / unregister APIs: - int *tep_register_trace_clock*(struct tep_handle pass:[*]_tep_, const char pass:[*]_trace_clock_); int *tep_register_function*(struct tep_handle pass:[*]_tep_, char pass:[*]_name_, unsigned long long _addr_, char pass:[*]_mod_); int *tep_register_event_handler*(struct tep_handle pass:[*]_tep_, int _id_, const char pass:[*]_sys_name_, const char pass:[*]_event_name_, tep_event_handler_func _func_, void pass:[*]_context_); int *tep_unregister_event_handler*(struct tep_handle pass:[*]tep, int id, const char pass:[*]sys_name, const char pass:[*]event_name, tep_event_handler_func func, void pass:[*]_context_); @@ -57,14 +54,7 @@ Event related APIs: int *tep_get_events_count*(struct tep_handle pass:[*]_tep_); struct tep_event pass:[*]pass:[*]*tep_list_events*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_); struct tep_event pass:[*]pass:[*]*tep_list_events_copy*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_); - -Event printing: - void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_, bool _use_trace_clock_); - void *tep_print_event_data*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_); - void *tep_event_info*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_); - void *tep_print_event_task*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_); - void *tep_print_event_time*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]record, bool _use_trace_clock_); - void *tep_set_print_raw*(struct tep_handle pass:[*]_tep_, int _print_raw_); + void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_, const char pass:[*]_fmt_, _..._); Event finding: struct tep_event pass:[*]*tep_find_event*(struct tep_handle pass:[*]_tep_, int _id_); @@ -116,7 +106,6 @@ Filter management: int *tep_filter_compare*(struct tep_event_filter pass:[*]_filter1_, struct tep_event_filter pass:[*]_filter2_); Parsing various data from the records: - void *tep_data_latency_format*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_); int *tep_data_type*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); int *tep_data_pid*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); int *tep_data_preempt_count*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_); diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile index 3292c290654f..c874c017c636 100644 --- a/tools/lib/traceevent/Makefile +++ b/tools/lib/traceevent/Makefile @@ -39,11 +39,12 @@ DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) - libdir_relative = lib64 + libdir_relative_temp = lib64 else - libdir_relative = lib + libdir_relative_temp = lib endif +libdir_relative ?= $(libdir_relative_temp) prefix ?= /usr/local libdir = $(prefix)/$(libdir_relative) man_dir = $(prefix)/share/man @@ -58,30 +59,6 @@ export man_dir man_dir_SQ INSTALL export DESTDIR DESTDIR_SQ export EVENT_PARSE_VERSION -set_plugin_dir := 1 - -# Set plugin_dir to preffered global plugin location -# If we install under $HOME directory we go under -# $(HOME)/.traceevent/plugins -# -# We dont set PLUGIN_DIR in case we install under $HOME -# directory, because by default the code looks under: -# $(HOME)/.traceevent/plugins by default. -# -ifeq ($(plugin_dir),) -ifeq ($(prefix),$(HOME)) -override plugin_dir = $(HOME)/.traceevent/plugins -set_plugin_dir := 0 -else -override plugin_dir = $(libdir)/traceevent/plugins -endif -endif - -ifeq ($(set_plugin_dir),1) -PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)" -PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))' -endif - include ../../scripts/Makefile.include # copy a bit from Linux kbuild @@ -105,7 +82,6 @@ export prefix libdir src obj # Shell quotes libdir_SQ = $(subst ','\'',$(libdir)) libdir_relative_SQ = $(subst ','\'',$(libdir_relative)) -plugin_dir_SQ = $(subst ','\'',$(plugin_dir)) CONFIG_INCLUDES = CONFIG_LIBS = @@ -122,6 +98,7 @@ EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION) LIB_TARGET = libtraceevent.a libtraceevent.so.$(EVENT_PARSE_VERSION) LIB_INSTALL = libtraceevent.a libtraceevent.so* +LIB_INSTALL := $(addprefix $(OUTPUT),$(LIB_INSTALL)) INCLUDES = -I. -I $(srctree)/tools/include $(CONFIG_INCLUDES) @@ -151,29 +128,14 @@ MAKEOVERRIDES= export srctree OUTPUT CC LD CFLAGS V build := -f $(srctree)/tools/build/Makefile.build dir=. obj -PLUGINS = plugin_jbd2.so -PLUGINS += plugin_hrtimer.so -PLUGINS += plugin_kmem.so -PLUGINS += plugin_kvm.so -PLUGINS += plugin_mac80211.so -PLUGINS += plugin_sched_switch.so -PLUGINS += plugin_function.so -PLUGINS += plugin_xen.so -PLUGINS += plugin_scsi.so -PLUGINS += plugin_cfg80211.so - -PLUGINS := $(addprefix $(OUTPUT),$(PLUGINS)) -PLUGINS_IN := $(PLUGINS:.so=-in.o) - TE_IN := $(OUTPUT)libtraceevent-in.o LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) -DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list -CMD_TARGETS = $(LIB_TARGET) $(PLUGINS) $(DYNAMIC_LIST_FILE) +CMD_TARGETS = $(LIB_TARGET) TARGETS = $(CMD_TARGETS) -all: all_cmd +all: all_cmd plugins all_cmd: $(CMD_TARGETS) @@ -188,17 +150,6 @@ $(OUTPUT)libtraceevent.so.$(EVENT_PARSE_VERSION): $(TE_IN) $(OUTPUT)libtraceevent.a: $(TE_IN) $(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^ -$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS) - $(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@) - -plugins: $(PLUGINS) - -__plugin_obj = $(notdir $@) - plugin_obj = $(__plugin_obj:-in.o=) - -$(PLUGINS_IN): force - $(Q)$(MAKE) $(build)=$(plugin_obj) - $(OUTPUT)%.so: $(OUTPUT)%-in.o $(QUIET_LINK)$(CC) $(CFLAGS) -shared $(LDFLAGS) -nostartfiles -o $@ $^ @@ -258,29 +209,11 @@ define do_install $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2' endef -define do_install_plugins - for plugin in $1; do \ - $(call do_install,$$plugin,$(plugin_dir_SQ)); \ - done -endef - -define do_generate_dynamic_list_file - symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \ - xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\ - if [ "$$symbol_type" = "U W w" ];then \ - (echo '{'; \ - $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ - echo '};'; \ - ) > $2; \ - else \ - (echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\ - fi -endef - -PKG_CONFIG_FILE = libtraceevent.pc +PKG_CONFIG_SOURCE_FILE = libtraceevent.pc +PKG_CONFIG_FILE := $(addprefix $(OUTPUT),$(PKG_CONFIG_SOURCE_FILE)) define do_install_pkgconfig_file if [ -n "${pkgconfig_dir}" ]; then \ - cp -f ${PKG_CONFIG_FILE}.template ${PKG_CONFIG_FILE}; \ + cp -f ${PKG_CONFIG_SOURCE_FILE}.template ${PKG_CONFIG_FILE}; \ sed -i "s|INSTALL_PREFIX|${1}|g" ${PKG_CONFIG_FILE}; \ sed -i "s|LIB_VERSION|${EVENT_PARSE_VERSION}|g" ${PKG_CONFIG_FILE}; \ sed -i "s|LIB_DIR|${libdir}|g" ${PKG_CONFIG_FILE}; \ @@ -296,24 +229,20 @@ install_lib: all_cmd install_plugins install_headers install_pkgconfig $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIB_INSTALL) $(DESTDIR)$(libdir_SQ) -install_plugins: $(PLUGINS) - $(call QUIET_INSTALL, trace_plugins) \ - $(call do_install_plugins, $(PLUGINS)) - install_pkgconfig: $(call QUIET_INSTALL, $(PKG_CONFIG_FILE)) \ $(call do_install_pkgconfig_file,$(prefix)) install_headers: $(call QUIET_INSTALL, headers) \ - $(call do_install,event-parse.h,$(DESTDIR)$(includedir_SQ),644); \ - $(call do_install,event-utils.h,$(DESTDIR)$(includedir_SQ),644); \ - $(call do_install,trace-seq.h,$(DESTDIR)$(includedir_SQ),644); \ - $(call do_install,kbuffer.h,$(DESTDIR)$(includedir_SQ),644) + $(call do_install,event-parse.h,$(includedir_SQ),644); \ + $(call do_install,event-utils.h,$(includedir_SQ),644); \ + $(call do_install,trace-seq.h,$(includedir_SQ),644); \ + $(call do_install,kbuffer.h,$(includedir_SQ),644) install: install_lib -clean: +clean: clean_plugins $(call QUIET_CLEAN, libtraceevent) \ $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd; \ $(RM) TRACEEVENT-CFLAGS tags TAGS; \ @@ -351,7 +280,19 @@ help: @echo ' doc-install - install the man pages' @echo ' doc-uninstall - uninstall the man pages' @echo'' -PHONY += force plugins + +PHONY += plugins +plugins: + $(call descend,plugins) + +PHONY += install_plugins +install_plugins: + $(call descend,plugins,install) + +PHONY += clean_plugins +clean_plugins: + $(call descend,plugins,clean) + force: # Declare the contents of the .PHONY variable as phony. We keep that diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c index 988587840c80..4faf52a65791 100644 --- a/tools/lib/traceevent/event-parse-api.c +++ b/tools/lib/traceevent/event-parse-api.c @@ -303,33 +303,6 @@ void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian) } /** - * tep_is_latency_format - get if the latency output format is configured - * @tep: a handle to the tep_handle - * - * This returns true if the latency output format is configured - * If @tep is NULL, false is returned. - */ -bool tep_is_latency_format(struct tep_handle *tep) -{ - if (tep) - return (tep->latency_format); - return false; -} - -/** - * tep_set_latency_format - set the latency output format - * @tep: a handle to the tep_handle - * @lat: non zero for latency output format - * - * This sets the latency output format - */ -void tep_set_latency_format(struct tep_handle *tep, int lat) -{ - if (tep) - tep->latency_format = lat; -} - -/** * tep_is_old_format - get if an old kernel is used * @tep: a handle to the tep_handle * @@ -345,19 +318,6 @@ bool tep_is_old_format(struct tep_handle *tep) } /** - * tep_set_print_raw - set a flag to force print in raw format - * @tep: a handle to the tep_handle - * @print_raw: the new value of the print_raw flag - * - * This sets a flag to force print in raw format - */ -void tep_set_print_raw(struct tep_handle *tep, int print_raw) -{ - if (tep) - tep->print_raw = print_raw; -} - -/** * tep_set_test_filters - set a flag to test a filter string * @tep: a handle to the tep_handle * @test_filters: the new value of the test_filters flag diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h index 09aa142f7fdd..cee469803a34 100644 --- a/tools/lib/traceevent/event-parse-local.h +++ b/tools/lib/traceevent/event-parse-local.h @@ -28,8 +28,6 @@ struct tep_handle { enum tep_endian file_bigendian; enum tep_endian host_bigendian; - int latency_format; - int old_format; int cpus; @@ -70,8 +68,6 @@ struct tep_handle { int ld_offset; int ld_size; - int print_raw; - int test_filters; int flags; @@ -85,8 +81,6 @@ struct tep_handle { /* cache */ struct tep_event *last_event; - - char *trace_clock; }; void tep_free_event(struct tep_event *event); diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index b36b536a9fcb..beaa8b8c08ff 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -142,6 +142,25 @@ static int cmdline_cmp(const void *a, const void *b) return 0; } +/* Looking for where to place the key */ +static int cmdline_slot_cmp(const void *a, const void *b) +{ + const struct tep_cmdline *ca = a; + const struct tep_cmdline *cb = b; + const struct tep_cmdline *cb1 = cb + 1; + + if (ca->pid < cb->pid) + return -1; + + if (ca->pid > cb->pid) { + if (ca->pid <= cb1->pid) + return 0; + return 1; + } + + return 0; +} + struct cmdline_list { struct cmdline_list *next; char *comm; @@ -239,6 +258,7 @@ static int add_new_comm(struct tep_handle *tep, struct tep_cmdline *cmdline; struct tep_cmdline key; char *new_comm; + int cnt; if (!pid) return 0; @@ -269,21 +289,43 @@ static int add_new_comm(struct tep_handle *tep, errno = ENOMEM; return -1; } + tep->cmdlines = cmdlines; - cmdlines[tep->cmdline_count].comm = strdup(comm); - if (!cmdlines[tep->cmdline_count].comm) { - free(cmdlines); + key.comm = strdup(comm); + if (!key.comm) { errno = ENOMEM; return -1; } - cmdlines[tep->cmdline_count].pid = pid; - - if (cmdlines[tep->cmdline_count].comm) + if (!tep->cmdline_count) { + /* no entries yet */ + tep->cmdlines[0] = key; tep->cmdline_count++; + return 0; + } - qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp); - tep->cmdlines = cmdlines; + /* Now find where we want to store the new cmdline */ + cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count - 1, + sizeof(*tep->cmdlines), cmdline_slot_cmp); + + cnt = tep->cmdline_count; + if (cmdline) { + /* cmdline points to the one before the spot we want */ + cmdline++; + cnt -= cmdline - tep->cmdlines; + + } else { + /* The new entry is either before or after the list */ + if (key.pid > tep->cmdlines[tep->cmdline_count - 1].pid) { + tep->cmdlines[tep->cmdline_count++] = key; + return 0; + } + cmdline = &tep->cmdlines[0]; + } + memmove(cmdline + 1, cmdline, (cnt * sizeof(*cmdline))); + *cmdline = key; + + tep->cmdline_count++; return 0; } @@ -351,16 +393,6 @@ int tep_override_comm(struct tep_handle *tep, const char *comm, int pid) return _tep_register_comm(tep, comm, pid, true); } -int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock) -{ - tep->trace_clock = strdup(trace_clock); - if (!tep->trace_clock) { - errno = ENOMEM; - return -1; - } - return 0; -} - struct func_map { unsigned long long addr; char *func; @@ -4335,10 +4367,20 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s switch (*ptr) { case 's': case 'S': - case 'f': - case 'F': case 'x': break; + case 'f': + case 'F': + /* + * Pre-5.5 kernels use %pf and + * %pF for printing symbols + * while kernels since 5.5 use + * %pfw for fwnodes. So check + * %p[fF] isn't followed by 'w'. + */ + if (ptr[1] != 'w') + break; + /* fall through */ default: /* * Older kernels do not process @@ -4353,8 +4395,10 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s /* fall through */ case 'd': case 'u': - case 'x': case 'i': + case 'x': + case 'X': + case 'o': switch (ls) { case 0: vsize = 4; @@ -4455,12 +4499,12 @@ get_bprint_format(void *data, int size __maybe_unused, printk = find_printk(tep, addr); if (!printk) { - if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0) + if (asprintf(&format, "%%ps: (NO FORMAT FOUND at %llx)\n", addr) < 0) return NULL; return format; } - if (asprintf(&format, "%s: %s", "%pf", printk->printk) < 0) + if (asprintf(&format, "%s: %s", "%ps", printk->printk) < 0) return NULL; return format; @@ -5036,10 +5080,11 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e /* fall through */ case 'd': + case 'u': case 'i': case 'x': case 'X': - case 'u': + case 'o': if (!arg) { do_warning_event(event, "no argument match"); event->flags |= TEP_EVENT_FL_FAILED; @@ -5170,24 +5215,20 @@ out_failed: } } -/** - * tep_data_latency_format - parse the data for the latency format - * @tep: a handle to the trace event parser context - * @s: the trace_seq to write to - * @record: the record to read from - * +/* * This parses out the Latency format (interrupts disabled, * need rescheduling, in hard/soft interrupt, preempt count * and lock depth) and places it into the trace_seq. */ -void tep_data_latency_format(struct tep_handle *tep, - struct trace_seq *s, struct tep_record *record) +static void data_latency_format(struct tep_handle *tep, struct trace_seq *s, + char *format, struct tep_record *record) { static int check_lock_depth = 1; static int check_migrate_disable = 1; static int lock_depth_exists; static int migrate_disable_exists; unsigned int lat_flags; + struct trace_seq sq; unsigned int pc; int lock_depth = 0; int migrate_disable = 0; @@ -5195,6 +5236,7 @@ void tep_data_latency_format(struct tep_handle *tep, int softirq; void *data = record->data; + trace_seq_init(&sq); lat_flags = parse_common_flags(tep, data); pc = parse_common_pc(tep, data); /* lock_depth may not always exist */ @@ -5222,7 +5264,7 @@ void tep_data_latency_format(struct tep_handle *tep, hardirq = lat_flags & TRACE_FLAG_HARDIRQ; softirq = lat_flags & TRACE_FLAG_SOFTIRQ; - trace_seq_printf(s, "%c%c%c", + trace_seq_printf(&sq, "%c%c%c", (lat_flags & TRACE_FLAG_IRQS_OFF) ? 'd' : (lat_flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : '.', @@ -5232,24 +5274,32 @@ void tep_data_latency_format(struct tep_handle *tep, hardirq ? 'h' : softirq ? 's' : '.'); if (pc) - trace_seq_printf(s, "%x", pc); + trace_seq_printf(&sq, "%x", pc); else - trace_seq_putc(s, '.'); + trace_seq_printf(&sq, "."); if (migrate_disable_exists) { if (migrate_disable < 0) - trace_seq_putc(s, '.'); + trace_seq_printf(&sq, "."); else - trace_seq_printf(s, "%d", migrate_disable); + trace_seq_printf(&sq, "%d", migrate_disable); } if (lock_depth_exists) { if (lock_depth < 0) - trace_seq_putc(s, '.'); + trace_seq_printf(&sq, "."); else - trace_seq_printf(s, "%d", lock_depth); + trace_seq_printf(&sq, "%d", lock_depth); + } + + if (sq.state == TRACE_SEQ__MEM_ALLOC_FAILED) { + s->state = TRACE_SEQ__MEM_ALLOC_FAILED; + return; } + trace_seq_terminate(&sq); + trace_seq_puts(s, sq.buffer); + trace_seq_destroy(&sq); trace_seq_terminate(s); } @@ -5410,21 +5460,16 @@ int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline) return cmdline->pid; } -/** - * tep_event_info - parse the data into the print format - * @s: the trace_seq to write to - * @event: the handle to the event - * @record: the record to read from - * +/* * This parses the raw @data using the given @event information and * writes the print format into the trace_seq. */ -void tep_event_info(struct trace_seq *s, struct tep_event *event, - struct tep_record *record) +static void print_event_info(struct trace_seq *s, char *format, bool raw, + struct tep_event *event, struct tep_record *record) { int print_pretty = 1; - if (event->tep->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW)) + if (raw || (event->flags & TEP_EVENT_FL_PRINTRAW)) tep_print_fields(s, record->data, record->size, event); else { @@ -5439,20 +5484,6 @@ void tep_event_info(struct trace_seq *s, struct tep_event *event, trace_seq_terminate(s); } -static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock) -{ - if (!trace_clock || !use_trace_clock) - return true; - - if (!strcmp(trace_clock, "local") || !strcmp(trace_clock, "global") - || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf") - || !strncmp(trace_clock, "mono", 4)) - return true; - - /* trace_clock is setting in tsc or counter mode */ - return false; -} - /** * tep_find_event_by_record - return the event from a given record * @tep: a handle to the trace event parser context @@ -5476,129 +5507,197 @@ tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record) return tep_find_event(tep, type); } -/** - * tep_print_event_task - Write the event task comm, pid and CPU - * @tep: a handle to the trace event parser context - * @s: the trace_seq to write to - * @event: the handle to the record's event - * @record: The record to get the event from - * - * Writes the tasks comm, pid and CPU to @s. +/* + * Writes the timestamp of the record into @s. Time divisor and precision can be + * specified as part of printf @format string. Example: + * "%3.1000d" - divide the time by 1000 and print the first 3 digits + * before the dot. Thus, the timestamp "123456000" will be printed as + * "123.456" */ -void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s, - struct tep_event *event, - struct tep_record *record) +static void print_event_time(struct tep_handle *tep, struct trace_seq *s, + char *format, struct tep_event *event, + struct tep_record *record) +{ + unsigned long long time; + char *divstr; + int prec = 0, pr; + int div = 0; + int p10 = 1; + + if (isdigit(*(format + 1))) + prec = atoi(format + 1); + divstr = strchr(format, '.'); + if (divstr && isdigit(*(divstr + 1))) + div = atoi(divstr + 1); + time = record->ts; + if (div) { + time += div / 2; + time /= div; + } + pr = prec; + while (pr--) + p10 *= 10; + + if (p10 > 1 && p10 < time) + trace_seq_printf(s, "%5llu.%0*llu", time / p10, prec, time % p10); + else + trace_seq_printf(s, "%12llu\n", time); +} + +struct print_event_type { + enum { + EVENT_TYPE_INT = 1, + EVENT_TYPE_STRING, + EVENT_TYPE_UNKNOWN, + } type; + char format[32]; +}; + +static void print_string(struct tep_handle *tep, struct trace_seq *s, + struct tep_record *record, struct tep_event *event, + const char *arg, struct print_event_type *type) { - void *data = record->data; const char *comm; int pid; - pid = parse_common_pid(tep, data); - comm = find_cmdline(tep, pid); + if (strncmp(arg, TEP_PRINT_LATENCY, strlen(TEP_PRINT_LATENCY)) == 0) { + data_latency_format(tep, s, type->format, record); + } else if (strncmp(arg, TEP_PRINT_COMM, strlen(TEP_PRINT_COMM)) == 0) { + pid = parse_common_pid(tep, record->data); + comm = find_cmdline(tep, pid); + trace_seq_printf(s, type->format, comm); + } else if (strncmp(arg, TEP_PRINT_INFO_RAW, strlen(TEP_PRINT_INFO_RAW)) == 0) { + print_event_info(s, type->format, true, event, record); + } else if (strncmp(arg, TEP_PRINT_INFO, strlen(TEP_PRINT_INFO)) == 0) { + print_event_info(s, type->format, false, event, record); + } else if (strncmp(arg, TEP_PRINT_NAME, strlen(TEP_PRINT_NAME)) == 0) { + trace_seq_printf(s, type->format, event->name); + } else { + trace_seq_printf(s, "[UNKNOWN TEP TYPE %s]", arg); + } - if (tep->latency_format) - trace_seq_printf(s, "%8.8s-%-5d %3d", comm, pid, record->cpu); - else - trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu); } -/** - * tep_print_event_time - Write the event timestamp - * @tep: a handle to the trace event parser context - * @s: the trace_seq to write to - * @event: the handle to the record's event - * @record: The record to get the event from - * @use_trace_clock: Set to parse according to the @tep->trace_clock - * - * Writes the timestamp of the record into @s. - */ -void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s, - struct tep_event *event, - struct tep_record *record, - bool use_trace_clock) +static void print_int(struct tep_handle *tep, struct trace_seq *s, + struct tep_record *record, struct tep_event *event, + int arg, struct print_event_type *type) { - unsigned long secs; - unsigned long usecs; - unsigned long nsecs; - int p; - bool use_usec_format; + int param; - use_usec_format = is_timestamp_in_us(tep->trace_clock, use_trace_clock); - if (use_usec_format) { - secs = record->ts / NSEC_PER_SEC; - nsecs = record->ts - secs * NSEC_PER_SEC; + switch (arg) { + case TEP_PRINT_CPU: + param = record->cpu; + break; + case TEP_PRINT_PID: + param = parse_common_pid(tep, record->data); + break; + case TEP_PRINT_TIME: + return print_event_time(tep, s, type->format, event, record); + default: + return; } + trace_seq_printf(s, type->format, param); +} - if (tep->latency_format) { - tep_data_latency_format(tep, s, record); - } +static int tep_print_event_param_type(char *format, + struct print_event_type *type) +{ + char *str = format + 1; + int i = 1; - if (use_usec_format) { - if (tep->flags & TEP_NSEC_OUTPUT) { - usecs = nsecs; - p = 9; - } else { - usecs = (nsecs + 500) / NSEC_PER_USEC; - /* To avoid usecs larger than 1 sec */ - if (usecs >= USEC_PER_SEC) { - usecs -= USEC_PER_SEC; - secs++; - } - p = 6; + type->type = EVENT_TYPE_UNKNOWN; + while (*str) { + switch (*str) { + case 'd': + case 'u': + case 'i': + case 'x': + case 'X': + case 'o': + type->type = EVENT_TYPE_INT; + break; + case 's': + type->type = EVENT_TYPE_STRING; + break; } - - trace_seq_printf(s, " %5lu.%0*lu:", secs, p, usecs); - } else - trace_seq_printf(s, " %12llu:", record->ts); + str++; + i++; + if (type->type != EVENT_TYPE_UNKNOWN) + break; + } + memset(type->format, 0, 32); + memcpy(type->format, format, i < 32 ? i : 31); + return i; } /** - * tep_print_event_data - Write the event data section + * tep_print_event - Write various event information * @tep: a handle to the trace event parser context * @s: the trace_seq to write to - * @event: the handle to the record's event * @record: The record to get the event from - * - * Writes the parsing of the record's data to @s. + * @format: a printf format string. Supported event fileds: + * TEP_PRINT_PID, "%d" - event PID + * TEP_PRINT_CPU, "%d" - event CPU + * TEP_PRINT_COMM, "%s" - event command string + * TEP_PRINT_NAME, "%s" - event name + * TEP_PRINT_LATENCY, "%s" - event latency + * TEP_PRINT_TIME, %d - event time stamp. A divisor and precision + * can be specified as part of this format string: + * "%precision.divisord". Example: + * "%3.1000d" - divide the time by 1000 and print the first + * 3 digits before the dot. Thus, the time stamp + * "123456000" will be printed as "123.456" + * TEP_PRINT_INFO, "%s" - event information. If any width is specified in + * the format string, the event information will be printed + * in raw format. + * Writes the specified event information into @s. */ -void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s, - struct tep_event *event, - struct tep_record *record) -{ - static const char *spaces = " "; /* 20 spaces */ - int len; - - trace_seq_printf(s, " %s: ", event->name); - - /* Space out the event names evenly. */ - len = strlen(event->name); - if (len < 20) - trace_seq_printf(s, "%.*s", 20 - len, spaces); - - tep_event_info(s, event, record); -} - void tep_print_event(struct tep_handle *tep, struct trace_seq *s, - struct tep_record *record, bool use_trace_clock) -{ + struct tep_record *record, const char *fmt, ...) +{ + struct print_event_type type; + char *format = strdup(fmt); + char *current = format; + char *str = format; + int offset; + va_list args; struct tep_event *event; - event = tep_find_event_by_record(tep, record); - if (!event) { - int i; - int type = trace_parse_common_type(tep, record->data); - - do_warning("ug! no event found for type %d", type); - trace_seq_printf(s, "[UNKNOWN TYPE %d]", type); - for (i = 0; i < record->size; i++) - trace_seq_printf(s, " %02x", - ((unsigned char *)record->data)[i]); + if (!format) return; - } - tep_print_event_task(tep, s, event, record); - tep_print_event_time(tep, s, event, record, use_trace_clock); - tep_print_event_data(tep, s, event, record); + event = tep_find_event_by_record(tep, record); + va_start(args, fmt); + while (*current) { + current = strchr(str, '%'); + if (!current) { + trace_seq_puts(s, str); + break; + } + memset(&type, 0, sizeof(type)); + offset = tep_print_event_param_type(current, &type); + *current = '\0'; + trace_seq_puts(s, str); + current += offset; + switch (type.type) { + case EVENT_TYPE_STRING: + print_string(tep, s, record, event, + va_arg(args, char*), &type); + break; + case EVENT_TYPE_INT: + print_int(tep, s, record, event, + va_arg(args, int), &type); + break; + case EVENT_TYPE_UNKNOWN: + default: + trace_seq_printf(s, "[UNKNOWN TYPE]"); + break; + } + str = current; + + } + va_end(args); + free(format); } static int events_id_cmp(const void *a, const void *b) @@ -6963,7 +7062,6 @@ void tep_free(struct tep_handle *tep) free_handler(handle); } - free(tep->trace_clock); free(tep->events); free(tep->sort_events); free(tep->func_resolver); diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 642f68ab5fb2..b77837f75a0d 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -435,25 +435,26 @@ int tep_set_function_resolver(struct tep_handle *tep, void tep_reset_function_resolver(struct tep_handle *tep); int tep_register_comm(struct tep_handle *tep, const char *comm, int pid); int tep_override_comm(struct tep_handle *tep, const char *comm, int pid); -int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock); int tep_register_function(struct tep_handle *tep, char *name, unsigned long long addr, char *mod); int tep_register_print_string(struct tep_handle *tep, const char *fmt, unsigned long long addr); bool tep_is_pid_registered(struct tep_handle *tep, int pid); -void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s, - struct tep_event *event, - struct tep_record *record); -void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s, - struct tep_event *event, - struct tep_record *record, - bool use_trace_clock); -void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s, - struct tep_event *event, - struct tep_record *record); +struct tep_event *tep_get_event(struct tep_handle *tep, int index); + +#define TEP_PRINT_INFO "INFO" +#define TEP_PRINT_INFO_RAW "INFO_RAW" +#define TEP_PRINT_COMM "COMM" +#define TEP_PRINT_LATENCY "LATENCY" +#define TEP_PRINT_NAME "NAME" +#define TEP_PRINT_PID 1U +#define TEP_PRINT_TIME 2U +#define TEP_PRINT_CPU 3U + void tep_print_event(struct tep_handle *tep, struct trace_seq *s, - struct tep_record *record, bool use_trace_clock); + struct tep_record *record, const char *fmt, ...) + __attribute__ ((format (printf, 4, 5))); int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size, int long_size); @@ -525,8 +526,6 @@ tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name struct tep_event * tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record); -void tep_data_latency_format(struct tep_handle *tep, - struct trace_seq *s, struct tep_record *record); int tep_data_type(struct tep_handle *tep, struct tep_record *rec); int tep_data_pid(struct tep_handle *tep, struct tep_record *rec); int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec); @@ -541,8 +540,6 @@ void tep_print_field(struct trace_seq *s, void *data, struct tep_format_field *field); void tep_print_fields(struct trace_seq *s, void *data, int size __maybe_unused, struct tep_event *event); -void tep_event_info(struct trace_seq *s, struct tep_event *event, - struct tep_record *record); int tep_strerror(struct tep_handle *tep, enum tep_errno errnum, char *buf, size_t buflen); @@ -566,12 +563,9 @@ bool tep_is_file_bigendian(struct tep_handle *tep); void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian); bool tep_is_local_bigendian(struct tep_handle *tep); void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian); -bool tep_is_latency_format(struct tep_handle *tep); -void tep_set_latency_format(struct tep_handle *tep, int lat); int tep_get_header_page_size(struct tep_handle *tep); int tep_get_header_timestamp_size(struct tep_handle *tep); bool tep_is_old_format(struct tep_handle *tep); -void tep_set_print_raw(struct tep_handle *tep, int print_raw); void tep_set_test_filters(struct tep_handle *tep, int test_filters); struct tep_handle *tep_alloc(void); diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c index 8ca28de9337a..e1f7ddd5a6cf 100644 --- a/tools/lib/traceevent/event-plugin.c +++ b/tools/lib/traceevent/event-plugin.c @@ -18,7 +18,7 @@ #include "event-utils.h" #include "trace-seq.h" -#define LOCAL_PLUGIN_DIR ".traceevent/plugins" +#define LOCAL_PLUGIN_DIR ".local/lib/traceevent/plugins/" static struct registered_plugin_options { struct registered_plugin_options *next; diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c index 552592d153fb..20eed719542e 100644 --- a/tools/lib/traceevent/parse-filter.c +++ b/tools/lib/traceevent/parse-filter.c @@ -1228,8 +1228,10 @@ filter_event(struct tep_event_filter *filter, struct tep_event *event, } filter_type = add_filter_type(filter, event->id); - if (filter_type == NULL) + if (filter_type == NULL) { + free_arg(arg); return TEP_ERRNO__MEM_ALLOC_FAILED; + } if (filter_type->filter) free_arg(filter_type->filter); @@ -1473,8 +1475,10 @@ static int copy_filter_type(struct tep_event_filter *filter, if (strcmp(str, "TRUE") == 0 || strcmp(str, "FALSE") == 0) { /* Add trivial event */ arg = allocate_arg(); - if (arg == NULL) + if (arg == NULL) { + free(str); return -1; + } arg->type = TEP_FILTER_ARG_BOOLEAN; if (strcmp(str, "TRUE") == 0) @@ -1483,8 +1487,11 @@ static int copy_filter_type(struct tep_event_filter *filter, arg->boolean.value = 0; filter_type = add_filter_type(filter, event->id); - if (filter_type == NULL) + if (filter_type == NULL) { + free(str); + free_arg(arg); return -1; + } filter_type->filter = arg; diff --git a/tools/lib/traceevent/plugins/Build b/tools/lib/traceevent/plugins/Build new file mode 100644 index 000000000000..210d26910613 --- /dev/null +++ b/tools/lib/traceevent/plugins/Build @@ -0,0 +1,10 @@ +plugin_jbd2-y += plugin_jbd2.o +plugin_hrtimer-y += plugin_hrtimer.o +plugin_kmem-y += plugin_kmem.o +plugin_kvm-y += plugin_kvm.o +plugin_mac80211-y += plugin_mac80211.o +plugin_sched_switch-y += plugin_sched_switch.o +plugin_function-y += plugin_function.o +plugin_xen-y += plugin_xen.o +plugin_scsi-y += plugin_scsi.o +plugin_cfg80211-y += plugin_cfg80211.o diff --git a/tools/lib/traceevent/plugins/Makefile b/tools/lib/traceevent/plugins/Makefile new file mode 100644 index 000000000000..349bb81482ab --- /dev/null +++ b/tools/lib/traceevent/plugins/Makefile @@ -0,0 +1,223 @@ +# SPDX-License-Identifier: GPL-2.0 + +#MAKEFLAGS += --no-print-directory + + +# Makefiles suck: This macro sets a default value of $(2) for the +# variable named by $(1), unless the variable has been set by +# environment or command line. This is necessary for CC and AR +# because make sets default values, so the simpler ?= approach +# won't work as expected. +define allow-override + $(if $(or $(findstring environment,$(origin $(1))),\ + $(findstring command line,$(origin $(1)))),,\ + $(eval $(1) = $(2))) +endef + +# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix. +$(call allow-override,CC,$(CROSS_COMPILE)gcc) +$(call allow-override,AR,$(CROSS_COMPILE)ar) +$(call allow-override,NM,$(CROSS_COMPILE)nm) +$(call allow-override,PKG_CONFIG,pkg-config) + +EXT = -std=gnu99 +INSTALL = install + +# Use DESTDIR for installing into a different root directory. +# This is useful for building a package. The program will be +# installed in this directory as if it was the root directory. +# Then the build tool can move it later. +DESTDIR ?= +DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))' + +LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) +ifeq ($(LP64), 1) + libdir_relative_tmp = lib64 +else + libdir_relative_tmp = lib +endif + +libdir_relative ?= $(libdir_relative_tmp) +prefix ?= /usr/local +libdir = $(prefix)/$(libdir_relative) + +set_plugin_dir := 1 + +# Set plugin_dir to preffered global plugin location +# If we install under $HOME directory we go under +# $(HOME)/.local/lib/traceevent/plugins +# +# We dont set PLUGIN_DIR in case we install under $HOME +# directory, because by default the code looks under: +# $(HOME)/.local/lib/traceevent/plugins by default. +# +ifeq ($(plugin_dir),) +ifeq ($(prefix),$(HOME)) +override plugin_dir = $(HOME)/.local/lib/traceevent/plugins +set_plugin_dir := 0 +else +override plugin_dir = $(libdir)/traceevent/plugins +endif +endif + +ifeq ($(set_plugin_dir),1) +PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)" +PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))' +endif + +include ../../../scripts/Makefile.include + +# copy a bit from Linux kbuild + +ifeq ("$(origin V)", "command line") + VERBOSE = $(V) +endif +ifndef VERBOSE + VERBOSE = 0 +endif + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(CURDIR))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +export prefix libdir src obj + +# Shell quotes +plugin_dir_SQ = $(subst ','\'',$(plugin_dir)) + +CONFIG_INCLUDES = +CONFIG_LIBS = +CONFIG_FLAGS = + +OBJ = $@ +N = + +INCLUDES = -I. -I.. -I $(srctree)/tools/include $(CONFIG_INCLUDES) + +# Set compile option CFLAGS +ifdef EXTRA_CFLAGS + CFLAGS := $(EXTRA_CFLAGS) +else + CFLAGS := -g -Wall +endif + +# Append required CFLAGS +override CFLAGS += -fPIC +override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ) +override CFLAGS += $(udis86-flags) -D_GNU_SOURCE + +ifeq ($(VERBOSE),1) + Q = +else + Q = @ +endif + +# Disable command line variables (CFLAGS) override from top +# level Makefile (perf), otherwise build Makefile will get +# the same command line setup. +MAKEOVERRIDES= + +export srctree OUTPUT CC LD CFLAGS V + +build := -f $(srctree)/tools/build/Makefile.build dir=. obj + +DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list + +PLUGINS = plugin_jbd2.so +PLUGINS += plugin_hrtimer.so +PLUGINS += plugin_kmem.so +PLUGINS += plugin_kvm.so +PLUGINS += plugin_mac80211.so +PLUGINS += plugin_sched_switch.so +PLUGINS += plugin_function.so +PLUGINS += plugin_xen.so +PLUGINS += plugin_scsi.so +PLUGINS += plugin_cfg80211.so + +PLUGINS := $(addprefix $(OUTPUT),$(PLUGINS)) +PLUGINS_IN := $(PLUGINS:.so=-in.o) + +plugins: $(PLUGINS) $(DYNAMIC_LIST_FILE) + +__plugin_obj = $(notdir $@) + plugin_obj = $(__plugin_obj:-in.o=) + +$(PLUGINS_IN): force + $(Q)$(MAKE) $(build)=$(plugin_obj) + +$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS) + $(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@) + +$(OUTPUT)%.so: $(OUTPUT)%-in.o + $(QUIET_LINK)$(CC) $(CFLAGS) -shared $(LDFLAGS) -nostartfiles -o $@ $^ + +define update_dir + (echo $1 > $@.tmp; \ + if [ -r $@ ] && cmp -s $@ $@.tmp; then \ + rm -f $@.tmp; \ + else \ + echo ' UPDATE $@'; \ + mv -f $@.tmp $@; \ + fi); +endef + +tags: force + $(RM) tags + find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \ + --regex-c++='/_PE\(([^,)]*).*/TEP_ERRNO__\1/' + +TAGS: force + $(RM) TAGS + find . -name '*.[ch]' | xargs etags \ + --regex='/_PE(\([^,)]*\).*/TEP_ERRNO__\1/' + +define do_install_mkdir + if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ + fi +endef + +define do_install + $(call do_install_mkdir,$2); \ + $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2' +endef + +define do_install_plugins + for plugin in $1; do \ + $(call do_install,$$plugin,$(plugin_dir_SQ)); \ + done +endef + +define do_generate_dynamic_list_file + symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \ + xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\ + if [ "$$symbol_type" = "U W" ];then \ + (echo '{'; \ + $(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\ + echo '};'; \ + ) > $2; \ + else \ + (echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\ + fi +endef + +install: $(PLUGINS) + $(call QUIET_INSTALL, trace_plugins) \ + $(call do_install_plugins, $(PLUGINS)) + +clean: + $(call QUIET_CLEAN, trace_plugins) \ + $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd; \ + $(RM) $(OUTPUT)libtraceevent-dynamic-list \ + $(RM) TRACEEVENT-CFLAGS tags TAGS; + +PHONY += force plugins +force: + +# 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) diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugins/plugin_cfg80211.c index 3d43b56a6c98..3d43b56a6c98 100644 --- a/tools/lib/traceevent/plugin_cfg80211.c +++ b/tools/lib/traceevent/plugins/plugin_cfg80211.c diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugins/plugin_function.c index 7770fcb78e0f..7770fcb78e0f 100644 --- a/tools/lib/traceevent/plugin_function.c +++ b/tools/lib/traceevent/plugins/plugin_function.c diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugins/plugin_hrtimer.c index bb434e0ed03a..bb434e0ed03a 100644 --- a/tools/lib/traceevent/plugin_hrtimer.c +++ b/tools/lib/traceevent/plugins/plugin_hrtimer.c diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugins/plugin_jbd2.c index 04fc125f38cb..04fc125f38cb 100644 --- a/tools/lib/traceevent/plugin_jbd2.c +++ b/tools/lib/traceevent/plugins/plugin_jbd2.c diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugins/plugin_kmem.c index edaec5d962c3..edaec5d962c3 100644 --- a/tools/lib/traceevent/plugin_kmem.c +++ b/tools/lib/traceevent/plugins/plugin_kmem.c diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugins/plugin_kvm.c index c8e623065a7e..c8e623065a7e 100644 --- a/tools/lib/traceevent/plugin_kvm.c +++ b/tools/lib/traceevent/plugins/plugin_kvm.c diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugins/plugin_mac80211.c index 884303c26b5c..884303c26b5c 100644 --- a/tools/lib/traceevent/plugin_mac80211.c +++ b/tools/lib/traceevent/plugins/plugin_mac80211.c diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugins/plugin_sched_switch.c index 957389a0ff7a..957389a0ff7a 100644 --- a/tools/lib/traceevent/plugin_sched_switch.c +++ b/tools/lib/traceevent/plugins/plugin_sched_switch.c diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugins/plugin_scsi.c index 5d0387a4b65a..5d0387a4b65a 100644 --- a/tools/lib/traceevent/plugin_scsi.c +++ b/tools/lib/traceevent/plugins/plugin_scsi.c diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugins/plugin_xen.c index 993b208d0323..993b208d0323 100644 --- a/tools/lib/traceevent/plugin_xen.c +++ b/tools/lib/traceevent/plugins/plugin_xen.c |
